From fba7b940194465ac7a8f0cdf793959fb5fbb8834 Mon Sep 17 00:00:00 2001 From: David Teigland Date: Mon, 16 Jan 2006 11:48:01 +0000 Subject: [PATCH] Add fs_subsys to enable filesystems to use sysfs This creates an "fs" subdirectory in sysfs so that GFS2 (or any other filesystem, come to that) can make use of sysfs. Signed-off-by: David Teigland Signed-off-by: Steven Whitehouse --- include/linux/fs.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 552cedfa6064..eabc80d22bbc 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1293,6 +1293,9 @@ extern int vfs_statfs(struct super_block *, struct kstatfs *); #define FLOCK_VERIFY_READ 1 #define FLOCK_VERIFY_WRITE 2 +/* /sys/fs */ +extern struct subsystem fs_subsys; + extern int locks_mandatory_locked(struct inode *); extern int locks_mandatory_area(int, struct inode *, struct file *, loff_t, size_t); -- cgit v1.2.3 From b3b94faa5fe5968827ba0640ee9fba4b3e7f736e Mon Sep 17 00:00:00 2001 From: David Teigland Date: Mon, 16 Jan 2006 16:50:04 +0000 Subject: [GFS2] The core of GFS2 This patch contains all the core files for GFS2. Signed-off-by: David Teigland Signed-off-by: Steven Whitehouse --- include/linux/gfs2_ioctl.h | 32 ++++ include/linux/gfs2_ondisk.h | 454 ++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 486 insertions(+) create mode 100644 include/linux/gfs2_ioctl.h create mode 100644 include/linux/gfs2_ondisk.h (limited to 'include/linux') diff --git a/include/linux/gfs2_ioctl.h b/include/linux/gfs2_ioctl.h new file mode 100644 index 000000000000..dde9840b1c30 --- /dev/null +++ b/include/linux/gfs2_ioctl.h @@ -0,0 +1,32 @@ +/* + * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. + * Copyright (C) 2004-2005 Red Hat, Inc. All rights reserved. + * + * This copyrighted material is made available to anyone wishing to use, + * modify, copy, or redistribute it subject to the terms and conditions + * of the GNU General Public License v.2. + */ + +#ifndef __GFS2_IOCTL_DOT_H__ +#define __GFS2_IOCTL_DOT_H__ + +#define _GFS2C_(x) (('G' << 16) | ('2' << 8) | (x)) + +/* Ioctls implemented */ + +#define GFS2_IOCTL_IDENTIFY _GFS2C_(1) +#define GFS2_IOCTL_SUPER _GFS2C_(2) +#define GFS2_IOCTL_SETFLAGS _GFS2C_(3) +#define GFS2_IOCTL_GETFLAGS _GFS2C_(4) + +struct gfs2_ioctl { + unsigned int gi_argc; + const char **gi_argv; + + char __user *gi_data; + unsigned int gi_size; + uint64_t gi_offset; +}; + +#endif /* ___GFS2_IOCTL_DOT_H__ */ + diff --git a/include/linux/gfs2_ondisk.h b/include/linux/gfs2_ondisk.h new file mode 100644 index 000000000000..213d664d495d --- /dev/null +++ b/include/linux/gfs2_ondisk.h @@ -0,0 +1,454 @@ +/* + * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. + * Copyright (C) 2004-2005 Red Hat, Inc. All rights reserved. + * + * This copyrighted material is made available to anyone wishing to use, + * modify, copy, or redistribute it subject to the terms and conditions + * of the GNU General Public License v.2. + */ + +#ifndef __GFS2_ONDISK_DOT_H__ +#define __GFS2_ONDISK_DOT_H__ + +#define GFS2_MAGIC 0x01161970 +#define GFS2_BASIC_BLOCK 512 +#define GFS2_BASIC_BLOCK_SHIFT 9 + +/* Lock numbers of the LM_TYPE_NONDISK type */ + +#define GFS2_MOUNT_LOCK 0 +#define GFS2_LIVE_LOCK 1 +#define GFS2_TRANS_LOCK 2 +#define GFS2_RENAME_LOCK 3 + +/* Format numbers for various metadata types */ + +#define GFS2_FORMAT_NONE 0 +#define GFS2_FORMAT_SB 100 +#define GFS2_FORMAT_RG 200 +#define GFS2_FORMAT_RB 300 +#define GFS2_FORMAT_DI 400 +#define GFS2_FORMAT_IN 500 +#define GFS2_FORMAT_LF 600 +#define GFS2_FORMAT_JD 700 +#define GFS2_FORMAT_LH 800 +#define GFS2_FORMAT_LD 900 +#define GFS2_FORMAT_LB 1000 +#define GFS2_FORMAT_EA 1100 +#define GFS2_FORMAT_ED 1200 +#define GFS2_FORMAT_UT 1300 +#define GFS2_FORMAT_QC 1400 +/* These are format numbers for entities contained in files */ +#define GFS2_FORMAT_RI 1500 +#define GFS2_FORMAT_DE 1600 +#define GFS2_FORMAT_QU 1700 +/* These are part of the superblock */ +#define GFS2_FORMAT_FS 1801 +#define GFS2_FORMAT_MULTI 1900 + +/* + * An on-disk inode number + */ + +#define gfs2_inum_equal(ino1, ino2) \ + (((ino1)->no_formal_ino == (ino2)->no_formal_ino) && \ + ((ino1)->no_addr == (ino2)->no_addr)) + +struct gfs2_inum { + __be64 no_formal_ino; + __be64 no_addr; +}; + +/* + * Generic metadata head structure + * Every inplace buffer logged in the journal must start with this. + */ + +#define GFS2_METATYPE_NONE 0 +#define GFS2_METATYPE_SB 1 +#define GFS2_METATYPE_RG 2 +#define GFS2_METATYPE_RB 3 +#define GFS2_METATYPE_DI 4 +#define GFS2_METATYPE_IN 5 +#define GFS2_METATYPE_LF 6 +#define GFS2_METATYPE_JD 7 +#define GFS2_METATYPE_LH 8 +#define GFS2_METATYPE_LD 9 +#define GFS2_METATYPE_LB 10 +#define GFS2_METATYPE_EA 11 +#define GFS2_METATYPE_ED 12 +#define GFS2_METATYPE_UT 13 +#define GFS2_METATYPE_QC 14 + +struct gfs2_meta_header { + __be32 mh_magic; + __be32 mh_type; + __be64 __pad0; /* Was generation number in gfs1 */ + __be32 mh_format; + __be32 __pad1; /* Was incarnation number in gfs1 */ +}; + +/* + * super-block structure + * + * It's probably good if SIZEOF_SB <= GFS2_BASIC_BLOCK (512 bytes) + * + * Order is important, need to be able to read old superblocks to do on-disk + * version upgrades. + */ + +/* Address of superblock in GFS2 basic blocks */ +#define GFS2_SB_ADDR 128 + +/* The lock number for the superblock (must be zero) */ +#define GFS2_SB_LOCK 0 + +/* Requirement: GFS2_LOCKNAME_LEN % 8 == 0 + Includes: the fencing zero at the end */ +#define GFS2_LOCKNAME_LEN 64 + +struct gfs2_sb { + struct gfs2_meta_header sb_header; + + __be32 sb_fs_format; + __be32 sb_multihost_format; + __u32 __pad0; /* Was superblock flags in gfs1 */ + + __be32 sb_bsize; + __be32 sb_bsize_shift; + __u32 __pad1; /* Was journal segment size in gfs1 */ + + struct gfs2_inum sb_master_dir; /* Was jindex dinode in gfs1 */ + struct gfs2_inum __pad2; /* Was rindex dinode in gfs1 */ + struct gfs2_inum sb_root_dir; + + char sb_lockproto[GFS2_LOCKNAME_LEN]; + char sb_locktable[GFS2_LOCKNAME_LEN]; + /* In gfs1, quota and license dinodes followed */ +}; + +/* + * resource index structure + */ + +struct gfs2_rindex { + __be64 ri_addr; /* grp block disk address */ + __be32 ri_length; /* length of rgrp header in fs blocks */ + __u32 __pad; + + __be64 ri_data0; /* first data location */ + __be32 ri_data; /* num of data blocks in rgrp */ + + __be32 ri_bitbytes; /* number of bytes in data bitmaps */ + + __u8 ri_reserved[64]; +}; + +/* + * resource group header structure + */ + +/* Number of blocks per byte in rgrp */ +#define GFS2_NBBY 4 +#define GFS2_BIT_SIZE 2 +#define GFS2_BIT_MASK 0x00000003 + +#define GFS2_BLKST_FREE 0 +#define GFS2_BLKST_USED 1 +#define GFS2_BLKST_INVALID 2 +#define GFS2_BLKST_DINODE 3 + +#define GFS2_RGF_JOURNAL 0x00000001 +#define GFS2_RGF_METAONLY 0x00000002 +#define GFS2_RGF_DATAONLY 0x00000004 +#define GFS2_RGF_NOALLOC 0x00000008 + +struct gfs2_rgrp { + struct gfs2_meta_header rg_header; + + __be32 rg_flags; + __be32 rg_free; + __be32 rg_dinodes; + + __u8 rg_reserved[92]; /* Several fields from gfs1 now reserved */ +}; + +/* + * quota structure + */ + +struct gfs2_quota { + __be64 qu_limit; + __be64 qu_warn; + __be64 qu_value; +}; + +/* + * dinode structure + */ + +#define GFS2_MAX_META_HEIGHT 10 +#define GFS2_DIR_MAX_DEPTH 17 + +#define DT2IF(dt) (((dt) << 12) & S_IFMT) +#define IF2DT(sif) (((sif) & S_IFMT) >> 12) + +/* Dinode flags */ +#define GFS2_DIF_JDATA 0x00000001 +#define GFS2_DIF_EXHASH 0x00000002 +#define GFS2_DIF_UNUSED 0x00000004 /* only in gfs1 */ +#define GFS2_DIF_EA_INDIRECT 0x00000008 +#define GFS2_DIF_DIRECTIO 0x00000010 +#define GFS2_DIF_IMMUTABLE 0x00000020 +#define GFS2_DIF_APPENDONLY 0x00000040 +#define GFS2_DIF_NOATIME 0x00000080 +#define GFS2_DIF_SYNC 0x00000100 +#define GFS2_DIF_SYSTEM 0x00000200 /* New in gfs2 */ +#define GFS2_DIF_TRUNC_IN_PROG 0x20000000 /* New in gfs2 */ +#define GFS2_DIF_INHERIT_DIRECTIO 0x40000000 +#define GFS2_DIF_INHERIT_JDATA 0x80000000 + +struct gfs2_dinode { + struct gfs2_meta_header di_header; + + struct gfs2_inum di_num; + + __be32 di_mode; /* mode of file */ + __be32 di_uid; /* owner's user id */ + __be32 di_gid; /* owner's group id */ + __be32 di_nlink; /* number of links to this file */ + __be64 di_size; /* number of bytes in file */ + __be64 di_blocks; /* number of blocks in file */ + __be64 di_atime; /* time last accessed */ + __be64 di_mtime; /* time last modified */ + __be64 di_ctime; /* time last changed */ + __be32 di_major; /* device major number */ + __be32 di_minor; /* device minor number */ + + /* This section varies from gfs1. Padding added to align with + * remainder of dinode + */ + __be64 di_goal_meta; /* rgrp to alloc from next */ + __be64 di_goal_data; /* data block goal */ + __u32 __pad[2]; + + __be32 di_flags; /* GFS2_DIF_... */ + __be32 di_payload_format; /* GFS2_FORMAT_... */ + __u16 __pad1; /* Was ditype in gfs1 */ + __be16 di_height; /* height of metadata */ + __u32 __pad2; /* Unused incarnation number from gfs1 */ + + /* These only apply to directories */ + __u16 __pad3; /* Padding */ + __be16 di_depth; /* Number of bits in the table */ + __be32 di_entries; /* The number of entries in the directory */ + + struct gfs2_inum __pad4; /* Unused even in current gfs1 */ + + __be64 di_eattr; /* extended attribute block number */ + + __u8 di_reserved[56]; +}; + +/* + * directory structure - many of these per directory file + */ + +#define GFS2_FNAMESIZE 255 +#define GFS2_DIRENT_SIZE(name_len) ((sizeof(struct gfs2_dirent) + (name_len) + 7) & ~7) + +struct gfs2_dirent { + struct gfs2_inum de_inum; + __be32 de_hash; + __be32 de_rec_len; + __u8 de_name_len; + __u8 de_type; + __u16 __pad1; + __u32 __pad2; +}; + +/* + * Header of leaf directory nodes + */ + +struct gfs2_leaf { + struct gfs2_meta_header lf_header; + + __be16 lf_depth; /* Depth of leaf */ + __be16 lf_entries; /* Number of dirents in leaf */ + __be32 lf_dirent_format; /* Format of the dirents */ + __be64 lf_next; /* Next leaf, if overflow */ + + __u8 lf_reserved[32]; +}; + +/* + * Extended attribute header format + */ + +#define GFS2_EA_MAX_NAME_LEN 255 +#define GFS2_EA_MAX_DATA_LEN 65536 + +#define GFS2_EATYPE_UNUSED 0 +#define GFS2_EATYPE_USR 1 +#define GFS2_EATYPE_SYS 2 + +#define GFS2_EATYPE_LAST 2 +#define GFS2_EATYPE_VALID(x) ((x) <= GFS2_EATYPE_LAST) + +#define GFS2_EAFLAG_LAST 0x01 /* last ea in block */ + +struct gfs2_ea_header { + __be32 ea_rec_len; + __be32 ea_data_len; + __u8 ea_name_len; /* no NULL pointer after the string */ + __u8 ea_type; /* GFS2_EATYPE_... */ + __u8 ea_flags; /* GFS2_EAFLAG_... */ + __u8 ea_num_ptrs; + __u32 __pad; +}; + +/* + * Log header structure + */ + +#define GFS2_LOG_HEAD_UNMOUNT 0x00000001 /* log is clean */ + +struct gfs2_log_header { + struct gfs2_meta_header lh_header; + + __be64 lh_sequence; /* Sequence number of this transaction */ + __be32 lh_flags; /* GFS2_LOG_HEAD_... */ + __be32 lh_tail; /* Block number of log tail */ + __be32 lh_blkno; + __be32 lh_hash; +}; + +/* + * Log type descriptor + */ + +#define GFS2_LOG_DESC_METADATA 300 +/* ld_data1 is the number of metadata blocks in the descriptor. + ld_data2 is unused. */ + +#define GFS2_LOG_DESC_REVOKE 301 +/* ld_data1 is the number of revoke blocks in the descriptor. + ld_data2 is unused. */ + +struct gfs2_log_descriptor { + struct gfs2_meta_header ld_header; + + __be32 ld_type; /* GFS2_LOG_DESC_... */ + __be32 ld_length; /* Number of buffers in this chunk */ + __be32 ld_data1; /* descriptor-specific field */ + __be32 ld_data2; /* descriptor-specific field */ + + __u8 ld_reserved[32]; +}; + +/* + * Inum Range + * Describe a range of formal inode numbers allocated to + * one machine to assign to inodes. + */ + +#define GFS2_INUM_QUANTUM 1048576 + +struct gfs2_inum_range { + __be64 ir_start; + __be64 ir_length; +}; + +/* + * Statfs change + * Describes an change to the pool of free and allocated + * blocks. + */ + +struct gfs2_statfs_change { + __be64 sc_total; + __be64 sc_free; + __be64 sc_dinodes; +}; + +/* + * Unlinked Tag + * Describes an allocated inode that isn't linked into + * the directory tree and might need to be deallocated. + */ + +#define GFS2_UTF_UNINIT 0x00000001 + +struct gfs2_unlinked_tag { + struct gfs2_inum ut_inum; + __be32 ut_flags; /* GFS2_UTF_... */ + __u32 __pad; +}; + +/* + * Quota change + * Describes an allocation change for a particular + * user or group. + */ + +#define GFS2_QCF_USER 0x00000001 + +struct gfs2_quota_change { + __be64 qc_change; + __be32 qc_flags; /* GFS2_QCF_... */ + __be32 qc_id; +}; + +/* Translation functions */ + +extern void gfs2_inum_in(struct gfs2_inum *no, char *buf); +extern void gfs2_inum_out(struct gfs2_inum *no, char *buf); +extern void gfs2_meta_header_in(struct gfs2_meta_header *mh, char *buf); +extern void gfs2_meta_header_out(struct gfs2_meta_header *mh, char *buf); +extern void gfs2_sb_in(struct gfs2_sb *sb, char *buf); +extern void gfs2_sb_out(struct gfs2_sb *sb, char *buf); +extern void gfs2_rindex_in(struct gfs2_rindex *ri, char *buf); +extern void gfs2_rindex_out(struct gfs2_rindex *ri, char *buf); +extern void gfs2_rgrp_in(struct gfs2_rgrp *rg, char *buf); +extern void gfs2_rgrp_out(struct gfs2_rgrp *rg, char *buf); +extern void gfs2_quota_in(struct gfs2_quota *qu, char *buf); +extern void gfs2_quota_out(struct gfs2_quota *qu, char *buf); +extern void gfs2_dinode_in(struct gfs2_dinode *di, char *buf); +extern void gfs2_dinode_out(struct gfs2_dinode *di, char *buf); +extern void gfs2_dirent_in(struct gfs2_dirent *de, char *buf); +extern void gfs2_dirent_out(struct gfs2_dirent *de, char *buf); +extern void gfs2_leaf_in(struct gfs2_leaf *lf, char *buf); +extern void gfs2_leaf_out(struct gfs2_leaf *lf, char *buf); +extern void gfs2_ea_header_in(struct gfs2_ea_header *ea, char *buf); +extern void gfs2_ea_header_out(struct gfs2_ea_header *ea, char *buf); +extern void gfs2_log_header_in(struct gfs2_log_header *lh, char *buf); +extern void gfs2_inum_range_in(struct gfs2_inum_range *ir, char *buf); +extern void gfs2_inum_range_out(struct gfs2_inum_range *ir, char *buf); +extern void gfs2_statfs_change_in(struct gfs2_statfs_change *sc, char *buf); +extern void gfs2_statfs_change_out(struct gfs2_statfs_change *sc, char *buf); +extern void gfs2_unlinked_tag_in(struct gfs2_unlinked_tag *ut, char *buf); +extern void gfs2_unlinked_tag_out(struct gfs2_unlinked_tag *ut, char *buf); +extern void gfs2_quota_change_in(struct gfs2_quota_change *qc, char *buf); +extern void gfs2_quota_change_out(struct gfs2_quota_change *qc, char *buf); + +/* Printing functions */ + +extern void gfs2_inum_print(struct gfs2_inum *no); +extern void gfs2_meta_header_print(struct gfs2_meta_header *mh); +extern void gfs2_sb_print(struct gfs2_sb *sb); +extern void gfs2_rindex_print(struct gfs2_rindex *ri); +extern void gfs2_rgrp_print(struct gfs2_rgrp *rg); +extern void gfs2_quota_print(struct gfs2_quota *qu); +extern void gfs2_dinode_print(struct gfs2_dinode *di); +extern void gfs2_dirent_print(struct gfs2_dirent *de, char *name); +extern void gfs2_leaf_print(struct gfs2_leaf *lf); +extern void gfs2_ea_header_print(struct gfs2_ea_header *ea, char *name); +extern void gfs2_log_header_print(struct gfs2_log_header *lh); +extern void gfs2_log_descriptor_print(struct gfs2_log_descriptor *ld); +extern void gfs2_inum_range_print(struct gfs2_inum_range *ir); +extern void gfs2_statfs_change_print(struct gfs2_statfs_change *sc); +extern void gfs2_unlinked_tag_print(struct gfs2_unlinked_tag *ut); +extern void gfs2_quota_change_print(struct gfs2_quota_change *qc); + +#endif /* __GFS2_ONDISK_DOT_H__ */ -- cgit v1.2.3 From 869d81df53ad28ce78fc92504b3365b8196a2fa1 Mon Sep 17 00:00:00 2001 From: David Teigland Date: Tue, 17 Jan 2006 08:47:12 +0000 Subject: [GFS2] An update of the GFS2 lock modules This brings the lock modules uptodate and removes the stray .mod.c file which accidently got included in the last check in. Signed-off-by: David Teigland Signed-off-by: Steven Whitehouse --- include/linux/lock_dlm_plock.h | 40 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 40 insertions(+) create mode 100644 include/linux/lock_dlm_plock.h (limited to 'include/linux') diff --git a/include/linux/lock_dlm_plock.h b/include/linux/lock_dlm_plock.h new file mode 100644 index 000000000000..007b07a178ab --- /dev/null +++ b/include/linux/lock_dlm_plock.h @@ -0,0 +1,40 @@ +/* + * Copyright (C) 2005 Red Hat, Inc. All rights reserved. + * + * This copyrighted material is made available to anyone wishing to use, + * modify, copy, or redistribute it subject to the terms and conditions + * of the GNU General Public License v.2. + */ + +#ifndef __LOCK_DLM_PLOCK_DOT_H__ +#define __LOCK_DLM_PLOCK_DOT_H__ + +#define GDLM_PLOCK_MISC_NAME "lock_dlm_plock" + +#define GDLM_PLOCK_VERSION_MAJOR 1 +#define GDLM_PLOCK_VERSION_MINOR 0 +#define GDLM_PLOCK_VERSION_PATCH 0 + +enum { + GDLM_PLOCK_OP_LOCK = 1, + GDLM_PLOCK_OP_UNLOCK, + GDLM_PLOCK_OP_GET, +}; + +struct gdlm_plock_info { + __u32 version[3]; + __u8 optype; + __u8 ex; + __u8 wait; + __u8 pad; + __u32 pid; + __s32 nodeid; + __s32 rv; + __u32 fsid; + __u64 number; + __u64 start; + __u64 end; +}; + +#endif + -- cgit v1.2.3 From cd1344fe322cd9d95b2c0f011d6766677cfcb29b Mon Sep 17 00:00:00 2001 From: David Teigland Date: Wed, 18 Jan 2006 08:53:38 +0000 Subject: [GFS2] Remove unused ioctls and unused structure Signed-off-by: David Teigland Signed-off-by: Steven Whitehouse --- include/linux/gfs2_ioctl.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfs2_ioctl.h b/include/linux/gfs2_ioctl.h index dde9840b1c30..ca9632862833 100644 --- a/include/linux/gfs2_ioctl.h +++ b/include/linux/gfs2_ioctl.h @@ -14,19 +14,8 @@ /* Ioctls implemented */ -#define GFS2_IOCTL_IDENTIFY _GFS2C_(1) -#define GFS2_IOCTL_SUPER _GFS2C_(2) #define GFS2_IOCTL_SETFLAGS _GFS2C_(3) #define GFS2_IOCTL_GETFLAGS _GFS2C_(4) -struct gfs2_ioctl { - unsigned int gi_argc; - const char **gi_argv; - - char __user *gi_data; - unsigned int gi_size; - uint64_t gi_offset; -}; - #endif /* ___GFS2_IOCTL_DOT_H__ */ -- cgit v1.2.3 From e7fd41792fc0ee52a05fcaac87511f118328d147 Mon Sep 17 00:00:00 2001 From: David Teigland Date: Wed, 18 Jan 2006 09:30:29 +0000 Subject: [DLM] The core of the DLM for GFS2/CLVM This is the core of the distributed lock manager which is required to use GFS2 as a cluster filesystem. It is also used by CLVM and can be used as a standalone lock manager independantly of either of these two projects. It implements VAX-style locking modes. Signed-off-by: David Teigland Signed-off-by: Steve Whitehouse --- include/linux/dlm.h | 312 +++++++++++++++++++++++++++++++++++++++++++++ include/linux/dlm_device.h | 84 ++++++++++++ 2 files changed, 396 insertions(+) create mode 100644 include/linux/dlm.h create mode 100644 include/linux/dlm_device.h (limited to 'include/linux') diff --git a/include/linux/dlm.h b/include/linux/dlm.h new file mode 100644 index 000000000000..dd324ba44d80 --- /dev/null +++ b/include/linux/dlm.h @@ -0,0 +1,312 @@ +/****************************************************************************** +******************************************************************************* +** +** Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. +** Copyright (C) 2004-2005 Red Hat, Inc. All rights reserved. +** +** This copyrighted material is made available to anyone wishing to use, +** modify, copy, or redistribute it subject to the terms and conditions +** of the GNU General Public License v.2. +** +******************************************************************************* +******************************************************************************/ + +#ifndef __DLM_DOT_H__ +#define __DLM_DOT_H__ + +/* + * Interface to Distributed Lock Manager (DLM) + * routines and structures to use DLM lockspaces + */ + +/* + * Lock Modes + */ + +#define DLM_LOCK_IV -1 /* invalid */ +#define DLM_LOCK_NL 0 /* null */ +#define DLM_LOCK_CR 1 /* concurrent read */ +#define DLM_LOCK_CW 2 /* concurrent write */ +#define DLM_LOCK_PR 3 /* protected read */ +#define DLM_LOCK_PW 4 /* protected write */ +#define DLM_LOCK_EX 5 /* exclusive */ + +/* + * Maximum size in bytes of a dlm_lock name + */ + +#define DLM_RESNAME_MAXLEN 64 + +/* + * Flags to dlm_lock + * + * DLM_LKF_NOQUEUE + * + * Do not queue the lock request on the wait queue if it cannot be granted + * immediately. If the lock cannot be granted because of this flag, DLM will + * either return -EAGAIN from the dlm_lock call or will return 0 from + * dlm_lock and -EAGAIN in the lock status block when the AST is executed. + * + * DLM_LKF_CANCEL + * + * Used to cancel a pending lock request or conversion. A converting lock is + * returned to its previously granted mode. + * + * DLM_LKF_CONVERT + * + * Indicates a lock conversion request. For conversions the name and namelen + * are ignored and the lock ID in the LKSB is used to identify the lock. + * + * DLM_LKF_VALBLK + * + * Requests DLM to return the current contents of the lock value block in the + * lock status block. When this flag is set in a lock conversion from PW or EX + * modes, DLM assigns the value specified in the lock status block to the lock + * value block of the lock resource. The LVB is a DLM_LVB_LEN size array + * containing application-specific information. + * + * DLM_LKF_QUECVT + * + * Force a conversion request to be queued, even if it is compatible with + * the granted modes of other locks on the same resource. + * + * DLM_LKF_IVVALBLK + * + * Invalidate the lock value block. + * + * DLM_LKF_CONVDEADLK + * + * Allows the dlm to resolve conversion deadlocks internally by demoting the + * granted mode of a converting lock to NL. The DLM_SBF_DEMOTED flag is + * returned for a conversion that's been effected by this. + * + * DLM_LKF_PERSISTENT + * + * Only relevant to locks originating in userspace. A persistent lock will not + * be removed if the process holding the lock exits. + * + * DLM_LKF_NODLKWT + * DLM_LKF_NODLCKBLK + * + * net yet implemented + * + * DLM_LKF_EXPEDITE + * + * Used only with new requests for NL mode locks. Tells the lock manager + * to grant the lock, ignoring other locks in convert and wait queues. + * + * DLM_LKF_NOQUEUEBAST + * + * Send blocking AST's before returning -EAGAIN to the caller. It is only + * used along with the NOQUEUE flag. Blocking AST's are not sent for failed + * NOQUEUE requests otherwise. + * + * DLM_LKF_HEADQUE + * + * Add a lock to the head of the convert or wait queue rather than the tail. + * + * DLM_LKF_NOORDER + * + * Disregard the standard grant order rules and grant a lock as soon as it + * is compatible with other granted locks. + * + * DLM_LKF_ORPHAN + * + * not yet implemented + * + * DLM_LKF_ALTPR + * + * If the requested mode cannot be granted immediately, try to grant the lock + * in PR mode instead. If this alternate mode is granted instead of the + * requested mode, DLM_SBF_ALTMODE is returned in the lksb. + * + * DLM_LKF_ALTCW + * + * The same as ALTPR, but the alternate mode is CW. + * + * DLM_LKF_FORCEUNLOCK + * + * Unlock the lock even if it is converting or waiting or has sublocks. + * Only really for use by the userland device.c code. + * + */ + +#define DLM_LKF_NOQUEUE 0x00000001 +#define DLM_LKF_CANCEL 0x00000002 +#define DLM_LKF_CONVERT 0x00000004 +#define DLM_LKF_VALBLK 0x00000008 +#define DLM_LKF_QUECVT 0x00000010 +#define DLM_LKF_IVVALBLK 0x00000020 +#define DLM_LKF_CONVDEADLK 0x00000040 +#define DLM_LKF_PERSISTENT 0x00000080 +#define DLM_LKF_NODLCKWT 0x00000100 +#define DLM_LKF_NODLCKBLK 0x00000200 +#define DLM_LKF_EXPEDITE 0x00000400 +#define DLM_LKF_NOQUEUEBAST 0x00000800 +#define DLM_LKF_HEADQUE 0x00001000 +#define DLM_LKF_NOORDER 0x00002000 +#define DLM_LKF_ORPHAN 0x00004000 +#define DLM_LKF_ALTPR 0x00008000 +#define DLM_LKF_ALTCW 0x00010000 +#define DLM_LKF_FORCEUNLOCK 0x00020000 + +/* + * Some return codes that are not in errno.h + */ + +#define DLM_ECANCEL 0x10001 +#define DLM_EUNLOCK 0x10002 + +typedef void dlm_lockspace_t; + +/* + * Lock range structure + */ + +struct dlm_range { + uint64_t ra_start; + uint64_t ra_end; +}; + +/* + * Lock status block + * + * Use this structure to specify the contents of the lock value block. For a + * conversion request, this structure is used to specify the lock ID of the + * lock. DLM writes the status of the lock request and the lock ID assigned + * to the request in the lock status block. + * + * sb_lkid: the returned lock ID. It is set on new (non-conversion) requests. + * It is available when dlm_lock returns. + * + * sb_lvbptr: saves or returns the contents of the lock's LVB according to rules + * shown for the DLM_LKF_VALBLK flag. + * + * sb_flags: DLM_SBF_DEMOTED is returned if in the process of promoting a lock, + * it was first demoted to NL to avoid conversion deadlock. + * DLM_SBF_VALNOTVALID is returned if the resource's LVB is marked invalid. + * + * sb_status: the returned status of the lock request set prior to AST + * execution. Possible return values: + * + * 0 if lock request was successful + * -EAGAIN if request would block and is flagged DLM_LKF_NOQUEUE + * -ENOMEM if there is no memory to process request + * -EINVAL if there are invalid parameters + * -DLM_EUNLOCK if unlock request was successful + * -DLM_ECANCEL if a cancel completed successfully + */ + +#define DLM_SBF_DEMOTED 0x01 +#define DLM_SBF_VALNOTVALID 0x02 +#define DLM_SBF_ALTMODE 0x04 + +struct dlm_lksb { + int sb_status; + uint32_t sb_lkid; + char sb_flags; + char * sb_lvbptr; +}; + + +#ifdef __KERNEL__ + +#define DLM_LSFL_NODIR 0x00000001 + +/* + * dlm_new_lockspace + * + * Starts a lockspace with the given name. If the named lockspace exists in + * the cluster, the calling node joins it. + */ + +int dlm_new_lockspace(char *name, int namelen, dlm_lockspace_t **lockspace, + uint32_t flags, int lvblen); + +/* + * dlm_release_lockspace + * + * Stop a lockspace. + */ + +int dlm_release_lockspace(dlm_lockspace_t *lockspace, int force); + +/* + * dlm_lock + * + * Make an asyncronous request to acquire or convert a lock on a named + * resource. + * + * lockspace: context for the request + * mode: the requested mode of the lock (DLM_LOCK_) + * lksb: lock status block for input and async return values + * flags: input flags (DLM_LKF_) + * name: name of the resource to lock, can be binary + * namelen: the length in bytes of the resource name (MAX_RESNAME_LEN) + * parent: the lock ID of a parent lock or 0 if none + * lockast: function DLM executes when it completes processing the request + * astarg: argument passed to lockast and bast functions + * bast: function DLM executes when this lock later blocks another request + * + * Returns: + * 0 if request is successfully queued for processing + * -EINVAL if any input parameters are invalid + * -EAGAIN if request would block and is flagged DLM_LKF_NOQUEUE + * -ENOMEM if there is no memory to process request + * -ENOTCONN if there is a communication error + * + * If the call to dlm_lock returns an error then the operation has failed and + * the AST routine will not be called. If dlm_lock returns 0 it is still + * possible that the lock operation will fail. The AST routine will be called + * when the locking is complete and the status is returned in the lksb. + * + * If the AST routines or parameter are passed to a conversion operation then + * they will overwrite those values that were passed to a previous dlm_lock + * call. + * + * AST routines should not block (at least not for long), but may make + * any locking calls they please. + */ + +int dlm_lock(dlm_lockspace_t *lockspace, + int mode, + struct dlm_lksb *lksb, + uint32_t flags, + void *name, + unsigned int namelen, + uint32_t parent_lkid, + void (*lockast) (void *astarg), + void *astarg, + void (*bast) (void *astarg, int mode), + struct dlm_range *range); + +/* + * dlm_unlock + * + * Asynchronously release a lock on a resource. The AST routine is called + * when the resource is successfully unlocked. + * + * lockspace: context for the request + * lkid: the lock ID as returned in the lksb + * flags: input flags (DLM_LKF_) + * lksb: if NULL the lksb parameter passed to last lock request is used + * astarg: the arg used with the completion ast for the unlock + * + * Returns: + * 0 if request is successfully queued for processing + * -EINVAL if any input parameters are invalid + * -ENOTEMPTY if the lock still has sublocks + * -EBUSY if the lock is waiting for a remote lock operation + * -ENOTCONN if there is a communication error + */ + +int dlm_unlock(dlm_lockspace_t *lockspace, + uint32_t lkid, + uint32_t flags, + struct dlm_lksb *lksb, + void *astarg); + +#endif /* __KERNEL__ */ + +#endif /* __DLM_DOT_H__ */ + diff --git a/include/linux/dlm_device.h b/include/linux/dlm_device.h new file mode 100644 index 000000000000..5e17d295544b --- /dev/null +++ b/include/linux/dlm_device.h @@ -0,0 +1,84 @@ +/****************************************************************************** +******************************************************************************* +** +** Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. +** Copyright (C) 2004-2005 Red Hat, Inc. All rights reserved. +** +** This copyrighted material is made available to anyone wishing to use, +** modify, copy, or redistribute it subject to the terms and conditions +** of the GNU General Public License v.2. +** +******************************************************************************* +******************************************************************************/ + +/* This is the device interface for dlm, most users will use a library + * interface. + */ + +#define DLM_USER_LVB_LEN 32 + +/* Version of the device interface */ +#define DLM_DEVICE_VERSION_MAJOR 3 +#define DLM_DEVICE_VERSION_MINOR 0 +#define DLM_DEVICE_VERSION_PATCH 0 + +/* struct passed to the lock write */ +struct dlm_lock_params { + __u8 mode; + __u16 flags; + __u32 lkid; + __u32 parent; + struct dlm_range range; + __u8 namelen; + void __user *castparam; + void __user *castaddr; + void __user *bastparam; + void __user *bastaddr; + struct dlm_lksb __user *lksb; + char lvb[DLM_USER_LVB_LEN]; + char name[1]; +}; + +struct dlm_lspace_params { + __u32 flags; + __u32 minor; + char name[1]; +}; + +struct dlm_write_request { + __u32 version[3]; + __u8 cmd; + + union { + struct dlm_lock_params lock; + struct dlm_lspace_params lspace; + } i; +}; + +/* struct read from the "device" fd, + consists mainly of userspace pointers for the library to use */ +struct dlm_lock_result { + __u32 length; + void __user * user_astaddr; + void __user * user_astparam; + struct dlm_lksb __user * user_lksb; + struct dlm_lksb lksb; + __u8 bast_mode; + /* Offsets may be zero if no data is present */ + __u32 lvb_offset; +}; + +/* Commands passed to the device */ +#define DLM_USER_LOCK 1 +#define DLM_USER_UNLOCK 2 +#define DLM_USER_QUERY 3 +#define DLM_USER_CREATE_LOCKSPACE 4 +#define DLM_USER_REMOVE_LOCKSPACE 5 + +/* Arbitrary length restriction */ +#define MAX_LS_NAME_LEN 64 + +/* Lockspace flags */ +#define DLM_USER_LSFLG_AUTOFREE 1 +#define DLM_USER_LSFLG_FORCEFREE 2 + -- cgit v1.2.3 From 3bd7662c4de28522d4709ab5a56033e3c33e1d4a Mon Sep 17 00:00:00 2001 From: Steven Whitehouse Date: Wed, 18 Jan 2006 10:40:17 +0000 Subject: [GFS2] Remove unused code from ondisk.c/gfs2_ondisk.h Removal of unused conversion functions from ondisk.c and gfs2_ondisk.h Signed-off-by: Steven Whitehouse --- include/linux/gfs2_ondisk.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfs2_ondisk.h b/include/linux/gfs2_ondisk.h index 213d664d495d..8354b9c4f408 100644 --- a/include/linux/gfs2_ondisk.h +++ b/include/linux/gfs2_ondisk.h @@ -407,7 +407,6 @@ extern void gfs2_inum_out(struct gfs2_inum *no, char *buf); extern void gfs2_meta_header_in(struct gfs2_meta_header *mh, char *buf); extern void gfs2_meta_header_out(struct gfs2_meta_header *mh, char *buf); extern void gfs2_sb_in(struct gfs2_sb *sb, char *buf); -extern void gfs2_sb_out(struct gfs2_sb *sb, char *buf); extern void gfs2_rindex_in(struct gfs2_rindex *ri, char *buf); extern void gfs2_rindex_out(struct gfs2_rindex *ri, char *buf); extern void gfs2_rgrp_in(struct gfs2_rgrp *rg, char *buf); @@ -416,10 +415,7 @@ extern void gfs2_quota_in(struct gfs2_quota *qu, char *buf); extern void gfs2_quota_out(struct gfs2_quota *qu, char *buf); extern void gfs2_dinode_in(struct gfs2_dinode *di, char *buf); extern void gfs2_dinode_out(struct gfs2_dinode *di, char *buf); -extern void gfs2_dirent_in(struct gfs2_dirent *de, char *buf); -extern void gfs2_dirent_out(struct gfs2_dirent *de, char *buf); extern void gfs2_leaf_in(struct gfs2_leaf *lf, char *buf); -extern void gfs2_leaf_out(struct gfs2_leaf *lf, char *buf); extern void gfs2_ea_header_in(struct gfs2_ea_header *ea, char *buf); extern void gfs2_ea_header_out(struct gfs2_ea_header *ea, char *buf); extern void gfs2_log_header_in(struct gfs2_log_header *lh, char *buf); @@ -430,7 +426,6 @@ extern void gfs2_statfs_change_out(struct gfs2_statfs_change *sc, char *buf); extern void gfs2_unlinked_tag_in(struct gfs2_unlinked_tag *ut, char *buf); extern void gfs2_unlinked_tag_out(struct gfs2_unlinked_tag *ut, char *buf); extern void gfs2_quota_change_in(struct gfs2_quota_change *qc, char *buf); -extern void gfs2_quota_change_out(struct gfs2_quota_change *qc, char *buf); /* Printing functions */ -- cgit v1.2.3 From b96ca4fa4e3b510d528a093a5bac0befbc2ba46d Mon Sep 17 00:00:00 2001 From: Steven Whitehouse Date: Wed, 18 Jan 2006 10:57:10 +0000 Subject: [GFS2] Update init_dinode() to reduce stack usage We no longer allocate a dinode on the stack in init_dinode() and we no longer use gfs2_dinode_out (eliminating one copy) and gfs2_meta_header_in (eliminating another copy). The meta_header_in fucntion is now no longer referenced from outside gfs2_ondisk.c, so make it static. Signed-off-by: Steven Whitehouse --- include/linux/gfs2_ondisk.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfs2_ondisk.h b/include/linux/gfs2_ondisk.h index 8354b9c4f408..f1302e2616da 100644 --- a/include/linux/gfs2_ondisk.h +++ b/include/linux/gfs2_ondisk.h @@ -404,8 +404,6 @@ struct gfs2_quota_change { extern void gfs2_inum_in(struct gfs2_inum *no, char *buf); extern void gfs2_inum_out(struct gfs2_inum *no, char *buf); -extern void gfs2_meta_header_in(struct gfs2_meta_header *mh, char *buf); -extern void gfs2_meta_header_out(struct gfs2_meta_header *mh, char *buf); extern void gfs2_sb_in(struct gfs2_sb *sb, char *buf); extern void gfs2_rindex_in(struct gfs2_rindex *ri, char *buf); extern void gfs2_rindex_out(struct gfs2_rindex *ri, char *buf); -- cgit v1.2.3 From 8ca05c60de49c3bb523a435abc216b6b6eeb1067 Mon Sep 17 00:00:00 2001 From: David Teigland Date: Tue, 24 Jan 2006 10:03:04 +0000 Subject: [GFS2] Update ioctl() numbering to use official numbers. This patch adds us into the official ioctl-number.txt registry and updates GFS2 accordingly. Signed-off-by: David Teigland Signed-off-by: Steven Whitehouse --- include/linux/gfs2_ioctl.h | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfs2_ioctl.h b/include/linux/gfs2_ioctl.h index ca9632862833..fb7c0cf72c56 100644 --- a/include/linux/gfs2_ioctl.h +++ b/include/linux/gfs2_ioctl.h @@ -10,12 +10,8 @@ #ifndef __GFS2_IOCTL_DOT_H__ #define __GFS2_IOCTL_DOT_H__ -#define _GFS2C_(x) (('G' << 16) | ('2' << 8) | (x)) - -/* Ioctls implemented */ - -#define GFS2_IOCTL_SETFLAGS _GFS2C_(3) -#define GFS2_IOCTL_GETFLAGS _GFS2C_(4) +#define GFS2_IOCTL_SETFLAGS _IOW('g', 3, long) +#define GFS2_IOCTL_GETFLAGS _IOR('g', 4, long) #endif /* ___GFS2_IOCTL_DOT_H__ */ -- cgit v1.2.3 From 18ec7d5c3f434aed9661ed10a9e1f48cdeb4981d Mon Sep 17 00:00:00 2001 From: Steven Whitehouse Date: Wed, 8 Feb 2006 11:50:51 +0000 Subject: [GFS2] Make journaled data files identical to normal files on disk This is a very large patch, with a few still to be resolved issues so you might want to check out the previous head of the tree since this is known to be unstable. Fixes for the various bugs will be forthcoming shortly. This patch removes the special data format which has been used up till now for journaled data files. Directories still retain the old format so that they will remain on disk compatible with earlier releases. As a result you can now do the following with journaled data files: 1) mmap them 2) export them over NFS 3) convert to/from normal files whenever you want to (the zero length restriction is gone) In addition the level at which GFS' locking is done has changed for all files (since they all now use the page cache) such that the locking is done at the page cache level rather than the level of the fs operations. This should mean that things like loopback mounts and other things which touch the page cache directly should now work. Current known issues: 1. There is a lock mode inversion problem related to the resource group hold function which needs to be resolved. 2. Any significant amount of I/O causes an oops with an offset of hex 320 (NULL pointer dereference) which appears to be related to a journaled data buffer appearing on a list where it shouldn't be. 3. Direct I/O writes are disabled for the time being (will reappear later) 4. There is probably a deadlock between the page lock and GFS' locks under certain combinations of mmap and fs operation I/O. 5. Issue relating to ref counting on internally used inodes causes a hang on umount (discovered before this patch, and not fixed by it) 6. One part of the directory metadata is different from GFS1 and will need to be resolved before next release. Signed-off-by: Steven Whitehouse --- include/linux/gfs2_ondisk.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gfs2_ondisk.h b/include/linux/gfs2_ondisk.h index f1302e2616da..99d7ae4f6b7e 100644 --- a/include/linux/gfs2_ondisk.h +++ b/include/linux/gfs2_ondisk.h @@ -336,6 +336,10 @@ struct gfs2_log_header { /* ld_data1 is the number of revoke blocks in the descriptor. ld_data2 is unused. */ +#define GFS2_LOG_DESC_JDATA 302 +/* ld_data1 is the number of data blocks in the descriptor. + ld_data2 is unused. */ + struct gfs2_log_descriptor { struct gfs2_meta_header ld_header; @@ -400,6 +404,7 @@ struct gfs2_quota_change { __be32 qc_id; }; +#ifdef __KERNEL__ /* Translation functions */ extern void gfs2_inum_in(struct gfs2_inum *no, char *buf); @@ -444,4 +449,6 @@ extern void gfs2_statfs_change_print(struct gfs2_statfs_change *sc); extern void gfs2_unlinked_tag_print(struct gfs2_unlinked_tag *ut); extern void gfs2_quota_change_print(struct gfs2_quota_change *qc); +#endif /* __KERNEL__ */ + #endif /* __GFS2_ONDISK_DOT_H__ */ -- cgit v1.2.3 From fc69d0d336214219abb521d8ff060f786d7f369e Mon Sep 17 00:00:00 2001 From: Steven Whitehouse Date: Mon, 13 Feb 2006 16:21:47 +0000 Subject: [GFS2] Change ondisk format (hopefully for the last time) There were one or two fields in structures which didn't get changed last time back to their gfs1 sizes and alignments. One or two constants have also changed back to their original values which were missed the first time. Its possible that indirect pointer blocks might need to change. If they don't we'll have to rewrite them all on upgrade due to a change in the amount of padding that they use. Signed-off-by: Steven Whitehouse --- include/linux/gfs2_ondisk.h | 42 +++++++++++++++++++++--------------------- 1 file changed, 21 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfs2_ondisk.h b/include/linux/gfs2_ondisk.h index 99d7ae4f6b7e..ec432e0c208d 100644 --- a/include/linux/gfs2_ondisk.h +++ b/include/linux/gfs2_ondisk.h @@ -1,11 +1,11 @@ /* - * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. - * Copyright (C) 2004-2005 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License v.2. - */ +* Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. +* Copyright (C) 2004-2005 Red Hat, Inc. All rights reserved. +* +* This copyrighted material is made available to anyone wishing to use, +* modify, copy, or redistribute it subject to the terms and conditions +* of the GNU General Public License v.2. +*/ #ifndef __GFS2_ONDISK_DOT_H__ #define __GFS2_ONDISK_DOT_H__ @@ -34,14 +34,14 @@ #define GFS2_FORMAT_LH 800 #define GFS2_FORMAT_LD 900 #define GFS2_FORMAT_LB 1000 -#define GFS2_FORMAT_EA 1100 -#define GFS2_FORMAT_ED 1200 +#define GFS2_FORMAT_EA 1600 +#define GFS2_FORMAT_ED 1700 #define GFS2_FORMAT_UT 1300 #define GFS2_FORMAT_QC 1400 /* These are format numbers for entities contained in files */ -#define GFS2_FORMAT_RI 1500 -#define GFS2_FORMAT_DE 1600 -#define GFS2_FORMAT_QU 1700 +#define GFS2_FORMAT_RI 1100 +#define GFS2_FORMAT_DE 1200 +#define GFS2_FORMAT_QU 1500 /* These are part of the superblock */ #define GFS2_FORMAT_FS 1801 #define GFS2_FORMAT_MULTI 1900 @@ -74,9 +74,9 @@ struct gfs2_inum { #define GFS2_METATYPE_JD 7 #define GFS2_METATYPE_LH 8 #define GFS2_METATYPE_LD 9 -#define GFS2_METATYPE_LB 10 -#define GFS2_METATYPE_EA 11 -#define GFS2_METATYPE_ED 12 +#define GFS2_METATYPE_LB 12 +#define GFS2_METATYPE_EA 10 +#define GFS2_METATYPE_ED 11 #define GFS2_METATYPE_UT 13 #define GFS2_METATYPE_QC 14 @@ -181,6 +181,7 @@ struct gfs2_quota { __be64 qu_limit; __be64 qu_warn; __be64 qu_value; + __u8 qu_reserved[64]; }; /* @@ -260,11 +261,10 @@ struct gfs2_dinode { struct gfs2_dirent { struct gfs2_inum de_inum; __be32 de_hash; - __be32 de_rec_len; - __u8 de_name_len; - __u8 de_type; - __u16 __pad1; - __u32 __pad2; + __be16 de_rec_len; + __be16 de_name_len; + __be16 de_type; + __u8 __pad[14]; }; /* @@ -279,7 +279,7 @@ struct gfs2_leaf { __be32 lf_dirent_format; /* Format of the dirents */ __be64 lf_next; /* Next leaf, if overflow */ - __u8 lf_reserved[32]; + __u8 lf_reserved[64]; }; /* -- cgit v1.2.3 From 3bcd3687f895f178fa8480a7bcc47a363817354a Mon Sep 17 00:00:00 2001 From: David Teigland Date: Thu, 23 Feb 2006 09:56:38 +0000 Subject: [DLM] Remove range locks from the DLM This patch removes support for range locking from the DLM Signed-off-by: David Teigland Signed-off-by: Steven Whitehouse --- include/linux/dlm.h | 12 +----------- include/linux/dlm_device.h | 3 +-- 2 files changed, 2 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dlm.h b/include/linux/dlm.h index dd324ba44d80..1b1dcb9a40bb 100644 --- a/include/linux/dlm.h +++ b/include/linux/dlm.h @@ -159,15 +159,6 @@ typedef void dlm_lockspace_t; -/* - * Lock range structure - */ - -struct dlm_range { - uint64_t ra_start; - uint64_t ra_end; -}; - /* * Lock status block * @@ -277,8 +268,7 @@ int dlm_lock(dlm_lockspace_t *lockspace, uint32_t parent_lkid, void (*lockast) (void *astarg), void *astarg, - void (*bast) (void *astarg, int mode), - struct dlm_range *range); + void (*bast) (void *astarg, int mode)); /* * dlm_unlock diff --git a/include/linux/dlm_device.h b/include/linux/dlm_device.h index 5e17d295544b..f8ba1981aa96 100644 --- a/include/linux/dlm_device.h +++ b/include/linux/dlm_device.h @@ -18,7 +18,7 @@ #define DLM_USER_LVB_LEN 32 /* Version of the device interface */ -#define DLM_DEVICE_VERSION_MAJOR 3 +#define DLM_DEVICE_VERSION_MAJOR 4 #define DLM_DEVICE_VERSION_MINOR 0 #define DLM_DEVICE_VERSION_PATCH 0 @@ -28,7 +28,6 @@ struct dlm_lock_params { __u16 flags; __u32 lkid; __u32 parent; - struct dlm_range range; __u8 namelen; void __user *castparam; void __user *castaddr; -- cgit v1.2.3 From 5c676f6d359b0404d53f542f02e1359583cb2895 Mon Sep 17 00:00:00 2001 From: Steven Whitehouse Date: Mon, 27 Feb 2006 17:23:27 -0500 Subject: [GFS2] Macros removal in gfs2.h As suggested by Pekka Enberg . The DIV_RU macro is renamed DIV_ROUND_UP and and moved to kernel.h The other macros are gone from gfs2.h as (although not requested by Pekka Enberg) are a number of included header file which are now included individually. The inode number comparison function is now an inline function. The DT2IF and IF2DT may be addressed in a future patch. Signed-off-by: Steven Whitehouse --- include/linux/gfs2_ondisk.h | 11 +++++++---- include/linux/kernel.h | 1 + 2 files changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfs2_ondisk.h b/include/linux/gfs2_ondisk.h index ec432e0c208d..8d4f0445df47 100644 --- a/include/linux/gfs2_ondisk.h +++ b/include/linux/gfs2_ondisk.h @@ -50,15 +50,18 @@ * An on-disk inode number */ -#define gfs2_inum_equal(ino1, ino2) \ - (((ino1)->no_formal_ino == (ino2)->no_formal_ino) && \ - ((ino1)->no_addr == (ino2)->no_addr)) - struct gfs2_inum { __be64 no_formal_ino; __be64 no_addr; }; +static inline int gfs2_inum_equal(const struct gfs2_inum *ino1, + const struct gfs2_inum *ino2) +{ + return ino1->no_formal_ino == ino2->no_formal_ino && + ino1->no_addr == ino2->no_addr; +} + /* * Generic metadata head structure * Every inplace buffer logged in the journal must start with this. diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 3b507bf05d09..f789278a625a 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -29,6 +29,7 @@ extern const char linux_banner[]; #define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) #define ALIGN(x,a) (((x)+(a)-1)&~((a)-1)) +#define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d)) #define KERN_EMERG "<0>" /* system is unusable */ #define KERN_ALERT "<1>" /* action must be taken immediately */ -- cgit v1.2.3 From c752666c17f870fa8ae9f16804dd457e9e6daaec Mon Sep 17 00:00:00 2001 From: Steven Whitehouse Date: Mon, 20 Mar 2006 12:30:04 -0500 Subject: [GFS2] Fix bug in directory code and tidy up Due to a typo, the dir leaf split operation was (for the first split in a directory) writing the new hash vaules at the wrong offset. This is now fixed. Also some other tidy ups are included: - We use GFS2's hash function for dentries (see ops_dentry.c) so that we don't have to keep recalculating the hash values. - A lot of common code is eliminated between the various directory lookup routines. - Better error checking on directory lookup (previously different routines checked for different errors) - The leaf split operation has a couple of redundant operations removed from it, so it should be faster. There is still further scope for further clean ups in the directory code, and readdir in particular could do with slimming down a bit. Signed-off-by: Steven Whitehouse --- include/linux/gfs2_ondisk.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfs2_ondisk.h b/include/linux/gfs2_ondisk.h index 8d4f0445df47..a5fb4f99aa45 100644 --- a/include/linux/gfs2_ondisk.h +++ b/include/linux/gfs2_ondisk.h @@ -411,7 +411,7 @@ struct gfs2_quota_change { /* Translation functions */ extern void gfs2_inum_in(struct gfs2_inum *no, char *buf); -extern void gfs2_inum_out(struct gfs2_inum *no, char *buf); +extern void gfs2_inum_out(const struct gfs2_inum *no, char *buf); extern void gfs2_sb_in(struct gfs2_sb *sb, char *buf); extern void gfs2_rindex_in(struct gfs2_rindex *ri, char *buf); extern void gfs2_rindex_out(struct gfs2_rindex *ri, char *buf); @@ -421,7 +421,6 @@ extern void gfs2_quota_in(struct gfs2_quota *qu, char *buf); extern void gfs2_quota_out(struct gfs2_quota *qu, char *buf); extern void gfs2_dinode_in(struct gfs2_dinode *di, char *buf); extern void gfs2_dinode_out(struct gfs2_dinode *di, char *buf); -extern void gfs2_leaf_in(struct gfs2_leaf *lf, char *buf); extern void gfs2_ea_header_in(struct gfs2_ea_header *ea, char *buf); extern void gfs2_ea_header_out(struct gfs2_ea_header *ea, char *buf); extern void gfs2_log_header_in(struct gfs2_log_header *lh, char *buf); -- cgit v1.2.3 From 94aabbd99370f738da4f6cb4ea0b94cd9024002f Mon Sep 17 00:00:00 2001 From: Steven Whitehouse Date: Tue, 21 Mar 2006 11:29:00 -0500 Subject: [GFS2] Remove ioctl support The various flags on inodes will in future be set and queried via the extended attributes interface, so this interface is no longer required. Signed-off-by: Steven Whitehouse --- include/linux/gfs2_ioctl.h | 17 ----------------- 1 file changed, 17 deletions(-) delete mode 100644 include/linux/gfs2_ioctl.h (limited to 'include/linux') diff --git a/include/linux/gfs2_ioctl.h b/include/linux/gfs2_ioctl.h deleted file mode 100644 index fb7c0cf72c56..000000000000 --- a/include/linux/gfs2_ioctl.h +++ /dev/null @@ -1,17 +0,0 @@ -/* - * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. - * Copyright (C) 2004-2005 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License v.2. - */ - -#ifndef __GFS2_IOCTL_DOT_H__ -#define __GFS2_IOCTL_DOT_H__ - -#define GFS2_IOCTL_SETFLAGS _IOW('g', 3, long) -#define GFS2_IOCTL_GETFLAGS _IOR('g', 4, long) - -#endif /* ___GFS2_IOCTL_DOT_H__ */ - -- cgit v1.2.3 From 7ea9ea832212c4a755650f7c7cc1ff0b63292a41 Mon Sep 17 00:00:00 2001 From: Steven Whitehouse Date: Fri, 31 Mar 2006 15:01:28 -0500 Subject: [GFS2] Update ioctl() to new interface This is designed as a fs independent way to set flags on a particular inode. The values of the ioctl() and flags are designed to be identical to the ext2/3 values. Assuming that this plan is acceptable to people in general, the plan is to then move other fs across to using the same set of #defines, etc. Signed-off-by: Steven Whitehouse --- include/linux/gfs2_ondisk.h | 16 +++++++ include/linux/iflags.h | 104 ++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 120 insertions(+) create mode 100644 include/linux/iflags.h (limited to 'include/linux') diff --git a/include/linux/gfs2_ondisk.h b/include/linux/gfs2_ondisk.h index a5fb4f99aa45..3ab40917383f 100644 --- a/include/linux/gfs2_ondisk.h +++ b/include/linux/gfs2_ondisk.h @@ -197,6 +197,22 @@ struct gfs2_quota { #define DT2IF(dt) (((dt) << 12) & S_IFMT) #define IF2DT(sif) (((sif) & S_IFMT) >> 12) +enum { + gfs2fl_Jdata = 0, + gfs2fl_ExHash = 1, + gfs2fl_Unused = 2, + gfs2fl_EaIndirect = 3, + gfs2fl_Directio = 4, + gfs2fl_Immutable = 5, + gfs2fl_AppendOnly = 6, + gfs2fl_NoAtime = 7, + gfs2fl_Sync = 8, + gfs2fl_System = 9, + gfs2fl_TruncInProg = 29, + gfs2fl_InheritDirectio = 30, + gfs2fl_InheritJdata = 31, +}; + /* Dinode flags */ #define GFS2_DIF_JDATA 0x00000001 #define GFS2_DIF_EXHASH 0x00000002 diff --git a/include/linux/iflags.h b/include/linux/iflags.h new file mode 100644 index 000000000000..1b4d9ef5d62b --- /dev/null +++ b/include/linux/iflags.h @@ -0,0 +1,104 @@ +#ifndef _LINUX_IFLAGS_H +#define _LINUX_IFLAGS_H + +/* + * A universal set of inode flags. + * + * Originally taken from ext2/3 with additions for other filesystems. + * Filesystems supporting this interface should interoperate with + * the lsattr and chattr command line tools. + * + * This interface is supported in whole or in part by: + * ext2 + * ext3 + * xfs + * jfs + * gfs2 + * + */ + +#define IFLAGS_GET_IOC _IOR('f', 1, long) +#define IFLAGS_SET_IOC _IOW('f', 2, long) + +/* + * These values are provided for use as indices of an array + * for use with the iflags_cvt function below + */ +enum { + iflag_SecureRm = 0, /* Secure deletion */ + iflag_Unrm = 1, /* Undelete */ + iflag_Compress = 2, /* Compress file */ + iflag_Sync = 3, /* Synchronous updates */ + iflag_Immutable = 4, /* Immutable */ + iflag_Append = 5, /* Append */ + iflag_NoDump = 6, /* Don't dump file */ + iflag_NoAtime = 7, /* No atime updates */ + /* Reserved for compression usage */ + iflag_Dirty = 8, + iflag_ComprBlk = 9, /* One or more compressed clusters */ + iflag_NoComp = 10, /* Don't compress */ + iflag_Ecompr = 11, /* Compression error */ + /* End of compression flags */ + iflag_Btree = 12, /* btree format dir */ + iflag_Index = 12, /* hash-indexed directory */ + iflag_Imagic = 13, /* AFS directory */ + iflag_JournalData = 14, /* file data should be journaled */ + iflag_NoTail = 15, /* file tail should not be merged */ + iflag_DirSync = 16, /* dirsync behaviour */ + iflag_TopDir = 17, /* Top of directory hierarchies */ + iflag_DirectIO = 18, /* Always use direct I/O on this file */ + iflag_InheritDirectIO = 19, /* Set DirectIO on new files in dir */ + iflag_InheritJdata = 20, /* Set JournalData on create in dir */ + iflag_Reserved = 31 /* reserved for ext2/3 lib */ +}; + +#define __IFL(x) (1<<(iflag_##x)) +#define IFLAG_SECRM __IFL(SecureRm) /* 0x00000001 */ +#define IFLAG_UNRM __IFL(Unrm) /* 0x00000002 */ +#define IFLAG_COMPR __IFL(Compr) /* 0x00000004 */ +#define IFLAG_SYNC __IFL(Sync) /* 0x00000008 */ +#define IFLAG_IMMUTABLE __IFL(Immutable) /* 0x00000010 */ +#define IFLAG_APPEND __IFL(Append) /* 0x00000020 */ +#define IFLAG_NODUMP __IFL(NoDump) /* 0x00000040 */ +#define IFLAG_NOATIME __IFL(NoAtime) /* 0x00000080 */ +#define IFLAG_DIRTY __IFL(Dirty) /* 0x00000100 */ +#define IFLAG_COMPRBLK __IFL(ComprBlk) /* 0x00000200 */ +#define IFLAG_NOCOMP __IFL(NoComp) /* 0x00000400 */ +#define IFLAG_ECOMPR __IFL(Ecompr) /* 0x00000800 */ +#define IFLAG_BTREE __IFL(Btree) /* 0x00001000 */ +#define IFLAG_INDEX __IFL(Index) /* 0x00001000 */ +#define IFLAG_IMAGIC __IFL(Imagic) /* 0x00002000 */ +#define IFLAG_JOURNAL_DATA __IFL(JournalData) /* 0x00004000 */ +#define IFLAG_NOTAIL __IFL(NoTail) /* 0x00008000 */ +#define IFLAG_DIRSYNC __IFL(DirSync) /* 0x00010000 */ +#define IFLAG_TOPDIR __IFL(TopDir) /* 0x00020000 */ +#define IFLAG_DIRECTIO __IFL(DirectIO) /* 0x00040000 */ +#define IFLAG_INHERITDIRECTIO __IFL(InheritDirectIO) /* 0x00080000 */ +#define IFLAG_INHERITJDATA __IFL(InheritJdata) /* 0x00100000 */ +#define IFLAG_RESERVED __IFL(Reserved) /* 0x80000000 */ + +#ifdef __KERNEL__ +/** + * iflags_cvt + * @table: A table of 32 u32 flags + * @val: a 32 bit value to convert + * + * This function can be used to convert between IFLAGS values and + * the filesystem's own flags values. + * + * Returns: the converted flags + */ +static inline u32 iflags_cvt(const u32 *table, u32 val) +{ + u32 res = 0; + while(val) { + if (val & 1) + res |= *table; + table++; + val >>= 1; + } + return res; +} +#endif /* __KERNEL__ */ + +#endif /* _LINUX_IFLAGS_H */ -- cgit v1.2.3 From 4bcf7091f9da595016f9d1175aa1bea8e736566f Mon Sep 17 00:00:00 2001 From: Steven Whitehouse Date: Tue, 25 Apr 2006 13:20:27 -0400 Subject: [GFS2] Remove inherited flags from exported flags. We don't need the inherited flags since this action can be implied by setting the flags on directories where they wouldn't otherwise make sense. It reduces the number of extra flags by two. Also updated the list of flags to take account of one extra ext2/3 flag. Cc: Andreas Dilger Signed-off-by: Steven Whitehouse --- include/linux/iflags.h | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iflags.h b/include/linux/iflags.h index 1b4d9ef5d62b..5b27102dfeaf 100644 --- a/include/linux/iflags.h +++ b/include/linux/iflags.h @@ -46,9 +46,8 @@ enum { iflag_NoTail = 15, /* file tail should not be merged */ iflag_DirSync = 16, /* dirsync behaviour */ iflag_TopDir = 17, /* Top of directory hierarchies */ - iflag_DirectIO = 18, /* Always use direct I/O on this file */ - iflag_InheritDirectIO = 19, /* Set DirectIO on new files in dir */ - iflag_InheritJdata = 20, /* Set JournalData on create in dir */ + iflag_Extent = 19, /* Extents */ + iflag_DirectIO = 20, /* Always use direct I/O on this file */ iflag_Reserved = 31 /* reserved for ext2/3 lib */ }; @@ -72,9 +71,8 @@ enum { #define IFLAG_NOTAIL __IFL(NoTail) /* 0x00008000 */ #define IFLAG_DIRSYNC __IFL(DirSync) /* 0x00010000 */ #define IFLAG_TOPDIR __IFL(TopDir) /* 0x00020000 */ -#define IFLAG_DIRECTIO __IFL(DirectIO) /* 0x00040000 */ -#define IFLAG_INHERITDIRECTIO __IFL(InheritDirectIO) /* 0x00080000 */ -#define IFLAG_INHERITJDATA __IFL(InheritJdata) /* 0x00100000 */ +#define IFLAG_EXTENT __IFL(Extent) /* 0x00080000 */ +#define IFLAG_DIRECTIO __IFL(DirectIO) /* 0x00100000 */ #define IFLAG_RESERVED __IFL(Reserved) /* 0x80000000 */ #ifdef __KERNEL__ -- cgit v1.2.3 From 08bc2dbc7327e89b9d5b9c8ef9401d1df2622fca Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Fri, 28 Apr 2006 10:59:12 -0400 Subject: [GFS2] [-mm patch] fs/gfs2/: possible cleanups This patch contains the following possible cleanups: - make needlessly global code static - #if 0 unused functions - remove the following global function that was both unused and unimplemented: - super.c: gfs2_do_upgrade() Signed-off-by: Adrian Bunk Signed-off-by: Steven Whitehouse --- include/linux/gfs2_ondisk.h | 14 -------------- 1 file changed, 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfs2_ondisk.h b/include/linux/gfs2_ondisk.h index 3ab40917383f..4356e3864643 100644 --- a/include/linux/gfs2_ondisk.h +++ b/include/linux/gfs2_ondisk.h @@ -450,22 +450,8 @@ extern void gfs2_quota_change_in(struct gfs2_quota_change *qc, char *buf); /* Printing functions */ -extern void gfs2_inum_print(struct gfs2_inum *no); -extern void gfs2_meta_header_print(struct gfs2_meta_header *mh); -extern void gfs2_sb_print(struct gfs2_sb *sb); extern void gfs2_rindex_print(struct gfs2_rindex *ri); -extern void gfs2_rgrp_print(struct gfs2_rgrp *rg); -extern void gfs2_quota_print(struct gfs2_quota *qu); extern void gfs2_dinode_print(struct gfs2_dinode *di); -extern void gfs2_dirent_print(struct gfs2_dirent *de, char *name); -extern void gfs2_leaf_print(struct gfs2_leaf *lf); -extern void gfs2_ea_header_print(struct gfs2_ea_header *ea, char *name); -extern void gfs2_log_header_print(struct gfs2_log_header *lh); -extern void gfs2_log_descriptor_print(struct gfs2_log_descriptor *ld); -extern void gfs2_inum_range_print(struct gfs2_inum_range *ir); -extern void gfs2_statfs_change_print(struct gfs2_statfs_change *sc); -extern void gfs2_unlinked_tag_print(struct gfs2_unlinked_tag *ut); -extern void gfs2_quota_change_print(struct gfs2_quota_change *qc); #endif /* __KERNEL__ */ -- cgit v1.2.3 From 639b6d79b8c20cce4079fb035640c65456324d1c Mon Sep 17 00:00:00 2001 From: Ryan O'Hara Date: Mon, 22 May 2006 10:08:35 -0400 Subject: [GFS2] selinux support This adds support to GFS2 for selinux extended attributes. There is a known bug in gfs2_ea_get() which is believed to be independant of this patch. Further patches will follow once that bug is fixed in order to make GFS2 use as much of the generic eattr infrastructure as possible. Signed-off-by: Ryan O'Hara Signed-off-by: Steven Whitehouse --- include/linux/gfs2_ondisk.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/gfs2_ondisk.h b/include/linux/gfs2_ondisk.h index 4356e3864643..3893aac4e3ae 100644 --- a/include/linux/gfs2_ondisk.h +++ b/include/linux/gfs2_ondisk.h @@ -311,8 +311,9 @@ struct gfs2_leaf { #define GFS2_EATYPE_UNUSED 0 #define GFS2_EATYPE_USR 1 #define GFS2_EATYPE_SYS 2 +#define GFS2_EATYPE_SECURITY 3 -#define GFS2_EATYPE_LAST 2 +#define GFS2_EATYPE_LAST 3 #define GFS2_EATYPE_VALID(x) ((x) <= GFS2_EATYPE_LAST) #define GFS2_EAFLAG_LAST 0x01 /* last ea in block */ -- cgit v1.2.3 From 22da645fd6675b7abc55cf937ddf6132f343e5b9 Mon Sep 17 00:00:00 2001 From: Patrick Caulfield Date: Fri, 9 Jun 2006 16:14:20 -0400 Subject: [DLM] compat patch Here's a patch which add 32/64 bit compat to the DLM IOs and tidies the structures for alignment. As it causes an ABI change I had few qualms about adding the extra flag for "is64bit" as it simply uses a byte that would have been padding. Cc: David Woodhouse Signed-off-by: Patrick Caulfield Signed-off-by: Steven Whitehouse --- include/linux/dlm_device.h | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dlm_device.h b/include/linux/dlm_device.h index f8ba1981aa96..2a2dd189b9fd 100644 --- a/include/linux/dlm_device.h +++ b/include/linux/dlm_device.h @@ -18,35 +18,37 @@ #define DLM_USER_LVB_LEN 32 /* Version of the device interface */ -#define DLM_DEVICE_VERSION_MAJOR 4 +#define DLM_DEVICE_VERSION_MAJOR 5 #define DLM_DEVICE_VERSION_MINOR 0 #define DLM_DEVICE_VERSION_PATCH 0 /* struct passed to the lock write */ struct dlm_lock_params { __u8 mode; + __u8 namelen; __u16 flags; __u32 lkid; __u32 parent; - __u8 namelen; void __user *castparam; void __user *castaddr; void __user *bastparam; void __user *bastaddr; struct dlm_lksb __user *lksb; char lvb[DLM_USER_LVB_LEN]; - char name[1]; + char name[0]; }; struct dlm_lspace_params { __u32 flags; __u32 minor; - char name[1]; + char name[0]; }; struct dlm_write_request { __u32 version[3]; __u8 cmd; + __u8 is64bit; + __u8 unused[2]; union { struct dlm_lock_params lock; @@ -63,6 +65,7 @@ struct dlm_lock_result { struct dlm_lksb __user * user_lksb; struct dlm_lksb lksb; __u8 bast_mode; + __u8 unused[3]; /* Offsets may be zero if no data is present */ __u32 lvb_offset; }; -- cgit v1.2.3 From feaa7bba026c181ce071d5a4884f7f9dd26207a1 Mon Sep 17 00:00:00 2001 From: Steven Whitehouse Date: Wed, 14 Jun 2006 15:32:57 -0400 Subject: [GFS2] Fix unlinked file handling This patch fixes the way we have been dealing with unlinked, but still open files. It removes all limits (other than memory for inodes, as per every other filesystem) on numbers of these which we can support on GFS2. It also means that (like other fs) its the responsibility of the last process to close the file to deallocate the storage, rather than the person who did the unlinking. Note that with GFS2, those two events might take place on different nodes. Also there are a number of other changes: o We use the Linux inode subsystem as it was intended to be used, wrt allocating GFS2 inodes o The Linux inode cache is now the point which we use for local enforcement of only holding one copy of the inode in core at once (previous to this we used the glock layer). o We no longer use the unlinked "special" file. We just ignore it completely. This makes unlinking more efficient. o We now use the 4th block allocation state. The previously unused state is used to track unlinked but still open inodes. o gfs2_inoded is no longer needed o Several fields are now no longer needed (and removed) from the in core struct gfs2_inode o Several fields are no longer needed (and removed) from the in core superblock There are a number of future possible optimisations and clean ups which have been made possible by this patch. Signed-off-by: Steven Whitehouse --- include/linux/gfs2_ondisk.h | 34 ++++++++-------------------------- 1 file changed, 8 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfs2_ondisk.h b/include/linux/gfs2_ondisk.h index 3893aac4e3ae..1181da831939 100644 --- a/include/linux/gfs2_ondisk.h +++ b/include/linux/gfs2_ondisk.h @@ -1,11 +1,11 @@ /* -* Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. -* Copyright (C) 2004-2005 Red Hat, Inc. All rights reserved. -* -* This copyrighted material is made available to anyone wishing to use, -* modify, copy, or redistribute it subject to the terms and conditions -* of the GNU General Public License v.2. -*/ + * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. + * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. + * + * This copyrighted material is made available to anyone wishing to use, + * modify, copy, or redistribute it subject to the terms and conditions + * of the GNU General Public License v.2. + */ #ifndef __GFS2_ONDISK_DOT_H__ #define __GFS2_ONDISK_DOT_H__ @@ -36,7 +36,6 @@ #define GFS2_FORMAT_LB 1000 #define GFS2_FORMAT_EA 1600 #define GFS2_FORMAT_ED 1700 -#define GFS2_FORMAT_UT 1300 #define GFS2_FORMAT_QC 1400 /* These are format numbers for entities contained in files */ #define GFS2_FORMAT_RI 1100 @@ -80,7 +79,6 @@ static inline int gfs2_inum_equal(const struct gfs2_inum *ino1, #define GFS2_METATYPE_LB 12 #define GFS2_METATYPE_EA 10 #define GFS2_METATYPE_ED 11 -#define GFS2_METATYPE_UT 13 #define GFS2_METATYPE_QC 14 struct gfs2_meta_header { @@ -158,7 +156,7 @@ struct gfs2_rindex { #define GFS2_BLKST_FREE 0 #define GFS2_BLKST_USED 1 -#define GFS2_BLKST_INVALID 2 +#define GFS2_BLKST_UNLINKED 2 #define GFS2_BLKST_DINODE 3 #define GFS2_RGF_JOURNAL 0x00000001 @@ -396,20 +394,6 @@ struct gfs2_statfs_change { __be64 sc_dinodes; }; -/* - * Unlinked Tag - * Describes an allocated inode that isn't linked into - * the directory tree and might need to be deallocated. - */ - -#define GFS2_UTF_UNINIT 0x00000001 - -struct gfs2_unlinked_tag { - struct gfs2_inum ut_inum; - __be32 ut_flags; /* GFS2_UTF_... */ - __u32 __pad; -}; - /* * Quota change * Describes an allocation change for a particular @@ -445,8 +429,6 @@ extern void gfs2_inum_range_in(struct gfs2_inum_range *ir, char *buf); extern void gfs2_inum_range_out(struct gfs2_inum_range *ir, char *buf); extern void gfs2_statfs_change_in(struct gfs2_statfs_change *sc, char *buf); extern void gfs2_statfs_change_out(struct gfs2_statfs_change *sc, char *buf); -extern void gfs2_unlinked_tag_in(struct gfs2_unlinked_tag *ut, char *buf); -extern void gfs2_unlinked_tag_out(struct gfs2_unlinked_tag *ut, char *buf); extern void gfs2_quota_change_in(struct gfs2_quota_change *qc, char *buf); /* Printing functions */ -- cgit v1.2.3 From c37bb26654bb8981ea237076e333eb37d4aa2dc6 Mon Sep 17 00:00:00 2001 From: Dennis Munsie Date: Tue, 20 Jun 2006 14:55:55 -0400 Subject: intelfb: add preliminary i2c support [01/07] i2c: add intelfb bit algorithm id Adds the intelfb bit algorithm id to i2c-id.h. Signed-off-by: Dennis Munsie --- include/linux/i2c-id.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/i2c-id.h b/include/linux/i2c-id.h index c8b81f419fd8..cce6074dd754 100644 --- a/include/linux/i2c-id.h +++ b/include/linux/i2c-id.h @@ -189,6 +189,7 @@ #define I2C_HW_B_RADEON 0x01001e /* radeon framebuffer driver */ #define I2C_HW_B_EM28XX 0x01001f /* em28xx video capture cards */ #define I2C_HW_B_CX2341X 0x010020 /* Conexant CX2341X MPEG encoder cards */ +#define I2C_HW_B_INTELFB 0x010021 /* intel framebuffer driver */ /* --- PCF 8584 based algorithms */ #define I2C_HW_P_LP 0x020000 /* Parallel port interface */ -- cgit v1.2.3 From 3864caea2ed2b43bfc92e5cfbe001abe3f002a06 Mon Sep 17 00:00:00 2001 From: Steven Whitehouse Date: Wed, 5 Jul 2006 11:17:36 -0400 Subject: [GFS2] Kbuild update to install correct headers Now that the headers_instakll target is in Linus' kernel, this update ensures that the correct GFS2/DLM headers are installed. Signed-off-by: Steven Whitehouse --- include/linux/Kbuild | 33 +++++++++++++++++---------------- 1 file changed, 17 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/Kbuild b/include/linux/Kbuild index 2b8a7d68fae3..2121cde187d8 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -8,7 +8,7 @@ header-y += affs_fs.h affs_hardblocks.h aio_abi.h a.out.h arcfb.h \ atmppp.h atmsap.h atmsvc.h atm_zatm.h auto_fs4.h auxvec.h \ awe_voice.h ax25.h b1lli.h baycom.h bfs_fs.h blkpg.h \ bpqether.h cdk.h chio.h coda_psdev.h coff.h comstats.h \ - consolemap.h cycx_cfm.h dm-ioctl.h dn.h dqblk_v1.h \ + consolemap.h cycx_cfm.h dlm_device.h dm-ioctl.h dn.h dqblk_v1.h \ dqblk_v2.h dqblk_xfs.h efs_fs_sb.h elf-fdpic.h elf.h elf-em.h \ fadvise.h fd.h fdreg.h ftape-header-segment.h ftape-vendors.h \ fuse.h futex.h genetlink.h gen_stats.h gigaset_dev.h hdsmart.h \ @@ -18,28 +18,29 @@ header-y += affs_fs.h affs_hardblocks.h aio_abi.h a.out.h arcfb.h \ if_plip.h if_ppp.h if_slip.h if_strip.h if_tunnel.h in6.h \ in_route.h ioctl.h ip.h ipmi_msgdefs.h ip_mp_alg.h ipsec.h \ ipx.h irda.h isdn_divertif.h iso_fs.h ite_gpio.h ixjuser.h \ - jffs2.h keyctl.h limits.h major.h matroxfb.h meye.h minix_fs.h \ - mmtimer.h mqueue.h mtio.h ncp_no.h netfilter_arp.h netrom.h \ - nfs2.h nfs4_mount.h nfs_mount.h openprom_fs.h param.h \ - pci_ids.h pci_regs.h personality.h pfkeyv2.h pg.h pkt_cls.h \ - pkt_sched.h posix_types.h ppdev.h prctl.h ps2esdi.h qic117.h \ - qnxtypes.h quotaio_v1.h quotaio_v2.h radeonfb.h raw.h \ - resource.h rose.h sctp.h smbno.h snmp.h sockios.h som.h \ - sound.h stddef.h synclink.h telephony.h termios.h ticable.h \ - times.h tiocl.h tipc.h toshiba.h ultrasound.h un.h utime.h \ - utsname.h video_decoder.h video_encoder.h videotext.h vt.h \ - wavefront.h wireless.h xattr.h x25.h zorro_ids.h + jffs2.h keyctl.h limits.h lock_dlm_plock.h major.h matroxfb.h \ + meye.h minix_fs.h mmtimer.h mqueue.h mtio.h ncp_no.h \ + netfilter_arp.h netrom.h nfs2.h nfs4_mount.h nfs_mount.h \ + openprom_fs.h param.h pci_ids.h pci_regs.h personality.h \ + pfkeyv2.h pg.h pkt_cls.h pkt_sched.h posix_types.h ppdev.h \ + prctl.h ps2esdi.h qic117.h qnxtypes.h quotaio_v1.h quotaio_v2.h \ + radeonfb.h raw.h resource.h rose.h sctp.h smbno.h snmp.h \ + sockios.h som.h sound.h stddef.h synclink.h telephony.h \ + termios.h ticable.h times.h tiocl.h tipc.h toshiba.h \ + ultrasound.h un.h utime.h utsname.h video_decoder.h \ + video_encoder.h videotext.h vt.h wavefront.h wireless.h xattr.h \ + x25.h zorro_ids.h unifdef-y += acct.h adb.h adfs_fs.h agpgart.h apm_bios.h atalk.h \ atmarp.h atmdev.h atm.h atm_tcp.h audit.h auto_fs.h binfmts.h \ capability.h capi.h cciss_ioctl.h cdrom.h cm4000_cs.h \ cn_proc.h coda.h connector.h cramfs_fs.h cuda.h cyclades.h \ - dccp.h dirent.h divert.h elfcore.h errno.h errqueue.h \ + dccp.h dirent.h divert.h dlm.h elfcore.h errno.h errqueue.h \ ethtool.h eventpoll.h ext2_fs.h ext3_fs.h fb.h fcntl.h \ filter.h flat.h fs.h ftape.h gameport.h generic_serial.h \ - genhd.h hayesesp.h hdlcdrv.h hdlc.h hdreg.h hiddev.h hpet.h \ - i2c.h i2o-dev.h icmpv6.h if_bridge.h if_ec.h \ - if_eql.h if_ether.h if_frad.h if_ltalk.h if_pppox.h \ + genhd.h gfs2_ondisk.h hayesesp.h hdlcdrv.h hdlc.h hdreg.h \ + hiddev.h hpet.h i2c.h i2o-dev.h icmpv6.h iflags.h if_bridge.h \ + if_ec.h if_eql.h if_ether.h if_frad.h if_ltalk.h if_pppox.h \ if_shaper.h if_tr.h if_tun.h if_vlan.h if_wanpipe.h igmp.h \ inet_diag.h in.h inotify.h input.h ipc.h ipmi.h ipv6.h \ ipv6_route.h isdn.h isdnif.h isdn_ppp.h isicom.h jbd.h \ -- cgit v1.2.3 From 4340fe62531f7d1dafb6f5359ffe0378bdb0db80 Mon Sep 17 00:00:00 2001 From: Steven Whitehouse Date: Tue, 11 Jul 2006 09:46:33 -0400 Subject: [GFS2] Add generation number This adds a generation number for the eventual use of NFS to the ondisk inode. Its backward compatible with the current code since it doesn't really matter what the generation number is to start with, and indeed since its set to zero, due to it being taken from padding in both the inode and rgrp header, it should be fine. The eventual plan is to use this rather than no_formal_ino in the NFS filehandles. At that point no_formal_ino will be unused. At the same time we also add a releasepages call back to the "normal" address space for gfs2 inodes. Also I've removed a one-linrer function thats not required any more. Signed-off-by: Steven Whitehouse --- include/linux/gfs2_ondisk.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfs2_ondisk.h b/include/linux/gfs2_ondisk.h index 1181da831939..3ebd8743ce8c 100644 --- a/include/linux/gfs2_ondisk.h +++ b/include/linux/gfs2_ondisk.h @@ -170,8 +170,10 @@ struct gfs2_rgrp { __be32 rg_flags; __be32 rg_free; __be32 rg_dinodes; + __be32 __pad; + __be64 rg_igeneration; - __u8 rg_reserved[92]; /* Several fields from gfs1 now reserved */ + __u8 rg_reserved[80]; /* Several fields from gfs1 now reserved */ }; /* @@ -248,7 +250,7 @@ struct gfs2_dinode { */ __be64 di_goal_meta; /* rgrp to alloc from next */ __be64 di_goal_data; /* data block goal */ - __u32 __pad[2]; + __be64 di_generation; /* generation number for NFS */ __be32 di_flags; /* GFS2_DIF_... */ __be32 di_payload_format; /* GFS2_FORMAT_... */ -- cgit v1.2.3 From 509ca1a9383601fdc5612d3d3ba5b981f6eb6c8b Mon Sep 17 00:00:00 2001 From: Anssi Hannula Date: Wed, 19 Jul 2006 01:40:22 -0400 Subject: Input: implement new force feedback interface Implement a new force feedback interface, in which all non-driver-specific operations are separated to a common module. This includes handling effect type validations, locking, etc. The effects are now file descriptor specific instead of the previous strange half-process half-fd specific behaviour. The effect memory of devices is not emptied if the root user opens and closes the device while another user is using effects. This is a minor change and most likely no force feedback aware programs are affected by this negatively. Otherwise the userspace interface is left unaltered. Signed-off-by: Anssi Hannula Signed-off-by: Dmitry Torokhov --- include/linux/input.h | 61 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 61 insertions(+) (limited to 'include/linux') diff --git a/include/linux/input.h b/include/linux/input.h index b3253ab72ff7..81c6ea5afedb 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -784,6 +784,9 @@ struct ff_effect { #define FF_INERTIA 0x56 #define FF_RAMP 0x57 +#define FF_EFFECT_MIN FF_RUMBLE +#define FF_EFFECT_MAX FF_RAMP + /* * Force feedback periodic effect types */ @@ -795,6 +798,9 @@ struct ff_effect { #define FF_SAW_DOWN 0x5c #define FF_CUSTOM 0x5d +#define FF_WAVEFORM_MIN FF_SQUARE +#define FF_WAVEFORM_MAX FF_CUSTOM + /* * Set ff device properties */ @@ -870,6 +876,8 @@ struct input_dev { unsigned int keycodesize; void *keycode; + struct ff_device *ff; + unsigned int repeat_key; struct timer_list timer; @@ -1108,5 +1116,58 @@ static inline void input_set_abs_params(struct input_dev *dev, int axis, int min extern struct class input_class; +/** + * struct ff_device - force-feedback part of an input device + * @upload: Called to upload an new effect into device + * @erase: Called to erase an effect from device + * @playback: Called to request device to start playing specified effect + * @set_gain: Called to set specified gain + * @set_autocenter: Called to auto-center device + * @destroy: called by input core when parent input device is being + * destroyed + * @private: driver-specific data, will be freed automatically + * @ffbit: bitmap of force feedback capabilities truly supported by + * device (not emulated like ones in input_dev->ffbit) + * @mutex: mutex for serializing access to the device + * @max_effects: maximum number of effects supported by device + * @effects: pointer to an array of effects currently loaded into device + * @effect_owners: array of effect owners; when file handle owning + * an effect gets closed the effcet is automatically erased + * + * Every force-feedback device must implement upload() and playback() + * methods; erase() is optional. set_gain() and set_autocenter() need + * only be implemented if driver sets up FF_GAIN and FF_AUTOCENTER + * bits. + */ +struct ff_device { + int (*upload)(struct input_dev *dev, struct ff_effect *effect, + struct ff_effect *old); + int (*erase)(struct input_dev *dev, int effect_id); + + int (*playback)(struct input_dev *dev, int effect_id, int value); + void (*set_gain)(struct input_dev *dev, u16 gain); + void (*set_autocenter)(struct input_dev *dev, u16 magnitude); + + void (*destroy)(struct ff_device *); + + void *private; + + unsigned long ffbit[NBITS(FF_MAX)]; + + struct mutex mutex; + + int max_effects; + struct ff_effect *effects; + struct file *effect_owners[]; +}; + +int input_ff_create(struct input_dev *dev, int max_effects); +void input_ff_destroy(struct input_dev *dev); + +int input_ff_event(struct input_dev *dev, unsigned int type, unsigned int code, int value); + +int input_ff_upload(struct input_dev *dev, struct ff_effect *effect, struct file *file); +int input_ff_erase(struct input_dev *dev, int effect_id, struct file *file); + #endif #endif -- cgit v1.2.3 From 7d928a2b14eede1f333db7b7b684c57f7fa7f456 Mon Sep 17 00:00:00 2001 From: Anssi Hannula Date: Wed, 19 Jul 2006 01:40:30 -0400 Subject: Input: unified force feedback support for memoryless devices Consolidate core implementing memoryless devices in one module; added support for gain and envelopes and periodic => rumble conversion. Signed-off-by: Anssi Hannula Signed-off-by: Dmitry Torokhov --- include/linux/input.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/input.h b/include/linux/input.h index 81c6ea5afedb..d8b0c5610c04 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -1169,5 +1169,8 @@ int input_ff_event(struct input_dev *dev, unsigned int type, unsigned int code, int input_ff_upload(struct input_dev *dev, struct ff_effect *effect, struct file *file); int input_ff_erase(struct input_dev *dev, int effect_id, struct file *file); +int input_ff_create_memless(struct input_dev *dev, void *data, + int (*play_effect)(struct input_dev *, void *, struct ff_effect *)); + #endif #endif -- cgit v1.2.3 From ff462551235d8d7d843a005950bc90924fcedede Mon Sep 17 00:00:00 2001 From: Anssi Hannula Date: Wed, 19 Jul 2006 01:41:09 -0400 Subject: Input: uinput - switch to the new FF interface The userspace interface of the force feedback part is changed and documentation in uinput.h is updated accordingly. MODULE_VERSION is also incremented to reflect the revision. Signed-off-by: Anssi Hannula Signed-off-by: Dmitry Torokhov --- include/linux/uinput.h | 35 +++++++++++++++++++++++------------ 1 file changed, 23 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uinput.h b/include/linux/uinput.h index 7168302f9844..1fd61eeed664 100644 --- a/include/linux/uinput.h +++ b/include/linux/uinput.h @@ -22,12 +22,18 @@ * Author: Aristeu Sergio Rozanski Filho * * Changes/Revisions: + * 0.3 24/05/2006 (Anssi Hannula ) + * - update ff support for the changes in kernel interface + * - add UINPUT_VERSION * 0.2 16/10/2004 (Micah Dowty ) * - added force feedback support * - added UI_SET_PHYS * 0.1 20/06/2002 * - first public version */ + +#define UINPUT_VERSION 3 + #ifdef __KERNEL__ #define UINPUT_MINOR 223 #define UINPUT_NAME "uinput" @@ -45,7 +51,10 @@ struct uinput_request { union { int effect_id; - struct ff_effect* effect; + struct { + struct ff_effect *effect; + struct ff_effect *old; + } upload; } u; }; @@ -58,6 +67,7 @@ struct uinput_device { unsigned char head; unsigned char tail; struct input_event buff[UINPUT_BUFFER_SIZE]; + int ff_effects_max; struct uinput_request *requests[UINPUT_NUM_REQUESTS]; wait_queue_head_t requests_waitq; @@ -69,6 +79,7 @@ struct uinput_ff_upload { int request_id; int retval; struct ff_effect effect; + struct ff_effect old; }; struct uinput_ff_erase { @@ -98,33 +109,33 @@ struct uinput_ff_erase { #define UI_BEGIN_FF_ERASE _IOWR(UINPUT_IOCTL_BASE, 202, struct uinput_ff_erase) #define UI_END_FF_ERASE _IOW(UINPUT_IOCTL_BASE, 203, struct uinput_ff_erase) -/* To write a force-feedback-capable driver, the upload_effect +/* + * To write a force-feedback-capable driver, the upload_effect * and erase_effect callbacks in input_dev must be implemented. * The uinput driver will generate a fake input event when one of * these callbacks are invoked. The userspace code then uses * ioctls to retrieve additional parameters and send the return code. * The callback blocks until this return code is sent. * - * The described callback mechanism is only used if EV_FF is set. - * Otherwise, default implementations of upload_effect and erase_effect - * are used. + * The described callback mechanism is only used if ff_effects_max + * is set. * * To implement upload_effect(): - * 1. Wait for an event with type==EV_UINPUT and code==UI_FF_UPLOAD. + * 1. Wait for an event with type == EV_UINPUT and code == UI_FF_UPLOAD. * A request ID will be given in 'value'. * 2. Allocate a uinput_ff_upload struct, fill in request_id with * the 'value' from the EV_UINPUT event. * 3. Issue a UI_BEGIN_FF_UPLOAD ioctl, giving it the * uinput_ff_upload struct. It will be filled in with the - * ff_effect passed to upload_effect(). - * 4. Perform the effect upload, and place the modified ff_effect - * and a return code back into the uinput_ff_upload struct. + * ff_effects passed to upload_effect(). + * 4. Perform the effect upload, and place a return code back into + the uinput_ff_upload struct. * 5. Issue a UI_END_FF_UPLOAD ioctl, also giving it the * uinput_ff_upload_effect struct. This will complete execution * of our upload_effect() handler. * * To implement erase_effect(): - * 1. Wait for an event with type==EV_UINPUT and code==UI_FF_ERASE. + * 1. Wait for an event with type == EV_UINPUT and code == UI_FF_ERASE. * A request ID will be given in 'value'. * 2. Allocate a uinput_ff_erase struct, fill in request_id with * the 'value' from the EV_UINPUT event. @@ -133,13 +144,13 @@ struct uinput_ff_erase { * effect ID passed to erase_effect(). * 4. Perform the effect erasure, and place a return code back * into the uinput_ff_erase struct. - * and a return code back into the uinput_ff_erase struct. * 5. Issue a UI_END_FF_ERASE ioctl, also giving it the * uinput_ff_erase_effect struct. This will complete execution * of our erase_effect() handler. */ -/* This is the new event type, used only by uinput. +/* + * This is the new event type, used only by uinput. * 'code' is UI_FF_UPLOAD or UI_FF_ERASE, and 'value' * is the unique request ID. This number was picked * arbitrarily, above EV_MAX (since the input system -- cgit v1.2.3 From 1f734cb461e1f029d751deb15c8d9f8137fb2ca7 Mon Sep 17 00:00:00 2001 From: Anssi Hannula Date: Wed, 19 Jul 2006 01:44:08 -0400 Subject: Input: drop remnants of the old force-feedback interface Signed-off-by: Anssi Hannula Signed-off-by: Dmitry Torokhov --- include/linux/input.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/input.h b/include/linux/input.h index d8b0c5610c04..4405d0283549 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -870,7 +870,6 @@ struct input_dev { unsigned long sndbit[NBITS(SND_MAX)]; unsigned long ffbit[NBITS(FF_MAX)]; unsigned long swbit[NBITS(SW_MAX)]; - int ff_effects_max; unsigned int keycodemax; unsigned int keycodesize; @@ -903,8 +902,6 @@ struct input_dev { void (*close)(struct input_dev *dev); int (*flush)(struct input_dev *dev, struct file *file); int (*event)(struct input_dev *dev, unsigned int type, unsigned int code, int value); - int (*upload_effect)(struct input_dev *dev, struct ff_effect *effect); - int (*erase_effect)(struct input_dev *dev, int effect_id); struct input_handle *grab; @@ -1078,11 +1075,6 @@ static inline void input_report_abs(struct input_dev *dev, unsigned int code, in input_event(dev, EV_ABS, code, value); } -static inline void input_report_ff(struct input_dev *dev, unsigned int code, int value) -{ - input_event(dev, EV_FF, code, value); -} - static inline void input_report_ff_status(struct input_dev *dev, unsigned int code, int value) { input_event(dev, EV_FF_STATUS, code, value); -- cgit v1.2.3 From 8b8277a17477de38d8df6783e8221aed55bab300 Mon Sep 17 00:00:00 2001 From: Anssi Hannula Date: Wed, 19 Jul 2006 01:44:22 -0400 Subject: Input: update the force feedback documentation Signed-off-by: Anssi Hannula Signed-off-by: Dmitry Torokhov --- include/linux/input.h | 175 +++++++++++++++++++++++++++++++++++--------------- 1 file changed, 122 insertions(+), 53 deletions(-) (limited to 'include/linux') diff --git a/include/linux/input.h b/include/linux/input.h index 4405d0283549..a7a1f55a5eed 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -667,98 +667,167 @@ struct input_absinfo { /* * Structures used in ioctls to upload effects to a device - * The first structures are not passed directly by using ioctls. - * They are sub-structures of the actually sent structure (called ff_effect) + * They are pieces of a bigger structure (called ff_effect) */ +/* + * All duration values are expressed in ms. Values above 32767 ms (0x7fff) + * should not be used and have unspecified results. + */ + +/** + * struct ff_replay - defines scheduling of the effect + * @length: duration of the effect + * @delay: delay before effect should start playing + */ struct ff_replay { - __u16 length; /* Duration of an effect in ms. All other times are also expressed in ms */ - __u16 delay; /* Time to wait before to start playing an effect */ + __u16 length; + __u16 delay; }; +/** + * struct ff_trigger - defines what triggers the effect + * @button: number of the button triggering the effect + * @interval: controls how soon the effect can be re-triggered + */ struct ff_trigger { - __u16 button; /* Number of button triggering an effect */ - __u16 interval; /* Time to wait before an effect can be re-triggered (ms) */ + __u16 button; + __u16 interval; }; +/** + * struct ff_envelope - generic effect envelope + * @attack_length: duration of the attack (ms) + * @attack_level: level at the beginning of the attack + * @fade_length: duration of fade (ms) + * @fade_level: level at the end of fade + * + * The @attack_level and @fade_level are absolute values; when applying + * envelope force-feedback core will convert to positive/negative + * value based on polarity of the default level of the effect. + * Valid range for the attack and fade levels is 0x0000 - 0x7fff + */ struct ff_envelope { - __u16 attack_length; /* Duration of attack (ms) */ - __u16 attack_level; /* Level at beginning of attack */ - __u16 fade_length; /* Duration of fade (ms) */ - __u16 fade_level; /* Level at end of fade */ + __u16 attack_length; + __u16 attack_level; + __u16 fade_length; + __u16 fade_level; }; -/* FF_CONSTANT */ +/** + * struct ff_constant_effect - defines parameters of a constant effect + * @level: strength of the effect; may be negative + * @envelope: envelope data + */ struct ff_constant_effect { - __s16 level; /* Strength of effect. Negative values are OK */ + __s16 level; struct ff_envelope envelope; }; -/* FF_RAMP */ +/** + * struct ff_ramp_effect - defines parameters of a ramp effect + * @start_level: beginning strength of the effect; may be negative + * @end_level: final strength of the effect; may be negative + * @envelope: envelope data + */ struct ff_ramp_effect { __s16 start_level; __s16 end_level; struct ff_envelope envelope; }; -/* FF_SPRING of FF_FRICTION */ +/** + * struct ff_condition_effect - defines a spring or friction effect + * @right_saturation: maximum level when joystick moved all way to the right + * @left_saturation: same for the left side + * @right_coeff: controls how fast the force grows when the joystick moves + * to the right + * @left_coeff: same for the left side + * @deadband: size of the dead zone, where no force is produced + * @center: position of the dead zone + */ struct ff_condition_effect { - __u16 right_saturation; /* Max level when joystick is on the right */ - __u16 left_saturation; /* Max level when joystick in on the left */ + __u16 right_saturation; + __u16 left_saturation; - __s16 right_coeff; /* Indicates how fast the force grows when the - joystick moves to the right */ - __s16 left_coeff; /* Same for left side */ - - __u16 deadband; /* Size of area where no force is produced */ - __s16 center; /* Position of dead zone */ + __s16 right_coeff; + __s16 left_coeff; + __u16 deadband; + __s16 center; }; -/* FF_PERIODIC */ +/** + * struct ff_periodic_effect - defines parameters of a periodic effect + * @waveform: kind of the effect (wave) + * @period: period of the wave (ms) + * @magnitude: peak value + * @offset: mean value of the wave (roughly) + * @phase: 'horizontal' shift + * @envelope: envelope data + * @custom_len: number of samples (FF_CUSTOM only) + * @custom_data: buffer of samples (FF_CUSTOM only) + * + * Known waveforms - FF_SQUARE, FF_TRIANGLE, FF_SINE, FF_SAW_UP, + * FF_SAW_DOWN, FF_CUSTOM. The exact syntax FF_CUSTOM is undefined + * for the time being as no driver supports it yet. + * + * Note: the data pointed by custom_data is copied by the driver. + * You can therefore dispose of the memory after the upload/update. + */ struct ff_periodic_effect { - __u16 waveform; /* Kind of wave (sine, square...) */ - __u16 period; /* in ms */ - __s16 magnitude; /* Peak value */ - __s16 offset; /* Mean value of wave (roughly) */ - __u16 phase; /* 'Horizontal' shift */ + __u16 waveform; + __u16 period; + __s16 magnitude; + __s16 offset; + __u16 phase; struct ff_envelope envelope; -/* Only used if waveform == FF_CUSTOM */ - __u32 custom_len; /* Number of samples */ - __s16 *custom_data; /* Buffer of samples */ -/* Note: the data pointed by custom_data is copied by the driver. You can - * therefore dispose of the memory after the upload/update */ + __u32 custom_len; + __s16 *custom_data; }; -/* FF_RUMBLE */ -/* Some rumble pads have two motors of different weight. - strong_magnitude represents the magnitude of the vibration generated - by the heavy motor. -*/ +/** + * struct ff_rumble_effect - defines parameters of a periodic effect + * @strong_magnitude: magnitude of the heavy motor + * @weak_magnitude: magnitude of the light one + * + * Some rumble pads have two motors of different weight. Strong_magnitude + * represents the magnitude of the vibration generated by the heavy one. + */ struct ff_rumble_effect { - __u16 strong_magnitude; /* Magnitude of the heavy motor */ - __u16 weak_magnitude; /* Magnitude of the light one */ + __u16 strong_magnitude; + __u16 weak_magnitude; }; -/* - * Structure sent through ioctl from the application to the driver +/** + * struct ff_effect - defines force feedback effect + * @type: type of the effect (FF_CONSTANT, FF_PERIODIC, FF_RAMP, FF_SPRING, + * FF_FRICTION, FF_DAMPER, FF_RUMBLE, FF_INERTIA, or FF_CUSTOM) + * @id: an unique id assigned to an effect + * @direction: direction of the effect + * @trigger: trigger conditions (struct ff_trigger) + * @replay: scheduling of the effect (struct ff_replay) + * @u: effect-specific structure (one of ff_constant_effect, ff_ramp_effect, + * ff_periodic_effect, ff_condition_effect, ff_rumble_effect) further + * defining effect parameters + * + * This structure is sent through ioctl from the application to the driver. + * To create a new effect aplication should set its @id to -1; the kernel + * will return assigned @id which can later be used to update or delete + * this effect. + * + * Direction of the effect is encoded as follows: + * 0 deg -> 0x0000 (down) + * 90 deg -> 0x4000 (left) + * 180 deg -> 0x8000 (up) + * 270 deg -> 0xC000 (right) */ struct ff_effect { __u16 type; -/* Following field denotes the unique id assigned to an effect. - * If user sets if to -1, a new effect is created, and its id is returned in the same field - * Else, the user sets it to the effect id it wants to update. - */ __s16 id; - - __u16 direction; /* Direction. 0 deg -> 0x0000 (down) - 90 deg -> 0x4000 (left) - 180 deg -> 0x8000 (up) - 270 deg -> 0xC000 (right) - */ - + __u16 direction; struct ff_trigger trigger; struct ff_replay replay; -- cgit v1.2.3 From de9b75d31e81e87685d8cc70052a003c654f1e8e Mon Sep 17 00:00:00 2001 From: David Teigland Date: Fri, 28 Jul 2006 14:00:20 -0500 Subject: [GFS2] add plock owner We need to use fl_owner instead of fl_pid to track the owner of a posix lock. Pass the owner value out to user space where cluster plocks are managed. Signed-off-by: David Teigland Signed-off-by: Steven Whitehouse --- include/linux/lock_dlm_plock.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/lock_dlm_plock.h b/include/linux/lock_dlm_plock.h index 007b07a178ab..fc3415113973 100644 --- a/include/linux/lock_dlm_plock.h +++ b/include/linux/lock_dlm_plock.h @@ -12,7 +12,7 @@ #define GDLM_PLOCK_MISC_NAME "lock_dlm_plock" #define GDLM_PLOCK_VERSION_MAJOR 1 -#define GDLM_PLOCK_VERSION_MINOR 0 +#define GDLM_PLOCK_VERSION_MINOR 1 #define GDLM_PLOCK_VERSION_PATCH 0 enum { @@ -34,6 +34,7 @@ struct gdlm_plock_info { __u64 number; __u64 start; __u64 end; + __u64 owner; }; #endif -- cgit v1.2.3 From ee4799997950e81437ef9055a4b104099e3272c4 Mon Sep 17 00:00:00 2001 From: Rick Koch Date: Sat, 5 Aug 2006 00:32:18 -0400 Subject: Input: add driver for Penmount serial touchscreens Signed-off-by: Rick Koch Signed-off-by: Dmitry Torokhov --- include/linux/serio.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/serio.h b/include/linux/serio.h index 6348e8330897..ad546a0205c6 100644 --- a/include/linux/serio.h +++ b/include/linux/serio.h @@ -217,5 +217,6 @@ static inline void serio_unpin_driver(struct serio *serio) #define SERIO_LKKBD 0x28 #define SERIO_ELO 0x29 #define SERIO_MICROTOUCH 0x30 +#define SERIO_PENMOUNT 0x31 #endif -- cgit v1.2.3 From 4003dff41e65ad338a60dde90019bffcb5531fb6 Mon Sep 17 00:00:00 2001 From: Rick Koch Date: Sat, 5 Aug 2006 00:32:24 -0400 Subject: Input: add driver for Touchright serial touchscreens Signed-off-by: Rick Koch Signed-off-by: Dmitry Torokhov --- include/linux/serio.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/serio.h b/include/linux/serio.h index ad546a0205c6..152606413158 100644 --- a/include/linux/serio.h +++ b/include/linux/serio.h @@ -218,5 +218,6 @@ static inline void serio_unpin_driver(struct serio *serio) #define SERIO_ELO 0x29 #define SERIO_MICROTOUCH 0x30 #define SERIO_PENMOUNT 0x31 +#define SERIO_TOUCHRIGHT 0x32 #endif -- cgit v1.2.3 From 11ea3173d5f2de71d037ef58ac43395795fed2bc Mon Sep 17 00:00:00 2001 From: Rick Koch Date: Sat, 5 Aug 2006 00:32:30 -0400 Subject: Input: add driver for Touchwin serial touchscreens Signed-off-by: Rick Koch Signed-off-by: Dmitry Torokhov --- include/linux/serio.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/serio.h b/include/linux/serio.h index 152606413158..c9069310b6ac 100644 --- a/include/linux/serio.h +++ b/include/linux/serio.h @@ -219,5 +219,6 @@ static inline void serio_unpin_driver(struct serio *serio) #define SERIO_MICROTOUCH 0x30 #define SERIO_PENMOUNT 0x31 #define SERIO_TOUCHRIGHT 0x32 +#define SERIO_TOUCHWIN 0x33 #endif -- cgit v1.2.3 From 38c60ef228596c8e331437ea9287ce035706b107 Mon Sep 17 00:00:00 2001 From: Steven Whitehouse Date: Mon, 4 Sep 2006 14:48:37 -0400 Subject: [GFS2] Use const in endian conversion routines Use const in endian conversion and printing of on-disk structures. Cc: Jan Engelhardt Signed-off-by: Steven Whitehouse --- include/linux/gfs2_ondisk.h | 42 +++++++++++++++++++++--------------------- 1 file changed, 21 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfs2_ondisk.h b/include/linux/gfs2_ondisk.h index 3ebd8743ce8c..a7ae7c177cac 100644 --- a/include/linux/gfs2_ondisk.h +++ b/include/linux/gfs2_ondisk.h @@ -413,30 +413,30 @@ struct gfs2_quota_change { #ifdef __KERNEL__ /* Translation functions */ -extern void gfs2_inum_in(struct gfs2_inum *no, char *buf); -extern void gfs2_inum_out(const struct gfs2_inum *no, char *buf); -extern void gfs2_sb_in(struct gfs2_sb *sb, char *buf); -extern void gfs2_rindex_in(struct gfs2_rindex *ri, char *buf); -extern void gfs2_rindex_out(struct gfs2_rindex *ri, char *buf); -extern void gfs2_rgrp_in(struct gfs2_rgrp *rg, char *buf); -extern void gfs2_rgrp_out(struct gfs2_rgrp *rg, char *buf); -extern void gfs2_quota_in(struct gfs2_quota *qu, char *buf); -extern void gfs2_quota_out(struct gfs2_quota *qu, char *buf); -extern void gfs2_dinode_in(struct gfs2_dinode *di, char *buf); -extern void gfs2_dinode_out(struct gfs2_dinode *di, char *buf); -extern void gfs2_ea_header_in(struct gfs2_ea_header *ea, char *buf); -extern void gfs2_ea_header_out(struct gfs2_ea_header *ea, char *buf); -extern void gfs2_log_header_in(struct gfs2_log_header *lh, char *buf); -extern void gfs2_inum_range_in(struct gfs2_inum_range *ir, char *buf); -extern void gfs2_inum_range_out(struct gfs2_inum_range *ir, char *buf); -extern void gfs2_statfs_change_in(struct gfs2_statfs_change *sc, char *buf); -extern void gfs2_statfs_change_out(struct gfs2_statfs_change *sc, char *buf); -extern void gfs2_quota_change_in(struct gfs2_quota_change *qc, char *buf); +extern void gfs2_inum_in(struct gfs2_inum *no, const void *buf); +extern void gfs2_inum_out(const struct gfs2_inum *no, void *buf); +extern void gfs2_sb_in(struct gfs2_sb *sb, const void *buf); +extern void gfs2_rindex_in(struct gfs2_rindex *ri, const void *buf); +extern void gfs2_rindex_out(const struct gfs2_rindex *ri, void *buf); +extern void gfs2_rgrp_in(struct gfs2_rgrp *rg, const void *buf); +extern void gfs2_rgrp_out(const struct gfs2_rgrp *rg, void *buf); +extern void gfs2_quota_in(struct gfs2_quota *qu, const void *buf); +extern void gfs2_quota_out(const struct gfs2_quota *qu, void *buf); +extern void gfs2_dinode_in(struct gfs2_dinode *di, const void *buf); +extern void gfs2_dinode_out(const struct gfs2_dinode *di, void *buf); +extern void gfs2_ea_header_in(struct gfs2_ea_header *ea, const void *buf); +extern void gfs2_ea_header_out(const struct gfs2_ea_header *ea, void *buf); +extern void gfs2_log_header_in(struct gfs2_log_header *lh, const void *buf); +extern void gfs2_inum_range_in(struct gfs2_inum_range *ir, const void *buf); +extern void gfs2_inum_range_out(const struct gfs2_inum_range *ir, void *buf); +extern void gfs2_statfs_change_in(struct gfs2_statfs_change *sc, const void *buf); +extern void gfs2_statfs_change_out(const struct gfs2_statfs_change *sc, void *buf); +extern void gfs2_quota_change_in(struct gfs2_quota_change *qc, const void *buf); /* Printing functions */ -extern void gfs2_rindex_print(struct gfs2_rindex *ri); -extern void gfs2_dinode_print(struct gfs2_dinode *di); +extern void gfs2_rindex_print(const struct gfs2_rindex *ri); +extern void gfs2_dinode_print(const struct gfs2_dinode *di); #endif /* __KERNEL__ */ -- cgit v1.2.3 From 9807879bfdc0c2b5106b4b378f5475c6a333d853 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Thu, 14 Sep 2006 01:31:27 -0400 Subject: Input: atkbd - support Microsoft Natural Elite Pro keyboards Microsoft Natural Elite Pro keyboard produces unisual response to the GET ID command - single byte 0xaa (normally keyboards produce 2-byte response). Fail GET ID command so atkbd gets a change to do alternate probe. Signed-off-by: Dmitry Torokhov --- include/linux/libps2.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/libps2.h b/include/linux/libps2.h index 08a450a9dbf7..f6f301e2b0f5 100644 --- a/include/linux/libps2.h +++ b/include/linux/libps2.h @@ -47,5 +47,6 @@ int ps2_schedule_command(struct ps2dev *ps2dev, unsigned char *param, int comman int ps2_handle_ack(struct ps2dev *ps2dev, unsigned char data); int ps2_handle_response(struct ps2dev *ps2dev, unsigned char data); void ps2_cmd_aborted(struct ps2dev *ps2dev); +int ps2_is_keyboard_id(char id); #endif /* _LIBPS2_H */ -- cgit v1.2.3 From 66e66118837ed95a299328437c2d9fb4b5137352 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Thu, 14 Sep 2006 01:31:59 -0400 Subject: Input: constify input core Signed-off-by: Dmitry Torokhov --- include/linux/input.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/input.h b/include/linux/input.h index a7a1f55a5eed..300036b7755a 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -1059,16 +1059,16 @@ struct input_handler { void *private; void (*event)(struct input_handle *handle, unsigned int type, unsigned int code, int value); - struct input_handle* (*connect)(struct input_handler *handler, struct input_dev *dev, struct input_device_id *id); + struct input_handle* (*connect)(struct input_handler *handler, struct input_dev *dev, const struct input_device_id *id); void (*disconnect)(struct input_handle *handle); void (*start)(struct input_handle *handle); const struct file_operations *fops; int minor; - char *name; + const char *name; - struct input_device_id *id_table; - struct input_device_id *blacklist; + const struct input_device_id *id_table; + const struct input_device_id *blacklist; struct list_head h_list; struct list_head node; @@ -1079,7 +1079,7 @@ struct input_handle { void *private; int open; - char *name; + const char *name; struct input_dev *dev; struct input_handler *handler; -- cgit v1.2.3 From 68c2a1607cd6dd12427c9566b39756e92708713c Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Thu, 14 Sep 2006 01:32:28 -0400 Subject: Input: remove cruft that was needed for transition to sysfs Signed-off-by: Dmitry Torokhov --- include/linux/input.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/input.h b/include/linux/input.h index 300036b7755a..155b2bc96842 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -978,9 +978,6 @@ struct input_dev { unsigned int users; struct class_device cdev; - struct device *dev; /* will be removed soon */ - - int dynalloc; /* temporarily */ struct list_head h_list; struct list_head node; @@ -1093,12 +1090,6 @@ struct input_handle { #define to_handle(n) container_of(n,struct input_handle,d_node) #define to_handle_h(n) container_of(n,struct input_handle,h_node) -static inline void init_input_dev(struct input_dev *dev) -{ - INIT_LIST_HEAD(&dev->h_list); - INIT_LIST_HEAD(&dev->node); -} - struct input_dev *input_allocate_device(void); void input_free_device(struct input_dev *dev); -- cgit v1.2.3 From 4263cf0fac28122c8381b6f4f9441a43cd93c81f Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Thu, 14 Sep 2006 01:32:39 -0400 Subject: Input: make input_register_handler() return error codes Signed-off-by: Dmitry Torokhov --- include/linux/input.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/input.h b/include/linux/input.h index 155b2bc96842..7025432350fa 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -1106,7 +1106,7 @@ static inline void input_put_device(struct input_dev *dev) int input_register_device(struct input_dev *); void input_unregister_device(struct input_dev *); -void input_register_handler(struct input_handler *); +int input_register_handler(struct input_handler *); void input_unregister_handler(struct input_handler *); int input_grab_device(struct input_handle *); -- cgit v1.2.3 From 132919ba80ad207755fe271277bfefff865a54fe Mon Sep 17 00:00:00 2001 From: Russell King Date: Sun, 27 Aug 2006 13:56:52 +0100 Subject: [MMC] Remove data->blksz_bits member data->blksz_bits is unused now - remove it. Signed-off-by: Russell King --- include/linux/mmc/mmc.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmc/mmc.h b/include/linux/mmc/mmc.h index 627e2c08ce41..a3594dfd6963 100644 --- a/include/linux/mmc/mmc.h +++ b/include/linux/mmc/mmc.h @@ -68,7 +68,6 @@ struct mmc_command { struct mmc_data { unsigned int timeout_ns; /* data timeout (in ns, max 80ms) */ unsigned int timeout_clks; /* data timeout (in clocks) */ - unsigned int blksz_bits; /* data block size */ unsigned int blksz; /* data block size */ unsigned int blocks; /* number of blocks */ unsigned int error; /* data error */ -- cgit v1.2.3 From db53f28b3a6d9338cca1b7e917dc063ac99e1871 Mon Sep 17 00:00:00 2001 From: Russell King Date: Wed, 30 Aug 2006 15:14:56 +0100 Subject: [MMC] Add multi block-write capability Add a capability flag for drivers to set when they can perform multi- block transfers to cards _and_ correctly report the number of bytes transferred should an error occur. The last point is very important - if a driver reports more bytes than were actually accepted by the card and an error occurs, there is the possibility for data loss. Pierre Ossman provided the patch for wbsd and sdhci. Signed-off-by: Pierre Ossman Signed-off-by: Russell King --- include/linux/mmc/host.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index ba095aebedff..b282ec9bba08 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -85,6 +85,7 @@ struct mmc_host { unsigned long caps; /* Host capabilities */ #define MMC_CAP_4_BIT_DATA (1 << 0) /* Can the host do 4 bit transfers */ +#define MMC_CAP_MULTIWRITE (1 << 1) /* Can accurately report bytes sent to card on error */ /* host specific block data */ unsigned int max_seg_size; /* see blk_queue_max_segment_size */ -- cgit v1.2.3 From 9a87fdded5742a9d14780e5dfd9c940d7862e0ec Mon Sep 17 00:00:00 2001 From: Michael Hanselmann Date: Tue, 19 Sep 2006 01:59:49 -0400 Subject: Input: add new BUS_VIRTUAL bus type BUS_VIRTUAL can be used when creating virtual devices using uinput driver. Note that when uinput is used to drive a real piece of hardware "real" bus type (such as BUS_USB, BUS_BLUETOOTH) should be specified. Signed-off-by: Michael Hanselmann Signed-off-by: Dmitry Torokhov --- include/linux/input.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/input.h b/include/linux/input.h index 7025432350fa..22a361040547 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -645,6 +645,7 @@ struct input_absinfo { #define BUS_USB 0x03 #define BUS_HIL 0x04 #define BUS_BLUETOOTH 0x05 +#define BUS_VIRTUAL 0x06 #define BUS_ISA 0x10 #define BUS_I8042 0x11 -- cgit v1.2.3 From 90da11514562020ea7d697982f912ac949adc317 Mon Sep 17 00:00:00 2001 From: Lennart Poettering Date: Tue, 19 Sep 2006 01:59:55 -0400 Subject: Input: add KEY_BLUETOOTH and KEY_WLAN definitions Some laptops have separate "rfkill" buttons for disabling/enabling Bluetooth and WLAN. Signed-off-by: Lennart Poettering Signed-off-by: Dmitry Torokhov --- include/linux/input.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/input.h b/include/linux/input.h index 22a361040547..5770105471dd 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -349,6 +349,9 @@ struct input_absinfo { #define KEY_BATTERY 236 +#define KEY_BLUETOOTH 237 +#define KEY_WLAN 238 + #define KEY_UNKNOWN 240 #define BTN_MISC 0x100 -- cgit v1.2.3 From 7d308590ae60d1f038a54a94e78a385c5c163452 Mon Sep 17 00:00:00 2001 From: Fabio Massimo Di Nitto Date: Tue, 19 Sep 2006 07:56:29 +0200 Subject: [GFS2] Export lm_interface to kernel headers lm_interface.h has a few out of the tree clients such as GFS1 and userland tools. Right now, these clients keeps a copy of the file in their build tree that can go out of sync. Move lm_interface.h to include/linux, export it to userland and clean up fs/gfs2 to use the new location. Signed-off-by: Fabio M. Di Nitto Signed-off-by: Steven Whitehouse --- include/linux/Kbuild | 6 +- include/linux/lm_interface.h | 273 +++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 276 insertions(+), 3 deletions(-) create mode 100644 include/linux/lm_interface.h (limited to 'include/linux') diff --git a/include/linux/Kbuild b/include/linux/Kbuild index 2121cde187d8..d8e720f9c21a 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -45,9 +45,9 @@ unifdef-y += acct.h adb.h adfs_fs.h agpgart.h apm_bios.h atalk.h \ inet_diag.h in.h inotify.h input.h ipc.h ipmi.h ipv6.h \ ipv6_route.h isdn.h isdnif.h isdn_ppp.h isicom.h jbd.h \ joystick.h kdev_t.h kd.h kernelcapi.h kernel.h keyboard.h \ - llc.h loop.h lp.h mempolicy.h mii.h mman.h mroute.h msdos_fs.h \ - msg.h nbd.h ncp_fs.h ncp.h ncp_mount.h netdevice.h \ - netfilter_bridge.h netfilter_decnet.h netfilter.h \ + llc.h lm_interface.h loop.h lp.h mempolicy.h mii.h mman.h \ + mroute.h msdos_fs.h msg.h nbd.h ncp_fs.h ncp.h ncp_mount.h \ + netdevice.h netfilter_bridge.h netfilter_decnet.h netfilter.h \ netfilter_ipv4.h netfilter_ipv6.h netfilter_logging.h net.h \ netlink.h nfs3.h nfs4.h nfsacl.h nfs_fs.h nfs.h nfs_idmap.h \ n_r3964.h nubus.h nvram.h parport.h patchkey.h pci.h pktcdvd.h \ diff --git a/include/linux/lm_interface.h b/include/linux/lm_interface.h new file mode 100644 index 000000000000..1418fdc9ac02 --- /dev/null +++ b/include/linux/lm_interface.h @@ -0,0 +1,273 @@ +/* + * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. + * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. + * + * This copyrighted material is made available to anyone wishing to use, + * modify, copy, or redistribute it subject to the terms and conditions + * of the GNU General Public License version 2. + */ + +#ifndef __LM_INTERFACE_DOT_H__ +#define __LM_INTERFACE_DOT_H__ + + +typedef void (*lm_callback_t) (void *ptr, unsigned int type, void *data); + +/* + * lm_mount() flags + * + * LM_MFLAG_SPECTATOR + * GFS is asking to join the filesystem's lockspace, but it doesn't want to + * modify the filesystem. The lock module shouldn't assign a journal to the FS + * mount. It shouldn't send recovery callbacks to the FS mount. If the node + * dies or withdraws, all locks can be wiped immediately. + */ + +#define LM_MFLAG_SPECTATOR 0x00000001 + +/* + * lm_lockstruct flags + * + * LM_LSFLAG_LOCAL + * The lock_nolock module returns LM_LSFLAG_LOCAL to GFS, indicating that GFS + * can make single-node optimizations. + */ + +#define LM_LSFLAG_LOCAL 0x00000001 + +/* + * lm_lockname types + */ + +#define LM_TYPE_RESERVED 0x00 +#define LM_TYPE_NONDISK 0x01 +#define LM_TYPE_INODE 0x02 +#define LM_TYPE_RGRP 0x03 +#define LM_TYPE_META 0x04 +#define LM_TYPE_IOPEN 0x05 +#define LM_TYPE_FLOCK 0x06 +#define LM_TYPE_PLOCK 0x07 +#define LM_TYPE_QUOTA 0x08 +#define LM_TYPE_JOURNAL 0x09 + +/* + * lm_lock() states + * + * SHARED is compatible with SHARED, not with DEFERRED or EX. + * DEFERRED is compatible with DEFERRED, not with SHARED or EX. + */ + +#define LM_ST_UNLOCKED 0 +#define LM_ST_EXCLUSIVE 1 +#define LM_ST_DEFERRED 2 +#define LM_ST_SHARED 3 + +/* + * lm_lock() flags + * + * LM_FLAG_TRY + * Don't wait to acquire the lock if it can't be granted immediately. + * + * LM_FLAG_TRY_1CB + * Send one blocking callback if TRY is set and the lock is not granted. + * + * LM_FLAG_NOEXP + * GFS sets this flag on lock requests it makes while doing journal recovery. + * These special requests should not be blocked due to the recovery like + * ordinary locks would be. + * + * LM_FLAG_ANY + * A SHARED request may also be granted in DEFERRED, or a DEFERRED request may + * also be granted in SHARED. The preferred state is whichever is compatible + * with other granted locks, or the specified state if no other locks exist. + * + * LM_FLAG_PRIORITY + * Override fairness considerations. Suppose a lock is held in a shared state + * and there is a pending request for the deferred state. A shared lock + * request with the priority flag would be allowed to bypass the deferred + * request and directly join the other shared lock. A shared lock request + * without the priority flag might be forced to wait until the deferred + * requested had acquired and released the lock. + */ + +#define LM_FLAG_TRY 0x00000001 +#define LM_FLAG_TRY_1CB 0x00000002 +#define LM_FLAG_NOEXP 0x00000004 +#define LM_FLAG_ANY 0x00000008 +#define LM_FLAG_PRIORITY 0x00000010 + +/* + * lm_lock() and lm_async_cb return flags + * + * LM_OUT_ST_MASK + * Masks the lower two bits of lock state in the returned value. + * + * LM_OUT_CACHEABLE + * The lock hasn't been released so GFS can continue to cache data for it. + * + * LM_OUT_CANCELED + * The lock request was canceled. + * + * LM_OUT_ASYNC + * The result of the request will be returned in an LM_CB_ASYNC callback. + */ + +#define LM_OUT_ST_MASK 0x00000003 +#define LM_OUT_CACHEABLE 0x00000004 +#define LM_OUT_CANCELED 0x00000008 +#define LM_OUT_ASYNC 0x00000080 +#define LM_OUT_ERROR 0x00000100 + +/* + * lm_callback_t types + * + * LM_CB_NEED_E LM_CB_NEED_D LM_CB_NEED_S + * Blocking callback, a remote node is requesting the given lock in + * EXCLUSIVE, DEFERRED, or SHARED. + * + * LM_CB_NEED_RECOVERY + * The given journal needs to be recovered. + * + * LM_CB_DROPLOCKS + * Reduce the number of cached locks. + * + * LM_CB_ASYNC + * The given lock has been granted. + */ + +#define LM_CB_NEED_E 257 +#define LM_CB_NEED_D 258 +#define LM_CB_NEED_S 259 +#define LM_CB_NEED_RECOVERY 260 +#define LM_CB_DROPLOCKS 261 +#define LM_CB_ASYNC 262 + +/* + * lm_recovery_done() messages + */ + +#define LM_RD_GAVEUP 308 +#define LM_RD_SUCCESS 309 + + +struct lm_lockname { + u64 ln_number; + unsigned int ln_type; +}; + +#define lm_name_equal(name1, name2) \ + (((name1)->ln_number == (name2)->ln_number) && \ + ((name1)->ln_type == (name2)->ln_type)) \ + +struct lm_async_cb { + struct lm_lockname lc_name; + int lc_ret; +}; + +struct lm_lockstruct; + +struct lm_lockops { + const char *lm_proto_name; + + /* + * Mount/Unmount + */ + + int (*lm_mount) (char *table_name, char *host_data, + lm_callback_t cb, void *cb_data, + unsigned int min_lvb_size, int flags, + struct lm_lockstruct *lockstruct, + struct kobject *fskobj); + + void (*lm_others_may_mount) (void *lockspace); + + void (*lm_unmount) (void *lockspace); + + void (*lm_withdraw) (void *lockspace); + + /* + * Lock oriented operations + */ + + int (*lm_get_lock) (void *lockspace, struct lm_lockname *name, void **lockp); + + void (*lm_put_lock) (void *lock); + + unsigned int (*lm_lock) (void *lock, unsigned int cur_state, + unsigned int req_state, unsigned int flags); + + unsigned int (*lm_unlock) (void *lock, unsigned int cur_state); + + void (*lm_cancel) (void *lock); + + int (*lm_hold_lvb) (void *lock, char **lvbp); + void (*lm_unhold_lvb) (void *lock, char *lvb); + + /* + * Posix Lock oriented operations + */ + + int (*lm_plock_get) (void *lockspace, struct lm_lockname *name, + struct file *file, struct file_lock *fl); + + int (*lm_plock) (void *lockspace, struct lm_lockname *name, + struct file *file, int cmd, struct file_lock *fl); + + int (*lm_punlock) (void *lockspace, struct lm_lockname *name, + struct file *file, struct file_lock *fl); + + /* + * Client oriented operations + */ + + void (*lm_recovery_done) (void *lockspace, unsigned int jid, + unsigned int message); + + struct module *lm_owner; +}; + +/* + * lm_mount() return values + * + * ls_jid - the journal ID this node should use + * ls_first - this node is the first to mount the file system + * ls_lvb_size - size in bytes of lock value blocks + * ls_lockspace - lock module's context for this file system + * ls_ops - lock module's functions + * ls_flags - lock module features + */ + +struct lm_lockstruct { + unsigned int ls_jid; + unsigned int ls_first; + unsigned int ls_lvb_size; + void *ls_lockspace; + const struct lm_lockops *ls_ops; + int ls_flags; +}; + +/* + * Lock module bottom interface. A lock module makes itself available to GFS + * with these functions. + */ + +int gfs2_register_lockproto(const struct lm_lockops *proto); +void gfs2_unregister_lockproto(const struct lm_lockops *proto); + +/* + * Lock module top interface. GFS calls these functions when mounting or + * unmounting a file system. + */ + +int gfs2_mount_lockproto(char *proto_name, char *table_name, char *host_data, + lm_callback_t cb, void *cb_data, + unsigned int min_lvb_size, int flags, + struct lm_lockstruct *lockstruct, + struct kobject *fskobj); + +void gfs2_unmount_lockproto(struct lm_lockstruct *lockstruct); + +void gfs2_withdraw_lockproto(struct lm_lockstruct *lockstruct); + +#endif /* __LM_INTERFACE_DOT_H__ */ + -- cgit v1.2.3 From d3465c921f79cfef0a4a8ceeeef9a3721bbbb57d Mon Sep 17 00:00:00 2001 From: Vitaly Bordug Date: Thu, 21 Sep 2006 22:38:05 +0400 Subject: POWERPC: overhaul with cpm2_map mechanism Incorporating the new way of cpm2 immr access, introduced in the previous patch, into CPM2 peripheral devices (fs_enet and cpm_uart). Both ppc and powerpc approved working( real actions taken in powerpc only, ppc just has a wrapper to keep init stuff consistent). Signed-off-by: Vitaly Bordug --- include/linux/fs_enet_pd.h | 10 ++++++---- include/linux/fs_uart_pd.h | 4 +++- 2 files changed, 9 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs_enet_pd.h b/include/linux/fs_enet_pd.h index 74ed35a00a94..932223550aca 100644 --- a/include/linux/fs_enet_pd.h +++ b/include/linux/fs_enet_pd.h @@ -87,18 +87,20 @@ struct fs_mii_bb_platform_info { }; struct fs_platform_info { - - void(*init_ioports)(void); + + void(*init_ioports)(struct fs_platform_info *); /* device specific information */ int fs_no; /* controller index */ u32 cp_page; /* CPM page */ u32 cp_block; /* CPM sblock */ - + u32 clk_trx; /* some stuff for pins & mux configuration*/ + u32 clk_rx; + u32 clk_tx; u32 clk_route; u32 clk_mask; - + u32 mem_offset; u32 dpram_offset; u32 fcc_regs_c; diff --git a/include/linux/fs_uart_pd.h b/include/linux/fs_uart_pd.h index f5975126b712..a99a020f95c2 100644 --- a/include/linux/fs_uart_pd.h +++ b/include/linux/fs_uart_pd.h @@ -46,7 +46,7 @@ static inline int fs_uart_id_fsid2smc(int id) } struct fs_uart_platform_info { - void(*init_ioports)(void); + void(*init_ioports)(struct fs_uart_platform_info *); /* device specific information */ int fs_no; /* controller index */ u32 uart_clk; @@ -55,6 +55,8 @@ struct fs_uart_platform_info { u8 rx_num_fifo; u8 rx_buf_size; u8 brg; + u8 clk_rx; + u8 clk_tx; }; #endif -- cgit v1.2.3 From 611a15afcdaacec6efba984c7eb089b853564bdf Mon Sep 17 00:00:00 2001 From: Vitaly Bordug Date: Thu, 21 Sep 2006 22:38:05 +0400 Subject: POWERPC: Bring the fs_no calculation to the relevant SoC enumeration The fs_no mean used to be fs_enet driver driven, hence it was an enumeration across all the possible fs_enet "users" in the SoC. Now, with QE on the pipeline, and to make DTS descriptions more clear, fs_no features relevant SoC part number, with additional field to describe the SoC type. Another reason for that is now not only fs_enet is going to utilize those stuff. There might be UART, HLDC, and even USB, so to prevent confusion and be ready for upcoming OF_device transfer, fs_enet and cpm_uart drivers were updated in that concern, as well as the relevant DTS. Signed-off-by: Vitaly Bordug --- include/linux/fs_enet_pd.h | 37 +++++++++++++++++++++++++++++++++++++ include/linux/fs_uart_pd.h | 10 ++++++++++ 2 files changed, 47 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs_enet_pd.h b/include/linux/fs_enet_pd.h index 932223550aca..543cd3cd9e77 100644 --- a/include/linux/fs_enet_pd.h +++ b/include/linux/fs_enet_pd.h @@ -55,6 +55,30 @@ static inline int fs_get_scc_index(enum fs_id id) return -1; } +static inline int fs_fec_index2id(int index) +{ + int id = fsid_fec1 + index - 1; + if (id >= fsid_fec1 && id <= fsid_fec2) + return id; + return FS_MAX_INDEX; + } + +static inline int fs_fcc_index2id(int index) +{ + int id = fsid_fcc1 + index - 1; + if (id >= fsid_fcc1 && id <= fsid_fcc3) + return id; + return FS_MAX_INDEX; +} + +static inline int fs_scc_index2id(int index) +{ + int id = fsid_scc1 + index - 1; + if (id >= fsid_scc1 && id <= fsid_scc4) + return id; + return FS_MAX_INDEX; +} + enum fs_mii_method { fsmii_fixed, fsmii_fec, @@ -91,6 +115,7 @@ struct fs_platform_info { void(*init_ioports)(struct fs_platform_info *); /* device specific information */ int fs_no; /* controller index */ + char fs_type[4]; /* controller type */ u32 cp_page; /* CPM page */ u32 cp_block; /* CPM sblock */ @@ -126,4 +151,16 @@ struct fs_mii_fec_platform_info { u32 irq[32]; u32 mii_speed; }; + +static inline int fs_get_id(struct fs_platform_info *fpi) +{ + if(strstr(fpi->fs_type, "SCC")) + return fs_scc_index2id(fpi->fs_no); + if(strstr(fpi->fs_type, "FCC")) + return fs_fcc_index2id(fpi->fs_no); + if(strstr(fpi->fs_type, "FEC")) + return fs_fec_index2id(fpi->fs_no); + return fpi->fs_no; +} + #endif diff --git a/include/linux/fs_uart_pd.h b/include/linux/fs_uart_pd.h index a99a020f95c2..809bb9ffc788 100644 --- a/include/linux/fs_uart_pd.h +++ b/include/linux/fs_uart_pd.h @@ -49,6 +49,7 @@ struct fs_uart_platform_info { void(*init_ioports)(struct fs_uart_platform_info *); /* device specific information */ int fs_no; /* controller index */ + char fs_type[4]; /* controller type */ u32 uart_clk; u8 tx_num_fifo; u8 tx_buf_size; @@ -59,4 +60,13 @@ struct fs_uart_platform_info { u8 clk_tx; }; +static inline int fs_uart_get_id(struct fs_uart_platform_info *fpi) +{ + if(strstr(fpi->fs_type, "SMC")) + return fs_uart_id_smc2fsid(fpi->fs_no); + if(strstr(fpi->fs_type, "SCC")) + return fs_uart_id_scc2fsid(fpi->fs_no); + return fpi->fs_no; +} + #endif -- cgit v1.2.3 From 42431acbac43eb47c774c29d370f5c59136805bf Mon Sep 17 00:00:00 2001 From: Russell King Date: Sun, 24 Sep 2006 10:44:09 +0100 Subject: [MMC] MMC_CAP_BYTEBLOCK flag for non-log2 block sizes capable hosts Some MMC hosts can only handle log2 block sizes. Unfortunately, the MMC password support needs to be able to send non-log2 block sizes. Provide a capability so that the MMC password support can decide whether it should use this support or not. The unfortunate side effect of this host limitation is that any MMC card protected by a password which is not a log2 block size can not be accessed on a host which only allows a log2 block size. This change just adds the flag. The MMC password support code needs updating to use it (if and when it is finally submitted.) Signed-off-by: Russell King --- include/linux/mmc/host.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index b282ec9bba08..587264a58d56 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -86,6 +86,7 @@ struct mmc_host { #define MMC_CAP_4_BIT_DATA (1 << 0) /* Can the host do 4 bit transfers */ #define MMC_CAP_MULTIWRITE (1 << 1) /* Can accurately report bytes sent to card on error */ +#define MMC_CAP_BYTEBLOCK (1 << 2) /* Can do non-log2 block sizes */ /* host specific block data */ unsigned int max_seg_size; /* see blk_queue_max_segment_size */ -- cgit v1.2.3 From 3b85c3211ebde263a86c8cd3c7277fdd2e440310 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Mon, 25 Sep 2006 17:06:53 +0100 Subject: [MTD NAND] Split nand_scan() into two parts; allow board driver to intervene Signed-off-by: David Woodhouse --- include/linux/mtd/nand.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 0b4cd2fa64aa..88d690d79d77 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -27,6 +27,11 @@ struct mtd_info; /* Scan and identify a NAND device */ extern int nand_scan (struct mtd_info *mtd, int max_chips); +/* Separate phases of nand_scan(), allowing board driver to intervene + * and override command or ECC setup according to flash type */ +extern int nand_scan_ident(struct mtd_info *mtd, int max_chips); +extern int nand_scan_tail(struct mtd_info *mtd); + /* Free resources held by the NAND device */ extern void nand_release (struct mtd_info *mtd); -- cgit v1.2.3 From 4bf63fcb83dc761853f69a77b15e47712689020b Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Mon, 25 Sep 2006 17:08:04 +0100 Subject: [MTD NAND] Allocate chip->buffers separately to allow it to be overridden In particular, the board driver might need it to be DMAable. Signed-off-by: David Woodhouse --- include/linux/mtd/nand.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 88d690d79d77..cd4fe9ae8622 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -183,7 +183,9 @@ typedef enum { #define NAND_USE_FLASH_BBT 0x00010000 /* This option skips the bbt scan during initialization. */ #define NAND_SKIP_BBTSCAN 0x00020000 - +/* This option is defined if the board driver allocates its own buffers + (e.g. because it needs them DMA-coherent */ +#define NAND_OWN_BUFFERS 0x00040000 /* Options set by nand scan */ /* Nand scan has allocated controller struct */ #define NAND_CONTROLLER_ALLOC 0x80000000 @@ -385,7 +387,7 @@ struct nand_chip { struct nand_ecclayout *ecclayout; struct nand_ecc_ctrl ecc; - struct nand_buffers buffers; + struct nand_buffers *buffers; struct nand_hw_control hwcontrol; struct mtd_oob_ops ops; -- cgit v1.2.3 From 956e944c7690ea994757a8cbedbb6241e1d9138f Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Mon, 25 Sep 2006 17:12:39 +0100 Subject: [MTD NAND] Allow override of page read and write functions. - allow high-level nand_write_page() function to be overridden - likewise low-level write_page_raw() and read_page_raw() functions - Clean up the abuse of chip->ecc.{write,read}_page() with MTD_OOB_RAW Signed-off-by: David Woodhouse --- include/linux/mtd/nand.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index cd4fe9ae8622..2bcbcc896835 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -235,6 +235,8 @@ struct nand_hw_control { * be provided if an hardware ECC is available * @calculate: function for ecc calculation or readback from ecc hardware * @correct: function for ecc correction, matching to ecc generator (sw/hw) + * @read_page_raw: function to read a raw page without ECC + * @write_page_raw: function to write a raw page without ECC * @read_page: function to read a page according to the ecc generator requirements * @write_page: function to write a page according to the ecc generator requirements * @read_oob: function to read chip OOB data @@ -256,6 +258,12 @@ struct nand_ecc_ctrl { int (*correct)(struct mtd_info *mtd, uint8_t *dat, uint8_t *read_ecc, uint8_t *calc_ecc); + int (*read_page_raw)(struct mtd_info *mtd, + struct nand_chip *chip, + uint8_t *buf); + void (*write_page_raw)(struct mtd_info *mtd, + struct nand_chip *chip, + const uint8_t *buf); int (*read_page)(struct mtd_info *mtd, struct nand_chip *chip, uint8_t *buf); @@ -344,6 +352,7 @@ struct nand_buffers { * @priv: [OPTIONAL] pointer to private chip date * @errstat: [OPTIONAL] hardware specific function to perform additional error status checks * (determine if errors are correctable) + * @write_page [REPLACEABLE] High-level page write function */ struct nand_chip { @@ -366,6 +375,8 @@ struct nand_chip { void (*erase_cmd)(struct mtd_info *mtd, int page); int (*scan_bbt)(struct mtd_info *mtd); int (*errstat)(struct mtd_info *mtd, struct nand_chip *this, int state, int status, int page); + int (*write_page)(struct mtd_info *mtd, struct nand_chip *chip, + const uint8_t *buf, int page, int cached, int raw); int chip_delay; unsigned int options; -- cgit v1.2.3 From baef186519c69b11cf7e48c26e75feb1e6173baa Mon Sep 17 00:00:00 2001 From: "John W. Linville" Date: Fri, 8 Sep 2006 16:04:05 -0400 Subject: [PATCH] WE-21 support (core API) This is version 21 of the Wireless Extensions. Changelog : o finishes migrating the ESSID API (remove the +1) o netdev->get_wireless_stats is no more o long/short retry This is a redacted version of a patch originally submitted by Jean Tourrilhes. I removed most of the additions, in order to minimize future support requirements for nl80211 (or other WE successor). CC: Jean Tourrilhes Signed-off-by: John W. Linville --- include/linux/netdevice.h | 1 - include/linux/wireless.h | 24 ++++++++++++++++++++---- 2 files changed, 20 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 43289127b458..ac4f50213bc3 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -334,7 +334,6 @@ struct net_device struct net_device_stats* (*get_stats)(struct net_device *dev); - struct iw_statistics* (*get_wireless_stats)(struct net_device *dev); /* List of functions to handle Wireless Extensions (instead of ioctl). * See for details. Jean II */ diff --git a/include/linux/wireless.h b/include/linux/wireless.h index 13588564b42b..a50a0130fd9e 100644 --- a/include/linux/wireless.h +++ b/include/linux/wireless.h @@ -1,7 +1,7 @@ /* * This file define a set of standard wireless extensions * - * Version : 20 17.2.06 + * Version : 21 14.3.06 * * Authors : Jean Tourrilhes - HPL - * Copyright (c) 1997-2006 Jean Tourrilhes, All Rights Reserved. @@ -69,9 +69,14 @@ /***************************** INCLUDES *****************************/ +/* This header is used in user-space, therefore need to be sanitised + * for that purpose. Those includes are usually not compatible with glibc. + * To know which includes to use in user-space, check iwlib.h. */ +#ifdef __KERNEL__ #include /* for "caddr_t" et al */ #include /* for "struct sockaddr" et al */ #include /* for IFNAMSIZ and co... */ +#endif /* __KERNEL__ */ /***************************** VERSION *****************************/ /* @@ -80,7 +85,7 @@ * (there is some stuff that will be added in the future...) * I just plan to increment with each new version. */ -#define WIRELESS_EXT 20 +#define WIRELESS_EXT 21 /* * Changes : @@ -208,6 +213,14 @@ * V19 to V20 * ---------- * - RtNetlink requests support (SET/GET) + * + * V20 to V21 + * ---------- + * - Remove (struct net_device *)->get_wireless_stats() + * - Change length in ESSID and NICK to strlen() instead of strlen()+1 + * - Add IW_RETRY_SHORT/IW_RETRY_LONG retry modifiers + * - Power/Retry relative values no longer * 100000 + * - Add explicit flag to tell stats are in 802.11k RCPI : IW_QUAL_RCPI */ /**************************** CONSTANTS ****************************/ @@ -448,6 +461,7 @@ #define IW_QUAL_QUAL_INVALID 0x10 /* Driver doesn't provide value */ #define IW_QUAL_LEVEL_INVALID 0x20 #define IW_QUAL_NOISE_INVALID 0x40 +#define IW_QUAL_RCPI 0x80 /* Level + Noise are 802.11k RCPI */ #define IW_QUAL_ALL_INVALID 0x70 /* Frequency flags */ @@ -500,10 +514,12 @@ #define IW_RETRY_TYPE 0xF000 /* Type of parameter */ #define IW_RETRY_LIMIT 0x1000 /* Maximum number of retries*/ #define IW_RETRY_LIFETIME 0x2000 /* Maximum duration of retries in us */ -#define IW_RETRY_MODIFIER 0x000F /* Modify a parameter */ +#define IW_RETRY_MODIFIER 0x00FF /* Modify a parameter */ #define IW_RETRY_MIN 0x0001 /* Value is a minimum */ #define IW_RETRY_MAX 0x0002 /* Value is a maximum */ #define IW_RETRY_RELATIVE 0x0004 /* Value is not in seconds/ms/us */ +#define IW_RETRY_SHORT 0x0010 /* Value is for short packets */ +#define IW_RETRY_LONG 0x0020 /* Value is for long packets */ /* Scanning request flags */ #define IW_SCAN_DEFAULT 0x0000 /* Default scan of the driver */ @@ -1017,7 +1033,7 @@ struct iw_range /* Note : this frequency list doesn't need to fit channel numbers, * because each entry contain its channel index */ - __u32 enc_capa; /* IW_ENC_CAPA_* bit field */ + __u32 enc_capa; /* IW_ENC_CAPA_* bit field */ }; /* -- cgit v1.2.3 From b77d95c78fb0ec330cd53e0d297ffa4fd2975e32 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Mon, 25 Sep 2006 21:58:50 +0100 Subject: [MTD NAND] Provide prototype for newly-exported nand_wait_ready() Signed-off-by: David Woodhouse --- include/linux/mtd/nand.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 2bcbcc896835..70420bbae82b 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -35,6 +35,9 @@ extern int nand_scan_tail(struct mtd_info *mtd); /* Free resources held by the NAND device */ extern void nand_release (struct mtd_info *mtd); +/* Internal helper for board drivers which need to override command function */ +extern void nand_wait_ready(struct mtd_info *mtd); + /* The maximum number of NAND chips in an array */ #define NAND_MAX_CHIPS 8 -- cgit v1.2.3 From 0b680e753724d31a9c45f059d1aad29df54584a1 Mon Sep 17 00:00:00 2001 From: Jay Vosburgh Date: Fri, 22 Sep 2006 21:54:10 -0700 Subject: [PATCH] bonding: Add priv_flag to avoid event mishandling Add priv_flag to specifically identify bonding-involved devices. Needed because IFF_MASTER is an unreliable identifier (vlan interfaces above bonding will inherit IFF_MASTER). Misidentification of devices would cause notifier events for other devices to be erroneously processed by bonding, causing various havoc. Bug discovered by Martin Papik ; this patch is modified from his original. Signed-off-by: Martin Papik Signed-off-by: Jay Vosburgh Signed-off-by: Jeff Garzik --- include/linux/if.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/if.h b/include/linux/if.h index cd080d765324..a023ec1274fe 100644 --- a/include/linux/if.h +++ b/include/linux/if.h @@ -59,6 +59,7 @@ #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 IFF_BONDING 0x20 /* bonding master or slave */ #define IF_GET_IFACE 0x0001 /* for querying only */ #define IF_GET_PROTO 0x0002 -- cgit v1.2.3 From f5b2b966f032f22d3a289045a5afd4afa09f09c6 Mon Sep 17 00:00:00 2001 From: Jay Vosburgh Date: Fri, 22 Sep 2006 21:54:53 -0700 Subject: [PATCH] bonding: Validate probe replies in ARP monitor Add logic to check ARP request / reply packets used for ARP monitor link integrity checking. The current method simply examines the slave device to see if it has sent and received traffic; this can be fooled by extraneous traffic. For example, if multiple hosts running bonding are behind a common switch, the probe traffic from the multiple instances of bonding will update the tx/rx times on each other's slave devices. Signed-off-by: Jay Vosburgh Signed-off-by: Jeff Garzik --- include/linux/if.h | 1 + include/linux/netdevice.h | 7 ++++++- 2 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/if.h b/include/linux/if.h index a023ec1274fe..8018c2e22c0c 100644 --- a/include/linux/if.h +++ b/include/linux/if.h @@ -60,6 +60,7 @@ #define IFF_MASTER_8023AD 0x8 /* bonding master, 802.3ad. */ #define IFF_MASTER_ALB 0x10 /* bonding master, balance-alb. */ #define IFF_BONDING 0x20 /* bonding master or slave */ +#define IFF_SLAVE_NEEDARP 0x40 /* need ARPs for validation */ #define IF_GET_IFACE 0x0001 /* for querying only */ #define IF_GET_PROTO 0x0002 diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 43289127b458..afd80eff2725 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1016,7 +1016,8 @@ static inline int netif_needs_gso(struct net_device *dev, struct sk_buff *skb) } /* On bonding slaves other than the currently active slave, suppress - * duplicates except for 802.3ad ETH_P_SLOW and alb non-mcast/bcast. + * duplicates except for 802.3ad ETH_P_SLOW, alb non-mcast/bcast, and + * ARP on active-backup slaves with arp_validate enabled. */ static inline int skb_bond_should_drop(struct sk_buff *skb) { @@ -1025,6 +1026,10 @@ static inline int skb_bond_should_drop(struct sk_buff *skb) if (master && (dev->priv_flags & IFF_SLAVE_INACTIVE)) { + if ((dev->priv_flags & IFF_SLAVE_NEEDARP) && + skb->protocol == __constant_htons(ETH_P_ARP)) + return 0; + if (master->priv_flags & IFF_MASTER_ALB) { if (skb->pkt_type != PACKET_BROADCAST && skb->pkt_type != PACKET_MULTICAST) -- cgit v1.2.3 From 1739adea321788e380794c1072c810d445090bca Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Sat, 26 Aug 2006 03:05:17 -0300 Subject: V4L/DVB (4545): Add missing v4l2_buf_type to struct v4l2_sliced_vbi_cap. Signed-off-by: Hans Verkuil 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 e3715d774197..d5746d470c73 100644 --- a/include/linux/videodev2.h +++ b/include/linux/videodev2.h @@ -1135,7 +1135,8 @@ struct v4l2_sliced_vbi_cap (equals frame lines 313-336 for 625 line video standards, 263-286 for 525 line standards) */ __u16 service_lines[2][24]; - __u32 reserved[4]; /* must be 0 */ + enum v4l2_buf_type type; + __u32 reserved[3]; /* must be 0 */ }; struct v4l2_sliced_vbi_data -- cgit v1.2.3 From 616b8b639e6491cfa63f79238a5c6fbee383eb09 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Fri, 1 Sep 2006 18:36:48 -0300 Subject: V4L/DVB (4585): VIDIOC_G_SLICED_VBI_CAP now accepts a v4l2_buf_type, make it IOWR The VIDIOC_G_SLICED_VBI_CAP needs to receive the v4l2_buf_type field before it can return a result. Hence this ioctl must be IOWR, not IOR. Since this ioctl is still marked experimental we can make this change. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/linux/videodev2.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/videodev2.h b/include/linux/videodev2.h index d5746d470c73..44c59da26ed2 100644 --- a/include/linux/videodev2.h +++ b/include/linux/videodev2.h @@ -1243,7 +1243,7 @@ struct v4l2_streamparm #define VIDIOC_G_PRIORITY _IOR ('V', 67, enum v4l2_priority) #define VIDIOC_S_PRIORITY _IOW ('V', 68, enum v4l2_priority) #if 1 -#define VIDIOC_G_SLICED_VBI_CAP _IOR ('V', 69, struct v4l2_sliced_vbi_cap) +#define VIDIOC_G_SLICED_VBI_CAP _IOWR ('V', 69, struct v4l2_sliced_vbi_cap) #endif #define VIDIOC_LOG_STATUS _IO ('V', 70) #define VIDIOC_G_EXT_CTRLS _IOWR ('V', 71, struct v4l2_ext_controls) -- cgit v1.2.3 From 28b79ff9661b22e4c41c0d00d4ab8503e810f13d Mon Sep 17 00:00:00 2001 From: Kyungmin Park Date: Tue, 26 Sep 2006 09:45:28 +0000 Subject: [MTD ONENAND] Check OneNAND lock scheme & all block unlock command support OneNAND lock scheme depends on density and process of chip. Some OneNAND chips support all block unlock Signed-off-by: Kyungmin Park Signed-off-by: David Woodhouse --- include/linux/mtd/onenand.h | 6 ++++-- include/linux/mtd/onenand_regs.h | 4 +++- 2 files changed, 7 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/onenand.h b/include/linux/mtd/onenand.h index 1f4972155249..6f045b586e76 100644 --- a/include/linux/mtd/onenand.h +++ b/include/linux/mtd/onenand.h @@ -1,7 +1,7 @@ /* * linux/include/linux/mtd/onenand.h * - * Copyright (C) 2005 Samsung Electronics + * Copyright (C) 2005-2006 Samsung Electronics * Kyungmin Park * * This program is free software; you can redistribute it and/or modify @@ -96,6 +96,7 @@ struct onenand_chip { void __iomem *base; unsigned int chipsize; unsigned int device_id; + unsigned int version_id; unsigned int density_mask; unsigned int options; @@ -149,7 +150,8 @@ struct onenand_chip { /* * Options bits */ -#define ONENAND_CONT_LOCK (0x0001) +#define ONENAND_HAS_CONT_LOCK (0x0001) +#define ONENAND_HAS_UNLOCK_ALL (0x0002) #define ONENAND_PAGEBUF_ALLOC (0x1000) /* diff --git a/include/linux/mtd/onenand_regs.h b/include/linux/mtd/onenand_regs.h index 4a72818d2545..9e409fe6ded6 100644 --- a/include/linux/mtd/onenand_regs.h +++ b/include/linux/mtd/onenand_regs.h @@ -3,7 +3,7 @@ * * OneNAND Register header file * - * Copyright (C) 2005 Samsung Electronics + * Copyright (C) 2005-2006 Samsung Electronics * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -72,6 +72,7 @@ #define ONENAND_DEVICE_VCC_MASK (0x3) #define ONENAND_DEVICE_DENSITY_512Mb (0x002) +#define ONENAND_DEVICE_DENSITY_1Gb (0x003) /* * Version ID Register F002h (R) @@ -110,6 +111,7 @@ #define ONENAND_CMD_UNLOCK (0x23) #define ONENAND_CMD_LOCK (0x2A) #define ONENAND_CMD_LOCK_TIGHT (0x2C) +#define ONENAND_CMD_UNLOCK_ALL (0x27) #define ONENAND_CMD_ERASE (0x94) #define ONENAND_CMD_RESET (0xF0) #define ONENAND_CMD_OTP_ACCESS (0x65) -- cgit v1.2.3 From 5e96f59f9b20373014abd5e30fba4805c5d4f53f Mon Sep 17 00:00:00 2001 From: Steven Whitehouse Date: Tue, 26 Sep 2006 17:14:02 -0400 Subject: [GFS2] Remove (extra) fs_subsys declaration This is already in Linus' tree, so we don't need to add another one. Signed-off-by: Steven Whitehouse --- 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 48f982100f5a..1d3e601ece73 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1377,9 +1377,6 @@ extern struct subsystem fs_subsys; #define FLOCK_VERIFY_READ 1 #define FLOCK_VERIFY_WRITE 2 -/* /sys/fs */ -extern struct subsystem fs_subsys; - extern int locks_mandatory_locked(struct inode *); extern int locks_mandatory_area(int, struct inode *, struct file *, loff_t, size_t); -- cgit v1.2.3 From eb2a2fd91f7c8a53b15063d6f08cf22b9a56cbfb Mon Sep 17 00:00:00 2001 From: Krzysztof Halasa Date: Tue, 26 Sep 2006 23:23:45 +0200 Subject: [PATCH] Modularize generic HDLC This patch enables building of individual WAN protocol support routines (parts of generic HDLC) as separate modules. All protocol-private definitions are moved from hdlc.h file to protocol drivers. User-space interface and interface between generic HDLC and underlying low-level HDLC drivers are unchanged. Signed-off-by: Krzysztof Halasa Signed-off-by: Jeff Garzik --- include/linux/hdlc.h | 201 ++++++++++----------------------------------- include/linux/hdlc/ioctl.h | 33 ++++++++ 2 files changed, 77 insertions(+), 157 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hdlc.h b/include/linux/hdlc.h index d5ebbb29aeae..d4b333938f73 100644 --- a/include/linux/hdlc.h +++ b/include/linux/hdlc.h @@ -11,95 +11,46 @@ #ifndef __HDLC_H #define __HDLC_H -#define GENERIC_HDLC_VERSION 4 /* For synchronization with sethdlc utility */ - -#define CLOCK_DEFAULT 0 /* Default setting */ -#define CLOCK_EXT 1 /* External TX and RX clock - DTE */ -#define CLOCK_INT 2 /* Internal TX and RX clock - DCE */ -#define CLOCK_TXINT 3 /* Internal TX and external RX clock */ -#define CLOCK_TXFROMRX 4 /* TX clock derived from external RX clock */ - - -#define ENCODING_DEFAULT 0 /* Default setting */ -#define ENCODING_NRZ 1 -#define ENCODING_NRZI 2 -#define ENCODING_FM_MARK 3 -#define ENCODING_FM_SPACE 4 -#define ENCODING_MANCHESTER 5 - - -#define PARITY_DEFAULT 0 /* Default setting */ -#define PARITY_NONE 1 /* No parity */ -#define PARITY_CRC16_PR0 2 /* CRC16, initial value 0x0000 */ -#define PARITY_CRC16_PR1 3 /* CRC16, initial value 0xFFFF */ -#define PARITY_CRC16_PR0_CCITT 4 /* CRC16, initial 0x0000, ITU-T version */ -#define PARITY_CRC16_PR1_CCITT 5 /* CRC16, initial 0xFFFF, ITU-T version */ -#define PARITY_CRC32_PR0_CCITT 6 /* CRC32, initial value 0x00000000 */ -#define PARITY_CRC32_PR1_CCITT 7 /* CRC32, initial value 0xFFFFFFFF */ - -#define LMI_DEFAULT 0 /* Default setting */ -#define LMI_NONE 1 /* No LMI, all PVCs are static */ -#define LMI_ANSI 2 /* ANSI Annex D */ -#define LMI_CCITT 3 /* ITU-T Annex A */ -#define LMI_CISCO 4 /* The "original" LMI, aka Gang of Four */ #define HDLC_MAX_MTU 1500 /* Ethernet 1500 bytes */ +#if 0 #define HDLC_MAX_MRU (HDLC_MAX_MTU + 10 + 14 + 4) /* for ETH+VLAN over FR */ +#else +#define HDLC_MAX_MRU 1600 /* as required for FR network */ +#endif #ifdef __KERNEL__ #include #include -#include #include -typedef struct { /* Used in Cisco and PPP mode */ - u8 address; - u8 control; - u16 protocol; -}__attribute__ ((packed)) hdlc_header; - - - -typedef struct { - u32 type; /* code */ - u32 par1; - u32 par2; - u16 rel; /* reliability */ - u32 time; -}__attribute__ ((packed)) cisco_packet; -#define CISCO_PACKET_LEN 18 -#define CISCO_BIG_PACKET_LEN 20 - - - -typedef struct pvc_device_struct { - struct net_device *master; - struct net_device *main; - struct net_device *ether; /* bridged Ethernet interface */ - struct pvc_device_struct *next; /* Sorted in ascending DLCI order */ - int dlci; - int open_count; - - struct { - unsigned int new: 1; - unsigned int active: 1; - unsigned int exist: 1; - unsigned int deleted: 1; - unsigned int fecn: 1; - unsigned int becn: 1; - unsigned int bandwidth; /* Cisco LMI reporting only */ - }state; -}pvc_device; - - - -typedef struct hdlc_device_struct { - /* To be initialized by hardware driver */ +/* Used by all network devices here, pointed to by netdev_priv(dev) */ +struct hdlc_device_desc { + int (*netif_rx)(struct sk_buff *skb); struct net_device_stats stats; - +}; + +/* This structure is a private property of HDLC protocols. + Hardware drivers have no interest here */ + +struct hdlc_proto { + int (*open)(struct net_device *dev); + void (*close)(struct net_device *dev); + void (*start)(struct net_device *dev); /* if open & DCD */ + void (*stop)(struct net_device *dev); /* if open & !DCD */ + void (*detach)(struct net_device *dev); + int (*ioctl)(struct net_device *dev, struct ifreq *ifr); + unsigned short (*type_trans)(struct sk_buff *skb, + struct net_device *dev); + struct module *module; + struct hdlc_proto *next; /* next protocol in the list */ +}; + + +typedef struct hdlc_device { /* used by HDLC layer to take control over HDLC device from hw driver*/ int (*attach)(struct net_device *dev, unsigned short encoding, unsigned short parity); @@ -107,82 +58,18 @@ typedef struct hdlc_device_struct { /* hardware driver must handle this instead of dev->hard_start_xmit */ int (*xmit)(struct sk_buff *skb, struct net_device *dev); - /* Things below are for HDLC layer internal use only */ - struct { - int (*open)(struct net_device *dev); - void (*close)(struct net_device *dev); - - /* if open & DCD */ - void (*start)(struct net_device *dev); - /* if open & !DCD */ - void (*stop)(struct net_device *dev); - - void (*detach)(struct hdlc_device_struct *hdlc); - int (*netif_rx)(struct sk_buff *skb); - unsigned short (*type_trans)(struct sk_buff *skb, - struct net_device *dev); - int id; /* IF_PROTO_HDLC/CISCO/FR/etc. */ - }proto; - + const struct hdlc_proto *proto; int carrier; int open; spinlock_t state_lock; - - union { - struct { - fr_proto settings; - pvc_device *first_pvc; - int dce_pvc_count; - - struct timer_list timer; - unsigned long last_poll; - int reliable; - int dce_changed; - int request; - int fullrep_sent; - u32 last_errors; /* last errors bit list */ - u8 n391cnt; - u8 txseq; /* TX sequence number */ - u8 rxseq; /* RX sequence number */ - }fr; - - struct { - cisco_proto settings; - - struct timer_list timer; - unsigned long last_poll; - int up; - int request_sent; - u32 txseq; /* TX sequence number */ - u32 rxseq; /* RX sequence number */ - }cisco; - - struct { - raw_hdlc_proto settings; - }raw_hdlc; - - struct { - struct ppp_device pppdev; - struct ppp_device *syncppp_ptr; - int (*old_change_mtu)(struct net_device *dev, - int new_mtu); - }ppp; - }state; + void *state; void *priv; }hdlc_device; -int hdlc_raw_ioctl(struct net_device *dev, struct ifreq *ifr); -int hdlc_raw_eth_ioctl(struct net_device *dev, struct ifreq *ifr); -int hdlc_cisco_ioctl(struct net_device *dev, struct ifreq *ifr); -int hdlc_ppp_ioctl(struct net_device *dev, struct ifreq *ifr); -int hdlc_fr_ioctl(struct net_device *dev, struct ifreq *ifr); -int hdlc_x25_ioctl(struct net_device *dev, struct ifreq *ifr); - - -/* Exported from hdlc.o */ +/* Exported from hdlc module */ /* Called by hardware driver when a user requests HDLC service */ int hdlc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd); @@ -191,17 +78,21 @@ int hdlc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd); #define register_hdlc_device(dev) register_netdev(dev) void unregister_hdlc_device(struct net_device *dev); + +void register_hdlc_protocol(struct hdlc_proto *proto); +void unregister_hdlc_protocol(struct hdlc_proto *proto); + struct net_device *alloc_hdlcdev(void *priv); -static __inline__ hdlc_device* dev_to_hdlc(struct net_device *dev) + +static __inline__ struct hdlc_device_desc* dev_to_desc(struct net_device *dev) { return netdev_priv(dev); } - -static __inline__ pvc_device* dev_to_pvc(struct net_device *dev) +static __inline__ hdlc_device* dev_to_hdlc(struct net_device *dev) { - return (pvc_device*)dev->priv; + return netdev_priv(dev) + sizeof(struct hdlc_device_desc); } @@ -225,18 +116,14 @@ int hdlc_open(struct net_device *dev); /* Must be called by hardware driver when HDLC device is being closed */ void hdlc_close(struct net_device *dev); +int attach_hdlc_protocol(struct net_device *dev, struct hdlc_proto *proto, + int (*rx)(struct sk_buff *skb), size_t size); /* May be used by hardware driver to gain control over HDLC device */ -static __inline__ void hdlc_proto_detach(hdlc_device *hdlc) -{ - if (hdlc->proto.detach) - hdlc->proto.detach(hdlc); - hdlc->proto.detach = NULL; -} - +void detach_hdlc_protocol(struct net_device *dev); static __inline__ struct net_device_stats *hdlc_stats(struct net_device *dev) { - return &dev_to_hdlc(dev)->stats; + return &dev_to_desc(dev)->stats; } @@ -248,8 +135,8 @@ static __inline__ __be16 hdlc_type_trans(struct sk_buff *skb, skb->mac.raw = skb->data; skb->dev = dev; - if (hdlc->proto.type_trans) - return hdlc->proto.type_trans(skb, dev); + if (hdlc->proto->type_trans) + return hdlc->proto->type_trans(skb, dev); else return htons(ETH_P_HDLC); } diff --git a/include/linux/hdlc/ioctl.h b/include/linux/hdlc/ioctl.h index 78430ba3ea69..583972364357 100644 --- a/include/linux/hdlc/ioctl.h +++ b/include/linux/hdlc/ioctl.h @@ -1,6 +1,39 @@ #ifndef __HDLC_IOCTL_H__ #define __HDLC_IOCTL_H__ + +#define GENERIC_HDLC_VERSION 4 /* For synchronization with sethdlc utility */ + +#define CLOCK_DEFAULT 0 /* Default setting */ +#define CLOCK_EXT 1 /* External TX and RX clock - DTE */ +#define CLOCK_INT 2 /* Internal TX and RX clock - DCE */ +#define CLOCK_TXINT 3 /* Internal TX and external RX clock */ +#define CLOCK_TXFROMRX 4 /* TX clock derived from external RX clock */ + + +#define ENCODING_DEFAULT 0 /* Default setting */ +#define ENCODING_NRZ 1 +#define ENCODING_NRZI 2 +#define ENCODING_FM_MARK 3 +#define ENCODING_FM_SPACE 4 +#define ENCODING_MANCHESTER 5 + + +#define PARITY_DEFAULT 0 /* Default setting */ +#define PARITY_NONE 1 /* No parity */ +#define PARITY_CRC16_PR0 2 /* CRC16, initial value 0x0000 */ +#define PARITY_CRC16_PR1 3 /* CRC16, initial value 0xFFFF */ +#define PARITY_CRC16_PR0_CCITT 4 /* CRC16, initial 0x0000, ITU-T version */ +#define PARITY_CRC16_PR1_CCITT 5 /* CRC16, initial 0xFFFF, ITU-T version */ +#define PARITY_CRC32_PR0_CCITT 6 /* CRC32, initial value 0x00000000 */ +#define PARITY_CRC32_PR1_CCITT 7 /* CRC32, initial value 0xFFFFFFFF */ + +#define LMI_DEFAULT 0 /* Default setting */ +#define LMI_NONE 1 /* No LMI, all PVCs are static */ +#define LMI_ANSI 2 /* ANSI Annex D */ +#define LMI_CCITT 3 /* ITU-T Annex A */ +#define LMI_CISCO 4 /* The "original" LMI, aka Gang of Four */ + typedef struct { unsigned int clock_rate; /* bits per second */ unsigned int clock_type; /* internal, external, TX-internal etc. */ -- cgit v1.2.3 From 51c3711704b66986373408cbc0540abea43d2380 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Sun, 13 Aug 2006 23:33:16 +0200 Subject: i2c-algo-sibyte: Merge into i2c-sibyte i2c-algo-sibyte: Merge into i2c-sibyte Merge i2c-algo-sibyte into i2c-sibyte, as this is a complete, hardware-dependent SMBus implementation and not a reusable algorithm. Perform some basic coding style cleanups while we're here (mainly space-based indentation replaced by tabulations.) Signed-off-by: Jean Delvare Cc: Ralf Baechle Signed-off-by: Greg Kroah-Hartman --- include/linux/i2c-algo-sibyte.h | 33 --------------------------------- 1 file changed, 33 deletions(-) delete mode 100644 include/linux/i2c-algo-sibyte.h (limited to 'include/linux') diff --git a/include/linux/i2c-algo-sibyte.h b/include/linux/i2c-algo-sibyte.h deleted file mode 100644 index 03914ded8614..000000000000 --- a/include/linux/i2c-algo-sibyte.h +++ /dev/null @@ -1,33 +0,0 @@ -/* - * Copyright (C) 2001,2002,2003 Broadcom Corporation - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2 - * of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. - */ - -#ifndef I2C_ALGO_SIBYTE_H -#define I2C_ALGO_SIBYTE_H 1 - -#include - -struct i2c_algo_sibyte_data { - void *data; /* private data */ - int bus; /* which bus */ - void *reg_base; /* CSR base */ -}; - -int i2c_sibyte_add_bus(struct i2c_adapter *, int speed); -int i2c_sibyte_del_bus(struct i2c_adapter *); - -#endif /* I2C_ALGO_SIBYTE_H */ -- cgit v1.2.3 From a0d9c63d3640bd4fc90a408e8334754ef44bcf48 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Sun, 27 Aug 2006 11:46:49 +0200 Subject: i2c-algo-bit: Discard the mdelay data struct member i2c-algo-bit: Discard the mdelay data struct member The i2c_algo_bit_data structure has an mdelay member, which is not used by the algorithm code (the code has always been ifdef'd out.) Let's discard it to save some code and memory. Signed-off-by: Jean Delvare Acked-by: Mauro Carvalho Chehab Cc: Adrian Bunk Signed-off-by: Greg Kroah-Hartman --- include/linux/i2c-algo-bit.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/i2c-algo-bit.h b/include/linux/i2c-algo-bit.h index c0e7fab28ce3..c8f8df25c7e0 100644 --- a/include/linux/i2c-algo-bit.h +++ b/include/linux/i2c-algo-bit.h @@ -40,7 +40,6 @@ struct i2c_algo_bit_data { /* local settings */ int udelay; /* half-clock-cycle time in microsecs */ /* i.e. clock is (500 / udelay) KHz */ - int mdelay; /* in millisecs, unused */ int timeout; /* in jiffies */ }; -- cgit v1.2.3 From 9b4ccb86b4abe644ffd218720da2f942b6a20fc2 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Sun, 3 Sep 2006 22:22:50 +0200 Subject: i2c-algo-pcf: Discard the mdelay data struct member i2c-algo-pcf: Discard the mdelay data struct member Just as i2c-algo-bit, i2c-algo-pcf has an unused mdelay struct member, which we can get rid of to spare some code and memory. Signed-off-by: Adrian Bunk Signed-off-by: Jean Delvare Signed-off-by: Greg Kroah-Hartman --- include/linux/i2c-algo-pcf.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/i2c-algo-pcf.h b/include/linux/i2c-algo-pcf.h index 18b0adf57a3d..9908f3fc4839 100644 --- a/include/linux/i2c-algo-pcf.h +++ b/include/linux/i2c-algo-pcf.h @@ -35,7 +35,6 @@ struct i2c_algo_pcf_data { /* local settings */ int udelay; - int mdelay; int timeout; }; -- cgit v1.2.3 From af71ff690b92894f66ccede27f731150dc10d80d Mon Sep 17 00:00:00 2001 From: David Brownell Date: Sun, 3 Sep 2006 22:37:11 +0200 Subject: i2c: Let drivers constify i2c_algorithm data i2c: Let drivers constify i2c_algorithm data Let drivers constify I2C algorithm method operations tables, moving them from ".data" to ".rodata". Signed-off-by: David Brownell Signed-off-by: Jean Delvare Signed-off-by: Greg Kroah-Hartman --- include/linux/i2c.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index eb0628a7ecc6..23ad1ee42a4c 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -220,7 +220,7 @@ struct i2c_adapter { struct module *owner; unsigned int id; unsigned int class; - struct i2c_algorithm *algo;/* the algorithm to access the bus */ + const struct i2c_algorithm *algo; /* the algorithm to access the bus */ void *algo_data; /* --- administration stuff. */ -- cgit v1.2.3 From 6d3aae9d74221b00e2cbf50a353527e5a71a58ba Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Sun, 3 Sep 2006 22:41:08 +0200 Subject: i2c: Drop unimplemented slave functions i2c: Drop unimplemented slave functions Drop the function declarations for slave mode support of i2c adapters. This was never implemented, and by the time it is I bet we will want something different anyway. Signed-off-by: Jean Delvare Signed-off-by: Greg Kroah-Hartman --- include/linux/i2c.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 23ad1ee42a4c..9b5d04768c2c 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -64,14 +64,6 @@ extern int i2c_master_recv(struct i2c_client *,char* ,int); */ extern int i2c_transfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num); -/* - * Some adapter types (i.e. PCF 8584 based ones) may support slave behaviuor. - * This is not tested/implemented yet and will change in the future. - */ -extern int i2c_slave_send(struct i2c_client *,char*,int); -extern int i2c_slave_recv(struct i2c_client *,char*,int); - - /* This is the very generalized SMBus access routine. You probably do not want to use this, though; one of the functions below may be much easier, @@ -201,10 +193,6 @@ struct i2c_algorithm { unsigned short flags, char read_write, u8 command, int size, union i2c_smbus_data * data); - /* --- these optional/future use for some adapter types.*/ - int (*slave_send)(struct i2c_adapter *,char*,int); - int (*slave_recv)(struct i2c_adapter *,char*,int); - /* --- ioctl like call to set div. parameters. */ int (*algo_control)(struct i2c_adapter *, unsigned int, unsigned long); -- cgit v1.2.3 From 46ff34633ed09f36ebc4b5c40ac37e592172df74 Mon Sep 17 00:00:00 2001 From: Brice Goglin Date: Thu, 31 Aug 2006 01:55:24 -0400 Subject: MSI: Rename PCI_CAP_ID_HT_IRQCONF into PCI_CAP_ID_HT 0x08 is the HT capability, while PCI_CAP_ID_HT_IRQCONF would be the subtype 0x80 that mpic_scan_ht_pic() uses. Rename PCI_CAP_ID_HT_IRQCONF into PCI_CAP_ID_HT. And by the way, use it in the ipath driver instead of defining its own HT_CAPABILITY_ID. Signed-off-by: Brice Goglin Signed-off-by: Greg Kroah-Hartman --- include/linux/pci_regs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci_regs.h b/include/linux/pci_regs.h index 96930cb5927c..7d0e26cba420 100644 --- a/include/linux/pci_regs.h +++ b/include/linux/pci_regs.h @@ -196,7 +196,7 @@ #define PCI_CAP_ID_MSI 0x05 /* Message Signalled Interrupts */ #define PCI_CAP_ID_CHSWP 0x06 /* CompactPCI HotSwap */ #define PCI_CAP_ID_PCIX 0x07 /* PCI-X */ -#define PCI_CAP_ID_HT_IRQCONF 0x08 /* HyperTransport IRQ Configuration */ +#define PCI_CAP_ID_HT 0x08 /* HyperTransport */ #define PCI_CAP_ID_VNDR 0x09 /* Vendor specific capability */ #define PCI_CAP_ID_SHPC 0x0C /* PCI Standard Hot-Plug Controller */ #define PCI_CAP_ID_EXP 0x10 /* PCI Express */ -- cgit v1.2.3 From 6397c75cbc4d7dbc3d07278b57c82a47dafb21b5 Mon Sep 17 00:00:00 2001 From: Brice Goglin Date: Thu, 31 Aug 2006 01:55:32 -0400 Subject: MSI: Blacklist PCI-E chipsets depending on Hypertransport MSI capability Introduce msi_ht_cap_enabled() to check the MSI capability in the Hypertransport configuration space. It is used in a generic quirk quirk_msi_ht_cap() to check whether MSI is enabled on hypertransport chipset, and a nVidia specific quirk quirk_nvidia_ck804_msi_ht_cap() where two 2 HT MSI mappings have to be checked. Both quirks set the PCI_BUS_FLAGS_NO_MSI bus flag when MSI is disabled. Signed-off-by: Brice Goglin Signed-off-by: Greg Kroah-Hartman --- 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 6a1e09834559..b9e263adebab 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1411,6 +1411,7 @@ #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_HT2000_PCIE 0x0132 #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 6c2b374d74857e892080ee726184ec1d15e7d4e4 Mon Sep 17 00:00:00 2001 From: "Zhang, Yanmin" Date: Mon, 31 Jul 2006 15:21:33 +0800 Subject: PCI-Express AER implemetation: AER core and aerdriver Patch 3 implements the core part of PCI-Express AER and aerdrv port service driver. When a root port service device is probed, the aerdrv will call request_irq to register irq handler for AER error interrupt. When a device sends an PCI-Express error message to the root port, the root port will trigger an interrupt, by either MSI or IO-APIC, then kernel would run the irq handler. The handler collects root error status register and schedules a work. The work will call the core part to process the error based on its type (Correctable/non-fatal/fatal). As for Correctable errors, the patch chooses to just clear the correctable error status register of the device. As for the non-fatal error, the patch follows generic PCI error handler rules to call the error callback functions of the endpoint's driver. If the device is a bridge, the patch chooses to broadcast the error to downstream devices. As for the fatal error, the patch resets the pci-express link and follows generic PCI error handler rules to call the error callback functions of the endpoint's driver. If the device is a bridge, the patch chooses to broadcast the error to downstream devices. Signed-off-by: Zhang Yanmin Signed-off-by: Greg Kroah-Hartman --- include/linux/aer.h | 24 ++++++++++++++++++++++++ include/linux/pcieport_if.h | 6 ++++++ 2 files changed, 30 insertions(+) create mode 100644 include/linux/aer.h (limited to 'include/linux') diff --git a/include/linux/aer.h b/include/linux/aer.h new file mode 100644 index 000000000000..402e178b38eb --- /dev/null +++ b/include/linux/aer.h @@ -0,0 +1,24 @@ +/* + * Copyright (C) 2006 Intel Corp. + * Tom Long Nguyen (tom.l.nguyen@intel.com) + * Zhang Yanmin (yanmin.zhang@intel.com) + */ + +#ifndef _AER_H_ +#define _AER_H_ + +#if defined(CONFIG_PCIEAER) +/* pci-e port driver needs this function to enable aer */ +extern int pci_enable_pcie_error_reporting(struct pci_dev *dev); +extern int pci_find_aer_capability(struct pci_dev *dev); +extern int pci_disable_pcie_error_reporting(struct pci_dev *dev); +extern int pci_cleanup_aer_uncorrect_error_status(struct pci_dev *dev); +#else +#define pci_enable_pcie_error_reporting(dev) do { } while (0) +#define pci_find_aer_capability(dev) do { } while (0) +#define pci_disable_pcie_error_reporting(dev) do { } while (0) +#define pci_cleanup_aer_uncorrect_error_status(dev) do { } while (0) +#endif + +#endif //_AER_H_ + diff --git a/include/linux/pcieport_if.h b/include/linux/pcieport_if.h index b44e01a70914..6cd91e3f9820 100644 --- a/include/linux/pcieport_if.h +++ b/include/linux/pcieport_if.h @@ -62,6 +62,12 @@ struct pcie_port_service_driver { int (*suspend) (struct pcie_device *dev, pm_message_t state); int (*resume) (struct pcie_device *dev); + /* Service Error Recovery Handler */ + struct pci_error_handlers *err_handler; + + /* Link Reset Capability - AER service driver specific */ + pci_ers_result_t (*reset_link) (struct pci_dev *dev); + const struct pcie_port_service_id *id_table; struct device_driver driver; }; -- cgit v1.2.3 From b19441af185559118e8247382ea4f2f76ebffc6d Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 28 Aug 2006 11:43:25 -0700 Subject: PCI: fix __must_check warnings Signed-off-by: Greg Kroah-Hartman --- include/linux/pci.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 3ec72551ac31..c9bb7bee52c7 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -431,7 +431,7 @@ int pci_scan_slot(struct pci_bus *bus, int devfn); struct pci_dev * pci_scan_single_device(struct pci_bus *bus, int devfn); void pci_device_add(struct pci_dev *dev, struct pci_bus *bus); unsigned int pci_scan_child_bus(struct pci_bus *bus); -void pci_bus_add_device(struct pci_dev *dev); +int __must_check pci_bus_add_device(struct pci_dev *dev); void pci_read_bridge_bases(struct pci_bus *child); struct resource *pci_find_parent_resource(const struct pci_dev *dev, struct resource *res); int pci_get_interrupt_pin(struct pci_dev *dev, struct pci_dev **bridge); -- cgit v1.2.3 From 50b0075520a0acba9cabab5203bbce918b966d9a Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Wed, 16 Aug 2006 17:42:18 +0100 Subject: PCI: Multiprobe sanitizer There are numerous drivers that can use multithreaded probing but having some kind of global flag as the way to control this makes migration to threaded probing hard and since it enables it everywhere and is almost as likely to cause serious pain as holding a clog dance in a minefield. If we have a pci_driver multithread_probe flag to inherit you can turn it on for one driver at a time. From playing so far however I think we need a different model at the device layer which serializes until the called probe function says "ok you can start another one now". That would need some kind of flag and semaphore plus a helper function. Anyway in the absence of that this is a starting point to usefully play with this stuff Signed-off-by: Alan Cox Signed-off-by: Greg Kroah-Hartman --- include/linux/pci.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index c9bb7bee52c7..549d8410974b 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -356,6 +356,8 @@ struct pci_driver { struct pci_error_handlers *err_handler; struct device_driver driver; struct pci_dynids dynids; + + int multithread_probe; }; #define to_pci_driver(drv) container_of(drv,struct pci_driver, driver) -- cgit v1.2.3 From 24f8aa9b464b73e0553f092b747770940ee0ea54 Mon Sep 17 00:00:00 2001 From: Satoru Takeuchi Date: Tue, 12 Sep 2006 10:16:36 -0700 Subject: PCI: add pci_stop_bus_device This patch adds pci_stop_bus_device() which stops a PCI device (detach the driver, remove from the global list and so on) and any children. This is needed for ACPI based PCI-to-PCI bridge hot-remove, and it will be also needed for ACPI based PCI root bridge hot-remove. Signed-off-by: Kenji Kaneshige Signed-off-by: MUNEDA Takahiro Signed-off-by: Satoru Takeuchi Signed-off-by: Kristen Carlson Accardi Signed-off-by: Greg Kroah-Hartman --- include/linux/pci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 549d8410974b..5c3a4176eb64 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -441,6 +441,7 @@ extern struct pci_dev *pci_dev_get(struct pci_dev *dev); extern void pci_dev_put(struct pci_dev *dev); extern void pci_remove_bus(struct pci_bus *b); extern void pci_remove_bus_device(struct pci_dev *dev); +extern void pci_stop_bus_device(struct pci_dev *dev); void pci_setup_cardbus(struct pci_bus *bus); /* Generic PCI functions exported to card drivers */ -- cgit v1.2.3 From d48f1de2d8170814fb64effa320848410c466f95 Mon Sep 17 00:00:00 2001 From: Ralf Baechle Date: Wed, 20 Sep 2006 20:56:02 +0100 Subject: [MIPS] Remove EV96100 as previously announced. Signed-off-by: Ralf Baechle --- include/linux/pci_ids.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 6a1e09834559..5c1c698a92ac 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1482,9 +1482,6 @@ #define PCI_DEVICE_ID_MARVELL_GT64260 0x6430 #define PCI_DEVICE_ID_MARVELL_MV64360 0x6460 #define PCI_DEVICE_ID_MARVELL_MV64460 0x6480 -#define PCI_DEVICE_ID_MARVELL_GT96100 0x9652 -#define PCI_DEVICE_ID_MARVELL_GT96100A 0x9653 - #define PCI_VENDOR_ID_V3 0x11b0 #define PCI_DEVICE_ID_V3_V960 0x0001 -- cgit v1.2.3 From ae6ddcc5f24d6b06ae9231dc128904750a4155e0 Mon Sep 17 00:00:00 2001 From: Mingming Cao Date: Wed, 27 Sep 2006 01:49:27 -0700 Subject: [PATCH] ext3 and jbd cleanup: remove whitespace Remove whitespace from ext3 and jbd, before we clone ext4. Signed-off-by: Mingming Cao Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ext3_jbd.h | 10 ++++----- include/linux/jbd.h | 56 ++++++++++++++++++++++++------------------------ 2 files changed, 33 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ext3_jbd.h b/include/linux/ext3_jbd.h index c8307c02dd07..ce0e6109aff0 100644 --- a/include/linux/ext3_jbd.h +++ b/include/linux/ext3_jbd.h @@ -23,7 +23,7 @@ /* Define the number of blocks we need to account to a transaction to * modify one block of data. - * + * * We may have to touch one inode, one bitmap buffer, up to three * indirection blocks, the group and superblock summaries, and the data * block to complete the transaction. */ @@ -88,16 +88,16 @@ #endif int -ext3_mark_iloc_dirty(handle_t *handle, +ext3_mark_iloc_dirty(handle_t *handle, struct inode *inode, struct ext3_iloc *iloc); -/* +/* * On success, We end up with an outstanding reference count against - * iloc->bh. This _must_ be cleaned up later. + * iloc->bh. This _must_ be cleaned up later. */ -int ext3_reserve_inode_write(handle_t *handle, struct inode *inode, +int ext3_reserve_inode_write(handle_t *handle, struct inode *inode, struct ext3_iloc *iloc); int ext3_mark_inode_dirty(handle_t *handle, struct inode *inode); diff --git a/include/linux/jbd.h b/include/linux/jbd.h index a04c154c5207..7d847931ee5a 100644 --- a/include/linux/jbd.h +++ b/include/linux/jbd.h @@ -1,6 +1,6 @@ /* * linux/include/linux/jbd.h - * + * * Written by Stephen C. Tweedie * * Copyright 1998-2000 Red Hat, Inc --- All Rights Reserved @@ -97,8 +97,8 @@ extern void jbd_slab_free(void *ptr, size_t size); * number of outstanding buffers possible at any time. When the * operation completes, any buffer credits not used are credited back to * the transaction, so that at all times we know how many buffers the - * outstanding updates on a transaction might possibly touch. - * + * outstanding updates on a transaction might possibly touch. + * * This is an opaque datatype. **/ typedef struct handle_s handle_t; /* Atomic operation type */ @@ -108,7 +108,7 @@ typedef struct handle_s handle_t; /* Atomic operation type */ * typedef journal_t - The journal_t maintains all of the journaling state information for a single filesystem. * * journal_t is linked to from the fs superblock structure. - * + * * We use the journal_t to keep track of all outstanding transaction * activity on the filesystem, and to manage the state of the log * writing process. @@ -128,7 +128,7 @@ typedef struct journal_s journal_t; /* Journal control structure */ * On-disk structures */ -/* +/* * Descriptor block types: */ @@ -149,8 +149,8 @@ typedef struct journal_header_s } journal_header_t; -/* - * The block tag: used to describe a single buffer in the journal +/* + * The block tag: used to describe a single buffer in the journal */ typedef struct journal_block_tag_s { @@ -158,9 +158,9 @@ typedef struct journal_block_tag_s __be32 t_flags; /* See below */ } journal_block_tag_t; -/* +/* * The revoke descriptor: used on disk to describe a series of blocks to - * be revoked from the log + * be revoked from the log */ typedef struct journal_revoke_header_s { @@ -374,10 +374,10 @@ struct jbd_revoke_table_s; **/ /* Docbook can't yet cope with the bit fields, but will leave the documentation - * in so it can be fixed later. + * in so it can be fixed later. */ -struct handle_s +struct handle_s { /* Which compound transaction is this update a part of? */ transaction_t *h_transaction; @@ -435,7 +435,7 @@ struct handle_s * */ -struct transaction_s +struct transaction_s { /* Pointer to the journal for this transaction. [no locking] */ journal_t *t_journal; @@ -455,7 +455,7 @@ struct transaction_s T_RUNDOWN, T_FLUSH, T_COMMIT, - T_FINISHED + T_FINISHED } t_state; /* @@ -569,7 +569,7 @@ struct transaction_s * journal_t. * @j_flags: General journaling state flags * @j_errno: Is there an outstanding uncleared error on the journal (from a - * prior abort)? + * prior abort)? * @j_sb_buffer: First part of superblock buffer * @j_superblock: Second part of superblock buffer * @j_format_version: Version of the superblock format @@ -583,7 +583,7 @@ struct transaction_s * @j_wait_transaction_locked: Wait queue for waiting for a locked transaction * to start committing, or for a barrier lock to be released * @j_wait_logspace: Wait queue for waiting for checkpointing to complete - * @j_wait_done_commit: Wait queue for waiting for commit to complete + * @j_wait_done_commit: Wait queue for waiting for commit to complete * @j_wait_checkpoint: Wait queue to trigger checkpointing * @j_wait_commit: Wait queue to trigger commit * @j_wait_updates: Wait queue to wait for updates to complete @@ -592,7 +592,7 @@ struct transaction_s * @j_tail: Journal tail - identifies the oldest still-used block in the * journal. * @j_free: Journal free - how many free blocks are there in the journal? - * @j_first: The block number of the first usable block + * @j_first: The block number of the first usable block * @j_last: The block number one beyond the last usable block * @j_dev: Device where we store the journal * @j_blocksize: blocksize for the location where we store the journal. @@ -604,12 +604,12 @@ struct transaction_s * @j_list_lock: Protects the buffer lists and internal buffer state. * @j_inode: Optional inode where we store the journal. If present, all journal * block numbers are mapped into this inode via bmap(). - * @j_tail_sequence: Sequence number of the oldest transaction in the log + * @j_tail_sequence: Sequence number of the oldest transaction in the log * @j_transaction_sequence: Sequence number of the next transaction to grant * @j_commit_sequence: Sequence number of the most recently committed * transaction * @j_commit_request: Sequence number of the most recent transaction wanting - * commit + * commit * @j_uuid: Uuid of client object. * @j_task: Pointer to the current commit thread for this journal * @j_max_transaction_buffers: Maximum number of metadata buffers to allow in a @@ -823,8 +823,8 @@ struct journal_s void *j_private; }; -/* - * Journal flag definitions +/* + * Journal flag definitions */ #define JFS_UNMOUNT 0x001 /* Journal thread is being destroyed */ #define JFS_ABORT 0x002 /* Journaling has been aborted for errors. */ @@ -833,7 +833,7 @@ struct journal_s #define JFS_LOADED 0x010 /* The journal superblock has been loaded */ #define JFS_BARRIER 0x020 /* Use IDE barriers */ -/* +/* * Function declarations for the journaling transaction and buffer * management */ @@ -862,7 +862,7 @@ int __journal_remove_checkpoint(struct journal_head *); void __journal_insert_checkpoint(struct journal_head *, transaction_t *); /* Buffer IO */ -extern int +extern int journal_write_metadata_buffer(transaction_t *transaction, struct journal_head *jh_in, struct journal_head **jh_out, @@ -890,7 +890,7 @@ static inline handle_t *journal_current_handle(void) /* The journaling code user interface: * * Create and destroy handles - * Register buffer modifications against the current transaction. + * Register buffer modifications against the current transaction. */ extern handle_t *journal_start(journal_t *, int nblocks); @@ -917,11 +917,11 @@ extern journal_t * journal_init_dev(struct block_device *bdev, int start, int len, int bsize); extern journal_t * journal_init_inode (struct inode *); extern int journal_update_format (journal_t *); -extern int journal_check_used_features +extern int journal_check_used_features (journal_t *, unsigned long, unsigned long, unsigned long); -extern int journal_check_available_features +extern int journal_check_available_features (journal_t *, unsigned long, unsigned long, unsigned long); -extern int journal_set_features +extern int journal_set_features (journal_t *, unsigned long, unsigned long, unsigned long); extern int journal_create (journal_t *); extern int journal_load (journal_t *journal); @@ -1015,7 +1015,7 @@ do { \ * bit, when set, indicates that we have had a fatal error somewhere, * either inside the journaling layer or indicated to us by the client * (eg. ext3), and that we and should not commit any further - * transactions. + * transactions. */ static inline int is_journal_aborted(journal_t *journal) @@ -1082,7 +1082,7 @@ static inline int jbd_space_needed(journal_t *journal) #define BJ_Reserved 7 /* Buffer is reserved for access by journal */ #define BJ_Locked 8 /* Locked for I/O during commit */ #define BJ_Types 9 - + extern int jbd_blocks_per_page(struct inode *inode); #ifdef __KERNEL__ -- cgit v1.2.3 From 37ed322290eb6d5cf2ab33915793ed4219eae1d6 Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Wed, 27 Sep 2006 01:49:31 -0700 Subject: [PATCH] JBD: 16T fixes These are a few places I've found in jbd that look like they may not be 16T-safe, or consistent with the use of unsigned longs for block containers. Problems here would be somewhat hard to hit, would require journal blocks past the 8T boundary, which would not be terribly common. Still, should fix. (some of these have come from the ext4 work on jbd as well). I think there's one more possibility that the wrap() function may not be safe IF your last block in the journal butts right up against the 232 block boundary, but that seems like a VERY remote possibility, and I'm not worrying about it at this point. Signed-off-by: Eric Sandeen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/jbd.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/jbd.h b/include/linux/jbd.h index 7d847931ee5a..dc262624efa5 100644 --- a/include/linux/jbd.h +++ b/include/linux/jbd.h @@ -732,7 +732,7 @@ struct journal_s */ struct block_device *j_dev; int j_blocksize; - unsigned int j_blk_offset; + unsigned long j_blk_offset; /* * Device which holds the client fs. For internal journal this will be @@ -866,7 +866,7 @@ extern int journal_write_metadata_buffer(transaction_t *transaction, struct journal_head *jh_in, struct journal_head **jh_out, - int blocknr); + unsigned long blocknr); /* Transaction locking */ extern void __wait_on_journal (journal_t *); -- cgit v1.2.3 From e9ad5620bfb901df8a7a2603c88689ededeecaf1 Mon Sep 17 00:00:00 2001 From: Dave Kleikamp Date: Wed, 27 Sep 2006 01:49:35 -0700 Subject: [PATCH] ext3: More whitespace cleanups More white space cleanups in preparation of cloning ext4 from ext3. Removing spaces that precede a tab. Signed-off-by: Dave Kleikamp Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ext3_fs.h | 2 +- include/linux/ext3_fs_i.h | 2 +- include/linux/jbd.h | 10 +++++----- 3 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h index 0eed918b3816..369c67502346 100644 --- a/include/linux/ext3_fs.h +++ b/include/linux/ext3_fs.h @@ -473,7 +473,7 @@ struct ext3_super_block { __u8 s_reserved_char_pad; __u16 s_reserved_word_pad; __le32 s_default_mount_opts; - __le32 s_first_meta_bg; /* First metablock block group */ + __le32 s_first_meta_bg; /* First metablock block group */ __u32 s_reserved[190]; /* Padding to the end of the block */ }; diff --git a/include/linux/ext3_fs_i.h b/include/linux/ext3_fs_i.h index 2f18b9511f21..4395e5206746 100644 --- a/include/linux/ext3_fs_i.h +++ b/include/linux/ext3_fs_i.h @@ -35,7 +35,7 @@ struct ext3_reserve_window { }; struct ext3_reserve_window_node { - struct rb_node rsv_node; + struct rb_node rsv_node; __u32 rsv_goal_size; __u32 rsv_alloc_hit; struct ext3_reserve_window rsv_window; diff --git a/include/linux/jbd.h b/include/linux/jbd.h index dc262624efa5..a6d9daa38c6d 100644 --- a/include/linux/jbd.h +++ b/include/linux/jbd.h @@ -64,7 +64,7 @@ extern int journal_enable_debug; if ((n) <= journal_enable_debug) { \ printk (KERN_DEBUG "(%s, %d): %s: ", \ __FILE__, __LINE__, __FUNCTION__); \ - printk (f, ## a); \ + printk (f, ## a); \ } \ } while (0) #else @@ -201,9 +201,9 @@ typedef struct journal_superblock_s /* 0x0024 */ /* Remaining fields are only valid in a version-2 superblock */ - __be32 s_feature_compat; /* compatible feature set */ - __be32 s_feature_incompat; /* incompatible feature set */ - __be32 s_feature_ro_compat; /* readonly-compatible feature set */ + __be32 s_feature_compat; /* compatible feature set */ + __be32 s_feature_incompat; /* incompatible feature set */ + __be32 s_feature_ro_compat; /* readonly-compatible feature set */ /* 0x0030 */ __u8 s_uuid[16]; /* 128-bit uuid for journal */ @@ -699,7 +699,7 @@ struct journal_s wait_queue_head_t j_wait_updates; /* Semaphore for locking against concurrent checkpoints */ - struct mutex j_checkpoint_mutex; + struct mutex j_checkpoint_mutex; /* * Journal head: identifies the first unused block in the journal. -- cgit v1.2.3 From a4e4de36dc446b2193bdc8ebb96a96e44b69dd94 Mon Sep 17 00:00:00 2001 From: Dave Kleikamp Date: Wed, 27 Sep 2006 01:49:36 -0700 Subject: [PATCH] ext3: Fix sparse warnings Fixing up some endian-ness warnings in preparation to clone ext4 from ext3. Signed-off-by: Dave Kleikamp Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ext3_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h index 369c67502346..cc08f56750da 100644 --- a/include/linux/ext3_fs.h +++ b/include/linux/ext3_fs.h @@ -460,7 +460,7 @@ struct ext3_super_block { */ __u8 s_prealloc_blocks; /* Nr of blocks to try to preallocate*/ __u8 s_prealloc_dir_blocks; /* Nr to preallocate for dirs */ - __u16 s_reserved_gdt_blocks; /* Per group desc for online growth */ + __le16 s_reserved_gdt_blocks; /* Per group desc for online growth */ /* * Journaling support valid if EXT3_FEATURE_COMPAT_HAS_JOURNAL set. */ -- cgit v1.2.3 From 133d205a18b7a4d8cb52959c5310f6664277cf61 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Wed, 27 Sep 2006 01:49:41 -0700 Subject: [PATCH] Make kmem_cache_destroy() return void un-, de-, -free, -destroy, -exit, etc functions should in general return void. Also, There is very little, say, filesystem driver code can do upon failed kmem_cache_destroy(). If it will be decided to BUG in this case, BUG should be put in generic code, instead. Signed-off-by: Alexey Dobriyan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 66d6eb78d1c6..a96fd9310d55 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -60,7 +60,7 @@ extern void __init kmem_cache_init(void); extern kmem_cache_t *kmem_cache_create(const char *, size_t, size_t, unsigned long, void (*)(void *, kmem_cache_t *, unsigned long), void (*)(void *, kmem_cache_t *, unsigned long)); -extern int kmem_cache_destroy(kmem_cache_t *); +extern void kmem_cache_destroy(kmem_cache_t *); extern int kmem_cache_shrink(kmem_cache_t *); extern void *kmem_cache_alloc(kmem_cache_t *, gfp_t); extern void *kmem_cache_zalloc(struct kmem_cache *, gfp_t); @@ -249,7 +249,7 @@ struct kmem_cache *kmem_cache_create(const char *c, size_t, size_t, unsigned long, void (*)(void *, struct kmem_cache *, unsigned long), void (*)(void *, struct kmem_cache *, unsigned long)); -int kmem_cache_destroy(struct kmem_cache *c); +void kmem_cache_destroy(struct kmem_cache *c); void *kmem_cache_alloc(struct kmem_cache *c, gfp_t flags); void *kmem_cache_zalloc(struct kmem_cache *, gfp_t); void kmem_cache_free(struct kmem_cache *c, void *b); -- cgit v1.2.3 From c713216deebd95d2b0ab38fef8bb2361c0180c2d Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 27 Sep 2006 01:49:43 -0700 Subject: [PATCH] Introduce mechanism for registering active regions of memory At a basic level, architectures define structures to record where active ranges of page frames are located. Once located, the code to calculate zone sizes and holes in each architecture is very similar. Some of this zone and hole sizing code is difficult to read for no good reason. This set of patches eliminates the similar-looking architecture-specific code. The patches introduce a mechanism where architectures register where the active ranges of page frames are with add_active_range(). When all areas have been discovered, free_area_init_nodes() is called to initialise the pgdat and zones. The zone sizes and holes are then calculated in an architecture independent manner. Patch 1 introduces the mechanism for registering and initialising PFN ranges Patch 2 changes ppc to use the mechanism - 139 arch-specific LOC removed Patch 3 changes x86 to use the mechanism - 136 arch-specific LOC removed Patch 4 changes x86_64 to use the mechanism - 74 arch-specific LOC removed Patch 5 changes ia64 to use the mechanism - 52 arch-specific LOC removed Patch 6 accounts for mem_map as a memory hole as the pages are not reclaimable. It adjusts the watermarks slightly Tony Luck has successfully tested for ia64 on Itanium with tiger_defconfig, gensparse_defconfig and defconfig. Bob Picco has also tested and debugged on IA64. Jack Steiner successfully boot tested on a mammoth SGI IA64-based machine. These were on patches against 2.6.17-rc1 and release 3 of these patches but there have been no ia64-changes since release 3. There are differences in the zone sizes for x86_64 as the arch-specific code for x86_64 accounts the kernel image and the starting mem_maps as memory holes but the architecture-independent code accounts the memory as present. The big benefit of this set of patches is a sizable reduction of architecture-specific code, some of which is very hairy. There should be a greater reduction when other architectures use the same mechanisms for zone and hole sizing but I lack the hardware to test on. Additional credit; Dave Hansen for the initial suggestion and comments on early patches Andy Whitcroft for reviewing early versions and catching numerous errors Tony Luck for testing and debugging on IA64 Bob Picco for fixing bugs related to pfn registration, reviewing a number of patch revisions, providing a number of suggestions on future direction and testing heavily Jack Steiner and Robin Holt for testing on IA64 and clarifying issues related to memory holes Yasunori for testing on IA64 Andi Kleen for reviewing and feeding back about x86_64 Christian Kujau for providing valuable information related to ACPI problems on x86_64 and testing potential fixes This patch: Define the structure to represent an active range of page frames within a node in an architecture independent manner. Architectures are expected to register active ranges of PFNs using add_active_range(nid, start_pfn, end_pfn) and call free_area_init_nodes() passing the PFNs of the end of each zone. Signed-off-by: Mel Gorman Signed-off-by: Bob Picco Cc: Dave Hansen Cc: Andy Whitcroft Cc: Andi Kleen Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: "Keith Mannthey" Cc: "Luck, Tony" Cc: KAMEZAWA Hiroyuki Cc: Yasunori Goto Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 47 +++++++++++++++++++++++++++++++++++++++++++++++ include/linux/mmzone.h | 10 +++++++++- 2 files changed, 56 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 856f0ee7e84a..c0402da7cce0 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -937,6 +937,53 @@ extern void free_area_init(unsigned long * zones_size); extern void free_area_init_node(int nid, pg_data_t *pgdat, unsigned long * zones_size, unsigned long zone_start_pfn, unsigned long *zholes_size); +#ifdef CONFIG_ARCH_POPULATES_NODE_MAP +/* + * With CONFIG_ARCH_POPULATES_NODE_MAP set, an architecture may initialise its + * zones, allocate the backing mem_map and account for memory holes in a more + * architecture independent manner. This is a substitute for creating the + * zone_sizes[] and zholes_size[] arrays and passing them to + * free_area_init_node() + * + * An architecture is expected to register range of page frames backed by + * physical memory with add_active_range() before calling + * free_area_init_nodes() passing in the PFN each zone ends at. At a basic + * usage, an architecture is expected to do something like + * + * unsigned long max_zone_pfns[MAX_NR_ZONES] = {max_dma, max_normal_pfn, + * max_highmem_pfn}; + * for_each_valid_physical_page_range() + * add_active_range(node_id, start_pfn, end_pfn) + * free_area_init_nodes(max_zone_pfns); + * + * If the architecture guarantees that there are no holes in the ranges + * registered with add_active_range(), free_bootmem_active_regions() + * will call free_bootmem_node() for each registered physical page range. + * Similarly sparse_memory_present_with_active_regions() calls + * memory_present() for each range when SPARSEMEM is enabled. + * + * See mm/page_alloc.c for more information on each function exposed by + * CONFIG_ARCH_POPULATES_NODE_MAP + */ +extern void free_area_init_nodes(unsigned long *max_zone_pfn); +extern void add_active_range(unsigned int nid, unsigned long start_pfn, + unsigned long end_pfn); +extern void shrink_active_range(unsigned int nid, unsigned long old_end_pfn, + unsigned long new_end_pfn); +extern void remove_all_active_ranges(void); +extern unsigned long absent_pages_in_range(unsigned long start_pfn, + unsigned long end_pfn); +extern void get_pfn_range_for_nid(unsigned int nid, + unsigned long *start_pfn, unsigned long *end_pfn); +extern unsigned long find_min_pfn_with_active_regions(void); +extern unsigned long find_max_pfn_with_active_regions(void); +extern void free_bootmem_with_active_regions(int nid, + unsigned long max_low_pfn); +extern void sparse_memory_present_with_active_regions(int nid); +#ifndef CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID +extern int early_pfn_to_nid(unsigned long pfn); +#endif /* CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID */ +#endif /* CONFIG_ARCH_POPULATES_NODE_MAP */ extern void memmap_init_zone(unsigned long, int, unsigned long, unsigned long); extern void setup_per_zone_pages_min(void); extern void mem_init(void); diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 3693f1a52788..7fa1cbe9fa7a 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -305,6 +305,13 @@ struct zonelist { struct zone *zones[MAX_NUMNODES * MAX_NR_ZONES + 1]; // NULL delimited }; +#ifdef CONFIG_ARCH_POPULATES_NODE_MAP +struct node_active_region { + unsigned long start_pfn; + unsigned long end_pfn; + int nid; +}; +#endif /* CONFIG_ARCH_POPULATES_NODE_MAP */ /* * The pg_data_t structure is used in machines with CONFIG_DISCONTIGMEM @@ -518,7 +525,8 @@ extern struct zone *next_zone(struct zone *zone); #endif -#ifndef CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID +#if !defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID) && \ + !defined(CONFIG_ARCH_POPULATES_NODE_MAP) #define early_pfn_to_nid(nid) (0UL) #endif -- cgit v1.2.3 From 0e0b864e069c52a7b3e4a7da56e29b03a012fd75 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 27 Sep 2006 01:49:56 -0700 Subject: [PATCH] Account for memmap and optionally the kernel image as holes The x86_64 code accounted for memmap and some portions of the the DMA zone as holes. This was because those areas would never be reclaimed and accounting for them as memory affects min watermarks. This patch will account for the memmap as a memory hole. Architectures may optionally use set_dma_reserve() if they wish to account for a portion of memory in ZONE_DMA as a hole. Signed-off-by: Mel Gorman Cc: Dave Hansen Cc: Andy Whitcroft Cc: Andi Kleen Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: "Keith Mannthey" Cc: "Luck, Tony" Cc: KAMEZAWA Hiroyuki Cc: Yasunori Goto Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index c0402da7cce0..22936e1fcdf2 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -984,6 +984,7 @@ extern void sparse_memory_present_with_active_regions(int nid); extern int early_pfn_to_nid(unsigned long pfn); #endif /* CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID */ #endif /* CONFIG_ARCH_POPULATES_NODE_MAP */ +extern void set_dma_reserve(unsigned long new_dma_reserve); extern void memmap_init_zone(unsigned long, int, unsigned long, unsigned long); extern void setup_per_zone_pages_min(void); extern void mem_init(void); -- cgit v1.2.3 From fb01439c5b778d5974a488c5d4fe85e6d0e18a68 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 27 Sep 2006 01:49:59 -0700 Subject: [PATCH] Allow an arch to expand node boundaries Arch-independent zone-sizing determines the size of a node (pgdat->node_spanned_pages) based on the physical memory that was registered by the architecture. However, when CONFIG_MEMORY_HOTPLUG_RESERVE is set, the architecture expects that the spanned_pages will be much larger and that mem_map will be allocated that is used lated on memory hot-add. This patch allows an architecture that sets CONFIG_MEMORY_HOTPLUG_RESERVE to call push_node_boundaries() which will set the node beginning and end to at *least* the requested boundary. Cc: Dave Hansen Cc: Andy Whitcroft Cc: Andi Kleen Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: "Keith Mannthey" Cc: "Luck, Tony" Cc: KAMEZAWA Hiroyuki Cc: Yasunori Goto Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 22936e1fcdf2..9d046db31e76 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -970,6 +970,8 @@ extern void add_active_range(unsigned int nid, unsigned long start_pfn, unsigned long end_pfn); extern void shrink_active_range(unsigned int nid, unsigned long old_end_pfn, unsigned long new_end_pfn); +extern void push_node_boundaries(unsigned int nid, unsigned long start_pfn, + unsigned long end_pfn); extern void remove_all_active_ranges(void); extern unsigned long absent_pages_in_range(unsigned long start_pfn, unsigned long end_pfn); -- cgit v1.2.3 From e129b5c23c2b471d47f1c5d2b8b193fc2034af43 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Wed, 27 Sep 2006 01:50:00 -0700 Subject: [PATCH] vm: add per-zone writeout counter The VM is supposed to minimise the number of pages which get written off the LRU (for IO scheduling efficiency, and for high reclaim-success rates). But we don't actually have a clear way of showing how true this is. So add `nr_vmscan_write' to /proc/vmstat and /proc/zoneinfo - the number of pages which have been written by the vm scanner in this zone and globally. Cc: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 7fa1cbe9fa7a..1b0680cd84d2 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -58,6 +58,7 @@ enum zone_stat_item { NR_WRITEBACK, NR_UNSTABLE_NFS, /* NFS unstable pages */ NR_BOUNCE, + NR_VMSCAN_WRITE, #ifdef CONFIG_NUMA NUMA_HIT, /* allocated in intended node */ NUMA_MISS, /* allocated in non intended node */ -- cgit v1.2.3 From 5b99cd0effaf846240a15441aec459a592577eaf Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Wed, 27 Sep 2006 01:50:01 -0700 Subject: [PATCH] own header file for struct page This moves the definition of struct page from mm.h to its own header file page-struct.h. This is a prereq to fix SetPageUptodate which is broken on s390: #define SetPageUptodate(_page) do { struct page *__page = (_page); if (!test_and_set_bit(PG_uptodate, &__page->flags)) page_test_and_clear_dirty(_page); } while (0) _page gets used twice in this macro which can cause subtle bugs. Using __page for the page_test_and_clear_dirty call doesn't work since it causes yet another problem with the page_test_and_clear_dirty macro as well. In order to avoid all these problems caused by macros it seems to be a good idea to get rid of them and convert them to static inline functions. Because of header file include order it's necessary to have a seperate header file for the struct page definition. Cc: Martin Schwidefsky Signed-off-by: Heiko Carstens Cc: Roman Zippel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 62 +------------------------------------------- include/linux/mm_types.h | 67 ++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/mmzone.h | 5 ++++ 3 files changed, 73 insertions(+), 61 deletions(-) create mode 100644 include/linux/mm_types.h (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 9d046db31e76..7477fb59c4f2 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -16,6 +16,7 @@ #include #include #include +#include struct mempolicy; struct anon_vma; @@ -215,62 +216,6 @@ struct vm_operations_struct { struct mmu_gather; struct inode; -/* - * Each physical page in the system has a struct page associated with - * it to keep track of whatever it is we are using the page for at the - * moment. Note that we have no way to track which tasks are using - * a page, though if it is a pagecache page, rmap structures can tell us - * who is mapping it. - */ -struct page { - unsigned long flags; /* Atomic flags, some possibly - * updated asynchronously */ - atomic_t _count; /* Usage count, see below. */ - atomic_t _mapcount; /* Count of ptes mapped in mms, - * to show when page is mapped - * & limit reverse map searches. - */ - union { - struct { - unsigned long private; /* Mapping-private opaque data: - * usually used for buffer_heads - * if PagePrivate set; used for - * swp_entry_t if PageSwapCache; - * indicates order in the buddy - * system if PG_buddy is set. - */ - struct address_space *mapping; /* If low bit clear, points to - * inode address_space, or NULL. - * If page mapped as anonymous - * memory, low bit is set, and - * it points to anon_vma object: - * see PAGE_MAPPING_ANON below. - */ - }; -#if NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS - spinlock_t ptl; -#endif - }; - pgoff_t index; /* Our offset within mapping. */ - struct list_head lru; /* Pageout list, eg. active_list - * protected by zone->lru_lock ! - */ - /* - * On machines where all RAM is mapped into kernel address space, - * we can simply calculate the virtual address. On machines with - * highmem some memory is mapped into kernel virtual memory - * dynamically, so we need a place to store that address. - * Note that this field could be 16 bits on x86 ... ;) - * - * Architectures with slow multiplication can define - * WANT_PAGE_VIRTUAL in asm/page.h - */ -#if defined(WANT_PAGE_VIRTUAL) - void *virtual; /* Kernel virtual address (NULL if - not kmapped, ie. highmem) */ -#endif /* WANT_PAGE_VIRTUAL */ -}; - #define page_private(page) ((page)->private) #define set_page_private(page, v) ((page)->private = (v)) @@ -546,11 +491,6 @@ static inline void set_page_links(struct page *page, enum zone_type zone, */ #include -#ifndef CONFIG_DISCONTIGMEM -/* The array of struct pages - for discontigmem use pgdat->lmem_map */ -extern struct page *mem_map; -#endif - static __always_inline void *lowmem_page_address(struct page *page) { return __va(page_to_pfn(page) << PAGE_SHIFT); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h new file mode 100644 index 000000000000..c3852fd4a1cc --- /dev/null +++ b/include/linux/mm_types.h @@ -0,0 +1,67 @@ +#ifndef _LINUX_MM_TYPES_H +#define _LINUX_MM_TYPES_H + +#include +#include +#include +#include + +struct address_space; + +/* + * Each physical page in the system has a struct page associated with + * it to keep track of whatever it is we are using the page for at the + * moment. Note that we have no way to track which tasks are using + * a page, though if it is a pagecache page, rmap structures can tell us + * who is mapping it. + */ +struct page { + unsigned long flags; /* Atomic flags, some possibly + * updated asynchronously */ + atomic_t _count; /* Usage count, see below. */ + atomic_t _mapcount; /* Count of ptes mapped in mms, + * to show when page is mapped + * & limit reverse map searches. + */ + union { + struct { + unsigned long private; /* Mapping-private opaque data: + * usually used for buffer_heads + * if PagePrivate set; used for + * swp_entry_t if PageSwapCache; + * indicates order in the buddy + * system if PG_buddy is set. + */ + struct address_space *mapping; /* If low bit clear, points to + * inode address_space, or NULL. + * If page mapped as anonymous + * memory, low bit is set, and + * it points to anon_vma object: + * see PAGE_MAPPING_ANON below. + */ + }; +#if NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS + spinlock_t ptl; +#endif + }; + pgoff_t index; /* Our offset within mapping. */ + struct list_head lru; /* Pageout list, eg. active_list + * protected by zone->lru_lock ! + */ + /* + * On machines where all RAM is mapped into kernel address space, + * we can simply calculate the virtual address. On machines with + * highmem some memory is mapped into kernel virtual memory + * dynamically, so we need a place to store that address. + * Note that this field could be 16 bits on x86 ... ;) + * + * Architectures with slow multiplication can define + * WANT_PAGE_VIRTUAL in asm/page.h + */ +#if defined(WANT_PAGE_VIRTUAL) + void *virtual; /* Kernel virtual address (NULL if + not kmapped, ie. highmem) */ +#endif /* WANT_PAGE_VIRTUAL */ +}; + +#endif /* _LINUX_MM_TYPES_H */ diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 1b0680cd84d2..562cf7a8f3ee 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -314,6 +314,11 @@ struct node_active_region { }; #endif /* CONFIG_ARCH_POPULATES_NODE_MAP */ +#ifndef CONFIG_DISCONTIGMEM +/* The array of struct pages - for discontigmem use pgdat->lmem_map */ +extern struct page *mem_map; +#endif + /* * The pg_data_t structure is used in machines with CONFIG_DISCONTIGMEM * (mostly NUMA machines?) to denote a higher-level memory zone than the -- cgit v1.2.3 From 08e0f6a9705376732fd3bc9bf8ba97a6b5211eb1 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Wed, 27 Sep 2006 01:50:06 -0700 Subject: [PATCH] Add NUMA_BUILD definition in kernel.h to avoid #ifdef CONFIG_NUMA The NUMA_BUILD constant is always available and will be set to 1 on NUMA_BUILDs. That way checks valid only under CONFIG_NUMA can easily be done without #ifdef CONFIG_NUMA F.e. if (NUMA_BUILD && ) { ... } [akpm: not a thing we'd normally do, but CONFIG_NUMA is special: it is causing ifdef explosion in core kernel, so let's see if this is a comfortable way in whcih to control that] Signed-off-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 4fa373bb18ac..4d00988dad03 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -350,4 +350,11 @@ struct sysinfo { /* Trap pasters of __FUNCTION__ at compile-time */ #define __FUNCTION__ (__func__) +/* This helps us to avoid #ifdef CONFIG_NUMA */ +#ifdef CONFIG_NUMA +#define NUMA_BUILD 1 +#else +#define NUMA_BUILD 0 +#endif + #endif -- cgit v1.2.3 From 77f700dab4c05f8ee17584ec869672796d7bcb87 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Wed, 27 Sep 2006 01:50:07 -0700 Subject: [PATCH] Disable GFP_THISNODE in the non-NUMA case GFP_THISNODE must be set to 0 in the non numa case otherwise we disable retry and warnings for failing allocations in the SMP and UP case. Signed-off-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 8b34aabfe4c6..bf2b6bc3f6fd 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -67,7 +67,12 @@ struct vm_area_struct; #define GFP_HIGHUSER (__GFP_WAIT | __GFP_IO | __GFP_FS | __GFP_HARDWALL | \ __GFP_HIGHMEM) +#ifdef CONFIG_NUMA #define GFP_THISNODE (__GFP_THISNODE | __GFP_NOWARN | __GFP_NORETRY) +#else +#define GFP_THISNODE 0 +#endif + /* Flag - indicates that the buffer will be suitable for DMA. Ignored on some platforms, used as appropriate on others */ -- cgit v1.2.3 From d5f541ed6e31518508c688912e7464facf253c87 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Wed, 27 Sep 2006 01:50:08 -0700 Subject: [PATCH] Add node to zone for the NUMA case Add the node in order to optimize zone_to_nid. Signed-off-by: Christoph Lameter Acked-by: Paul Jackson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 6 +++++- include/linux/mmzone.h | 1 + 2 files changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 7477fb59c4f2..8e433bbc6e7e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -446,7 +446,11 @@ static inline struct zone *page_zone(struct page *page) static inline unsigned long zone_to_nid(struct zone *zone) { - return zone->zone_pgdat->node_id; +#ifdef CONFIG_NUMA + return zone->node; +#else + return 0; +#endif } static inline unsigned long page_to_nid(struct page *page) diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 562cf7a8f3ee..59855b8718a0 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -168,6 +168,7 @@ struct zone { unsigned long lowmem_reserve[MAX_NR_ZONES]; #ifdef CONFIG_NUMA + int node; /* * zone reclaim becomes active if more unmapped pages exist. */ -- cgit v1.2.3 From f4b81804a2d1ab341a4613089dc31ecce0800ed8 Mon Sep 17 00:00:00 2001 From: Jes Sorensen Date: Wed, 27 Sep 2006 01:50:10 -0700 Subject: [PATCH] do_no_pfn() Implement do_no_pfn() for handling mapping of memory without a struct page backing it. This avoids creating fake page table entries for regions which are not backed by real memory. This feature is used by the MSPEC driver and other users, where it is highly undesirable to have a struct page sitting behind the page (for instance if the page is accessed in cached mode via the struct page in parallel to the the driver accessing it uncached, which can result in data corruption on some architectures, such as ia64). This version uses specific NOPFN_{SIGBUS,OOM} return values, rather than expect all negative pfn values would be an error. It also bugs on cow mappings as this would not work with the VM. [akpm@osdl.org: micro-optimise] Signed-off-by: Jes Sorensen Cc: Hugh Dickins Cc: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 8e433bbc6e7e..22165cb18906 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -199,6 +199,7 @@ struct vm_operations_struct { void (*open)(struct vm_area_struct * area); void (*close)(struct vm_area_struct * area); struct page * (*nopage)(struct vm_area_struct * area, unsigned long address, int *type); + unsigned long (*nopfn)(struct vm_area_struct * area, unsigned long address); int (*populate)(struct vm_area_struct * area, unsigned long address, unsigned long len, pgprot_t prot, unsigned long pgoff, int nonblock); /* notification that a previously read-only page is about to become @@ -593,6 +594,12 @@ static inline int page_mapped(struct page *page) #define NOPAGE_SIGBUS (NULL) #define NOPAGE_OOM ((struct page *) (-1)) +/* + * Error return values for the *_nopfn functions + */ +#define NOPFN_SIGBUS ((unsigned long) -1) +#define NOPFN_OOM ((unsigned long) -2) + /* * Different kinds of faults, as returned by handle_mm_fault(). * Used to decide whether a process gets delivered SIGBUS or -- cgit v1.2.3 From d24afc57d51b1be41f95521e81399061fa5875a6 Mon Sep 17 00:00:00 2001 From: Rolf Eike Beer Date: Wed, 27 Sep 2006 01:50:13 -0700 Subject: [PATCH] Mark __remove_vm_area() static The function is exported but not used from anywhere else. It's also marked as "not for driver use" so noone out there should really care. Signed-off-by: Rolf Eike Beer Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index dee88c6b6fa7..ce5f1482e6be 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -62,7 +62,6 @@ extern struct vm_struct *__get_vm_area(unsigned long size, unsigned long flags, extern struct vm_struct *get_vm_area_node(unsigned long size, unsigned long flags, int node); extern struct vm_struct *remove_vm_area(void *addr); -extern struct vm_struct *__remove_vm_area(void *addr); extern int map_vm_area(struct vm_struct *area, pgprot_t prot, struct page ***pages); extern void unmap_vm_area(struct vm_struct *area); -- cgit v1.2.3 From 5da6185bca064e35aa73a7c1f27488d2b96434f4 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 27 Sep 2006 01:50:16 -0700 Subject: [PATCH] NOMMU: Set BDI capabilities for /dev/mem and /dev/kmem Set the backing device info capabilities for /dev/mem and /dev/kmem to permit direct sharing under no-MMU conditions and full mapping capabilities under MMU conditions. Make the BDI used by these available to all directly mappable character devices. Also comment the capabilities for /dev/zero. [akpm@osdl.org: ifdef reductions] Signed-off-by: David Howells Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cdev.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cdev.h b/include/linux/cdev.h index 2216638962d2..ee5f53f2ca15 100644 --- a/include/linux/cdev.h +++ b/include/linux/cdev.h @@ -23,5 +23,7 @@ void cdev_del(struct cdev *); void cd_forget(struct inode *); +extern struct backing_dev_info directly_mappable_cdev_bdi; + #endif #endif -- cgit v1.2.3 From dbf8685c8e21404e3a8ed244bd0219d3c4b89101 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 27 Sep 2006 01:50:19 -0700 Subject: [PATCH] NOMMU: Implement /proc/pid/maps for NOMMU Implement /proc/pid/maps for NOMMU by reading the vm_area_list attached to current->mm->context.vmlist. Signed-off-by: David Howells Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/proc_fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 3435ca38dd14..57f70bc8b24b 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -268,7 +268,9 @@ static inline struct proc_dir_entry *PDE(const struct inode *inode) struct proc_maps_private { struct pid *pid; struct task_struct *task; +#ifdef CONFIG_MMU struct vm_area_struct *tail_vma; +#endif }; #endif /* _LINUX_PROC_FS_H */ -- cgit v1.2.3 From f269fdd1829acc5e53bf57b145003e5733133f2b Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 27 Sep 2006 01:50:23 -0700 Subject: [PATCH] NOMMU: move the fallback arch_vma_name() to a sensible place Move the fallback arch_vma_name() to a sensible place (kernel/signal.c). Currently it's in fs/proc/task_mmu.c, a file that is dependent on both CONFIG_PROC_FS and CONFIG_MMU being enabled, but it's used from kernel/signal.c from where it is called unconditionally. [akpm@osdl.org: build fix] Signed-off-by: David Howells 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 22165cb18906..7b703b6d4358 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1131,7 +1131,7 @@ void drop_slab(void); extern int randomize_va_space; #endif -const char *arch_vma_name(struct vm_area_struct *vma); +__attribute__((weak)) const char *arch_vma_name(struct vm_area_struct *vma); #endif /* __KERNEL__ */ #endif /* _LINUX_MM_H */ -- cgit v1.2.3 From 7e96287ddc4f42081e18248b6167041c0908004c Mon Sep 17 00:00:00 2001 From: Vivek Goyal Date: Wed, 27 Sep 2006 01:50:44 -0700 Subject: [PATCH] kdump: introduce "reset_devices" command line option Resetting the devices during driver initialization can be a costly operation in terms of time (especially scsi devices). This option can be used by drivers to know that user forcibly wants the devices to be reset during initialization. This option can be useful while kernel is booting in unreliable environment. For ex. during kdump boot where devices are in unknown random state and BIOS execution has been skipped. Signed-off-by: Vivek Goyal Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/init.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/init.h b/include/linux/init.h index 6667785dd1ff..e92b1455d7af 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -68,6 +68,7 @@ extern initcall_t __security_initcall_start[], __security_initcall_end[]; /* Defined in init/main.c */ extern char saved_command_line[]; +extern unsigned int reset_devices; /* used by init/main.c */ extern void setup_arch(char **); -- cgit v1.2.3 From 8e18e2941c53416aa219708e7dcad21fb4bd6794 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Wed, 27 Sep 2006 01:50:46 -0700 Subject: [PATCH] inode_diet: Replace inode.u.generic_ip with inode.i_private The following patches reduce the size of the VFS inode structure by 28 bytes on a UP x86. (It would be more on an x86_64 system). This is a 10% reduction in the inode size on a UP kernel that is configured in a production mode (i.e., with no spinlock or other debugging functions enabled; if you want to save memory taken up by in-core inodes, the first thing you should do is disable the debugging options; they are responsible for a huge amount of bloat in the VFS inode structure). This patch: The filesystem or device-specific pointer in the inode is inside a union, which is pretty pointless given that all 30+ users of this field have been using the void pointer. Get rid of the union and rename it to i_private, with a comment to explain who is allowed to use the void pointer. This is just a cleanup, but it allows us to reuse the union 'u' for something something where the union will actually be used. [judith@osdl.org: powerpc build fix] Signed-off-by: "Theodore Ts'o" Signed-off-by: Judith Lebzelter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 1d3e601ece73..4f77ec9c3353 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -554,9 +554,7 @@ struct inode { atomic_t i_writecount; void *i_security; - union { - void *generic_ip; - } u; + void *i_private; /* fs or device private pointer */ #ifdef __NEED_I_SIZE_ORDERED seqcount_t i_size_seqcount; #endif -- cgit v1.2.3 From 4c1541680f8d189d21dd07b053bc12996574646e Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Wed, 27 Sep 2006 01:50:47 -0700 Subject: [PATCH] inode-diet: Move i_pipe into a union Move the i_pipe pointer into a union that will be shared with i_bdev and i_cdev. Signed-off-by: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 4f77ec9c3353..ca695fc8d69c 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -528,9 +528,10 @@ struct inode { #ifdef CONFIG_QUOTA struct dquot *i_dquot[MAXQUOTAS]; #endif - /* These three should probably be a union */ struct list_head i_devices; - struct pipe_inode_info *i_pipe; + union { + struct pipe_inode_info *i_pipe; + }; struct block_device *i_bdev; struct cdev *i_cdev; int i_cindex; -- cgit v1.2.3 From eaf796e7ef6014f208c409b2b14fddcfaafe7e3a Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Wed, 27 Sep 2006 01:50:48 -0700 Subject: [PATCH] inode-diet: Move i_bdev into a union Move the i_bdev pointer in struct inode into a union. Signed-off-by: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index ca695fc8d69c..98ff684a5b1c 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -531,8 +531,8 @@ struct inode { struct list_head i_devices; union { struct pipe_inode_info *i_pipe; + struct block_device *i_bdev; }; - struct block_device *i_bdev; struct cdev *i_cdev; int i_cindex; -- cgit v1.2.3 From 577c4eb09d1034d0739e3135fd2cff50588024be Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Wed, 27 Sep 2006 01:50:49 -0700 Subject: [PATCH] inode-diet: Move i_cdev into a union Move the i_cdev pointer in struct inode into a union. Signed-off-by: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 98ff684a5b1c..192e69bb55b5 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -532,8 +532,8 @@ struct inode { union { struct pipe_inode_info *i_pipe; struct block_device *i_bdev; + struct cdev *i_cdev; }; - struct cdev *i_cdev; int i_cindex; __u32 i_generation; -- cgit v1.2.3 From ba52de123d454b57369f291348266d86f4b35070 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Wed, 27 Sep 2006 01:50:49 -0700 Subject: [PATCH] inode-diet: Eliminate i_blksize from the inode structure This eliminates the i_blksize field from struct inode. Filesystems that want to provide a per-inode st_blksize can do so by providing their own getattr routine instead of using the generic_fillattr() function. Note that some filesystems were providing pretty much random (and incorrect) values for i_blksize. [bunk@stusta.de: cleanup] [akpm@osdl.org: generic_fillattr() fix] Signed-off-by: "Theodore Ts'o" Signed-off-by: Adrian Bunk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 1 - include/linux/nfsd/nfsfh.h | 10 ++-------- include/linux/smb.h | 1 - 3 files changed, 2 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 192e69bb55b5..8f74dfbb2edd 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -512,7 +512,6 @@ struct inode { struct timespec i_mtime; struct timespec i_ctime; unsigned int i_blkbits; - unsigned long i_blksize; unsigned long i_version; blkcnt_t i_blocks; unsigned short i_bytes; diff --git a/include/linux/nfsd/nfsfh.h b/include/linux/nfsd/nfsfh.h index f9edcd2ff3c8..31a3cb617ce0 100644 --- a/include/linux/nfsd/nfsfh.h +++ b/include/linux/nfsd/nfsfh.h @@ -269,14 +269,8 @@ fill_post_wcc(struct svc_fh *fhp) fhp->fh_post_uid = inode->i_uid; fhp->fh_post_gid = inode->i_gid; fhp->fh_post_size = inode->i_size; - if (inode->i_blksize) { - fhp->fh_post_blksize = inode->i_blksize; - fhp->fh_post_blocks = inode->i_blocks; - } else { - fhp->fh_post_blksize = BLOCK_SIZE; - /* how much do we care for accuracy with MinixFS? */ - fhp->fh_post_blocks = (inode->i_size+511) >> 9; - } + fhp->fh_post_blksize = BLOCK_SIZE; + fhp->fh_post_blocks = inode->i_blocks; fhp->fh_post_rdev[0] = htonl((u32)imajor(inode)); fhp->fh_post_rdev[1] = htonl((u32)iminor(inode)); fhp->fh_post_atime = inode->i_atime; diff --git a/include/linux/smb.h b/include/linux/smb.h index 6df3b1501559..f098dff93f6b 100644 --- a/include/linux/smb.h +++ b/include/linux/smb.h @@ -89,7 +89,6 @@ struct smb_fattr { struct timespec f_atime; struct timespec f_mtime; struct timespec f_ctime; - unsigned long f_blksize; unsigned long f_blocks; int f_unix; }; -- cgit v1.2.3 From ebba5f9fcb882306bef7175dee987342ec6fcf2f Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 27 Sep 2006 01:50:55 -0700 Subject: [PATCH] consistently use MAX_ERRNO in __syscall_return Consistently use MAX_ERRNO when checking for errors in __syscall_return(). [ralf@linux-mips.org: build fix] Signed-off-by: Randy Dunlap Signed-off-by: Ralf Baechle Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/err.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/err.h b/include/linux/err.h index cd3b367f7445..1ab1d44f8d3b 100644 --- a/include/linux/err.h +++ b/include/linux/err.h @@ -15,6 +15,8 @@ */ #define MAX_ERRNO 4095 +#ifndef __ASSEMBLY__ + #define IS_ERR_VALUE(x) unlikely((x) >= (unsigned long)-MAX_ERRNO) static inline void *ERR_PTR(long error) @@ -32,4 +34,6 @@ static inline long IS_ERR(const void *ptr) return IS_ERR_VALUE((unsigned long)ptr); } +#endif + #endif /* _LINUX_ERR_H */ -- cgit v1.2.3 From 07563c711fbc25389e58ab9c9f0b9de2fce56760 Mon Sep 17 00:00:00 2001 From: Michael Tokarev Date: Wed, 27 Sep 2006 01:50:56 -0700 Subject: [PATCH] EISA bus MODALIAS attributes support Add modalias attribute support for the almost forgotten now EISA bus and (at least some) EISA-aware modules. The modalias entry looks like (for an 3c509 NIC): eisa:sTCM5093 and the in-module alias like: eisa:sTCM5093* The patch moves struct eisa_device_id declaration from include/linux/eisa.h to include/linux/mod_devicetable.h (so that the former now #includes the latter), adds proper MODULE_DEVICE_TABLE(eisa, ...) statements for all drivers with EISA IDs I found (some drivers already have that DEVICE_TABLE declared), and adds recognision of __mod_eisa_device_table to scripts/mod/file2alias.c so that proper modules.alias will be generated. There's no support for /lib/modules/$kver/modules.eisamap, as it's not used by any existing tools, and because with in-kernel modalias mechanism those maps are obsolete anyway. The rationale for this patch is: a) to make EISA bus to act as other busses with modalias support, to unify driver loading b) to foget about EISA finally - with this patch, kernel (who still supports EISA) will be the only one who knows how to choose the necessary drivers for this bus ;) [akpm@osdl.org: fix the kbuild bit] Signed-off-by: Michael Tokarev Cc: Rusty Russell Cc: Randy Dunlap Acked-the-net-bits-by: Jeff Garzik Acked-the-tulip-bit-by: Valerie Henson Cc: James Bottomley Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/eisa.h | 8 +------- include/linux/mod_devicetable.h | 12 ++++++++++++ 2 files changed, 13 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/eisa.h b/include/linux/eisa.h index 4079242dced8..1ff7c1392525 100644 --- a/include/linux/eisa.h +++ b/include/linux/eisa.h @@ -3,8 +3,8 @@ #include #include +#include -#define EISA_SIG_LEN 8 #define EISA_MAX_SLOTS 8 #define EISA_MAX_RESOURCES 4 @@ -27,12 +27,6 @@ #define EISA_CONFIG_ENABLED 1 #define EISA_CONFIG_FORCED 2 -/* The EISA signature, in ASCII form, null terminated */ -struct eisa_device_id { - char sig[EISA_SIG_LEN]; - unsigned long driver_data; -}; - /* There is not much we can say about an EISA device, apart from * signature, slot number, and base address. dma_mask is set by * default to parent device mask..*/ diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index f7ca0b09075d..e0c393cc7240 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -308,4 +308,16 @@ struct input_device_id { kernel_ulong_t driver_info; }; +/* EISA */ + +#define EISA_SIG_LEN 8 + +/* The EISA signature, in ASCII form, null terminated */ +struct eisa_device_id { + char sig[EISA_SIG_LEN]; + kernel_ulong_t driver_data; +}; + +#define EISA_DEVICE_MODALIAS_FMT "eisa:s%s" + #endif /* LINUX_MOD_DEVICETABLE_H */ -- cgit v1.2.3 From c18258c6f0848f97e85287f6271c511a092bb784 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 27 Sep 2006 01:51:06 -0700 Subject: [PATCH] pid: Implement transfer_pid and use it to simplify de_thread In de_thread we move pids from one process to another, a rather ugly case. The function transfer_pid makes it clear what we are doing, and makes the action atomic. This is useful we ever want to atomically traverse the process group and session lists, in a rcu safe manner. Even if the atomic properties this change should be a win as transfer_pid should be less code to execute than executing both attach_pid and detach_pid, and this should make de_thread slightly smaller as only a single function call needs to be emitted. The only downside is that the code might be slower to execute as the odds are against transfer_pid being in cache. Signed-off-by: Eric W. Biederman Cc: Oleg Nesterov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pid.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pid.h b/include/linux/pid.h index 29960b03bef7..93da7e2d9f30 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -76,6 +76,8 @@ extern int FASTCALL(attach_pid(struct task_struct *task, enum pid_type type, int nr)); extern void FASTCALL(detach_pid(struct task_struct *task, enum pid_type)); +extern void FASTCALL(transfer_pid(struct task_struct *old, + struct task_struct *new, enum pid_type)); /* * look up a PID in the hash table. Must be called with the tasklist_lock -- cgit v1.2.3 From 66f37509fc7191df468a8d183374f48b13bacb73 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Wed, 27 Sep 2006 01:51:13 -0700 Subject: [PATCH] fs/nfs/: make code static Signed-off-by: Adrian Bunk Acked-by: Trond Myklebust Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nfs_fs.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 36f5bcf513b0..98c9b9f667a5 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -315,10 +315,6 @@ extern void nfs_end_data_update(struct inode *); extern struct nfs_open_context *get_nfs_open_context(struct nfs_open_context *ctx); extern void put_nfs_open_context(struct nfs_open_context *ctx); extern struct nfs_open_context *nfs_find_open_context(struct inode *inode, struct rpc_cred *cred, int mode); -extern struct vfsmount *nfs_do_submount(const struct vfsmount *mnt_parent, - const struct dentry *dentry, - struct nfs_fh *fh, - struct nfs_fattr *fattr); /* linux/net/ipv4/ipconfig.c: trims ip addr off front of name, too. */ extern u32 root_nfs_parse_addr(char *name); /*__init*/ -- cgit v1.2.3 From 1b79e5513d52e8533a08af35a3595dad80c74d1f Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Wed, 27 Sep 2006 01:51:14 -0700 Subject: [PATCH] add probe_kernel_address() Add a version of __get_user() which is safe to call inside mmap_sem. Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/uaccess.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include/linux') diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 391e7ed1eb3f..a48d7f11c7be 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -19,4 +19,26 @@ static inline unsigned long __copy_from_user_nocache(void *to, #endif /* ARCH_HAS_NOCACHE_UACCESS */ +/** + * probe_kernel_address(): safely attempt to read from a location + * @addr: address to read from - its type is type typeof(retval)* + * @retval: read into this variable + * + * Safely read from address @addr into variable @revtal. If a kernel fault + * happens, handle that and return -EFAULT. + * We ensure that the __get_user() is executed in atomic context so that + * do_page_fault() doesn't attempt to take mmap_sem. This makes + * probe_kernel_address() suitable for use within regions where the caller + * already holds mmap_sem, or other locks which nest inside mmap_sem. + */ +#define probe_kernel_address(addr, retval) \ + ({ \ + long ret; \ + \ + inc_preempt_count(); \ + ret = __get_user(retval, addr); \ + dec_preempt_count(); \ + ret; \ + }) + #endif /* __LINUX_UACCESS_H__ */ -- cgit v1.2.3 From 3a16f7b4a75d68364c3278523f51ac141a12758a Mon Sep 17 00:00:00 2001 From: David Brownell Date: Thu, 29 Jun 2006 12:27:23 -0700 Subject: USB: move to Move to . Signed-off-by: David Brownell Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/otg.h | 131 ++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/usb_otg.h | 131 ------------------------------------------------ 2 files changed, 131 insertions(+), 131 deletions(-) create mode 100644 include/linux/usb/otg.h delete mode 100644 include/linux/usb_otg.h (limited to 'include/linux') diff --git a/include/linux/usb/otg.h b/include/linux/usb/otg.h new file mode 100644 index 000000000000..9897f7a818c5 --- /dev/null +++ b/include/linux/usb/otg.h @@ -0,0 +1,131 @@ +// include/linux/usb/otg.h + +/* + * These APIs may be used between USB controllers. USB device drivers + * (for either host or peripheral roles) don't use these calls; they + * continue to use just usb_device and usb_gadget. + */ + + +/* OTG defines lots of enumeration states before device reset */ +enum usb_otg_state { + OTG_STATE_UNDEFINED = 0, + + /* single-role peripheral, and dual-role default-b */ + OTG_STATE_B_IDLE, + OTG_STATE_B_SRP_INIT, + OTG_STATE_B_PERIPHERAL, + + /* extra dual-role default-b states */ + OTG_STATE_B_WAIT_ACON, + OTG_STATE_B_HOST, + + /* dual-role default-a */ + OTG_STATE_A_IDLE, + OTG_STATE_A_WAIT_VRISE, + OTG_STATE_A_WAIT_BCON, + OTG_STATE_A_HOST, + OTG_STATE_A_SUSPEND, + OTG_STATE_A_PERIPHERAL, + OTG_STATE_A_WAIT_VFALL, + OTG_STATE_A_VBUS_ERR, +}; + +/* + * the otg driver needs to interact with both device side and host side + * usb controllers. it decides which controller is active at a given + * moment, using the transceiver, ID signal, HNP and sometimes static + * configuration information (including "board isn't wired for otg"). + */ +struct otg_transceiver { + struct device *dev; + const char *label; + + u8 default_a; + enum usb_otg_state state; + + struct usb_bus *host; + struct usb_gadget *gadget; + + /* to pass extra port status to the root hub */ + u16 port_status; + u16 port_change; + + /* bind/unbind the host controller */ + int (*set_host)(struct otg_transceiver *otg, + struct usb_bus *host); + + /* bind/unbind the peripheral controller */ + int (*set_peripheral)(struct otg_transceiver *otg, + struct usb_gadget *gadget); + + /* effective for B devices, ignored for A-peripheral */ + int (*set_power)(struct otg_transceiver *otg, + unsigned mA); + + /* for non-OTG B devices: set transceiver into suspend mode */ + int (*set_suspend)(struct otg_transceiver *otg, + int suspend); + + /* for B devices only: start session with A-Host */ + int (*start_srp)(struct otg_transceiver *otg); + + /* start or continue HNP role switch */ + int (*start_hnp)(struct otg_transceiver *otg); + +}; + + +/* for board-specific init logic */ +extern int otg_set_transceiver(struct otg_transceiver *); + + +/* for usb host and peripheral controller drivers */ +extern struct otg_transceiver *otg_get_transceiver(void); + +static inline int +otg_start_hnp(struct otg_transceiver *otg) +{ + return otg->start_hnp(otg); +} + + +/* for HCDs */ +static inline int +otg_set_host(struct otg_transceiver *otg, struct usb_bus *host) +{ + return otg->set_host(otg, host); +} + + +/* for usb peripheral controller drivers */ +static inline int +otg_set_peripheral(struct otg_transceiver *otg, struct usb_gadget *periph) +{ + return otg->set_peripheral(otg, periph); +} + +static inline int +otg_set_power(struct otg_transceiver *otg, unsigned mA) +{ + return otg->set_power(otg, mA); +} + +static inline int +otg_set_suspend(struct otg_transceiver *otg, int suspend) +{ + if (otg->set_suspend != NULL) + return otg->set_suspend(otg, suspend); + else + return 0; +} + +static inline int +otg_start_srp(struct otg_transceiver *otg) +{ + return otg->start_srp(otg); +} + + +/* for OTG controller drivers (and maybe other stuff) */ +extern int usb_bus_start_enum(struct usb_bus *bus, unsigned port_num); diff --git a/include/linux/usb_otg.h b/include/linux/usb_otg.h deleted file mode 100644 index f827f6e203c2..000000000000 --- a/include/linux/usb_otg.h +++ /dev/null @@ -1,131 +0,0 @@ -// include/linux/usb_otg.h - -/* - * These APIs may be used between USB controllers. USB device drivers - * (for either host or peripheral roles) don't use these calls; they - * continue to use just usb_device and usb_gadget. - */ - - -/* OTG defines lots of enumeration states before device reset */ -enum usb_otg_state { - OTG_STATE_UNDEFINED = 0, - - /* single-role peripheral, and dual-role default-b */ - OTG_STATE_B_IDLE, - OTG_STATE_B_SRP_INIT, - OTG_STATE_B_PERIPHERAL, - - /* extra dual-role default-b states */ - OTG_STATE_B_WAIT_ACON, - OTG_STATE_B_HOST, - - /* dual-role default-a */ - OTG_STATE_A_IDLE, - OTG_STATE_A_WAIT_VRISE, - OTG_STATE_A_WAIT_BCON, - OTG_STATE_A_HOST, - OTG_STATE_A_SUSPEND, - OTG_STATE_A_PERIPHERAL, - OTG_STATE_A_WAIT_VFALL, - OTG_STATE_A_VBUS_ERR, -}; - -/* - * the otg driver needs to interact with both device side and host side - * usb controllers. it decides which controller is active at a given - * moment, using the transceiver, ID signal, HNP and sometimes static - * configuration information (including "board isn't wired for otg"). - */ -struct otg_transceiver { - struct device *dev; - const char *label; - - u8 default_a; - enum usb_otg_state state; - - struct usb_bus *host; - struct usb_gadget *gadget; - - /* to pass extra port status to the root hub */ - u16 port_status; - u16 port_change; - - /* bind/unbind the host controller */ - int (*set_host)(struct otg_transceiver *otg, - struct usb_bus *host); - - /* bind/unbind the peripheral controller */ - int (*set_peripheral)(struct otg_transceiver *otg, - struct usb_gadget *gadget); - - /* effective for B devices, ignored for A-peripheral */ - int (*set_power)(struct otg_transceiver *otg, - unsigned mA); - - /* for non-OTG B devices: set transceiver into suspend mode */ - int (*set_suspend)(struct otg_transceiver *otg, - int suspend); - - /* for B devices only: start session with A-Host */ - int (*start_srp)(struct otg_transceiver *otg); - - /* start or continue HNP role switch */ - int (*start_hnp)(struct otg_transceiver *otg); - -}; - - -/* for board-specific init logic */ -extern int otg_set_transceiver(struct otg_transceiver *); - - -/* for usb host and peripheral controller drivers */ -extern struct otg_transceiver *otg_get_transceiver(void); - -static inline int -otg_start_hnp(struct otg_transceiver *otg) -{ - return otg->start_hnp(otg); -} - - -/* for HCDs */ -static inline int -otg_set_host(struct otg_transceiver *otg, struct usb_bus *host) -{ - return otg->set_host(otg, host); -} - - -/* for usb peripheral controller drivers */ -static inline int -otg_set_peripheral(struct otg_transceiver *otg, struct usb_gadget *periph) -{ - return otg->set_peripheral(otg, periph); -} - -static inline int -otg_set_power(struct otg_transceiver *otg, unsigned mA) -{ - return otg->set_power(otg, mA); -} - -static inline int -otg_set_suspend(struct otg_transceiver *otg, int suspend) -{ - if (otg->set_suspend != NULL) - return otg->set_suspend(otg, suspend); - else - return 0; -} - -static inline int -otg_start_srp(struct otg_transceiver *otg) -{ - return otg->start_srp(otg); -} - - -/* for OTG controller drivers (and maybe other stuff) */ -extern int usb_bus_start_enum(struct usb_bus *bus, unsigned port_num); -- cgit v1.2.3 From 8bb54ab573ecd1b4fe2ed66416a8d99a86e65316 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Sat, 1 Jul 2006 22:08:49 -0400 Subject: usbcore: add usb_device_driver definition This patch (as732) adds a usb_device_driver structure, for representing drivers that manage an entire USB device as opposed to just an interface. Support routines like usb_register_device_driver, usb_deregister_device_driver, usb_probe_device, and usb_unbind_device are also added. Unlike an earlier version of this patch, the new code is type-safe. To accomplish this, the existing struct driver embedded in struct usb_driver had to be wrapped in an intermediate wrapper. This enables the core to tell at runtime whether a particular struct driver belongs to a device driver or to an interface driver. Signed-off-by: Alan Stern Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 58 ++++++++++++++++++++++++++++++++++++++++++++++------- 1 file changed, 51 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index d2bd0c8e0154..b4ccce6d0982 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -540,7 +540,17 @@ struct usb_dynids { }; /** - * struct usb_driver - identifies USB driver to usbcore + * struct usbdrv_wrap - wrapper for driver-model structure + * @driver: The driver-model core driver structure. + * @for_devices: Non-zero for device drivers, 0 for interface drivers. + */ +struct usbdrv_wrap { + struct device_driver driver; + int for_devices; +}; + +/** + * struct usb_driver - identifies USB interface driver to usbcore * @name: The driver name should be unique among USB drivers, * and should normally be the same as the module name. * @probe: Called to see if the driver is willing to manage a particular @@ -567,12 +577,12 @@ struct usb_dynids { * or your driver's probe function will never get called. * @dynids: used internally to hold the list of dynamically added device * ids for this driver. - * @driver: the driver model core driver structure. + * @drvwrap: Driver-model core structure wrapper. * @no_dynamic_id: if set to 1, the USB core will not allow dynamic ids to be * added to this driver by preventing the sysfs file from being created. * - * USB drivers must provide a name, probe() and disconnect() methods, - * and an id_table. Other driver fields are optional. + * USB interface drivers must provide a name, probe() and disconnect() + * methods, and an id_table. Other driver fields are optional. * * The id_table is used in hotplugging. It holds a set of descriptors, * and specialized data may be associated with each entry. That table @@ -606,10 +616,40 @@ struct usb_driver { const struct usb_device_id *id_table; struct usb_dynids dynids; - struct device_driver driver; + struct usbdrv_wrap drvwrap; unsigned int no_dynamic_id:1; }; -#define to_usb_driver(d) container_of(d, struct usb_driver, driver) +#define to_usb_driver(d) container_of(d, struct usb_driver, drvwrap.driver) + +/** + * struct usb_device_driver - identifies USB device driver to usbcore + * @name: The driver name should be unique among USB drivers, + * and should normally be the same as the module name. + * @probe: Called to see if the driver is willing to manage a particular + * device. If it is, probe returns zero and uses dev_set_drvdata() + * to associate driver-specific data with the device. If unwilling + * to manage the device, return a negative errno value. + * @disconnect: Called when the device is no longer accessible, usually + * because it has been (or is being) disconnected or the driver's + * module is being unloaded. + * @suspend: Called when the device is going to be suspended by the system. + * @resume: Called when the device is being resumed by the system. + * @drvwrap: Driver-model core structure wrapper. + * + * USB drivers must provide all the fields listed above except drvwrap. + */ +struct usb_device_driver { + const char *name; + + int (*probe) (struct usb_device *udev); + void (*disconnect) (struct usb_device *udev); + + int (*suspend) (struct usb_device *udev, pm_message_t message); + int (*resume) (struct usb_device *udev); + struct usbdrv_wrap drvwrap; +}; +#define to_usb_device_driver(d) container_of(d, struct usb_device_driver, \ + drvwrap.driver) extern struct bus_type usb_bus_type; @@ -633,13 +673,17 @@ struct usb_class_driver { * use these in module_init()/module_exit() * and don't forget MODULE_DEVICE_TABLE(usb, ...) */ -int usb_register_driver(struct usb_driver *, struct module *); +extern int usb_register_driver(struct usb_driver *, struct module *); static inline int usb_register(struct usb_driver *driver) { return usb_register_driver(driver, THIS_MODULE); } extern void usb_deregister(struct usb_driver *); +extern int usb_register_device_driver(struct usb_device_driver *, + struct module *); +extern void usb_deregister_device_driver(struct usb_device_driver *); + extern int usb_register_dev(struct usb_interface *intf, struct usb_class_driver *class_driver); extern void usb_deregister_dev(struct usb_interface *intf, -- cgit v1.2.3 From 4d064c080265a41324d108fccc26b72106d43db3 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Sat, 1 Jul 2006 22:11:44 -0400 Subject: usbcore: track whether interfaces are suspended Currently we rely on intf->dev.power.power_state.event for tracking whether intf is suspended. This is not a reliable technique because that value is owned by the PM core, not by usbcore. This patch (as718b) adds a new flag so that we can accurately tell which interfaces are suspended and which aren't. At first one might think these flags aren't needed, since interfaces will be suspended along with their devices. It turns out there are a couple of intermediate situations where that's not quite true, such as while processing a remote-wakeup request. Signed-off-by: Alan Stern Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index b4ccce6d0982..e22f4b386605 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -102,6 +102,7 @@ enum usb_interface_condition { * number from the USB core by calling usb_register_dev(). * @condition: binding state of the interface: not bound, binding * (in probe()), bound to a driver, or unbinding (in disconnect()) + * @is_active: flag set when the interface is bound and not suspended. * @dev: driver model's view of this device * @class_dev: driver model's class view of this device. * @@ -142,6 +143,8 @@ struct usb_interface { int minor; /* minor number this interface is * bound to */ enum usb_interface_condition condition; /* state of binding */ + unsigned is_active:1; /* the interface is not suspended */ + struct device dev; /* interface specific device info */ struct class_device *class_dev; }; -- cgit v1.2.3 From f2ebf92c9e1930a8f79b7eb49a32122931929014 Mon Sep 17 00:00:00 2001 From: Ben Williamson Date: Tue, 1 Aug 2006 11:28:16 +1000 Subject: USB: gmidi: New USB MIDI Gadget class driver. This driver is glue between the USB gadget interface and the ALSA MIDI interface. It allows us to appear as a MIDI Streaming device to a host system on the other end of a USB cable. This includes linux/usb/audio.h and linux/usb/midi.h containing definitions from the relevant USB specifications for USB audio and USB MIDI devices. The following changes have been made since the first RFC posting: * Bug fixes to endpoint handling. * Workaround for USB_REQ_SET_CONFIGURATION handling, not understood yet. * Added SND and SND_RAWMIDI dependencies in Kconfig. * Moved usb_audio.h and usb_midi.h to usb/*.h * Added module parameters for ALSA card index and id. * Added module parameters for USB descriptor IDs and strings. * Removed some unneeded stuff inherited from zero.c, more to go. * Provide DECLARE_* macros for the variable-length structs. * Use kmalloc instead of usb_ep_alloc_buffer. * Limit source to 80 columns. * Return actual error code instead of -ENOMEM in a few places. Signed-off-by: Ben Williamson Cc: David Brownell Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/audio.h | 53 ++++++++++++++++++++++ include/linux/usb/midi.h | 112 ++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 165 insertions(+) create mode 100644 include/linux/usb/audio.h create mode 100644 include/linux/usb/midi.h (limited to 'include/linux') diff --git a/include/linux/usb/audio.h b/include/linux/usb/audio.h new file mode 100644 index 000000000000..6bd235994dc2 --- /dev/null +++ b/include/linux/usb/audio.h @@ -0,0 +1,53 @@ +/* + * -- USB Audio definitions. + * + * Copyright (C) 2006 Thumtronics Pty Ltd. + * Developed for Thumtronics by Grey Innovation + * Ben Williamson + * + * This software is distributed under the terms of the GNU General Public + * License ("GPL") version 2, as published by the Free Software Foundation. + * + * This file holds USB constants and structures defined + * by the USB Device Class Definition for Audio Devices. + * Comments below reference relevant sections of that document: + * + * http://www.usb.org/developers/devclass_docs/audio10.pdf + */ + +#ifndef __LINUX_USB_AUDIO_H +#define __LINUX_USB_AUDIO_H + +#include + +/* A.2 Audio Interface Subclass Codes */ +#define USB_SUBCLASS_AUDIOCONTROL 0x01 +#define USB_SUBCLASS_AUDIOSTREAMING 0x02 +#define USB_SUBCLASS_MIDISTREAMING 0x03 + +/* 4.3.2 Class-Specific AC Interface Descriptor */ +struct usb_ac_header_descriptor { + __u8 bLength; // 8+n + __u8 bDescriptorType; // USB_DT_CS_INTERFACE + __u8 bDescriptorSubtype; // USB_MS_HEADER + __le16 bcdADC; // 0x0100 + __le16 wTotalLength; // includes Unit and Terminal desc. + __u8 bInCollection; // n + __u8 baInterfaceNr[]; // [n] +} __attribute__ ((packed)); + +#define USB_DT_AC_HEADER_SIZE(n) (8+(n)) + +/* As above, but more useful for defining your own descriptors: */ +#define DECLARE_USB_AC_HEADER_DESCRIPTOR(n) \ +struct usb_ac_header_descriptor_##n { \ + __u8 bLength; \ + __u8 bDescriptorType; \ + __u8 bDescriptorSubtype; \ + __le16 bcdADC; \ + __le16 wTotalLength; \ + __u8 bInCollection; \ + __u8 baInterfaceNr[n]; \ +} __attribute__ ((packed)) + +#endif diff --git a/include/linux/usb/midi.h b/include/linux/usb/midi.h new file mode 100644 index 000000000000..11a97d5ffd34 --- /dev/null +++ b/include/linux/usb/midi.h @@ -0,0 +1,112 @@ +/* + * -- USB MIDI definitions. + * + * Copyright (C) 2006 Thumtronics Pty Ltd. + * Developed for Thumtronics by Grey Innovation + * Ben Williamson + * + * This software is distributed under the terms of the GNU General Public + * License ("GPL") version 2, as published by the Free Software Foundation. + * + * This file holds USB constants and structures defined + * by the USB Device Class Definition for MIDI Devices. + * Comments below reference relevant sections of that document: + * + * http://www.usb.org/developers/devclass_docs/midi10.pdf + */ + +#ifndef __LINUX_USB_MIDI_H +#define __LINUX_USB_MIDI_H + +#include + +/* A.1 MS Class-Specific Interface Descriptor Subtypes */ +#define USB_MS_HEADER 0x01 +#define USB_MS_MIDI_IN_JACK 0x02 +#define USB_MS_MIDI_OUT_JACK 0x03 +#define USB_MS_ELEMENT 0x04 + +/* A.2 MS Class-Specific Endpoint Descriptor Subtypes */ +#define USB_MS_GENERAL 0x01 + +/* A.3 MS MIDI IN and OUT Jack Types */ +#define USB_MS_EMBEDDED 0x01 +#define USB_MS_EXTERNAL 0x02 + +/* 6.1.2.1 Class-Specific MS Interface Header Descriptor */ +struct usb_ms_header_descriptor { + __u8 bLength; + __u8 bDescriptorType; + __u8 bDescriptorSubtype; + __le16 bcdMSC; + __le16 wTotalLength; +} __attribute__ ((packed)); + +#define USB_DT_MS_HEADER_SIZE 7 + +/* 6.1.2.2 MIDI IN Jack Descriptor */ +struct usb_midi_in_jack_descriptor { + __u8 bLength; + __u8 bDescriptorType; // USB_DT_CS_INTERFACE + __u8 bDescriptorSubtype; // USB_MS_MIDI_IN_JACK + __u8 bJackType; // USB_MS_EMBEDDED/EXTERNAL + __u8 bJackID; + __u8 iJack; +} __attribute__ ((packed)); + +#define USB_DT_MIDI_IN_SIZE 6 + +struct usb_midi_source_pin { + __u8 baSourceID; + __u8 baSourcePin; +} __attribute__ ((packed)); + +/* 6.1.2.3 MIDI OUT Jack Descriptor */ +struct usb_midi_out_jack_descriptor { + __u8 bLength; + __u8 bDescriptorType; // USB_DT_CS_INTERFACE + __u8 bDescriptorSubtype; // USB_MS_MIDI_OUT_JACK + __u8 bJackType; // USB_MS_EMBEDDED/EXTERNAL + __u8 bJackID; + __u8 bNrInputPins; // p + struct usb_midi_source_pin pins[]; // [p] + /*__u8 iJack; -- ommitted due to variable-sized pins[] */ +} __attribute__ ((packed)); + +#define USB_DT_MIDI_OUT_SIZE(p) (7 + 2 * (p)) + +/* As above, but more useful for defining your own descriptors: */ +#define DECLARE_USB_MIDI_OUT_JACK_DESCRIPTOR(p) \ +struct usb_midi_out_jack_descriptor_##p { \ + __u8 bLength; \ + __u8 bDescriptorType; \ + __u8 bDescriptorSubtype; \ + __u8 bJackType; \ + __u8 bJackID; \ + __u8 bNrInputPins; \ + struct usb_midi_source_pin pins[p]; \ + __u8 iJack; \ +} __attribute__ ((packed)) + +/* 6.2.2 Class-Specific MS Bulk Data Endpoint Descriptor */ +struct usb_ms_endpoint_descriptor { + __u8 bLength; // 4+n + __u8 bDescriptorType; // USB_DT_CS_ENDPOINT + __u8 bDescriptorSubtype; // USB_MS_GENERAL + __u8 bNumEmbMIDIJack; // n + __u8 baAssocJackID[]; // [n] +} __attribute__ ((packed)); + +#define USB_DT_MS_ENDPOINT_SIZE(n) (4 + (n)) + +/* As above, but more useful for defining your own descriptors: */ +#define DECLARE_USB_MS_ENDPOINT_DESCRIPTOR(n) \ +struct usb_ms_endpoint_descriptor_##n { \ + __u8 bLength; \ + __u8 bDescriptorType; \ + __u8 bDescriptorSubtype; \ + __u8 bNumEmbMIDIJack; \ + __u8 baAssocJackID[n]; \ +} __attribute__ ((packed)) + +#endif -- cgit v1.2.3 From 3d5b2510f6e361e2203e163c03b93d0026de5629 Mon Sep 17 00:00:00 2001 From: Jesper Juhl Date: Sun, 30 Jul 2006 18:43:43 +0200 Subject: USB: making the kernel -Wshadow clean - USB & completion include/linux/usb.h causes a lot of -Wshadow warnings - fix them. include/linux/usb.h:901: warning: declaration of 'complete' shadows a global declaration include/linux/completion.h:52: warning: shadowed declaration is here include/linux/usb.h:932: warning: declaration of 'complete' shadows a global declaration include/linux/completion.h:52: warning: shadowed declaration is here include/linux/usb.h:967: warning: declaration of 'complete' shadows a global declaration include/linux/completion.h:52: warning: shadowed declaration is here Signed-off-by: Jesper Juhl Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index e22f4b386605..3d5cfa731680 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -932,7 +932,7 @@ struct urb * @setup_packet: pointer to the setup_packet buffer * @transfer_buffer: pointer to the transfer buffer * @buffer_length: length of the transfer buffer - * @complete: pointer to the usb_complete_t function + * @complete_fn: pointer to the usb_complete_t function * @context: what to set the urb context to. * * Initializes a control urb with the proper information needed to submit @@ -944,7 +944,7 @@ static inline void usb_fill_control_urb (struct urb *urb, unsigned char *setup_packet, void *transfer_buffer, int buffer_length, - usb_complete_t complete, + usb_complete_t complete_fn, void *context) { spin_lock_init(&urb->lock); @@ -953,7 +953,7 @@ static inline void usb_fill_control_urb (struct urb *urb, urb->setup_packet = setup_packet; urb->transfer_buffer = transfer_buffer; urb->transfer_buffer_length = buffer_length; - urb->complete = complete; + urb->complete = complete_fn; urb->context = context; } @@ -964,7 +964,7 @@ static inline void usb_fill_control_urb (struct urb *urb, * @pipe: the endpoint pipe * @transfer_buffer: pointer to the transfer buffer * @buffer_length: length of the transfer buffer - * @complete: pointer to the usb_complete_t function + * @complete_fn: pointer to the usb_complete_t function * @context: what to set the urb context to. * * Initializes a bulk urb with the proper information needed to submit it @@ -975,7 +975,7 @@ static inline void usb_fill_bulk_urb (struct urb *urb, unsigned int pipe, void *transfer_buffer, int buffer_length, - usb_complete_t complete, + usb_complete_t complete_fn, void *context) { spin_lock_init(&urb->lock); @@ -983,7 +983,7 @@ static inline void usb_fill_bulk_urb (struct urb *urb, urb->pipe = pipe; urb->transfer_buffer = transfer_buffer; urb->transfer_buffer_length = buffer_length; - urb->complete = complete; + urb->complete = complete_fn; urb->context = context; } @@ -994,7 +994,7 @@ static inline void usb_fill_bulk_urb (struct urb *urb, * @pipe: the endpoint pipe * @transfer_buffer: pointer to the transfer buffer * @buffer_length: length of the transfer buffer - * @complete: pointer to the usb_complete_t function + * @complete_fn: pointer to the usb_complete_t function * @context: what to set the urb context to. * @interval: what to set the urb interval to, encoded like * the endpoint descriptor's bInterval value. @@ -1010,7 +1010,7 @@ static inline void usb_fill_int_urb (struct urb *urb, unsigned int pipe, void *transfer_buffer, int buffer_length, - usb_complete_t complete, + usb_complete_t complete_fn, void *context, int interval) { @@ -1019,7 +1019,7 @@ static inline void usb_fill_int_urb (struct urb *urb, urb->pipe = pipe; urb->transfer_buffer = transfer_buffer; urb->transfer_buffer_length = buffer_length; - urb->complete = complete; + urb->complete = complete_fn; urb->context = context; if (dev->speed == USB_SPEED_HIGH) urb->interval = 1 << (interval - 1); -- cgit v1.2.3 From b7cfaaaf86571732c7728e95a2231a860385463c Mon Sep 17 00:00:00 2001 From: "Luiz Fernando N. Capitulino" Date: Wed, 27 Sep 2006 11:58:53 -0700 Subject: USB: New functions to check endpoints info. These functions makes USB driver's code simpler when dealing with endpoints by avoiding them from accessing the endpoint's descriptor structure directly when they only need to know the endpoint's transfer type and/or direction. Please, read each functions' documentation in order to know how to use them. Signed-off-by: Luiz Fernando N. Capitulino Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index 3d5cfa731680..f807479ef65b 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -467,6 +467,20 @@ static inline int usb_make_path (struct usb_device *dev, char *buf, /*-------------------------------------------------------------------------*/ +extern int usb_endpoint_dir_in(const struct usb_endpoint_descriptor *epd); +extern int usb_endpoint_dir_out(const struct usb_endpoint_descriptor *epd); +extern int usb_endpoint_xfer_bulk(const struct usb_endpoint_descriptor *epd); +extern int usb_endpoint_xfer_int(const struct usb_endpoint_descriptor *epd); +extern int usb_endpoint_xfer_isoc(const struct usb_endpoint_descriptor *epd); +extern int usb_endpoint_is_bulk_in(const struct usb_endpoint_descriptor *epd); +extern int usb_endpoint_is_bulk_out(const struct usb_endpoint_descriptor *epd); +extern int usb_endpoint_is_int_in(const struct usb_endpoint_descriptor *epd); +extern int usb_endpoint_is_int_out(const struct usb_endpoint_descriptor *epd); +extern int usb_endpoint_is_isoc_in(const struct usb_endpoint_descriptor *epd); +extern int usb_endpoint_is_isoc_out(const struct usb_endpoint_descriptor *epd); + +/*-------------------------------------------------------------------------*/ + #define USB_DEVICE_ID_MATCH_DEVICE \ (USB_DEVICE_ID_MATCH_VENDOR | USB_DEVICE_ID_MATCH_PRODUCT) #define USB_DEVICE_ID_MATCH_DEV_RANGE \ -- cgit v1.2.3 From dfe0d3ba20e860d0b9a16c4c6524180b8f93be05 Mon Sep 17 00:00:00 2001 From: Matthew Dharm Date: Sun, 13 Aug 2006 17:30:14 -0700 Subject: USB Storage: add rio karma eject support This changeset from Keith Bennett (via Bob Copeland) moves the Karma initializer to its own file and adds trapping of the START_STOP command to enable eject of the device. Signed-off-by: Keith Bennett Signed-off-by: Bob Copeland Signed-off-by: Matthew Dharm Signed-off-by: Greg Kroah-Hartman --- include/linux/usb_usual.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb_usual.h b/include/linux/usb_usual.h index e7fc5fed5b98..2ae76fe52ff7 100644 --- a/include/linux/usb_usual.h +++ b/include/linux/usb_usual.h @@ -108,6 +108,9 @@ enum { US_DO_ALL_FLAGS }; #ifdef CONFIG_USB_STORAGE_ALAUDA #define US_PR_ALAUDA 0xf4 /* Alauda chipsets */ #endif +#ifdef CONFIG_USB_STORAGE_KARMA +#define US_PR_KARMA 0xf5 /* Rio Karma */ +#endif #define US_PR_DEVICE 0xff /* Use device's value */ -- cgit v1.2.3 From 095bc335360a51623dd8571839bbf465851a7f4b Mon Sep 17 00:00:00 2001 From: "Luiz Fernando N. Capitulino" Date: Sat, 26 Aug 2006 23:48:11 -0300 Subject: USB core: Use const where possible. This patch marks some USB core's functions parameters as const. This improves the design (we're saying to the caller that its parameter is not going to be modified) and may help in compiler's optimisation work. Signed-off-by: Luiz Fernando N. Capitulino Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index f807479ef65b..26d8a5f36896 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -387,7 +387,7 @@ extern void usb_put_dev(struct usb_device *dev); #define usb_unlock_device(udev) up(&(udev)->dev.sem) #define usb_trylock_device(udev) down_trylock(&(udev)->dev.sem) extern int usb_lock_device_for_reset(struct usb_device *udev, - struct usb_interface *iface); + const struct usb_interface *iface); /* USB port reset for device reinitialization */ extern int usb_reset_device(struct usb_device *dev); @@ -426,10 +426,10 @@ const struct usb_device_id *usb_match_id(struct usb_interface *interface, extern struct usb_interface *usb_find_interface(struct usb_driver *drv, int minor); -extern struct usb_interface *usb_ifnum_to_if(struct usb_device *dev, +extern struct usb_interface *usb_ifnum_to_if(const struct usb_device *dev, unsigned ifnum); extern struct usb_host_interface *usb_altnum_to_altsetting( - struct usb_interface *intf, unsigned int altnum); + const struct usb_interface *intf, unsigned int altnum); /** @@ -1064,14 +1064,14 @@ void usb_buffer_unmap (struct urb *urb); #endif struct scatterlist; -int usb_buffer_map_sg (struct usb_device *dev, unsigned pipe, - struct scatterlist *sg, int nents); +int usb_buffer_map_sg(const struct usb_device *dev, unsigned pipe, + struct scatterlist *sg, int nents); #if 0 -void usb_buffer_dmasync_sg (struct usb_device *dev, unsigned pipe, - struct scatterlist *sg, int n_hw_ents); +void usb_buffer_dmasync_sg(const struct usb_device *dev, unsigned pipe, + struct scatterlist *sg, int n_hw_ents); #endif -void usb_buffer_unmap_sg (struct usb_device *dev, unsigned pipe, - struct scatterlist *sg, int n_hw_ents); +void usb_buffer_unmap_sg(const struct usb_device *dev, unsigned pipe, + struct scatterlist *sg, int n_hw_ents); /*-------------------------------------------------------------------* * SYNCHRONOUS CALL SUPPORT * -- cgit v1.2.3 From 088dc270e1da03744d977cbd9edd4311af142348 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Mon, 21 Aug 2006 12:08:19 -0400 Subject: usbcore: help drivers to change device configs It's generally a bad idea for USB interface drivers to try to change a device's configuration, and usbcore doesn't provide any way for them to do it. However in a few exceptional circumstances it can make sense. This patch (as767) adds a roundabout mechanism to help drivers that may need it. Signed-off-by: Alan Stern Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index 26d8a5f36896..f104efa04d79 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -1099,6 +1099,9 @@ extern int usb_clear_halt(struct usb_device *dev, int pipe); extern int usb_reset_configuration(struct usb_device *dev); extern int usb_set_interface(struct usb_device *dev, int ifnum, int alternate); +/* this request isn't really synchronous, but it belongs with the others */ +extern int usb_driver_set_configuration(struct usb_device *udev, int config); + /* * timeouts, in milliseconds, used for sending/receiving control messages * they typically complete within a few frames (msec) after they're issued -- cgit v1.2.3 From a6d2bb9ff919b4685bd684620ec7a1ffa8bf2349 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Wed, 30 Aug 2006 11:27:36 -0400 Subject: USB: remove struct usb_operations All of the currently-supported USB host controller drivers use the HCD bus-glue framework. As part of the program for flattening out the glue layer, this patch (as769) removes the usb_operations structure. All function calls now go directly to the HCD routines (slightly renamed to remain within the "usb_" namespace). The patch also removes usb_alloc_bus(), because it's not useful in the HCD framework and it wasn't referenced anywhere. Signed-off-by: Alan Stern Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index f104efa04d79..4709033f8fa7 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -257,8 +257,6 @@ int __usb_get_extra_descriptor(char *buffer, unsigned size, /* ----------------------------------------------------------------------- */ -struct usb_operations; - /* USB device number allocation bitmap */ struct usb_devmap { unsigned long devicemap[128 / (8*sizeof(unsigned long))]; @@ -279,7 +277,6 @@ struct usb_bus { * round-robin allocation */ struct usb_devmap devmap; /* device address allocation map */ - struct usb_operations *op; /* Operations (specific to the HC) */ struct usb_device *root_hub; /* Root hub */ struct list_head bus_list; /* list of busses */ void *hcpriv; /* Host Controller private data */ @@ -1051,7 +1048,6 @@ extern int usb_submit_urb(struct urb *urb, gfp_t mem_flags); extern int usb_unlink_urb(struct urb *urb); extern void usb_kill_urb(struct urb *urb); -#define HAVE_USB_BUFFERS void *usb_buffer_alloc (struct usb_device *dev, size_t size, gfp_t mem_flags, dma_addr_t *dma); void usb_buffer_free (struct usb_device *dev, size_t size, -- cgit v1.2.3 From dd990f16a39d4e615c0b70a0ab50b79b32bfb16d Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Wed, 30 Aug 2006 11:29:56 -0400 Subject: usbcore: Add flag for whether a host controller uses DMA This patch (as770b) introduces a new field to usb_bus: a flag indicating whether or not the host controller uses DMA. This serves to encapsulate the computation. It also means we will have only one spot to update if the DMA API changes. Signed-off-by: Alan Stern Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index 4709033f8fa7..09661759621f 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -269,6 +269,7 @@ struct usb_bus { struct device *controller; /* host/master side hardware */ int busnum; /* Bus number (in order of reg) */ char *bus_name; /* stable id (PCI slot_name etc) */ + u8 uses_dma; /* Does the host controller use DMA? */ u8 otg_port; /* 0, or number of OTG/HNP port */ unsigned is_b_host:1; /* true during some HNP roleswitches */ unsigned b_hnp_enable:1; /* OTG: did A-Host enable HNP? */ -- cgit v1.2.3 From 1720058343fa43a1a25bfad9e62ea06e7e9743b6 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Wed, 30 Aug 2006 11:32:52 -0400 Subject: usbcore: trim down usb_bus structure As part of the ongoing program to flatten out the HCD bus-glue layer, this patch (as771b) eliminates the hcpriv, release, and kref fields from struct usb_bus. hcpriv and release were not being used for anything worthwhile, and kref has been moved into the enclosing usb_hcd structure. Along with those changes, the patch gets rid of usb_bus_get and usb_bus_put, replacing them with usb_get_hcd and usb_put_hcd. The one interesting aspect is that the dev_set_drvdata call was removed from usb_put_hcd, where it clearly doesn't belong. This means the driver private data won't get reset to NULL. It shouldn't cause any problems, since the private data is undefined when no driver is bound. Signed-off-by: Alan Stern Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index 09661759621f..c66303285a45 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -280,7 +280,6 @@ struct usb_bus { struct usb_devmap devmap; /* device address allocation map */ struct usb_device *root_hub; /* Root hub */ struct list_head bus_list; /* list of busses */ - void *hcpriv; /* Host Controller private data */ int bandwidth_allocated; /* on this bus: how much of the time * reserved for periodic (intr/iso) @@ -295,8 +294,6 @@ struct usb_bus { struct dentry *usbfs_dentry; /* usbfs dentry entry for the bus */ struct class_device *class_dev; /* class device for this bus */ - struct kref kref; /* reference counting for this bus */ - void (*release)(struct usb_bus *bus); #if defined(CONFIG_USB_MON) struct mon_bus *mon_bus; /* non-null when associated */ -- cgit v1.2.3 From b6956ffa595db97656d5901ca8fec77ef272d41a Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Wed, 30 Aug 2006 15:46:48 -0400 Subject: usbcore: store each usb_device's level in the tree This patch (as778) adds a field to struct usb_device to store the device's level in the USB tree. In itself this number isn't really important. But the overhead is very low, and in a later patch it will be used for preventing bogus warnings from the lockdep checker. Signed-off-by: Alan Stern Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index c66303285a45..df5c93eb3ce9 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -348,6 +348,7 @@ struct usb_device { unsigned short bus_mA; /* Current available from the bus */ u8 portnum; /* Parent port number (origin 1) */ + u8 level; /* Number of USB hub ancestors */ int have_langid; /* whether string_langid is valid */ int string_langid; /* language ID for strings */ -- cgit v1.2.3 From 645daaab0b6adc35c1838df2a82f9d729fdb1767 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Wed, 30 Aug 2006 15:47:02 -0400 Subject: usbcore: add autosuspend/autoresume infrastructure This patch (as739) adds the basic infrastructure for USB autosuspend and autoresume. The main features are: PM usage counters added to struct usb_device and struct usb_interface, indicating whether it's okay to autosuspend them or they are currently in use. Flag added to usb_device indicating whether the current suspend/resume operation originated from outside or as an autosuspend/autoresume. Flag added to usb_driver indicating whether the driver supports autosuspend. If not, no device bound to the driver will be autosuspended. Mutex added to usb_device for protecting PM operations. Unlike the device semaphore, the locking rule for the pm_mutex is that you must acquire the locks going _up_ the device tree. New routines handling autosuspend/autoresume requests for interfaces and devices. Suspend and resume requests are propagated up the device tree (but not outside the USB subsystem). work_struct added to usb_device, for carrying out delayed autosuspend requests. Autoresume added (and autosuspend prevented) during probe and disconnect. Signed-off-by: Alan Stern Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index df5c93eb3ce9..0da15b0b02be 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -19,6 +19,7 @@ #include /* for struct file_operations */ #include /* for struct completion */ #include /* for current && schedule_timeout */ +#include /* for struct mutex */ struct usb_device; struct usb_driver; @@ -103,8 +104,12 @@ enum usb_interface_condition { * @condition: binding state of the interface: not bound, binding * (in probe()), bound to a driver, or unbinding (in disconnect()) * @is_active: flag set when the interface is bound and not suspended. + * @needs_remote_wakeup: flag set when the driver requires remote-wakeup + * capability during autosuspend. * @dev: driver model's view of this device * @class_dev: driver model's class view of this device. + * @pm_usage_cnt: PM usage counter for this interface; autosuspend is not + * allowed unless the counter is 0. * * USB device drivers attach to interfaces on a physical device. Each * interface encapsulates a single high level function, such as feeding @@ -144,9 +149,11 @@ struct usb_interface { * bound to */ enum usb_interface_condition condition; /* state of binding */ unsigned is_active:1; /* the interface is not suspended */ + unsigned needs_remote_wakeup:1; /* driver requires remote wakeup */ struct device dev; /* interface specific device info */ struct class_device *class_dev; + int pm_usage_cnt; /* usage counter for autosuspend */ }; #define to_usb_interface(d) container_of(d, struct usb_interface, dev) #define interface_to_usbdev(intf) \ @@ -372,6 +379,15 @@ struct usb_device { int maxchild; /* Number of ports if hub */ struct usb_device *children[USB_MAXCHILDREN]; + +#ifdef CONFIG_PM + struct work_struct autosuspend; /* for delayed autosuspends */ + struct mutex pm_mutex; /* protects PM operations */ + int pm_usage_cnt; /* usage counter for autosuspend */ + + unsigned auto_pm:1; /* autosuspend/resume in progress */ + unsigned do_remote_wakeup:1; /* remote wakeup should be enabled */ +#endif }; #define to_usb_device(d) container_of(d, struct usb_device, dev) @@ -392,6 +408,17 @@ extern int usb_reset_composite_device(struct usb_device *dev, extern struct usb_device *usb_find_device(u16 vendor_id, u16 product_id); +/* USB autosuspend and autoresume */ +#ifdef CONFIG_USB_SUSPEND +extern int usb_autopm_get_interface(struct usb_interface *intf); +extern void usb_autopm_put_interface(struct usb_interface *intf); + +#else +#define usb_autopm_get_interface(intf) 0 +#define usb_autopm_put_interface(intf) do {} while (0) +#endif + + /*-------------------------------------------------------------------------*/ /* for drivers using iso endpoints */ @@ -593,6 +620,8 @@ struct usbdrv_wrap { * @drvwrap: Driver-model core structure wrapper. * @no_dynamic_id: if set to 1, the USB core will not allow dynamic ids to be * added to this driver by preventing the sysfs file from being created. + * @supports_autosuspend: if set to 0, the USB core will not allow autosuspend + * for interfaces bound to this driver. * * USB interface drivers must provide a name, probe() and disconnect() * methods, and an id_table. Other driver fields are optional. @@ -631,6 +660,7 @@ struct usb_driver { struct usb_dynids dynids; struct usbdrv_wrap drvwrap; unsigned int no_dynamic_id:1; + unsigned int supports_autosuspend:1; }; #define to_usb_driver(d) container_of(d, struct usb_driver, drvwrap.driver) @@ -648,6 +678,8 @@ struct usb_driver { * @suspend: Called when the device is going to be suspended by the system. * @resume: Called when the device is being resumed by the system. * @drvwrap: Driver-model core structure wrapper. + * @supports_autosuspend: if set to 0, the USB core will not allow autosuspend + * for devices bound to this driver. * * USB drivers must provide all the fields listed above except drvwrap. */ @@ -660,6 +692,7 @@ struct usb_device_driver { int (*suspend) (struct usb_device *udev, pm_message_t message); int (*resume) (struct usb_device *udev); struct usbdrv_wrap drvwrap; + unsigned int supports_autosuspend:1; }; #define to_usb_device_driver(d) container_of(d, struct usb_device_driver, \ drvwrap.driver) -- cgit v1.2.3 From 54bb3a94b192be09feb85993b664ff118d6433d0 Mon Sep 17 00:00:00 2001 From: Jeff Garzik Date: Wed, 27 Sep 2006 22:20:11 -0400 Subject: [libata] Use new PCI_VDEVICE() macro to dramatically shorten ID lists 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 d6a3d4b345fc..df44b09fbae8 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -109,6 +109,10 @@ static inline u32 ata_msg_init(int dval, int default_msg_enable_bits) #define ATA_TAG_POISON 0xfafbfcfdU /* move to PCI layer? */ +#define PCI_VDEVICE(vendor, device) \ + PCI_VENDOR_ID_##vendor, (device), \ + PCI_ANY_ID, PCI_ANY_ID, 0, 0 + static inline struct device *pci_dev_to_dev(struct pci_dev *pdev) { return &pdev->dev; -- cgit v1.2.3 From 29fa06c1292f473ae51a84f55c8fe22179bc1080 Mon Sep 17 00:00:00 2001 From: Rudolf Marek Date: Mon, 28 Aug 2006 14:40:17 +0200 Subject: hwmon: New driver k8temp Add support for the temperature sensor(s) found in AMD K8 CPUs. Signed-off-by: Rudolf Marek Signed-off-by: Jean Delvare Signed-off-by: Greg Kroah-Hartman --- 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 ab032ceafa84..61db1907f06f 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -479,6 +479,7 @@ #define PCI_VENDOR_ID_AMD 0x1022 #define PCI_DEVICE_ID_AMD_K8_NB 0x1100 +#define PCI_DEVICE_ID_AMD_K8_NB_MISC 0x1103 #define PCI_DEVICE_ID_AMD_LANCE 0x2000 #define PCI_DEVICE_ID_AMD_LANCE_HOME 0x2001 #define PCI_DEVICE_ID_AMD_SCSI 0x2020 -- cgit v1.2.3 From e0318ebff4d96131bb3524308b845f642e64df81 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Tue, 26 Sep 2006 14:50:20 -0400 Subject: USB: fix autosuspend when CONFIG_PM isn't set This patch (as791b) fixes things up to avoid compiler warnings or errors when CONFIG_USB_SUSPEND or CONFIG_PM isn't set. Signed-off-by: Alan Stern Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index 0da15b0b02be..190cc1b78fe2 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -380,10 +380,10 @@ struct usb_device { int maxchild; /* Number of ports if hub */ struct usb_device *children[USB_MAXCHILDREN]; + int pm_usage_cnt; /* usage counter for autosuspend */ #ifdef CONFIG_PM struct work_struct autosuspend; /* for delayed autosuspends */ struct mutex pm_mutex; /* protects PM operations */ - int pm_usage_cnt; /* usage counter for autosuspend */ unsigned auto_pm:1; /* autosuspend/resume in progress */ unsigned do_remote_wakeup:1; /* remote wakeup should be enabled */ -- cgit v1.2.3 From 2a50f28c326d20ab4556be1b867ecddf6aefbb88 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 26 Sep 2006 21:22:08 -0700 Subject: [ATALK]: endianness annotations Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/atalk.h | 40 +--------------------------------------- 1 file changed, 1 insertion(+), 39 deletions(-) (limited to 'include/linux') diff --git a/include/linux/atalk.h b/include/linux/atalk.h index 6ba3aa8a81f4..75b8baca08f3 100644 --- a/include/linux/atalk.h +++ b/include/linux/atalk.h @@ -88,15 +88,7 @@ static inline struct atalk_sock *at_sk(struct sock *sk) #include struct ddpehdr { -#ifdef __LITTLE_ENDIAN_BITFIELD - __u16 deh_len:10, - deh_hops:4, - deh_pad:2; -#else - __u16 deh_pad:2, - deh_hops:4, - deh_len:10; -#endif + __be16 deh_len_hops; /* lower 10 bits are length, next 4 - hops */ __be16 deh_sum; __be16 deh_dnet; __be16 deh_snet; @@ -112,36 +104,6 @@ static __inline__ struct ddpehdr *ddp_hdr(struct sk_buff *skb) return (struct ddpehdr *)skb->h.raw; } -/* - * Don't drop the struct into the struct above. You'll get some - * surprise padding. - */ -struct ddpebits { -#ifdef __LITTLE_ENDIAN_BITFIELD - __u16 deh_len:10, - deh_hops:4, - deh_pad:2; -#else - __u16 deh_pad:2, - deh_hops:4, - deh_len:10; -#endif -}; - -/* Short form header */ -struct ddpshdr { -#ifdef __LITTLE_ENDIAN_BITFIELD - __u16 dsh_len:10, - dsh_pad:6; -#else - __u16 dsh_pad:6, - dsh_len:10; -#endif - __u8 dsh_dport; - __u8 dsh_sport; - /* And netatalk apps expect to stick the type in themselves */ -}; - /* AppleTalk AARP headers */ struct elapaarp { __be16 hw_type; -- cgit v1.2.3 From 0ac0760a57a6b1eb75c21a590e578be5dfc2f88b Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 26 Sep 2006 21:23:16 -0700 Subject: [TR]: endiannness annotations Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/trdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/trdevice.h b/include/linux/trdevice.h index 99e02ef54c47..bfc84a7aecc5 100644 --- a/include/linux/trdevice.h +++ b/include/linux/trdevice.h @@ -28,7 +28,7 @@ #include #ifdef __KERNEL__ -extern unsigned short tr_type_trans(struct sk_buff *skb, struct net_device *dev); +extern __be16 tr_type_trans(struct sk_buff *skb, struct net_device *dev); extern void tr_source_route(struct sk_buff *skb, struct trh_hdr *trh, struct net_device *dev); extern struct net_device *alloc_trdev(int sizeof_priv); -- cgit v1.2.3 From 046d033148e6936ee2466d38214cf0743a210f39 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 26 Sep 2006 21:24:24 -0700 Subject: [IPV4]: headers endianness Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/ip.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ip.h b/include/linux/ip.h index 2f4600146f83..6b25d36fc54c 100644 --- a/include/linux/ip.h +++ b/include/linux/ip.h @@ -96,7 +96,7 @@ struct iphdr { __be16 frag_off; __u8 ttl; __u8 protocol; - __u16 check; + __be16 check; __be32 saddr; __be32 daddr; /*The options start here. */ @@ -105,22 +105,22 @@ struct iphdr { struct ip_auth_hdr { __u8 nexthdr; __u8 hdrlen; /* This one is measured in 32 bit units! */ - __u16 reserved; - __u32 spi; - __u32 seq_no; /* Sequence number */ + __be16 reserved; + __be32 spi; + __be32 seq_no; /* Sequence number */ __u8 auth_data[0]; /* Variable len but >=4. Mind the 64 bit alignment! */ }; struct ip_esp_hdr { - __u32 spi; - __u32 seq_no; /* Sequence number */ + __be32 spi; + __be32 seq_no; /* Sequence number */ __u8 enc_data[0]; /* Variable len but >=8. Mind the 64 bit alignment! */ }; struct ip_comp_hdr { __u8 nexthdr; __u8 flags; - __u16 cpi; + __be16 cpi; }; #endif /* _LINUX_IP_H */ -- cgit v1.2.3 From a61ced5d1c2e773620d7855ea2009d770c10a6e6 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 26 Sep 2006 21:27:54 -0700 Subject: [IPV4]: inet_select_addr() annotations argument and return value are net-endian. Annotated function and inferred net-endian variables in callers. Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/inetdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index 92297ff24e85..40d07d0b896b 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -110,7 +110,7 @@ extern int devinet_ioctl(unsigned int cmd, void __user *); extern void devinet_init(void); extern struct in_device *inetdev_init(struct net_device *dev); extern struct in_device *inetdev_by_index(int); -extern u32 inet_select_addr(const struct net_device *dev, u32 dst, int scope); +extern __be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope); extern u32 inet_confirm_addr(const struct net_device *dev, u32 dst, u32 local, int scope); extern struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, u32 prefix, u32 mask); extern void inet_forward_change(void); -- cgit v1.2.3 From a60c4923da795c74db9ff61a60e2f1df5754e4ce Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 26 Sep 2006 21:28:34 -0700 Subject: [IPV4]: ip_check_mc() annotations annotated arguments Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/igmp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/igmp.h b/include/linux/igmp.h index 899c3d4776f3..8e7eedb3a574 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -197,7 +197,7 @@ struct ip_mc_list #define IGMPV3_QQIC(value) IGMPV3_EXP(0x80, 4, 3, value) #define IGMPV3_MRC(value) IGMPV3_EXP(0x80, 4, 3, value) -extern int ip_check_mc(struct in_device *dev, u32 mc_addr, u32 src_addr, u16 proto); +extern int ip_check_mc(struct in_device *dev, __be32 mc_addr, __be32 src_addr, u16 proto); extern int igmp_rcv(struct sk_buff *); extern int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr); extern int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr); -- cgit v1.2.3 From ff428d72c59b35e4ba34bc1b487e707648010fe3 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 26 Sep 2006 22:13:35 -0700 Subject: [IPV4]: inet_addr_onlink() annotated Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/inetdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index 40d07d0b896b..5ae09372c144 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -105,7 +105,7 @@ extern int register_inetaddr_notifier(struct notifier_block *nb); extern int unregister_inetaddr_notifier(struct notifier_block *nb); extern struct net_device *ip_dev_find(u32 addr); -extern int inet_addr_onlink(struct in_device *in_dev, u32 a, u32 b); +extern int inet_addr_onlink(struct in_device *in_dev, __be32 a, __be32 b); extern int devinet_ioctl(unsigned int cmd, void __user *); extern void devinet_init(void); extern struct in_device *inetdev_init(struct net_device *dev); -- cgit v1.2.3 From a144ea4b7a13087081ab5402fa9ad0bcfd249e67 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 28 Sep 2006 18:00:55 -0700 Subject: [IPV4]: annotate struct in_ifaddr ifa_local, ifa_address, ifa_mask, ifa_broadcast and ifa_anycast are net-endian. Annotated them and variables that are inferred to be net-endian. Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/inetdevice.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index 5ae09372c144..54b32e8b8f65 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -90,11 +90,11 @@ struct in_ifaddr struct in_ifaddr *ifa_next; struct in_device *ifa_dev; struct rcu_head rcu_head; - u32 ifa_local; - u32 ifa_address; - u32 ifa_mask; - u32 ifa_broadcast; - u32 ifa_anycast; + __be32 ifa_local; + __be32 ifa_address; + __be32 ifa_mask; + __be32 ifa_broadcast; + __be32 ifa_anycast; unsigned char ifa_scope; unsigned char ifa_flags; unsigned char ifa_prefixlen; -- cgit v1.2.3 From 60cad5da5791ceb0beefe9a79b570cca45791f50 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 26 Sep 2006 22:17:09 -0700 Subject: [IPV4]: annotate inetdev.h helpers inet_confirm_addr(), inet_ifa_byprefix(), ip_dev_find(), inet_make_mask() and inet_ifa_match() annotated, along with inferred net-endian variables Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/inetdevice.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index 54b32e8b8f65..5a0ab04627bc 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -104,18 +104,18 @@ struct in_ifaddr extern int register_inetaddr_notifier(struct notifier_block *nb); extern int unregister_inetaddr_notifier(struct notifier_block *nb); -extern struct net_device *ip_dev_find(u32 addr); +extern struct net_device *ip_dev_find(__be32 addr); extern int inet_addr_onlink(struct in_device *in_dev, __be32 a, __be32 b); extern int devinet_ioctl(unsigned int cmd, void __user *); extern void devinet_init(void); extern struct in_device *inetdev_init(struct net_device *dev); extern struct in_device *inetdev_by_index(int); extern __be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope); -extern u32 inet_confirm_addr(const struct net_device *dev, u32 dst, u32 local, int scope); -extern struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, u32 prefix, u32 mask); +extern __be32 inet_confirm_addr(const struct net_device *dev, __be32 dst, __be32 local, int scope); +extern struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix, __be32 mask); extern void inet_forward_change(void); -static __inline__ int inet_ifa_match(u32 addr, struct in_ifaddr *ifa) +static __inline__ int inet_ifa_match(__be32 addr, struct in_ifaddr *ifa) { return !((addr^ifa->ifa_address)&ifa->ifa_mask); } @@ -183,7 +183,7 @@ static inline void in_dev_put(struct in_device *idev) #endif /* __KERNEL__ */ -static __inline__ __u32 inet_make_mask(int logmask) +static __inline__ __be32 inet_make_mask(int logmask) { if (logmask) return htonl(~((1<<(32-logmask))-1)); -- cgit v1.2.3 From 7699431301b189fca7ccbb64fe54e5a5170f8497 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Tue, 26 Sep 2006 22:28:46 -0700 Subject: [SUNRPC]: svc_{get,put}nl() * add svc_getnl(): Take network-endian value from buffer, convert to host-endian and return it. * add svc_putnl(): Take host-endian value, convert to network-endian and put it into a buffer. * annotate svc_getu32()/svc_putu32() as dealing with network-endian. * convert to svc_getnl(), svc_putnl(). [AV: in large part it's a carved-up Alexey's patch] Signed-off-by: Alexey Dobriyan Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/sunrpc/svc.h | 31 ++++++++++++++++++++++++------- 1 file changed, 24 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 7b27c09b5604..5df1d319f5d5 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -78,28 +78,45 @@ struct svc_serv { */ #define RPCSVC_MAXPAGES ((RPCSVC_MAXPAYLOAD+PAGE_SIZE-1)/PAGE_SIZE + 2) -static inline u32 svc_getu32(struct kvec *iov) +static inline u32 svc_getnl(struct kvec *iov) { - u32 val, *vp; + __be32 val, *vp; vp = iov->iov_base; val = *vp++; iov->iov_base = (void*)vp; - iov->iov_len -= sizeof(u32); + iov->iov_len -= sizeof(__be32); + return ntohl(val); +} + +static inline void svc_putnl(struct kvec *iov, u32 val) +{ + __be32 *vp = iov->iov_base + iov->iov_len; + *vp = htonl(val); + iov->iov_len += sizeof(__be32); +} + +static inline __be32 svc_getu32(struct kvec *iov) +{ + __be32 val, *vp; + vp = iov->iov_base; + val = *vp++; + iov->iov_base = (void*)vp; + iov->iov_len -= sizeof(__be32); return val; } static inline void svc_ungetu32(struct kvec *iov) { - u32 *vp = (u32 *)iov->iov_base; + __be32 *vp = (__be32 *)iov->iov_base; iov->iov_base = (void *)(vp - 1); iov->iov_len += sizeof(*vp); } -static inline void svc_putu32(struct kvec *iov, u32 val) +static inline void svc_putu32(struct kvec *iov, __be32 val) { - u32 *vp = iov->iov_base + iov->iov_len; + __be32 *vp = iov->iov_base + iov->iov_len; *vp = val; - iov->iov_len += sizeof(u32); + iov->iov_len += sizeof(__be32); } -- cgit v1.2.3 From d8ed029d6000ba2e2908d9286409e4833c091b4c Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Tue, 26 Sep 2006 22:29:38 -0700 Subject: [SUNRPC]: trivial endianness annotations pure s/u32/__be32/ [AV: large part based on Alexey's patches] Signed-off-by: Alexey Dobriyan Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/sunrpc/auth.h | 16 ++++++++-------- include/linux/sunrpc/msg_prot.h | 2 +- include/linux/sunrpc/svc.h | 14 +++++++------- include/linux/sunrpc/svcauth.h | 4 ++-- include/linux/sunrpc/xdr.h | 38 +++++++++++++++++++------------------- include/linux/sunrpc/xprt.h | 12 ++++++------ 6 files changed, 43 insertions(+), 43 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h index a6de332e57d4..862c0d8c8381 100644 --- a/include/linux/sunrpc/auth.h +++ b/include/linux/sunrpc/auth.h @@ -109,13 +109,13 @@ struct rpc_credops { void (*crdestroy)(struct rpc_cred *); int (*crmatch)(struct auth_cred *, struct rpc_cred *, int); - u32 * (*crmarshal)(struct rpc_task *, u32 *); + __be32 * (*crmarshal)(struct rpc_task *, __be32 *); int (*crrefresh)(struct rpc_task *); - u32 * (*crvalidate)(struct rpc_task *, u32 *); + __be32 * (*crvalidate)(struct rpc_task *, __be32 *); int (*crwrap_req)(struct rpc_task *, kxdrproc_t, - void *, u32 *, void *); + void *, __be32 *, void *); int (*crunwrap_resp)(struct rpc_task *, kxdrproc_t, - void *, u32 *, void *); + void *, __be32 *, void *); }; extern struct rpc_authops authunix_ops; @@ -134,10 +134,10 @@ struct rpc_cred * rpcauth_bindcred(struct rpc_task *); void rpcauth_holdcred(struct rpc_task *); void put_rpccred(struct rpc_cred *); void rpcauth_unbindcred(struct rpc_task *); -u32 * rpcauth_marshcred(struct rpc_task *, u32 *); -u32 * rpcauth_checkverf(struct rpc_task *, u32 *); -int rpcauth_wrap_req(struct rpc_task *task, kxdrproc_t encode, void *rqstp, u32 *data, void *obj); -int rpcauth_unwrap_resp(struct rpc_task *task, kxdrproc_t decode, void *rqstp, u32 *data, void *obj); +__be32 * rpcauth_marshcred(struct rpc_task *, __be32 *); +__be32 * rpcauth_checkverf(struct rpc_task *, __be32 *); +int rpcauth_wrap_req(struct rpc_task *task, kxdrproc_t encode, void *rqstp, __be32 *data, void *obj); +int rpcauth_unwrap_resp(struct rpc_task *task, kxdrproc_t decode, void *rqstp, __be32 *data, void *obj); int rpcauth_refreshcred(struct rpc_task *); void rpcauth_invalcred(struct rpc_task *); int rpcauth_uptodatecred(struct rpc_task *); diff --git a/include/linux/sunrpc/msg_prot.h b/include/linux/sunrpc/msg_prot.h index f43f237360ae..d9f5934ac9fe 100644 --- a/include/linux/sunrpc/msg_prot.h +++ b/include/linux/sunrpc/msg_prot.h @@ -95,7 +95,7 @@ enum rpc_auth_stat { * 2GB. */ -typedef u32 rpc_fraghdr; +typedef __be32 rpc_fraghdr; #define RPC_LAST_STREAM_FRAGMENT (1U << 31) #define RPC_FRAGMENT_SIZE_MASK (~RPC_LAST_STREAM_FRAGMENT) diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 5df1d319f5d5..73140ee5c638 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -147,7 +147,7 @@ struct svc_rqst { short rq_arghi; /* pages available in argument page list */ short rq_resused; /* pages used for result */ - u32 rq_xid; /* transmission id */ + __be32 rq_xid; /* transmission id */ u32 rq_prog; /* program number */ u32 rq_vers; /* program version */ u32 rq_proc; /* procedure number */ @@ -156,7 +156,7 @@ struct svc_rqst { rq_secure : 1; /* secure port */ - __u32 rq_daddr; /* dest addr of request - reply from here */ + __be32 rq_daddr; /* dest addr of request - reply from here */ void * rq_argp; /* decoded arguments */ void * rq_resp; /* xdr'd results */ @@ -186,7 +186,7 @@ struct svc_rqst { * Check buffer bounds after decoding arguments */ static inline int -xdr_argsize_check(struct svc_rqst *rqstp, u32 *p) +xdr_argsize_check(struct svc_rqst *rqstp, __be32 *p) { char *cp = (char *)p; struct kvec *vec = &rqstp->rq_arg.head[0]; @@ -195,7 +195,7 @@ xdr_argsize_check(struct svc_rqst *rqstp, u32 *p) } static inline int -xdr_ressize_check(struct svc_rqst *rqstp, u32 *p) +xdr_ressize_check(struct svc_rqst *rqstp, __be32 *p) { struct kvec *vec = &rqstp->rq_res.head[0]; char *cp = (char*)p; @@ -266,10 +266,10 @@ struct svc_deferred_req { u32 prot; /* protocol (UDP or TCP) */ struct sockaddr_in addr; struct svc_sock *svsk; /* where reply must go */ - u32 daddr; /* where reply must come from */ + __be32 daddr; /* where reply must come from */ struct cache_deferred_req handle; int argslen; - u32 args[0]; + __be32 args[0]; }; /* @@ -301,7 +301,7 @@ struct svc_version { * A return value of 0 means drop the request. * vs_dispatch == NULL means use default dispatcher. */ - int (*vs_dispatch)(struct svc_rqst *, u32 *); + int (*vs_dispatch)(struct svc_rqst *, __be32 *); }; /* diff --git a/include/linux/sunrpc/svcauth.h b/include/linux/sunrpc/svcauth.h index 2fe2087edd66..a6601650deeb 100644 --- a/include/linux/sunrpc/svcauth.h +++ b/include/linux/sunrpc/svcauth.h @@ -95,7 +95,7 @@ struct auth_ops { char * name; struct module *owner; int flavour; - int (*accept)(struct svc_rqst *rq, u32 *authp); + int (*accept)(struct svc_rqst *rq, __be32 *authp); int (*release)(struct svc_rqst *rq); void (*domain_release)(struct auth_domain *); int (*set_client)(struct svc_rqst *rq); @@ -112,7 +112,7 @@ struct auth_ops { #define SVC_COMPLETE 9 -extern int svc_authenticate(struct svc_rqst *rqstp, u32 *authp); +extern int svc_authenticate(struct svc_rqst *rqstp, __be32 *authp); extern int svc_authorise(struct svc_rqst *rqstp); extern int svc_set_client(struct svc_rqst *rqstp); extern int svc_auth_register(rpc_authflavor_t flavor, struct auth_ops *aops); diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index e6d3d349506c..953723b09bc6 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -32,7 +32,7 @@ struct xdr_netobj { * side) or svc_rqst pointer (server side). * Encode functions always assume there's enough room in the buffer. */ -typedef int (*kxdrproc_t)(void *rqstp, u32 *data, void *obj); +typedef int (*kxdrproc_t)(void *rqstp, __be32 *data, void *obj); /* * Basic structure for transmission/reception of a client XDR message. @@ -88,19 +88,19 @@ struct xdr_buf { /* * Miscellaneous XDR helper functions */ -u32 * xdr_encode_opaque_fixed(u32 *p, const void *ptr, unsigned int len); -u32 * xdr_encode_opaque(u32 *p, const void *ptr, unsigned int len); -u32 * xdr_encode_string(u32 *p, const char *s); -u32 * xdr_decode_string_inplace(u32 *p, char **sp, int *lenp, int maxlen); -u32 * xdr_encode_netobj(u32 *p, const struct xdr_netobj *); -u32 * xdr_decode_netobj(u32 *p, struct xdr_netobj *); +__be32 *xdr_encode_opaque_fixed(__be32 *p, const void *ptr, unsigned int len); +__be32 *xdr_encode_opaque(__be32 *p, const void *ptr, unsigned int len); +__be32 *xdr_encode_string(__be32 *p, const char *s); +__be32 *xdr_decode_string_inplace(__be32 *p, char **sp, int *lenp, int maxlen); +__be32 *xdr_encode_netobj(__be32 *p, const struct xdr_netobj *); +__be32 *xdr_decode_netobj(__be32 *p, struct xdr_netobj *); void xdr_encode_pages(struct xdr_buf *, struct page **, unsigned int, unsigned int); void xdr_inline_pages(struct xdr_buf *, unsigned int, struct page **, unsigned int, unsigned int); -static inline u32 *xdr_encode_array(u32 *p, const void *s, unsigned int len) +static inline __be32 *xdr_encode_array(__be32 *p, const void *s, unsigned int len) { return xdr_encode_opaque(p, s, len); } @@ -108,16 +108,16 @@ static inline u32 *xdr_encode_array(u32 *p, const void *s, unsigned int len) /* * Decode 64bit quantities (NFSv3 support) */ -static inline u32 * -xdr_encode_hyper(u32 *p, __u64 val) +static inline __be32 * +xdr_encode_hyper(__be32 *p, __u64 val) { *p++ = htonl(val >> 32); *p++ = htonl(val & 0xFFFFFFFF); return p; } -static inline u32 * -xdr_decode_hyper(u32 *p, __u64 *valp) +static inline __be32 * +xdr_decode_hyper(__be32 *p, __u64 *valp) { *valp = ((__u64) ntohl(*p++)) << 32; *valp |= ntohl(*p++); @@ -128,7 +128,7 @@ xdr_decode_hyper(u32 *p, __u64 *valp) * Adjust kvec to reflect end of xdr'ed data (RPC client XDR) */ static inline int -xdr_adjust_iovec(struct kvec *iov, u32 *p) +xdr_adjust_iovec(struct kvec *iov, __be32 *p) { return iov->iov_len = ((u8 *) p - (u8 *) iov->iov_base); } @@ -180,19 +180,19 @@ extern int xdr_encode_array2(struct xdr_buf *buf, unsigned int base, * Provide some simple tools for XDR buffer overflow-checking etc. */ struct xdr_stream { - uint32_t *p; /* start of available buffer */ + __be32 *p; /* start of available buffer */ struct xdr_buf *buf; /* XDR buffer to read/write */ - uint32_t *end; /* end of available buffer space */ + __be32 *end; /* end of available buffer space */ struct kvec *iov; /* pointer to the current kvec */ }; -extern void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf, uint32_t *p); -extern uint32_t *xdr_reserve_space(struct xdr_stream *xdr, size_t nbytes); +extern void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p); +extern __be32 *xdr_reserve_space(struct xdr_stream *xdr, size_t nbytes); extern void xdr_write_pages(struct xdr_stream *xdr, struct page **pages, unsigned int base, unsigned int len); -extern void xdr_init_decode(struct xdr_stream *xdr, struct xdr_buf *buf, uint32_t *p); -extern uint32_t *xdr_inline_decode(struct xdr_stream *xdr, size_t nbytes); +extern void xdr_init_decode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p); +extern __be32 *xdr_inline_decode(struct xdr_stream *xdr, size_t nbytes); extern void xdr_read_pages(struct xdr_stream *xdr, unsigned int len); extern void xdr_enter_page(struct xdr_stream *xdr, unsigned int len); diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index bdeba8538c71..6cf626580752 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -79,7 +79,7 @@ struct rpc_rqst { * This is the private part */ struct rpc_task * rq_task; /* RPC task data */ - __u32 rq_xid; /* request XID */ + __be32 rq_xid; /* request XID */ int rq_cong; /* has incremented xprt->cong */ int rq_received; /* receive completed */ u32 rq_seqno; /* gss seq no. used on req. */ @@ -171,9 +171,9 @@ struct rpc_xprt { /* * State of TCP reply receive stuff */ - u32 tcp_recm, /* Fragment header */ - tcp_xid, /* Current XID */ - tcp_reclen, /* fragment length */ + __be32 tcp_recm, /* Fragment header */ + tcp_xid; /* Current XID */ + u32 tcp_reclen, /* fragment length */ tcp_offset; /* fragment offset */ unsigned long tcp_copied, /* copied to request */ tcp_flags; @@ -253,7 +253,7 @@ void xprt_release(struct rpc_task *task); struct rpc_xprt * xprt_get(struct rpc_xprt *xprt); void xprt_put(struct rpc_xprt *xprt); -static inline u32 *xprt_skip_transport_header(struct rpc_xprt *xprt, u32 *p) +static inline __be32 *xprt_skip_transport_header(struct rpc_xprt *xprt, __be32 *p) { return p + xprt->tsh_size; } @@ -268,7 +268,7 @@ void xprt_wait_for_buffer_space(struct rpc_task *task); void xprt_write_space(struct rpc_xprt *xprt); void xprt_update_rtt(struct rpc_task *task); void xprt_adjust_cwnd(struct rpc_task *task, int result); -struct rpc_rqst * xprt_lookup_rqst(struct rpc_xprt *xprt, u32 xid); +struct rpc_rqst * xprt_lookup_rqst(struct rpc_xprt *xprt, __be32 xid); void xprt_complete_rqst(struct rpc_task *task, int copied); void xprt_release_rqst_cong(struct rpc_task *task); void xprt_disconnect(struct rpc_xprt *xprt); -- cgit v1.2.3 From 126a336822a6594662f5898f1ddf33e6d048fcc7 Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Wed, 27 Sep 2006 16:03:07 -0700 Subject: [TG3]: Add 5722 and 5756 support. Add IDs to support 5722 and 5756. 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 61db1907f06f..ea3140d226e6 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1904,6 +1904,7 @@ #define PCI_DEVICE_ID_TIGON3_5705_2 0x1654 #define PCI_DEVICE_ID_TIGON3_5720 0x1658 #define PCI_DEVICE_ID_TIGON3_5721 0x1659 +#define PCI_DEVICE_ID_TIGON3_5722 0x165a #define PCI_DEVICE_ID_TIGON3_5705M 0x165d #define PCI_DEVICE_ID_TIGON3_5705M_2 0x165e #define PCI_DEVICE_ID_TIGON3_5714 0x1668 @@ -1913,6 +1914,7 @@ #define PCI_DEVICE_ID_TIGON3_5705F 0x166e #define PCI_DEVICE_ID_TIGON3_5754M 0x1672 #define PCI_DEVICE_ID_TIGON3_5755M 0x1673 +#define PCI_DEVICE_ID_TIGON3_5756 0x1674 #define PCI_DEVICE_ID_TIGON3_5750 0x1676 #define PCI_DEVICE_ID_TIGON3_5751 0x1677 #define PCI_DEVICE_ID_TIGON3_5715 0x1678 -- cgit v1.2.3 From b5d3772ccbe0bc5ac8ffbb5356b74ca698aee28c Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Wed, 27 Sep 2006 16:06:21 -0700 Subject: [TG3]: Add basic 5906 support. Add support for the new 5709 device. This is a new 10/100 Mbps chip. The mailbox access and firmware interface are quite different from all other tg3 chips. 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 ea3140d226e6..b7e85ff045ea 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1944,6 +1944,8 @@ #define PCI_DEVICE_ID_TIGON3_5901 0x170d #define PCI_DEVICE_ID_BCM4401B1 0x170c #define PCI_DEVICE_ID_TIGON3_5901_2 0x170e +#define PCI_DEVICE_ID_TIGON3_5906 0x1712 +#define PCI_DEVICE_ID_TIGON3_5906M 0x1713 #define PCI_DEVICE_ID_BCM4401 0x4401 #define PCI_DEVICE_ID_BCM4401B0 0x4402 -- cgit v1.2.3 From 00a5020cd51febbb3166ff7a09a2901c47ba251a Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 27 Sep 2006 18:29:47 -0700 Subject: [IPV4]: annotate ipv4 address fields in struct ip_msfilter and struct ip_mreq_source Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/in.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/in.h b/include/linux/in.h index bcaca8399aed..d79fc75fa7c2 100644 --- a/include/linux/in.h +++ b/include/linux/in.h @@ -123,17 +123,17 @@ struct ip_mreqn }; struct ip_mreq_source { - __u32 imr_multiaddr; - __u32 imr_interface; - __u32 imr_sourceaddr; + __be32 imr_multiaddr; + __be32 imr_interface; + __be32 imr_sourceaddr; }; struct ip_msfilter { - __u32 imsf_multiaddr; - __u32 imsf_interface; + __be32 imsf_multiaddr; + __be32 imsf_interface; __u32 imsf_fmode; __u32 imsf_numsrc; - __u32 imsf_slist[1]; + __be32 imsf_slist[1]; }; #define IP_MSFILTER_SIZE(numsrc) \ -- cgit v1.2.3 From 8f935bbd7c6c66796c2403aefdab74bb48045bf6 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 27 Sep 2006 18:30:07 -0700 Subject: [IPV4]: ip_mc_{inc,dec}_group() annotations Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/igmp.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/igmp.h b/include/linux/igmp.h index 8e7eedb3a574..dd49ba9065ae 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -215,7 +215,7 @@ extern void ip_mc_init_dev(struct in_device *); extern void ip_mc_destroy_dev(struct in_device *); extern void ip_mc_up(struct in_device *); extern void ip_mc_down(struct in_device *); -extern void ip_mc_dec_group(struct in_device *in_dev, u32 addr); -extern void ip_mc_inc_group(struct in_device *in_dev, u32 addr); +extern void ip_mc_dec_group(struct in_device *in_dev, __be32 addr); +extern void ip_mc_inc_group(struct in_device *in_dev, __be32 addr); #endif #endif -- cgit v1.2.3 From 942bf921e922560c05fde6afb00ddedf6224c608 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 27 Sep 2006 18:30:28 -0700 Subject: [IPV4]: IGMP on-the-wire data is net-endian Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/igmp.h | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/igmp.h b/include/linux/igmp.h index dd49ba9065ae..fd207d9b2733 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -30,8 +30,8 @@ struct igmphdr { __u8 type; __u8 code; /* For newer IGMP */ - __u16 csum; - __u32 group; + __be16 csum; + __be32 group; }; /* V3 group record types [grec_type] */ @@ -45,25 +45,25 @@ struct igmphdr struct igmpv3_grec { __u8 grec_type; __u8 grec_auxwords; - __u16 grec_nsrcs; - __u32 grec_mca; - __u32 grec_src[0]; + __be16 grec_nsrcs; + __be32 grec_mca; + __be32 grec_src[0]; }; struct igmpv3_report { __u8 type; __u8 resv1; - __u16 csum; - __u16 resv2; - __u16 ngrec; + __be16 csum; + __be16 resv2; + __be16 ngrec; struct igmpv3_grec grec[0]; }; struct igmpv3_query { __u8 type; __u8 code; - __u16 csum; - __u32 group; + __be16 csum; + __be32 group; #if defined(__LITTLE_ENDIAN_BITFIELD) __u8 qrv:3, suppress:1, @@ -76,8 +76,8 @@ struct igmpv3_query { #error "Please fix " #endif __u8 qqic; - __u16 nsrcs; - __u32 srcs[0]; + __be16 nsrcs; + __be32 srcs[0]; }; #define IGMP_HOST_MEMBERSHIP_QUERY 0x11 /* From RFC1112 */ -- cgit v1.2.3 From ea4d9e7220d32348cc9742ba6d27de5165262664 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 27 Sep 2006 18:30:52 -0700 Subject: [IPV4]: struct ip_sf_list and struct ip_sf_socklist annotated Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/igmp.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/igmp.h b/include/linux/igmp.h index fd207d9b2733..4e9f3fe77cf9 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -136,7 +136,7 @@ struct ip_sf_socklist { unsigned int sl_max; unsigned int sl_count; - __u32 sl_addr[0]; + __be32 sl_addr[0]; }; #define IP_SFLSIZE(count) (sizeof(struct ip_sf_socklist) + \ @@ -159,7 +159,7 @@ struct ip_mc_socklist struct ip_sf_list { struct ip_sf_list *sf_next; - __u32 sf_inaddr; + __be32 sf_inaddr; unsigned long sf_count[2]; /* include/exclude counts */ unsigned char sf_gsresp; /* include in g & s response? */ unsigned char sf_oldin; /* change state */ -- cgit v1.2.3 From c0cda068aac3481d40795b115e4fd36f7d386e3a Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 27 Sep 2006 18:31:10 -0700 Subject: [IPV4]: ip_mc_sf_allow() annotated ip_mc_sf_allow() expects addresses to be passed net-endian. Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/igmp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/igmp.h b/include/linux/igmp.h index 4e9f3fe77cf9..7514cceb4fe3 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -209,7 +209,7 @@ extern int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf, struct ip_msfilter __user *optval, int __user *optlen); extern int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf, struct group_filter __user *optval, int __user *optlen); -extern int ip_mc_sf_allow(struct sock *sk, u32 local, u32 rmt, int dif); +extern int ip_mc_sf_allow(struct sock *sk, __be32 local, __be32 rmt, int dif); extern void ip_mr_init(void); extern void ip_mc_init_dev(struct in_device *); extern void ip_mc_destroy_dev(struct in_device *); -- cgit v1.2.3 From 63007727e0bb09e8d906f73d36a09b9fac0d5893 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 27 Sep 2006 18:31:32 -0700 Subject: [IPV4]: trivial igmp annotations Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/igmp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/igmp.h b/include/linux/igmp.h index 7514cceb4fe3..03f43e2893a4 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -140,7 +140,7 @@ struct ip_sf_socklist }; #define IP_SFLSIZE(count) (sizeof(struct ip_sf_socklist) + \ - (count) * sizeof(__u32)) + (count) * sizeof(__be32)) #define IP_SFBLOCK 10 /* allocate this many at once */ -- cgit v1.2.3 From 46a97324a5ebdc1e343a0223d993e79551adab0f Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 27 Sep 2006 18:31:51 -0700 Subject: [IPV4]: TCP headers annotated Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/tcp.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 8ebf497907f8..543f06371840 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -21,10 +21,10 @@ #include struct tcphdr { - __u16 source; - __u16 dest; - __u32 seq; - __u32 ack_seq; + __be16 source; + __be16 dest; + __be32 seq; + __be32 ack_seq; #if defined(__LITTLE_ENDIAN_BITFIELD) __u16 res1:4, doff:4, @@ -50,9 +50,9 @@ struct tcphdr { #else #error "Adjust your defines" #endif - __u16 window; - __u16 check; - __u16 urg_ptr; + __be16 window; + __be16 check; + __be16 urg_ptr; }; /* @@ -62,7 +62,7 @@ struct tcphdr { */ union tcp_word_hdr { struct tcphdr hdr; - __u32 words[5]; + __be32 words[5]; }; #define tcp_flag_word(tp) ( ((union tcp_word_hdr *)(tp))->words [3]) -- cgit v1.2.3 From 269bd27e66037a7932cee6d6aa7ef7defd0bfe38 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 27 Sep 2006 18:32:28 -0700 Subject: [TCP]: struct tcp_sack_block annotations Some of the instances of tcp_sack_block are host-endian, some - net-endian. Define struct tcp_sack_block_wire identical to struct tcp_sack_block with u32 replaced with __be32; annotate uses of tcp_sack_block replacing net-endian ones with tcp_sack_block_wire. Change is obviously safe since for cc(1) __be32 is typedefed to u32. Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/tcp.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 543f06371840..9632aa866de4 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -166,6 +166,11 @@ struct tcp_info #include /* This defines a selective acknowledgement block. */ +struct tcp_sack_block_wire { + __be32 start_seq; + __be32 end_seq; +}; + struct tcp_sack_block { __u32 start_seq; __u32 end_seq; -- cgit v1.2.3 From dddc93c05d7dba60b44866486502c155e96ab915 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 27 Sep 2006 18:32:46 -0700 Subject: [TCP]: struct tcp_sock .pred_flags is net-endian Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/tcp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 9632aa866de4..0e058a2d1c6d 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -216,7 +216,7 @@ struct tcp_sock { * Header prediction flags * 0x5?10 << 16 + snd_wnd in net byte order */ - __u32 pred_flags; + __be32 pred_flags; /* * RFC793 variables by their proper names. This means you can -- cgit v1.2.3 From b406313c733156c8eea7d9c1891476f400914367 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 27 Sep 2006 18:34:02 -0700 Subject: [NET]: struct sock_exterr_skb annotations ->port is net-endian Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/errqueue.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/errqueue.h b/include/linux/errqueue.h index 408118a07763..92f8d4fab32b 100644 --- a/include/linux/errqueue.h +++ b/include/linux/errqueue.h @@ -38,7 +38,7 @@ struct sock_exterr_skb } header; struct sock_extended_err ee; u16 addr_offset; - u16 port; + __be16 port; }; #endif -- cgit v1.2.3 From bd6d610a14f2ed896b76dfb61fbdec829e44b8d3 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 27 Sep 2006 18:35:47 -0700 Subject: [IPV4]: ARP header annotated Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/if_arp.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_arp.h b/include/linux/if_arp.h index a8b1a2071838..7f5714214ee3 100644 --- a/include/linux/if_arp.h +++ b/include/linux/if_arp.h @@ -130,11 +130,11 @@ struct arpreq_old { struct arphdr { - unsigned short ar_hrd; /* format of hardware address */ - unsigned short ar_pro; /* format of protocol address */ + __be16 ar_hrd; /* format of hardware address */ + __be16 ar_pro; /* format of protocol address */ unsigned char ar_hln; /* length of hardware address */ unsigned char ar_pln; /* length of protocol address */ - unsigned short ar_op; /* ARP opcode (command) */ + __be16 ar_op; /* ARP opcode (command) */ #if 0 /* -- cgit v1.2.3 From 4e7e0c7592cafe5453e5b2f115fc0065d11b3d44 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 27 Sep 2006 18:37:19 -0700 Subject: [IPV4]: UDP header annotations Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/udp.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/udp.h b/include/linux/udp.h index 90223f057d50..014b41d1e308 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -20,10 +20,10 @@ #include struct udphdr { - __u16 source; - __u16 dest; - __u16 len; - __u16 check; + __be16 source; + __be16 dest; + __be16 len; + __be16 check; }; /* UDP socket options */ -- cgit v1.2.3 From b1dd39ac963040c2d282ab8026b9c9aa9306ea06 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 27 Sep 2006 18:38:13 -0700 Subject: [IPV4]: ICMP header annotations Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/icmp.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/icmp.h b/include/linux/icmp.h index f0b571f1060b..878cfe4e587f 100644 --- a/include/linux/icmp.h +++ b/include/linux/icmp.h @@ -68,16 +68,16 @@ struct icmphdr { __u8 type; __u8 code; - __u16 checksum; + __be16 checksum; union { struct { - __u16 id; - __u16 sequence; + __be16 id; + __be16 sequence; } echo; - __u32 gateway; + __be32 gateway; struct { - __u16 __unused; - __u16 mtu; + __be16 __unused; + __be16 mtu; } frag; } un; }; -- cgit v1.2.3 From 1b620154273d5cc57690e0d199282c6bb9e56974 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 27 Sep 2006 18:39:09 -0700 Subject: [IPV4]: PIMv2 header annotations Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/mroute.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mroute.h b/include/linux/mroute.h index e05d54a90743..c7dd4c11f667 100644 --- a/include/linux/mroute.h +++ b/include/linux/mroute.h @@ -213,8 +213,8 @@ struct pimreghdr { __u8 type; __u8 reserved; - __u16 csum; - __u32 flags; + __be16 csum; + __be32 flags; }; extern int pim_rcv_v1(struct sk_buff *); -- cgit v1.2.3 From 114c7844f34c1608aec20ae7ff85cec471ac90ae Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 27 Sep 2006 18:39:29 -0700 Subject: [IPV4]: mroute annotations Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/mroute.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mroute.h b/include/linux/mroute.h index c7dd4c11f667..7da2cee8e132 100644 --- a/include/linux/mroute.h +++ b/include/linux/mroute.h @@ -142,7 +142,7 @@ struct vif_device unsigned long rate_limit; /* Traffic shaping (NI) */ unsigned char threshold; /* TTL threshold */ unsigned short flags; /* Control flags */ - __u32 local,remote; /* Addresses(remote for tunnels)*/ + __be32 local,remote; /* Addresses(remote for tunnels)*/ int link; /* Physical interface index */ }; @@ -151,8 +151,8 @@ struct vif_device struct mfc_cache { struct mfc_cache *next; /* Next entry on cache line */ - __u32 mfc_mcastgrp; /* Group the entry belongs to */ - __u32 mfc_origin; /* Source of packet */ + __be32 mfc_mcastgrp; /* Group the entry belongs to */ + __be32 mfc_origin; /* Source of packet */ vifi_t mfc_parent; /* Source interface */ int mfc_flags; /* Flags on line */ @@ -179,9 +179,9 @@ struct mfc_cache #define MFC_LINES 64 #ifdef __BIG_ENDIAN -#define MFC_HASH(a,b) ((((a)>>24)^((b)>>26))&(MFC_LINES-1)) +#define MFC_HASH(a,b) (((((__force u32)(__be32)a)>>24)^(((__force u32)(__be32)b)>>26))&(MFC_LINES-1)) #else -#define MFC_HASH(a,b) (((a)^((b)>>2))&(MFC_LINES-1)) +#define MFC_HASH(a,b) ((((__force u32)(__be32)a)^(((__force u32)(__be32)b)>>2))&(MFC_LINES-1)) #endif #endif -- cgit v1.2.3 From 4f765d842fa6e6fe15d555b247b640118d65b4dd Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 27 Sep 2006 18:43:07 -0700 Subject: [IPV4]: INET_MATCH() annotations INET_MATCH() and friends depend on an interesting set of kludges: * there's a pair of adjacent fields in struct inet_sock - __be16 dport followed by __u16 num. We want to search by pair, so we combine the keys into a single 32bit value and compare with 32bit value read from &...->dport. * on 64bit targets we combine comparisons with pair of adjacent __be32 fields in the same way. Make sure that we don't mix those values with anything else and that pairs we form them from have correct types. Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/ipv6.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index caca57df0d7d..6dc07ee7702e 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -461,7 +461,7 @@ static inline struct raw6_sock *raw6_sk(const struct sock *sk) #define INET6_MATCH(__sk, __hash, __saddr, __daddr, __ports, __dif)\ (((__sk)->sk_hash == (__hash)) && \ - ((*((__u32 *)&(inet_sk(__sk)->dport))) == (__ports)) && \ + ((*((__portpair *)&(inet_sk(__sk)->dport))) == (__ports)) && \ ((__sk)->sk_family == AF_INET6) && \ ipv6_addr_equal(&inet6_sk(__sk)->daddr, (__saddr)) && \ ipv6_addr_equal(&inet6_sk(__sk)->rcv_saddr, (__daddr)) && \ -- cgit v1.2.3 From 9f8552996d969f56039ec88128cf5ad35b12f141 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 27 Sep 2006 18:44:30 -0700 Subject: [IPV4]: inet_diag annotations Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/inet_diag.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/inet_diag.h b/include/linux/inet_diag.h index a4606e5810e5..6e8bc548635a 100644 --- a/include/linux/inet_diag.h +++ b/include/linux/inet_diag.h @@ -9,10 +9,10 @@ /* Socket identity */ struct inet_diag_sockid { - __u16 idiag_sport; - __u16 idiag_dport; - __u32 idiag_src[4]; - __u32 idiag_dst[4]; + __be16 idiag_sport; + __be16 idiag_dport; + __be32 idiag_src[4]; + __be32 idiag_dst[4]; __u32 idiag_if; __u32 idiag_cookie[2]; #define INET_DIAG_NOCOOKIE (~0U) @@ -67,7 +67,7 @@ struct inet_diag_hostcond { __u8 family; __u8 prefix_len; int port; - __u32 addr[0]; + __be32 addr[0]; }; /* Base info structure. It contains socket identity (addrs/ports/cookie) -- cgit v1.2.3 From 48818f822d2b2e16f4bf4d1ed1185e7d2146dc34 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 27 Sep 2006 18:44:54 -0700 Subject: [IPV6]: struct in6_addr annotations in6_addr elements are net-endian Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/in6.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/in6.h b/include/linux/in6.h index d776829b443f..348ecd4a36fe 100644 --- a/include/linux/in6.h +++ b/include/linux/in6.h @@ -32,8 +32,8 @@ struct in6_addr union { __u8 u6_addr8[16]; - __u16 u6_addr16[8]; - __u32 u6_addr32[4]; + __be16 u6_addr16[8]; + __be32 u6_addr32[4]; } in6_u; #define s6_addr in6_u.u6_addr8 #define s6_addr16 in6_u.u6_addr16 -- cgit v1.2.3 From 43505077df075545e9b28b7c6ea12d82b3caf036 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 27 Sep 2006 18:45:11 -0700 Subject: [IPV6]: IPv6 headers annotations Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/ipv6.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 6dc07ee7702e..4f435c59de06 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -99,22 +99,22 @@ struct ipv6_destopt_hao { struct ipv6_auth_hdr { __u8 nexthdr; __u8 hdrlen; /* This one is measured in 32 bit units! */ - __u16 reserved; - __u32 spi; - __u32 seq_no; /* Sequence number */ + __be16 reserved; + __be32 spi; + __be32 seq_no; /* Sequence number */ __u8 auth_data[0]; /* Length variable but >=4. Mind the 64 bit alignment! */ }; struct ipv6_esp_hdr { - __u32 spi; - __u32 seq_no; /* Sequence number */ + __be32 spi; + __be32 seq_no; /* Sequence number */ __u8 enc_data[0]; /* Length variable but >=8. Mind the 64 bit alignment! */ }; struct ipv6_comp_hdr { __u8 nexthdr; __u8 flags; - __u16 cpi; + __be16 cpi; }; /* @@ -136,7 +136,7 @@ struct ipv6hdr { #endif __u8 flow_lbl[3]; - __u16 payload_len; + __be16 payload_len; __u8 nexthdr; __u8 hop_limit; -- cgit v1.2.3 From e2e38e819bd03e9674c102aaa2c9dc8151a3c3d0 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 27 Sep 2006 18:45:27 -0700 Subject: [IPV6]: sin6_port is net-endian Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/in6.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/in6.h b/include/linux/in6.h index 348ecd4a36fe..9be6a4756f0b 100644 --- a/include/linux/in6.h +++ b/include/linux/in6.h @@ -53,7 +53,7 @@ extern const struct in6_addr in6addr_loopback; struct sockaddr_in6 { unsigned short int sin6_family; /* AF_INET6 */ - __u16 sin6_port; /* Transport layer port # */ + __be16 sin6_port; /* Transport layer port # */ __u32 sin6_flowinfo; /* IPv6 flow information */ struct in6_addr sin6_addr; /* IPv6 address */ __u32 sin6_scope_id; /* scope id (new in RFC2553) */ -- cgit v1.2.3 From 8f83f23e6db8b9a9fe787d02f73489224668c4e2 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 27 Sep 2006 18:46:11 -0700 Subject: [XFRM]: ports in struct xfrm_selector annotated Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/xfrm.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/xfrm.h b/include/linux/xfrm.h index 14ecd19f4cdc..3aae9b9ce79b 100644 --- a/include/linux/xfrm.h +++ b/include/linux/xfrm.h @@ -49,10 +49,10 @@ struct xfrm_selector { xfrm_address_t daddr; xfrm_address_t saddr; - __u16 dport; - __u16 dport_mask; - __u16 sport; - __u16 sport_mask; + __be16 dport; + __be16 dport_mask; + __be16 sport; + __be16 sport_mask; __u16 family; __u8 prefixlen_d; __u8 prefixlen_s; -- cgit v1.2.3 From 737b5761dfc609b5be4163deb2cf09226f56bcbc Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 27 Sep 2006 18:46:48 -0700 Subject: [XFRM]: xfrm_address_t annotations Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/xfrm.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/xfrm.h b/include/linux/xfrm.h index 3aae9b9ce79b..4b321842d65f 100644 --- a/include/linux/xfrm.h +++ b/include/linux/xfrm.h @@ -12,8 +12,8 @@ */ typedef union { - __u32 a4; - __u32 a6[4]; + __be32 a4; + __be32 a6[4]; } xfrm_address_t; /* Ident of a specific xfrm_state. It is used on input to lookup -- cgit v1.2.3 From e037c39bf965ca66fde902e191d849a90de278fe Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 27 Sep 2006 18:47:40 -0700 Subject: [XFRM]: struct xfrm_id annotations Signed-off-by: Al Viro 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 4b321842d65f..c894267ff5dd 100644 --- a/include/linux/xfrm.h +++ b/include/linux/xfrm.h @@ -23,7 +23,7 @@ typedef union struct xfrm_id { xfrm_address_t daddr; - __u32 spi; + __be32 spi; __u8 proto; }; -- cgit v1.2.3 From 9916ecb0a6f52f1475fa2f71845227d3c75fb40c Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 27 Sep 2006 18:48:48 -0700 Subject: [XFRM]: struct xfrm_usersa_id annotations Signed-off-by: Al Viro 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 c894267ff5dd..430afd058269 100644 --- a/include/linux/xfrm.h +++ b/include/linux/xfrm.h @@ -281,7 +281,7 @@ struct xfrm_usersa_info { struct xfrm_usersa_id { xfrm_address_t daddr; - __u32 spi; + __be32 spi; __u16 family; __u8 proto; }; -- cgit v1.2.3 From cbde1668e4f08e0a150207646010bc65e1e2a42b Mon Sep 17 00:00:00 2001 From: YOSHIFUJI Hideaki Date: Wed, 27 Sep 2006 22:40:19 -0700 Subject: [NET]: Move netlink interface bits to linux/if_link.h. Moving netlink interface bits to linux/if.h is rather troublesome for applications including both linux/if.h (which was changed to be included from linux/rtnetlink.h automatically) and net/if.h. Signed-off-by: YOSHIFUJI Hideaki Signed-off-by: David S. Miller --- include/linux/if.h | 130 -------------------------------------------- include/linux/if_link.h | 136 ++++++++++++++++++++++++++++++++++++++++++++++ include/linux/rtnetlink.h | 2 +- 3 files changed, 137 insertions(+), 131 deletions(-) create mode 100644 include/linux/if_link.h (limited to 'include/linux') diff --git a/include/linux/if.h b/include/linux/if.h index 8018c2e22c0c..32bf419351f1 100644 --- a/include/linux/if.h +++ b/include/linux/if.h @@ -214,134 +214,4 @@ struct ifconf #define ifc_buf ifc_ifcu.ifcu_buf /* buffer address */ #define ifc_req ifc_ifcu.ifcu_req /* array of structures */ -/* The struct should be in sync with struct net_device_stats */ -struct rtnl_link_stats -{ - __u32 rx_packets; /* total packets received */ - __u32 tx_packets; /* total packets transmitted */ - __u32 rx_bytes; /* total bytes received */ - __u32 tx_bytes; /* total bytes transmitted */ - __u32 rx_errors; /* bad packets received */ - __u32 tx_errors; /* packet transmit problems */ - __u32 rx_dropped; /* no space in linux buffers */ - __u32 tx_dropped; /* no space available in linux */ - __u32 multicast; /* multicast packets received */ - __u32 collisions; - - /* detailed rx_errors: */ - __u32 rx_length_errors; - __u32 rx_over_errors; /* receiver ring buff overflow */ - __u32 rx_crc_errors; /* recved pkt with crc error */ - __u32 rx_frame_errors; /* recv'd frame alignment error */ - __u32 rx_fifo_errors; /* recv'r fifo overrun */ - __u32 rx_missed_errors; /* receiver missed packet */ - - /* detailed tx_errors */ - __u32 tx_aborted_errors; - __u32 tx_carrier_errors; - __u32 tx_fifo_errors; - __u32 tx_heartbeat_errors; - __u32 tx_window_errors; - - /* for cslip etc */ - __u32 rx_compressed; - __u32 tx_compressed; -}; - -/* The struct should be in sync with struct ifmap */ -struct rtnl_link_ifmap -{ - __u64 mem_start; - __u64 mem_end; - __u64 base_addr; - __u16 irq; - __u8 dma; - __u8 port; -}; - -enum -{ - IFLA_UNSPEC, - IFLA_ADDRESS, - IFLA_BROADCAST, - IFLA_IFNAME, - IFLA_MTU, - IFLA_LINK, - IFLA_QDISC, - IFLA_STATS, - IFLA_COST, -#define IFLA_COST IFLA_COST - IFLA_PRIORITY, -#define IFLA_PRIORITY IFLA_PRIORITY - IFLA_MASTER, -#define IFLA_MASTER IFLA_MASTER - IFLA_WIRELESS, /* Wireless Extension event - see wireless.h */ -#define IFLA_WIRELESS IFLA_WIRELESS - IFLA_PROTINFO, /* Protocol specific information for a link */ -#define IFLA_PROTINFO IFLA_PROTINFO - IFLA_TXQLEN, -#define IFLA_TXQLEN IFLA_TXQLEN - IFLA_MAP, -#define IFLA_MAP IFLA_MAP - IFLA_WEIGHT, -#define IFLA_WEIGHT IFLA_WEIGHT - IFLA_OPERSTATE, - IFLA_LINKMODE, - __IFLA_MAX -}; - - -#define IFLA_MAX (__IFLA_MAX - 1) - -/* ifi_flags. - - IFF_* flags. - - The only change is: - IFF_LOOPBACK, IFF_BROADCAST and IFF_POINTOPOINT are - more not changeable by user. They describe link media - characteristics and set by device driver. - - Comments: - - Combination IFF_BROADCAST|IFF_POINTOPOINT is invalid - - If neither of these three flags are set; - the interface is NBMA. - - - IFF_MULTICAST does not mean anything special: - multicasts can be used on all not-NBMA links. - IFF_MULTICAST means that this media uses special encapsulation - for multicast frames. Apparently, all IFF_POINTOPOINT and - IFF_BROADCAST devices are able to use multicasts too. - */ - -/* IFLA_LINK. - For usual devices it is equal ifi_index. - If it is a "virtual interface" (f.e. tunnel), ifi_link - can point to real physical interface (f.e. for bandwidth calculations), - or maybe 0, what means, that real media is unknown (usual - for IPIP tunnels, when route to endpoint is allowed to change) - */ - -/* Subtype attributes for IFLA_PROTINFO */ -enum -{ - IFLA_INET6_UNSPEC, - IFLA_INET6_FLAGS, /* link flags */ - IFLA_INET6_CONF, /* sysctl parameters */ - IFLA_INET6_STATS, /* statistics */ - IFLA_INET6_MCAST, /* MC things. What of them? */ - IFLA_INET6_CACHEINFO, /* time values and max reasm size */ - __IFLA_INET6_MAX -}; - -#define IFLA_INET6_MAX (__IFLA_INET6_MAX - 1) - -struct ifla_cacheinfo -{ - __u32 max_reasm_len; - __u32 tstamp; /* ipv6InterfaceTable updated timestamp */ - __u32 reachable_time; - __u32 retrans_time; -}; - #endif /* _LINUX_IF_H */ diff --git a/include/linux/if_link.h b/include/linux/if_link.h new file mode 100644 index 000000000000..e963a077e6f5 --- /dev/null +++ b/include/linux/if_link.h @@ -0,0 +1,136 @@ +#ifndef _LINUX_IF_LINK_H +#define _LINUX_IF_LINK_H + +#include + +/* The struct should be in sync with struct net_device_stats */ +struct rtnl_link_stats +{ + __u32 rx_packets; /* total packets received */ + __u32 tx_packets; /* total packets transmitted */ + __u32 rx_bytes; /* total bytes received */ + __u32 tx_bytes; /* total bytes transmitted */ + __u32 rx_errors; /* bad packets received */ + __u32 tx_errors; /* packet transmit problems */ + __u32 rx_dropped; /* no space in linux buffers */ + __u32 tx_dropped; /* no space available in linux */ + __u32 multicast; /* multicast packets received */ + __u32 collisions; + + /* detailed rx_errors: */ + __u32 rx_length_errors; + __u32 rx_over_errors; /* receiver ring buff overflow */ + __u32 rx_crc_errors; /* recved pkt with crc error */ + __u32 rx_frame_errors; /* recv'd frame alignment error */ + __u32 rx_fifo_errors; /* recv'r fifo overrun */ + __u32 rx_missed_errors; /* receiver missed packet */ + + /* detailed tx_errors */ + __u32 tx_aborted_errors; + __u32 tx_carrier_errors; + __u32 tx_fifo_errors; + __u32 tx_heartbeat_errors; + __u32 tx_window_errors; + + /* for cslip etc */ + __u32 rx_compressed; + __u32 tx_compressed; +}; + +/* The struct should be in sync with struct ifmap */ +struct rtnl_link_ifmap +{ + __u64 mem_start; + __u64 mem_end; + __u64 base_addr; + __u16 irq; + __u8 dma; + __u8 port; +}; + +enum +{ + IFLA_UNSPEC, + IFLA_ADDRESS, + IFLA_BROADCAST, + IFLA_IFNAME, + IFLA_MTU, + IFLA_LINK, + IFLA_QDISC, + IFLA_STATS, + IFLA_COST, +#define IFLA_COST IFLA_COST + IFLA_PRIORITY, +#define IFLA_PRIORITY IFLA_PRIORITY + IFLA_MASTER, +#define IFLA_MASTER IFLA_MASTER + IFLA_WIRELESS, /* Wireless Extension event - see wireless.h */ +#define IFLA_WIRELESS IFLA_WIRELESS + IFLA_PROTINFO, /* Protocol specific information for a link */ +#define IFLA_PROTINFO IFLA_PROTINFO + IFLA_TXQLEN, +#define IFLA_TXQLEN IFLA_TXQLEN + IFLA_MAP, +#define IFLA_MAP IFLA_MAP + IFLA_WEIGHT, +#define IFLA_WEIGHT IFLA_WEIGHT + IFLA_OPERSTATE, + IFLA_LINKMODE, + __IFLA_MAX +}; + + +#define IFLA_MAX (__IFLA_MAX - 1) + +/* ifi_flags. + + IFF_* flags. + + The only change is: + IFF_LOOPBACK, IFF_BROADCAST and IFF_POINTOPOINT are + more not changeable by user. They describe link media + characteristics and set by device driver. + + Comments: + - Combination IFF_BROADCAST|IFF_POINTOPOINT is invalid + - If neither of these three flags are set; + the interface is NBMA. + + - IFF_MULTICAST does not mean anything special: + multicasts can be used on all not-NBMA links. + IFF_MULTICAST means that this media uses special encapsulation + for multicast frames. Apparently, all IFF_POINTOPOINT and + IFF_BROADCAST devices are able to use multicasts too. + */ + +/* IFLA_LINK. + For usual devices it is equal ifi_index. + If it is a "virtual interface" (f.e. tunnel), ifi_link + can point to real physical interface (f.e. for bandwidth calculations), + or maybe 0, what means, that real media is unknown (usual + for IPIP tunnels, when route to endpoint is allowed to change) + */ + +/* Subtype attributes for IFLA_PROTINFO */ +enum +{ + IFLA_INET6_UNSPEC, + IFLA_INET6_FLAGS, /* link flags */ + IFLA_INET6_CONF, /* sysctl parameters */ + IFLA_INET6_STATS, /* statistics */ + IFLA_INET6_MCAST, /* MC things. What of them? */ + IFLA_INET6_CACHEINFO, /* time values and max reasm size */ + __IFLA_INET6_MAX +}; + +#define IFLA_INET6_MAX (__IFLA_INET6_MAX - 1) + +struct ifla_cacheinfo +{ + __u32 max_reasm_len; + __u32 tstamp; /* ipv6InterfaceTable updated timestamp */ + __u32 reachable_time; + __u32 retrans_time; +}; + +#endif /* _LINUX_IF_LINK_H */ diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 9c92dc8b9a08..3a18addaed4c 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -2,7 +2,7 @@ #define __LINUX_RTNETLINK_H #include -#include +#include /**** * Routing/neighbour discovery messages. -- cgit v1.2.3 From b854d0d218688b30ccea70521d6ea5f3f56d4e12 Mon Sep 17 00:00:00 2001 From: YOSHIFUJI Hideaki Date: Wed, 27 Sep 2006 22:43:05 -0700 Subject: [NET] KBUILD: Add missing entries for new net headers. Add the following for userspace export by the 'headers_include' make target: linux/fib_rules.h, linux/if_addr.h, linux/if_link.h, linux/neighbour.h. Signed-off-by: YOSHIFUJI Hideaki Signed-off-by: David S. Miller --- include/linux/Kbuild | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/Kbuild b/include/linux/Kbuild index 1df2ac30a4d2..f7a52e19b4be 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -58,6 +58,7 @@ header-y += elf-em.h header-y += fadvise.h header-y += fd.h header-y += fdreg.h +header-y += fib_rules.h header-y += ftape-header-segment.h header-y += ftape-vendors.h header-y += fuse.h @@ -70,6 +71,7 @@ header-y += hysdn_if.h header-y += i2c-dev.h header-y += i8k.h header-y += icmp.h +header-y += if_addr.h header-y += if_arcnet.h header-y += if_arp.h header-y += if_bonding.h @@ -79,6 +81,7 @@ header-y += if_fddi.h header-y += if.h header-y += if_hippi.h header-y += if_infiniband.h +header-y += if_link.h header-y += if_packet.h header-y += if_plip.h header-y += if_ppp.h @@ -110,6 +113,7 @@ header-y += mmtimer.h header-y += mqueue.h header-y += mtio.h header-y += ncp_no.h +header-y += neighbour.h header-y += netfilter_arp.h header-y += netrom.h header-y += nfs2.h -- cgit v1.2.3 From d77072ecfb6d28287d5e2a61d60d87a3a444ac97 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 28 Sep 2006 14:20:34 -0700 Subject: [NET]: Annotate dst_ops protocol Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 13d6d4eb8b3a..9264139bd8df 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -187,7 +187,7 @@ struct hh_cache { struct hh_cache *hh_next; /* Next entry */ atomic_t hh_refcnt; /* number of users */ - unsigned short hh_type; /* protocol identifier, f.e ETH_P_IP + __be16 hh_type; /* protocol identifier, f.e ETH_P_IP * NOTE: For VLANs, this will be the * encapuslated type. --BLG */ -- cgit v1.2.3 From 59b8bfd8fd608821e5addc9f4682c7f2424afd8c Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 28 Sep 2006 14:21:07 -0700 Subject: [NETFILTER]: netfilter misc annotations Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/netfilter_arp/arp_tables.h | 6 +++--- include/linux/netfilter_ipv4/ip_queue.h | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_arp/arp_tables.h b/include/linux/netfilter_arp/arp_tables.h index 149e87c9ab13..44e39b61d9e7 100644 --- a/include/linux/netfilter_arp/arp_tables.h +++ b/include/linux/netfilter_arp/arp_tables.h @@ -46,11 +46,11 @@ struct arpt_arp { struct arpt_devaddr_info tgt_devaddr; /* ARP operation code. */ - u_int16_t arpop, arpop_mask; + __be16 arpop, arpop_mask; /* ARP hardware address and protocol address format. */ - u_int16_t arhrd, arhrd_mask; - u_int16_t arpro, arpro_mask; + __be16 arhrd, arhrd_mask; + __be16 arpro, arpro_mask; /* The protocol address length is only accepted if it is 4 * so there is no use in offering a way to do filtering on it. diff --git a/include/linux/netfilter_ipv4/ip_queue.h b/include/linux/netfilter_ipv4/ip_queue.h index aa08d68c4841..a03507f465f8 100644 --- a/include/linux/netfilter_ipv4/ip_queue.h +++ b/include/linux/netfilter_ipv4/ip_queue.h @@ -26,7 +26,7 @@ typedef struct ipq_packet_msg { unsigned int hook; /* Netfilter hook we rode in on */ char indev_name[IFNAMSIZ]; /* Name of incoming interface */ char outdev_name[IFNAMSIZ]; /* Name of outgoing interface */ - unsigned short hw_protocol; /* Hardware protocol (network order) */ + __be16 hw_protocol; /* Hardware protocol (network order) */ unsigned short hw_type; /* Hardware type */ unsigned char hw_addrlen; /* Hardware address length */ unsigned char hw_addr[8]; /* Hardware address */ -- cgit v1.2.3 From cdcb71bf964e02e0a22007f5d90ead7bede3b85b Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 28 Sep 2006 14:21:37 -0700 Subject: [NETFILTER]: conntrack annotations Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/netfilter_ipv4/ip_conntrack.h | 2 +- include/linux/netfilter_ipv4/ip_conntrack_tuple.h | 16 ++++++++-------- 2 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv4/ip_conntrack.h b/include/linux/netfilter_ipv4/ip_conntrack.h index 51dbec1892c8..64e868034c4a 100644 --- a/include/linux/netfilter_ipv4/ip_conntrack.h +++ b/include/linux/netfilter_ipv4/ip_conntrack.h @@ -157,7 +157,7 @@ struct ip_conntrack_expect unsigned int flags; #ifdef CONFIG_IP_NF_NAT_NEEDED - u_int32_t saved_ip; + __be32 saved_ip; /* This is the original per-proto part, used to map the * expected connection the way the recipient expects. */ union ip_conntrack_manip_proto saved_proto; diff --git a/include/linux/netfilter_ipv4/ip_conntrack_tuple.h b/include/linux/netfilter_ipv4/ip_conntrack_tuple.h index 2fdabdb4c0ef..c228bde74c33 100644 --- a/include/linux/netfilter_ipv4/ip_conntrack_tuple.h +++ b/include/linux/netfilter_ipv4/ip_conntrack_tuple.h @@ -23,13 +23,13 @@ union ip_conntrack_manip_proto __be16 port; } tcp; struct { - u_int16_t port; + __be16 port; } udp; struct { - u_int16_t id; + __be16 id; } icmp; struct { - u_int16_t port; + __be16 port; } sctp; struct { __be16 key; /* key is 32bit, pptp only uses 16 */ @@ -39,7 +39,7 @@ union ip_conntrack_manip_proto /* The manipulable part of the tuple. */ struct ip_conntrack_manip { - u_int32_t ip; + __be32 ip; union ip_conntrack_manip_proto u; }; @@ -50,22 +50,22 @@ struct ip_conntrack_tuple /* These are the parts of the tuple which are fixed. */ struct { - u_int32_t ip; + __be32 ip; union { /* Add other protocols here. */ u_int16_t all; struct { - u_int16_t port; + __be16 port; } tcp; struct { - u_int16_t port; + __be16 port; } udp; struct { u_int8_t type, code; } icmp; struct { - u_int16_t port; + __be16 port; } sctp; struct { __be16 key; /* key is 32bit, -- cgit v1.2.3 From a76b11dd25957287af12ce6855be6d7fd415b3a9 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 28 Sep 2006 14:22:02 -0700 Subject: [NETFILTER]: NAT annotations Signed-off-by: Al Viro 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 98f8407e4cb5..bdf553620ca1 100644 --- a/include/linux/netfilter_ipv4/ip_nat.h +++ b/include/linux/netfilter_ipv4/ip_nat.h @@ -33,7 +33,7 @@ struct ip_nat_range unsigned int flags; /* Inclusive: network order. */ - u_int32_t min_ip, max_ip; + __be32 min_ip, max_ip; /* Inclusive: network order */ union ip_conntrack_manip_proto min, max; -- cgit v1.2.3 From 6a19d61472d0802a24493c0d200e88f99ad39cd8 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 28 Sep 2006 14:22:24 -0700 Subject: [NETFILTER]: ipt annotations Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/netfilter_ipv4/ipt_iprange.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv4/ipt_iprange.h b/include/linux/netfilter_ipv4/ipt_iprange.h index 3ecb3bd63676..34ab0fb736e2 100644 --- a/include/linux/netfilter_ipv4/ipt_iprange.h +++ b/include/linux/netfilter_ipv4/ipt_iprange.h @@ -8,7 +8,7 @@ struct ipt_iprange { /* Inclusive: network order. */ - u_int32_t min_ip, max_ip; + __be32 min_ip, max_ip; }; struct ipt_iprange_info -- cgit v1.2.3 From d4263cde88d3fee2af0aac8836bb785cdb6b06c0 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 28 Sep 2006 14:22:51 -0700 Subject: [NETFILTER]: h323 annotations Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/netfilter_ipv4/ip_conntrack_h323.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv4/ip_conntrack_h323.h b/include/linux/netfilter_ipv4/ip_conntrack_h323.h index 3cbff7379002..943cc6a4871d 100644 --- a/include/linux/netfilter_ipv4/ip_conntrack_h323.h +++ b/include/linux/netfilter_ipv4/ip_conntrack_h323.h @@ -30,7 +30,7 @@ struct ip_ct_h323_master { struct ip_conntrack_expect; extern int get_h225_addr(unsigned char *data, TransportAddress * addr, - u_int32_t * ip, u_int16_t * port); + __be32 * ip, u_int16_t * port); extern void ip_conntrack_h245_expect(struct ip_conntrack *new, struct ip_conntrack_expect *this); extern void ip_conntrack_q931_expect(struct ip_conntrack *new, @@ -38,11 +38,11 @@ extern void ip_conntrack_q931_expect(struct ip_conntrack *new, extern int (*set_h245_addr_hook) (struct sk_buff ** pskb, unsigned char **data, int dataoff, H245_TransportAddress * addr, - u_int32_t ip, u_int16_t port); + __be32 ip, u_int16_t port); extern int (*set_h225_addr_hook) (struct sk_buff ** pskb, unsigned char **data, int dataoff, TransportAddress * addr, - u_int32_t ip, u_int16_t port); + __be32 ip, u_int16_t port); extern int (*set_sig_addr_hook) (struct sk_buff ** pskb, struct ip_conntrack * ct, enum ip_conntrack_info ctinfo, -- cgit v1.2.3 From 32f50cdee666333168b5203c7864bede159f789e Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Thu, 28 Sep 2006 14:51:47 -0700 Subject: [NetLabel]: add audit support for configuration changes This patch adds audit support to NetLabel, including six new audit message types shown below. #define AUDIT_MAC_UNLBL_ACCEPT 1406 #define AUDIT_MAC_UNLBL_DENY 1407 #define AUDIT_MAC_CIPSOV4_ADD 1408 #define AUDIT_MAC_CIPSOV4_DEL 1409 #define AUDIT_MAC_MAP_ADD 1410 #define AUDIT_MAC_MAP_DEL 1411 Signed-off-by: Paul Moore Acked-by: James Morris Signed-off-by: David S. Miller --- include/linux/audit.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index 40a6c26294ae..42719d07612a 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -95,6 +95,12 @@ #define AUDIT_MAC_POLICY_LOAD 1403 /* Policy file load */ #define AUDIT_MAC_STATUS 1404 /* Changed enforcing,permissive,off */ #define AUDIT_MAC_CONFIG_CHANGE 1405 /* Changes to booleans */ +#define AUDIT_MAC_UNLBL_ACCEPT 1406 /* NetLabel: allow unlabeled traffic */ +#define AUDIT_MAC_UNLBL_DENY 1407 /* NetLabel: deny unlabeled traffic */ +#define AUDIT_MAC_CIPSOV4_ADD 1408 /* NetLabel: add CIPSOv4 DOI entry */ +#define AUDIT_MAC_CIPSOV4_DEL 1409 /* NetLabel: del CIPSOv4 DOI entry */ +#define AUDIT_MAC_MAP_ADD 1410 /* NetLabel: add LSM domain mapping */ +#define AUDIT_MAC_MAP_DEL 1411 /* NetLabel: del LSM domain mapping */ #define AUDIT_FIRST_KERN_ANOM_MSG 1700 #define AUDIT_LAST_KERN_ANOM_MSG 1799 -- cgit v1.2.3 From 0891a8d706d6e6838a926b6dec42f95581747d0e Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 29 Sep 2006 01:58:34 -0700 Subject: [PATCH] __percpu_alloc_mask() has to be __always_inline in UP case ... or we'll end up with cpu_online_map being evaluated on UP. In modules. cpumask.h is very careful to avoid that, and for a very good reason. So should we... PS: yes, it really triggers (on alpha). Signed-off-by: Al Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/percpu.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 3835a9642f13..46ec72fa2c84 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -74,7 +74,7 @@ static inline int __percpu_populate_mask(void *__pdata, size_t size, gfp_t gfp, return 0; } -static inline void *__percpu_alloc_mask(size_t size, gfp_t gfp, cpumask_t *mask) +static __always_inline void *__percpu_alloc_mask(size_t size, gfp_t gfp, cpumask_t *mask) { return kzalloc(size, gfp); } -- cgit v1.2.3 From e04da1dfd9041e306cb33d1b40b6005c23c5b325 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 29 Sep 2006 01:58:35 -0700 Subject: [PATCH] sys_getcpu() prototype annotated Signed-off-by: Al Viro 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 3f0f716225ec..2d1c3d5c83ac 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -597,6 +597,6 @@ asmlinkage long sys_get_robust_list(int pid, size_t __user *len_ptr); asmlinkage long sys_set_robust_list(struct robust_list_head __user *head, size_t len); -asmlinkage long sys_getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *cache); +asmlinkage long sys_getcpu(unsigned __user *cpu, unsigned __user *node, struct getcpu_cache __user *cache); #endif -- cgit v1.2.3 From f71b2f10f56802075d67c5710cd9f1816382d720 Mon Sep 17 00:00:00 2001 From: Dave Kleikamp Date: Fri, 29 Sep 2006 01:58:39 -0700 Subject: [PATCH] JBD: Make journal_brelse_array() static It's always good to make symbols static when we can, and this also eliminates the need to rename the function in jbd2 Suggested by Eric Sandeen. Signed-off-by: Dave Kleikamp Cc: Eric Sandeen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/jbd.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/jbd.h b/include/linux/jbd.h index a6d9daa38c6d..fe89444b1c6f 100644 --- a/include/linux/jbd.h +++ b/include/linux/jbd.h @@ -977,7 +977,6 @@ extern void journal_write_revoke_records(journal_t *, transaction_t *); extern int journal_set_revoke(journal_t *, unsigned long, tid_t); extern int journal_test_revoke(journal_t *, unsigned long, tid_t); extern void journal_clear_revoke(journal_t *); -extern void journal_brelse_array(struct buffer_head *b[], int n); extern void journal_switch_revoke_table(journal_t *journal); /* -- cgit v1.2.3 From 2dcea57ae19275451a756a2d5bf96b329487b0e0 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Fri, 29 Sep 2006 01:58:41 -0700 Subject: [PATCH] convert s390 page handling macros to functions Convert s390 page handling macros to functions. In particular this fixes a problem with s390's SetPageUptodate macro which uses its input parameter twice which again can cause subtle bugs. [akpm@osdl.org: build fix] Cc: Martin Schwidefsky Signed-off-by: Heiko Carstens Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 9d7921dd50f0..4830a3bedfb2 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -128,12 +128,11 @@ #define PageUptodate(page) test_bit(PG_uptodate, &(page)->flags) #ifdef CONFIG_S390 -#define SetPageUptodate(_page) \ - do { \ - struct page *__page = (_page); \ - if (!test_and_set_bit(PG_uptodate, &__page->flags)) \ - page_test_and_clear_dirty(_page); \ - } while (0) +static inline void SetPageUptodate(struct page *page) +{ + if (!test_and_set_bit(PG_uptodate, &page->flags)) + page_test_and_clear_dirty(page); +} #else #define SetPageUptodate(page) set_bit(PG_uptodate, &(page)->flags) #endif -- cgit v1.2.3 From 199a9afc3dbe98c35326f1d3907ab94dae953a6e Mon Sep 17 00:00:00 2001 From: Dave Jones Date: Fri, 29 Sep 2006 01:59:00 -0700 Subject: [PATCH] Debug variants of linked list macros Signed-off-by: Dave Jones Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/list.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/list.h b/include/linux/list.h index 65a5b5ceda49..a9c90287c0ff 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -39,6 +39,7 @@ static inline void INIT_LIST_HEAD(struct list_head *list) * This is only for internal list manipulation where we know * the prev/next entries already! */ +#ifndef CONFIG_DEBUG_LIST static inline void __list_add(struct list_head *new, struct list_head *prev, struct list_head *next) @@ -48,6 +49,11 @@ static inline void __list_add(struct list_head *new, new->prev = prev; prev->next = new; } +#else +extern void __list_add(struct list_head *new, + struct list_head *prev, + struct list_head *next); +#endif /** * list_add - add a new entry @@ -57,10 +63,15 @@ static inline void __list_add(struct list_head *new, * Insert a new entry after the specified head. * This is good for implementing stacks. */ +#ifndef CONFIG_DEBUG_LIST static inline void list_add(struct list_head *new, struct list_head *head) { __list_add(new, head, head->next); } +#else +extern void list_add(struct list_head *new, struct list_head *head); +#endif + /** * list_add_tail - add a new entry @@ -153,12 +164,16 @@ static inline void __list_del(struct list_head * prev, struct list_head * next) * Note: list_empty on entry does not return true after this, the entry is * in an undefined state. */ +#ifndef CONFIG_DEBUG_LIST static inline void list_del(struct list_head *entry) { __list_del(entry->prev, entry->next); entry->next = LIST_POISON1; entry->prev = LIST_POISON2; } +#else +extern void list_del(struct list_head *entry); +#endif /** * list_del_rcu - deletes entry from list without re-initialization -- cgit v1.2.3 From 9938406ab6b2558d60c0c7200cc8e12f1ea7104a Mon Sep 17 00:00:00 2001 From: Michal Schmidt Date: Fri, 29 Sep 2006 01:59:03 -0700 Subject: [PATCH] Make touch_nmi_watchdog imply touch_softlockup_watchdog on all archs touch_nmi_watchdog() calls touch_softlockup_watchdog() on both architectures that implement it (i386 and x86_64). On other architectures it does nothing at all. touch_nmi_watchdog() should imply touch_softlockup_watchdog() on all architectures. Suggested by Andi Kleen. [heiko.carstens@de.ibm.com: s390 fix] Signed-off-by: Michal Schmidt Cc: Andi Kleen Cc: Martin Schwidefsky Signed-off-by: Heiko Carstens Cc: Michal Schmidt Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nmi.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nmi.h b/include/linux/nmi.h index c8f4d2f627d7..e16904e28c3a 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -4,6 +4,7 @@ #ifndef LINUX_NMI_H #define LINUX_NMI_H +#include #include /** @@ -16,7 +17,7 @@ #ifdef ARCH_HAS_NMI_WATCHDOG extern void touch_nmi_watchdog(void); #else -# define touch_nmi_watchdog() do { } while(0) +# define touch_nmi_watchdog() touch_softlockup_watchdog() #endif #endif -- cgit v1.2.3 From 58012cd788443b9d144bd7c72260a84b6b30f45d Mon Sep 17 00:00:00 2001 From: Chris Boot Date: Fri, 29 Sep 2006 01:59:07 -0700 Subject: [PATCH] scx200_gpio export cleanups Use EXPORT_SYMBOL_GPL for new symbols, and declare the struct in the header file for access by other modules. Signed-off-by: Chris Boot Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/scx200_gpio.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/scx200_gpio.h b/include/linux/scx200_gpio.h index 90dd069cc145..1a82d30c4b17 100644 --- a/include/linux/scx200_gpio.h +++ b/include/linux/scx200_gpio.h @@ -4,6 +4,7 @@ u32 scx200_gpio_configure(unsigned index, u32 set, u32 clear); extern unsigned scx200_gpio_base; extern long scx200_gpio_shadow[2]; +extern struct nsc_gpio_ops scx200_gpio_ops; #define scx200_gpio_present() (scx200_gpio_base!=0) -- cgit v1.2.3 From 6c9979185c7ef4feeb7f8d29be032b8f032a1838 Mon Sep 17 00:00:00 2001 From: "Serge E. Hallyn" Date: Fri, 29 Sep 2006 01:59:11 -0700 Subject: [PATCH] kthread: convert loop.c to kthread Convert loop.c from the deprecated kernel_thread to kthread. This patch simplifies the code quite a bit and passes similar testing to the previous submission on both emulated x86 and s390. Changes since last submission: switched to using a rather simple loop based on wait_event_interruptible. Signed-off-by: Serge E. Hallyn Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/loop.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/loop.h b/include/linux/loop.h index e76c7611d6cc..191a595055f0 100644 --- a/include/linux/loop.h +++ b/include/linux/loop.h @@ -59,10 +59,9 @@ struct loop_device { struct bio *lo_bio; struct bio *lo_biotail; int lo_state; - struct completion lo_done; - struct completion lo_bh_done; struct mutex lo_ctl_mutex; - int lo_pending; + struct task_struct *lo_thread; + wait_queue_head_t lo_event; request_queue_t *lo_queue; }; -- cgit v1.2.3 From db0b0ead60815155c791e8f479ee4777e7946369 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Fri, 29 Sep 2006 01:59:28 -0700 Subject: [PATCH] lockdep: don't pull in includes when lockdep disabled Do not pull in various includes through lockdep.h if lockdep is disabled. Signed-off-by: Michael S. Tsirkin Cc: Ingo Molnar Cc: Arjan van de Ven Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/lockdep.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index c040a8c969aa..1314ca0f29be 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -8,13 +8,13 @@ #ifndef __LINUX_LOCKDEP_H #define __LINUX_LOCKDEP_H +#ifdef CONFIG_LOCKDEP + #include #include #include #include -#ifdef CONFIG_LOCKDEP - /* * Lock-class usage-state bits: */ -- cgit v1.2.3 From 650a898342b3fa21c392c06a2b7010fa19823efa Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Fri, 29 Sep 2006 01:59:35 -0700 Subject: [PATCH] vfs: define new lookup flag for chdir In the "operation does permission checking" model used by fuse, chdir permission is not checked, since there's no chdir method. For this case set a lookup flag, which will be passed to ->permission(), so fuse can distinguish it from permission checks for other operations. Signed-off-by: Miklos Szeredi Cc: Al Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/namei.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/namei.h b/include/linux/namei.h index 45511a5918d3..c6470ba00668 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -54,6 +54,7 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND}; #define LOOKUP_OPEN (0x0100) #define LOOKUP_CREATE (0x0200) #define LOOKUP_ACCESS (0x0400) +#define LOOKUP_CHDIR (0x0800) extern int FASTCALL(__user_walk(const char __user *, unsigned, struct nameidata *)); extern int FASTCALL(__user_walk_fd(int dfd, const char __user *, unsigned, struct nameidata *)); -- cgit v1.2.3 From 2e0c1f6ce7b816f63fea2af3e5e2cb20c66430e9 Mon Sep 17 00:00:00 2001 From: Shem Multinymous Date: Fri, 29 Sep 2006 01:59:37 -0700 Subject: [PATCH] DMI: Decode and save OEM String information This teaches dmi_decode() how to decode and save OEM Strings (type 11) DMI information, which is currently discarded silently. Existing code using DMI is not affected. Follows the "System Management BIOS (SMBIOS) Specification" (http://www.dmtf.org/standards/smbios), and also the userspace dmidecode.c code. OEM Strings are the only safe way to identify some hardware, e.g., the ThinkPad embedded controller used by the soon-to-be-submitted tp_smapi driver. This will also let us eliminate the long whitelist in the mainline hdaps driver (in a future patch). Signed-off-by: Shem Multinymous Cc: Bjorn Helgaas Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/dmi.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dmi.h b/include/linux/dmi.h index b2cd2071d432..38dc403be70b 100644 --- a/include/linux/dmi.h +++ b/include/linux/dmi.h @@ -27,7 +27,8 @@ enum dmi_device_type { DMI_DEV_TYPE_ETHERNET, DMI_DEV_TYPE_TOKENRING, DMI_DEV_TYPE_SOUND, - DMI_DEV_TYPE_IPMI = -1 + DMI_DEV_TYPE_IPMI = -1, + DMI_DEV_TYPE_OEM_STRING = -2 }; struct dmi_header { -- cgit v1.2.3 From 402749ea2538be9ddad981a990739b93a0178bc6 Mon Sep 17 00:00:00 2001 From: Matthias Urlichs Date: Fri, 29 Sep 2006 01:59:37 -0700 Subject: [PATCH] Remove unused tty_struct field Unused: tty_struct.max_flip_cnt $ git grep max_flip_cnt include/linux/tty.h: int max_flip_cnt; $ Cc: Paul Fulghum Acked-by: Alan Cox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/tty.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 04827ca65781..d1dec3d0c814 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -190,7 +190,6 @@ struct tty_struct { struct tty_struct *link; struct fasync_struct *fasync; struct tty_bufhead buf; - int max_flip_cnt; int alt_speed; /* For magic substitution of 38400 bps */ wait_queue_head_t write_wait; wait_queue_head_t read_wait; -- cgit v1.2.3 From 3d5b6fccc4b900cc4267692f015ea500bad4c6bf Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Fri, 29 Sep 2006 01:59:40 -0700 Subject: [PATCH] task_struct: ifdef Missed'em V IPC ipc/sem.c only. $ agrep sysvsem -w -n ipc/sem.c:912: undo_list = current->sysvsem.undo_list; ipc/sem.c:932: undo_list = current->sysvsem.undo_list; ipc/sem.c:954: undo_list = current->sysvsem.undo_list; ipc/sem.c:963: current->sysvsem.undo_list = undo_list; ipc/sem.c:1247: tsk->sysvsem.undo_list = undo_list; ipc/sem.c:1249: tsk->sysvsem.undo_list = NULL; ipc/sem.c:1271: undo_list = tsk->sysvsem.undo_list; include/linux/sched.h:876: struct sysv_sem sysvsem; Signed-off-by: Alexey Dobriyan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 9d4aa7f95bc8..27122575d902 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -886,8 +886,10 @@ struct task_struct { - initialized normally by flush_old_exec */ /* file system info */ int link_count, total_link_count; +#ifdef CONFIG_SYSVIPC /* ipc stuff */ struct sysv_sem sysvsem; +#endif /* CPU-specific state of this task */ struct thread_struct thread; /* filesystem information */ -- cgit v1.2.3 From 6c5c934153513dc72e2d6464f39e8ef1f27c0a3e Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Fri, 29 Sep 2006 01:59:40 -0700 Subject: [PATCH] ifdef blktrace debugging fields Signed-off-by: Alexey Dobriyan Acked-by: Jens Axboe Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/blkdev.h | 4 ++-- include/linux/sched.h | 3 ++- 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c773ee545ebd..cfde8b3ee919 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -417,9 +417,9 @@ struct request_queue unsigned int sg_timeout; unsigned int sg_reserved_size; int node; - +#ifdef CONFIG_BLK_DEV_IO_TRACE struct blk_trace *blk_trace; - +#endif /* * reserved for flush operations */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 27122575d902..3696f2f7126d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -784,8 +784,9 @@ struct task_struct { struct prio_array *array; unsigned short ioprio; +#ifdef CONFIG_BLK_DEV_IO_TRACE unsigned int btrace_seq; - +#endif unsigned long sleep_avg; unsigned long long timestamp, last_ran; unsigned long long sched_time; /* sched_clock time spent running */ -- cgit v1.2.3 From d6bd3a39f7c6ebad49c261c3d458df974c880758 Mon Sep 17 00:00:00 2001 From: Rolf Eike Beer Date: Fri, 29 Sep 2006 01:59:48 -0700 Subject: [PATCH] Move valid_dma_direction() from x86_64 to generic code As suggested by Muli Ben-Yehuda this function is moved to generic code as may be useful for all archs. [akpm@osdl.org: fix] Signed-off-by: Rolf Eike Beer Cc: Muli Ben-Yehuda Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/dma-mapping.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 635690cf3e3d..ff203c465fed 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -24,6 +24,13 @@ enum dma_data_direction { #define DMA_28BIT_MASK 0x000000000fffffffULL #define DMA_24BIT_MASK 0x0000000000ffffffULL +static inline int valid_dma_direction(int dma_direction) +{ + return ((dma_direction == DMA_BIDIRECTIONAL) || + (dma_direction == DMA_TO_DEVICE) || + (dma_direction == DMA_FROM_DEVICE)); +} + #include /* Backwards compat, remove in 2.7.x */ -- cgit v1.2.3 From 0e51a720b9d9ea5ebf0fda39108919c6626bffa3 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Fri, 29 Sep 2006 01:59:56 -0700 Subject: [PATCH] ifdef ->quota_read, ->quota_write All suppliers of ->quota_read, ->quota_write (I've found ext2, ext3, UFS, reiserfs) already have them properly ifdeffed. All callers of ->quota_read, ->quota_write are under CONFIG_QUOTA umbrella, so... Signed-off-by: Alexey Dobriyan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 8f74dfbb2edd..4caec6cebc42 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1143,9 +1143,10 @@ struct super_operations { int (*show_options)(struct seq_file *, struct vfsmount *); int (*show_stats)(struct seq_file *, struct vfsmount *); - +#ifdef CONFIG_QUOTA ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t); ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t); +#endif }; /* Inode state bits. Protected by inode_lock. */ -- cgit v1.2.3 From 068fbb315dd1e9dd3418aac39a9cfeabe39c16a6 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Fri, 29 Sep 2006 01:59:58 -0700 Subject: [PATCH] reiserfs: ifdef xattr_sem Shrink reiserfs inode by 12 bytes for xattr non-users (me). -reiser_inode_cache 356 11 +reiser_inode_cache 344 11 Signed-off-by: Alexey Dobriyan Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/reiserfs_fs_i.h | 2 ++ include/linux/reiserfs_xattr.h | 8 ++++++++ 2 files changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/reiserfs_fs_i.h b/include/linux/reiserfs_fs_i.h index 149be8d9a0c9..711e7e7cafa5 100644 --- a/include/linux/reiserfs_fs_i.h +++ b/include/linux/reiserfs_fs_i.h @@ -55,7 +55,9 @@ struct reiserfs_inode_info { struct posix_acl *i_acl_access; struct posix_acl *i_acl_default; +#ifdef CONFIG_REISERFS_FS_XATTR struct rw_semaphore xattr_sem; +#endif struct inode vfs_inode; }; diff --git a/include/linux/reiserfs_xattr.h b/include/linux/reiserfs_xattr.h index 5e961035c725..966c35851b2e 100644 --- a/include/linux/reiserfs_xattr.h +++ b/include/linux/reiserfs_xattr.h @@ -97,6 +97,11 @@ static inline void reiserfs_mark_inode_private(struct inode *inode) inode->i_flags |= S_PRIVATE; } +static inline void reiserfs_init_xattr_rwsem(struct inode *inode) +{ + init_rwsem(&REISERFS_I(inode)->xattr_sem); +} + #else #define is_reiserfs_priv_object(inode) 0 @@ -129,6 +134,9 @@ static inline int reiserfs_xattr_init(struct super_block *sb, int mount_flags) sb->s_flags = (sb->s_flags & ~MS_POSIXACL); /* to be sure */ return 0; }; +static inline void reiserfs_init_xattr_rwsem(struct inode *inode) +{ +} #endif #endif /* __KERNEL__ */ -- cgit v1.2.3 From cfe14677f286c9be5d683b88214def8f4b8a6f24 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Fri, 29 Sep 2006 02:00:00 -0700 Subject: [PATCH] reiserfs: ifdef ACL stuff from inode Shrink reiserfs inode more (by 8 bytes) for ACL non-users: -reiser_inode_cache 344 11 +reiser_inode_cache 336 11 Signed-off-by: Alexey Dobriyan Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/reiserfs_acl.h | 17 +++++++++++++++++ include/linux/reiserfs_fs_i.h | 3 ++- 2 files changed, 19 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/reiserfs_acl.h b/include/linux/reiserfs_acl.h index 806ec5b06707..fe00f781a622 100644 --- a/include/linux/reiserfs_acl.h +++ b/include/linux/reiserfs_acl.h @@ -56,6 +56,16 @@ extern int reiserfs_xattr_posix_acl_init(void) __init; extern int reiserfs_xattr_posix_acl_exit(void); extern struct reiserfs_xattr_handler posix_acl_default_handler; extern struct reiserfs_xattr_handler posix_acl_access_handler; + +static inline void reiserfs_init_acl_access(struct inode *inode) +{ + REISERFS_I(inode)->i_acl_access = NULL; +} + +static inline void reiserfs_init_acl_default(struct inode *inode) +{ + REISERFS_I(inode)->i_acl_default = NULL; +} #else #define reiserfs_cache_default_acl(inode) 0 @@ -87,4 +97,11 @@ reiserfs_inherit_default_acl(const struct inode *dir, struct dentry *dentry, return 0; } +static inline void reiserfs_init_acl_access(struct inode *inode) +{ +} + +static inline void reiserfs_init_acl_default(struct inode *inode) +{ +} #endif diff --git a/include/linux/reiserfs_fs_i.h b/include/linux/reiserfs_fs_i.h index 711e7e7cafa5..5b3b297aa2c5 100644 --- a/include/linux/reiserfs_fs_i.h +++ b/include/linux/reiserfs_fs_i.h @@ -52,9 +52,10 @@ struct reiserfs_inode_info { ** flushed */ unsigned long i_trans_id; struct reiserfs_journal_list *i_jl; - +#ifdef CONFIG_REISERFS_FS_POSIX_ACL struct posix_acl *i_acl_access; struct posix_acl *i_acl_default; +#endif #ifdef CONFIG_REISERFS_FS_XATTR struct rw_semaphore xattr_sem; #endif -- cgit v1.2.3 From 50462062a02226a698a211d5bd535376c89b8603 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Fri, 29 Sep 2006 02:00:01 -0700 Subject: [PATCH] fs.h: ifdef security fields [assuming BSD security levels are deleted] The only user of i_security, f_security, s_security fields is SELinux, however, quite a few security modules are trying to get into kernel. So, wrap them under CONFIG_SECURITY. Adding config option for each security field is likely an overkill. Following Stephen Smalley's suggestion, i_security initialization is moved to security_inode_alloc() to not clutter core code with ifdefs and make alloc_inode() codepath tiny little bit smaller and faster. The user of (highly greppable) struct fown_struct::security field is still to be found. I've checked every "fown_struct" and every "f_owner" occurence. Additionally it's removal doesn't break i386 allmodconfig build. struct inode, struct file, struct super_block, struct fown_struct become smaller. P.S. Combined with two reiserfs inode shrinking patches sent to linux-fsdevel, I can finally suck 12 reiserfs inodes into one page. /proc/slabinfo -ext2_inode_cache 388 10 +ext2_inode_cache 384 10 -inode_cache 280 14 +inode_cache 276 14 -proc_inode_cache 296 13 +proc_inode_cache 292 13 -reiser_inode_cache 336 11 +reiser_inode_cache 332 12 <= -shmem_inode_cache 372 10 +shmem_inode_cache 368 10 Signed-off-by: Alexey Dobriyan Cc: Stephen Smalley Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 8 ++++++-- include/linux/security.h | 1 + 2 files changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 4caec6cebc42..6eafbe309483 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -553,7 +553,9 @@ struct inode { unsigned int i_flags; atomic_t i_writecount; +#ifdef CONFIG_SECURITY void *i_security; +#endif void *i_private; /* fs or device private pointer */ #ifdef __NEED_I_SIZE_ORDERED seqcount_t i_size_seqcount; @@ -645,7 +647,6 @@ struct fown_struct { rwlock_t lock; /* protects pid, uid, euid fields */ int pid; /* pid or -pgrp where SIGIO should be sent */ uid_t uid, euid; /* uid/euid of process setting the owner */ - void *security; int signum; /* posix.1b rt signal to be delivered on IO */ }; @@ -688,8 +689,9 @@ struct file { struct file_ra_state f_ra; unsigned long f_version; +#ifdef CONFIG_SECURITY void *f_security; - +#endif /* needed for tty driver, and maybe others */ void *private_data; @@ -877,7 +879,9 @@ struct super_block { int s_syncing; int s_need_sync_fs; atomic_t s_active; +#ifdef CONFIG_SECURITY void *s_security; +#endif struct xattr_handler **s_xattr; struct list_head s_inodes; /* all inodes */ diff --git a/include/linux/security.h b/include/linux/security.h index 9f56fb8a4a6c..9b5fea81f55e 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1595,6 +1595,7 @@ static inline void security_sb_post_pivotroot (struct nameidata *old_nd, static inline int security_inode_alloc (struct inode *inode) { + inode->i_security = NULL; return security_ops->inode_alloc_security (inode); } -- cgit v1.2.3 From ae78bf9c4f5fde3c67e2829505f195d7347ce3e4 Mon Sep 17 00:00:00 2001 From: Chris Mason Date: Fri, 29 Sep 2006 02:00:03 -0700 Subject: [PATCH] add -o flush for fat Fat is commonly used on removable media. Mounting with -o flush tells the FS to write things to disk as quickly as possible. It is like -o sync, but much faster (and not as safe). Signed-off-by: Chris Mason Cc: OGAWA Hirofumi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/msdos_fs.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/msdos_fs.h b/include/linux/msdos_fs.h index bae62d62dc3e..ce6c85815cbd 100644 --- a/include/linux/msdos_fs.h +++ b/include/linux/msdos_fs.h @@ -204,6 +204,7 @@ struct fat_mount_options { 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 */ + flush:1, /* write things quickly */ nocase:1; /* Does this need case conversion? 0=need case conversion*/ }; @@ -412,6 +413,8 @@ extern int fat_sync_inode(struct inode *inode); extern int fat_fill_super(struct super_block *sb, void *data, int silent, struct inode_operations *fs_dir_inode_ops, int isvfat); +extern int fat_flush_inodes(struct super_block *sb, struct inode *i1, + struct inode *i2); /* fat/misc.c */ extern void fat_fs_panic(struct super_block *s, const char *fmt, ...); extern void fat_clusters_flush(struct super_block *sb); -- cgit v1.2.3 From ca9bda00b4aafc42cd3d1b9d32934463e2993b4c Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Fri, 29 Sep 2006 02:00:03 -0700 Subject: [PATCH] tty locking on resize The current kernel serializes console resizes but does not serialize the resize against the tty structure updates. This means that while two parallel resizes cannot mess up the console you can get incorrect results reported. Secondly while doing this I added vc_lock_resize() to lock and resize the console. This leaves all knowledge of the console_sem in the vt/console driver and kicks it out of the tty layer, which is good Thirdly while doing this I decided I couldn't stand "disallocate" any longer so I switched it to "deallocate". Signed-off-by: Alan Cox Cc: Paul Fulghum Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vt_kern.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/vt_kern.h b/include/linux/vt_kern.h index 918a29763aea..1009d3fe1fc2 100644 --- a/include/linux/vt_kern.h +++ b/include/linux/vt_kern.h @@ -33,7 +33,8 @@ extern int fg_console, last_console, want_console; int vc_allocate(unsigned int console); int vc_cons_allocated(unsigned int console); int vc_resize(struct vc_data *vc, unsigned int cols, unsigned int lines); -void vc_disallocate(unsigned int console); +int vc_lock_resize(struct vc_data *vc, unsigned int cols, unsigned int lines); +void vc_deallocate(unsigned int console); void reset_palette(struct vc_data *vc); void do_blank_screen(int entering_gfx); void do_unblank_screen(int leaving_gfx); -- cgit v1.2.3 From 3b9b8ab65d8eed784b9164d03807cb2bda7b5cd6 Mon Sep 17 00:00:00 2001 From: Kirill Korotaev Date: Fri, 29 Sep 2006 02:00:05 -0700 Subject: [PATCH] Fix unserialized task->files changing Fixed race on put_files_struct on exec with proc. Restoring files on current on error path may lead to proc having a pointer to already kfree-d files_struct. ->files changing at exit.c and khtread.c are safe as exit_files() makes all things under lock. Found during OpenVZ stress testing. [akpm@osdl.org: add export] Signed-off-by: Pavel Emelianov Signed-off-by: Kirill Korotaev Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/file.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/file.h b/include/linux/file.h index 9f7c2513866f..74183e6f7f45 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -112,5 +112,6 @@ struct task_struct; struct files_struct *get_files_struct(struct task_struct *); void FASTCALL(put_files_struct(struct files_struct *fs)); +void reset_files_struct(struct task_struct *, struct files_struct *); #endif /* __LINUX_FILE_H */ -- cgit v1.2.3 From f400e198b2ed26ce55b22a1412ded0896e7516ac Mon Sep 17 00:00:00 2001 From: Sukadev Bhattiprolu Date: Fri, 29 Sep 2006 02:00:07 -0700 Subject: [PATCH] pidspace: is_init() This is an updated version of Eric Biederman's is_init() patch. (http://lkml.org/lkml/2006/2/6/280). It applies cleanly to 2.6.18-rc3 and replaces a few more instances of ->pid == 1 with is_init(). Further, is_init() checks pid and thus removes dependency on Eric's other patches for now. Eric's original description: There are a lot of places in the kernel where we test for init because we give it special properties. Most significantly init must not die. This results in code all over the kernel test ->pid == 1. Introduce is_init to capture this case. With multiple pid spaces for all of the cases affected we are looking for only the first process on the system, not some other process that has pid == 1. Signed-off-by: Eric W. Biederman Signed-off-by: Sukadev Bhattiprolu Cc: Dave Hansen Cc: Serge Hallyn Cc: Cedric Le Goater Cc: Acked-by: Paul Mackerras Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 3696f2f7126d..ed2af8671589 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1033,6 +1033,16 @@ static inline int pid_alive(struct task_struct *p) return p->pids[PIDTYPE_PID].pid != NULL; } +/** + * is_init - check if a task structure is the first user space + * task the kernel created. + * @p: Task structure to be checked. + */ +static inline int is_init(struct task_struct *tsk) +{ + return tsk->pid == 1; +} + extern void free_task(struct task_struct *tsk); #define get_task_struct(tsk) do { atomic_inc(&(tsk)->usage); } while(0) -- cgit v1.2.3 From 3ca212b813299899d2968aa0a24a797c3746f5ec Mon Sep 17 00:00:00 2001 From: Dave Jones Date: Fri, 29 Sep 2006 02:00:14 -0700 Subject: [PATCH] Remove another config.h After the asm/ uses of #include this one is the next biggest source of noise. Signed-off-by: Dave Jones Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmstat.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 176c7f797339..c89df55f6e03 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -3,7 +3,6 @@ #include #include -#include #include #include -- cgit v1.2.3 From af410fc13d95f079910fc3dca7496590c3275967 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 29 Sep 2006 02:00:14 -0700 Subject: [PATCH] make leds.h include relevant headers Make it possible to include linux/leds.h without first including list.h and spinlock.h. Signed-off-by: Johannes Berg Acked-by: Richard Purdie Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/leds.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/leds.h b/include/linux/leds.h index dc23c7c639f3..88afceffb7cb 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -12,6 +12,9 @@ #ifndef __LINUX_LEDS_H_INCLUDED #define __LINUX_LEDS_H_INCLUDED +#include +#include + struct device; struct class_device; /* -- cgit v1.2.3 From 1711ef3866b0360e102327389fe4b76c849bbe83 Mon Sep 17 00:00:00 2001 From: Toyo Abe Date: Fri, 29 Sep 2006 02:00:28 -0700 Subject: [PATCH] posix-timers: Fix clock_nanosleep() doesn't return the remaining time in compatibility mode The clock_nanosleep() function does not return the time remaining when the sleep is interrupted by a signal. This patch creates a new call out, compat_clock_nanosleep_restart(), which handles returning the remaining time after a sleep is interrupted. This patch revives clock_nanosleep_restart(). It is now accessed via the new call out. The compat_clock_nanosleep_restart() is used for compatibility access. Since this is implemented in compatibility mode the normal path is virtually unaffected - no real performance impact. Signed-off-by: Toyo Abe Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hrtimer.h | 1 + include/linux/posix-timers.h | 4 ++++ 2 files changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 4fc379de6c2f..fca93025ab51 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -138,6 +138,7 @@ extern long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp, const enum hrtimer_mode mode, const clockid_t clockid); +extern long hrtimer_nanosleep_restart(struct restart_block *restart_block); extern void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, struct task_struct *tsk); diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index 95572c434bc9..a7dd38f30ade 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -72,6 +72,7 @@ struct k_clock { int (*timer_create) (struct k_itimer *timer); int (*nsleep) (const clockid_t which_clock, int flags, struct timespec *, struct timespec __user *); + long (*nsleep_restart) (struct restart_block *restart_block); int (*timer_set) (struct k_itimer * timr, int flags, struct itimerspec * new_setting, struct itimerspec * old_setting); @@ -97,6 +98,7 @@ int posix_cpu_clock_set(const clockid_t which_clock, const struct timespec *ts); int posix_cpu_timer_create(struct k_itimer *timer); int posix_cpu_nsleep(const clockid_t which_clock, int flags, struct timespec *rqtp, struct timespec __user *rmtp); +long posix_cpu_nsleep_restart(struct restart_block *restart_block); int posix_cpu_timer_set(struct k_itimer *timer, int flags, struct itimerspec *new, struct itimerspec *old); int posix_cpu_timer_del(struct k_itimer *timer); @@ -111,4 +113,6 @@ void posix_cpu_timers_exit_group(struct task_struct *task); void set_process_cpu_timer(struct task_struct *task, unsigned int clock_idx, cputime_t *newval, cputime_t *oldval); +long clock_nanosleep_restart(struct restart_block *restart_block); + #endif -- cgit v1.2.3 From 3171a0305d62e6627a24bff35af4f997e4988a80 Mon Sep 17 00:00:00 2001 From: Atsushi Nemoto Date: Fri, 29 Sep 2006 02:00:32 -0700 Subject: [PATCH] simplify update_times (avoid jiffies/jiffies_64 aliasing problem) Pass ticks to do_timer() and update_times(), and adjust x86_64 and s390 timer interrupt handler with this change. Currently update_times() calculates ticks by "jiffies - wall_jiffies", but callers of do_timer() should know how many ticks to update. Passing ticks get rid of this redundant calculation. Also there are another redundancy pointed out by Martin Schwidefsky. This cleanup make a barrier added by 5aee405c662ca644980c184774277fc6d0769a84 needless. So this patch removes it. As a bonus, this cleanup make wall_jiffies can be removed easily, since now wall_jiffies is always synced with jiffies. (This patch does not really remove wall_jiffies. It would be another cleanup patch) Signed-off-by: Atsushi Nemoto Cc: Martin Schwidefsky Cc: "Eric W. Biederman" Cc: Thomas Gleixner Cc: Ingo Molnar Cc: john stultz Cc: Andi Kleen Cc: Paul Mackerras Cc: Benjamin Herrenschmidt Cc: Richard Henderson Cc: Ivan Kokshaysky Acked-by: Russell King Cc: Ian Molton Cc: Mikael Starvik Acked-by: David Howells Cc: Yoshinori Sato Cc: Hirokazu Takata Acked-by: Ralf Baechle Cc: Kyle McMartin Cc: Heiko Carstens Cc: Martin Schwidefsky Cc: Paul Mundt Cc: Kazumoto Kojima Cc: Richard Curnow Cc: William Lee Irwin III Cc: "David S. Miller" Cc: Jeff Dike Cc: Paolo 'Blaisorblade' Giarrusso Cc: Miles Bader Cc: Chris Zankel Acked-by: "Luck, Tony" Cc: Geert Uytterhoeven Cc: Roman Zippel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index ed2af8671589..503dea61ff99 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1206,7 +1206,7 @@ extern void switch_uid(struct user_struct *); #include -extern void do_timer(struct pt_regs *); +extern void do_timer(unsigned long ticks); extern int FASTCALL(wake_up_state(struct task_struct * tsk, unsigned int state)); extern int FASTCALL(wake_up_process(struct task_struct * tsk)); -- cgit v1.2.3 From 5785c95baede8459d70c4aa0f7becb6e8b5fde4b Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Fri, 29 Sep 2006 02:00:43 -0700 Subject: [PATCH] tty: make termios_sem a mutex [akpm@osdl.org: fix] Cc: Alan Cox Cc: Arjan van de Ven Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/tty.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index d1dec3d0c814..ea4c2605f8da 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -174,7 +174,7 @@ struct tty_struct { struct tty_driver *driver; int index; struct tty_ldisc ldisc; - struct semaphore termios_sem; + struct mutex termios_mutex; struct termios *termios, *termios_locked; char name[64]; int pgrp; -- cgit v1.2.3 From 416bc51292f977b43b010c6dd937522b90062390 Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Fri, 29 Sep 2006 02:00:45 -0700 Subject: [PATCH] Use decimal for PTRACE_ATTACH and PTRACE_DETACH. It is sure confusing that linux/ptrace.h has: #define PTRACE_SINGLESTEP 9 #define PTRACE_ATTACH 0x10 #define PTRACE_DETACH 0x11 #define PTRACE_SYSCALL 24 All the low-numbered constants are in decimal, but the last two in hex. It sure makes it likely that someone will look at this and think that 9, 10, 11 are used, and that 16 and 17 are not used. How about we use the same notation for all the numbers [0,24] in the same short list? Signed-off-by: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ptrace.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 8b2749a259dc..eeb1976ef7bf 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -16,8 +16,8 @@ #define PTRACE_KILL 8 #define PTRACE_SINGLESTEP 9 -#define PTRACE_ATTACH 0x10 -#define PTRACE_DETACH 0x11 +#define PTRACE_ATTACH 16 +#define PTRACE_DETACH 17 #define PTRACE_SYSCALL 24 -- cgit v1.2.3 From 57a6f51c4281aa3119975473c70dce0480d322bd Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 29 Sep 2006 02:00:49 -0700 Subject: [PATCH] introduce is_rt_policy() helper Imho, makes the code a bit easier to read. Signed-off-by: Oleg Nesterov Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Steven Rostedt Cc: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 503dea61ff99..fbc69cc3923d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -504,8 +504,8 @@ struct signal_struct { #define rt_prio(prio) unlikely((prio) < MAX_RT_PRIO) #define rt_task(p) rt_prio((p)->prio) #define batch_task(p) (unlikely((p)->policy == SCHED_BATCH)) -#define has_rt_policy(p) \ - unlikely((p)->policy != SCHED_NORMAL && (p)->policy != SCHED_BATCH) +#define is_rt_policy(p) ((p) != SCHED_NORMAL && (p) != SCHED_BATCH) +#define has_rt_policy(p) unlikely(is_rt_policy((p)->policy)) /* * Some day this will be a full-fledged user tracking system.. -- cgit v1.2.3 From 9f50b93f066f8dc339de9b0eb78a22a75e6c8f8f Mon Sep 17 00:00:00 2001 From: Josh Triplett Date: Fri, 29 Sep 2006 02:00:59 -0700 Subject: [PATCH] Make spinlock/rwlock annotations more accurate by using parameters, not types The lock annotations used on spinlocks and rwlocks currently use __{acquires,releases}(spinlock_t) and __{acquires,releases}(rwlock_t), respectively. This loses the information of which lock actually got acquired or released, and assumes a different type for the parameter of __acquires and __releases than the rest of the kernel. While the current implementations of __acquires and __releases throw away their argument, this will not always remain the case. Change this to use the lock parameter instead, to preserve this information and increase consistency in usage of __acquires and __releases. Signed-off-by: Josh Triplett Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/spinlock_api_smp.h | 50 ++++++++++++++++++++-------------------- 1 file changed, 25 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/include/linux/spinlock_api_smp.h b/include/linux/spinlock_api_smp.h index b2c4f8299464..8828b8155e9c 100644 --- a/include/linux/spinlock_api_smp.h +++ b/include/linux/spinlock_api_smp.h @@ -19,41 +19,41 @@ int in_lock_functions(unsigned long addr); #define assert_spin_locked(x) BUG_ON(!spin_is_locked(x)) -void __lockfunc _spin_lock(spinlock_t *lock) __acquires(spinlock_t); +void __lockfunc _spin_lock(spinlock_t *lock) __acquires(lock); void __lockfunc _spin_lock_nested(spinlock_t *lock, int subclass) - __acquires(spinlock_t); -void __lockfunc _read_lock(rwlock_t *lock) __acquires(rwlock_t); -void __lockfunc _write_lock(rwlock_t *lock) __acquires(rwlock_t); -void __lockfunc _spin_lock_bh(spinlock_t *lock) __acquires(spinlock_t); -void __lockfunc _read_lock_bh(rwlock_t *lock) __acquires(rwlock_t); -void __lockfunc _write_lock_bh(rwlock_t *lock) __acquires(rwlock_t); -void __lockfunc _spin_lock_irq(spinlock_t *lock) __acquires(spinlock_t); -void __lockfunc _read_lock_irq(rwlock_t *lock) __acquires(rwlock_t); -void __lockfunc _write_lock_irq(rwlock_t *lock) __acquires(rwlock_t); + __acquires(lock); +void __lockfunc _read_lock(rwlock_t *lock) __acquires(lock); +void __lockfunc _write_lock(rwlock_t *lock) __acquires(lock); +void __lockfunc _spin_lock_bh(spinlock_t *lock) __acquires(lock); +void __lockfunc _read_lock_bh(rwlock_t *lock) __acquires(lock); +void __lockfunc _write_lock_bh(rwlock_t *lock) __acquires(lock); +void __lockfunc _spin_lock_irq(spinlock_t *lock) __acquires(lock); +void __lockfunc _read_lock_irq(rwlock_t *lock) __acquires(lock); +void __lockfunc _write_lock_irq(rwlock_t *lock) __acquires(lock); unsigned long __lockfunc _spin_lock_irqsave(spinlock_t *lock) - __acquires(spinlock_t); + __acquires(lock); unsigned long __lockfunc _read_lock_irqsave(rwlock_t *lock) - __acquires(rwlock_t); + __acquires(lock); unsigned long __lockfunc _write_lock_irqsave(rwlock_t *lock) - __acquires(rwlock_t); + __acquires(lock); int __lockfunc _spin_trylock(spinlock_t *lock); int __lockfunc _read_trylock(rwlock_t *lock); int __lockfunc _write_trylock(rwlock_t *lock); int __lockfunc _spin_trylock_bh(spinlock_t *lock); -void __lockfunc _spin_unlock(spinlock_t *lock) __releases(spinlock_t); -void __lockfunc _read_unlock(rwlock_t *lock) __releases(rwlock_t); -void __lockfunc _write_unlock(rwlock_t *lock) __releases(rwlock_t); -void __lockfunc _spin_unlock_bh(spinlock_t *lock) __releases(spinlock_t); -void __lockfunc _read_unlock_bh(rwlock_t *lock) __releases(rwlock_t); -void __lockfunc _write_unlock_bh(rwlock_t *lock) __releases(rwlock_t); -void __lockfunc _spin_unlock_irq(spinlock_t *lock) __releases(spinlock_t); -void __lockfunc _read_unlock_irq(rwlock_t *lock) __releases(rwlock_t); -void __lockfunc _write_unlock_irq(rwlock_t *lock) __releases(rwlock_t); +void __lockfunc _spin_unlock(spinlock_t *lock) __releases(lock); +void __lockfunc _read_unlock(rwlock_t *lock) __releases(lock); +void __lockfunc _write_unlock(rwlock_t *lock) __releases(lock); +void __lockfunc _spin_unlock_bh(spinlock_t *lock) __releases(lock); +void __lockfunc _read_unlock_bh(rwlock_t *lock) __releases(lock); +void __lockfunc _write_unlock_bh(rwlock_t *lock) __releases(lock); +void __lockfunc _spin_unlock_irq(spinlock_t *lock) __releases(lock); +void __lockfunc _read_unlock_irq(rwlock_t *lock) __releases(lock); +void __lockfunc _write_unlock_irq(rwlock_t *lock) __releases(lock); void __lockfunc _spin_unlock_irqrestore(spinlock_t *lock, unsigned long flags) - __releases(spinlock_t); + __releases(lock); void __lockfunc _read_unlock_irqrestore(rwlock_t *lock, unsigned long flags) - __releases(rwlock_t); + __releases(lock); void __lockfunc _write_unlock_irqrestore(rwlock_t *lock, unsigned long flags) - __releases(rwlock_t); + __releases(lock); #endif /* __LINUX_SPINLOCK_API_SMP_H */ -- cgit v1.2.3 From 303912e2a32aa73785b4c4dee15466d944a38a46 Mon Sep 17 00:00:00 2001 From: Josh Triplett Date: Fri, 29 Sep 2006 02:01:00 -0700 Subject: [PATCH] Replace _spin_trylock with spin_trylock in the IRQ variants to use __cond_lock spin_trylock_irq and spin_trylock_irqsave use _spin_trylock, which does not use the __cond_lock wrapper annotation and thus does not affect the lock context; change them to use spin_trylock instead, which does use __cond_lock. Signed-off-by: Josh Triplett Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/spinlock.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index 31473db92d3b..456e74f0e129 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -241,14 +241,14 @@ do { \ #define spin_trylock_irq(lock) \ ({ \ local_irq_disable(); \ - _spin_trylock(lock) ? \ + spin_trylock(lock) ? \ 1 : ({ local_irq_enable(); 0; }); \ }) #define spin_trylock_irqsave(lock, flags) \ ({ \ local_irq_save(flags); \ - _spin_trylock(lock) ? \ + spin_trylock(lock) ? \ 1 : ({ local_irq_restore(flags); 0; }); \ }) -- cgit v1.2.3 From dcc8e559ee5ae03fa6bdb8611d76d86d0083e793 Mon Sep 17 00:00:00 2001 From: Josh Triplett Date: Fri, 29 Sep 2006 02:01:03 -0700 Subject: [PATCH] Pass a lock expression to __cond_lock, like __acquire and __release Currently, __acquire and __release take a lock expression, but __cond_lock takes only a condition, not the lock acquired if the expression evaluates to true. Change __cond_lock to accept a lock expression, and change all the callers to pass in a lock expression. Signed-off-by: Josh Triplett Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compiler.h | 4 ++-- include/linux/spinlock.h | 10 +++++----- 2 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 060b96112ec6..0780de440220 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -14,7 +14,7 @@ # define __releases(x) __attribute__((context(1,0))) # define __acquire(x) __context__(1) # define __release(x) __context__(-1) -# define __cond_lock(x) ((x) ? ({ __context__(1); 1; }) : 0) +# define __cond_lock(x,c) ((c) ? ({ __acquire(x); 1; }) : 0) extern void __chk_user_ptr(void __user *); extern void __chk_io_ptr(void __iomem *); #else @@ -31,7 +31,7 @@ extern void __chk_io_ptr(void __iomem *); # define __releases(x) # define __acquire(x) (void)0 # define __release(x) (void)0 -# define __cond_lock(x) (x) +# define __cond_lock(x,c) (c) #endif #ifdef __KERNEL__ diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index 456e74f0e129..b800d2d68b32 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -167,9 +167,9 @@ do { \ * regardless of whether CONFIG_SMP or CONFIG_PREEMPT are set. The various * methods are defined as nops in the case they are not required. */ -#define spin_trylock(lock) __cond_lock(_spin_trylock(lock)) -#define read_trylock(lock) __cond_lock(_read_trylock(lock)) -#define write_trylock(lock) __cond_lock(_write_trylock(lock)) +#define spin_trylock(lock) __cond_lock(lock, _spin_trylock(lock)) +#define read_trylock(lock) __cond_lock(lock, _read_trylock(lock)) +#define write_trylock(lock) __cond_lock(lock, _write_trylock(lock)) #define spin_lock(lock) _spin_lock(lock) @@ -236,7 +236,7 @@ do { \ _write_unlock_irqrestore(lock, flags) #define write_unlock_bh(lock) _write_unlock_bh(lock) -#define spin_trylock_bh(lock) __cond_lock(_spin_trylock_bh(lock)) +#define spin_trylock_bh(lock) __cond_lock(lock, _spin_trylock_bh(lock)) #define spin_trylock_irq(lock) \ ({ \ @@ -264,7 +264,7 @@ do { \ */ extern int _atomic_dec_and_lock(atomic_t *atomic, spinlock_t *lock); #define atomic_dec_and_lock(atomic, lock) \ - __cond_lock(_atomic_dec_and_lock(atomic, lock)) + __cond_lock(lock, _atomic_dec_and_lock(atomic, lock)) /** * spin_can_lock - would spin_trylock() succeed? -- cgit v1.2.3 From 368bdb3d616fa352971f45b423ae6344715e620b Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Fri, 29 Sep 2006 02:01:05 -0700 Subject: [PATCH] cramfs: make cramfs_uncompress_exit() return void It always returns 0, so relying on it is useless. The only caller isn't checking return value. In general, un-, de-, -free functions should return void. Signed-off-by: Alexey Dobriyan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cramfs_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cramfs_fs.h b/include/linux/cramfs_fs.h index a41f38428c37..1dba681e428d 100644 --- a/include/linux/cramfs_fs.h +++ b/include/linux/cramfs_fs.h @@ -87,6 +87,6 @@ struct cramfs_super { /* Uncompression interfaces to the underlying zlib */ int cramfs_uncompress_block(void *dst, int dstlen, void *src, int srclen); int cramfs_uncompress_init(void); -int cramfs_uncompress_exit(void); +void cramfs_uncompress_exit(void); #endif -- cgit v1.2.3 From e8106b941ceab68cc5ff713df7b1276484554584 Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Fri, 29 Sep 2006 02:01:08 -0700 Subject: [PATCH] lockdep: core, add enable/disable_irq_irqsave/irqrestore() APIs Introduce the disable_irq_nosync_lockdep_irqsave() and enable_irq_lockdep_irqrestore() APIs. These are needed for NE2000; basically NE2000 calls disable_irq and enable_irq as locking against the IRQ handler, but both in cases where interrupts are on and off. This means that lockdep needs to track the old state of the virtual irq flags on disable_irq, and restore these at enable_irq time. Signed-off-by: Arjan van de Ven Signed-off-by: Ingo Molnar Cc: Jeff Garzik Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/interrupt.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index d5afee95fd43..1f97e3d92639 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -123,6 +123,14 @@ static inline void disable_irq_nosync_lockdep(unsigned int irq) #endif } +static inline void disable_irq_nosync_lockdep_irqsave(unsigned int irq, unsigned long *flags) +{ + disable_irq_nosync(irq); +#ifdef CONFIG_LOCKDEP + local_irq_save(*flags); +#endif +} + static inline void disable_irq_lockdep(unsigned int irq) { disable_irq(irq); @@ -139,6 +147,14 @@ static inline void enable_irq_lockdep(unsigned int irq) enable_irq(irq); } +static inline void enable_irq_lockdep_irqrestore(unsigned int irq, unsigned long *flags) +{ +#ifdef CONFIG_LOCKDEP + local_irq_restore(*flags); +#endif + enable_irq(irq); +} + /* IRQ wakeup (PM) control: */ extern int set_irq_wake(unsigned int irq, unsigned int on); -- cgit v1.2.3 From 55a101f8f71a3d3dbda7b5c77083ffe47552f831 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 29 Sep 2006 02:01:10 -0700 Subject: [PATCH] kill PF_DEAD flag After the previous change (->flags & PF_DEAD) <=> (->state == EXIT_DEAD), we don't need PF_DEAD any longer. Signed-off-by: Oleg Nesterov Cc: Ingo Molnar 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 fbc69cc3923d..9763de334f09 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1061,7 +1061,6 @@ static inline void put_task_struct(struct task_struct *t) /* Not implemented yet, only for 486*/ #define PF_STARTING 0x00000002 /* being created */ #define PF_EXITING 0x00000004 /* getting shut down */ -#define PF_DEAD 0x00000008 /* Dead */ #define PF_FORKNOEXEC 0x00000040 /* forked but didn't exec */ #define PF_SUPERPRIV 0x00000100 /* used super-user privileges */ #define PF_DUMPCORE 0x00000200 /* dumped core */ -- cgit v1.2.3 From c394cc9fbb367f87faa2228ec2eabacd2d4701c6 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 29 Sep 2006 02:01:11 -0700 Subject: [PATCH] introduce TASK_DEAD state I am not sure about this patch, I am asking Ingo to take a decision. task_struct->state == EXIT_DEAD is a very special case, to avoid a confusion it makes sense to introduce a new state, TASK_DEAD, while EXIT_DEAD should live only in ->exit_state as documented in sched.h. Note that this state is not visible to user-space, get_task_state() masks off unsuitable states. Signed-off-by: Oleg Nesterov Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 9763de334f09..a06fc89cf6e5 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -148,6 +148,7 @@ extern unsigned long weighted_cpuload(const int cpu); #define EXIT_DEAD 32 /* in tsk->state again */ #define TASK_NONINTERACTIVE 64 +#define TASK_DEAD 128 #define __set_task_state(tsk, state_value) \ do { (tsk)->state = (state_value); } while (0) -- cgit v1.2.3 From 38837fc75acb7fa9b0e111b0241fe4fe76c5d4b3 Mon Sep 17 00:00:00 2001 From: Paul Jackson Date: Fri, 29 Sep 2006 02:01:16 -0700 Subject: [PATCH] cpuset: top_cpuset tracks hotplug changes to node_online_map Change the list of memory nodes allowed to tasks in the top (root) nodeset to dynamically track what cpus are online, using a call to a cpuset hook from the memory hotplug code. Make this top cpus file read-only. On systems that have cpusets configured in their kernel, but that aren't actively using cpusets (for some distros, this covers the majority of systems) all tasks end up in the top cpuset. If that system does support memory hotplug, then these tasks cannot make use of memory nodes that are added after system boot, because the memory nodes are not allowed in the top cpuset. This is a surprising regression over earlier kernels that didn't have cpusets enabled. One key motivation for this change is to remain consistent with the behaviour for the top_cpuset's 'cpus', which is also read-only, and which automatically tracks the cpu_online_map. This change also has the minor benefit that it fixes a long standing, little noticed, minor bug in cpusets. The cpuset performance tweak to short circuit the cpuset_zone_allowed() check on systems with just a single cpuset (see 'number_of_cpusets', in linux/cpuset.h) meant that simply changing the 'mems' of the top_cpuset had no affect, even though the change (the write system call) appeared to succeed. With the following change, that write to the 'mems' file fails -EACCES, and the 'mems' file stubbornly refuses to be changed via user space writes. Thus no one should be mislead into thinking they've changed the top_cpusets's 'mems' when in affect they haven't. In order to keep the behaviour of cpusets consistent between systems actively making use of them and systems not using them, this patch changes the behaviour of the 'mems' file in the top (root) cpuset, making it read only, and making it automatically track the value of node_online_map. Thus tasks in the top cpuset will have automatic use of hot plugged memory nodes allowed by their cpuset. [akpm@osdl.org: build fix] [bunk@stusta.de: build fix] Signed-off-by: Paul Jackson Signed-off-by: Adrian Bunk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cpuset.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index 9354722a9217..4d8adf663681 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -63,6 +63,8 @@ static inline int cpuset_do_slab_mem_spread(void) return current->flags & PF_SPREAD_SLAB; } +extern void cpuset_track_online_nodes(void); + #else /* !CONFIG_CPUSETS */ static inline int cpuset_init_early(void) { return 0; } @@ -126,6 +128,8 @@ static inline int cpuset_do_slab_mem_spread(void) return 0; } +static inline void cpuset_track_online_nodes(void) {} + #endif /* !CONFIG_CPUSETS */ #endif /* _LINUX_CPUSET_H */ -- cgit v1.2.3 From 2d1d43f6a43b703587e759145f69467e7c6553a7 Mon Sep 17 00:00:00 2001 From: Chandra Seetharaman Date: Fri, 29 Sep 2006 02:01:25 -0700 Subject: [PATCH] call mm/page-writeback.c:set_ratelimit() when new pages are hot-added ratelimit_pages in page-writeback.c is recalculated (in set_ratelimit()) every time a CPU is hot-added/removed. But this value is not recalculated when new pages are hot-added. This patch fixes that problem by calling set_ratelimit() when new pages are hot-added. [akpm@osdl.org: cleanups] Signed-off-by: Chandra Seetharaman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/writeback.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 56a23a0e7f2e..9d4074ecd0cd 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -117,6 +117,7 @@ int sync_page_range(struct inode *inode, struct address_space *mapping, int sync_page_range_nolock(struct inode *inode, struct address_space *mapping, loff_t pos, loff_t count); void set_page_dirty_balance(struct page *page); +void writeback_set_ratelimit(void); /* pdflush.c */ extern int nr_pdflush_threads; /* Global so it can be exported to sysctl -- cgit v1.2.3 From 04b1db9fd7eea63c9663072feece616ea41b0a79 Mon Sep 17 00:00:00 2001 From: "Ian S. Nelson" Date: Fri, 29 Sep 2006 02:01:31 -0700 Subject: [PATCH] /sys/modules: allow full length section names I've been using systemtap for some debugging and I noticed that it can't probe a lot of modules. Turns out it's kind of silly, the sections section of /sys/module is limited to 32byte filenames and many of the actual sections are a a bit longer than that. [akpm@osdl.org: rewrite to use dymanic allocation] Cc: Rusty Russell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/module.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index d4486cc2e7fe..2c599175c583 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -232,17 +232,17 @@ enum module_state }; /* Similar stuff for section attributes. */ -#define MODULE_SECT_NAME_LEN 32 struct module_sect_attr { struct module_attribute mattr; - char name[MODULE_SECT_NAME_LEN]; + char *name; unsigned long address; }; struct module_sect_attrs { struct attribute_group grp; + int nsections; struct module_sect_attr attrs[0]; }; -- cgit v1.2.3 From f0c8bd164e1a0585d7e46896553136b4f488bd19 Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Fri, 29 Sep 2006 02:01:34 -0700 Subject: [PATCH] Generic infrastructure for acls The patches solve the following problem: We want to grant access to devices based on who is logged in from where, etc. This includes switching back and forth between multiple user sessions, etc. Using ACLs to define device access for logged-in users gives us all the flexibility we need in order to fully solve the problem. Device special files nowadays usually live on tmpfs, hence tmpfs ACLs. Different distros have come up with solutions that solve the problem to different degrees: SUSE uses a resource manager which tracks login sessions and sets ACLs on device inodes as appropriate. RedHat uses pam_console, which changes the primary file ownership to the logged-in user. Others use a set of groups that users must be in in order to be granted the appropriate accesses. The freedesktop.org project plans to implement a combination of a console-tracker and a HAL-device-list based solution to grant access to devices to users, and more distros will likely follow this approach. These patches have first been posted here on 2 February 2005, and again on 8 January 2006. We have been shipping them in SLES9 and SLES10 with no problems reported. The previous submission is archived here: http://lkml.org/lkml/2006/1/8/229 http://lkml.org/lkml/2006/1/8/230 http://lkml.org/lkml/2006/1/8/231 This patch: Add some infrastructure for access control lists on in-memory filesystems such as tmpfs. Signed-off-by: Andreas Gruenbacher Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/generic_acl.h | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) create mode 100644 include/linux/generic_acl.h (limited to 'include/linux') diff --git a/include/linux/generic_acl.h b/include/linux/generic_acl.h new file mode 100644 index 000000000000..80764f40be75 --- /dev/null +++ b/include/linux/generic_acl.h @@ -0,0 +1,36 @@ +/* + * fs/generic_acl.c + * + * (C) 2005 Andreas Gruenbacher + * + * This file is released under the GPL. + */ + +#ifndef GENERIC_ACL_H +#define GENERIC_ACL_H + +#include +#include + +/** + * struct generic_acl_operations - filesystem operations + * + * Filesystems must make these operations available to the generic + * operations. + */ +struct generic_acl_operations { + struct posix_acl *(*getacl)(struct inode *, int); + void (*setacl)(struct inode *, int, struct posix_acl *); +}; + +size_t generic_acl_list(struct inode *, struct generic_acl_operations *, int, + char *, size_t); +int generic_acl_get(struct inode *, struct generic_acl_operations *, int, + void *, size_t); +int generic_acl_set(struct inode *, struct generic_acl_operations *, int, + const void *, size_t); +int generic_acl_init(struct inode *, struct inode *, + struct generic_acl_operations *); +int generic_acl_chmod(struct inode *, struct generic_acl_operations *); + +#endif -- cgit v1.2.3 From 39f0247d3823e4e0bf8f6838a10362864b1e1053 Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Fri, 29 Sep 2006 02:01:35 -0700 Subject: [PATCH] Access Control Lists for tmpfs Add access control lists for tmpfs. Signed-off-by: Andreas Gruenbacher Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/shmem_fs.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include/linux') diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index c057f0b32318..f3c51899117f 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -19,6 +19,10 @@ struct shmem_inode_info { swp_entry_t i_direct[SHMEM_NR_DIRECT]; /* first blocks */ struct list_head swaplist; /* chain of maybes on swap */ struct inode vfs_inode; +#ifdef CONFIG_TMPFS_POSIX_ACL + struct posix_acl *i_acl; + struct posix_acl *i_default_acl; +#endif }; struct shmem_sb_info { @@ -36,4 +40,24 @@ static inline struct shmem_inode_info *SHMEM_I(struct inode *inode) return container_of(inode, struct shmem_inode_info, vfs_inode); } +#ifdef CONFIG_TMPFS_POSIX_ACL +int shmem_permission(struct inode *, int, struct nameidata *); +int shmem_acl_init(struct inode *, struct inode *); +void shmem_acl_destroy_inode(struct inode *); + +extern struct xattr_handler shmem_xattr_acl_access_handler; +extern struct xattr_handler shmem_xattr_acl_default_handler; + +extern struct generic_acl_operations shmem_acl_ops; + +#else +static inline int shmem_acl_init(struct inode *inode, struct inode *dir) +{ + return 0; +} +static inline void shmem_acl_destroy_inode(struct inode *inode) +{ +} +#endif /* CONFIG_TMPFS_POSIX_ACL */ + #endif -- cgit v1.2.3 From 34596dc9e59d7bece16fe5aba08116b49465da26 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Sat, 30 Sep 2006 01:47:55 +0200 Subject: [PATCH] Define vsyscall cache as blob to make clearer that user space shouldn't use it Signed-off-by: Andi Kleen --- include/linux/getcpu.h | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/getcpu.h b/include/linux/getcpu.h index 031ed3780e45..c7372d7a97be 100644 --- a/include/linux/getcpu.h +++ b/include/linux/getcpu.h @@ -1,16 +1,18 @@ #ifndef _LINUX_GETCPU_H #define _LINUX_GETCPU_H 1 -/* Cache for getcpu() to speed it up. Results might be upto a jiffie +/* Cache for getcpu() to speed it up. Results might be a short time out of date, but will be faster. + User programs should not refer to the contents of this structure. - It is only a cache for vgetcpu(). It might change in future kernels. + I repeat they should not refer to it. If they do they will break + in future kernels. + + It is only a private cache for vgetcpu(). It will change in future kernels. The user program must store this information per thread (__thread) If you want 100% accurate information pass NULL instead. */ struct getcpu_cache { - unsigned long t0; - unsigned long t1; - unsigned long res[4]; + unsigned long blob[128 / sizeof(long)]; }; #endif -- cgit v1.2.3 From 95d4e6be25a68cd9fbe8c0d356b585504d8db1c7 Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Fri, 29 Sep 2006 17:05:05 -0700 Subject: [NetLabel]: audit fixups due to delayed feedback Fix some issues Steve Grubb had with the way NetLabel was using the audit subsystem. This should make NetLabel more consistent with other kernel generated audit messages specifying configuration changes. Signed-off-by: Paul Moore Acked-by: Steve Grubb Signed-off-by: David S. Miller --- include/linux/audit.h | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index 42719d07612a..c3aa09751814 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -95,12 +95,11 @@ #define AUDIT_MAC_POLICY_LOAD 1403 /* Policy file load */ #define AUDIT_MAC_STATUS 1404 /* Changed enforcing,permissive,off */ #define AUDIT_MAC_CONFIG_CHANGE 1405 /* Changes to booleans */ -#define AUDIT_MAC_UNLBL_ACCEPT 1406 /* NetLabel: allow unlabeled traffic */ -#define AUDIT_MAC_UNLBL_DENY 1407 /* NetLabel: deny unlabeled traffic */ -#define AUDIT_MAC_CIPSOV4_ADD 1408 /* NetLabel: add CIPSOv4 DOI entry */ -#define AUDIT_MAC_CIPSOV4_DEL 1409 /* NetLabel: del CIPSOv4 DOI entry */ -#define AUDIT_MAC_MAP_ADD 1410 /* NetLabel: add LSM domain mapping */ -#define AUDIT_MAC_MAP_DEL 1411 /* NetLabel: del LSM domain mapping */ +#define AUDIT_MAC_UNLBL_ALLOW 1406 /* NetLabel: allow unlabeled traffic */ +#define AUDIT_MAC_CIPSOV4_ADD 1407 /* NetLabel: add CIPSOv4 DOI entry */ +#define AUDIT_MAC_CIPSOV4_DEL 1408 /* NetLabel: del CIPSOv4 DOI entry */ +#define AUDIT_MAC_MAP_ADD 1409 /* NetLabel: add LSM domain mapping */ +#define AUDIT_MAC_MAP_DEL 1410 /* NetLabel: del LSM domain mapping */ #define AUDIT_FIRST_KERN_ANOM_MSG 1700 #define AUDIT_LAST_KERN_ANOM_MSG 1799 -- cgit v1.2.3 From f9317a40c4e09e20ef01601fc9f5de9e6acb5b96 Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Fri, 29 Sep 2006 17:06:23 -0700 Subject: [BNX2]: Disable MSI on 5706 if AMD 8132 bridge is present. MSI is defined to be 32-bit write. The 5706 does 64-bit MSI writes with byte enables disabled on the unused 32-bit word. This is legal but causes problems on the AMD 8132 which will eventually stop responding after a while. Without this patch, the MSI test done by the driver during open will pass, but MSI will eventually stop working after a few MSIs are written by the device. AMD believes this incompatibility is unique to the 5706, and prefers to locally disable MSI rather than globally disabling it using pci_msi_quirk. Update version to 1.4.45. 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 b7e85ff045ea..c9ffbc3843d5 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -507,6 +507,7 @@ #define PCI_DEVICE_ID_AMD_8151_0 0x7454 #define PCI_DEVICE_ID_AMD_8131_BRIDGE 0x7450 #define PCI_DEVICE_ID_AMD_8131_APIC 0x7451 +#define PCI_DEVICE_ID_AMD_8132_BRIDGE 0x7458 #define PCI_DEVICE_ID_AMD_CS5536_ISA 0x2090 #define PCI_DEVICE_ID_AMD_CS5536_FLASH 0x2091 #define PCI_DEVICE_ID_AMD_CS5536_AUDIO 0x2093 -- cgit v1.2.3 From 1c9d3e72a7164c590437f2ab6c2c4f6da91f1703 Mon Sep 17 00:00:00 2001 From: Chas Williams Date: Fri, 29 Sep 2006 17:13:24 -0700 Subject: [ATM]: [lec] header indent, comment and whitespace cleanup Signed-off-by: Chas Williams Signed-off-by: David S. Miller --- include/linux/atmlec.h | 119 ++++++++++++++++++++++++++----------------------- 1 file changed, 64 insertions(+), 55 deletions(-) (limited to 'include/linux') diff --git a/include/linux/atmlec.h b/include/linux/atmlec.h index f267f2442766..6f5a1bab8f50 100644 --- a/include/linux/atmlec.h +++ b/include/linux/atmlec.h @@ -1,9 +1,7 @@ /* - * - * ATM Lan Emulation Daemon vs. driver interface - * - * mkiiskila@yahoo.com + * ATM Lan Emulation Daemon driver interface * + * Marko Kiiskila */ #ifndef _ATMLEC_H_ @@ -13,76 +11,87 @@ #include #include #include + /* ATM lec daemon control socket */ -#define ATMLEC_CTRL _IO('a',ATMIOC_LANE) -#define ATMLEC_DATA _IO('a',ATMIOC_LANE+1) -#define ATMLEC_MCAST _IO('a',ATMIOC_LANE+2) +#define ATMLEC_CTRL _IO('a', ATMIOC_LANE) +#define ATMLEC_DATA _IO('a', ATMIOC_LANE+1) +#define ATMLEC_MCAST _IO('a', ATMIOC_LANE+2) /* Maximum number of LEC interfaces (tweakable) */ #define MAX_LEC_ITF 48 -/* From the total of MAX_LEC_ITF, last NUM_TR_DEVS are reserved for Token Ring. +/* + * From the total of MAX_LEC_ITF, last NUM_TR_DEVS are reserved for Token Ring. * E.g. if MAX_LEC_ITF = 48 and NUM_TR_DEVS = 8, then lec0-lec39 are for * Ethernet ELANs and lec40-lec47 are for Token Ring ELANS. */ #define NUM_TR_DEVS 8 -typedef enum { - l_set_mac_addr, l_del_mac_addr, - l_svc_setup, - l_addr_delete, l_topology_change, - l_flush_complete, l_arp_update, - l_narp_req, /* LANE2 mandates the use of this */ - l_config, l_flush_tran_id, - l_set_lecid, l_arp_xmt, - l_rdesc_arp_xmt, - l_associate_req, - l_should_bridge /* should we bridge this MAC? */ +typedef enum { + l_set_mac_addr, + l_del_mac_addr, + l_svc_setup, + l_addr_delete, + l_topology_change, + l_flush_complete, + l_arp_update, + l_narp_req, /* LANE2 mandates the use of this */ + l_config, + l_flush_tran_id, + l_set_lecid, + l_arp_xmt, + l_rdesc_arp_xmt, + l_associate_req, + l_should_bridge /* should we bridge this MAC? */ } atmlec_msg_type; #define ATMLEC_MSG_TYPE_MAX l_should_bridge struct atmlec_config_msg { - unsigned int maximum_unknown_frame_count; - unsigned int max_unknown_frame_time; - unsigned short max_retry_count; - unsigned int aging_time; - unsigned int forward_delay_time; - unsigned int arp_response_time; - unsigned int flush_timeout; - unsigned int path_switching_delay; - unsigned int lane_version; /* LANE2: 1 for LANEv1, 2 for LANEv2 */ - int mtu; - int is_proxy; + unsigned int maximum_unknown_frame_count; + unsigned int max_unknown_frame_time; + unsigned short max_retry_count; + unsigned int aging_time; + unsigned int forward_delay_time; + unsigned int arp_response_time; + unsigned int flush_timeout; + unsigned int path_switching_delay; + unsigned int lane_version; /* LANE2: 1 for LANEv1, 2 for LANEv2 */ + int mtu; + int is_proxy; }; - + struct atmlec_msg { - atmlec_msg_type type; - int sizeoftlvs; /* LANE2: if != 0, tlvs follow */ - union { - struct { - unsigned char mac_addr[ETH_ALEN]; - unsigned char atm_addr[ATM_ESA_LEN]; - unsigned int flag;/* Topology_change flag, - remoteflag, permanent flag, - lecid, transaction id */ - unsigned int targetless_le_arp; /* LANE2 */ - unsigned int no_source_le_narp; /* LANE2 */ - } normal; - struct atmlec_config_msg config; - struct { - uint16_t lec_id; /* requestor lec_id */ - uint32_t tran_id; /* transaction id */ - unsigned char mac_addr[ETH_ALEN]; /* dst mac addr */ - unsigned char atm_addr[ATM_ESA_LEN]; /* reqestor ATM addr */ - } proxy; - /* For mapping LE_ARP requests to responses. Filled by */ - } content; /* zeppelin, returned by kernel. Used only when proxying */ + atmlec_msg_type type; + int sizeoftlvs; /* LANE2: if != 0, tlvs follow */ + union { + struct { + unsigned char mac_addr[ETH_ALEN]; + unsigned char atm_addr[ATM_ESA_LEN]; + unsigned int flag; /* + * Topology_change flag, + * remoteflag, permanent flag, + * lecid, transaction id + */ + unsigned int targetless_le_arp; /* LANE2 */ + unsigned int no_source_le_narp; /* LANE2 */ + } normal; + struct atmlec_config_msg config; + struct { + uint16_t lec_id; /* requestor lec_id */ + uint32_t tran_id; /* transaction id */ + unsigned char mac_addr[ETH_ALEN]; /* dst mac addr */ + unsigned char atm_addr[ATM_ESA_LEN]; /* reqestor ATM addr */ + } proxy; /* + * For mapping LE_ARP requests to responses. Filled by + * zeppelin, returned by kernel. Used only when proxying + */ + } content; } __ATM_API_ALIGN; struct atmlec_ioc { - int dev_num; - unsigned char atm_addr[ATM_ESA_LEN]; - unsigned char receive; /* 1= receive vcc, 0 = send vcc */ + int dev_num; + unsigned char atm_addr[ATM_ESA_LEN]; + unsigned char receive; /* 1= receive vcc, 0 = send vcc */ }; #endif /* _ATMLEC_H_ */ -- cgit v1.2.3 From e5c9e081e9c980fa785cd9002c25a251cf3f090e Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Sat, 30 Sep 2006 19:44:39 +0900 Subject: [PATCH] libata: cosmetic changes to constants Cosmetic changes to ATA_DFLAG_* constants for soon-to-follow NCQ-off patch. 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 df44b09fbae8..e54a5fd6a41e 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -142,8 +142,8 @@ enum { ATA_DFLAG_NCQ = (1 << 3), /* device supports NCQ */ ATA_DFLAG_CFG_MASK = (1 << 8) - 1, - ATA_DFLAG_PIO = (1 << 8), /* device currently in PIO mode */ - ATA_DFLAG_SUSPENDED = (1 << 9), /* device suspended */ + ATA_DFLAG_PIO = (1 << 8), /* device limited to PIO mode */ + ATA_DFLAG_SUSPENDED = (1 << 10), /* device suspended */ ATA_DFLAG_INIT_MASK = (1 << 16) - 1, ATA_DFLAG_DETACH = (1 << 16), -- cgit v1.2.3 From 360f654e7cda850034f3f6252a7a7cff3fa77356 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Sat, 30 Sep 2006 19:45:00 +0900 Subject: [PATCH] libata: turn off NCQ if queue depth is adjusted to 1 Turn off NCQ if queue depth is adjusted to 1. 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 e54a5fd6a41e..d1af1dbeaeb4 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -143,6 +143,7 @@ enum { ATA_DFLAG_CFG_MASK = (1 << 8) - 1, ATA_DFLAG_PIO = (1 << 8), /* device limited to PIO mode */ + ATA_DFLAG_NCQ_OFF = (1 << 9), /* devied limited to non-NCQ mode */ ATA_DFLAG_SUSPENDED = (1 << 10), /* device suspended */ ATA_DFLAG_INIT_MASK = (1 << 16) - 1, -- cgit v1.2.3 From 4aff5e2333c9a1609662f2091f55c3f6fffdad36 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 10 Aug 2006 08:44:47 +0200 Subject: [PATCH] Split struct request ->flags into two parts Right now ->flags is a bit of a mess: some are request types, and others are just modifiers. Clean this up by splitting it into ->cmd_type and ->cmd_flags. This allows introduction of generic Linux block message types, useful for sending generic Linux commands to block devices. Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 180 ++++++++++++++++++++++++------------------- include/linux/blktrace_api.h | 2 +- 2 files changed, 100 insertions(+), 82 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index cfde8b3ee919..b2a412cf468f 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -120,6 +120,86 @@ struct request_list { wait_queue_head_t wait[2]; }; +/* + * request command types + */ +enum rq_cmd_type_bits { + REQ_TYPE_FS = 1, /* fs request */ + REQ_TYPE_BLOCK_PC, /* scsi command */ + REQ_TYPE_SENSE, /* sense request */ + REQ_TYPE_PM_SUSPEND, /* suspend request */ + REQ_TYPE_PM_RESUME, /* resume request */ + REQ_TYPE_PM_SHUTDOWN, /* shutdown request */ + REQ_TYPE_FLUSH, /* flush request */ + REQ_TYPE_SPECIAL, /* driver defined type */ + REQ_TYPE_LINUX_BLOCK, /* generic block layer message */ + /* + * for ATA/ATAPI devices. this really doesn't belong here, ide should + * use REQ_TYPE_SPECIAL and use rq->cmd[0] with the range of driver + * private REQ_LB opcodes to differentiate what type of request this is + */ + REQ_TYPE_ATA_CMD, + REQ_TYPE_ATA_TASK, + REQ_TYPE_ATA_TASKFILE, +}; + +/* + * For request of type REQ_TYPE_LINUX_BLOCK, rq->cmd[0] is the opcode being + * sent down (similar to how REQ_TYPE_BLOCK_PC means that ->cmd[] holds a + * SCSI cdb. + * + * 0x00 -> 0x3f are driver private, to be used for whatever purpose they need, + * typically to differentiate REQ_TYPE_SPECIAL requests. + * + */ +enum { + /* + * just examples for now + */ + REQ_LB_OP_EJECT = 0x40, /* eject request */ + REQ_LB_OP_FLUSH = 0x41, /* flush device */ +}; + +/* + * request type modified bits. first three bits match BIO_RW* bits, important + */ +enum rq_flag_bits { + __REQ_RW, /* not set, read. set, write */ + __REQ_FAILFAST, /* no low level driver retries */ + __REQ_SORTED, /* elevator knows about this request */ + __REQ_SOFTBARRIER, /* may not be passed by ioscheduler */ + __REQ_HARDBARRIER, /* may not be passed by drive either */ + __REQ_FUA, /* forced unit access */ + __REQ_NOMERGE, /* don't touch this for merging */ + __REQ_STARTED, /* drive already may have started this one */ + __REQ_DONTPREP, /* don't call prep for this one */ + __REQ_QUEUED, /* uses queueing */ + __REQ_ELVPRIV, /* elevator private data attached */ + __REQ_FAILED, /* set if the request failed */ + __REQ_QUIET, /* don't worry about errors */ + __REQ_PREEMPT, /* set for "ide_preempt" requests */ + __REQ_ORDERED_COLOR, /* is before or after barrier */ + __REQ_RW_SYNC, /* request is sync (O_DIRECT) */ + __REQ_NR_BITS, /* stops here */ +}; + +#define REQ_RW (1 << __REQ_RW) +#define REQ_FAILFAST (1 << __REQ_FAILFAST) +#define REQ_SORTED (1 << __REQ_SORTED) +#define REQ_SOFTBARRIER (1 << __REQ_SOFTBARRIER) +#define REQ_HARDBARRIER (1 << __REQ_HARDBARRIER) +#define REQ_FUA (1 << __REQ_FUA) +#define REQ_NOMERGE (1 << __REQ_NOMERGE) +#define REQ_STARTED (1 << __REQ_STARTED) +#define REQ_DONTPREP (1 << __REQ_DONTPREP) +#define REQ_QUEUED (1 << __REQ_QUEUED) +#define REQ_ELVPRIV (1 << __REQ_ELVPRIV) +#define REQ_FAILED (1 << __REQ_FAILED) +#define REQ_QUIET (1 << __REQ_QUIET) +#define REQ_PREEMPT (1 << __REQ_PREEMPT) +#define REQ_ORDERED_COLOR (1 << __REQ_ORDERED_COLOR) +#define REQ_RW_SYNC (1 << __REQ_RW_SYNC) + #define BLK_MAX_CDB 16 /* @@ -129,7 +209,8 @@ struct request { struct list_head queuelist; struct list_head donelist; - unsigned long flags; /* see REQ_ bits below */ + unsigned int cmd_flags; + enum rq_cmd_type_bits cmd_type; /* Maintain bio traversal state for part by part I/O submission. * hard_* are block layer internals, no driver should touch them! @@ -202,73 +283,7 @@ struct request { }; /* - * first three bits match BIO_RW* bits, important - */ -enum rq_flag_bits { - __REQ_RW, /* not set, read. set, write */ - __REQ_FAILFAST, /* no low level driver retries */ - __REQ_SORTED, /* elevator knows about this request */ - __REQ_SOFTBARRIER, /* may not be passed by ioscheduler */ - __REQ_HARDBARRIER, /* may not be passed by drive either */ - __REQ_FUA, /* forced unit access */ - __REQ_CMD, /* is a regular fs rw request */ - __REQ_NOMERGE, /* don't touch this for merging */ - __REQ_STARTED, /* drive already may have started this one */ - __REQ_DONTPREP, /* don't call prep for this one */ - __REQ_QUEUED, /* uses queueing */ - __REQ_ELVPRIV, /* elevator private data attached */ - /* - * for ATA/ATAPI devices - */ - __REQ_PC, /* packet command (special) */ - __REQ_BLOCK_PC, /* queued down pc from block layer */ - __REQ_SENSE, /* sense retrival */ - - __REQ_FAILED, /* set if the request failed */ - __REQ_QUIET, /* don't worry about errors */ - __REQ_SPECIAL, /* driver suplied command */ - __REQ_DRIVE_CMD, - __REQ_DRIVE_TASK, - __REQ_DRIVE_TASKFILE, - __REQ_PREEMPT, /* set for "ide_preempt" requests */ - __REQ_PM_SUSPEND, /* suspend request */ - __REQ_PM_RESUME, /* resume request */ - __REQ_PM_SHUTDOWN, /* shutdown request */ - __REQ_ORDERED_COLOR, /* is before or after barrier */ - __REQ_RW_SYNC, /* request is sync (O_DIRECT) */ - __REQ_NR_BITS, /* stops here */ -}; - -#define REQ_RW (1 << __REQ_RW) -#define REQ_FAILFAST (1 << __REQ_FAILFAST) -#define REQ_SORTED (1 << __REQ_SORTED) -#define REQ_SOFTBARRIER (1 << __REQ_SOFTBARRIER) -#define REQ_HARDBARRIER (1 << __REQ_HARDBARRIER) -#define REQ_FUA (1 << __REQ_FUA) -#define REQ_CMD (1 << __REQ_CMD) -#define REQ_NOMERGE (1 << __REQ_NOMERGE) -#define REQ_STARTED (1 << __REQ_STARTED) -#define REQ_DONTPREP (1 << __REQ_DONTPREP) -#define REQ_QUEUED (1 << __REQ_QUEUED) -#define REQ_ELVPRIV (1 << __REQ_ELVPRIV) -#define REQ_PC (1 << __REQ_PC) -#define REQ_BLOCK_PC (1 << __REQ_BLOCK_PC) -#define REQ_SENSE (1 << __REQ_SENSE) -#define REQ_FAILED (1 << __REQ_FAILED) -#define REQ_QUIET (1 << __REQ_QUIET) -#define REQ_SPECIAL (1 << __REQ_SPECIAL) -#define REQ_DRIVE_CMD (1 << __REQ_DRIVE_CMD) -#define REQ_DRIVE_TASK (1 << __REQ_DRIVE_TASK) -#define REQ_DRIVE_TASKFILE (1 << __REQ_DRIVE_TASKFILE) -#define REQ_PREEMPT (1 << __REQ_PREEMPT) -#define REQ_PM_SUSPEND (1 << __REQ_PM_SUSPEND) -#define REQ_PM_RESUME (1 << __REQ_PM_RESUME) -#define REQ_PM_SHUTDOWN (1 << __REQ_PM_SHUTDOWN) -#define REQ_ORDERED_COLOR (1 << __REQ_ORDERED_COLOR) -#define REQ_RW_SYNC (1 << __REQ_RW_SYNC) - -/* - * State information carried for REQ_PM_SUSPEND and REQ_PM_RESUME + * State information carried for REQ_TYPE_PM_SUSPEND and REQ_TYPE_PM_RESUME * requests. Some step values could eventually be made generic. */ struct request_pm_state @@ -490,25 +505,28 @@ enum { #define blk_queue_stopped(q) test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags) #define blk_queue_flushing(q) ((q)->ordseq) -#define blk_fs_request(rq) ((rq)->flags & REQ_CMD) -#define blk_pc_request(rq) ((rq)->flags & REQ_BLOCK_PC) -#define blk_noretry_request(rq) ((rq)->flags & REQ_FAILFAST) -#define blk_rq_started(rq) ((rq)->flags & REQ_STARTED) +#define blk_fs_request(rq) ((rq)->cmd_type == REQ_TYPE_FS) +#define blk_pc_request(rq) ((rq)->cmd_type == REQ_TYPE_BLOCK_PC) +#define blk_special_request(rq) ((rq)->cmd_type == REQ_TYPE_SPECIAL) +#define blk_sense_request(rq) ((rq)->cmd_type == REQ_TYPE_SENSE) + +#define blk_noretry_request(rq) ((rq)->cmd_flags & REQ_FAILFAST) +#define blk_rq_started(rq) ((rq)->cmd_flags & REQ_STARTED) #define blk_account_rq(rq) (blk_rq_started(rq) && blk_fs_request(rq)) -#define blk_pm_suspend_request(rq) ((rq)->flags & REQ_PM_SUSPEND) -#define blk_pm_resume_request(rq) ((rq)->flags & REQ_PM_RESUME) +#define blk_pm_suspend_request(rq) ((rq)->cmd_type == REQ_TYPE_PM_SUSPEND) +#define blk_pm_resume_request(rq) ((rq)->cmd_type == REQ_TYPE_PM_RESUME) #define blk_pm_request(rq) \ - ((rq)->flags & (REQ_PM_SUSPEND | REQ_PM_RESUME)) + (blk_pm_suspend_request(rq) || blk_pm_resume_request(rq)) -#define blk_sorted_rq(rq) ((rq)->flags & REQ_SORTED) -#define blk_barrier_rq(rq) ((rq)->flags & REQ_HARDBARRIER) -#define blk_fua_rq(rq) ((rq)->flags & REQ_FUA) +#define blk_sorted_rq(rq) ((rq)->cmd_flags & REQ_SORTED) +#define blk_barrier_rq(rq) ((rq)->cmd_flags & REQ_HARDBARRIER) +#define blk_fua_rq(rq) ((rq)->cmd_flags & REQ_FUA) #define list_entry_rq(ptr) list_entry((ptr), struct request, queuelist) -#define rq_data_dir(rq) ((rq)->flags & 1) +#define rq_data_dir(rq) ((rq)->cmd_flags & 1) static inline int blk_queue_full(struct request_queue *q, int rw) { @@ -541,7 +559,7 @@ static inline void blk_clear_queue_full(struct request_queue *q, int rw) #define RQ_NOMERGE_FLAGS \ (REQ_NOMERGE | REQ_STARTED | REQ_HARDBARRIER | REQ_SOFTBARRIER) #define rq_mergeable(rq) \ - (!((rq)->flags & RQ_NOMERGE_FLAGS) && blk_fs_request((rq))) + (!((rq)->cmd_flags & RQ_NOMERGE_FLAGS) && blk_fs_request((rq))) /* * noop, requests are automagically marked as active/inactive by I/O @@ -737,7 +755,7 @@ extern void blk_put_queue(request_queue_t *); */ #define blk_queue_tag_depth(q) ((q)->queue_tags->busy) #define blk_queue_tag_queue(q) ((q)->queue_tags->busy < (q)->queue_tags->max_depth) -#define blk_rq_tagged(rq) ((rq)->flags & REQ_QUEUED) +#define blk_rq_tagged(rq) ((rq)->cmd_flags & REQ_QUEUED) extern int blk_queue_start_tag(request_queue_t *, struct request *); extern struct request *blk_queue_find_tag(request_queue_t *, int); extern void blk_queue_end_tag(request_queue_t *, struct request *); diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index 7520cc1ff9e2..ea48eb1b3fd3 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -148,7 +148,7 @@ static inline void blk_add_trace_rq(struct request_queue *q, struct request *rq, u32 what) { struct blk_trace *bt = q->blk_trace; - int rw = rq->flags & 0x03; + int rw = rq->cmd_flags & 0x03; if (likely(!bt)) return; -- cgit v1.2.3 From 9817064b68fef7e4580c6df1ea597e106b9ff88b Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 28 Jul 2006 09:23:08 +0200 Subject: [PATCH] elevator: move the backmerging logic into the elevator core Right now, every IO scheduler implements its own backmerging (except for noop, which does no merging). That results in duplicated code for essentially the same operation, which is never a good thing. This patch moves the backmerging out of the io schedulers and into the elevator core. We save 1.6kb of text and as a bonus get backmerging for noop as well. Win-win! Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 17 ++--------------- include/linux/elevator.h | 2 ++ 2 files changed, 4 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index b2a412cf468f..8f5486964671 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -229,6 +229,8 @@ struct request { struct bio *bio; struct bio *biotail; + struct hlist_node hash; /* merge hash */ + void *elevator_private; void *completion_data; @@ -696,21 +698,6 @@ static inline void blkdev_dequeue_request(struct request *req) elv_dequeue_request(req->q, req); } -/* - * This should be in elevator.h, but that requires pulling in rq and q - */ -static inline void elv_dispatch_add_tail(struct request_queue *q, - struct request *rq) -{ - if (q->last_merge == rq) - q->last_merge = NULL; - q->nr_sorted--; - - q->end_sector = rq_end_sector(rq); - q->boundary_rq = rq; - list_add_tail(&rq->queuelist, &q->queue_head); -} - /* * Access functions for manipulating queue properties */ diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 1713ace808bf..2c270e90b33e 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -82,12 +82,14 @@ struct elevator_queue struct kobject kobj; struct elevator_type *elevator_type; struct mutex sysfs_lock; + struct hlist_head *hash; }; /* * block elevator interface */ extern void elv_dispatch_sort(request_queue_t *, struct request *); +extern void elv_dispatch_add_tail(request_queue_t *, struct request *); extern void elv_add_request(request_queue_t *, struct request *, int, int); extern void __elv_add_request(request_queue_t *, struct request *, int, int); extern void elv_insert(request_queue_t *, struct request *, int); -- cgit v1.2.3 From 10fd48f2376db52f08bf0420d2c4f580e39269e1 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 11 Jul 2006 21:15:52 +0200 Subject: [PATCH] rbtree: fixed reversed RB_EMPTY_NODE and rb_next/prev The conditions got reserved. Also make rb_next() and rb_prev() check for the empty condition. Signed-off-by: Jens Axboe --- include/linux/rbtree.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rbtree.h b/include/linux/rbtree.h index 8d5382e62c08..344bc3495ddb 100644 --- a/include/linux/rbtree.h +++ b/include/linux/rbtree.h @@ -133,7 +133,7 @@ static inline void rb_set_color(struct rb_node *rb, int color) #define rb_entry(ptr, type, member) container_of(ptr, type, member) #define RB_EMPTY_ROOT(root) ((root)->rb_node == NULL) -#define RB_EMPTY_NODE(node) (rb_parent(node) != node) +#define RB_EMPTY_NODE(node) (rb_parent(node) == node) #define RB_CLEAR_NODE(node) (rb_set_parent(node, node)) extern void rb_insert_color(struct rb_node *, struct rb_root *); -- cgit v1.2.3 From 2e662b65f05d550b6799ed6bfa9963b82279e6b7 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 13 Jul 2006 11:55:04 +0200 Subject: [PATCH] elevator: abstract out the rbtree sort handling The rbtree sort/lookup/reposition logic is mostly duplicated in cfq/deadline/as, so move it to the elevator core. The io schedulers still provide the actual rb root, as we don't want to impose any sort of specific handling on the schedulers. Introduce the helpers and rb_node in struct request to help migrate the IO schedulers. Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 + include/linux/elevator.h | 18 ++++++++++++++++-- 2 files changed, 17 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 8f5486964671..a905c4934a55 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -230,6 +230,7 @@ struct request { struct bio *biotail; struct hlist_node hash; /* merge hash */ + struct rb_node rb_node; /* sort/lookup */ void *elevator_private; void *completion_data; diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 2c270e90b33e..95b2a04b969c 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -6,7 +6,7 @@ typedef int (elevator_merge_fn) (request_queue_t *, struct request **, typedef void (elevator_merge_req_fn) (request_queue_t *, struct request *, struct request *); -typedef void (elevator_merged_fn) (request_queue_t *, struct request *); +typedef void (elevator_merged_fn) (request_queue_t *, struct request *, int); typedef int (elevator_dispatch_fn) (request_queue_t *, int); @@ -96,7 +96,7 @@ extern void elv_insert(request_queue_t *, struct request *, int); extern int elv_merge(request_queue_t *, struct request **, struct bio *); extern void elv_merge_requests(request_queue_t *, struct request *, struct request *); -extern void elv_merged_request(request_queue_t *, struct request *); +extern void elv_merged_request(request_queue_t *, struct request *, int); extern void elv_dequeue_request(request_queue_t *, struct request *); extern void elv_requeue_request(request_queue_t *, struct request *); extern int elv_queue_empty(request_queue_t *); @@ -126,6 +126,19 @@ extern int elevator_init(request_queue_t *, char *); extern void elevator_exit(elevator_t *); extern int elv_rq_merge_ok(struct request *, struct bio *); +/* + * Helper functions. + */ +extern struct request *elv_rb_former_request(request_queue_t *, struct request *); +extern struct request *elv_rb_latter_request(request_queue_t *, struct request *); + +/* + * rb support functions. + */ +extern struct request *elv_rb_add(struct rb_root *, struct request *); +extern void elv_rb_del(struct rb_root *, struct request *); +extern struct request *elv_rb_find(struct rb_root *, sector_t); + /* * Return values from elevator merger */ @@ -151,5 +164,6 @@ enum { }; #define rq_end_sector(rq) ((rq)->sector + (rq)->nr_sectors) +#define rb_entry_rq(node) rb_entry((node), struct request, rb_node) #endif -- cgit v1.2.3 From 1fbfdfcddff4df188b24d9d05271a76a85064583 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 11 Jul 2006 21:49:15 +0200 Subject: [PATCH] elevator: introduce a way to reuse rq for internal FIFO handling The io schedulers can use this instead of having to allocate space for it themselves. Signed-off-by: Jens Axboe --- include/linux/elevator.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 95b2a04b969c..0e7b1a733919 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -166,4 +166,16 @@ enum { #define rq_end_sector(rq) ((rq)->sector + (rq)->nr_sectors) #define rb_entry_rq(node) rb_entry((node), struct request, rb_node) +/* + * Hack to reuse the donelist list_head as the fifo time holder while + * the request is in the io scheduler. Saves an unsigned long in rq. + */ +#define rq_fifo_time(rq) ((unsigned long) (rq)->donelist.next) +#define rq_set_fifo_time(rq,exp) ((rq)->donelist.next = (void *) (exp)) +#define rq_entry_fifo(ptr) list_entry((ptr), struct request, queuelist) +#define rq_fifo_clear(rq) do { \ + list_del_init(&(rq)->queuelist); \ + INIT_LIST_HEAD(&(rq)->donelist); \ + } while (0) + #endif -- cgit v1.2.3 From 9e2585a8a23f3a42f815b2a638725d85a921cd65 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 28 Jul 2006 09:26:13 +0200 Subject: [PATCH] as-iosched: remove arq->is_sync member We can track this in struct request. Signed-off-by: Jens Axboe Signed-off-by: Nick Piggin --- include/linux/blkdev.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index a905c4934a55..55ef6efe3eb5 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -531,6 +531,11 @@ enum { #define rq_data_dir(rq) ((rq)->cmd_flags & 1) +/* + * We regard a request as sync, if it's a READ or a SYNC write. + */ +#define rq_is_sync(rq) (rq_data_dir((rq)) == READ || (rq)->cmd_flags & REQ_RW_SYNC) + static inline int blk_queue_full(struct request_queue *q, int rw) { if (rw == READ) -- cgit v1.2.3 From ff7d145fd911266ae42af7552edc32681c01addb Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 12 Jul 2006 14:04:37 +0200 Subject: [PATCH] Add one more pointer to struct request for IO scheduler usage Then we have enough room in the request to get rid of the dynamic allocations in CFQ/AS. Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 55ef6efe3eb5..d2dc17151f6c 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -232,7 +232,13 @@ struct request { struct hlist_node hash; /* merge hash */ struct rb_node rb_node; /* sort/lookup */ + /* + * two pointers are available for the IO schedulers, if they need + * more they have to dynamically allocate it. + */ void *elevator_private; + void *elevator_private2; + void *completion_data; int rq_status; /* should split this into a few status bits */ -- cgit v1.2.3 From c00895ab2f08df7044e58ee01c38bf0a661ea0eb Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sat, 30 Sep 2006 20:29:12 +0200 Subject: [PATCH] Remove ->waiting member from struct request As the comments indicates in blkdev.h, we can fold it into ->end_io_data usage as that is really what ->waiting is. Fixup the users of blk_end_sync_rq(). Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d2dc17151f6c..604f23189097 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -266,7 +266,6 @@ struct request { request_queue_t *q; struct request_list *rl; - struct completion *waiting; void *special; char *buffer; @@ -285,7 +284,7 @@ struct request { int retries; /* - * completion callback. end_io_data should be folded in with waiting + * completion callback. */ rq_end_io_fn *end_io; void *end_io_data; -- cgit v1.2.3 From 49171e5c6f414d49a061b5c1c84967c2eb569822 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 10 Aug 2006 08:59:11 +0200 Subject: [PATCH] Remove struct request_list from struct request It is always identical to &q->rq, and we only use it for detecting whether this request came out of our mempool or not. So replace it with an additional ->flags bit flag. Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 604f23189097..d4c1dd046e27 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -180,6 +180,7 @@ enum rq_flag_bits { __REQ_PREEMPT, /* set for "ide_preempt" requests */ __REQ_ORDERED_COLOR, /* is before or after barrier */ __REQ_RW_SYNC, /* request is sync (O_DIRECT) */ + __REQ_ALLOCED, /* request came from our alloc pool */ __REQ_NR_BITS, /* stops here */ }; @@ -199,6 +200,7 @@ enum rq_flag_bits { #define REQ_PREEMPT (1 << __REQ_PREEMPT) #define REQ_ORDERED_COLOR (1 << __REQ_ORDERED_COLOR) #define REQ_RW_SYNC (1 << __REQ_RW_SYNC) +#define REQ_ALLOCED (1 << __REQ_ALLOCED) #define BLK_MAX_CDB 16 @@ -264,7 +266,6 @@ struct request { int ref_count; request_queue_t *q; - struct request_list *rl; void *special; char *buffer; -- cgit v1.2.3 From cdd6026217c0e4cda2efce1bdc318661bef1f66f Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 28 Jul 2006 09:32:07 +0200 Subject: [PATCH] Remove ->rq_status from struct request After Christophs SCSI change, the only usage left is RQ_ACTIVE and RQ_INACTIVE. The block layer sets RQ_INACTIVE right before freeing the request, so any check for RQ_INACTIVE in a driver is a bug and indicates use-after-free. So kill/clean the remaining users, straight forward. Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 13 +++++-------- 1 file changed, 5 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d4c1dd046e27..8a3e309e0842 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -243,8 +243,6 @@ struct request { void *completion_data; - int rq_status; /* should split this into a few status bits */ - int errors; struct gendisk *rq_disk; unsigned long start_time; @@ -262,14 +260,16 @@ struct request { unsigned short ioprio; - int tag; - - int ref_count; request_queue_t *q; void *special; char *buffer; + int tag; + int errors; + + int ref_count; + /* * when request is used as a packet command carrier */ @@ -456,9 +456,6 @@ struct request_queue struct mutex sysfs_lock; }; -#define RQ_INACTIVE (-1) -#define RQ_ACTIVE 1 - #define QUEUE_FLAG_CLUSTER 0 /* cluster several segments into 1 */ #define QUEUE_FLAG_QUEUED 1 /* uses generic tag queueing */ #define QUEUE_FLAG_STOPPED 2 /* queue is stopped */ -- cgit v1.2.3 From cb78b285c8f9d59b0d4e4f6a54c2977ce1d9b880 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 28 Jul 2006 09:32:57 +0200 Subject: [PATCH] Drop useless bio passing in may_queue/set_request API It's not needed for anything, so kill the bio passing. Signed-off-by: Jens Axboe --- include/linux/elevator.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 0e7b1a733919..cc81645a3e18 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -14,9 +14,9 @@ typedef void (elevator_add_req_fn) (request_queue_t *, struct request *); typedef int (elevator_queue_empty_fn) (request_queue_t *); typedef struct request *(elevator_request_list_fn) (request_queue_t *, struct request *); typedef void (elevator_completed_req_fn) (request_queue_t *, struct request *); -typedef int (elevator_may_queue_fn) (request_queue_t *, int, struct bio *); +typedef int (elevator_may_queue_fn) (request_queue_t *, int); -typedef int (elevator_set_req_fn) (request_queue_t *, struct request *, struct bio *, gfp_t); +typedef int (elevator_set_req_fn) (request_queue_t *, struct request *, gfp_t); typedef void (elevator_put_req_fn) (request_queue_t *, struct request *); typedef void (elevator_activate_req_fn) (request_queue_t *, struct request *); typedef void (elevator_deactivate_req_fn) (request_queue_t *, struct request *); @@ -105,9 +105,9 @@ extern struct request *elv_former_request(request_queue_t *, struct request *); extern struct request *elv_latter_request(request_queue_t *, struct request *); extern int elv_register_queue(request_queue_t *q); extern void elv_unregister_queue(request_queue_t *q); -extern int elv_may_queue(request_queue_t *, int, struct bio *); +extern int elv_may_queue(request_queue_t *, int); extern void elv_completed_request(request_queue_t *, struct request *); -extern int elv_set_request(request_queue_t *, struct request *, struct bio *, gfp_t); +extern int elv_set_request(request_queue_t *, struct request *, gfp_t); extern void elv_put_request(request_queue_t *, struct request *); /* -- cgit v1.2.3 From e6a1c874a064e7d07f24986aba7cd537b7f4a25d Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 10 Aug 2006 09:00:21 +0200 Subject: [PATCH] struct request: shrink and optimize some more Move some members around and unionize completion_data and rb_node since they cannot ever be used at the same time. Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 20 +++++++++++++------- 1 file changed, 13 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 8a3e309e0842..a1e288069e2e 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -211,6 +211,8 @@ struct request { struct list_head queuelist; struct list_head donelist; + request_queue_t *q; + unsigned int cmd_flags; enum rq_cmd_type_bits cmd_type; @@ -219,12 +221,12 @@ struct request { */ sector_t sector; /* next sector to submit */ + sector_t hard_sector; /* next sector to complete */ unsigned long nr_sectors; /* no. of sectors left to submit */ + unsigned long hard_nr_sectors; /* no. of sectors left to complete */ /* no. of sectors left to submit in the current segment */ unsigned int current_nr_sectors; - sector_t hard_sector; /* next sector to complete */ - unsigned long hard_nr_sectors; /* no. of sectors left to complete */ /* no. of sectors left to complete in the current segment */ unsigned int hard_cur_sectors; @@ -232,7 +234,15 @@ struct request { struct bio *biotail; struct hlist_node hash; /* merge hash */ - struct rb_node rb_node; /* sort/lookup */ + /* + * The rb_node is only used inside the io scheduler, requests + * are pruned when moved to the dispatch queue. So let the + * completion_data share space with the rb_node. + */ + union { + struct rb_node rb_node; /* sort/lookup */ + void *completion_data; + }; /* * two pointers are available for the IO schedulers, if they need @@ -241,8 +251,6 @@ struct request { void *elevator_private; void *elevator_private2; - void *completion_data; - struct gendisk *rq_disk; unsigned long start_time; @@ -260,8 +268,6 @@ struct request { unsigned short ioprio; - request_queue_t *q; - void *special; char *buffer; -- cgit v1.2.3 From fc46379daf90dce57bf765c81d3b39f55150aac2 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 29 Aug 2006 09:05:44 +0200 Subject: [PATCH] cfq-iosched: kill cfq_exit_lock cfq_exit_lock is protecting two things now: - The per-ioc rbtree of cfq_io_contexts - The per-cfqd linked list of cfq_io_contexts The per-cfqd linked list can be protected by the queue lock, as it is (by definition) per cfqd as the queue lock is. The per-ioc rbtree is mainly used and updated by the process itself only. The only outside use is the io priority changing. If we move the priority changing to not browsing the rbtree, we can remove any locking from the rbtree updates and lookup completely. Let the sys_ioprio syscall just mark processes as having the iopriority changed and lazily update the private cfq io contexts the next time io is queued, and we can remove this locking as well. Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index a1e288069e2e..79cb9fa8034a 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -90,7 +90,7 @@ struct io_context { atomic_t refcount; struct task_struct *task; - int (*set_ioprio)(struct io_context *, unsigned int); + unsigned int ioprio_changed; /* * For request batching -- cgit v1.2.3 From 4a893e837bb470867d74c05d6c6b97bba5a96185 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sat, 22 Jul 2006 15:37:43 +0200 Subject: [PATCH] elevator: define ioc counting mechanism None of the in-kernel primitives for handling "atomic" counting seem to be a good fit. We need something that is essentially free for incrementing/decrementing, while the read side may be more expensive as we only ever need to do that when a device is removed from the kernel. Use a per-cpu variable for maintaining a per-cpu ioc count and define a reading mechanism that just sums up the values. Signed-off-by: Jens Axboe --- include/linux/elevator.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'include/linux') diff --git a/include/linux/elevator.h b/include/linux/elevator.h index cc81645a3e18..9c5a04f6114c 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -1,6 +1,8 @@ #ifndef _LINUX_ELEVATOR_H #define _LINUX_ELEVATOR_H +#include + typedef int (elevator_merge_fn) (request_queue_t *, struct request **, struct bio *); @@ -178,4 +180,27 @@ enum { INIT_LIST_HEAD(&(rq)->donelist); \ } while (0) +/* + * io context count accounting + */ +#define elv_ioc_count_mod(name, __val) \ + do { \ + preempt_disable(); \ + __get_cpu_var(name) += (__val); \ + preempt_enable(); \ + } while (0) + +#define elv_ioc_count_inc(name) elv_ioc_count_mod(name, 1) +#define elv_ioc_count_dec(name) elv_ioc_count_mod(name, -1) + +#define elv_ioc_count_read(name) \ +({ \ + unsigned long __val = 0; \ + int __cpu; \ + smp_wmb(); \ + for_each_possible_cpu(__cpu) \ + __val += per_cpu(name, __cpu); \ + __val; \ +}) + #endif -- cgit v1.2.3 From a3b05e8f58c95dfccbf2c824d0c68e5990571f24 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 28 Jul 2006 09:36:46 +0200 Subject: [PATCH] Kill various deprecated/unused block layer defines/functions Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 29 ----------------------------- include/linux/fs.h | 1 - 2 files changed, 30 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 79cb9fa8034a..593386162f47 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -578,12 +578,6 @@ static inline void blk_clear_queue_full(struct request_queue *q, int rw) #define rq_mergeable(rq) \ (!((rq)->cmd_flags & RQ_NOMERGE_FLAGS) && blk_fs_request((rq))) -/* - * noop, requests are automagically marked as active/inactive by I/O - * scheduler -- see elv_next_request - */ -#define blk_queue_headactive(q, head_active) - /* * q->prep_rq_fn return values */ @@ -621,11 +615,6 @@ static inline void blk_queue_bounce(request_queue_t *q, struct bio **bio) if ((rq->bio)) \ for (_bio = (rq)->bio; _bio; _bio = _bio->bi_next) -struct sec_size { - unsigned block_size; - unsigned block_size_bits; -}; - extern int blk_register_queue(struct gendisk *disk); extern void blk_unregister_queue(struct gendisk *disk); extern void register_disk(struct gendisk *dev); @@ -690,16 +679,6 @@ extern void end_that_request_last(struct request *, int); extern void end_request(struct request *req, int uptodate); extern void blk_complete_request(struct request *); -static inline int rq_all_done(struct request *rq, unsigned int nr_bytes) -{ - if (blk_fs_request(rq)) - return (nr_bytes >= (rq->hard_nr_sectors << 9)); - else if (blk_pc_request(rq)) - return nr_bytes >= rq->data_len; - - return 0; -} - /* * end_that_request_first/chunk() takes an uptodate argument. we account * any value <= as an io error. 0 means -EIO for compatability reasons, @@ -807,14 +786,6 @@ static inline int queue_dma_alignment(request_queue_t *q) return retval; } -static inline int bdev_dma_aligment(struct block_device *bdev) -{ - return queue_dma_alignment(bdev_get_queue(bdev)); -} - -#define blk_finished_io(nsects) do { } while (0) -#define blk_started_io(nsects) do { } while (0) - /* assumes size > 256 */ static inline unsigned int blksize_bits(unsigned int size) { diff --git a/include/linux/fs.h b/include/linux/fs.h index 6eafbe309483..9306f63bf77e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -79,7 +79,6 @@ extern int dir_notify_enable; #define WRITE 1 #define READA 2 /* read-ahead - don't block if no resources */ #define SWRITE 3 /* for ll_rw_block() - wait for buffer lock */ -#define SPECIAL 4 /* For non-blockdevice requests in request queue */ #define READ_SYNC (READ | (1 << BIO_RW_SYNC)) #define WRITE_SYNC (WRITE | (1 << BIO_RW_SYNC)) #define WRITE_BARRIER ((1 << BIO_RW) | (1 << BIO_RW_BARRIER)) -- cgit v1.2.3 From b5deef901282628d88c784f4c9d2f0583ec3b355 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 19 Jul 2006 23:39:40 +0200 Subject: [PATCH] Make sure all block/io scheduler setups are node aware Some were kmalloc_node(), some were still kmalloc(). Change them all to kmalloc_node(). Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 593386162f47..6609371c303e 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -104,8 +104,7 @@ struct io_context { void put_io_context(struct io_context *ioc); void exit_io_context(void); -struct io_context *current_io_context(gfp_t gfp_flags); -struct io_context *get_io_context(gfp_t gfp_flags); +struct io_context *get_io_context(gfp_t gfp_flags, int node); void copy_io_context(struct io_context **pdst, struct io_context **psrc); void swap_io_context(struct io_context **ioc1, struct io_context **ioc2); -- cgit v1.2.3 From dc72ef4ae35c2016fb594bcc85ce871376682174 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 20 Jul 2006 14:54:05 +0200 Subject: [PATCH] Add blk_start_queueing() helper CFQ implements this on its own now, but it's really block layer knowledge. Tells a device queue to start dispatching requests to the driver, taking care to unplug if needed. Also fixes the issue where as/cfq will invoke a stopped queue, which we really don't want. Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 6609371c303e..5d8e288db163 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -635,6 +635,7 @@ extern void blk_stop_queue(request_queue_t *q); extern void blk_sync_queue(struct request_queue *q); extern void __blk_stop_queue(request_queue_t *q); extern void blk_run_queue(request_queue_t *); +extern void blk_start_queueing(request_queue_t *); extern void blk_queue_activity_fn(request_queue_t *, activity_fn *, void *); extern int blk_rq_map_user(request_queue_t *, struct request *, void __user *, unsigned int); extern int blk_rq_unmap_user(struct bio *, unsigned int); -- cgit v1.2.3 From 5404bc7a87b9949cf61e0174b21f80e73239ab25 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 10 Aug 2006 09:01:02 +0200 Subject: [PATCH] Allow file systems to differentiate between data and meta reads We can use this information for making more intelligent priority decisions, and it will also be useful for blktrace. Signed-off-by: Jens Axboe --- include/linux/bio.h | 2 ++ include/linux/blkdev.h | 3 +++ include/linux/fs.h | 1 + 3 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 76bdaeab6f62..711c321a7011 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -148,6 +148,7 @@ struct bio { #define BIO_RW_BARRIER 2 #define BIO_RW_FAILFAST 3 #define BIO_RW_SYNC 4 +#define BIO_RW_META 5 /* * upper 16 bits of bi_rw define the io priority of this bio @@ -178,6 +179,7 @@ struct bio { #define bio_sync(bio) ((bio)->bi_rw & (1 << BIO_RW_SYNC)) #define bio_failfast(bio) ((bio)->bi_rw & (1 << BIO_RW_FAILFAST)) #define bio_rw_ahead(bio) ((bio)->bi_rw & (1 << BIO_RW_AHEAD)) +#define bio_rw_meta(bio) ((bio)->bi_rw & (1 << BIO_RW_META)) /* * will die diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 5d8e288db163..2c01a90998a7 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -180,6 +180,7 @@ enum rq_flag_bits { __REQ_ORDERED_COLOR, /* is before or after barrier */ __REQ_RW_SYNC, /* request is sync (O_DIRECT) */ __REQ_ALLOCED, /* request came from our alloc pool */ + __REQ_RW_META, /* metadata io request */ __REQ_NR_BITS, /* stops here */ }; @@ -200,6 +201,7 @@ enum rq_flag_bits { #define REQ_ORDERED_COLOR (1 << __REQ_ORDERED_COLOR) #define REQ_RW_SYNC (1 << __REQ_RW_SYNC) #define REQ_ALLOCED (1 << __REQ_ALLOCED) +#define REQ_RW_META (1 << __REQ_RW_META) #define BLK_MAX_CDB 16 @@ -543,6 +545,7 @@ enum { * We regard a request as sync, if it's a READ or a SYNC write. */ #define rq_is_sync(rq) (rq_data_dir((rq)) == READ || (rq)->cmd_flags & REQ_RW_SYNC) +#define rq_is_meta(rq) ((rq)->cmd_flags & REQ_RW_META) static inline int blk_queue_full(struct request_queue *q, int rw) { diff --git a/include/linux/fs.h b/include/linux/fs.h index 9306f63bf77e..d68c37af4dfb 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -80,6 +80,7 @@ extern int dir_notify_enable; #define READA 2 /* read-ahead - don't block if no resources */ #define SWRITE 3 /* for ll_rw_block() - wait for buffer lock */ #define READ_SYNC (READ | (1 << BIO_RW_SYNC)) +#define READ_META (READ | (1 << BIO_RW_META)) #define WRITE_SYNC (WRITE | (1 << BIO_RW_SYNC)) #define WRITE_BARRIER ((1 << BIO_RW) | (1 << BIO_RW_BARRIER)) -- cgit v1.2.3 From 7457e6e2d7406c7009e9ad03db1335fe93b5fb71 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sun, 23 Jul 2006 02:12:01 +0200 Subject: [PATCH] blktrace: support for logging metadata reads Signed-off-by: Jens Axboe --- include/linux/blktrace_api.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index ea48eb1b3fd3..b99a714fcac6 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -20,6 +20,7 @@ enum blktrace_cat { BLK_TC_PC = 1 << 9, /* pc requests */ BLK_TC_NOTIFY = 1 << 10, /* special message */ BLK_TC_AHEAD = 1 << 11, /* readahead */ + BLK_TC_META = 1 << 12, /* metadata */ BLK_TC_END = 1 << 15, /* only 16-bits, reminder */ }; -- cgit v1.2.3 From cf9a2ae8d49948f861b56e5333530e491a9da190 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 29 Aug 2006 19:05:54 +0100 Subject: [PATCH] BLOCK: Move functions out of buffer code [try #6] Move some functions out of the buffering code that aren't strictly buffering specific. This is a precursor to being able to disable the block layer. (*) Moved some stuff out of fs/buffer.c: (*) The file sync and general sync stuff moved to fs/sync.c. (*) The superblock sync stuff moved to fs/super.c. (*) do_invalidatepage() moved to mm/truncate.c. (*) try_to_release_page() moved to mm/filemap.c. (*) Moved some related declarations between header files: (*) declarations for do_invalidatepage() and try_to_release_page() moved to linux/mm.h. (*) __set_page_dirty_buffers() moved to linux/buffer_head.h. Signed-Off-By: David Howells Signed-off-by: Jens Axboe --- include/linux/buffer_head.h | 3 +-- include/linux/fs.h | 1 + include/linux/mm.h | 4 +++- 3 files changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 737e407d0cd1..64b508e35d2a 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -190,9 +190,7 @@ extern int buffer_heads_over_limit; * Generic address_space_operations implementations for buffer_head-backed * address_spaces. */ -int try_to_release_page(struct page * page, gfp_t gfp_mask); void block_invalidatepage(struct page *page, unsigned long offset); -void do_invalidatepage(struct page *page, unsigned long offset); int block_write_full_page(struct page *page, get_block_t *get_block, struct writeback_control *wbc); int block_read_full_page(struct page*, get_block_t*); @@ -302,4 +300,5 @@ static inline void lock_buffer(struct buffer_head *bh) __lock_buffer(bh); } +extern int __set_page_dirty_buffers(struct page *page); #endif /* _LINUX_BUFFER_HEAD_H */ diff --git a/include/linux/fs.h b/include/linux/fs.h index d68c37af4dfb..1728142ec4b6 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1546,6 +1546,7 @@ extern int __filemap_fdatawrite_range(struct address_space *mapping, extern long do_fsync(struct file *file, int datasync); extern void sync_supers(void); extern void sync_filesystems(int wait); +extern void __fsync_super(struct super_block *sb); extern void emergency_sync(void); extern void emergency_remount(void); extern int do_remount_sb(struct super_block *sb, int flags, diff --git a/include/linux/mm.h b/include/linux/mm.h index 7b703b6d4358..4edf1934e5ca 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -743,7 +743,9 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, unsigned long int len, int write, int force, struct page **pages, struct vm_area_struct **vmas); void print_bad_pte(struct vm_area_struct *, pte_t, unsigned long); -int __set_page_dirty_buffers(struct page *page); +extern int try_to_release_page(struct page * page, gfp_t gfp_mask); +extern void do_invalidatepage(struct page *page, unsigned long offset); + int __set_page_dirty_nobuffers(struct page *page); int redirty_page_for_writepage(struct writeback_control *wbc, struct page *page); -- cgit v1.2.3 From 0d67a46df0125e20d14f12dbd3646f1f1bf23e8c Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 29 Aug 2006 19:05:56 +0100 Subject: [PATCH] BLOCK: Remove duplicate declaration of exit_io_context() [try #6] Remove the duplicate declaration of exit_io_context() from linux/sched.h. Signed-Off-By: David Howells Signed-off-by: Jens Axboe --- 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 a06fc89cf6e5..fc4a9873ec10 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -710,7 +710,6 @@ extern unsigned int max_cache_size; struct io_context; /* See blkdev.h */ -void exit_io_context(void); struct cpuset; #define NGROUPS_SMALL 32 -- cgit v1.2.3 From 07f3f05c1e3052b8656129b2a5aca9f888241a34 Mon Sep 17 00:00:00 2001 From: David Howells Date: Sat, 30 Sep 2006 20:52:18 +0200 Subject: [PATCH] BLOCK: Move extern declarations out of fs/*.c into header files [try #6] Create a new header file, fs/internal.h, for common definitions local to the sources in the fs/ directory. Move extern definitions that should be in header files from fs/*.c to fs/internal.h or other main header files where they span directories. Signed-Off-By: David Howells Signed-off-by: Jens Axboe --- include/linux/ramfs.h | 1 + include/linux/tty.h | 3 +++ 2 files changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ramfs.h b/include/linux/ramfs.h index 00b340ba6612..b160fb18e8d6 100644 --- a/include/linux/ramfs.h +++ b/include/linux/ramfs.h @@ -17,5 +17,6 @@ extern int ramfs_nommu_mmap(struct file *file, struct vm_area_struct *vma); extern const struct file_operations ramfs_file_operations; extern struct vm_operations_struct generic_file_vm_ops; +extern int __init init_rootfs(void); #endif diff --git a/include/linux/tty.h b/include/linux/tty.h index ea4c2605f8da..44091c0db0b4 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -307,6 +307,9 @@ extern void tty_ldisc_put(int); extern void tty_wakeup(struct tty_struct *tty); extern void tty_ldisc_flush(struct tty_struct *tty); +extern int tty_ioctl(struct inode *inode, struct file *file, unsigned int cmd, + unsigned long arg); + extern struct mutex tty_mutex; /* n_tty.c */ -- cgit v1.2.3 From 811d736f9e8013966e1a5a930c0db09508bdbb15 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 29 Aug 2006 19:06:09 +0100 Subject: [PATCH] BLOCK: Dissociate generic_writepages() from mpage stuff [try #6] Dissociate the generic_writepages() function from the mpage stuff, moving its declaration to linux/mm.h and actually emitting a full implementation into mm/page-writeback.c. The implementation is a partial duplicate of mpage_writepages() with all BIO references removed. It is used by NFS to do writeback. Signed-Off-By: David Howells Signed-off-by: Jens Axboe --- include/linux/mpage.h | 6 ------ include/linux/writeback.h | 2 ++ 2 files changed, 2 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mpage.h b/include/linux/mpage.h index 3ca880463c47..517c098fde20 100644 --- a/include/linux/mpage.h +++ b/include/linux/mpage.h @@ -20,9 +20,3 @@ int mpage_writepages(struct address_space *mapping, struct writeback_control *wbc, get_block_t get_block); int mpage_writepage(struct page *page, get_block_t *get_block, struct writeback_control *wbc); - -static inline int -generic_writepages(struct address_space *mapping, struct writeback_control *wbc) -{ - return mpage_writepages(mapping, wbc, NULL); -} diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 9d4074ecd0cd..4f4d98addb44 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -111,6 +111,8 @@ balance_dirty_pages_ratelimited(struct address_space *mapping) } int pdflush_operation(void (*fn)(unsigned long), unsigned long arg0); +extern int generic_writepages(struct address_space *mapping, + struct writeback_control *wbc); int do_writepages(struct address_space *mapping, struct writeback_control *wbc); int sync_page_range(struct inode *inode, struct address_space *mapping, loff_t pos, loff_t count); -- cgit v1.2.3 From 863d5b822c02d0e7215fb84ca79e9f8c3e35f04e Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 29 Aug 2006 19:06:14 +0100 Subject: [PATCH] BLOCK: Move the loop device ioctl compat stuff to the loop driver [try #6] Move the loop device ioctl compat stuff from fs/compat_ioctl.c to the loop driver so that the loop header file doesn't need to be included. Signed-Off-By: David Howells Signed-off-by: Jens Axboe --- include/linux/compat_ioctl.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compat_ioctl.h b/include/linux/compat_ioctl.h index bea0255196c4..98d40e08ba6e 100644 --- a/include/linux/compat_ioctl.h +++ b/include/linux/compat_ioctl.h @@ -395,12 +395,6 @@ COMPATIBLE_IOCTL(DVD_WRITE_STRUCT) COMPATIBLE_IOCTL(DVD_AUTH) /* pktcdvd */ COMPATIBLE_IOCTL(PACKET_CTRL_CMD) -/* Big L */ -ULONG_IOCTL(LOOP_SET_FD) -ULONG_IOCTL(LOOP_CHANGE_FD) -COMPATIBLE_IOCTL(LOOP_CLR_FD) -COMPATIBLE_IOCTL(LOOP_GET_STATUS64) -COMPATIBLE_IOCTL(LOOP_SET_STATUS64) /* Big A */ /* sparc only */ /* Big Q for sound/OSS */ -- cgit v1.2.3 From 36695673b012096228ebdc1b39a6a5850daa474e Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 29 Aug 2006 19:06:16 +0100 Subject: [PATCH] BLOCK: Move common FS-specific ioctls to linux/fs.h [try #6] Move common FS-specific ioctls from linux/ext2_fs.h to linux/fs.h as FS_IOC_* and FS_IOC32_* and have the users of them use those as a base. Also move the GETFLAGS/SETFLAGS flags to linux/fs.h as FS_*_FL macros, and then have the other users use them as a base. Signed-Off-By: David Howells Signed-off-by: Jens Axboe --- include/linux/ext2_fs.h | 64 +++++++++++++++++++++++++-------------------- include/linux/ext3_fs.h | 20 +++++++++++--- include/linux/fs.h | 39 +++++++++++++++++++++++++++ include/linux/reiserfs_fs.h | 28 +++++++++----------- 4 files changed, 104 insertions(+), 47 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ext2_fs.h b/include/linux/ext2_fs.h index 33a1aa107329..153d755376a4 100644 --- a/include/linux/ext2_fs.h +++ b/include/linux/ext2_fs.h @@ -165,41 +165,49 @@ struct ext2_group_desc #define EXT2_N_BLOCKS (EXT2_TIND_BLOCK + 1) /* - * Inode flags + * Inode flags (GETFLAGS/SETFLAGS) */ -#define EXT2_SECRM_FL 0x00000001 /* Secure deletion */ -#define EXT2_UNRM_FL 0x00000002 /* Undelete */ -#define EXT2_COMPR_FL 0x00000004 /* Compress file */ -#define EXT2_SYNC_FL 0x00000008 /* Synchronous updates */ -#define EXT2_IMMUTABLE_FL 0x00000010 /* Immutable file */ -#define EXT2_APPEND_FL 0x00000020 /* writes to file may only append */ -#define EXT2_NODUMP_FL 0x00000040 /* do not dump file */ -#define EXT2_NOATIME_FL 0x00000080 /* do not update atime */ +#define EXT2_SECRM_FL FS_SECRM_FL /* Secure deletion */ +#define EXT2_UNRM_FL FS_UNRM_FL /* Undelete */ +#define EXT2_COMPR_FL FS_COMPR_FL /* Compress file */ +#define EXT2_SYNC_FL FS_SYNC_FL /* Synchronous updates */ +#define EXT2_IMMUTABLE_FL FS_IMMUTABLE_FL /* Immutable file */ +#define EXT2_APPEND_FL FS_APPEND_FL /* writes to file may only append */ +#define EXT2_NODUMP_FL FS_NODUMP_FL /* do not dump file */ +#define EXT2_NOATIME_FL FS_NOATIME_FL /* do not update atime */ /* Reserved for compression usage... */ -#define EXT2_DIRTY_FL 0x00000100 -#define EXT2_COMPRBLK_FL 0x00000200 /* One or more compressed clusters */ -#define EXT2_NOCOMP_FL 0x00000400 /* Don't compress */ -#define EXT2_ECOMPR_FL 0x00000800 /* Compression error */ +#define EXT2_DIRTY_FL FS_DIRTY_FL +#define EXT2_COMPRBLK_FL FS_COMPRBLK_FL /* One or more compressed clusters */ +#define EXT2_NOCOMP_FL FS_NOCOMP_FL /* Don't compress */ +#define EXT2_ECOMPR_FL FS_ECOMPR_FL /* Compression error */ /* End compression flags --- maybe not all used */ -#define EXT2_BTREE_FL 0x00001000 /* btree format dir */ -#define EXT2_INDEX_FL 0x00001000 /* hash-indexed directory */ -#define EXT2_IMAGIC_FL 0x00002000 /* AFS directory */ -#define EXT2_JOURNAL_DATA_FL 0x00004000 /* Reserved for ext3 */ -#define EXT2_NOTAIL_FL 0x00008000 /* file tail should not be merged */ -#define EXT2_DIRSYNC_FL 0x00010000 /* dirsync behaviour (directories only) */ -#define EXT2_TOPDIR_FL 0x00020000 /* Top of directory hierarchies*/ -#define EXT2_RESERVED_FL 0x80000000 /* reserved for ext2 lib */ - -#define EXT2_FL_USER_VISIBLE 0x0003DFFF /* User visible flags */ -#define EXT2_FL_USER_MODIFIABLE 0x000380FF /* User modifiable flags */ +#define EXT2_BTREE_FL FS_BTREE_FL /* btree format dir */ +#define EXT2_INDEX_FL FS_INDEX_FL /* hash-indexed directory */ +#define EXT2_IMAGIC_FL FS_IMAGIC_FL /* AFS directory */ +#define EXT2_JOURNAL_DATA_FL FS_JOURNAL_DATA_FL /* Reserved for ext3 */ +#define EXT2_NOTAIL_FL FS_NOTAIL_FL /* file tail should not be merged */ +#define EXT2_DIRSYNC_FL FS_DIRSYNC_FL /* dirsync behaviour (directories only) */ +#define EXT2_TOPDIR_FL FS_TOPDIR_FL /* Top of directory hierarchies*/ +#define EXT2_RESERVED_FL FS_RESERVED_FL /* reserved for ext2 lib */ + +#define EXT2_FL_USER_VISIBLE FS_FL_USER_VISIBLE /* User visible flags */ +#define EXT2_FL_USER_MODIFIABLE FS_FL_USER_MODIFIABLE /* User modifiable flags */ /* * ioctl commands */ -#define EXT2_IOC_GETFLAGS _IOR('f', 1, long) -#define EXT2_IOC_SETFLAGS _IOW('f', 2, long) -#define EXT2_IOC_GETVERSION _IOR('v', 1, long) -#define EXT2_IOC_SETVERSION _IOW('v', 2, long) +#define EXT2_IOC_GETFLAGS FS_IOC_GETFLAGS +#define EXT2_IOC_SETFLAGS FS_IOC_SETFLAGS +#define EXT2_IOC_GETVERSION FS_IOC_GETVERSION +#define EXT2_IOC_SETVERSION FS_IOC_SETVERSION + +/* + * ioctl commands in 32 bit emulation + */ +#define EXT2_IOC32_GETFLAGS FS_IOC32_GETFLAGS +#define EXT2_IOC32_SETFLAGS FS_IOC32_SETFLAGS +#define EXT2_IOC32_GETVERSION FS_IOC32_GETVERSION +#define EXT2_IOC32_SETVERSION FS_IOC32_SETVERSION /* * Structure of an inode on the disk diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h index cc08f56750da..a7a01ff44669 100644 --- a/include/linux/ext3_fs.h +++ b/include/linux/ext3_fs.h @@ -216,20 +216,32 @@ struct ext3_new_group_data { /* * ioctl commands */ -#define EXT3_IOC_GETFLAGS _IOR('f', 1, long) -#define EXT3_IOC_SETFLAGS _IOW('f', 2, long) +#define EXT3_IOC_GETFLAGS FS_IOC_GETFLAGS +#define EXT3_IOC_SETFLAGS FS_IOC_SETFLAGS #define EXT3_IOC_GETVERSION _IOR('f', 3, long) #define EXT3_IOC_SETVERSION _IOW('f', 4, long) #define EXT3_IOC_GROUP_EXTEND _IOW('f', 7, unsigned long) #define EXT3_IOC_GROUP_ADD _IOW('f', 8,struct ext3_new_group_input) -#define EXT3_IOC_GETVERSION_OLD _IOR('v', 1, long) -#define EXT3_IOC_SETVERSION_OLD _IOW('v', 2, long) +#define EXT3_IOC_GETVERSION_OLD FS_IOC_GETVERSION +#define EXT3_IOC_SETVERSION_OLD FS_IOC_SETVERSION #ifdef CONFIG_JBD_DEBUG #define EXT3_IOC_WAIT_FOR_READONLY _IOR('f', 99, long) #endif #define EXT3_IOC_GETRSVSZ _IOR('f', 5, long) #define EXT3_IOC_SETRSVSZ _IOW('f', 6, long) +/* + * ioctl commands in 32 bit emulation + */ +#define EXT3_IOC32_GETVERSION _IOR('f', 3, int) +#define EXT3_IOC32_SETVERSION _IOW('f', 4, int) +#define EXT3_IOC32_GETRSVSZ _IOR('f', 5, int) +#define EXT3_IOC32_SETRSVSZ _IOW('f', 6, int) +#define EXT3_IOC32_GROUP_EXTEND _IOW('f', 7, unsigned int) +#ifdef CONFIG_JBD_DEBUG +#define EXT3_IOC32_WAIT_FOR_READONLY _IOR('f', 99, int) +#endif + /* * Mount options */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 1728142ec4b6..b73a47582dbe 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -217,6 +217,45 @@ extern int dir_notify_enable; #define FIBMAP _IO(0x00,1) /* bmap access */ #define FIGETBSZ _IO(0x00,2) /* get the block size used for bmap */ +#define FS_IOC_GETFLAGS _IOR('f', 1, long) +#define FS_IOC_SETFLAGS _IOW('f', 2, long) +#define FS_IOC_GETVERSION _IOR('v', 1, long) +#define FS_IOC_SETVERSION _IOW('v', 2, long) +#define FS_IOC32_GETFLAGS _IOR('f', 1, int) +#define FS_IOC32_SETFLAGS _IOW('f', 2, int) +#define FS_IOC32_GETVERSION _IOR('v', 1, int) +#define FS_IOC32_SETVERSION _IOW('v', 2, int) + +/* + * Inode flags (FS_IOC_GETFLAGS / FS_IOC_SETFLAGS) + */ +#define FS_SECRM_FL 0x00000001 /* Secure deletion */ +#define FS_UNRM_FL 0x00000002 /* Undelete */ +#define FS_COMPR_FL 0x00000004 /* Compress file */ +#define FS_SYNC_FL 0x00000008 /* Synchronous updates */ +#define FS_IMMUTABLE_FL 0x00000010 /* Immutable file */ +#define FS_APPEND_FL 0x00000020 /* writes to file may only append */ +#define FS_NODUMP_FL 0x00000040 /* do not dump file */ +#define FS_NOATIME_FL 0x00000080 /* do not update atime */ +/* Reserved for compression usage... */ +#define FS_DIRTY_FL 0x00000100 +#define FS_COMPRBLK_FL 0x00000200 /* One or more compressed clusters */ +#define FS_NOCOMP_FL 0x00000400 /* Don't compress */ +#define FS_ECOMPR_FL 0x00000800 /* Compression error */ +/* End compression flags --- maybe not all used */ +#define FS_BTREE_FL 0x00001000 /* btree format dir */ +#define FS_INDEX_FL 0x00001000 /* hash-indexed directory */ +#define FS_IMAGIC_FL 0x00002000 /* AFS directory */ +#define FS_JOURNAL_DATA_FL 0x00004000 /* Reserved for ext3 */ +#define FS_NOTAIL_FL 0x00008000 /* file tail should not be merged */ +#define FS_DIRSYNC_FL 0x00010000 /* dirsync behaviour (directories only) */ +#define FS_TOPDIR_FL 0x00020000 /* Top of directory hierarchies*/ +#define FS_RESERVED_FL 0x80000000 /* reserved for ext2 lib */ + +#define FS_FL_USER_VISIBLE 0x0003DFFF /* User visible flags */ +#define FS_FL_USER_MODIFIABLE 0x000380FF /* User modifiable flags */ + + #define SYNC_FILE_RANGE_WAIT_BEFORE 1 #define SYNC_FILE_RANGE_WRITE 2 #define SYNC_FILE_RANGE_WAIT_AFTER 4 diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h index 28493ffaafe7..0100d6d1d84c 100644 --- a/include/linux/reiserfs_fs.h +++ b/include/linux/reiserfs_fs.h @@ -807,21 +807,19 @@ struct stat_data_v1 { #define set_sd_v1_first_direct_byte(sdp,v) \ ((sdp)->sd_first_direct_byte = cpu_to_le32(v)) -#include - /* inode flags stored in sd_attrs (nee sd_reserved) */ /* we want common flags to have the same values as in ext2, so chattr(1) will work without problems */ -#define REISERFS_IMMUTABLE_FL EXT2_IMMUTABLE_FL -#define REISERFS_APPEND_FL EXT2_APPEND_FL -#define REISERFS_SYNC_FL EXT2_SYNC_FL -#define REISERFS_NOATIME_FL EXT2_NOATIME_FL -#define REISERFS_NODUMP_FL EXT2_NODUMP_FL -#define REISERFS_SECRM_FL EXT2_SECRM_FL -#define REISERFS_UNRM_FL EXT2_UNRM_FL -#define REISERFS_COMPR_FL EXT2_COMPR_FL -#define REISERFS_NOTAIL_FL EXT2_NOTAIL_FL +#define REISERFS_IMMUTABLE_FL FS_IMMUTABLE_FL +#define REISERFS_APPEND_FL FS_APPEND_FL +#define REISERFS_SYNC_FL FS_SYNC_FL +#define REISERFS_NOATIME_FL FS_NOATIME_FL +#define REISERFS_NODUMP_FL FS_NODUMP_FL +#define REISERFS_SECRM_FL FS_SECRM_FL +#define REISERFS_UNRM_FL FS_UNRM_FL +#define REISERFS_COMPR_FL FS_COMPR_FL +#define REISERFS_NOTAIL_FL FS_NOTAIL_FL /* persistent flags that file inherits from the parent directory */ #define REISERFS_INHERIT_MASK ( REISERFS_IMMUTABLE_FL | \ @@ -2168,10 +2166,10 @@ int reiserfs_ioctl(struct inode *inode, struct file *filp, #define REISERFS_IOC_UNPACK _IOW(0xCD,1,long) /* define following flags to be the same as in ext2, so that chattr(1), lsattr(1) will work with us. */ -#define REISERFS_IOC_GETFLAGS EXT2_IOC_GETFLAGS -#define REISERFS_IOC_SETFLAGS EXT2_IOC_SETFLAGS -#define REISERFS_IOC_GETVERSION EXT2_IOC_GETVERSION -#define REISERFS_IOC_SETVERSION EXT2_IOC_SETVERSION +#define REISERFS_IOC_GETFLAGS FS_IOC_GETFLAGS +#define REISERFS_IOC_SETFLAGS FS_IOC_SETFLAGS +#define REISERFS_IOC_GETVERSION FS_IOC_GETVERSION +#define REISERFS_IOC_SETVERSION FS_IOC_SETVERSION /* Locking primitives */ /* Right now we are still falling back to (un)lock_kernel, but eventually that -- cgit v1.2.3 From 52b499c438ff60991eb3855ca090782569b3e8cf Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 29 Aug 2006 19:06:18 +0100 Subject: [PATCH] BLOCK: Move the ReiserFS device ioctl compat stuff to the ReiserFS driver [try #6] Move the ReiserFS device ioctl compat stuff from fs/compat_ioctl.c to the ReiserFS driver so that the ReiserFS header file doesn't need to be included. Signed-Off-By: David Howells Signed-off-by: Jens Axboe --- include/linux/reiserfs_fs.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h index 0100d6d1d84c..9c63abffd7b2 100644 --- a/include/linux/reiserfs_fs.h +++ b/include/linux/reiserfs_fs.h @@ -2161,6 +2161,8 @@ __u32 r5_hash(const signed char *msg, int len); /* prototypes from ioctl.c */ int reiserfs_ioctl(struct inode *inode, struct file *filp, unsigned int cmd, unsigned long arg); +long reiserfs_compat_ioctl(struct file *filp, + unsigned int cmd, unsigned long arg); /* ioctl's command */ #define REISERFS_IOC_UNPACK _IOW(0xCD,1,long) @@ -2171,6 +2173,13 @@ int reiserfs_ioctl(struct inode *inode, struct file *filp, #define REISERFS_IOC_GETVERSION FS_IOC_GETVERSION #define REISERFS_IOC_SETVERSION FS_IOC_SETVERSION +/* the 32 bit compat definitions with int argument */ +#define REISERFS_IOC32_UNPACK _IOW(0xCD, 1, int) +#define REISERFS_IOC32_GETFLAGS FS_IOC32_GETFLAGS +#define REISERFS_IOC32_SETFLAGS FS_IOC32_SETFLAGS +#define REISERFS_IOC32_GETVERSION FS_IOC32_GETVERSION +#define REISERFS_IOC32_SETVERSION FS_IOC32_SETVERSION + /* Locking primitives */ /* Right now we are still falling back to (un)lock_kernel, but eventually that would evolve into real per-fs locks */ -- cgit v1.2.3 From 52a700c5675f399c07e6e57328291e57f13ef3bb Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 29 Aug 2006 19:06:23 +0100 Subject: [PATCH] BLOCK: Move the Ext3 device ioctl compat stuff to the Ext3 driver [try #6] Move the Ext3 device ioctl compat stuff from fs/compat_ioctl.c to the Ext3 driver so that the Ext3 header file doesn't need to be included. Signed-Off-By: David Howells Signed-off-by: Jens Axboe --- include/linux/ext3_fs.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h index a7a01ff44669..11cca1bdc0c7 100644 --- a/include/linux/ext3_fs.h +++ b/include/linux/ext3_fs.h @@ -233,6 +233,8 @@ struct ext3_new_group_data { /* * ioctl commands in 32 bit emulation */ +#define EXT3_IOC32_GETFLAGS FS_IOC32_GETFLAGS +#define EXT3_IOC32_SETFLAGS FS_IOC32_SETFLAGS #define EXT3_IOC32_GETVERSION _IOR('f', 3, int) #define EXT3_IOC32_SETVERSION _IOW('f', 4, int) #define EXT3_IOC32_GETRSVSZ _IOR('f', 5, int) @@ -241,6 +243,9 @@ struct ext3_new_group_data { #ifdef CONFIG_JBD_DEBUG #define EXT3_IOC32_WAIT_FOR_READONLY _IOR('f', 99, int) #endif +#define EXT3_IOC32_GETVERSION_OLD FS_IOC32_GETVERSION +#define EXT3_IOC32_SETVERSION_OLD FS_IOC32_SETVERSION + /* * Mount options @@ -824,6 +829,7 @@ extern void ext3_set_aops(struct inode *inode); /* ioctl.c */ extern int ext3_ioctl (struct inode *, struct file *, unsigned int, unsigned long); +extern long ext3_compat_ioctl (struct file *, unsigned int, unsigned long); /* namei.c */ extern int ext3_orphan_add(handle_t *, struct inode *); -- cgit v1.2.3 From 9361401eb7619c033e2394e4f9f6d410d6719ac7 Mon Sep 17 00:00:00 2001 From: David Howells Date: Sat, 30 Sep 2006 20:45:40 +0200 Subject: [PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 50 +++++++++++++++++++++++++++++++------------- include/linux/buffer_head.h | 16 ++++++++++++++ include/linux/compat_ioctl.h | 2 ++ include/linux/elevator.h | 3 +++ include/linux/fs.h | 25 +++++++++++++++++++--- include/linux/genhd.h | 4 ++++ include/linux/mpage.h | 3 +++ include/linux/raid/md.h | 3 +++ include/linux/raid/md_k.h | 3 +++ 9 files changed, 92 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 2c01a90998a7..3e36107d342a 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -16,6 +16,22 @@ #include +#ifdef CONFIG_LBD +# include +# define sector_div(a, b) do_div(a, b) +#else +# define sector_div(n, b)( \ +{ \ + int _res; \ + _res = (n) % (b); \ + (n) /= (b); \ + _res; \ +} \ +) +#endif + +#ifdef CONFIG_BLOCK + struct scsi_ioctl_command; struct request_queue; @@ -818,24 +834,30 @@ struct work_struct; int kblockd_schedule_work(struct work_struct *work); void kblockd_flush(void); -#ifdef CONFIG_LBD -# include -# define sector_div(a, b) do_div(a, b) -#else -# define sector_div(n, b)( \ -{ \ - int _res; \ - _res = (n) % (b); \ - (n) /= (b); \ - _res; \ -} \ -) -#endif - #define MODULE_ALIAS_BLOCKDEV(major,minor) \ MODULE_ALIAS("block-major-" __stringify(major) "-" __stringify(minor)) #define MODULE_ALIAS_BLOCKDEV_MAJOR(major) \ MODULE_ALIAS("block-major-" __stringify(major) "-*") +#else /* CONFIG_BLOCK */ +/* + * stubs for when the block layer is configured out + */ +#define buffer_heads_over_limit 0 + +static inline long blk_congestion_wait(int rw, long timeout) +{ + return timeout; +} + +static inline long nr_blockdev_pages(void) +{ + return 0; +} + +static inline void exit_io_context(void) {} + +#endif /* CONFIG_BLOCK */ + #endif diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 64b508e35d2a..131ffd37e716 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -14,6 +14,8 @@ #include #include +#ifdef CONFIG_BLOCK + enum bh_state_bits { BH_Uptodate, /* Contains valid data */ BH_Dirty, /* Is dirty */ @@ -301,4 +303,18 @@ static inline void lock_buffer(struct buffer_head *bh) } extern int __set_page_dirty_buffers(struct page *page); + +#else /* CONFIG_BLOCK */ + +static inline void buffer_init(void) {} +static inline int try_to_free_buffers(struct page *page) { return 1; } +static inline int sync_blockdev(struct block_device *bdev) { return 0; } +static inline int inode_has_buffers(struct inode *inode) { return 0; } +static inline void invalidate_inode_buffers(struct inode *inode) {} +static inline int remove_inode_buffers(struct inode *inode) { return 1; } +static inline int sync_mapping_buffers(struct address_space *mapping) { return 0; } +static inline void invalidate_bdev(struct block_device *bdev, int destroy_dirty_buffers) {} + + +#endif /* CONFIG_BLOCK */ #endif /* _LINUX_BUFFER_HEAD_H */ diff --git a/include/linux/compat_ioctl.h b/include/linux/compat_ioctl.h index 98d40e08ba6e..d61ef5951538 100644 --- a/include/linux/compat_ioctl.h +++ b/include/linux/compat_ioctl.h @@ -90,6 +90,7 @@ COMPATIBLE_IOCTL(FDTWADDLE) COMPATIBLE_IOCTL(FDFMTTRK) COMPATIBLE_IOCTL(FDRAWCMD) /* 0x12 */ +#ifdef CONFIG_BLOCK COMPATIBLE_IOCTL(BLKRASET) COMPATIBLE_IOCTL(BLKROSET) COMPATIBLE_IOCTL(BLKROGET) @@ -103,6 +104,7 @@ COMPATIBLE_IOCTL(BLKTRACESETUP) COMPATIBLE_IOCTL(BLKTRACETEARDOWN) ULONG_IOCTL(BLKRASET) ULONG_IOCTL(BLKFRASET) +#endif /* RAID */ COMPATIBLE_IOCTL(RAID_VERSION) COMPATIBLE_IOCTL(GET_ARRAY_INFO) diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 9c5a04f6114c..b3370ef5164d 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -3,6 +3,8 @@ #include +#ifdef CONFIG_BLOCK + typedef int (elevator_merge_fn) (request_queue_t *, struct request **, struct bio *); @@ -203,4 +205,5 @@ enum { __val; \ }) +#endif /* CONFIG_BLOCK */ #endif diff --git a/include/linux/fs.h b/include/linux/fs.h index b73a47582dbe..5baf3a153403 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1482,6 +1482,7 @@ extern void __init vfs_caches_init(unsigned long); extern void putname(const char *name); #endif +#ifdef CONFIG_BLOCK extern int register_blkdev(unsigned int, const char *); extern int unregister_blkdev(unsigned int, const char *); extern struct block_device *bdget(dev_t); @@ -1490,11 +1491,15 @@ extern void bd_forget(struct inode *inode); extern void bdput(struct block_device *); extern struct block_device *open_by_devnum(dev_t, unsigned); extern struct block_device *open_partition_by_devnum(dev_t, unsigned); -extern const struct file_operations def_blk_fops; extern const struct address_space_operations def_blk_aops; +#else +static inline void bd_forget(struct inode *inode) {} +#endif +extern const struct file_operations def_blk_fops; extern const struct file_operations def_chr_fops; extern const struct file_operations bad_sock_fops; extern const struct file_operations def_fifo_fops; +#ifdef CONFIG_BLOCK extern int ioctl_by_bdev(struct block_device *, unsigned, unsigned long); extern int blkdev_ioctl(struct inode *, struct file *, unsigned, unsigned long); extern long compat_blkdev_ioctl(struct file *, unsigned, unsigned long); @@ -1510,6 +1515,7 @@ extern void bd_release_from_disk(struct block_device *, struct gendisk *); #define bd_claim_by_disk(bdev, holder, disk) bd_claim(bdev, holder) #define bd_release_from_disk(bdev, disk) bd_release(bdev) #endif +#endif /* fs/char_dev.c */ #define CHRDEV_MAJOR_HASH_SIZE 255 @@ -1523,14 +1529,19 @@ extern int chrdev_open(struct inode *, struct file *); extern void chrdev_show(struct seq_file *,off_t); /* fs/block_dev.c */ -#define BLKDEV_MAJOR_HASH_SIZE 255 #define BDEVNAME_SIZE 32 /* Largest string for a blockdev identifier */ + +#ifdef CONFIG_BLOCK +#define BLKDEV_MAJOR_HASH_SIZE 255 extern const char *__bdevname(dev_t, char *buffer); extern const char *bdevname(struct block_device *bdev, char *buffer); extern struct block_device *lookup_bdev(const char *); extern struct block_device *open_bdev_excl(const char *, int, void *); extern void close_bdev_excl(struct block_device *); extern void blkdev_show(struct seq_file *,off_t); +#else +#define BLKDEV_MAJOR_HASH_SIZE 0 +#endif extern void init_special_inode(struct inode *, umode_t, dev_t); @@ -1544,6 +1555,7 @@ extern const struct file_operations rdwr_fifo_fops; extern int fs_may_remount_ro(struct super_block *); +#ifdef CONFIG_BLOCK /* * return READ, READA, or WRITE */ @@ -1555,9 +1567,10 @@ extern int fs_may_remount_ro(struct super_block *); #define bio_data_dir(bio) ((bio)->bi_rw & 1) extern int check_disk_change(struct block_device *); -extern int invalidate_inodes(struct super_block *); extern int __invalidate_device(struct block_device *); extern int invalidate_partition(struct gendisk *, int); +#endif +extern int invalidate_inodes(struct super_block *); unsigned long invalidate_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t end); unsigned long invalidate_inode_pages(struct address_space *mapping); @@ -1590,7 +1603,9 @@ extern void emergency_sync(void); extern void emergency_remount(void); extern int do_remount_sb(struct super_block *sb, int flags, void *data, int force); +#ifdef CONFIG_BLOCK extern sector_t bmap(struct inode *, sector_t); +#endif extern int notify_change(struct dentry *, struct iattr *); extern int permission(struct inode *, int, struct nameidata *); extern int generic_permission(struct inode *, int, @@ -1673,9 +1688,11 @@ static inline void insert_inode_hash(struct inode *inode) { extern struct file * get_empty_filp(void); extern void file_move(struct file *f, struct list_head *list); extern void file_kill(struct file *f); +#ifdef CONFIG_BLOCK struct bio; extern void submit_bio(int, struct bio *); extern int bdev_read_only(struct block_device *); +#endif extern int set_blocksize(struct block_device *, int); extern int sb_set_blocksize(struct super_block *, int); extern int sb_min_blocksize(struct super_block *, int); @@ -1756,6 +1773,7 @@ static inline void do_generic_file_read(struct file * filp, loff_t *ppos, actor); } +#ifdef CONFIG_BLOCK ssize_t __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, struct block_device *bdev, const struct iovec *iov, loff_t offset, unsigned long nr_segs, get_block_t get_block, dio_iodone_t end_io, @@ -1793,6 +1811,7 @@ static inline ssize_t blockdev_direct_IO_own_locking(int rw, struct kiocb *iocb, return __blockdev_direct_IO(rw, iocb, inode, bdev, iov, offset, nr_segs, get_block, end_io, DIO_OWN_LOCKING); } +#endif extern const struct file_operations generic_ro_fops; diff --git a/include/linux/genhd.h b/include/linux/genhd.h index e4af57e87c17..41f276fdd185 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -11,6 +11,8 @@ #include +#ifdef CONFIG_BLOCK + enum { /* These three have identical behaviour; use the second one if DOS FDISK gets confused about extended/logical partitions starting past cylinder 1023. */ @@ -420,3 +422,5 @@ static inline struct block_device *bdget_disk(struct gendisk *disk, int index) #endif #endif + +#endif diff --git a/include/linux/mpage.h b/include/linux/mpage.h index 517c098fde20..cc5fb75af78a 100644 --- a/include/linux/mpage.h +++ b/include/linux/mpage.h @@ -9,6 +9,7 @@ * (And no, it doesn't do the #ifdef __MPAGE_H thing, and it doesn't do * nested includes. Get it right in the .c file). */ +#ifdef CONFIG_BLOCK struct writeback_control; typedef int (writepage_t)(struct page *page, struct writeback_control *wbc); @@ -20,3 +21,5 @@ int mpage_writepages(struct address_space *mapping, struct writeback_control *wbc, get_block_t get_block); int mpage_writepage(struct page *page, get_block_t *get_block, struct writeback_control *wbc); + +#endif diff --git a/include/linux/raid/md.h b/include/linux/raid/md.h index eb3e547c8fee..c588709acbbc 100644 --- a/include/linux/raid/md.h +++ b/include/linux/raid/md.h @@ -53,6 +53,8 @@ #include #include +#ifdef CONFIG_MD + /* * Different major versions are not compatible. * Different minor versions are only downward compatible. @@ -95,5 +97,6 @@ extern void md_new_event(mddev_t *mddev); extern void md_update_sb(mddev_t * mddev); +#endif /* CONFIG_MD */ #endif diff --git a/include/linux/raid/md_k.h b/include/linux/raid/md_k.h index d28890295852..920b94fe31fa 100644 --- a/include/linux/raid/md_k.h +++ b/include/linux/raid/md_k.h @@ -18,6 +18,8 @@ /* and dm-bio-list.h is not under include/linux because.... ??? */ #include "../../../drivers/md/dm-bio-list.h" +#ifdef CONFIG_BLOCK + #define LEVEL_MULTIPATH (-4) #define LEVEL_LINEAR (-1) #define LEVEL_FAULTY (-5) @@ -362,5 +364,6 @@ static inline void safe_put_page(struct page *p) if (p) put_page(p); } +#endif /* CONFIG_BLOCK */ #endif -- cgit v1.2.3 From bcfd8d36151e531e1c6c731f1fbf792509a1c494 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Thu, 31 Aug 2006 12:56:06 +0200 Subject: [PATCH] CONFIG_BLOCK: blk_congestion_wait() fix Don't just do nothing: it'll cause busywaits all over writeback and page reclaim. For now, take a fixed-length nap. Will improve when NFS starts waking up throttled processes. Signed-off-by: Andrew Morton Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 3e36107d342a..1d79b8d4ca6d 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1,6 +1,7 @@ #ifndef _LINUX_BLKDEV_H #define _LINUX_BLKDEV_H +#include #include #include #include @@ -848,7 +849,7 @@ void kblockd_flush(void); static inline long blk_congestion_wait(int rw, long timeout) { - return timeout; + return io_schedule_timeout(timeout); } static inline long nr_blockdev_pages(void) @@ -856,7 +857,9 @@ static inline long nr_blockdev_pages(void) return 0; } -static inline void exit_io_context(void) {} +static inline void exit_io_context(void) +{ +} #endif /* CONFIG_BLOCK */ -- cgit v1.2.3 From 236561e5df009f79f1939e3ca269b9b6f18092f5 Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Sat, 30 Sep 2006 23:27:03 -0700 Subject: [PATCH] PCI quirks update This fixes two things Firstly someone mistakenly used "errata" for the singular. This causes Dave Woodhouse to emit diagnostics whenever the string is read, and so should be fixed. Secondly the AMD AGP tunnel has an erratum which causes hangs if you try and do direct PCI to AGP transfers in some cases. We have a flag for PCI/PCI failures but we need a different flag for this really as in this case we don't want to stop PCI/PCI transfers using things like IOAT and the new RAID offload work. I'll post some updates to make proper use of the PCIAGP flag in the media/video drivers to Mauro. Signed-off-by: Alan Cox Cc: David Woodhouse Signed-off-by: Greg Kroah-Hartman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pci.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 5c3a4176eb64..4431ce4e1e6f 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -787,12 +787,13 @@ enum pci_fixup_pass { void pci_fixup_device(enum pci_fixup_pass pass, struct pci_dev *dev); extern int pci_pci_problems; -#define PCIPCI_FAIL 1 +#define PCIPCI_FAIL 1 /* No PCI PCI DMA */ #define PCIPCI_TRITON 2 #define PCIPCI_NATOMA 4 #define PCIPCI_VIAETBF 8 #define PCIPCI_VSFX 16 -#define PCIPCI_ALIMAGIK 32 +#define PCIPCI_ALIMAGIK 32 /* Need low latency setting */ +#define PCIAGP_FAIL 64 /* No PCI to AGP DMA */ #endif /* __KERNEL__ */ #endif /* LINUX_PCI_H */ -- cgit v1.2.3 From f28c5edc06ecd8068b38b7662ad19f4d20d741af Mon Sep 17 00:00:00 2001 From: Keith Mannthey Date: Sat, 30 Sep 2006 23:27:04 -0700 Subject: [PATCH] hot-add-mem x86_64: fixup externs Fix up externs in memory_hotplug.c. Cleanup. Signed-off-by: Keith Mannthey Cc: KAMEZAWA Hiroyuki Cc: Andi Kleen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 2 ++ include/linux/mm.h | 2 ++ 2 files changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 218501cfaeb9..7b54666cea8e 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -172,5 +172,7 @@ static inline int __remove_pages(struct zone *zone, unsigned long start_pfn, extern int add_memory(int nid, u64 start, u64 size); extern int arch_add_memory(int nid, u64 start, u64 size); extern int remove_memory(u64 start, u64 size); +extern int sparse_add_one_section(struct zone *zone, unsigned long start_pfn, + int nr_pages); #endif /* __LINUX_MEMORY_HOTPLUG_H */ diff --git a/include/linux/mm.h b/include/linux/mm.h index 4edf1934e5ca..b7966ab8cb6a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -946,6 +946,8 @@ extern void mem_init(void); extern void show_mem(void); extern void si_meminfo(struct sysinfo * val); extern void si_meminfo_node(struct sysinfo *val, int nid); +extern void zonetable_add(struct zone *zone, int nid, enum zone_type zid, + unsigned long pfn, unsigned long size); #ifdef CONFIG_NUMA extern void setup_per_cpu_pageset(void); -- cgit v1.2.3 From 53947027ad90542ddb2bb746e3175827c270610a Mon Sep 17 00:00:00 2001 From: Keith Mannthey Date: Sat, 30 Sep 2006 23:27:08 -0700 Subject: [PATCH] hot-add-mem x86_64: use CONFIG_MEMORY_HOTPLUG_SPARSE Migate CONFIG_MEMORY_HOTPLUG to CONFIG_MEMORY_HOTPLUG_SPARSE where needed. Signed-off-by: Keith Mannthey Cc: KAMEZAWA Hiroyuki Cc: Andi Kleen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memory.h b/include/linux/memory.h index 8f04143ca363..654ef5544878 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -57,7 +57,7 @@ struct memory_block { struct notifier_block; struct mem_section; -#ifndef CONFIG_MEMORY_HOTPLUG +#ifndef CONFIG_MEMORY_HOTPLUG_SPARSE static inline int memory_dev_init(void) { return 0; @@ -78,7 +78,7 @@ extern int remove_memory_block(unsigned long, struct mem_section *, int); #define CONFIG_MEM_BLOCK_SIZE (PAGES_PER_SECTION< Date: Sat, 30 Sep 2006 23:27:11 -0700 Subject: [PATCH] Generic boolean This patch defines: * a generic boolean-type, named 'bool' * aliases to 0 and 1, named 'false' and 'true' Removing colliding definitions of 'bool', 'false' and 'true'. Signed-off-by: Richard Knutsson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/stddef.h | 6 ++++++ include/linux/types.h | 2 ++ 2 files changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/stddef.h b/include/linux/stddef.h index ea65dfb60cd8..6a40c76bdcf1 100644 --- a/include/linux/stddef.h +++ b/include/linux/stddef.h @@ -11,6 +11,12 @@ #endif #ifdef __KERNEL__ + +enum { + false = 0, + true = 1 +}; + #undef offsetof #ifdef __compiler_offsetof #define offsetof(TYPE,MEMBER) __compiler_offsetof(TYPE,MEMBER) diff --git a/include/linux/types.h b/include/linux/types.h index 3f235660a3cd..406d4ae57631 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -33,6 +33,8 @@ typedef __kernel_clockid_t clockid_t; typedef __kernel_mqd_t mqd_t; #ifdef __KERNEL__ +typedef _Bool bool; + typedef __kernel_uid32_t uid_t; typedef __kernel_gid32_t gid_t; typedef __kernel_uid16_t uid16_t; -- cgit v1.2.3 From 5c87579e65ee4f419b2369407f82326d38b5d2d8 Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Sat, 30 Sep 2006 23:27:17 -0700 Subject: [PATCH] maximum latency tracking infrastructure Add infrastructure to track "maximum allowable latency" for power saving policies. The reason for adding this infrastructure is that power management in the idle loop needs to make a tradeoff between latency and power savings (deeper power save modes have a longer latency to running code again). The code that today makes this tradeoff just does a rather simple algorithm; however this is not good enough: There are devices and use cases where a lower latency is required than that the higher power saving states provide. An example would be audio playback, but another example is the ipw2100 wireless driver that right now has a very direct and ugly acpi hook to disable some higher power states randomly when it gets certain types of error. The proposed solution is to have an interface where drivers can * announce the maximum latency (in microseconds) that they can deal with * modify this latency * give up their constraint and a function where the code that decides on power saving strategy can query the current global desired maximum. This patch has a user of each side: on the consumer side, ACPI is patched to use this, on the producer side the ipw2100 driver is patched. A generic maximum latency is also registered of 2 timer ticks (more and you lose accurate time tracking after all). While the existing users of the patch are x86 specific, the infrastructure is not. I'd like to ask the arch maintainers of other architectures if the infrastructure is generic enough for their use (assuming the architecture has such a tradeoff as concept at all), and the sound/multimedia driver owners to look at the driver facing API to see if this is something they can use. [akpm@osdl.org: cleanups] Signed-off-by: Arjan van de Ven Signed-off-by: Ingo Molnar Acked-by: Jesse Barnes Cc: "Brown, Len" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/latency.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) create mode 100644 include/linux/latency.h (limited to 'include/linux') diff --git a/include/linux/latency.h b/include/linux/latency.h new file mode 100644 index 000000000000..c08b52bb55b0 --- /dev/null +++ b/include/linux/latency.h @@ -0,0 +1,25 @@ +/* + * latency.h: Explicit system-wide latency-expectation infrastructure + * + * (C) Copyright 2006 Intel Corporation + * Author: Arjan van de Ven + * + */ + +#ifndef _INCLUDE_GUARD_LATENCY_H_ +#define _INCLUDE_GUARD_LATENCY_H_ + +#include + +void set_acceptable_latency(char *identifier, int usecs); +void modify_acceptable_latency(char *identifier, int usecs); +void remove_acceptable_latency(char *identifier); +void synchronize_acceptable_latency(void); +int system_latency_constraint(void); + +int register_latency_notifier(struct notifier_block * nb); +int unregister_latency_notifier(struct notifier_block * nb); + +#define INFINITE_LATENCY 1000000 + +#endif -- cgit v1.2.3 From 1a2f67b459bb7846d4a15924face63eb2683acc2 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Sat, 30 Sep 2006 23:27:20 -0700 Subject: [PATCH] kmemdup: introduce One of idiomatic ways to duplicate a region of memory is dst = kmalloc(len, GFP_KERNEL); if (!dst) return -ENOMEM; memcpy(dst, src, len); which is neat code except a programmer needs to write size twice. Which sometimes leads to mistakes. If len passed to kmalloc is smaller that len passed to memcpy, it's straight overwrite-beyond-end. If len passed to memcpy is smaller than len passed to kmalloc, it's either a) legit behaviour ;-), or b) cloned buffer will contain garbage in second half. Slight trolling of commit lists shows several duplications bugs done exactly because of diverged lenghts: Linux: [CRYPTO]: Fix memcpy/memset args. [PATCH] memcpy/memset fixes OpenBSD: kerberosV/src/lib/asn1: der_copy.c:1.4 If programmer is given only one place to play with lengths, I believe, such mistakes could be avoided. With kmemdup, the snippet above will be rewritten as: dst = kmemdup(src, len, GFP_KERNEL); if (!dst) return -ENOMEM; This also leads to smaller code (kzalloc effect). Quick grep shows 200+ places where kmemdup() can be used. Signed-off-by: Alexey Dobriyan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/string.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/string.h b/include/linux/string.h index e4c755860316..4f69ef9e6eb5 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -99,6 +99,7 @@ extern void * memchr(const void *,int,__kernel_size_t); #endif extern char *kstrdup(const char *s, gfp_t gfp); +extern void *kmemdup(const void *src, size_t len, gfp_t gfp); #ifdef __cplusplus } -- cgit v1.2.3 From 82b0547cfae1fb2ee26cad588f6d49a347d24740 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Sat, 30 Sep 2006 23:27:22 -0700 Subject: [PATCH] Create fs/utimes.c * fs/open.c is getting bit crowdy * preparation to lutimes(2) Signed-off-by: Alexey Dobriyan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/namei.h | 1 + include/linux/utime.h | 2 ++ 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/namei.h b/include/linux/namei.h index c6470ba00668..f5f19606effb 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -1,6 +1,7 @@ #ifndef _LINUX_NAMEI_H #define _LINUX_NAMEI_H +#include #include struct vfsmount; diff --git a/include/linux/utime.h b/include/linux/utime.h index c6bf27b7897e..640be6a1959e 100644 --- a/include/linux/utime.h +++ b/include/linux/utime.h @@ -1,6 +1,8 @@ #ifndef _LINUX_UTIME_H #define _LINUX_UTIME_H +#include + struct utimbuf { time_t actime; time_t modtime; -- cgit v1.2.3 From cb10dc9ac7eea2c891df6b79b9ef1fbe59cb5429 Mon Sep 17 00:00:00 2001 From: Paul Fulghum Date: Sat, 30 Sep 2006 23:27:45 -0700 Subject: [PATCH] synclink_gt: add bisync and monosync modes Add bisync and monosync serial protocol support to the synclink_gt driver. Signed-off-by: Paul Fulghum Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/synclink.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/synclink.h b/include/linux/synclink.h index 0577f5284cbc..c8b042667af1 100644 --- a/include/linux/synclink.h +++ b/include/linux/synclink.h @@ -1,7 +1,7 @@ /* * SyncLink Multiprotocol Serial Adapter Driver * - * $Id: synclink.h,v 3.13 2006/05/23 18:25:06 paulkf Exp $ + * $Id: synclink.h,v 3.14 2006/07/17 20:15:43 paulkf Exp $ * * Copyright (C) 1998-2000 by Microgate Corporation * @@ -124,6 +124,8 @@ #define MGSL_MODE_ASYNC 1 #define MGSL_MODE_HDLC 2 +#define MGSL_MODE_MONOSYNC 3 +#define MGSL_MODE_BISYNC 4 #define MGSL_MODE_RAW 6 #define MGSL_BUS_TYPE_ISA 1 -- cgit v1.2.3 From 89bbc03c01f68e627a2b120963f136e2815f0d84 Mon Sep 17 00:00:00 2001 From: Thomas Petazzoni Date: Sat, 30 Sep 2006 23:27:54 -0700 Subject: [PATCH] Prevent multiple inclusion of linux/sysrq.h Prevent multiple inclusions of include/linux/sysrq.h using traditional #ifndef..#endif. Signed-off-by: Thomas Petazzoni Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sysrq.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sysrq.h b/include/linux/sysrq.h index 4812ff60561c..e657e523b9bf 100644 --- a/include/linux/sysrq.h +++ b/include/linux/sysrq.h @@ -11,6 +11,8 @@ * based upon discusions in irc://irc.openprojects.net/#kernelnewbies */ +#ifndef _LINUX_SYSRQ_H +#define _LINUX_SYSRQ_H struct pt_regs; struct tty_struct; @@ -57,3 +59,5 @@ static inline int __reterr(void) #define unregister_sysrq_key(ig,nore) __reterr() #endif + +#endif /* _LINUX_SYSRQ_H */ -- cgit v1.2.3 From 54f67f631dfc25ca7a8b19200e34013abc974337 Mon Sep 17 00:00:00 2001 From: Petr Vandrovec Date: Sat, 30 Sep 2006 23:27:55 -0700 Subject: [PATCH] Move ncpfs 32bit compat ioctl to ncpfs The ncp specific compat ioctls are clearly local to one file system, so the code can better live there. This version of the patch moves everything into the generic ioctl handler and uses it for both 32 and 64 bit calls. Signed-off-by: Arnd Bergmann Signed-off-by: Petr Vandrovec Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compat_ioctl.h | 12 ------------ include/linux/ncp_fs.h | 1 + 2 files changed, 1 insertion(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compat_ioctl.h b/include/linux/compat_ioctl.h index d61ef5951538..d5b7abc4f409 100644 --- a/include/linux/compat_ioctl.h +++ b/include/linux/compat_ioctl.h @@ -569,18 +569,6 @@ COMPATIBLE_IOCTL(RAW_SETBIND) COMPATIBLE_IOCTL(RAW_GETBIND) /* SMB ioctls which do not need any translations */ COMPATIBLE_IOCTL(SMB_IOC_NEWCONN) -/* NCP ioctls which do not need any translations */ -COMPATIBLE_IOCTL(NCP_IOC_CONN_LOGGED_IN) -COMPATIBLE_IOCTL(NCP_IOC_SIGN_INIT) -COMPATIBLE_IOCTL(NCP_IOC_SIGN_WANTED) -COMPATIBLE_IOCTL(NCP_IOC_SET_SIGN_WANTED) -COMPATIBLE_IOCTL(NCP_IOC_LOCKUNLOCK) -COMPATIBLE_IOCTL(NCP_IOC_GETROOT) -COMPATIBLE_IOCTL(NCP_IOC_SETROOT) -COMPATIBLE_IOCTL(NCP_IOC_GETCHARSETS) -COMPATIBLE_IOCTL(NCP_IOC_SETCHARSETS) -COMPATIBLE_IOCTL(NCP_IOC_GETDENTRYTTL) -COMPATIBLE_IOCTL(NCP_IOC_SETDENTRYTTL) /* Little a */ COMPATIBLE_IOCTL(ATMSIGD_CTRL) COMPATIBLE_IOCTL(ATMARPD_CTRL) diff --git a/include/linux/ncp_fs.h b/include/linux/ncp_fs.h index 02e352be717e..0ea7f89e613c 100644 --- a/include/linux/ncp_fs.h +++ b/include/linux/ncp_fs.h @@ -212,6 +212,7 @@ void ncp_date_unix2dos(int unix_date, __le16 * time, __le16 * date); /* linux/fs/ncpfs/ioctl.c */ int ncp_ioctl(struct inode *, struct file *, unsigned int, unsigned long); +long ncp_compat_ioctl(struct file *, unsigned int, unsigned long); /* linux/fs/ncpfs/sock.c */ int ncp_request2(struct ncp_server *server, int function, -- cgit v1.2.3 From c69c31270c35a6b8421a8e4ba81de1247ac6df95 Mon Sep 17 00:00:00 2001 From: Corey Minyard Date: Sat, 30 Sep 2006 23:27:56 -0700 Subject: [PATCH] IPMI: per-channel command registration This patch adds the ability to register for a command per-channel in the IPMI driver. If your BMC supports multiple channels, incoming messages can be useful to have the ability to register to receive commands on a specific channel instead the current behaviour of all channels. Signed-off-by: David Barksdale Signed-off-by: Corey Minyard Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ipmi.h | 48 ++++++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 44 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ipmi.h b/include/linux/ipmi.h index d09fbeabf1dc..796ca009fd46 100644 --- a/include/linux/ipmi.h +++ b/include/linux/ipmi.h @@ -148,6 +148,13 @@ struct ipmi_lan_addr #define IPMI_BMC_CHANNEL 0xf #define IPMI_NUM_CHANNELS 0x10 +/* + * Used to signify an "all channel" bitmask. This is more than the + * actual number of channels because this is used in userland and + * will cover us if the number of channels is extended. + */ +#define IPMI_CHAN_ALL (~0) + /* * A raw IPMI message without any addressing. This covers both @@ -350,18 +357,21 @@ int ipmi_request_supply_msgs(ipmi_user_t user, /* * When commands come in to the SMS, the user can register to receive - * them. Only one user can be listening on a specific netfn/cmd pair + * them. Only one user can be listening on a specific netfn/cmd/chan tuple * at a time, you will get an EBUSY error if the command is already * registered. If a command is received that does not have a user * registered, the driver will automatically return the proper - * error. + * error. Channels are specified as a bitfield, use IPMI_CHAN_ALL to + * mean all channels. */ int ipmi_register_for_cmd(ipmi_user_t user, unsigned char netfn, - unsigned char cmd); + unsigned char cmd, + unsigned int chans); int ipmi_unregister_for_cmd(ipmi_user_t user, unsigned char netfn, - unsigned char cmd); + unsigned char cmd, + unsigned int chans); /* * Allow run-to-completion mode to be set for the interface of @@ -571,6 +581,36 @@ struct ipmi_cmdspec #define IPMICTL_UNREGISTER_FOR_CMD _IOR(IPMI_IOC_MAGIC, 15, \ struct ipmi_cmdspec) +/* + * Register to get commands from other entities on specific channels. + * This way, you can only listen on specific channels, or have messages + * from some channels go to one place and other channels to someplace + * else. The chans field is a bitmask, (1 << channel) for each channel. + * It may be IPMI_CHAN_ALL for all channels. + */ +struct ipmi_cmdspec_chans +{ + unsigned int netfn; + unsigned int cmd; + unsigned int chans; +}; + +/* + * Register to receive a specific command on specific channels. error values: + * - EFAULT - an address supplied was invalid. + * - EBUSY - One of the netfn/cmd/chans supplied was already in use. + * - ENOMEM - could not allocate memory for the entry. + */ +#define IPMICTL_REGISTER_FOR_CMD_CHANS _IOR(IPMI_IOC_MAGIC, 28, \ + struct ipmi_cmdspec_chans) +/* + * Unregister some netfn/cmd/chans. error values: + * - EFAULT - an address supplied was invalid. + * - ENOENT - None of the netfn/cmd/chans were found registered for this user. + */ +#define IPMICTL_UNREGISTER_FOR_CMD_CHANS _IOR(IPMI_IOC_MAGIC, 29, \ + struct ipmi_cmdspec_chans) + /* * Set whether this interface receives events. Note that the first * user registered for events will get all pending events for the -- cgit v1.2.3 From 3a2711116073db258224afd2cc0f478bdf305575 Mon Sep 17 00:00:00 2001 From: Rolf Eike Beer Date: Sat, 30 Sep 2006 23:28:09 -0700 Subject: [PATCH] Remove BUG_ON(unlikely) in include/linux/aio.h BUG_ON() does this unlikely check itself, as bugs in Linux are unlikely anyway :) Signed-off-by: Rolf Eike Beer Acked-by: Zach Brown Acked-by: Benjamin LaHaise Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/aio.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/aio.h b/include/linux/aio.h index 00c8efa95cc3..8a0193385a9b 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -213,11 +213,11 @@ int FASTCALL(io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb, struct iocb *iocb)); #define get_ioctx(kioctx) do { \ - BUG_ON(unlikely(atomic_read(&(kioctx)->users) <= 0)); \ + BUG_ON(atomic_read(&(kioctx)->users) <= 0); \ atomic_inc(&(kioctx)->users); \ } while (0) #define put_ioctx(kioctx) do { \ - BUG_ON(unlikely(atomic_read(&(kioctx)->users) <= 0)); \ + BUG_ON(atomic_read(&(kioctx)->users) <= 0); \ if (unlikely(atomic_dec_and_test(&(kioctx)->users))) \ __put_ioctx(kioctx); \ } while (0) -- cgit v1.2.3 From ff8371ac9a5a55c956991fed8e5f58640c7a32f3 Mon Sep 17 00:00:00 2001 From: David Brownell Date: Sat, 30 Sep 2006 23:28:17 -0700 Subject: [PATCH] constify rtc_class_ops: update drivers Update RTC framework so that drivers can constify their method tables, moving them from ".data" to ".rodata". Then update the drivers. Signed-off-by: David Brownell Cc: Alessandro Zummo 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 5371e4e74595..b89f09357054 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -141,7 +141,7 @@ struct rtc_device int id; char name[RTC_DEVICE_NAME_SIZE]; - struct rtc_class_ops *ops; + const struct rtc_class_ops *ops; struct mutex ops_lock; struct class_device *rtc_dev; @@ -172,7 +172,7 @@ struct rtc_device extern struct rtc_device *rtc_device_register(const char *name, struct device *dev, - struct rtc_class_ops *ops, + const struct rtc_class_ops *ops, struct module *owner); extern void rtc_device_unregister(struct rtc_device *rdev); extern int rtc_interface_register(struct class_interface *intf); -- cgit v1.2.3 From c902e0a0102f1095eec4b3511c13c84ca2bc4577 Mon Sep 17 00:00:00 2001 From: Josh Triplett Date: Sat, 30 Sep 2006 23:28:21 -0700 Subject: [PATCH] Pass sparse the lock expression given to lock annotations The lock annotation macros __acquires, __releases, __acquire, and __release all currently throw away the lock expression passed as an argument. Now that sparse can parse __context__ and __attribute__((context)) with a context expression, pass the lock expression down to sparse as the context expression. This requires a version of sparse from GIT commit 37475a6c1c3e66219e68d912d5eb833f4098fd72 or later. Signed-off-by: Josh Triplett Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compiler.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 0780de440220..538423d4a865 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -10,10 +10,10 @@ # define __force __attribute__((force)) # define __nocast __attribute__((nocast)) # define __iomem __attribute__((noderef, address_space(2))) -# define __acquires(x) __attribute__((context(0,1))) -# define __releases(x) __attribute__((context(1,0))) -# define __acquire(x) __context__(1) -# define __release(x) __context__(-1) +# define __acquires(x) __attribute__((context(x,0,1))) +# define __releases(x) __attribute__((context(x,1,0))) +# define __acquire(x) __context__(x,1) +# define __release(x) __context__(x,-1) # define __cond_lock(x,c) ((c) ? ({ __acquire(x); 1; }) : 0) extern void __chk_user_ptr(void __user *); extern void __chk_io_ptr(void __iomem *); -- cgit v1.2.3 From 4c7ee8de956fc250fe31e2fa91f6da980fabe317 Mon Sep 17 00:00:00 2001 From: john stultz Date: Sat, 30 Sep 2006 23:28:22 -0700 Subject: [PATCH] NTP: Move all the NTP related code to ntp.c Move all the NTP related code to ntp.c [akpm@osdl.org: cleanups, build fix] Signed-off-by: John Stultz Cc: Ingo Molnar Cc: Roman Zippel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/timex.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/timex.h b/include/linux/timex.h index d543d3871e38..2a21485bf183 100644 --- a/include/linux/timex.h +++ b/include/linux/timex.h @@ -294,11 +294,15 @@ extern void register_time_interpolator(struct time_interpolator *); extern void unregister_time_interpolator(struct time_interpolator *); extern void time_interpolator_reset(void); extern unsigned long time_interpolator_get_offset(void); +extern void time_interpolator_update(long delta_nsec); #else /* !CONFIG_TIME_INTERPOLATION */ -static inline void -time_interpolator_reset(void) +static inline void time_interpolator_reset(void) +{ +} + +static inline void time_interpolator_update(long delta_nsec) { } @@ -309,6 +313,8 @@ time_interpolator_reset(void) /* Returns how long ticks are at present, in ns / 2^(SHIFT_SCALE-10). */ extern u64 current_tick_length(void); +extern void second_overflow(void); +extern void update_ntp_one_tick(void); extern int do_adjtimex(struct timex *); #endif /* KERNEL */ -- cgit v1.2.3 From b0ee75561beadc4db4d9a899c8ef4a7db50aa0ab Mon Sep 17 00:00:00 2001 From: Roman Zippel Date: Sat, 30 Sep 2006 23:28:22 -0700 Subject: [PATCH] ntp: add ntp_update_frequency This introduces ntp_update_frequency() and deinlines ntp_clear() (as it's not performance critical). ntp_update_frequency() calculates the base tick length using tick_usec and adds a base adjustment, in case the frequency doesn't divide evenly by HZ. Signed-off-by: Roman Zippel Cc: john stultz Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/timex.h | 14 ++------------ 1 file changed, 2 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/timex.h b/include/linux/timex.h index 2a21485bf183..b589c8218bb9 100644 --- a/include/linux/timex.h +++ b/include/linux/timex.h @@ -219,18 +219,8 @@ extern long time_reftime; /* time at last adjustment (s) */ extern long time_adjust; /* The amount of adjtime left */ extern long time_next_adjust; /* Value for time_adjust at next tick */ -/** - * ntp_clear - Clears the NTP state variables - * - * Must be called while holding a write on the xtime_lock - */ -static inline void ntp_clear(void) -{ - time_adjust = 0; /* stop active adjtime() */ - time_status |= STA_UNSYNC; - time_maxerror = NTP_PHASE_LIMIT; - time_esterror = NTP_PHASE_LIMIT; -} +extern void ntp_clear(void); +extern void ntp_update_frequency(void); /** * ntp_synced - Returns 1 if the NTP status is not UNSYNC -- cgit v1.2.3 From 3d3675cc3d04d7fd4bb11e8c1ea79e5ade4f5e44 Mon Sep 17 00:00:00 2001 From: Roman Zippel Date: Sat, 30 Sep 2006 23:28:25 -0700 Subject: [PATCH] ntp: prescale time_offset This converts time_offset into a scaled per tick value. This avoids now completely the crude compensation in second_overflow(). Signed-off-by: Roman Zippel Cc: john stultz Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/timex.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/timex.h b/include/linux/timex.h index b589c8218bb9..1cde6f6a2712 100644 --- a/include/linux/timex.h +++ b/include/linux/timex.h @@ -89,7 +89,7 @@ * FINENSEC is 1 ns in SHIFT_UPDATE units of the time_phase variable. */ #define SHIFT_SCALE 22 /* phase scale (shift) */ -#define SHIFT_UPDATE (SHIFT_KG + MAXTC) /* time offset scale (shift) */ +#define SHIFT_UPDATE (SHIFT_HZ + 1) /* time offset scale (shift) */ #define SHIFT_USEC 16 /* frequency offset scale (shift) */ #define FINENSEC (1L << (SHIFT_SCALE - 10)) /* ~1 ns in phase units */ -- cgit v1.2.3 From 8f807f8d2137ba728d22820103131038639b68a9 Mon Sep 17 00:00:00 2001 From: Roman Zippel Date: Sat, 30 Sep 2006 23:28:25 -0700 Subject: [PATCH] ntp: add time_adjust to tick length This folds update_ntp_one_tick() into second_overflow() and adds time_adjust to the tick length, this makes time_next_adjust unnecessary. This slightly changes the adjtime() behaviour, instead of applying it to the next tick, it's applied to the next second. Signed-off-by: Roman Zippel Cc: john stultz Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/timex.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/timex.h b/include/linux/timex.h index 1cde6f6a2712..b5f297e17668 100644 --- a/include/linux/timex.h +++ b/include/linux/timex.h @@ -217,7 +217,6 @@ extern long time_freq; /* frequency offset (scaled ppm) */ extern long time_reftime; /* time at last adjustment (s) */ extern long time_adjust; /* The amount of adjtime left */ -extern long time_next_adjust; /* Value for time_adjust at next tick */ extern void ntp_clear(void); extern void ntp_update_frequency(void); -- cgit v1.2.3 From 97eebe138caaf78354b1fad233e63bafdcc4fd54 Mon Sep 17 00:00:00 2001 From: Roman Zippel Date: Sat, 30 Sep 2006 23:28:26 -0700 Subject: [PATCH] ntp: remove time_tolerance time_tolerance isn't changed at all in the kernel, so simply remove it, this simplifies the next patch, as it avoids a number of conversions. Signed-off-by: Roman Zippel Cc: john stultz Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/timex.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/timex.h b/include/linux/timex.h index b5f297e17668..7715b4c0caf9 100644 --- a/include/linux/timex.h +++ b/include/linux/timex.h @@ -208,7 +208,6 @@ extern int time_state; /* clock status */ extern int time_status; /* clock synchronization status bits */ extern long time_offset; /* time adjustment (us) */ extern long time_constant; /* pll time constant */ -extern long time_tolerance; /* frequency tolerance (ppm) */ extern long time_precision; /* clock precision (us) */ extern long time_maxerror; /* maximum error */ extern long time_esterror; /* estimated error */ -- cgit v1.2.3 From 04b617e71e363e640e88be1e43f53fa6a3afef9f Mon Sep 17 00:00:00 2001 From: Roman Zippel Date: Sat, 30 Sep 2006 23:28:27 -0700 Subject: [PATCH] ntp: convert time_freq to nsec value This converts time_freq to a scaled nsec value and adds around 6bit of extra resolution. This pushes the time_freq to its 32bit limits so the calculatons have to be done with 64bit. Signed-off-by: Roman Zippel Cc: john stultz Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/timex.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/timex.h b/include/linux/timex.h index 7715b4c0caf9..671609ee1a3d 100644 --- a/include/linux/timex.h +++ b/include/linux/timex.h @@ -91,10 +91,12 @@ #define SHIFT_SCALE 22 /* phase scale (shift) */ #define SHIFT_UPDATE (SHIFT_HZ + 1) /* time offset scale (shift) */ #define SHIFT_USEC 16 /* frequency offset scale (shift) */ +#define SHIFT_NSEC 12 /* kernel frequency offset scale */ #define FINENSEC (1L << (SHIFT_SCALE - 10)) /* ~1 ns in phase units */ #define MAXPHASE 512000L /* max phase error (us) */ #define MAXFREQ (512L << SHIFT_USEC) /* max frequency error (ppm) */ +#define MAXFREQ_NSEC (512000L << SHIFT_NSEC) /* max frequency error (ppb) */ #define MINSEC 16L /* min interval between updates (s) */ #define MAXSEC 1200L /* max interval between updates (s) */ #define NTP_PHASE_LIMIT (MAXPHASE << 5) /* beyond max. dispersion */ -- cgit v1.2.3 From f19923937321244e7dc334767eb4b67e0e3d5c74 Mon Sep 17 00:00:00 2001 From: Roman Zippel Date: Sat, 30 Sep 2006 23:28:28 -0700 Subject: [PATCH] ntp: convert to the NTP4 reference model This converts the kernel ntp model into a model which matches the nanokernel reference implementations. The previous patches already increased the resolution and precision of the computations, so that this conversion becomes quite simple. explains: The original NTP kernel interface was defined in units of microseconds. That's what Linux implements. As computers have gotten faster and can now split microseconds easily, a new kernel interface using nanosecond units was defined ("the nanokernel", confusing as that name is to OS hackers), and there's an STA_NANO bit in the adjtimex() status field to tell the application which units it's using. The current ntpd supports both, but Linux loses some possible timing resolution because of quantization effects, and the ntpd hackers would really like to be able to drop the backwards compatibility code. Ulrich Windl has been maintaining a patch set to do the conversion for years, but it's hard to keep in sync. Signed-off-by: Roman Zippel Cc: john stultz Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/timex.h | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/timex.h b/include/linux/timex.h index 671609ee1a3d..ac808f13fa0e 100644 --- a/include/linux/timex.h +++ b/include/linux/timex.h @@ -69,10 +69,9 @@ * zero to MAXTC, the PLL will converge in 15 minutes to 16 hours, * respectively. */ -#define SHIFT_KG 6 /* phase factor (shift) */ -#define SHIFT_KF 16 /* PLL frequency factor (shift) */ -#define SHIFT_KH 2 /* FLL frequency factor (shift) */ -#define MAXTC 6 /* maximum time constant (shift) */ +#define SHIFT_PLL 4 /* PLL frequency factor (shift) */ +#define SHIFT_FLL 2 /* FLL frequency factor (shift) */ +#define MAXTC 10 /* maximum time constant (shift) */ /* * The SHIFT_SCALE define establishes the decimal point of the time_phase @@ -97,8 +96,8 @@ #define MAXPHASE 512000L /* max phase error (us) */ #define MAXFREQ (512L << SHIFT_USEC) /* max frequency error (ppm) */ #define MAXFREQ_NSEC (512000L << SHIFT_NSEC) /* max frequency error (ppb) */ -#define MINSEC 16L /* min interval between updates (s) */ -#define MAXSEC 1200L /* max interval between updates (s) */ +#define MINSEC 256 /* min interval between updates (s) */ +#define MAXSEC 2048 /* max interval between updates (s) */ #define NTP_PHASE_LIMIT (MAXPHASE << 5) /* beyond max. dispersion */ /* -- cgit v1.2.3 From 0883d899ef862c1b0f8b2c2d38098470c193a3dd Mon Sep 17 00:00:00 2001 From: Roman Zippel Date: Sat, 30 Sep 2006 23:28:29 -0700 Subject: [PATCH] ntp: cleanup defines and comments Remove a few unused defines and remove obsolete information from comments. Signed-off-by: Roman Zippel Cc: john stultz Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/timex.h | 13 +++---------- 1 file changed, 3 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/timex.h b/include/linux/timex.h index ac808f13fa0e..261381b5da82 100644 --- a/include/linux/timex.h +++ b/include/linux/timex.h @@ -74,24 +74,17 @@ #define MAXTC 10 /* maximum time constant (shift) */ /* - * The SHIFT_SCALE define establishes the decimal point of the time_phase - * variable which serves as an extension to the low-order bits of the - * system clock variable. The SHIFT_UPDATE define establishes the decimal - * point of the time_offset variable which represents the current offset - * with respect to standard time. The FINENSEC define represents 1 nsec in - * scaled units. + * The SHIFT_UPDATE define establishes the decimal point of the + * time_offset variable which represents the current offset with + * respect to standard time. * * SHIFT_USEC defines the scaling (shift) of the time_freq and * time_tolerance variables, which represent the current frequency * offset and maximum frequency tolerance. - * - * FINENSEC is 1 ns in SHIFT_UPDATE units of the time_phase variable. */ -#define SHIFT_SCALE 22 /* phase scale (shift) */ #define SHIFT_UPDATE (SHIFT_HZ + 1) /* time offset scale (shift) */ #define SHIFT_USEC 16 /* frequency offset scale (shift) */ #define SHIFT_NSEC 12 /* kernel frequency offset scale */ -#define FINENSEC (1L << (SHIFT_SCALE - 10)) /* ~1 ns in phase units */ #define MAXPHASE 512000L /* max phase error (us) */ #define MAXFREQ (512L << SHIFT_USEC) /* max frequency error (ppm) */ -- cgit v1.2.3 From 70bc42f90a3f4721c89dbe865e6c95da8565b41c Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Sat, 30 Sep 2006 23:28:29 -0700 Subject: [PATCH] kernel/time/ntp.c: possible cleanups This patch contains the following possible cleanups: - make the following needlessly global function static: - ntp_update_frequency() - make the following needlessly global variables static: - time_state - time_offset - time_constant - time_reftime - remove the following read-only global variable: - time_precision Signed-off-by: Adrian Bunk Cc: Roman Zippel Cc: john stultz Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/timex.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/timex.h b/include/linux/timex.h index 261381b5da82..049dfe4a11f2 100644 --- a/include/linux/timex.h +++ b/include/linux/timex.h @@ -198,21 +198,15 @@ extern int tickadj; /* amount of adjustment per tick */ /* * phase-lock loop variables */ -extern int time_state; /* clock status */ extern int time_status; /* clock synchronization status bits */ -extern long time_offset; /* time adjustment (us) */ -extern long time_constant; /* pll time constant */ -extern long time_precision; /* clock precision (us) */ extern long time_maxerror; /* maximum error */ extern long time_esterror; /* estimated error */ extern long time_freq; /* frequency offset (scaled ppm) */ -extern long time_reftime; /* time at last adjustment (s) */ extern long time_adjust; /* The amount of adjtime left */ extern void ntp_clear(void); -extern void ntp_update_frequency(void); /** * ntp_synced - Returns 1 if the NTP status is not UNSYNC -- cgit v1.2.3 From e1fabd3ccf02901374bffa434e0af472749a5bd9 Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Sat, 30 Sep 2006 23:28:40 -0700 Subject: [PATCH] reiserfs: fix is_reusable bitmap check to not traverse the bitmap info array There is a check in is_reusable to determine if a particular block is a bitmap block. It verifies this by going through the array of bitmap block buffer heads and comparing the block number to each one. Bitmap blocks are at defined locations on the disk in both old and current formats. Simply checking against the known good values is enough. This is a trivial optimization for a non-production codepath, but this is the first in a series of patches that will ultimately remove the buffer heads from that array. Signed-off-by: Jeff Mahoney Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/reiserfs_fs_sb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/reiserfs_fs_sb.h b/include/linux/reiserfs_fs_sb.h index 31b4c0bd4fa0..4f21ad388c79 100644 --- a/include/linux/reiserfs_fs_sb.h +++ b/include/linux/reiserfs_fs_sb.h @@ -414,6 +414,7 @@ struct reiserfs_sb_info { /* Definitions of reiserfs on-disk properties: */ #define REISERFS_3_5 0 #define REISERFS_3_6 1 +#define REISERFS_OLD_FORMAT 2 enum reiserfs_mount_options { /* Mount options */ -- cgit v1.2.3 From 6f01046b35d940079822827498a7dd6d3eec8c6b Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Sat, 30 Sep 2006 23:28:43 -0700 Subject: [PATCH] reiserfs: reorganize bitmap loading functions This patch moves the bitmap loading code from super.c to bitmap.c The code is also restructured somewhat. The only difference between new format bitmaps and old format bitmaps is where they are. That's a two liner before loading the block to use the correct one. There's no need for an entirely separate code path. The load path is generally the same, with the pattern being to throw out a bunch of requests and then wait for them, then cache the metadata from the contents. Again, like the previous patches, the purpose is to set up for later ones. Update: There was a bug in the previously posted version of this that resulted in corruption. The problem was that bitmap 0 on new format file systems must be treated specially, and wasn't. A stupid bug with an easy fix. This is hopefully the last fix for the disaster that is the reiserfs bitmap patch set. If a bitmap block was full, first_zero_hint would end up at zero since it would never be changed from it's zeroed out value. This just sets it beyond the end of the bitmap block. If any bits are freed, it will be reset to a valid bit. When info->free_count = 0, then we already know it's full. Signed-off-by: Jeff Mahoney Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/reiserfs_fs.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h index 9c63abffd7b2..7bc6bfb86253 100644 --- a/include/linux/reiserfs_fs.h +++ b/include/linux/reiserfs_fs.h @@ -2073,6 +2073,10 @@ void reiserfs_init_alloc_options(struct super_block *s); */ __le32 reiserfs_choose_packing(struct inode *dir); +int reiserfs_init_bitmap_cache(struct super_block *sb); +void reiserfs_free_bitmap_cache(struct super_block *sb); +void reiserfs_cache_bitmap_metadata(struct super_block *sb, struct buffer_head *bh, struct reiserfs_bitmap_info *info); +struct buffer_head *reiserfs_read_bitmap_block(struct super_block *sb, unsigned int bitmap); int is_reusable(struct super_block *s, b_blocknr_t block, int bit_value); void reiserfs_free_block(struct reiserfs_transaction_handle *th, struct inode *, b_blocknr_t, int for_unformatted); -- cgit v1.2.3 From 5065227b46235ec0131b383cc2f537069b55c6b6 Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Sat, 30 Sep 2006 23:28:44 -0700 Subject: [PATCH] reiserfs: on-demand bitmap loading This is the patch the three previous ones have been leading up to. It changes the behavior of ReiserFS from loading and caching all the bitmaps as special, to treating the bitmaps like any other bit of metadata and just letting the system-wide caches figure out what to hang on to. Buffer heads are allocated on the fly, so there is no need to retain pointers to all of them. The caching of the metadata occurs when the data is read and updated, and is considered invalid and uncached until then. I needed to remove the vs-4040 check for performing a duplicate operation on a particular bit. The reason is that while the other sites for working with bitmaps are allowed to schedule, is_reusable() is called from do_balance(), which will panic if a schedule occurs in certain places. The benefit of on-demand bitmaps clearly outweighs a sanity check that depends on a compile-time option that is discouraged. [akpm@osdl.org: warning fix] Signed-off-by: Jeff Mahoney Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/reiserfs_fs_sb.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/reiserfs_fs_sb.h b/include/linux/reiserfs_fs_sb.h index 4f21ad388c79..73e0becec086 100644 --- a/include/linux/reiserfs_fs_sb.h +++ b/include/linux/reiserfs_fs_sb.h @@ -267,7 +267,6 @@ struct reiserfs_bitmap_info { // FIXME: Won't work with block sizes > 8K __u16 first_zero_hint; __u16 free_count; - struct buffer_head *bh; /* the actual bitmap */ }; struct proc_dir_entry; -- cgit v1.2.3 From 027445c37282bc1ed26add45e573ad2d3e4860a5 Mon Sep 17 00:00:00 2001 From: Badari Pulavarty Date: Sat, 30 Sep 2006 23:28:46 -0700 Subject: [PATCH] Vectorize aio_read/aio_write fileop methods This patch vectorizes aio_read() and aio_write() methods to prepare for collapsing all aio & vectored operations into one interface - which is aio_read()/aio_write(). Signed-off-by: Badari Pulavarty Signed-off-by: Christoph Hellwig Cc: Michael Holzheu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/aio.h | 2 ++ include/linux/fs.h | 10 +++++----- include/linux/nfs_fs.h | 10 ++++++---- 3 files changed, 13 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/aio.h b/include/linux/aio.h index 8a0193385a9b..58349e58b749 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -4,6 +4,7 @@ #include #include #include +#include #include @@ -112,6 +113,7 @@ struct kiocb { long ki_retried; /* just for testing */ long ki_kicked; /* just for testing */ long ki_queued; /* just for testing */ + struct iovec ki_inline_vec; /* inline vector */ struct list_head ki_list; /* the aio core uses this * for cancellation */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 5baf3a153403..257bae16f545 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1097,9 +1097,9 @@ struct file_operations { struct module *owner; loff_t (*llseek) (struct file *, loff_t, int); ssize_t (*read) (struct file *, char __user *, size_t, loff_t *); - ssize_t (*aio_read) (struct kiocb *, char __user *, size_t, loff_t); ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *); - ssize_t (*aio_write) (struct kiocb *, const char __user *, size_t, loff_t); + ssize_t (*aio_read) (struct kiocb *, const struct iovec *, unsigned long, loff_t); + ssize_t (*aio_write) (struct kiocb *, const struct iovec *, unsigned long, loff_t); int (*readdir) (struct file *, void *, filldir_t); unsigned int (*poll) (struct file *, struct poll_table_struct *); int (*ioctl) (struct inode *, struct file *, unsigned int, unsigned long); @@ -1704,11 +1704,11 @@ extern int file_send_actor(read_descriptor_t * desc, struct page *page, unsigned extern ssize_t generic_file_read(struct file *, char __user *, size_t, loff_t *); int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk); extern ssize_t generic_file_write(struct file *, const char __user *, size_t, loff_t *); -extern ssize_t generic_file_aio_read(struct kiocb *, char __user *, size_t, loff_t); +extern ssize_t generic_file_aio_read(struct kiocb *, const struct iovec *, unsigned long, loff_t); extern ssize_t __generic_file_aio_read(struct kiocb *, const struct iovec *, unsigned long, loff_t *); -extern ssize_t generic_file_aio_write(struct kiocb *, const char __user *, size_t, loff_t); +extern ssize_t generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long, loff_t); extern ssize_t generic_file_aio_write_nolock(struct kiocb *, const struct iovec *, - unsigned long, loff_t *); + unsigned long, loff_t); extern ssize_t generic_file_direct_write(struct kiocb *, const struct iovec *, unsigned long *, loff_t, loff_t *, size_t, size_t); extern ssize_t generic_file_buffered_write(struct kiocb *, const struct iovec *, diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 98c9b9f667a5..76ff54846ada 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -367,10 +367,12 @@ extern int nfs3_removexattr (struct dentry *, const char *name); */ extern ssize_t nfs_direct_IO(int, struct kiocb *, const struct iovec *, loff_t, unsigned long); -extern ssize_t nfs_file_direct_read(struct kiocb *iocb, char __user *buf, - size_t count, loff_t pos); -extern ssize_t nfs_file_direct_write(struct kiocb *iocb, const char __user *buf, - size_t count, loff_t pos); +extern ssize_t nfs_file_direct_read(struct kiocb *iocb, + const struct iovec *iov, unsigned long nr_segs, + loff_t pos); +extern ssize_t nfs_file_direct_write(struct kiocb *iocb, + const struct iovec *iov, unsigned long nr_segs, + loff_t pos); /* * linux/fs/nfs/dir.c -- cgit v1.2.3 From ee0b3e671baff681d69fbf0db33b47603c0a8280 Mon Sep 17 00:00:00 2001 From: Badari Pulavarty Date: Sat, 30 Sep 2006 23:28:47 -0700 Subject: [PATCH] Remove readv/writev methods and use aio_read/aio_write instead This patch removes readv() and writev() methods and replaces them with aio_read()/aio_write() methods. Signed-off-by: Badari Pulavarty Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 257bae16f545..afb6e6f89a01 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1113,8 +1113,6 @@ struct file_operations { int (*aio_fsync) (struct kiocb *, int datasync); int (*fasync) (int, struct file *, int); int (*lock) (struct file *, int, struct file_lock *); - ssize_t (*readv) (struct file *, const struct iovec *, unsigned long, loff_t *); - ssize_t (*writev) (struct file *, const struct iovec *, unsigned long, loff_t *); ssize_t (*sendfile) (struct file *, loff_t *, size_t, read_actor_t, void *); ssize_t (*sendpage) (struct file *, struct page *, int, size_t, loff_t *, int); unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); @@ -1734,10 +1732,6 @@ extern long do_splice_direct(struct file *in, loff_t *ppos, struct file *out, extern void file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping); -extern ssize_t generic_file_readv(struct file *filp, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos); -ssize_t generic_file_writev(struct file *filp, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos); extern loff_t no_llseek(struct file *file, loff_t offset, int origin); extern loff_t generic_file_llseek(struct file *file, loff_t offset, int origin); extern loff_t remote_llseek(struct file *file, loff_t offset, int origin); -- cgit v1.2.3 From 543ade1fc901db4c3dbe9fb27241fb977f1f3eea Mon Sep 17 00:00:00 2001 From: Badari Pulavarty Date: Sat, 30 Sep 2006 23:28:48 -0700 Subject: [PATCH] Streamline generic_file_* interfaces and filemap cleanups This patch cleans up generic_file_*_read/write() interfaces. Christoph Hellwig gave me the idea for this clean ups. In a nutshell, all filesystems should set .aio_read/.aio_write methods and use do_sync_read/ do_sync_write() as their .read/.write methods. This allows us to cleanup all variants of generic_file_* routines. Final available interfaces: generic_file_aio_read() - read handler generic_file_aio_write() - write handler generic_file_aio_write_nolock() - no lock write handler __generic_file_aio_write_nolock() - internal worker routine Signed-off-by: Badari Pulavarty Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index afb6e6f89a01..011129f8803e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1699,11 +1699,8 @@ extern int generic_file_mmap(struct file *, struct vm_area_struct *); extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); extern int file_read_actor(read_descriptor_t * desc, struct page *page, unsigned long offset, unsigned long size); extern int file_send_actor(read_descriptor_t * desc, struct page *page, unsigned long offset, unsigned long size); -extern ssize_t generic_file_read(struct file *, char __user *, size_t, loff_t *); int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk); -extern ssize_t generic_file_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t generic_file_aio_read(struct kiocb *, const struct iovec *, unsigned long, loff_t); -extern ssize_t __generic_file_aio_read(struct kiocb *, const struct iovec *, unsigned long, loff_t *); extern ssize_t generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long, loff_t); extern ssize_t generic_file_aio_write_nolock(struct kiocb *, const struct iovec *, unsigned long, loff_t); @@ -1713,8 +1710,6 @@ extern ssize_t generic_file_buffered_write(struct kiocb *, const struct iovec *, unsigned long, loff_t, loff_t *, size_t, ssize_t); extern ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos); extern ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos); -ssize_t generic_file_write_nolock(struct file *file, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos); extern ssize_t generic_file_sendfile(struct file *, loff_t *, size_t, read_actor_t, void *); extern void do_generic_mapping_read(struct address_space *mapping, struct file_ra_state *, struct file *, -- cgit v1.2.3 From eed4e51fb60c3863c134a5e9f6006b29805ead97 Mon Sep 17 00:00:00 2001 From: Badari Pulavarty Date: Sat, 30 Sep 2006 23:28:49 -0700 Subject: [PATCH] Add vector AIO support This work is initially done by Zach Brown to add support for vectored aio. These are the core changes for AIO to support IOCB_CMD_PREADV/IOCB_CMD_PWRITEV. [akpm@osdl.org: huge build fix] Signed-off-by: Zach Brown Signed-off-by: Christoph Hellwig Signed-off-by: Badari Pulavarty Acked-by: Benjamin LaHaise Acked-by: James Morris Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/aio.h | 4 ++++ include/linux/aio_abi.h | 2 ++ include/linux/fs.h | 5 +++++ 3 files changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/aio.h b/include/linux/aio.h index 58349e58b749..5722568fc71e 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -7,6 +7,7 @@ #include #include +#include #define AIO_MAXSEGS 4 #define AIO_KIOGRP_NR_ATOMIC 8 @@ -114,6 +115,9 @@ struct kiocb { long ki_kicked; /* just for testing */ long ki_queued; /* just for testing */ struct iovec ki_inline_vec; /* inline vector */ + struct iovec *ki_iovec; + unsigned long ki_nr_segs; + unsigned long ki_cur_seg; struct list_head ki_list; /* the aio core uses this * for cancellation */ diff --git a/include/linux/aio_abi.h b/include/linux/aio_abi.h index 30fdcc89d142..3466b1d0ffd2 100644 --- a/include/linux/aio_abi.h +++ b/include/linux/aio_abi.h @@ -41,6 +41,8 @@ enum { * IOCB_CMD_POLL = 5, */ IOCB_CMD_NOOP = 6, + IOCB_CMD_PREADV = 7, + IOCB_CMD_PWRITEV = 8, }; /* read() from /dev/aio returns these structures. */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 011129f8803e..4bb70871873f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1150,6 +1150,11 @@ struct inode_operations { struct seq_file; +ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector, + unsigned long nr_segs, unsigned long fast_segs, + struct iovec *fast_pointer, + struct iovec **ret_pointer); + extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *); extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t vfs_readv(struct file *, const struct iovec __user *, -- cgit v1.2.3 From 31608214fe21dc31d8046679054ab033b1fe5cf1 Mon Sep 17 00:00:00 2001 From: "Chen, Kenneth W" Date: Sat, 30 Sep 2006 23:28:50 -0700 Subject: [PATCH] clean up unused kiocb variables Signed-off-by: Ken Chen Acked-by: Zach Brown Cc: Suparna Bhattacharya Cc: Benjamin LaHaise Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/aio.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/aio.h b/include/linux/aio.h index 5722568fc71e..0d71c0041f13 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -112,8 +112,6 @@ struct kiocb { char __user *ki_buf; /* remaining iocb->aio_buf */ size_t ki_left; /* remaining bytes */ long ki_retried; /* just for testing */ - long ki_kicked; /* just for testing */ - long ki_queued; /* just for testing */ struct iovec ki_inline_vec; /* inline vector */ struct iovec *ki_iovec; unsigned long ki_nr_segs; -- cgit v1.2.3 From f3cef7a99469afc159fec3a61b42dc7ca5b6824f Mon Sep 17 00:00:00 2001 From: Jay Lan Date: Sat, 30 Sep 2006 23:28:55 -0700 Subject: [PATCH] csa: basic accounting over taskstats Add some basic accounting fields to the taskstats struct, add a new kernel/tsacct.c to handle basic accounting data handling upon exit. A handle is added to taskstats.c to invoke the basic accounting data handling. Signed-off-by: Jay Lan Cc: Shailabh Nagar Cc: Balbir Singh Cc: Jes Sorensen Cc: Chris Sturtivant Cc: Tony Ernst Cc: Guillaume Thouvenin Cc: "Michal Piotrowski" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/taskstats.h | 29 ++++++++++++++++++++++++----- include/linux/tsacct_kern.h | 19 +++++++++++++++++++ 2 files changed, 43 insertions(+), 5 deletions(-) create mode 100644 include/linux/tsacct_kern.h (limited to 'include/linux') diff --git a/include/linux/taskstats.h b/include/linux/taskstats.h index f1cb6cddd19d..af93a63a5092 100644 --- a/include/linux/taskstats.h +++ b/include/linux/taskstats.h @@ -2,6 +2,7 @@ * * Copyright (C) Shailabh Nagar, IBM Corp. 2006 * (C) Balbir Singh, IBM Corp. 2006 + * (C) Jay Lan, SGI, 2006 * * This program is free software; you can redistribute it and/or modify it * under the terms of version 2.1 of the GNU Lesser General Public License @@ -29,16 +30,18 @@ * c) add new fields after version comment; maintain 64-bit alignment */ -#define TASKSTATS_VERSION 1 + +#define TASKSTATS_VERSION 2 +#define TS_COMM_LEN 16 /* should sync up with TASK_COMM_LEN + * in linux/sched.h */ struct taskstats { /* Version 1 */ __u16 version; - __u16 padding[3]; /* Userspace should not interpret the padding - * field which can be replaced by useful - * fields if struct taskstats is extended. - */ + __u32 ac_exitcode; /* Exit status */ + __u8 ac_flag; /* Record flags */ + __u8 ac_nice; /* task_nice */ /* Delay accounting fields start * @@ -88,6 +91,22 @@ struct taskstats { __u64 cpu_run_virtual_total; /* Delay accounting fields end */ /* version 1 ends here */ + + /* Basic Accounting Fields start */ + char ac_comm[TS_COMM_LEN]; /* Command name */ + __u8 ac_sched; /* Scheduling discipline */ + __u8 ac_pad[3]; + __u32 ac_uid; /* User ID */ + __u32 ac_gid; /* Group ID */ + __u32 ac_pid; /* Process ID */ + __u32 ac_ppid; /* Parent process ID */ + __u32 ac_btime; /* Begin time [sec since 1970] */ + __u64 ac_etime; /* Elapsed time [usec] */ + __u64 ac_utime; /* User CPU time [usec] */ + __u64 ac_stime; /* SYstem CPU time [usec] */ + __u64 ac_minflt; /* Minor Page Fault */ + __u64 ac_majflt; /* Major Page Fault */ + /* Basic Accounting Fields end */ }; diff --git a/include/linux/tsacct_kern.h b/include/linux/tsacct_kern.h new file mode 100644 index 000000000000..7e8196a02118 --- /dev/null +++ b/include/linux/tsacct_kern.h @@ -0,0 +1,19 @@ +/* + * tsacct_kern.h - kernel header for system accounting over taskstats interface + * + * Copyright (C) Jay Lan SGI + */ + +#ifndef _LINUX_TSACCT_KERN_H +#define _LINUX_TSACCT_KERN_H + +#include + +#ifdef CONFIG_TASKSTATS +extern void bacct_add_tsk(struct taskstats *stats, struct task_struct *tsk); +#else +static inline void bacct_add_tsk(struct taskstats *stats, struct task_struct *tsk) +{} +#endif /* CONFIG_TASKSTATS */ + +#endif -- cgit v1.2.3 From 9acc1853519a0473620d424105f9d49ea5b4e62e Mon Sep 17 00:00:00 2001 From: Jay Lan Date: Sat, 30 Sep 2006 23:28:58 -0700 Subject: [PATCH] csa: Extended system accounting over taskstats Add extended system accounting handling over taskstats interface. A CONFIG_TASK_XACCT flag is created to enable the extended accounting code. Signed-off-by: Jay Lan Cc: Shailabh Nagar Cc: Balbir Singh Cc: Jes Sorensen Cc: Chris Sturtivant Cc: Tony Ernst Cc: Guillaume Thouvenin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/taskstats.h | 11 +++++++++++ include/linux/tsacct_kern.h | 9 +++++++++ 2 files changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/taskstats.h b/include/linux/taskstats.h index af93a63a5092..3d2c304886b0 100644 --- a/include/linux/taskstats.h +++ b/include/linux/taskstats.h @@ -107,6 +107,17 @@ struct taskstats { __u64 ac_minflt; /* Minor Page Fault */ __u64 ac_majflt; /* Major Page Fault */ /* Basic Accounting Fields end */ + + /* Extended accounting fields start */ + __u64 acct_rss_mem1; /* accumulated rss usage */ + __u64 acct_vm_mem1; /* accumulated virtual memory usage */ + __u64 hiwater_rss; /* High-watermark of RSS usage */ + __u64 hiwater_vm; /* High-water virtual memory usage */ + __u64 read_char; /* bytes read */ + __u64 write_char; /* bytes written */ + __u64 read_syscalls; /* read syscalls */ + __u64 write_syscalls; /* write syscalls */ + /* Extended accounting fields end */ }; diff --git a/include/linux/tsacct_kern.h b/include/linux/tsacct_kern.h index 7e8196a02118..74102dcae67a 100644 --- a/include/linux/tsacct_kern.h +++ b/include/linux/tsacct_kern.h @@ -16,4 +16,13 @@ static inline void bacct_add_tsk(struct taskstats *stats, struct task_struct *ts {} #endif /* CONFIG_TASKSTATS */ +#ifdef CONFIG_TASK_XACCT +extern void xacct_add_tsk(struct taskstats *stats, struct task_struct *p); +#else +static inline void xacct_add_tsk(struct taskstats *stats, struct task_struct *p) +{} +#endif /* CONFIG_TASK_XACCT */ + #endif + + -- cgit v1.2.3 From 8f0ab5147951267134612570604cf8341901a80c Mon Sep 17 00:00:00 2001 From: Jay Lan Date: Sat, 30 Sep 2006 23:28:59 -0700 Subject: [PATCH] csa: convert CONFIG tag for extended accounting routines There were a few accounting data/macros that are used in CSA but are #ifdef'ed inside CONFIG_BSD_PROCESS_ACCT. This patch is to change those ifdef's from CONFIG_BSD_PROCESS_ACCT to CONFIG_TASK_XACCT. A few defines are moved from kernel/acct.c and include/linux/acct.h to kernel/tsacct.c and include/linux/tsacct_kern.h. Signed-off-by: Jay Lan Cc: Shailabh Nagar Cc: Balbir Singh Cc: Jes Sorensen Cc: Chris Sturtivant Cc: Tony Ernst Cc: Guillaume Thouvenin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/acct.h | 4 ---- include/linux/sched.h | 2 +- include/linux/tsacct_kern.h | 6 ++++++ 3 files changed, 7 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/acct.h b/include/linux/acct.h index e86bae7324d2..0496d1f09952 100644 --- a/include/linux/acct.h +++ b/include/linux/acct.h @@ -124,16 +124,12 @@ extern void acct_auto_close(struct super_block *sb); extern void acct_init_pacct(struct pacct_struct *pacct); extern void acct_collect(long exitcode, int group_dead); extern void acct_process(void); -extern void acct_update_integrals(struct task_struct *tsk); -extern void acct_clear_integrals(struct task_struct *tsk); #else #define acct_auto_close_mnt(x) do { } while (0) #define acct_auto_close(x) do { } while (0) #define acct_init_pacct(x) do { } while (0) #define acct_collect(x,y) do { } while (0) #define acct_process() do { } while (0) -#define acct_update_integrals(x) do { } while (0) -#define acct_clear_integrals(task) do { } while (0) #endif /* diff --git a/include/linux/sched.h b/include/linux/sched.h index fc4a9873ec10..4ddeb0f982fb 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -981,7 +981,7 @@ struct task_struct { wait_queue_t *io_wait; /* i/o counters(bytes read/written, #syscalls */ u64 rchar, wchar, syscr, syscw; -#if defined(CONFIG_BSD_PROCESS_ACCT) +#if defined(CONFIG_TASK_XACCT) u64 acct_rss_mem1; /* accumulated rss usage */ u64 acct_vm_mem1; /* accumulated virtual memory usage */ clock_t acct_stimexpd; /* clock_t-converted stime since last update */ diff --git a/include/linux/tsacct_kern.h b/include/linux/tsacct_kern.h index 74102dcae67a..7e50ac795b0b 100644 --- a/include/linux/tsacct_kern.h +++ b/include/linux/tsacct_kern.h @@ -18,9 +18,15 @@ static inline void bacct_add_tsk(struct taskstats *stats, struct task_struct *ts #ifdef CONFIG_TASK_XACCT extern void xacct_add_tsk(struct taskstats *stats, struct task_struct *p); +extern void acct_update_integrals(struct task_struct *tsk); +extern void acct_clear_integrals(struct task_struct *tsk); #else static inline void xacct_add_tsk(struct taskstats *stats, struct task_struct *p) {} +static inline void acct_update_integrals(struct task_struct *tsk) +{} +static inline void acct_clear_integrals(struct task_struct *tsk) +{} #endif /* CONFIG_TASK_XACCT */ #endif -- cgit v1.2.3 From db5fed26b2e0beed939b773dd5896077a1794d65 Mon Sep 17 00:00:00 2001 From: Jay Lan Date: Sat, 30 Sep 2006 23:29:00 -0700 Subject: [PATCH] csa accounting taskstats update ChangeLog: Feedbacks from Andrew Morton: - define TS_COMM_LEN to 32 - change acct_stimexpd field of task_struct to be of cputime_t, which is to be used to save the tsk->stime of last timer interrupt update. - a new Documentation/accounting/taskstats-struct.txt to describe fields of taskstats struct. Feedback from Balbir Singh: - keep the stime of a task to be zero when both stime and utime are zero as recoreded in task_struct. Misc: - convert accumulated RSS/VM from platform dependent pages-ticks to MBytes-usecs in the kernel Cc: Shailabh Nagar Cc: Balbir Singh Cc: Jes Sorensen Cc: Chris Sturtivant Cc: Tony Ernst Cc: Guillaume Thouvenin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 2 +- include/linux/taskstats.h | 40 +++++++++++++++++++++++++++++++--------- 2 files changed, 32 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 4ddeb0f982fb..7ef899c47c29 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -984,7 +984,7 @@ struct task_struct { #if defined(CONFIG_TASK_XACCT) u64 acct_rss_mem1; /* accumulated rss usage */ u64 acct_vm_mem1; /* accumulated virtual memory usage */ - clock_t acct_stimexpd; /* clock_t-converted stime since last update */ + cputime_t acct_stimexpd;/* stime since last update */ #endif #ifdef CONFIG_NUMA struct mempolicy *mempolicy; diff --git a/include/linux/taskstats.h b/include/linux/taskstats.h index 3d2c304886b0..45248806ae9c 100644 --- a/include/linux/taskstats.h +++ b/include/linux/taskstats.h @@ -32,14 +32,21 @@ #define TASKSTATS_VERSION 2 -#define TS_COMM_LEN 16 /* should sync up with TASK_COMM_LEN +#define TS_COMM_LEN 32 /* should be >= TASK_COMM_LEN * in linux/sched.h */ struct taskstats { - /* Version 1 */ + /* The version number of this struct. This field is always set to + * TAKSTATS_VERSION, which is defined in . + * Each time the struct is changed, the value should be incremented. + */ __u16 version; - __u32 ac_exitcode; /* Exit status */ + __u32 ac_exitcode; /* Exit status */ + + /* The accounting flags of a task as defined in + * Defined values are AFORK, ASU, ACOMPAT, ACORE, and AXSIG. + */ __u8 ac_flag; /* Record flags */ __u8 ac_nice; /* task_nice */ @@ -104,15 +111,30 @@ struct taskstats { __u64 ac_etime; /* Elapsed time [usec] */ __u64 ac_utime; /* User CPU time [usec] */ __u64 ac_stime; /* SYstem CPU time [usec] */ - __u64 ac_minflt; /* Minor Page Fault */ - __u64 ac_majflt; /* Major Page Fault */ + __u64 ac_minflt; /* Minor Page Fault Count */ + __u64 ac_majflt; /* Major Page Fault Count */ /* Basic Accounting Fields end */ /* Extended accounting fields start */ - __u64 acct_rss_mem1; /* accumulated rss usage */ - __u64 acct_vm_mem1; /* accumulated virtual memory usage */ - __u64 hiwater_rss; /* High-watermark of RSS usage */ - __u64 hiwater_vm; /* High-water virtual memory usage */ + /* Accumulated RSS usage in duration of a task, in MBytes-usecs. + * The current rss usage is added to this counter every time + * a tick is charged to a task's system time. So, at the end we + * will have memory usage multiplied by system time. Thus an + * average usage per system time unit can be calculated. + */ + __u64 coremem; /* accumulated RSS usage in MB-usec */ + /* Accumulated virtual memory usage in duration of a task. + * Same as acct_rss_mem1 above except that we keep track of VM usage. + */ + __u64 virtmem; /* accumulated VM usage in MB-usec */ + + /* High watermark of RSS and virtual memory usage in duration of + * a task, in KBytes. + */ + __u64 hiwater_rss; /* High-watermark of RSS usage, in KB */ + __u64 hiwater_vm; /* High-water VM usage, in KB */ + + /* The following four fields are I/O statistics of a task. */ __u64 read_char; /* bytes read */ __u64 write_char; /* bytes written */ __u64 read_syscalls; /* read syscalls */ -- cgit v1.2.3 From 9a53c3a783c2fa9b969628e65695c11c3e51e673 Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Sat, 30 Sep 2006 23:29:03 -0700 Subject: [PATCH] r/o bind mounts: unlink: monitor i_nlink When a filesystem decrements i_nlink to zero, it means that a write must be performed in order to drop the inode from the filesystem. We're shortly going to have keep filesystems from being remounted r/o between the time that this i_nlink decrement and that write occurs. So, add a little helper function to do the decrements. We'll tie into it in a bit to note when i_nlink hits zero. Signed-off-by: Dave Hansen Acked-by: Christoph Hellwig Cc: Al Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 4bb70871873f..26d3c61116c0 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1225,9 +1225,14 @@ static inline void inode_inc_link_count(struct inode *inode) mark_inode_dirty(inode); } -static inline void inode_dec_link_count(struct inode *inode) +static inline void drop_nlink(struct inode *inode) { inode->i_nlink--; +} + +static inline void inode_dec_link_count(struct inode *inode) +{ + drop_nlink(inode); mark_inode_dirty(inode); } -- cgit v1.2.3 From d8c76e6f45c111c32a4b3e50a2adc9210737b0d8 Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Sat, 30 Sep 2006 23:29:04 -0700 Subject: [PATCH] r/o bind mount prepwork: inc_nlink() helper This is mostly included for parity with dec_nlink(), where we will have some more hooks. This one should stay pretty darn straightforward for now. Signed-off-by: Dave Hansen Acked-by: Christoph Hellwig Cc: Al Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 26d3c61116c0..6a5267da565f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1219,9 +1219,14 @@ static inline void mark_inode_dirty_sync(struct inode *inode) __mark_inode_dirty(inode, I_DIRTY_SYNC); } -static inline void inode_inc_link_count(struct inode *inode) +static inline void inc_nlink(struct inode *inode) { inode->i_nlink++; +} + +static inline void inode_inc_link_count(struct inode *inode) +{ + inc_nlink(inode); mark_inode_dirty(inode); } -- cgit v1.2.3 From ce71ec36840368b877fb63bd14c8e67ab62d08b1 Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Sat, 30 Sep 2006 23:29:06 -0700 Subject: [PATCH] r/o bind mounts: monitor zeroing of i_nlink Some filesystems, instead of simply decrementing i_nlink, simply zero it during an unlink operation. We need to catch these in addition to the decrement operations. Signed-off-by: Dave Hansen Acked-by: Christoph Hellwig Cc: Al Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 6a5267da565f..3493d2828f7d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1235,6 +1235,11 @@ static inline void drop_nlink(struct inode *inode) inode->i_nlink--; } +static inline void clear_nlink(struct inode *inode) +{ + inode->i_nlink = 0; +} + static inline void inode_dec_link_count(struct inode *inode) { drop_nlink(inode); -- cgit v1.2.3 From 74588d8ba34ff1bda027cfa737972af01ab00c8b Mon Sep 17 00:00:00 2001 From: Haavard Skinnemoen Date: Sat, 30 Sep 2006 23:29:12 -0700 Subject: [PATCH] Generic ioremap_page_range: implementation This patch adds a generic implementation of ioremap_page_range() in lib/ioremap.c based on the i386 implementation. It differs from the i386 version in the following ways: * The PTE flags are passed as a pgprot_t argument and must be determined up front by the arch-specific code. No additional PTE flags are added. * Uses set_pte_at() instead of set_pte() [bunk@stusta.de: warning fix] ]dhowells@redhat.com: nommu build fix] Signed-off-by: Haavard Skinnemoen Cc: Richard Henderson Cc: Ivan Kokshaysky Cc: Russell King Cc: Mikael Starvik Cc: Andi Kleen Cc: Cc: Ralf Baechle Cc: Kyle McMartin Cc: Martin Schwidefsky Cc: Paul Mundt Signed-off-by: Adrian Bunk Signed-off-by: David Howells Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/io.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/io.h b/include/linux/io.h index 420e2fdf26f6..aa3f5af670b5 100644 --- a/include/linux/io.h +++ b/include/linux/io.h @@ -19,8 +19,12 @@ #define _LINUX_IO_H #include +#include void __iowrite32_copy(void __iomem *to, const void *from, size_t count); void __iowrite64_copy(void __iomem *to, const void *from, size_t count); +int ioremap_page_range(unsigned long addr, unsigned long end, + unsigned long phys_addr, pgprot_t prot); + #endif /* _LINUX_IO_H */ -- cgit v1.2.3 From d6cbd281d189977b38eac7eb2a4678de19b6b483 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Sat, 30 Sep 2006 23:29:26 -0700 Subject: [PATCH] Some cleanup in the pipe code Split the big and hard to read do_pipe function into smaller pieces. This creates new create_write_pipe/free_write_pipe/create_read_pipe functions. These functions are made global so that they can be used by other parts of the kernel. The resulting code is more generic and easier to read and has cleaner error handling and less gotos. [akpm@osdl.org: cleanup] Signed-off-by: Andi Kleen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 3493d2828f7d..2e29a2edaeec 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1641,6 +1641,9 @@ static inline void allow_write_access(struct file *file) atomic_inc(&file->f_dentry->d_inode->i_writecount); } extern int do_pipe(int *); +extern struct file *create_read_pipe(struct file *f); +extern struct file *create_write_pipe(void); +extern void free_write_pipe(struct file *); extern int open_namei(int dfd, const char *, int, int, struct nameidata *); extern int may_open(struct nameidata *, int, int); -- cgit v1.2.3 From e239ca540594cff00adcce163dc332b27015d8e5 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Sat, 30 Sep 2006 23:29:27 -0700 Subject: [PATCH] Create call_usermodehelper_pipe() A new member in the ever growing family of call_usermode* functions is born. The new call_usermodehelper_pipe() function allows to pipe data to the stdin of the called user mode progam and behaves otherwise like the normal call_usermodehelp() (except that it always waits for the child to finish) Signed-off-by: Andi Kleen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kmod.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kmod.h b/include/linux/kmod.h index 0db22a1ab474..10f505c8431d 100644 --- a/include/linux/kmod.h +++ b/include/linux/kmod.h @@ -47,4 +47,8 @@ call_usermodehelper(char *path, char **argv, char **envp, int wait) extern void usermodehelper_init(void); +struct file; +extern int call_usermodehelper_pipe(char *path, char *argv[], char *envp[], + struct file **filp); + #endif /* __LINUX_KMOD_H__ */ -- cgit v1.2.3 From 5a73fdc5ea836d2edc5e02890b51185fe304d7d3 Mon Sep 17 00:00:00 2001 From: Zachary Amsden Date: Sat, 30 Sep 2006 23:29:38 -0700 Subject: [PATCH] Some config.h removals During tracking down a PAE compile failure, I found that config.h was being included in a bunch of places in i386 code. It is no longer necessary, so drop it. Signed-off-by: Zachary Amsden Cc: Rusty Russell Cc: Jeremy Fitzhardinge Cc: Andi Kleen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/unwind.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/unwind.h b/include/linux/unwind.h index ce48e2cd37a2..73e1751d03dd 100644 --- a/include/linux/unwind.h +++ b/include/linux/unwind.h @@ -12,8 +12,6 @@ * is not much point in implementing the full Dwarf2 unwind API. */ -#include - struct module; #ifdef CONFIG_STACK_UNWIND -- cgit v1.2.3 From a6b93a908508810c5d51dd9b390283345af6f2d9 Mon Sep 17 00:00:00 2001 From: Russell King Date: Sun, 1 Oct 2006 17:17:40 +0100 Subject: [SERIAL] Fix oops when removing suspended serial port A serial card might have been removed when the system is resumed. This results in a suspended port being shut down, which results in the ports shutdown method being called twice in a row. This causes BUGs. Avoid this by tracking the suspended state separately from the initialised state. Signed-off-by: Russell King --- include/linux/serial_core.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 86501a3de2ac..f9fdf97506ea 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -319,6 +319,7 @@ struct uart_info { #define UIF_CTS_FLOW ((__force uif_t) (1 << 26)) #define UIF_NORMAL_ACTIVE ((__force uif_t) (1 << 29)) #define UIF_INITIALIZED ((__force uif_t) (1 << 31)) +#define UIF_SUSPENDED ((__force uif_t) (1 << 30)) int blocked_open; -- cgit v1.2.3 From d8d64d6b29d331f1217c77999f5104fe68b0ef3a Mon Sep 17 00:00:00 2001 From: Simon Tatham Date: Mon, 25 Sep 2006 16:51:28 -0700 Subject: [SERIAL] Magic SysRq SAK does nothing on serial consoles Make sysrq-K work on serial console by passing in the tty. Signed-off-by: Andrew Morton Signed-off-by: Russell King --- include/linux/serial_core.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index f9fdf97506ea..de2e68159d96 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -415,7 +415,7 @@ uart_handle_sysrq_char(struct uart_port *port, unsigned int ch, #ifdef SUPPORT_SYSRQ if (port->sysrq) { if (ch && time_before(jiffies, port->sysrq)) { - handle_sysrq(ch, regs, NULL); + handle_sysrq(ch, regs, port->info->tty); port->sysrq = 0; return 1; } -- cgit v1.2.3 From 322acc96d4bd3debea11cd0160b18bd5d7ff0d73 Mon Sep 17 00:00:00 2001 From: Steve Wise Date: Mon, 2 Oct 2006 02:17:00 -0700 Subject: [PATCH] LIB: add gen_pool_destroy() Modules using the genpool allocator need to be able to destroy the data structure when unloading. Signed-off-by: Steve Wise Cc: Randy Dunlap Cc: Dean Nelson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/genalloc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/genalloc.h b/include/linux/genalloc.h index 690c42803d2e..9869ef3674ac 100644 --- a/include/linux/genalloc.h +++ b/include/linux/genalloc.h @@ -31,5 +31,6 @@ struct gen_pool_chunk { extern struct gen_pool *gen_pool_create(int, int); extern int gen_pool_add(struct gen_pool *, unsigned long, size_t, int); +extern void gen_pool_destroy(struct gen_pool *); extern unsigned long gen_pool_alloc(struct gen_pool *, size_t); extern void gen_pool_free(struct gen_pool *, unsigned long, size_t); -- cgit v1.2.3 From 2bc2d61a9638dab670d8361e928d1a5a291173ef Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 2 Oct 2006 02:17:02 -0700 Subject: [PATCH] list module taint flags in Oops/panic When listing loaded modules during an oops or panic, also list each module's Tainted flags if non-zero (P: Proprietary or F: Forced load only). If a module is did not taint the kernel, it is just listed like usbcore but if it did taint the kernel, it is listed like wizmodem(PF) Example: [ 3260.121718] Unable to handle kernel NULL pointer dereference at 0000000000000000 RIP: [ 3260.121729] [] :dump_test:proc_dump_test+0x99/0xc8 [ 3260.121742] PGD fe8d067 PUD 264a6067 PMD 0 [ 3260.121748] Oops: 0002 [1] SMP [ 3260.121753] CPU 1 [ 3260.121756] Modules linked in: dump_test(P) snd_pcm_oss snd_mixer_oss snd_seq snd_seq_device ide_cd generic ohci1394 snd_hda_intel snd_hda_codec snd_pcm snd_timer snd ieee1394 snd_page_alloc piix ide_core arcmsr aic79xx scsi_transport_spi usblp [ 3260.121785] Pid: 5556, comm: bash Tainted: P 2.6.18-git10 #1 [Alternatively, I can look into listing tainted flags with 'lsmod', but that won't help in oopsen/panics so much.] [akpm@osdl.org: cleanup] Signed-off-by: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/module.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index 2c599175c583..4b2d8091a410 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -320,6 +320,8 @@ struct module /* Am I GPL-compatible */ int license_gplok; + unsigned int taints; /* same bits as kernel:tainted */ + #ifdef CONFIG_MODULE_UNLOAD /* Reference counts */ struct module_ref ref[NR_CPUS]; -- cgit v1.2.3 From 0804ef4b0de7121261f77c565b20a11ac694e877 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 2 Oct 2006 02:17:04 -0700 Subject: [PATCH] proc: readdir race fix (take 3) The problem: An opendir, readdir, closedir sequence can fail to report process ids that are continually in use throughout the sequence of system calls. For this race to trigger the process that proc_pid_readdir stops at must exit before readdir is called again. This can cause ps to fail to report processes, and it is in violation of posix guarantees and normal application expectations with respect to readdir. Currently there is no way to work around this problem in user space short of providing a gargantuan buffer to user space so the directory read all happens in on system call. This patch implements the normal directory semantics for proc, that guarantee that a directory entry that is neither created nor destroyed while reading the directory entry will be returned. For directory that are either created or destroyed during the readdir you may or may not see them. Furthermore you may seek to a directory offset you have previously seen. These are the guarantee that ext[23] provides and that posix requires, and more importantly that user space expects. Plus it is a simple semantic to implement reliable service. It is just a matter of calling readdir a second time if you are wondering if something new has show up. These better semantics are implemented by scanning through the pids in numerical order and by making the file offset a pid plus a fixed offset. The pid scan happens on the pid bitmap, which when you look at it is remarkably efficient for a brute force algorithm. Given that a typical cache line is 64 bytes and thus covers space for 64*8 == 200 pids. There are only 40 cache lines for the entire 32K pid space. A typical system will have 100 pids or more so this is actually fewer cache lines we have to look at to scan a linked list, and the worst case of having to scan the entire pid bitmap is pretty reasonable. If we need something more efficient we can go to a more efficient data structure for indexing the pids, but for now what we have should be sufficient. In addition this takes no additional locks and is actually less code than what we are doing now. Also another very subtle bug in this area has been fixed. It is possible to catch a task in the middle of de_thread where a thread is assuming the thread of it's thread group leader. This patch carefully handles that case so if we hit it we don't fail to return the pid, that is undergoing the de_thread dance. Thanks to KAMEZAWA Hiroyuki for providing the first fix, pointing this out and working on it. [oleg@tv-sign.ru: fix it] Signed-off-by: Eric W. Biederman Acked-by: KAMEZAWA Hiroyuki Signed-off-by: Oleg Nesterov Cc: Jean Delvare Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pid.h | 1 + include/linux/sched.h | 11 +++++++++++ 2 files changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pid.h b/include/linux/pid.h index 93da7e2d9f30..359121086de1 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -89,6 +89,7 @@ extern struct pid *FASTCALL(find_pid(int nr)); * Lookup a PID in the hash table, and return with it's count elevated. */ extern struct pid *find_get_pid(int nr); +extern struct pid *find_ge_pid(int nr); extern struct pid *alloc_pid(void); extern void FASTCALL(free_pid(struct pid *pid)); diff --git a/include/linux/sched.h b/include/linux/sched.h index 7ef899c47c29..be658e33bd26 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1358,6 +1358,17 @@ extern void wait_task_inactive(struct task_struct * p); /* de_thread depends on thread_group_leader not being a pid based check */ #define thread_group_leader(p) (p == p->group_leader) +/* Do to the insanities of de_thread it is possible for a process + * to have the pid of the thread group leader without actually being + * the thread group leader. For iteration through the pids in proc + * all we care about is that we have a task with the appropriate + * pid, we don't actually care if we have the right task. + */ +static inline int has_group_leader_pid(struct task_struct *p) +{ + return p->pid == p->tgid; +} + static inline struct task_struct *next_thread(const struct task_struct *p) { return list_entry(rcu_dereference(p->thread_group.next), -- cgit v1.2.3 From 20cdc894c45d2e4ab0c69e95a56b7c5ed36ae0dd Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 2 Oct 2006 02:17:07 -0700 Subject: [PATCH] proc: modify proc_pident_lookup to be completely table driven Currently proc_pident_lookup gets the names and types from a table and then has a huge switch statement to get the inode and file operations it needs. That is silly and is becoming increasingly hard to maintain so I just put all of the information in the table. Signed-off-by: Eric W. Biederman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/proc_fs.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 57f70bc8b24b..87dec8fe6de9 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -244,13 +244,15 @@ static inline void kclist_add(struct kcore_list *new, void *addr, size_t size) extern void kclist_add(struct kcore_list *, void *, size_t); #endif +union proc_op { + int (*proc_get_link)(struct inode *, struct dentry **, struct vfsmount **); + int (*proc_read)(struct task_struct *task, char *page); +}; + struct proc_inode { struct pid *pid; int fd; - union { - int (*proc_get_link)(struct inode *, struct dentry **, struct vfsmount **); - int (*proc_read)(struct task_struct *task, char *page); - } op; + union proc_op op; struct proc_dir_entry *pde; struct inode vfs_inode; }; -- cgit v1.2.3 From 22c935f47c03399c78e64c71b757eb36fa917ff6 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 2 Oct 2006 02:17:09 -0700 Subject: [PATCH] pid: implement access helpers for a tacks various process groups In the last round of cleaning up the pid hash table a more general struct pid was introduced, that can be referenced counted. With the more general struct pid most if not all places where we store a pid_t we can now store a struct pid * and remove the need for a hash table lookup, and avoid any possible problems with pid roll over. Looking forward to the pid namespaces struct pid * gives us an absolute form a pid so we can compare and use them without caring which pid namespace we are in. This patchset introduces the infrastructure needed to use struct pid instead of pid_t, and then it goes on to convert two different kernel users that currently store a pid_t value. There are a lot more places to go but this is enough to get the basic idea. Before we can merge a pid namespace patch all of the kernel pid_t users need to be examined. Those that deal with user space processes need to be converted to using a struct pid *. Those that deal with kernel processes need to converted to using the kthread api. A rare few that only use their current processes pid values get to be left alone. This patch: task_session returns the struct pid of a tasks session. task_pgrp returns the struct pid of a tasks process group. task_tgid returns the struct pid of a tasks thread group. task_pid returns the struct pid of a tasks process id. These can be used to avoid unnecessary hash table lookups, and to implement safe pid comparisions in the face of a pid namespace. Signed-off-by: Eric W. Biederman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index be658e33bd26..660b02f80523 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1020,6 +1020,26 @@ static inline pid_t process_group(struct task_struct *tsk) return tsk->signal->pgrp; } +static inline struct pid *task_pid(struct task_struct *task) +{ + return task->pids[PIDTYPE_PID].pid; +} + +static inline struct pid *task_tgid(struct task_struct *task) +{ + return task->group_leader->pids[PIDTYPE_PID].pid; +} + +static inline struct pid *task_pgrp(struct task_struct *task) +{ + return task->group_leader->pids[PIDTYPE_PGID].pid; +} + +static inline struct pid *task_session(struct task_struct *task) +{ + return task->group_leader->pids[PIDTYPE_SID].pid; +} + /** * pid_alive - check that a task structure is not stale * @p: Task structure to be checked. -- cgit v1.2.3 From 558cb325485aaf655130f140e8ddd25392f6c972 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 2 Oct 2006 02:17:09 -0700 Subject: [PATCH] pid: add do_each_pid_task To avoid pid rollover confusion the kernel needs to work with struct pid * instead of pid_t. Currently there is not an iterator that walks through all of the tasks of a given pid type starting with a struct pid. This prevents us replacing some pid_t instances with struct pid. So this patch adds do_each_pid_task which walks through the set of task for a given pid type starting with a struct pid. Signed-off-by: Eric W. Biederman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pid.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pid.h b/include/linux/pid.h index 359121086de1..8cf9b11ed264 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -119,4 +119,17 @@ extern void FASTCALL(free_pid(struct pid *pid)); 1; }) ); \ } +#define do_each_pid_task(pid, type, task) \ + if ((task = pid_task(pid, type))) { \ + prefetch(pid_next(task, type)); \ + do { + +#define while_each_pid_task(pid, type, task) \ + } while (pid_next(task, type) && ({ \ + task = pid_next_task(task, type); \ + rcu_dereference(task); \ + prefetch(pid_next(task, type)); \ + 1; }) ); \ + } + #endif /* _LINUX_PID_H */ -- cgit v1.2.3 From c4b92fc112f7be5cce308128236ff75cc98535c3 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 2 Oct 2006 02:17:10 -0700 Subject: [PATCH] pid: implement signal functions that take a struct pid * Currently the signal functions all either take a task or a pid_t argument. This patch implements variants that take a struct pid *. After all of the users have been update it is my intention to remove the variants that take a pid_t as using pid_t can be more work (an extra hash table lookup) and difficult to get right in the presence of multiple pid namespaces. There are two kinds of functions introduced in this patch. The are the general use functions kill_pgrp and kill_pid which take a priv argument that is ultimately used to create the appropriate siginfo information, Then there are _kill_pgrp_info, kill_pgrp_info, kill_pid_info the internal implementation helpers that take an explicit siginfo. The distinction is made because filling out an explcit siginfo is tricky, and will be even more tricky when pid namespaces are introduced. Signed-off-by: Eric W. Biederman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 660b02f80523..dd6c2164e4a4 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1267,6 +1267,11 @@ extern int send_sig_info(int, struct siginfo *, struct task_struct *); extern int send_group_sig_info(int, struct siginfo *, struct task_struct *); extern int force_sigsegv(int, struct task_struct *); extern int force_sig_info(int, struct siginfo *, struct task_struct *); +extern int __kill_pgrp_info(int sig, struct siginfo *info, struct pid *pgrp); +extern int kill_pgrp_info(int sig, struct siginfo *info, struct pid *pgrp); +extern int kill_pid_info(int sig, struct siginfo *info, struct pid *pid); +extern int kill_pgrp(struct pid *pid, int sig, int priv); +extern int kill_pid(struct pid *pid, int sig, int priv); extern int __kill_pg_info(int sig, struct siginfo *info, pid_t pgrp); extern int kill_pg_info(int, struct siginfo *, pid_t); extern int kill_proc_info(int, struct siginfo *, pid_t); -- cgit v1.2.3 From 5feb8f5f8403d8874a04aac443692dfe83bd63d2 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 2 Oct 2006 02:17:12 -0700 Subject: [PATCH] pid: implement pid_nr As we stop storing pid_t's and move to storing struct pid *. We need a way to get the pid_t from the struct pid to report to user space what we have stored. Having a clean well defined way to do this is especially important as we move to multiple pid spaces as may need to report a different value to the caller depending on which pid space the caller is in. Signed-off-by: Eric W. Biederman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pid.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pid.h b/include/linux/pid.h index 8cf9b11ed264..dba1b2d677a3 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -94,6 +94,14 @@ extern struct pid *find_ge_pid(int nr); extern struct pid *alloc_pid(void); extern void FASTCALL(free_pid(struct pid *pid)); +static inline pid_t pid_nr(struct pid *pid) +{ + pid_t nr = 0; + if (pid) + nr = pid->nr; + return nr; +} + #define pid_next(task, type) \ ((task)->pids[(type)].node.next) -- cgit v1.2.3 From 81af8d67d4fc35b1ee6e0feb1f1b34b3a33eeb44 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 2 Oct 2006 02:17:13 -0700 Subject: [PATCH] vt: rework the console spawning variables This is such a rare path it took me a while to figure out how to test this after soring out the locking. This patch does several things. - The variables used are moved into a structure and declared in vt_kern.h - A spinlock is added so we don't have SMP races updating the values. - Instead of raw pid_t value a struct_pid is used to guard against pid wrap around issues, if the daemon to spawn a new console dies. Signed-off-by: Eric W. Biederman Cc: Oleg Nesterov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vt_kern.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vt_kern.h b/include/linux/vt_kern.h index 1009d3fe1fc2..37a1a41f5b65 100644 --- a/include/linux/vt_kern.h +++ b/include/linux/vt_kern.h @@ -84,4 +84,11 @@ void reset_vc(struct vc_data *vc); extern char con_buf[CON_BUF_SIZE]; extern struct semaphore con_buf_sem; +struct vt_spawn_console { + spinlock_t lock; + struct pid *pid; + int sig; +}; +extern struct vt_spawn_console vt_spawn_con; + #endif /* _VT_KERN_H */ -- cgit v1.2.3 From bde0d2c98bcfc9acc83ac79c33a6ac1335b95a92 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 2 Oct 2006 02:17:14 -0700 Subject: [PATCH] vt: Make vt_pid a struct pid (making it pid wrap around safe). I took a good hard look at the locking and it appears the locking on vt_pid is the console semaphore. Every modified path is called under the console semaphore except reset_vc when it is called from fn_SAK or do_SAK both of which appear to be in interrupt context. In addition I need to be careful because in the presence of an oops the console_sem may be arbitrarily dropped. Which leads me to conclude the current locking is inadequate for my needs. Given the weird cases we could hit because of oops printing instead of introducing an extra spin lock to protect the data and keep the pid to signal and the signal to send in sync, I have opted to use xchg on just the struct pid * pointer instead. Due to console_sem we will stay in sync between vt_pid and vt_mode except for a small window during a SAK, or oops handling. SAK handling should kill any user space process that care, and oops handling we are broken anyway. Besides the worst that can happen is that I try to send the wrong signal. Signed-off-by: Eric W. Biederman Cc: Oleg Nesterov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/console_struct.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/console_struct.h b/include/linux/console_struct.h index 25423f79bf9f..ed6c0fee1ac7 100644 --- a/include/linux/console_struct.h +++ b/include/linux/console_struct.h @@ -54,7 +54,7 @@ struct vc_data { struct tty_struct *vc_tty; /* TTY we are attached to */ /* data for manual vt switching */ struct vt_mode vt_mode; - int vt_pid; + struct pid *vt_pid; int vt_newvt; wait_queue_head_t paste_wait; /* mode flags */ -- cgit v1.2.3 From 609d7fa9565c754428d2520cac2accc9052e1245 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 2 Oct 2006 02:17:15 -0700 Subject: [PATCH] file: modify struct fown_struct to use a struct pid File handles can be requested to send sigio and sigurg to processes. By tracking the destination processes using struct pid instead of pid_t we make the interface safe from all potential pid wrap around problems. Signed-off-by: Eric W. Biederman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 2e29a2edaeec..91c0b2a32a90 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -684,7 +684,8 @@ extern struct block_device *I_BDEV(struct inode *inode); struct fown_struct { rwlock_t lock; /* protects pid, uid, euid fields */ - int pid; /* pid or -pgrp where SIGIO should be sent */ + struct pid *pid; /* pid or -pgrp where SIGIO should be sent */ + enum pid_type pid_type; /* Kind of process group SIGIO should be sent to */ uid_t uid, euid; /* uid/euid of process setting the owner */ int signum; /* posix.1b rt signal to be delivered on IO */ }; @@ -880,8 +881,10 @@ extern void kill_fasync(struct fasync_struct **, int, int); /* only for net: no internal synchronization */ extern void __kill_fasync(struct fasync_struct *, int, int); +extern int __f_setown(struct file *filp, struct pid *, enum pid_type, int force); extern int f_setown(struct file *filp, unsigned long arg, int force); extern void f_delown(struct file *filp); +extern pid_t f_getown(struct file *filp); extern int send_sigurg(struct fown_struct *fown); /* -- cgit v1.2.3 From b68e31d0ebbcc909d1941f9f230c9d062a3a13d3 Mon Sep 17 00:00:00 2001 From: Jeff Dike Date: Mon, 2 Oct 2006 02:17:18 -0700 Subject: [PATCH] const struct tty_operations As part of an SMP cleanliness pass over UML, I consted a bunch of structures in order to not have to document their locking. One of these structures was a struct tty_operations. In order to const it in UML without introducing compiler complaints, the declaration of tty_set_operations needs to be changed, and then all of its callers need to be fixed. This patch declares all struct tty_operations in the tree as const. In all cases, they are static and used only as input to tty_set_operations. As an extra check, I ran an i386 allyesconfig build which produced no extra warnings. 53 drivers are affected. I checked the history of a bunch of them, and in most cases, there have been only a handful of maintenance changes in the last six months. serial_core.c was the busiest one that I looked at. Signed-off-by: Jeff Dike Acked-by: Alan Cox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/tty_driver.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h index 58c961c9e170..5c8473bb6882 100644 --- a/include/linux/tty_driver.h +++ b/include/linux/tty_driver.h @@ -219,7 +219,8 @@ extern struct list_head tty_drivers; struct tty_driver *alloc_tty_driver(int lines); void put_tty_driver(struct tty_driver *driver); -void tty_set_operations(struct tty_driver *driver, struct tty_operations *op); +void tty_set_operations(struct tty_driver *driver, + const struct tty_operations *op); /* tty driver magic number */ #define TTY_DRIVER_MAGIC 0x5402 -- cgit v1.2.3 From d387cae075b0aec479adbdfb71df39f7de8e9adb Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Mon, 2 Oct 2006 02:17:22 -0700 Subject: [PATCH] pid: simplify pid iterators I think it is hardly possible to read the current do_each_task_pid(). The new version is much simpler and makes the code smaller. Only the do_each_task_pid change is tested, the do_each_pid_task isn't. Signed-off-by: Oleg Nesterov Cc: "Eric W. Biederman" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pid.h | 59 +++++++++++++++++++++-------------------------------- 1 file changed, 23 insertions(+), 36 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pid.h b/include/linux/pid.h index dba1b2d677a3..7e39767b4c60 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -102,42 +102,29 @@ static inline pid_t pid_nr(struct pid *pid) return nr; } -#define pid_next(task, type) \ - ((task)->pids[(type)].node.next) -#define pid_next_task(task, type) \ - hlist_entry(pid_next(task, type), struct task_struct, \ - pids[(type)].node) - - -/* We could use hlist_for_each_entry_rcu here but it takes more arguments - * than the do_each_task_pid/while_each_task_pid. So we roll our own - * to preserve the existing interface. - */ -#define do_each_task_pid(who, type, task) \ - if ((task = find_task_by_pid_type(type, who))) { \ - prefetch(pid_next(task, type)); \ - do { - -#define while_each_task_pid(who, type, task) \ - } while (pid_next(task, type) && ({ \ - task = pid_next_task(task, type); \ - rcu_dereference(task); \ - prefetch(pid_next(task, type)); \ - 1; }) ); \ - } - -#define do_each_pid_task(pid, type, task) \ - if ((task = pid_task(pid, type))) { \ - prefetch(pid_next(task, type)); \ - do { - -#define while_each_pid_task(pid, type, task) \ - } while (pid_next(task, type) && ({ \ - task = pid_next_task(task, type); \ - rcu_dereference(task); \ - prefetch(pid_next(task, type)); \ - 1; }) ); \ - } +#define do_each_task_pid(who, type, task) \ + do { \ + struct hlist_node *pos___; \ + struct pid *pid___ = find_pid(who); \ + if (pid___ != NULL) \ + hlist_for_each_entry_rcu((task), pos___, \ + &pid___->tasks[type], pids[type].node) { + +#define while_each_task_pid(who, type, task) \ + } \ + } while (0) + + +#define do_each_pid_task(pid, type, task) \ + do { \ + struct hlist_node *pos___; \ + if (pid != NULL) \ + hlist_for_each_entry_rcu((task), pos___, \ + &pid->tasks[type], pids[type].node) { + +#define while_each_pid_task(pid, type, task) \ + } \ + } while (0) #endif /* _LINUX_PID_H */ -- cgit v1.2.3 From aa5a6662f93f52605b6c447ba6f7291e92f515c5 Mon Sep 17 00:00:00 2001 From: Sukadev Bhattiprolu Date: Mon, 2 Oct 2006 02:17:23 -0700 Subject: [PATCH] Move pidmap to pspace.h Move struct pidmap and PIDMAP_ENTRIES to a new file, include/linux/pspace.h where it will be used in subsequent patches to define pid spaces. Its a subset of Eric Biederman's patch http://lkml.org/lkml/2006/2/6/285 [akpm@osdl.org: cleanups] Signed-off-by: Eric W. Biederman Signed-off-by: Sukadev Bhattiprolu Cc: Dave Hansen Cc: Serge Hallyn Cc: Cedric Le Goater Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pspace.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) create mode 100644 include/linux/pspace.h (limited to 'include/linux') diff --git a/include/linux/pspace.h b/include/linux/pspace.h new file mode 100644 index 000000000000..a8a064b0ad18 --- /dev/null +++ b/include/linux/pspace.h @@ -0,0 +1,16 @@ +#ifndef _LINUX_PSPACE_H +#define _LINUX_PSPACE_H + +#include +#include +#include +#include + +struct pidmap { + atomic_t nr_free; + void *page; +}; + +#define PIDMAP_ENTRIES ((PID_MAX_LIMIT + 8*PAGE_SIZE - 1)/PAGE_SIZE/8) + +#endif /* _LINUX_PSPACE_H */ -- cgit v1.2.3 From 3fbc96486459324e182717b03c50c90c880be6ec Mon Sep 17 00:00:00 2001 From: Sukadev Bhattiprolu Date: Mon, 2 Oct 2006 02:17:24 -0700 Subject: [PATCH] Define struct pspace Define a per-container pid space object. And create one instance of this object, init_pspace, to define the entire pid space. Subsequent patches will provide/use interfaces to create/destroy pid spaces. Its a subset/rework of Eric Biederman's patch http://lkml.org/lkml/2006/2/6/285 . Signed-off-by: Eric Biederman Signed-off-by: Sukadev Bhattiprolu Cc: Dave Hansen Cc: Serge Hallyn Cc: Cedric Le Goater Cc: Kirill Korotaev Cc: Andrey Savochkin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pspace.h | 7 +++++++ include/linux/sched.h | 1 - 2 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pspace.h b/include/linux/pspace.h index a8a064b0ad18..91d48b8b2d99 100644 --- a/include/linux/pspace.h +++ b/include/linux/pspace.h @@ -13,4 +13,11 @@ struct pidmap { #define PIDMAP_ENTRIES ((PID_MAX_LIMIT + 8*PAGE_SIZE - 1)/PAGE_SIZE/8) +struct pspace { + struct pidmap pidmap[PIDMAP_ENTRIES]; + int last_pid; +}; + +extern struct pspace init_pspace; + #endif /* _LINUX_PSPACE_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index dd6c2164e4a4..3b7c99265ace 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -118,7 +118,6 @@ extern unsigned long avenrun[]; /* Load averages */ extern unsigned long total_forks; extern int nr_threads; -extern int last_pid; DECLARE_PER_CPU(unsigned long, process_counts); extern int nr_processes(void); extern unsigned long nr_running(void); -- cgit v1.2.3 From 2425c08b37244005ff221efe4957d8aaff18609c Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 2 Oct 2006 02:17:28 -0700 Subject: [PATCH] usb: fixup usb so it uses struct pid The problem with remembering a user space process by its pid is that it is possible that the process will exit, pid wrap around will occur. Converting to a struct pid avoid that problem, and paves the way for implementing a pid namespace. Also since usb is the only user of kill_proc_info_as_uid rename kill_proc_info_as_uid to kill_pid_info_as_uid and have the new version take a struct pid. Signed-off-by: Eric W. Biederman Acked-by: Greg Kroah-Hartman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 3b7c99265ace..a7fff3304bd6 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1269,12 +1269,12 @@ extern int force_sig_info(int, struct siginfo *, struct task_struct *); extern int __kill_pgrp_info(int sig, struct siginfo *info, struct pid *pgrp); extern int kill_pgrp_info(int sig, struct siginfo *info, struct pid *pgrp); extern int kill_pid_info(int sig, struct siginfo *info, struct pid *pid); +extern int kill_pid_info_as_uid(int, struct siginfo *, struct pid *, uid_t, uid_t, u32); extern int kill_pgrp(struct pid *pid, int sig, int priv); extern int kill_pid(struct pid *pid, int sig, int priv); extern int __kill_pg_info(int sig, struct siginfo *info, pid_t pgrp); extern int kill_pg_info(int, struct siginfo *, pid_t); extern int kill_proc_info(int, struct siginfo *, pid_t); -extern int kill_proc_info_as_uid(int, struct siginfo *, pid_t, uid_t, uid_t, u32); extern void do_notify_parent(struct task_struct *, int); extern void force_sig(int, struct task_struct *); extern void force_sig_specific(int, struct task_struct *); -- cgit v1.2.3 From 3a872d89baae821a0f6e2c1055d4b47650661137 Mon Sep 17 00:00:00 2001 From: Ananth N Mavinakayanahalli Date: Mon, 2 Oct 2006 02:17:30 -0700 Subject: [PATCH] Kprobes: Make kprobe modules more portable In an effort to make kprobe modules more portable, here is a patch that: o Introduces the "symbol_name" field to struct kprobe. The symbol->address resolution now happens in the kernel in an architecture agnostic manner. 64-bit powerpc users no longer have to specify the ".symbols" o Introduces the "offset" field to struct kprobe to allow a user to specify an offset into a symbol. o The legacy mechanism of specifying the kprobe.addr is still supported. However, if both the kprobe.addr and kprobe.symbol_name are specified, probe registration fails with an -EINVAL. o The symbol resolution code uses kallsyms_lookup_name(). So CONFIG_KPROBES now depends on CONFIG_KALLSYMS o Apparantly kprobe modules were the only legitimate out-of-tree user of the kallsyms_lookup_name() EXPORT. Now that the symbol resolution happens in-kernel, remove the EXPORT as suggested by Christoph Hellwig o Modify tcp_probe.c that uses the kprobe interface so as to make it work on multiple platforms (in its earlier form, the code wouldn't work, say, on powerpc) Signed-off-by: Ananth N Mavinakayanahalli Signed-off-by: Prasanna S Panchamukhi Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kprobes.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 8bf6702da2a0..a5c5a0cb0d5c 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -77,6 +77,12 @@ struct kprobe { /* location of the probe point */ kprobe_opcode_t *addr; + /* Allow user to indicate symbol name of the probe point */ + char *symbol_name; + + /* Offset into the symbol */ + unsigned int offset; + /* Called before addr is executed. */ kprobe_pre_handler_t pre_handler; -- cgit v1.2.3 From 99219a3fbc2dcf2eaa954f7b2ac27299fd7894cd Mon Sep 17 00:00:00 2001 From: "bibo,mao" Date: Mon, 2 Oct 2006 02:17:35 -0700 Subject: [PATCH] kretprobe spinlock deadlock patch kprobe_flush_task() possibly calls kfree function during holding kretprobe_lock spinlock, if kfree function is probed by kretprobe that will incur spinlock deadlock. This patch moves kfree function out scope of kretprobe_lock. Signed-off-by: bibo, mao Signed-off-by: Ananth N Mavinakayanahalli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kprobes.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index a5c5a0cb0d5c..ac4c0559f751 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -202,7 +202,7 @@ void unregister_kretprobe(struct kretprobe *rp); struct kretprobe_instance *get_free_rp_inst(struct kretprobe *rp); void add_rp_inst(struct kretprobe_instance *ri); void kprobe_flush_task(struct task_struct *tk); -void recycle_rp_inst(struct kretprobe_instance *ri); +void recycle_rp_inst(struct kretprobe_instance *ri, struct hlist_head *head); #else /* CONFIG_KPROBES */ #define __kprobes /**/ -- cgit v1.2.3 From 0f532f3861d2c4e5aa7dcd33fb18e9975eb28457 Mon Sep 17 00:00:00 2001 From: Greg Banks Date: Mon, 2 Oct 2006 02:17:39 -0700 Subject: [PATCH] cpumask: add highest_possible_node_id cpumask: add highest_possible_node_id(), analogous to highest_possible_processor_id(). [pj@sgi.com: fix typo] Signed-off-by: Greg Banks Signed-off-by: Paul Jackson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nodemask.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index 1a9ef3e627d1..5dce5c21822c 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -352,6 +352,7 @@ extern nodemask_t node_possible_map; #define node_possible(node) node_isset((node), node_possible_map) #define first_online_node first_node(node_online_map) #define next_online_node(nid) next_node((nid), node_online_map) +int highest_possible_node_id(void); #else #define num_online_nodes() 1 #define num_possible_nodes() 1 @@ -359,6 +360,7 @@ extern nodemask_t node_possible_map; #define node_possible(node) ((node) == 0) #define first_online_node 0 #define next_online_node(nid) (MAX_NUMNODES) +#define highest_possible_node_id() 0 #endif #define any_online_node(mask) \ -- cgit v1.2.3 From bc591ccff27e6a85d3a0d6fcb16cfadcc45267a8 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 2 Oct 2006 02:17:44 -0700 Subject: [PATCH] knfsd: add a callback for when last rpc thread finishes nfsd has some cleanup that it wants to do when the last thread exits, and there will shortly be some more. So collect this all into one place and define a callback for an rpc service to call when the service is about to be destroyed. [akpm@osdl.org: cleanups, build fix] Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sunrpc/svc.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 73140ee5c638..bff5e9b486c2 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -42,6 +42,11 @@ struct svc_serv { int sv_tmpcnt; /* count of temporary sockets */ char * sv_name; /* service name */ + + void (*sv_shutdown)(struct svc_serv *serv); + /* Callback to use when last thread + * exits. + */ }; /* @@ -328,7 +333,8 @@ typedef void (*svc_thread_fn)(struct svc_rqst *); /* * Function prototypes. */ -struct svc_serv * svc_create(struct svc_program *, unsigned int); +struct svc_serv * svc_create(struct svc_program *, unsigned int, + void (*shutdown)(struct svc_serv*)); int svc_create_thread(svc_thread_fn, struct svc_serv *); void svc_exit_thread(struct svc_rqst *); void svc_destroy(struct svc_serv *); -- cgit v1.2.3 From 24e36663c375df577d2dcae437713481ffd6850c Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 2 Oct 2006 02:17:45 -0700 Subject: [PATCH] knfsd: be more selective in which sockets lockd listens on Currently lockd listens on UDP always, and TCP if CONFIG_NFSD_TCP is set. However as lockd performs services of the client as well, this is a problem. If CONFIG_NfSD_TCP is not set, and a tcp mount is used, the server will not be able to call back to lockd. So: - add an option to lockd_up saying which protocol is needed - Always open sockets for which an explicit port was given, otherwise only open a socket of the type required - Change nfsd to do one lockd_up per socket rather than one per thread. This - removes the dependancy on CONFIG_NFSD_TCP - means that lockd may open sockets other than at startup - means that lockd will *not* listen on UDP if the only mounts are TCP mount (and nfsd hasn't started). The latter is the only one that concerns me at all - I don't know if this might be a problem with some servers. Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/lockd/bind.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/lockd/bind.h b/include/linux/lockd/bind.h index b054debef2e0..81e3a185f951 100644 --- a/include/linux/lockd/bind.h +++ b/include/linux/lockd/bind.h @@ -30,7 +30,7 @@ extern struct nlmsvc_binding * nlmsvc_ops; * Functions exported by the lockd module */ extern int nlmclnt_proc(struct inode *, int, struct file_lock *); -extern int lockd_up(void); +extern int lockd_up(int proto); extern void lockd_down(void); #endif /* LINUX_LOCKD_BIND_H */ -- cgit v1.2.3 From 6658d3a7bbfd1768a7b599def47939417f0ee8ef Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 2 Oct 2006 02:17:46 -0700 Subject: [PATCH] knfsd: remove nfsd_versbits as intermediate storage for desired versions We have an array 'nfsd_version' which lists the available versions of nfsd, and 'nfsd_versions' (poor choice there :-() which lists the currently active versions. Then we have a bitmap - nfsd_versbits which says which versions are wanted. The bits in this bitset cause content to be copied from nfsd_version to nfsd_versions when nfsd starts. This patch removes nfsd_versbits and moves information directly from nfsd_version to nfsd_versions when requests for version changes arrive. Note that this doesn't make it possible to change versions while the server is running. This is because serv->sv_xdrsize is calculated when a service is created, and used when threads are created, and xdrsize depends on the active versions. Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nfsd/nfsd.h | 4 ++++ include/linux/nfsd/syscall.h | 17 ----------------- 2 files changed, 4 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfsd/nfsd.h b/include/linux/nfsd/nfsd.h index 2dcad295fece..46f1dc5b96dd 100644 --- a/include/linux/nfsd/nfsd.h +++ b/include/linux/nfsd/nfsd.h @@ -140,6 +140,10 @@ struct posix_acl *nfsd_get_posix_acl(struct svc_fh *, int); int nfsd_set_posix_acl(struct svc_fh *, int, struct posix_acl *); #endif +enum vers_op {NFSD_SET, NFSD_CLEAR, NFSD_TEST, NFSD_AVAIL }; +int nfsd_vers(int vers, enum vers_op change); +void nfsd_reset_versions(void); + /* * NFSv4 State diff --git a/include/linux/nfsd/syscall.h b/include/linux/nfsd/syscall.h index dae0faea2807..8bcddccb6c42 100644 --- a/include/linux/nfsd/syscall.h +++ b/include/linux/nfsd/syscall.h @@ -38,21 +38,6 @@ #define NFSCTL_GETFD 7 /* get an fh by path (used by mountd) */ #define NFSCTL_GETFS 8 /* get an fh by path with max FH len */ -/* - * Macros used to set version - */ -#define NFSCTL_VERSET(_cltbits, _v) ((_cltbits) |= (1 << (_v))) -#define NFSCTL_VERUNSET(_cltbits, _v) ((_cltbits) &= ~(1 << (_v))) -#define NFSCTL_VERISSET(_cltbits, _v) ((_cltbits) & (1 << (_v))) - -#if defined(CONFIG_NFSD_V4) -#define NFSCTL_VERALL (0x1c /* 0b011100 */) -#elif defined(CONFIG_NFSD_V3) -#define NFSCTL_VERALL (0x0c /* 0b001100 */) -#else -#define NFSCTL_VERALL (0x04 /* 0b000100 */) -#endif - /* SVC */ struct nfsctl_svc { unsigned short svc_port; @@ -134,8 +119,6 @@ extern int exp_delclient(struct nfsctl_client *ncp); extern int exp_export(struct nfsctl_export *nxp); extern int exp_unexport(struct nfsctl_export *nxp); -extern unsigned int nfsd_versbits; - #endif /* __KERNEL__ */ #endif /* NFSD_SYSCALL_H */ -- cgit v1.2.3 From 80212d59e32a8a8e030c2ddc5861d8ff70542c56 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 2 Oct 2006 02:17:47 -0700 Subject: [PATCH] knfsd: define new nfsdfs file: portlist - contains list of ports This file will list all ports that nfsd has open. Default when TCP enabled will be ipv4 udp 0.0.0.0 2049 ipv4 tcp 0.0.0.0 2049 Later, the list of ports will be settable. 'portlist' chosen rather than 'ports', to avoid unnecessary confusion with non-mainline patches which created 'ports' with different semantics. [akpm@osdl.org: cleanups, build fix] Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sunrpc/svcsock.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svcsock.h b/include/linux/sunrpc/svcsock.h index b4acb3d37c3f..3caf92d72a81 100644 --- a/include/linux/sunrpc/svcsock.h +++ b/include/linux/sunrpc/svcsock.h @@ -61,5 +61,6 @@ int svc_recv(struct svc_serv *, struct svc_rqst *, long); int svc_send(struct svc_rqst *); void svc_drop(struct svc_rqst *); void svc_sock_update_bufs(struct svc_serv *serv); +int svc_sock_names(char *buf, struct svc_serv *serv); #endif /* SUNRPC_SVCSOCK_H */ -- cgit v1.2.3 From b41b66d63c730cc45a1024e1f1e67439e507e40f Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 2 Oct 2006 02:17:48 -0700 Subject: [PATCH] knfsd: allow sockets to be passed to nfsd via 'portlist' Userspace should create and bind a socket (but not connectted) and write the 'fd' to portlist. This will cause the nfs server to listen on that socket. To close a socket, the name of the socket - as read from 'portlist' can be written to 'portlist' with a preceding '-'. Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nfsd/nfsd.h | 1 + include/linux/sunrpc/svcsock.h | 6 +++++- 2 files changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfsd/nfsd.h b/include/linux/nfsd/nfsd.h index 46f1dc5b96dd..e1dbc86c270b 100644 --- a/include/linux/nfsd/nfsd.h +++ b/include/linux/nfsd/nfsd.h @@ -143,6 +143,7 @@ int nfsd_set_posix_acl(struct svc_fh *, int, struct posix_acl *); enum vers_op {NFSD_SET, NFSD_CLEAR, NFSD_TEST, NFSD_AVAIL }; int nfsd_vers(int vers, enum vers_op change); void nfsd_reset_versions(void); +int nfsd_create_serv(void); /* diff --git a/include/linux/sunrpc/svcsock.h b/include/linux/sunrpc/svcsock.h index 3caf92d72a81..b8a9652b8755 100644 --- a/include/linux/sunrpc/svcsock.h +++ b/include/linux/sunrpc/svcsock.h @@ -61,6 +61,10 @@ int svc_recv(struct svc_serv *, struct svc_rqst *, long); int svc_send(struct svc_rqst *); void svc_drop(struct svc_rqst *); void svc_sock_update_bufs(struct svc_serv *serv); -int svc_sock_names(char *buf, struct svc_serv *serv); +int svc_sock_names(char *buf, struct svc_serv *serv, char *toclose); +int svc_addsock(struct svc_serv *serv, + int fd, + char *name_return, + int *proto); #endif /* SUNRPC_SVCSOCK_H */ -- cgit v1.2.3 From 6fb2b47fa16c81317ec282248e6cff521cca31c2 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 2 Oct 2006 02:17:50 -0700 Subject: [PATCH] knfsd: Drop 'serv' option to svc_recv and svc_process It isn't needed as it is available in rqstp->rq_server, and dropping it allows some local vars to be dropped. [akpm@osdl.org: build fix] Cc: "J. Bruce Fields" Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sunrpc/svc.h | 2 +- include/linux/sunrpc/svcsock.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index bff5e9b486c2..cb341f96eb8d 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -338,7 +338,7 @@ struct svc_serv * svc_create(struct svc_program *, unsigned int, int svc_create_thread(svc_thread_fn, struct svc_serv *); void svc_exit_thread(struct svc_rqst *); void svc_destroy(struct svc_serv *); -int svc_process(struct svc_serv *, struct svc_rqst *); +int svc_process(struct svc_rqst *); int svc_register(struct svc_serv *, int, unsigned short); void svc_wake_up(struct svc_serv *); void svc_reserve(struct svc_rqst *rqstp, int space); diff --git a/include/linux/sunrpc/svcsock.h b/include/linux/sunrpc/svcsock.h index b8a9652b8755..d5f15e8db929 100644 --- a/include/linux/sunrpc/svcsock.h +++ b/include/linux/sunrpc/svcsock.h @@ -57,7 +57,7 @@ struct svc_sock { */ int svc_makesock(struct svc_serv *, int, unsigned short); void svc_delete_socket(struct svc_sock *); -int svc_recv(struct svc_serv *, struct svc_rqst *, long); +int svc_recv(struct svc_rqst *, long); int svc_send(struct svc_rqst *); void svc_drop(struct svc_rqst *); void svc_sock_update_bufs(struct svc_serv *serv); -- cgit v1.2.3 From 36bdfc8bae51339aa27ef8e4ce148185293061ae Mon Sep 17 00:00:00 2001 From: Greg Banks Date: Mon, 2 Oct 2006 02:17:54 -0700 Subject: [PATCH] knfsd: move tempsock aging to a timer Following are 11 patches from Greg Banks which combine to make knfsd more Numa-aware. They reduce hitting on 'global' data structures, and create some data-structures that can be node-local. knfsd threads are bound to a particular node, and the thread to handle a new request is chosen from the threads that are attach to the node that received the interrupt. The distribution of threads across nodes can be controlled by a new file in the 'nfsd' filesystem, though the default approach of an even spread is probably fine for most sites. Some (old) numbers that show the efficacy of these patches: N == number of NICs == number of CPUs == nmber of clients. Number of NUMA nodes == N/2 N Throughput, MiB/s CPU usage, % (max=N*100) Before After Before After --- ------ ---- ----- ----- 4 312 435 350 228 6 500 656 501 418 8 562 804 690 589 This patch: Move the aging of RPC/TCP connection sockets from the main svc_recv() loop to a timer which uses a mark-and-sweep algorithm every 6 minutes. This reduces the amount of work that needs to be done in the main RPC loop and the length of time we need to hold the (effectively global) svc_serv->sv_lock. [akpm@osdl.org: cleanup] Signed-off-by: Greg Banks Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sunrpc/svc.h | 1 + include/linux/sunrpc/svcsock.h | 2 ++ 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index cb341f96eb8d..5eabded11061 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -40,6 +40,7 @@ struct svc_serv { struct list_head sv_permsocks; /* all permanent sockets */ struct list_head sv_tempsocks; /* all temporary sockets */ int sv_tmpcnt; /* count of temporary sockets */ + struct timer_list sv_temptimer; /* timer for aging temporary sockets */ char * sv_name; /* service name */ diff --git a/include/linux/sunrpc/svcsock.h b/include/linux/sunrpc/svcsock.h index d5f15e8db929..846aee95eec7 100644 --- a/include/linux/sunrpc/svcsock.h +++ b/include/linux/sunrpc/svcsock.h @@ -31,6 +31,8 @@ struct svc_sock { #define SK_DEAD 6 /* socket closed */ #define SK_CHNGBUF 7 /* need to change snd/rcv buffer sizes */ #define SK_DEFERRED 8 /* request on sk_deferred */ +#define SK_OLD 9 /* used for temp socket aging mark+sweep */ +#define SK_DETACHED 10 /* detached from tempsocks list */ int sk_reserved; /* space on outq that is reserved */ -- cgit v1.2.3 From c45c357d7dbc9e94338f44349e0035149da86b26 Mon Sep 17 00:00:00 2001 From: Greg Banks Date: Mon, 2 Oct 2006 02:17:54 -0700 Subject: [PATCH] knfsd: convert sk_inuse to atomic_t Convert the svc_sock->sk_inuse counter from an int protected by svc_serv->sv_lock, to an atomic. This reduces the number of places we need to take the (effectively global) svc_serv->sv_lock. Signed-off-by: Greg Banks Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- 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 846aee95eec7..17cb834a748c 100644 --- a/include/linux/sunrpc/svcsock.h +++ b/include/linux/sunrpc/svcsock.h @@ -21,7 +21,7 @@ struct svc_sock { struct sock * sk_sk; /* INET layer */ struct svc_serv * sk_server; /* service for this socket */ - unsigned int sk_inuse; /* use count */ + atomic_t sk_inuse; /* use count */ unsigned long sk_flags; #define SK_BUSY 0 /* enqueued/receiving */ #define SK_CONN 1 /* conn pending */ -- cgit v1.2.3 From 1a68d952af5f43032012d26dd0d5164c9e9986bc Mon Sep 17 00:00:00 2001 From: Greg Banks Date: Mon, 2 Oct 2006 02:17:55 -0700 Subject: [PATCH] knfsd: use new lock for svc_sock deferred list Protect the svc_sock->sk_deferred list with a new lock svc_sock->sk_defer_lock instead of svc_serv->sv_lock. Using the more fine-grained lock reduces the number of places we need to take the svc_serv lock. Signed-off-by: Greg Banks Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sunrpc/svcsock.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svcsock.h b/include/linux/sunrpc/svcsock.h index 17cb834a748c..7766a1001660 100644 --- a/include/linux/sunrpc/svcsock.h +++ b/include/linux/sunrpc/svcsock.h @@ -36,6 +36,7 @@ struct svc_sock { int sk_reserved; /* space on outq that is reserved */ + spinlock_t sk_defer_lock; /* protects sk_deferred */ struct list_head sk_deferred; /* deferred requests that need to * be revisted */ struct mutex sk_mutex; /* to serialize sending data */ -- cgit v1.2.3 From 5685f0fa1c24b138d041ef129ed419c5effa40e1 Mon Sep 17 00:00:00 2001 From: Greg Banks Date: Mon, 2 Oct 2006 02:17:56 -0700 Subject: [PATCH] knfsd: convert sk_reserved to atomic_t Convert the svc_sock->sk_reserved variable from an int protected by svc_serv->sv_lock, to an atomic. This reduces (by 1) the number of places we need to take the (effectively global) svc_serv->sv_lock. Signed-off-by: Greg Banks Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- 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 7766a1001660..7154e71c6d1f 100644 --- a/include/linux/sunrpc/svcsock.h +++ b/include/linux/sunrpc/svcsock.h @@ -34,7 +34,7 @@ struct svc_sock { #define SK_OLD 9 /* used for temp socket aging mark+sweep */ #define SK_DETACHED 10 /* detached from tempsocks list */ - int sk_reserved; /* space on outq that is reserved */ + atomic_t sk_reserved; /* space on outq that is reserved */ spinlock_t sk_defer_lock; /* protects sk_deferred */ struct list_head sk_deferred; /* deferred requests that need to -- cgit v1.2.3 From 3262c816a3d7fb1eaabce633caa317887ed549ae Mon Sep 17 00:00:00 2001 From: Greg Banks Date: Mon, 2 Oct 2006 02:17:58 -0700 Subject: [PATCH] knfsd: split svc_serv into pools Split out the list of idle threads and pending sockets from svc_serv into a new svc_pool structure, and allocate a fixed number (in this patch, 1) of pools per svc_serv. The new structure contains a lock which takes over several of the duties of svc_serv->sv_lock, which is now relegated to protecting only sv_tempsocks, sv_permsocks, and sv_tmpcnt in svc_serv. The point is to move the hottest fields out of svc_serv and into svc_pool, allowing a following patch to arrange for a svc_pool per NUMA node or per CPU. This is a major step towards making the NFS server NUMA-friendly. Signed-off-by: Greg Banks Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sunrpc/svc.h | 25 +++++++++++++++++++++++-- include/linux/sunrpc/svcsock.h | 1 + 2 files changed, 24 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 5eabded11061..c27d806af310 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -17,6 +17,25 @@ #include #include + +/* + * + * RPC service thread pool. + * + * Pool of threads and temporary sockets. Generally there is only + * a single one of these per RPC service, but on NUMA machines those + * services that can benefit from it (i.e. nfs but not lockd) will + * have one pool per NUMA node. This optimisation reduces cross- + * node traffic on multi-node NUMA NFS servers. + */ +struct svc_pool { + unsigned int sp_id; /* pool id; also node id on NUMA */ + spinlock_t sp_lock; /* protects all fields */ + struct list_head sp_threads; /* idle server threads */ + struct list_head sp_sockets; /* pending sockets */ + unsigned int sp_nrthreads; /* # of threads in pool */ +} ____cacheline_aligned_in_smp; + /* * RPC service. * @@ -28,8 +47,6 @@ * We currently do not support more than one RPC program per daemon. */ struct svc_serv { - struct list_head sv_threads; /* idle server threads */ - struct list_head sv_sockets; /* pending sockets */ struct svc_program * sv_program; /* RPC program */ struct svc_stat * sv_stats; /* RPC statistics */ spinlock_t sv_lock; @@ -44,6 +61,9 @@ struct svc_serv { char * sv_name; /* service name */ + unsigned int sv_nrpools; /* number of thread pools */ + struct svc_pool * sv_pools; /* array of thread pools */ + void (*sv_shutdown)(struct svc_serv *serv); /* Callback to use when last thread * exits. @@ -138,6 +158,7 @@ struct svc_rqst { int rq_addrlen; struct svc_serv * rq_server; /* RPC service definition */ + struct svc_pool * rq_pool; /* thread pool */ struct svc_procedure * rq_procinfo; /* procedure info */ struct auth_ops * rq_authop; /* authentication flavour */ struct svc_cred rq_cred; /* auth info */ diff --git a/include/linux/sunrpc/svcsock.h b/include/linux/sunrpc/svcsock.h index 7154e71c6d1f..4c296152cbfa 100644 --- a/include/linux/sunrpc/svcsock.h +++ b/include/linux/sunrpc/svcsock.h @@ -20,6 +20,7 @@ struct svc_sock { struct socket * sk_sock; /* berkeley socket layer */ struct sock * sk_sk; /* INET layer */ + struct svc_pool * sk_pool; /* current pool iff queued */ struct svc_serv * sk_server; /* service for this socket */ atomic_t sk_inuse; /* use count */ unsigned long sk_flags; -- cgit v1.2.3 From 9a24ab5749a31aa10ee60d9310ad72f24d7c38ab Mon Sep 17 00:00:00 2001 From: Greg Banks Date: Mon, 2 Oct 2006 02:17:58 -0700 Subject: [PATCH] knfsd: add svc_get add svc_get() for those occasions when we need to temporarily bump up svc_serv->sv_nrthreads as a pseudo refcount. Signed-off-by: Greg Banks Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sunrpc/svc.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index c27d806af310..54d8e7bc2341 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -70,6 +70,17 @@ struct svc_serv { */ }; +/* + * We use sv_nrthreads as a reference count. svc_destroy() drops + * this refcount, so we need to bump it up around operations that + * change the number of threads. Horrible, but there it is. + * Should be called with the BKL held. + */ +static inline void svc_get(struct svc_serv *serv) +{ + serv->sv_nrthreads++; +} + /* * Maximum payload size supported by a kernel RPC server. * This is use to determine the max number of pages nfsd is -- cgit v1.2.3 From a74554429eada89a7ddb47317e6a2968d03e41a2 Mon Sep 17 00:00:00 2001 From: Greg Banks Date: Mon, 2 Oct 2006 02:17:59 -0700 Subject: [PATCH] knfsd: add svc_set_num_threads Currently knfsd keeps its own list of all nfsd threads in nfssvc.c; add a new way of managing the list of all threads in a svc_serv. Add svc_create_pooled() to allow creation of a svc_serv whose threads are managed by the sunrpc code. Add svc_set_num_threads() to manage the number of threads in a service, either per-pool or globally across the service. Signed-off-by: Greg Banks Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sunrpc/svc.h | 21 ++++++++++++++++----- 1 file changed, 16 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 54d8e7bc2341..f2eeb833e7d8 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -17,6 +17,10 @@ #include #include +/* + * This is the RPC server thread function prototype + */ +typedef void (*svc_thread_fn)(struct svc_rqst *); /* * @@ -34,6 +38,7 @@ struct svc_pool { struct list_head sp_threads; /* idle server threads */ struct list_head sp_sockets; /* pending sockets */ unsigned int sp_nrthreads; /* # of threads in pool */ + struct list_head sp_all_threads; /* all server threads */ } ____cacheline_aligned_in_smp; /* @@ -68,6 +73,11 @@ struct svc_serv { /* Callback to use when last thread * exits. */ + + struct module * sv_module; /* optional module to count when + * adding threads */ + svc_thread_fn sv_function; /* main function for threads */ + int sv_kill_signal; /* signal to kill threads */ }; /* @@ -164,6 +174,7 @@ static inline void svc_putu32(struct kvec *iov, __be32 val) */ struct svc_rqst { struct list_head rq_list; /* idle list */ + struct list_head rq_all; /* all threads list */ struct svc_sock * rq_sock; /* socket */ struct sockaddr_in rq_addr; /* peer address */ int rq_addrlen; @@ -218,6 +229,7 @@ struct svc_rqst { * to prevent encrypting page * cache pages */ wait_queue_head_t rq_wait; /* synchronization */ + struct task_struct *rq_task; /* service thread */ }; /* @@ -358,11 +370,6 @@ struct svc_procedure { unsigned int pc_xdrressize; /* maximum size of XDR reply */ }; -/* - * This is the RPC server thread function prototype - */ -typedef void (*svc_thread_fn)(struct svc_rqst *); - /* * Function prototypes. */ @@ -370,6 +377,10 @@ struct svc_serv * svc_create(struct svc_program *, unsigned int, void (*shutdown)(struct svc_serv*)); int svc_create_thread(svc_thread_fn, struct svc_serv *); void svc_exit_thread(struct svc_rqst *); +struct svc_serv * svc_create_pooled(struct svc_program *, unsigned int, + void (*shutdown)(struct svc_serv*), + svc_thread_fn, int sig, struct module *); +int svc_set_num_threads(struct svc_serv *, struct svc_pool *, int); void svc_destroy(struct svc_serv *); int svc_process(struct svc_rqst *); int svc_register(struct svc_serv *, int, unsigned short); -- cgit v1.2.3 From bfd241600a3b0db4fe43c859f1460d0a958d924a Mon Sep 17 00:00:00 2001 From: Greg Banks Date: Mon, 2 Oct 2006 02:18:01 -0700 Subject: [PATCH] knfsd: make rpc threads pools numa aware Actually implement multiple pools. On NUMA machines, allocate a svc_pool per NUMA node; on SMP a svc_pool per CPU; otherwise a single global pool. Enqueue sockets on the svc_pool corresponding to the CPU on which the socket bh is run (i.e. the NIC interrupt CPU). Threads have their cpu mask set to limit them to the CPUs in the svc_pool that owns them. This is the patch that allows an Altix to scale NFS traffic linearly beyond 4 CPUs and 4 NICs. Incorporates changes and feedback from Neil Brown, Trond Myklebust, and Christoph Hellwig. Signed-off-by: Greg Banks Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sunrpc/svc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index f2eeb833e7d8..4ebcdf91f3b3 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -386,5 +386,6 @@ int svc_process(struct svc_rqst *); int svc_register(struct svc_serv *, int, unsigned short); void svc_wake_up(struct svc_serv *); void svc_reserve(struct svc_rqst *rqstp, int space); +struct svc_pool * svc_pool_for_cpu(struct svc_serv *serv, int cpu); #endif /* SUNRPC_SVC_H */ -- cgit v1.2.3 From 12fd352038c037ba3a7071a2ca8597c55114abc3 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 2 Oct 2006 02:18:03 -0700 Subject: [PATCH] nfsd: lockdep annotation while doing a kernel make modules_install install over an NFS mount. ============================================= [ INFO: possible recursive locking detected ] --------------------------------------------- nfsd/9550 is trying to acquire lock: (&inode->i_mutex){--..}, at: [] mutex_lock+0x1c/0x1f but task is already holding lock: (&inode->i_mutex){--..}, at: [] mutex_lock+0x1c/0x1f other info that might help us debug this: 2 locks held by nfsd/9550: #0: (hash_sem){..--}, at: [] exp_readlock+0xd/0xf [nfsd] #1: (&inode->i_mutex){--..}, at: [] mutex_lock+0x1c/0x1f stack backtrace: [] show_trace_log_lvl+0x58/0x152 [] show_trace+0xd/0x10 [] dump_stack+0x19/0x1b [] __lock_acquire+0x77a/0x9a3 [] lock_acquire+0x60/0x80 [] __mutex_lock_slowpath+0xa7/0x20e [] mutex_lock+0x1c/0x1f [] vfs_unlink+0x34/0x8a [] nfsd_unlink+0x18f/0x1e2 [nfsd] [] nfsd3_proc_remove+0x95/0xa2 [nfsd] [] nfsd_dispatch+0xc0/0x178 [nfsd] [] svc_process+0x3a5/0x5ed [] nfsd+0x1a7/0x305 [nfsd] [] kernel_thread_helper+0x5/0xb DWARF2 unwinder stuck at kernel_thread_helper+0x5/0xb Leftover inexact backtrace: [] show_trace+0xd/0x10 [] dump_stack+0x19/0x1b [] __lock_acquire+0x77a/0x9a3 [] lock_acquire+0x60/0x80 [] __mutex_lock_slowpath+0xa7/0x20e [] mutex_lock+0x1c/0x1f [] vfs_unlink+0x34/0x8a [] nfsd_unlink+0x18f/0x1e2 [nfsd] [] nfsd3_proc_remove+0x95/0xa2 [nfsd] [] nfsd_dispatch+0xc0/0x178 [nfsd] [] svc_process+0x3a5/0x5ed [] nfsd+0x1a7/0x305 [nfsd] [] kernel_thread_helper+0x5/0xb ============================================= [ INFO: possible recursive locking detected ] --------------------------------------------- nfsd/9580 is trying to acquire lock: (&inode->i_mutex){--..}, at: [] mutex_lock+0x1c/0x1f but task is already holding lock: (&inode->i_mutex){--..}, at: [] mutex_lock+0x1c/0x1f other info that might help us debug this: 2 locks held by nfsd/9580: #0: (hash_sem){..--}, at: [] exp_readlock+0xd/0xf [nfsd] #1: (&inode->i_mutex){--..}, at: [] mutex_lock+0x1c/0x1f stack backtrace: [] show_trace_log_lvl+0x58/0x152 [] show_trace+0xd/0x10 [] dump_stack+0x19/0x1b [] __lock_acquire+0x77a/0x9a3 [] lock_acquire+0x60/0x80 [] __mutex_lock_slowpath+0xa7/0x20e [] mutex_lock+0x1c/0x1f [] nfsd_setattr+0x2c8/0x499 [nfsd] [] nfsd_create_v3+0x31b/0x4ac [nfsd] [] nfsd3_proc_create+0x128/0x138 [nfsd] [] nfsd_dispatch+0xc0/0x178 [nfsd] [] svc_process+0x3a5/0x5ed [] nfsd+0x1a7/0x305 [nfsd] [] kernel_thread_helper+0x5/0xb DWARF2 unwinder stuck at kernel_thread_helper+0x5/0xb Leftover inexact backtrace: [] show_trace+0xd/0x10 [] dump_stack+0x19/0x1b [] __lock_acquire+0x77a/0x9a3 [] lock_acquire+0x60/0x80 [] __mutex_lock_slowpath+0xa7/0x20e [] mutex_lock+0x1c/0x1f [] nfsd_setattr+0x2c8/0x499 [nfsd] [] nfsd_create_v3+0x31b/0x4ac [nfsd] [] nfsd3_proc_create+0x128/0x138 [nfsd] [] nfsd_dispatch+0xc0/0x178 [nfsd] [] svc_process+0x3a5/0x5ed [] nfsd+0x1a7/0x305 [nfsd] [] kernel_thread_helper+0x5/0xb Signed-off-by: Peter Zijlstra Cc: Neil Brown Cc: Ingo Molnar Cc: Arjan van de Ven Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nfsd/nfsfh.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfsd/nfsfh.h b/include/linux/nfsd/nfsfh.h index 31a3cb617ce0..069257ea99a0 100644 --- a/include/linux/nfsd/nfsfh.h +++ b/include/linux/nfsd/nfsfh.h @@ -290,8 +290,9 @@ fill_post_wcc(struct svc_fh *fhp) * vfs.c:nfsd_rename as it needs to grab 2 i_mutex's at once * so, any changes here should be reflected there. */ + static inline void -fh_lock(struct svc_fh *fhp) +fh_lock_nested(struct svc_fh *fhp, unsigned int subclass) { struct dentry *dentry = fhp->fh_dentry; struct inode *inode; @@ -310,11 +311,17 @@ fh_lock(struct svc_fh *fhp) } inode = dentry->d_inode; - mutex_lock(&inode->i_mutex); + mutex_lock_nested(&inode->i_mutex, subclass); fill_pre_wcc(fhp); fhp->fh_locked = 1; } +static inline void +fh_lock(struct svc_fh *fhp) +{ + fh_lock_nested(fhp, I_MUTEX_NORMAL); +} + /* * Unlock a file handle/inode */ -- cgit v1.2.3 From ab516013ad9ca47f1d3a936fa81303bfbf734d52 Mon Sep 17 00:00:00 2001 From: "Serge E. Hallyn" Date: Mon, 2 Oct 2006 02:18:06 -0700 Subject: [PATCH] namespaces: add nsproxy This patch adds a nsproxy structure to the task struct. Later patches will move the fs namespace pointer into this structure, and introduce a new utsname namespace into the nsproxy. The vserver and openvz functionality, then, would be implemented in large part by virtualizing/isolating more and more resources into namespaces, each contained in the nsproxy. [akpm@osdl.org: build fix] Signed-off-by: Serge Hallyn Cc: Kirill Korotaev Cc: "Eric W. Biederman" Cc: Herbert Poetzl Cc: Andrey Savochkin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/init_task.h | 7 +++++++ include/linux/nsproxy.h | 45 +++++++++++++++++++++++++++++++++++++++++++++ include/linux/sched.h | 2 ++ 3 files changed, 54 insertions(+) create mode 100644 include/linux/nsproxy.h (limited to 'include/linux') diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 60aac2cea0cf..8f8bb422a5c7 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -68,6 +68,12 @@ .session = 1, \ } +extern struct nsproxy init_nsproxy; +#define INIT_NSPROXY(nsproxy) { \ + .count = ATOMIC_INIT(1), \ + .nslock = SPIN_LOCK_UNLOCKED, \ +} + #define INIT_SIGHAND(sighand) { \ .count = ATOMIC_INIT(1), \ .action = { { { .sa_handler = NULL, } }, }, \ @@ -117,6 +123,7 @@ extern struct group_info init_groups; .files = &init_files, \ .signal = &init_signals, \ .sighand = &init_sighand, \ + .nsproxy = &init_nsproxy, \ .pending = { \ .list = LIST_HEAD_INIT(tsk.pending.list), \ .signal = {{0}}}, \ diff --git a/include/linux/nsproxy.h b/include/linux/nsproxy.h new file mode 100644 index 000000000000..7bdebfaab6a5 --- /dev/null +++ b/include/linux/nsproxy.h @@ -0,0 +1,45 @@ +#ifndef _LINUX_NSPROXY_H +#define _LINUX_NSPROXY_H + +#include +#include + +/* + * A structure to contain pointers to all per-process + * namespaces - fs (mount), uts, network, sysvipc, etc. + * + * 'count' is the number of tasks holding a reference. + * The count for each namespace, then, will be the number + * of nsproxies pointing to it, not the number of tasks. + * + * The nsproxy is shared by tasks which share all namespaces. + * As soon as a single namespace is cloned or unshared, the + * nsproxy is copied. + */ +struct nsproxy { + atomic_t count; + spinlock_t nslock; +}; +extern struct nsproxy init_nsproxy; + +struct nsproxy *dup_namespaces(struct nsproxy *orig); +int copy_namespaces(int flags, struct task_struct *tsk); +void get_task_namespaces(struct task_struct *tsk); +void free_nsproxy(struct nsproxy *ns); + +static inline void put_nsproxy(struct nsproxy *ns) +{ + if (atomic_dec_and_test(&ns->count)) { + free_nsproxy(ns); + } +} + +static inline void exit_task_namespaces(struct task_struct *p) +{ + struct nsproxy *ns = p->nsproxy; + if (ns) { + put_nsproxy(ns); + p->nsproxy = NULL; + } +} +#endif diff --git a/include/linux/sched.h b/include/linux/sched.h index a7fff3304bd6..4fa631fa55e3 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -239,6 +239,7 @@ extern signed long schedule_timeout_uninterruptible(signed long timeout); asmlinkage void schedule(void); struct namespace; +struct nsproxy; /* Maximum number of active map areas.. This is a random (large) number */ #define DEFAULT_MAX_MAP_COUNT 65536 @@ -898,6 +899,7 @@ struct task_struct { struct files_struct *files; /* namespace */ struct namespace *namespace; + struct nsproxy *nsproxy; /* signal handlers */ struct signal_struct *signal; struct sighand_struct *sighand; -- cgit v1.2.3 From 1651e14e28a2d9f446018ef522882e0709a2ce4f Mon Sep 17 00:00:00 2001 From: "Serge E. Hallyn" Date: Mon, 2 Oct 2006 02:18:08 -0700 Subject: [PATCH] namespaces: incorporate fs namespace into nsproxy This moves the mount namespace into the nsproxy. The mount namespace count now refers to the number of nsproxies point to it, rather than the number of tasks. As a result, the unshare_namespace() function in kernel/fork.c no longer checks whether it is being shared. Signed-off-by: Serge Hallyn Cc: Kirill Korotaev Cc: "Eric W. Biederman" Cc: Herbert Poetzl Cc: Andrey Savochkin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/init_task.h | 1 + include/linux/namespace.h | 6 ++---- include/linux/nsproxy.h | 3 +++ include/linux/sched.h | 4 +--- 4 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 8f8bb422a5c7..4865348ca8bd 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -72,6 +72,7 @@ extern struct nsproxy init_nsproxy; #define INIT_NSPROXY(nsproxy) { \ .count = ATOMIC_INIT(1), \ .nslock = SPIN_LOCK_UNLOCKED, \ + .namespace = NULL, \ } #define INIT_SIGHAND(sighand) { \ diff --git a/include/linux/namespace.h b/include/linux/namespace.h index 3abc8e3b4879..d137009f0b2b 100644 --- a/include/linux/namespace.h +++ b/include/linux/namespace.h @@ -4,6 +4,7 @@ #include #include +#include struct namespace { atomic_t count; @@ -26,11 +27,8 @@ static inline void put_namespace(struct namespace *namespace) static inline void exit_namespace(struct task_struct *p) { - struct namespace *namespace = p->namespace; + struct namespace *namespace = p->nsproxy->namespace; if (namespace) { - task_lock(p); - p->namespace = NULL; - task_unlock(p); put_namespace(namespace); } } diff --git a/include/linux/nsproxy.h b/include/linux/nsproxy.h index 7bdebfaab6a5..7ebe66670c59 100644 --- a/include/linux/nsproxy.h +++ b/include/linux/nsproxy.h @@ -4,6 +4,8 @@ #include #include +struct namespace; + /* * A structure to contain pointers to all per-process * namespaces - fs (mount), uts, network, sysvipc, etc. @@ -19,6 +21,7 @@ struct nsproxy { atomic_t count; spinlock_t nslock; + struct namespace *namespace; }; extern struct nsproxy init_nsproxy; diff --git a/include/linux/sched.h b/include/linux/sched.h index 4fa631fa55e3..670b89a20070 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -238,7 +238,6 @@ extern signed long schedule_timeout_interruptible(signed long timeout); extern signed long schedule_timeout_uninterruptible(signed long timeout); asmlinkage void schedule(void); -struct namespace; struct nsproxy; /* Maximum number of active map areas.. This is a random (large) number */ @@ -897,8 +896,7 @@ struct task_struct { struct fs_struct *fs; /* open file information */ struct files_struct *files; -/* namespace */ - struct namespace *namespace; +/* namespaces */ struct nsproxy *nsproxy; /* signal handlers */ struct signal_struct *signal; -- cgit v1.2.3 From 0bdd7aab7f0ecd5d337910816aa058c18398628e Mon Sep 17 00:00:00 2001 From: "Serge E. Hallyn" Date: Mon, 2 Oct 2006 02:18:10 -0700 Subject: [PATCH] namespaces: utsname: introduce temporary helpers Define utsname() and init_utsname() which return &system_utsname. Users of system_utsname will be changed to use these helpers, after which system_utsname will disappear. Signed-off-by: Serge E. Hallyn Cc: Kirill Korotaev Cc: "Eric W. Biederman" Cc: Herbert Poetzl Cc: Andrey Savochkin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/utsname.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/utsname.h b/include/linux/utsname.h index 13e1da0c538d..77e97a5755d9 100644 --- a/include/linux/utsname.h +++ b/include/linux/utsname.h @@ -32,5 +32,15 @@ struct new_utsname { extern struct new_utsname system_utsname; +static inline struct new_utsname *utsname(void) +{ + return &system_utsname; +} + +static inline struct new_utsname *init_utsname(void) +{ + return &system_utsname; +} + extern struct rw_semaphore uts_sem; #endif -- cgit v1.2.3 From e9ff3990f08e9a0c2839cc22808b01732ea5b3e4 Mon Sep 17 00:00:00 2001 From: "Serge E. Hallyn" Date: Mon, 2 Oct 2006 02:18:11 -0700 Subject: [PATCH] namespaces: utsname: switch to using uts namespaces Replace references to system_utsname to the per-process uts namespace where appropriate. This includes things like uname. Changes: Per Eric Biederman's comments, use the per-process uts namespace for ELF_PLATFORM, sunrpc, and parts of net/ipv4/ipconfig.c [jdike@addtoit.com: UML fix] [clg@fr.ibm.com: cleanup] [akpm@osdl.org: build fix] Signed-off-by: Serge E. Hallyn Cc: Kirill Korotaev Cc: "Eric W. Biederman" Cc: Herbert Poetzl Cc: Andrey Savochkin Signed-off-by: Cedric Le Goater Cc: Jeff Dike Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/lockd/lockd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index 0d92c468d55a..47b7dbd647a6 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -80,7 +80,7 @@ struct nlm_wait; /* * Memory chunk for NLM client RPC request. */ -#define NLMCLNT_OHSIZE (sizeof(system_utsname.nodename)+10) +#define NLMCLNT_OHSIZE (sizeof(utsname()->nodename)+10) struct nlm_rqst { unsigned int a_flags; /* initial RPC task flags */ struct nlm_host * a_host; /* host handle */ -- cgit v1.2.3 From 4865ecf1315b450ab3317a745a6678c04d311e40 Mon Sep 17 00:00:00 2001 From: "Serge E. Hallyn" Date: Mon, 2 Oct 2006 02:18:14 -0700 Subject: [PATCH] namespaces: utsname: implement utsname namespaces This patch defines the uts namespace and some manipulators. Adds the uts namespace to task_struct, and initializes a system-wide init namespace. It leaves a #define for system_utsname so sysctl will compile. This define will be removed in a separate patch. [akpm@osdl.org: build fix, cleanup] Signed-off-by: Serge Hallyn Cc: Kirill Korotaev Cc: "Eric W. Biederman" Cc: Herbert Poetzl Cc: Andrey Savochkin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/init_task.h | 2 ++ include/linux/nsproxy.h | 2 ++ include/linux/sched.h | 1 + include/linux/utsname.h | 40 +++++++++++++++++++++++++++++++++++++--- 4 files changed, 42 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 4865348ca8bd..e08531ec32f0 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -4,6 +4,7 @@ #include #include #include +#include #include #define INIT_FDTABLE \ @@ -72,6 +73,7 @@ extern struct nsproxy init_nsproxy; #define INIT_NSPROXY(nsproxy) { \ .count = ATOMIC_INIT(1), \ .nslock = SPIN_LOCK_UNLOCKED, \ + .uts_ns = &init_uts_ns, \ .namespace = NULL, \ } diff --git a/include/linux/nsproxy.h b/include/linux/nsproxy.h index 7ebe66670c59..9c2e0ad508db 100644 --- a/include/linux/nsproxy.h +++ b/include/linux/nsproxy.h @@ -5,6 +5,7 @@ #include struct namespace; +struct uts_namespace; /* * A structure to contain pointers to all per-process @@ -21,6 +22,7 @@ struct namespace; struct nsproxy { atomic_t count; spinlock_t nslock; + struct uts_namespace *uts_ns; struct namespace *namespace; }; extern struct nsproxy init_nsproxy; diff --git a/include/linux/sched.h b/include/linux/sched.h index 670b89a20070..46d6f5be72f2 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -753,6 +753,7 @@ static inline void prefetch_stack(struct task_struct *t) { } struct audit_context; /* See audit.c */ struct mempolicy; struct pipe_inode_info; +struct uts_namespace; enum sleep_type { SLEEP_NORMAL, diff --git a/include/linux/utsname.h b/include/linux/utsname.h index 77e97a5755d9..afa54e1542b3 100644 --- a/include/linux/utsname.h +++ b/include/linux/utsname.h @@ -1,6 +1,11 @@ #ifndef _LINUX_UTSNAME_H #define _LINUX_UTSNAME_H +#include +#include +#include +#include + #define __OLD_UTS_LEN 8 struct oldold_utsname { @@ -30,17 +35,46 @@ struct new_utsname { char domainname[65]; }; -extern struct new_utsname system_utsname; +struct uts_namespace { + struct kref kref; + struct new_utsname name; +}; +extern struct uts_namespace init_uts_ns; + +static inline void get_uts_ns(struct uts_namespace *ns) +{ + kref_get(&ns->kref); +} + +#ifdef CONFIG_UTS_NS +extern int copy_utsname(int flags, struct task_struct *tsk); +extern void free_uts_ns(struct kref *kref); + +static inline void put_uts_ns(struct uts_namespace *ns) +{ + kref_put(&ns->kref, free_uts_ns); +} +#else +static inline int copy_utsname(int flags, struct task_struct *tsk) +{ + return 0; +} +static inline void put_uts_ns(struct uts_namespace *ns) +{ +} +#endif static inline struct new_utsname *utsname(void) { - return &system_utsname; + return ¤t->nsproxy->uts_ns->name; } static inline struct new_utsname *init_utsname(void) { - return &system_utsname; + return &init_uts_ns.name; } +#define system_utsname init_uts_ns.name + extern struct rw_semaphore uts_sem; #endif -- cgit v1.2.3 From bf47fdcda65b44dbd674eeedcaa06e0aa28a5a00 Mon Sep 17 00:00:00 2001 From: "Serge E. Hallyn" Date: Mon, 2 Oct 2006 02:18:16 -0700 Subject: [PATCH] namespaces: utsname: remove system_utsname The system_utsname isn't needed now that kernel/sysctl.c is fixed. Nuke it. Signed-off-by: Serge E. Hallyn Cc: Kirill Korotaev Cc: "Eric W. Biederman" Cc: Herbert Poetzl Cc: Andrey Savochkin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/utsname.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/utsname.h b/include/linux/utsname.h index afa54e1542b3..99e522369f4f 100644 --- a/include/linux/utsname.h +++ b/include/linux/utsname.h @@ -74,7 +74,5 @@ static inline struct new_utsname *init_utsname(void) return &init_uts_ns.name; } -#define system_utsname init_uts_ns.name - extern struct rw_semaphore uts_sem; #endif -- cgit v1.2.3 From 071df104f808b8195c40643dcb4d060681742e29 Mon Sep 17 00:00:00 2001 From: "Serge E. Hallyn" Date: Mon, 2 Oct 2006 02:18:17 -0700 Subject: [PATCH] namespaces: utsname: implement CLONE_NEWUTS flag Implement a CLONE_NEWUTS flag, and use it at clone and sys_unshare. [clg@fr.ibm.com: IPC unshare fix] [bunk@stusta.de: cleanup] Signed-off-by: Serge Hallyn Cc: Kirill Korotaev Cc: "Eric W. Biederman" Cc: Herbert Poetzl Cc: Andrey Savochkin Signed-off-by: Adrian Bunk Signed-off-by: Cedric Le Goater Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 1 + include/linux/utsname.h | 11 +++++++++++ 2 files changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 46d6f5be72f2..a973e7012315 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -24,6 +24,7 @@ #define CLONE_UNTRACED 0x00800000 /* set if the tracing process can't force CLONE_PTRACE on this clone */ #define CLONE_CHILD_SETTID 0x01000000 /* set the TID in the child */ #define CLONE_STOPPED 0x02000000 /* Start in stopped state */ +#define CLONE_NEWUTS 0x04000000 /* New utsname group? */ /* * Scheduling policies diff --git a/include/linux/utsname.h b/include/linux/utsname.h index 99e522369f4f..02e4b6972064 100644 --- a/include/linux/utsname.h +++ b/include/linux/utsname.h @@ -47,6 +47,8 @@ static inline void get_uts_ns(struct uts_namespace *ns) } #ifdef CONFIG_UTS_NS +extern int unshare_utsname(unsigned long unshare_flags, + struct uts_namespace **new_uts); extern int copy_utsname(int flags, struct task_struct *tsk); extern void free_uts_ns(struct kref *kref); @@ -55,6 +57,15 @@ static inline void put_uts_ns(struct uts_namespace *ns) kref_put(&ns->kref, free_uts_ns); } #else +static inline int unshare_utsname(unsigned long unshare_flags, + struct uts_namespace **new_uts) +{ + if (unshare_flags & CLONE_NEWUTS) + return -EINVAL; + + return 0; +} + static inline int copy_utsname(int flags, struct task_struct *tsk) { return 0; -- cgit v1.2.3 From 25b21cb2f6d69b0475b134e0a3e8e269137270fa Mon Sep 17 00:00:00 2001 From: Kirill Korotaev Date: Mon, 2 Oct 2006 02:18:19 -0700 Subject: [PATCH] IPC namespace core This patch set allows to unshare IPCs and have a private set of IPC objects (sem, shm, msg) inside namespace. Basically, it is another building block of containers functionality. This patch implements core IPC namespace changes: - ipc_namespace structure - new config option CONFIG_IPC_NS - adds CLONE_NEWIPC flag - unshare support [clg@fr.ibm.com: small fix for unshare of ipc namespace] [akpm@osdl.org: build fix] Signed-off-by: Pavel Emelianov Signed-off-by: Kirill Korotaev Signed-off-by: Cedric Le Goater Cc: "Eric W. Biederman" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/init_task.h | 1 + include/linux/ipc.h | 36 ++++++++++++++++++++++++++++++++++++ include/linux/nsproxy.h | 2 ++ include/linux/sched.h | 1 + 4 files changed, 40 insertions(+) (limited to 'include/linux') diff --git a/include/linux/init_task.h b/include/linux/init_task.h index e08531ec32f0..ceecf69dfa39 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -74,6 +74,7 @@ extern struct nsproxy init_nsproxy; .count = ATOMIC_INIT(1), \ .nslock = SPIN_LOCK_UNLOCKED, \ .uts_ns = &init_uts_ns, \ + .ipc_ns = &init_ipc_ns, \ .namespace = NULL, \ } diff --git a/include/linux/ipc.h b/include/linux/ipc.h index b291189737e7..36027b10f283 100644 --- a/include/linux/ipc.h +++ b/include/linux/ipc.h @@ -2,6 +2,7 @@ #define _LINUX_IPC_H #include +#include #define IPC_PRIVATE ((__kernel_key_t) 0) @@ -68,6 +69,41 @@ struct kern_ipc_perm void *security; }; +struct ipc_ids; +struct ipc_namespace { + struct kref kref; + struct ipc_ids *ids[3]; + + int sem_ctls[4]; + int used_sems; + + int msg_ctlmax; + int msg_ctlmnb; + int msg_ctlmni; + + size_t shm_ctlmax; + size_t shm_ctlall; + int shm_ctlmni; + int shm_tot; +}; + +extern struct ipc_namespace init_ipc_ns; +extern void free_ipc_ns(struct kref *kref); +extern int copy_ipcs(unsigned long flags, struct task_struct *tsk); +extern int unshare_ipcs(unsigned long flags, struct ipc_namespace **ns); + +static inline struct ipc_namespace *get_ipc_ns(struct ipc_namespace *ns) +{ + if (ns) + kref_get(&ns->kref); + return ns; +} + +static inline void put_ipc_ns(struct ipc_namespace *ns) +{ + kref_put(&ns->kref, free_ipc_ns); +} + #endif /* __KERNEL__ */ #endif /* _LINUX_IPC_H */ diff --git a/include/linux/nsproxy.h b/include/linux/nsproxy.h index 9c2e0ad508db..f6baecdeecd6 100644 --- a/include/linux/nsproxy.h +++ b/include/linux/nsproxy.h @@ -6,6 +6,7 @@ struct namespace; struct uts_namespace; +struct ipc_namespace; /* * A structure to contain pointers to all per-process @@ -23,6 +24,7 @@ struct nsproxy { atomic_t count; spinlock_t nslock; struct uts_namespace *uts_ns; + struct ipc_namespace *ipc_ns; struct namespace *namespace; }; extern struct nsproxy init_nsproxy; diff --git a/include/linux/sched.h b/include/linux/sched.h index a973e7012315..9ba959e34266 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -25,6 +25,7 @@ #define CLONE_CHILD_SETTID 0x01000000 /* set the TID in the child */ #define CLONE_STOPPED 0x02000000 /* Start in stopped state */ #define CLONE_NEWUTS 0x04000000 /* New utsname group? */ +#define CLONE_NEWIPC 0x08000000 /* New ipcs */ /* * Scheduling policies -- cgit v1.2.3 From 73ea41302bab5e02c9e86ab15c509494a550f1db Mon Sep 17 00:00:00 2001 From: Kirill Korotaev Date: Mon, 2 Oct 2006 02:18:20 -0700 Subject: [PATCH] IPC namespace - utils This patch adds basic IPC namespace functionality to IPC utils: - init_ipc_ns - copy/clone/unshare/free IPC ns - /proc preparations Signed-off-by: Pavel Emelianov Signed-off-by: Kirill Korotaev Cc: "Eric W. Biederman" Cc: Cedric Le Goater Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/init_task.h | 3 ++- include/linux/ipc.h | 18 ++++++++++++++++++ 2 files changed, 20 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/init_task.h b/include/linux/init_task.h index ceecf69dfa39..33c5daacc743 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -6,6 +6,7 @@ #include #include #include +#include #define INIT_FDTABLE \ { \ @@ -74,8 +75,8 @@ extern struct nsproxy init_nsproxy; .count = ATOMIC_INIT(1), \ .nslock = SPIN_LOCK_UNLOCKED, \ .uts_ns = &init_uts_ns, \ - .ipc_ns = &init_ipc_ns, \ .namespace = NULL, \ + INIT_IPC_NS(ipc_ns) \ } #define INIT_SIGHAND(sighand) { \ diff --git a/include/linux/ipc.h b/include/linux/ipc.h index 36027b10f283..d9e2b3f36c35 100644 --- a/include/linux/ipc.h +++ b/include/linux/ipc.h @@ -88,20 +88,38 @@ struct ipc_namespace { }; extern struct ipc_namespace init_ipc_ns; + +#ifdef CONFIG_SYSVIPC +#define INIT_IPC_NS(ns) .ns = &init_ipc_ns, +#else +#define INIT_IPC_NS(ns) +#endif + +#ifdef CONFIG_IPC_NS extern void free_ipc_ns(struct kref *kref); extern int copy_ipcs(unsigned long flags, struct task_struct *tsk); extern int unshare_ipcs(unsigned long flags, struct ipc_namespace **ns); +#else +static inline int copy_ipcs(unsigned long flags, struct task_struct *tsk) +{ + return 0; +} +#endif static inline struct ipc_namespace *get_ipc_ns(struct ipc_namespace *ns) { +#ifdef CONFIG_IPC_NS if (ns) kref_get(&ns->kref); +#endif return ns; } static inline void put_ipc_ns(struct ipc_namespace *ns) { +#ifdef CONFIG_IPC_NS kref_put(&ns->kref, free_ipc_ns); +#endif } #endif /* __KERNEL__ */ -- cgit v1.2.3 From 3db03b4afb3ecd66a0399b8ba57742ca953b0ecd Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 2 Oct 2006 02:18:31 -0700 Subject: [PATCH] rename the provided execve functions to kernel_execve Some architectures provide an execve function that does not set errno, but instead returns the result code directly. Rename these to kernel_execve to get the right semantics there. Moreover, there is no reasone for any of these architectures to still provide __KERNEL_SYSCALLS__ or _syscallN macros, so remove these right away. [akpm@osdl.org: build fix] [bunk@stusta.de: build fix] Signed-off-by: Arnd Bergmann Cc: Andi Kleen Acked-by: Paul Mackerras Cc: Benjamin Herrenschmidt Cc: Richard Henderson Cc: Ivan Kokshaysky Cc: Russell King Cc: Ian Molton Cc: Mikael Starvik Cc: David Howells Cc: Yoshinori Sato Cc: Hirokazu Takata Cc: Ralf Baechle Cc: Kyle McMartin Cc: Heiko Carstens Cc: Martin Schwidefsky Cc: Paul Mundt Cc: Kazumoto Kojima Cc: Richard Curnow Cc: William Lee Irwin III Cc: "David S. Miller" Cc: Jeff Dike Cc: Paolo 'Blaisorblade' Giarrusso Cc: Miles Bader Cc: Chris Zankel Cc: "Luck, Tony" Cc: Geert Uytterhoeven Cc: Roman Zippel Signed-off-by: Adrian Bunk Cc: Arnd Bergmann Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/syscalls.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 2d1c3d5c83ac..3efcfc7e9c6c 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -599,4 +599,6 @@ asmlinkage long sys_set_robust_list(struct robust_list_head __user *head, size_t len); asmlinkage long sys_getcpu(unsigned __user *cpu, unsigned __user *node, struct getcpu_cache __user *cache); +int kernel_execve(const char *filename, char *const argv[], char *const envp[]); + #endif -- cgit v1.2.3 From 135ab6ec8fdad6f61aabe53f456821baf4a4aa0e Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 2 Oct 2006 02:18:44 -0700 Subject: [PATCH] remove remaining errno and __KERNEL_SYSCALLS__ references The last in-kernel user of errno is gone, so we should remove the definition and everything referring to it. This also removes the now-unused lib/execve.c file that was introduced earlier. Also remove every trace of __KERNEL_SYSCALLS__ that still remained in the kernel. Signed-off-by: Arnd Bergmann Cc: Andi Kleen Cc: Paul Mackerras Cc: Benjamin Herrenschmidt Cc: Richard Henderson Cc: Ivan Kokshaysky Cc: Russell King Cc: Ian Molton Cc: Mikael Starvik Cc: David Howells Cc: Yoshinori Sato Cc: Hirokazu Takata Cc: Ralf Baechle Cc: Kyle McMartin Cc: Heiko Carstens Cc: Martin Schwidefsky Cc: Paul Mundt Cc: Kazumoto Kojima Cc: Richard Curnow Cc: William Lee Irwin III Cc: "David S. Miller" Cc: Jeff Dike Cc: Paolo 'Blaisorblade' Giarrusso Cc: Miles Bader Cc: Chris Zankel Cc: "Luck, Tony" Cc: Geert Uytterhoeven Cc: Roman Zippel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/unistd.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/unistd.h b/include/linux/unistd.h index c18c60f3254e..aa8d5b5e2e3e 100644 --- a/include/linux/unistd.h +++ b/include/linux/unistd.h @@ -1,12 +1,8 @@ #ifndef _LINUX_UNISTD_H_ #define _LINUX_UNISTD_H_ -#ifdef __KERNEL__ -extern int errno; -#endif - /* - * Include machine specific syscallX macros + * Include machine specific syscall numbers */ #include -- cgit v1.2.3 From 1a657f78dcc8ea7c53eaa1f2a45ea2315738c15f Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Mon, 2 Oct 2006 02:18:59 -0700 Subject: [PATCH] introduce get_task_pid() to fix unsafe get_pid() proc_pid_make_inode: ei->pid = get_pid(task_pid(task)); I think this is not safe. get_pid() can be preempted after checking "pid != NULL". Then the task exits, does detach_pid(), and RCU frees the pid. Signed-off-by: Oleg Nesterov Cc: "Eric W. Biederman" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pid.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pid.h b/include/linux/pid.h index 7e39767b4c60..17b9e04d3586 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -68,6 +68,8 @@ extern struct task_struct *FASTCALL(pid_task(struct pid *pid, enum pid_type)); extern struct task_struct *FASTCALL(get_pid_task(struct pid *pid, enum pid_type)); +extern struct pid *get_task_pid(struct task_struct *task, enum pid_type type); + /* * attach_pid() and detach_pid() must be called with the tasklist_lock * write-held. -- cgit v1.2.3 From 9ec52099e4b8678a60e9f93e41ad87885d64f3e6 Mon Sep 17 00:00:00 2001 From: Cedric Le Goater Date: Mon, 2 Oct 2006 02:19:00 -0700 Subject: [PATCH] replace cad_pid by a struct pid There are a few places in the kernel where the init task is signaled. The ctrl+alt+del sequence is one them. It kills a task, usually init, using a cached pid (cad_pid). This patch replaces the pid_t by a struct pid to avoid pid wrap around problem. The struct pid is initialized at boot time in init() and can be modified through systctl with /proc/sys/kernel/cad_pid [ I haven't found any distro using it ? ] It also introduces a small helper routine kill_cad_pid() which is used where it seemed ok to use cad_pid instead of pid 1. [akpm@osdl.org: cleanups, build fix] Signed-off-by: Cedric Le Goater Cc: Eric W. Biederman Cc: Martin Schwidefsky Cc: Paul Mackerras Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 9ba959e34266..38530232d92f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1065,6 +1065,8 @@ static inline int is_init(struct task_struct *tsk) return tsk->pid == 1; } +extern struct pid *cad_pid; + extern void free_task(struct task_struct *tsk); #define get_task_struct(tsk) do { atomic_inc(&(tsk)->usage); } while(0) @@ -1292,6 +1294,11 @@ extern int send_group_sigqueue(int, struct sigqueue *, struct task_struct *); extern int do_sigaction(int, struct k_sigaction *, struct k_sigaction *); extern int do_sigaltstack(const stack_t __user *, stack_t __user *, unsigned long); +static inline int kill_cad_pid(int sig, int priv) +{ + return kill_pid(cad_pid, sig, priv); +} + /* These can be the second arg to send_sig_info/send_group_sig_info. */ #define SEND_SIG_NOINFO ((struct siginfo *) 0) #define SEND_SIG_PRIV ((struct siginfo *) 1) -- cgit v1.2.3 From 3f2e05e90e0846c42626e3d272454f26be34a1bc Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 2 Oct 2006 14:12:31 +0100 Subject: [PATCH] BLOCK: Revert patch to hack around undeclared sigset_t in linux/compat.h Revert Andrew Morton's patch to temporarily hack around the lack of a declaration of sigset_t in linux/compat.h to make the block-disablement patches build on IA64. This got accidentally pushed to Linus and should be fixed in a different manner. Also make linux/compat.h #include asm/signal.h to gain a definition of sigset_t so that it can externally declare sigset_from_compat(). This has been compile-tested for i386, x86_64, ia64, mips, mips64, frv, ppc and ppc64 and run-tested on frv. Signed-off-by: David Howells Signed-off-by: Linus Torvalds --- include/linux/compat.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 9760753e662b..6f110957cc97 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -13,6 +13,7 @@ #include #include +#include #define compat_jiffies_to_clock_t(x) \ (((unsigned long)(x) * COMPAT_USER_HZ) / HZ) -- cgit v1.2.3 From 128e5ebaf8abbda375bba82690b09630003c9213 Mon Sep 17 00:00:00 2001 From: Steven Whitehouse Date: Mon, 2 Oct 2006 11:24:43 -0400 Subject: [GFS2] Remove iflags.h, use FS_ Update GFS2 in the light of David Howells' patch: [PATCH] BLOCK: Move common FS-specific ioctls to linux/fs.h [try #6] 36695673b012096228ebdc1b39a6a5850daa474e which calls the filesystem independant flags FS_..._FL. As a result we no longer need the flags.h file and the conversion routine is moved into the GFS2 source code. Userland programs which used to include iflags.h should now include fs.h and use the new flag names. Signed-off-by: Steven Whitehouse --- include/linux/Kbuild | 1 - include/linux/fs.h | 2 + include/linux/iflags.h | 102 ------------------------------------------------- 3 files changed, 2 insertions(+), 103 deletions(-) delete mode 100644 include/linux/iflags.h (limited to 'include/linux') diff --git a/include/linux/Kbuild b/include/linux/Kbuild index 839a97ee1f7c..15667cc947d5 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -223,7 +223,6 @@ unifdef-y += hpet.h unifdef-y += i2c.h unifdef-y += i2o-dev.h unifdef-y += icmpv6.h -unifdef-y += iflags.h unifdef-y += if_bridge.h unifdef-y += if_ec.h unifdef-y += if_eql.h diff --git a/include/linux/fs.h b/include/linux/fs.h index 2e29a2edaeec..bc0e645abb80 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -250,6 +250,8 @@ extern int dir_notify_enable; #define FS_NOTAIL_FL 0x00008000 /* file tail should not be merged */ #define FS_DIRSYNC_FL 0x00010000 /* dirsync behaviour (directories only) */ #define FS_TOPDIR_FL 0x00020000 /* Top of directory hierarchies*/ +#define FS_EXTENT_FL 0x00080000 /* Extents */ +#define FS_DIRECTIO_FL 0x00100000 /* Use direct i/o */ #define FS_RESERVED_FL 0x80000000 /* reserved for ext2 lib */ #define FS_FL_USER_VISIBLE 0x0003DFFF /* User visible flags */ diff --git a/include/linux/iflags.h b/include/linux/iflags.h deleted file mode 100644 index 5b27102dfeaf..000000000000 --- a/include/linux/iflags.h +++ /dev/null @@ -1,102 +0,0 @@ -#ifndef _LINUX_IFLAGS_H -#define _LINUX_IFLAGS_H - -/* - * A universal set of inode flags. - * - * Originally taken from ext2/3 with additions for other filesystems. - * Filesystems supporting this interface should interoperate with - * the lsattr and chattr command line tools. - * - * This interface is supported in whole or in part by: - * ext2 - * ext3 - * xfs - * jfs - * gfs2 - * - */ - -#define IFLAGS_GET_IOC _IOR('f', 1, long) -#define IFLAGS_SET_IOC _IOW('f', 2, long) - -/* - * These values are provided for use as indices of an array - * for use with the iflags_cvt function below - */ -enum { - iflag_SecureRm = 0, /* Secure deletion */ - iflag_Unrm = 1, /* Undelete */ - iflag_Compress = 2, /* Compress file */ - iflag_Sync = 3, /* Synchronous updates */ - iflag_Immutable = 4, /* Immutable */ - iflag_Append = 5, /* Append */ - iflag_NoDump = 6, /* Don't dump file */ - iflag_NoAtime = 7, /* No atime updates */ - /* Reserved for compression usage */ - iflag_Dirty = 8, - iflag_ComprBlk = 9, /* One or more compressed clusters */ - iflag_NoComp = 10, /* Don't compress */ - iflag_Ecompr = 11, /* Compression error */ - /* End of compression flags */ - iflag_Btree = 12, /* btree format dir */ - iflag_Index = 12, /* hash-indexed directory */ - iflag_Imagic = 13, /* AFS directory */ - iflag_JournalData = 14, /* file data should be journaled */ - iflag_NoTail = 15, /* file tail should not be merged */ - iflag_DirSync = 16, /* dirsync behaviour */ - iflag_TopDir = 17, /* Top of directory hierarchies */ - iflag_Extent = 19, /* Extents */ - iflag_DirectIO = 20, /* Always use direct I/O on this file */ - iflag_Reserved = 31 /* reserved for ext2/3 lib */ -}; - -#define __IFL(x) (1<<(iflag_##x)) -#define IFLAG_SECRM __IFL(SecureRm) /* 0x00000001 */ -#define IFLAG_UNRM __IFL(Unrm) /* 0x00000002 */ -#define IFLAG_COMPR __IFL(Compr) /* 0x00000004 */ -#define IFLAG_SYNC __IFL(Sync) /* 0x00000008 */ -#define IFLAG_IMMUTABLE __IFL(Immutable) /* 0x00000010 */ -#define IFLAG_APPEND __IFL(Append) /* 0x00000020 */ -#define IFLAG_NODUMP __IFL(NoDump) /* 0x00000040 */ -#define IFLAG_NOATIME __IFL(NoAtime) /* 0x00000080 */ -#define IFLAG_DIRTY __IFL(Dirty) /* 0x00000100 */ -#define IFLAG_COMPRBLK __IFL(ComprBlk) /* 0x00000200 */ -#define IFLAG_NOCOMP __IFL(NoComp) /* 0x00000400 */ -#define IFLAG_ECOMPR __IFL(Ecompr) /* 0x00000800 */ -#define IFLAG_BTREE __IFL(Btree) /* 0x00001000 */ -#define IFLAG_INDEX __IFL(Index) /* 0x00001000 */ -#define IFLAG_IMAGIC __IFL(Imagic) /* 0x00002000 */ -#define IFLAG_JOURNAL_DATA __IFL(JournalData) /* 0x00004000 */ -#define IFLAG_NOTAIL __IFL(NoTail) /* 0x00008000 */ -#define IFLAG_DIRSYNC __IFL(DirSync) /* 0x00010000 */ -#define IFLAG_TOPDIR __IFL(TopDir) /* 0x00020000 */ -#define IFLAG_EXTENT __IFL(Extent) /* 0x00080000 */ -#define IFLAG_DIRECTIO __IFL(DirectIO) /* 0x00100000 */ -#define IFLAG_RESERVED __IFL(Reserved) /* 0x80000000 */ - -#ifdef __KERNEL__ -/** - * iflags_cvt - * @table: A table of 32 u32 flags - * @val: a 32 bit value to convert - * - * This function can be used to convert between IFLAGS values and - * the filesystem's own flags values. - * - * Returns: the converted flags - */ -static inline u32 iflags_cvt(const u32 *table, u32 val) -{ - u32 res = 0; - while(val) { - if (val & 1) - res |= *table; - table++; - val >>= 1; - } - return res; -} -#endif /* __KERNEL__ */ - -#endif /* _LINUX_IFLAGS_H */ -- cgit v1.2.3 From 0235497f7a961db57ef975eb889503809ce82fe5 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 2 Oct 2006 14:05:20 -0700 Subject: Add prototype for sigset_from_compat() Duh. I screwed up editing David Howells patch in commit 3f2e05e90e0846c42626e3d272454f26be34a1bc, and the actual declaration for the sigset_from_compat() function went missing. My bad. Olaf Hering saved the day and noticed that I'm a moron. Signed-off-by: Linus Torvalds --- include/linux/compat.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 6f110957cc97..ef5cd192784c 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -228,6 +228,7 @@ static inline int compat_timespec_compare(struct compat_timespec *lhs, asmlinkage long compat_sys_adjtimex(struct compat_timex __user *utp); extern int compat_printk(const char *fmt, ...); +extern void sigset_from_compat(sigset_t *set, compat_sigset_t *compat); #endif /* CONFIG_COMPAT */ #endif /* _LINUX_COMPAT_H */ -- cgit v1.2.3 From 1d32849b14bc8792e6f35ab27dd990d74b16126c Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Tue, 3 Oct 2006 01:13:45 -0700 Subject: [PATCH] pid.h cleanup Make the pid.h macros look less revolting in an 80-col window. Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pid.h | 30 +++++++++++++++--------------- 1 file changed, 15 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pid.h b/include/linux/pid.h index 17b9e04d3586..2c0007d17218 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -105,28 +105,28 @@ static inline pid_t pid_nr(struct pid *pid) } -#define do_each_task_pid(who, type, task) \ - do { \ - struct hlist_node *pos___; \ - struct pid *pid___ = find_pid(who); \ - if (pid___ != NULL) \ - hlist_for_each_entry_rcu((task), pos___, \ +#define do_each_task_pid(who, type, task) \ + do { \ + struct hlist_node *pos___; \ + struct pid *pid___ = find_pid(who); \ + if (pid___ != NULL) \ + hlist_for_each_entry_rcu((task), pos___, \ &pid___->tasks[type], pids[type].node) { -#define while_each_task_pid(who, type, task) \ - } \ +#define while_each_task_pid(who, type, task) \ + } \ } while (0) -#define do_each_pid_task(pid, type, task) \ - do { \ - struct hlist_node *pos___; \ - if (pid != NULL) \ - hlist_for_each_entry_rcu((task), pos___, \ +#define do_each_pid_task(pid, type, task) \ + do { \ + struct hlist_node *pos___; \ + if (pid != NULL) \ + hlist_for_each_entry_rcu((task), pos___, \ &pid->tasks[type], pids[type].node) { -#define while_each_pid_task(pid, type, task) \ - } \ +#define while_each_pid_task(pid, type, task) \ + } \ } while (0) #endif /* _LINUX_PID_H */ -- cgit v1.2.3 From afefdbb28a0a2af689926c30b94a14aea6036719 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 3 Oct 2006 01:13:46 -0700 Subject: [PATCH] VFS: Make filldir_t and struct kstat deal in 64-bit inode numbers These patches make the kernel pass 64-bit inode numbers internally when communicating to userspace, even on a 32-bit system. They are required because some filesystems have intrinsic 64-bit inode numbers: NFS3+ and XFS for example. The 64-bit inode numbers are then propagated to userspace automatically where the arch supports it. Problems have been seen with userspace (eg: ld.so) using the 64-bit inode number returned by stat64() or getdents64() to differentiate files, and failing because the 64-bit inode number space was compressed to 32-bits, and so overlaps occur. This patch: Make filldir_t take a 64-bit inode number and struct kstat carry a 64-bit inode number so that 64-bit inode numbers can be passed back to userspace. The stat functions then returns the full 64-bit inode number where available and where possible. If it is not possible to represent the inode number supplied by the filesystem in the field provided by userspace, then error EOVERFLOW will be issued. Similarly, the getdents/readdir functions now pass the full 64-bit inode number to userspace where possible, returning EOVERFLOW instead when a directory entry is encountered that can't be properly represented. Note that this means that some inodes will not be stat'able on a 32-bit system with old libraries where they were before - but it does mean that there will be no ambiguity over what a 32-bit inode number refers to. Note similarly that directory scans may be cut short with an error on a 32-bit system with old libraries where the scan would work before for the same reasons. It is judged unlikely that this situation will occur because modern glibc uses 64-bit capable versions of stat and getdents class functions exclusively, and that older systems are unlikely to encounter unrepresentable inode numbers anyway. [akpm: alpha build fix] Signed-off-by: David Howells Cc: Trond Myklebust Cc: Al Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 2 +- include/linux/stat.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 91c0b2a32a90..7b61e94bf8fc 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1049,7 +1049,7 @@ int generic_osync_inode(struct inode *, struct address_space *, int); * This allows the kernel to read directories into kernel space or * to have different dirent layouts depending on the binary type. */ -typedef int (*filldir_t)(void *, const char *, int, loff_t, ino_t, unsigned); +typedef int (*filldir_t)(void *, const char *, int, loff_t, u64, unsigned); struct block_device_operations { int (*open) (struct inode *, struct file *); diff --git a/include/linux/stat.h b/include/linux/stat.h index 8669291352db..679ef0d70b6b 100644 --- a/include/linux/stat.h +++ b/include/linux/stat.h @@ -57,7 +57,7 @@ #include struct kstat { - unsigned long ino; + u64 ino; dev_t dev; umode_t mode; unsigned int nlink; -- cgit v1.2.3 From ffc5089196446c08d9a005cf0dd7cab18d119606 Mon Sep 17 00:00:00 2001 From: Franck Bui-Huu Date: Tue, 3 Oct 2006 01:13:48 -0700 Subject: [PATCH] Create kallsyms_lookup_size_offset() Some uses of kallsyms_lookup() do not need to find out the name of a symbol and its module's name it belongs. This is specially true in arch specific code, which needs to unwind the stack to show the back trace during oops (mips is an example). In this specific case, we just need to retreive the function's size and the offset of the active intruction inside it. Adds a new entry "kallsyms_lookup_size_offset()" This new entry does exactly the same as kallsyms_lookup() but does not require any buffers to store any names. It returns 0 if it fails otherwise 1. Signed-off-by: Franck Bui-Huu Cc: Rusty Russell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kallsyms.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h index 849043ce4ed6..1cebcbc28b47 100644 --- a/include/linux/kallsyms.h +++ b/include/linux/kallsyms.h @@ -12,6 +12,10 @@ /* Lookup the address for a symbol. Returns 0 if not found. */ unsigned long kallsyms_lookup_name(const char *name); +extern int kallsyms_lookup_size_offset(unsigned long addr, + unsigned long *symbolsize, + unsigned long *offset); + /* Lookup an address. modname is set to NULL if it's in the kernel. */ const char *kallsyms_lookup(unsigned long addr, unsigned long *symbolsize, @@ -28,6 +32,13 @@ static inline unsigned long kallsyms_lookup_name(const char *name) return 0; } +static inline int kallsyms_lookup_size_offset(unsigned long addr, + unsigned long *symbolsize, + unsigned long *offset) +{ + return 0; +} + static inline const char *kallsyms_lookup(unsigned long addr, unsigned long *symbolsize, unsigned long *offset, -- cgit v1.2.3 From 1a84887080dc15f048db7c3a643e98f1435790d6 Mon Sep 17 00:00:00 2001 From: "Siddha, Suresh B" Date: Tue, 3 Oct 2006 01:14:08 -0700 Subject: [PATCH] sched: introduce child field in sched_domain Introduce the child field in sched_domain struct and use it in sched_balance_self(). We will also use this field in cleaning up the sched group cpu_power setup(done in a different patch) code. Signed-off-by: Suresh Siddha Acked-by: Ingo Molnar Acked-by: Nick Piggin Cc: Paul Jackson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 1 + include/linux/topology.h | 3 +++ 2 files changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 38530232d92f..8e26c9069f15 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -644,6 +644,7 @@ struct sched_group { struct sched_domain { /* These fields must be setup */ struct sched_domain *parent; /* top domain must be null terminated */ + struct sched_domain *child; /* bottom domain must be null terminated */ struct sched_group *groups; /* the balancing groups of the domain */ cpumask_t span; /* span of all CPUs in this domain */ unsigned long min_interval; /* Minimum balance interval ms */ diff --git a/include/linux/topology.h b/include/linux/topology.h index ec1eca85290a..486bec23f986 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -89,6 +89,7 @@ #define SD_SIBLING_INIT (struct sched_domain) { \ .span = CPU_MASK_NONE, \ .parent = NULL, \ + .child = NULL, \ .groups = NULL, \ .min_interval = 1, \ .max_interval = 2, \ @@ -119,6 +120,7 @@ #define SD_CPU_INIT (struct sched_domain) { \ .span = CPU_MASK_NONE, \ .parent = NULL, \ + .child = NULL, \ .groups = NULL, \ .min_interval = 1, \ .max_interval = 4, \ @@ -146,6 +148,7 @@ #define SD_ALLNODES_INIT (struct sched_domain) { \ .span = CPU_MASK_NONE, \ .parent = NULL, \ + .child = NULL, \ .groups = NULL, \ .min_interval = 64, \ .max_interval = 64*num_online_cpus(), \ -- cgit v1.2.3 From 89c4710ee9bbbefe6a4d469d9f36266a92c275c5 Mon Sep 17 00:00:00 2001 From: "Siddha, Suresh B" Date: Tue, 3 Oct 2006 01:14:09 -0700 Subject: [PATCH] sched: cleanup sched_group cpu_power setup Up to now sched group's cpu_power for each sched domain is initialized independently. This made the setup code ugly as the new sched domains are getting added. Make the sched group cpu_power setup code generic, by using domain child field and new domain flag in sched_domain. For most of the sched domains(except NUMA), sched group's cpu_power is now computed generically using the domain properties of itself and of the child domain. sched groups in NUMA domains are setup little differently and hence they don't use this generic mechanism. Signed-off-by: Suresh Siddha Acked-by: Ingo Molnar Acked-by: Nick Piggin Cc: Paul Jackson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 12 ++++++++++-- include/linux/topology.h | 43 +++++++++++++++++++++++++++++++++---------- 2 files changed, 43 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 8e26c9069f15..331f4502e92b 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -625,9 +625,17 @@ enum idle_type #define SD_WAKE_BALANCE 64 /* Perform balancing at task wakeup */ #define SD_SHARE_CPUPOWER 128 /* Domain members share cpu power */ #define SD_POWERSAVINGS_BALANCE 256 /* Balance for power savings */ +#define SD_SHARE_PKG_RESOURCES 512 /* Domain members share cpu pkg resources */ -#define BALANCE_FOR_POWER ((sched_mc_power_savings || sched_smt_power_savings) \ - ? SD_POWERSAVINGS_BALANCE : 0) +#define BALANCE_FOR_MC_POWER \ + (sched_smt_power_savings ? SD_POWERSAVINGS_BALANCE : 0) + +#define BALANCE_FOR_PKG_POWER \ + ((sched_mc_power_savings || sched_smt_power_savings) ? \ + SD_POWERSAVINGS_BALANCE : 0) + +#define test_sd_parent(sd, flag) ((sd->parent && \ + (sd->parent->flags & flag)) ? 1 : 0) struct sched_group { diff --git a/include/linux/topology.h b/include/linux/topology.h index 486bec23f986..da508d1998e4 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -115,6 +115,38 @@ #endif #endif /* CONFIG_SCHED_SMT */ +#ifdef CONFIG_SCHED_MC +/* Common values for MC siblings. for now mostly derived from SD_CPU_INIT */ +#ifndef SD_MC_INIT +#define SD_MC_INIT (struct sched_domain) { \ + .span = CPU_MASK_NONE, \ + .parent = NULL, \ + .child = NULL, \ + .groups = NULL, \ + .min_interval = 1, \ + .max_interval = 4, \ + .busy_factor = 64, \ + .imbalance_pct = 125, \ + .cache_nice_tries = 1, \ + .per_cpu_gain = 100, \ + .busy_idx = 2, \ + .idle_idx = 1, \ + .newidle_idx = 2, \ + .wake_idx = 1, \ + .forkexec_idx = 1, \ + .flags = SD_LOAD_BALANCE \ + | SD_BALANCE_NEWIDLE \ + | SD_BALANCE_EXEC \ + | SD_WAKE_AFFINE \ + | SD_SHARE_PKG_RESOURCES\ + | BALANCE_FOR_MC_POWER, \ + .last_balance = jiffies, \ + .balance_interval = 1, \ + .nr_balance_failed = 0, \ +} +#endif +#endif /* CONFIG_SCHED_MC */ + /* Common values for CPUs */ #ifndef SD_CPU_INIT #define SD_CPU_INIT (struct sched_domain) { \ @@ -137,7 +169,7 @@ | SD_BALANCE_NEWIDLE \ | SD_BALANCE_EXEC \ | SD_WAKE_AFFINE \ - | BALANCE_FOR_POWER, \ + | BALANCE_FOR_PKG_POWER,\ .last_balance = jiffies, \ .balance_interval = 1, \ .nr_balance_failed = 0, \ @@ -168,15 +200,6 @@ .nr_balance_failed = 0, \ } -#ifdef CONFIG_SCHED_MC -#ifndef SD_MC_INIT -/* for now its same as SD_CPU_INIT. - * TBD: Tune Domain parameters! - */ -#define SD_MC_INIT SD_CPU_INIT -#endif -#endif - #ifdef CONFIG_NUMA #ifndef SD_NODE_INIT #error Please define an appropriate SD_NODE_INIT in include/asm/topology.h!!! -- cgit v1.2.3 From 020e322de3ff75d32daa58e431aad07071da27c6 Mon Sep 17 00:00:00 2001 From: Sergei Shtylylov Date: Tue, 3 Oct 2006 01:14:13 -0700 Subject: [PATCH] IDE: claim extra DMA ports regardless of channel - Claim extra DMA I/O ports regardless of what IDE channels are present/enabled. - Remove extra ports handling from ide_mapped_mmio_dma() since it's not applicable to the custom-mapping IDE drivers. Signed-off-by: Sergei Shtylyov Cc: Bartlomiej Zolnierkiewicz Cc: Alan Cox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ide.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 99620451d958..11608cd03d4c 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -775,10 +775,12 @@ typedef struct hwif_s { unsigned long dma_prdtable; /* actual prd table address */ unsigned long dma_base2; /* extended base addr for dma ports */ - unsigned dma_extra; /* extra addr for dma ports */ unsigned long config_data; /* for use by chipset-specific code */ unsigned long select_data; /* for use by chipset-specific code */ + unsigned long extra_base; /* extra addr for dma ports */ + unsigned extra_ports; /* number of extra dma ports */ + unsigned noprobe : 1; /* don't probe for this interface */ unsigned present : 1; /* this interface exists */ unsigned hold : 1; /* this interface is always present */ -- cgit v1.2.3 From 83d7dbc4095a0c314b191c573be5fb4fa6ce0897 Mon Sep 17 00:00:00 2001 From: Matt Mackall Date: Tue, 3 Oct 2006 01:14:16 -0700 Subject: [PATCH] Make number of IDE interfaces configurable Make IDE_HWIFS configurable if EMBEDDED This lets us lop as much as 16k off an x86 build. It's a little ugly, but it's dead simple. Note the fix for HWIFS < 2. Sizing interfaces dynamically unfortunately turns out to be pretty major surgery. add/remove: 0/1 grow/shrink: 0/11 up/down: 0/-16182 (-16182) function old new delta ide_hwifs 16920 1692 -15228 init_irq 1113 750 -363 ideprobe_init 283 138 -145 ide_pci_setup_ports 1329 1193 -136 save_match 85 - -85 ide_register_hw_with_fixup 367 287 -80 ide_setup 1364 1308 -56 is_chipset_set 40 4 -36 create_proc_ide_interfaces 225 205 -20 init_ide_data 84 67 -17 ide_probe_for_cmd640x 1198 1183 -15 ide_unregister 1452 1451 -1 Signed-off-by: Matt Mackall Cc: Bartlomiej Zolnierkiewicz Acked-by: Alan Cox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ide.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 11608cd03d4c..bdb2733208c5 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -251,7 +251,8 @@ static inline void ide_std_init_ports(hw_regs_t *hw, #include -#ifndef MAX_HWIFS +#if !defined(MAX_HWIFS) || defined(CONFIG_EMBEDDED) +#undef MAX_HWIFS #define MAX_HWIFS CONFIG_IDE_MAX_HWIFS #endif -- cgit v1.2.3 From 27ac6036f31dea8117ecc525e0dbfd17b23e8c09 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Tue, 3 Oct 2006 01:14:24 -0700 Subject: [PATCH] drivers/ide/: cleanups - setup-pci.c: remove the unused ide_pci_unregister_driver() - ide-dma.c: remove the unused EXPORT_SYMBOL_GPL(ide_in_drive_list) Signed-off-by: Adrian Bunk Acked-by: Alan Cox Cc: Bartlomiej Zolnierkiewicz Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ide.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index bdb2733208c5..097d16e5ab37 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -1193,7 +1193,6 @@ extern int ideprobe_init(void); extern void ide_scan_pcibus(int scan_direction) __init; extern int __ide_pci_register_driver(struct pci_driver *driver, struct module *owner); #define ide_pci_register_driver(d) __ide_pci_register_driver(d, THIS_MODULE) -extern void ide_pci_unregister_driver(struct pci_driver *driver); void ide_pci_setup_ports(struct pci_dev *, struct ide_pci_device_s *, int, ata_index_t *); extern void ide_setup_pci_noise (struct pci_dev *dev, struct ide_pci_device_s *d); -- cgit v1.2.3 From 3f63c5e88a5ce45b423f3712293f1664115b09c0 Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Tue, 3 Oct 2006 01:14:25 -0700 Subject: [PATCH] ide: remove dma_base2 field from ide_hwif_t Remove dma_base2 field from ide_hwif_t as it's used only in 2 drivers and without great need. Signed-off-by: Sergei Shtylyov Cc: John Keller Signed-off-by: Jeremy Higdon Acked-by: Alan Cox Cc: Bartlomiej Zolnierkiewicz Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ide.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 097d16e5ab37..a9a9e33e448f 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -774,7 +774,6 @@ typedef struct hwif_s { unsigned long dma_status; /* dma status register */ unsigned long dma_vendor3; /* dma vendor 3 register */ unsigned long dma_prdtable; /* actual prd table address */ - unsigned long dma_base2; /* extended base addr for dma ports */ unsigned long config_data; /* for use by chipset-specific code */ unsigned long select_data; /* for use by chipset-specific code */ -- cgit v1.2.3 From 913759ac90a727b86da72efcfb70931f497d1cb7 Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Tue, 3 Oct 2006 01:14:33 -0700 Subject: [PATCH] ide: Fix crash on repeated reset Michal Miroslaw reported a problem (bugzilla #7023) where a user initiated reset while the IDE layer was already resetting the channel caused a crash, and provided a rough fix. This is a slightly cleaner version of the fix which tracks the reset state and blocks further reset requests while a reset is in progress. Note this is not a security issue - random end users can't access the ioctl in question anyway. Signed-off-by: Alan Cox Cc: Michal Miroslaw Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ide.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index a9a9e33e448f..07d8d725541f 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -825,6 +825,9 @@ typedef struct hwgroup_s { unsigned int sleeping : 1; /* BOOL: polling active & poll_timeout field valid */ unsigned int polling : 1; + /* BOOL: in a polling reset situation. Must not trigger another reset yet */ + unsigned int resetting : 1; + /* current drive */ ide_drive_t *drive; /* ptr to current hwif in linked-list */ -- cgit v1.2.3 From fc5891c8a3ba284f13994d7bc1f1bfa8283982de Mon Sep 17 00:00:00 2001 From: Dennis Munsie Date: Tue, 3 Oct 2006 01:14:42 -0700 Subject: [PATCH] fbdev: Add generic ddc read functionality Adds functionality to read the EDID information over the DDC bus in a generic way. This code is based on the DDC implementation in the radeon driver. [adaplas] - separate from fbmon.c and place in new file fb_ddc.c - remove dependency to CONFIG_I2C and CONFIG_I2C_ALGOBIT, otherwise, feature will not compile if i2c support is compiled as a module - feature is selectable only by drivers needing it. It must have a 'select FB_DDC if xxx' in Kconfig - change printk's to dev_*, the i2c people prefers it Signed-off-by: Dennis Munsie Signed-off-by: Antonino Daplas Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fb.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fb.h b/include/linux/fb.h index 2f335e966011..37aab314f0c4 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -2,6 +2,7 @@ #define _LINUX_FB_H #include +#include /* Definitions of frame buffers */ @@ -940,6 +941,7 @@ extern void fb_edid_to_monspecs(unsigned char *edid, struct fb_monspecs *specs); extern void fb_destroy_modedb(struct fb_videomode *modedb); extern int fb_find_mode_cvt(struct fb_videomode *mode, int margins, int rb); +extern unsigned char *fb_ddc_read(struct i2c_adapter *adapter); /* drivers/video/modedb.c */ #define VESA_MODEDB_SIZE 34 -- cgit v1.2.3 From 1a6600be3e5dafe2ddcc5d969d931c2591eed896 Mon Sep 17 00:00:00 2001 From: "Antonino A. Daplas" Date: Tue, 3 Oct 2006 01:14:50 -0700 Subject: [PATCH] fbdev: Honor the return value of device_create_file Check the return value of device_create_file(). If return is 'fail', remove attributes by calling device_remove_file(). Signed-off-by: Antonino Daplas Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fb.h b/include/linux/fb.h index 37aab314f0c4..3e69241e6a81 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -776,6 +776,7 @@ struct fb_info { struct fb_ops *fbops; struct device *device; struct class_device *class_device; /* sysfs per device attrs */ + int class_flag; /* private sysfs flags */ #ifdef CONFIG_FB_TILEBLITTING struct fb_tile_ops *tileops; /* Tile Blitting */ #endif -- cgit v1.2.3 From 3cb340ecbb010013229ac56f26707252ebed09b8 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Tue, 3 Oct 2006 01:15:06 -0700 Subject: [PATCH] vt: proper prototypes for some console functions This patch adds proper prototypes to header files for three console init functions used on drivers/char/vt.c Signed-off-by: Adrian Bunk Signed-off-by: Antonino Daplas Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/console.h | 3 +++ include/linux/consolemap.h | 1 + 2 files changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/console.h b/include/linux/console.h index 76a1807726eb..7d0420274de0 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -129,6 +129,9 @@ static inline void suspend_console(void) {} static inline void resume_console(void) {} #endif /* CONFIG_DISABLE_CONSOLE_SUSPEND */ +int mda_console_init(void); +void prom_con_init(void); + /* Some debug stub to catch some of the obvious races in the VT code */ #if 1 #define WARN_CONSOLE_UNLOCKED() WARN_ON(!is_console_locked() && !oops_in_progress) diff --git a/include/linux/consolemap.h b/include/linux/consolemap.h index 65842efc1b70..82c9a1f11020 100644 --- a/include/linux/consolemap.h +++ b/include/linux/consolemap.h @@ -13,3 +13,4 @@ struct vc_data; extern unsigned char inverse_translate(struct vc_data *conp, int glyph); extern unsigned short *set_translate(int m, struct vc_data *vc); extern int conv_uni_to_pc(struct vc_data *conp, long ucs); +void console_map_init(void); -- cgit v1.2.3 From aa129a2247b164173d45da8ad43cca5de9211403 Mon Sep 17 00:00:00 2001 From: Milan Broz Date: Tue, 3 Oct 2006 01:15:15 -0700 Subject: [PATCH] dm: support ioctls on mapped devices Extend the core device-mapper infrastructure to accept arbitrary ioctls on a mapped device provided that it has exactly one target and it is capable of supporting ioctls. [We can't use unlocked_ioctl because we need 'inode': 'file' might be NULL. Is it worth changing this?] Signed-off-by: Milan Broz Signed-off-by: Alasdair G Kergon Arnd Bergmann wrote: > Am Wednesday 21 June 2006 21:31 schrieb Alasdair G Kergon: > > static struct block_device_operations dm_blk_dops = { > > .open = dm_blk_open, > > .release = dm_blk_close, > > +.ioctl = dm_blk_ioctl, > > .getgeo = dm_blk_getgeo, > > .owner = THIS_MODULE > > I guess this also needs a ->compat_ioctl method, otherwise it won't > work for ioctl numbers that have a compat_ioctl implementation in the > low-level device driver. Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/device-mapper.h | 5 +++++ include/linux/dm-ioctl.h | 2 +- 2 files changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index e3d1c33d1558..d44a99650af3 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -64,6 +64,10 @@ typedef int (*dm_status_fn) (struct dm_target *ti, status_type_t status_type, typedef int (*dm_message_fn) (struct dm_target *ti, unsigned argc, char **argv); +typedef int (*dm_ioctl_fn) (struct dm_target *ti, struct inode *inode, + struct file *filp, unsigned int cmd, + unsigned long arg); + void dm_error(const char *message); /* @@ -91,6 +95,7 @@ struct target_type { dm_resume_fn resume; dm_status_fn status; dm_message_fn message; + dm_ioctl_fn ioctl; }; struct io_restrictions { diff --git a/include/linux/dm-ioctl.h b/include/linux/dm-ioctl.h index 9623bb625090..b349b768df35 100644 --- a/include/linux/dm-ioctl.h +++ b/include/linux/dm-ioctl.h @@ -285,7 +285,7 @@ typedef char ioctl_struct[308]; #define DM_DEV_SET_GEOMETRY _IOWR(DM_IOCTL, DM_DEV_SET_GEOMETRY_CMD, struct dm_ioctl) #define DM_VERSION_MAJOR 4 -#define DM_VERSION_MINOR 7 +#define DM_VERSION_MINOR 8 #define DM_VERSION_PATCHLEVEL 0 #define DM_VERSION_EXTRA "-ioctl (2006-06-24)" -- cgit v1.2.3 From 7006f6eca874cd44d37ccb8cfeb8bed04e3bff22 Mon Sep 17 00:00:00 2001 From: Alasdair G Kergon Date: Tue, 3 Oct 2006 01:15:21 -0700 Subject: [PATCH] dm: export blkdev_driver_ioctl Export blkdev_driver_ioctl for device-mapper. If we get as far as the device-mapper ioctl handler, we know the ioctl is not a standard block layer BLK* one, so we don't need to check for them a second time and can call blkdev_driver_ioctl() directly. Signed-off-by: Alasdair G Kergon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 7b61e94bf8fc..f53bf4ff1955 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1523,6 +1523,9 @@ extern const struct file_operations def_fifo_fops; #ifdef CONFIG_BLOCK extern int ioctl_by_bdev(struct block_device *, unsigned, unsigned long); extern int blkdev_ioctl(struct inode *, struct file *, unsigned, unsigned long); +extern int blkdev_driver_ioctl(struct inode *inode, struct file *file, + struct gendisk *disk, unsigned cmd, + unsigned long arg); extern long compat_blkdev_ioctl(struct file *, unsigned, unsigned long); extern int blkdev_get(struct block_device *, mode_t, unsigned); extern int blkdev_put(struct block_device *); -- cgit v1.2.3 From 8757b7764f13e336f3c0eb1f634440d4ee4c3a67 Mon Sep 17 00:00:00 2001 From: Milan Broz Date: Tue, 3 Oct 2006 01:15:36 -0700 Subject: [PATCH] dm table: add target preresume This patch adds a target preresume hook. It is called before the targets are resumed and if it returns an error the resume gets cancelled. The crypt target will use this to indicate that it is unable to process I/O because no encryption key has been supplied. Signed-off-by: Milan Broz Signed-off-by: Alasdair G Kergon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/device-mapper.h | 2 ++ include/linux/dm-ioctl.h | 4 ++-- 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index d44a99650af3..8cbc46b8e3db 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -57,6 +57,7 @@ typedef int (*dm_endio_fn) (struct dm_target *ti, typedef void (*dm_presuspend_fn) (struct dm_target *ti); typedef void (*dm_postsuspend_fn) (struct dm_target *ti); +typedef int (*dm_preresume_fn) (struct dm_target *ti); typedef void (*dm_resume_fn) (struct dm_target *ti); typedef int (*dm_status_fn) (struct dm_target *ti, status_type_t status_type, @@ -92,6 +93,7 @@ struct target_type { dm_endio_fn end_io; dm_presuspend_fn presuspend; dm_postsuspend_fn postsuspend; + dm_preresume_fn preresume; dm_resume_fn resume; dm_status_fn status; dm_message_fn message; diff --git a/include/linux/dm-ioctl.h b/include/linux/dm-ioctl.h index b349b768df35..f28b5c87aa6b 100644 --- a/include/linux/dm-ioctl.h +++ b/include/linux/dm-ioctl.h @@ -285,9 +285,9 @@ typedef char ioctl_struct[308]; #define DM_DEV_SET_GEOMETRY _IOWR(DM_IOCTL, DM_DEV_SET_GEOMETRY_CMD, struct dm_ioctl) #define DM_VERSION_MAJOR 4 -#define DM_VERSION_MINOR 8 +#define DM_VERSION_MINOR 9 #define DM_VERSION_PATCHLEVEL 0 -#define DM_VERSION_EXTRA "-ioctl (2006-06-24)" +#define DM_VERSION_EXTRA "-ioctl (2006-09-14)" /* Status bits */ #define DM_READONLY_FLAG (1 << 0) /* In/Out */ -- cgit v1.2.3 From 3cb4021453a69585e458ec2177677c0c1300dccf Mon Sep 17 00:00:00 2001 From: Bryn Reeves Date: Tue, 3 Oct 2006 01:15:42 -0700 Subject: [PATCH] dm: extract device limit setting Separate the setting of device I/O limits from dm_get_device(). dm-loop will use this. Signed-off-by: Bryn Reeves Signed-off-by: Alasdair G Kergon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/device-mapper.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 8cbc46b8e3db..7a48d428d0a1 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -71,6 +71,11 @@ typedef int (*dm_ioctl_fn) (struct dm_target *ti, struct inode *inode, void dm_error(const char *message); +/* + * Combine device limits. + */ +void dm_set_device_limits(struct dm_target *ti, struct block_device *bdev); + /* * Constructors should call these functions to ensure destination devices * are opened/closed correctly. -- cgit v1.2.3 From 999d816851c3e080412a19558f111d01852d2f04 Mon Sep 17 00:00:00 2001 From: Bryn Reeves Date: Tue, 3 Oct 2006 01:15:43 -0700 Subject: [PATCH] dm table: add target flush This patch adds support for a per-target dm_flush_fn method. This is needed to allow dm-loop to invalidate page cache mappings in response to BLKFLSBUF ioctl commands. Signed-off-by: Bryn Reeves Signed-off-by: Alasdair G Kergon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/device-mapper.h | 2 ++ include/linux/dm-ioctl.h | 2 +- 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 7a48d428d0a1..03ef41c1eaac 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -55,6 +55,7 @@ typedef int (*dm_endio_fn) (struct dm_target *ti, struct bio *bio, int error, union map_info *map_context); +typedef void (*dm_flush_fn) (struct dm_target *ti); typedef void (*dm_presuspend_fn) (struct dm_target *ti); typedef void (*dm_postsuspend_fn) (struct dm_target *ti); typedef int (*dm_preresume_fn) (struct dm_target *ti); @@ -96,6 +97,7 @@ struct target_type { dm_dtr_fn dtr; dm_map_fn map; dm_endio_fn end_io; + dm_flush_fn flush; dm_presuspend_fn presuspend; dm_postsuspend_fn postsuspend; dm_preresume_fn preresume; diff --git a/include/linux/dm-ioctl.h b/include/linux/dm-ioctl.h index f28b5c87aa6b..8853fc4d1c5e 100644 --- a/include/linux/dm-ioctl.h +++ b/include/linux/dm-ioctl.h @@ -285,7 +285,7 @@ typedef char ioctl_struct[308]; #define DM_DEV_SET_GEOMETRY _IOWR(DM_IOCTL, DM_DEV_SET_GEOMETRY_CMD, struct dm_ioctl) #define DM_VERSION_MAJOR 4 -#define DM_VERSION_MINOR 9 +#define DM_VERSION_MINOR 10 #define DM_VERSION_PATCHLEVEL 0 #define DM_VERSION_EXTRA "-ioctl (2006-09-14)" -- cgit v1.2.3 From fbedac04fa11d7f9f9f425c7ec253f55becaae57 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Tue, 3 Oct 2006 01:15:44 -0700 Subject: [PATCH] md: the scheduled removal of the START_ARRAY ioctl for md This patch contains the scheduled removal of the START_ARRAY ioctl for md. Signed-off-by: Adrian Bunk Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compat_ioctl.h | 1 - include/linux/raid/md_u.h | 2 +- 2 files changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compat_ioctl.h b/include/linux/compat_ioctl.h index d5b7abc4f409..fad3957728a2 100644 --- a/include/linux/compat_ioctl.h +++ b/include/linux/compat_ioctl.h @@ -122,7 +122,6 @@ COMPATIBLE_IOCTL(PROTECT_ARRAY) ULONG_IOCTL(HOT_ADD_DISK) ULONG_IOCTL(SET_DISK_FAULTY) COMPATIBLE_IOCTL(RUN_ARRAY) -ULONG_IOCTL(START_ARRAY) COMPATIBLE_IOCTL(STOP_ARRAY) COMPATIBLE_IOCTL(STOP_ARRAY_RO) COMPATIBLE_IOCTL(RESTART_ARRAY_RW) diff --git a/include/linux/raid/md_u.h b/include/linux/raid/md_u.h index 81da20ccec4d..7192035fc4b0 100644 --- a/include/linux/raid/md_u.h +++ b/include/linux/raid/md_u.h @@ -41,7 +41,7 @@ /* usage */ #define RUN_ARRAY _IOW (MD_MAJOR, 0x30, mdu_param_t) -#define START_ARRAY _IO (MD_MAJOR, 0x31) +/* 0x31 was START_ARRAY */ #define STOP_ARRAY _IO (MD_MAJOR, 0x32) #define STOP_ARRAY_RO _IO (MD_MAJOR, 0x33) #define RESTART_ARRAY_RW _IO (MD_MAJOR, 0x34) -- cgit v1.2.3 From b5c124af69119c1b5c1e728bd2e7b5b1fad9b7be Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 3 Oct 2006 01:15:45 -0700 Subject: [PATCH] md: fix a comment that is wrong in raid5.h Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/raid/raid5.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/raid/raid5.h b/include/linux/raid/raid5.h index 20ed4c997636..f1e28952a82f 100644 --- a/include/linux/raid/raid5.h +++ b/include/linux/raid/raid5.h @@ -195,8 +195,9 @@ struct stripe_head { * it to the count of prereading stripes. * When write is initiated, or the stripe refcnt == 0 (just in case) we * clear the PREREAD_ACTIVE flag and decrement the count - * Whenever the delayed queue is empty and the device is not plugged, we - * move any strips from delayed to handle and clear the DELAYED flag and set PREREAD_ACTIVE. + * Whenever the 'handle' queue is empty and the device is not plugged, we + * move any strips from delayed to handle and clear the DELAYED flag and set + * PREREAD_ACTIVE. * In stripe_handle, if we find pre-reading is necessary, we do it if * PREREAD_ACTIVE is set, else we set DELAYED which will send it to the delayed queue. * HANDLE gets cleared if stripe_handle leave nothing locked. -- cgit v1.2.3 From 850b2b420cd5b363ed4cf48a8816d656c8b5251b Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 3 Oct 2006 01:15:46 -0700 Subject: [PATCH] md: replace magic numbers in sb_dirty with well defined bit flags Instead of magic numbers (0,1,2,3) in sb_dirty, we have some flags instead: MD_CHANGE_DEVS Some device state has changed requiring superblock update on all devices. MD_CHANGE_CLEAN The array has transitions from 'clean' to 'dirty' or back, requiring a superblock update on active devices, but possibly not on spares MD_CHANGE_PENDING A superblock update is underway. We wait for an update to complete by waiting for all flags to be clear. A flag can be set at any time, even during an update, without risk that the change will be lost. Stop exporting md_update_sb - isn't needed. Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/raid/md.h | 1 - include/linux/raid/md_k.h | 6 +++++- 2 files changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/raid/md.h b/include/linux/raid/md.h index c588709acbbc..866a1e2b0ce0 100644 --- a/include/linux/raid/md.h +++ b/include/linux/raid/md.h @@ -95,7 +95,6 @@ extern int sync_page_io(struct block_device *bdev, sector_t sector, int size, extern void md_do_sync(mddev_t *mddev); extern void md_new_event(mddev_t *mddev); -extern void md_update_sb(mddev_t * mddev); #endif /* CONFIG_MD */ #endif diff --git a/include/linux/raid/md_k.h b/include/linux/raid/md_k.h index 920b94fe31fa..e423dad1a7fd 100644 --- a/include/linux/raid/md_k.h +++ b/include/linux/raid/md_k.h @@ -116,7 +116,11 @@ struct mddev_s dev_t unit; int md_minor; struct list_head disks; - int sb_dirty; + unsigned long flags; +#define MD_CHANGE_DEVS 0 /* Some device status has changed */ +#define MD_CHANGE_CLEAN 1 /* transition to or from 'clean' */ +#define MD_CHANGE_PENDING 2 /* superblock update in progress */ + int ro; struct gendisk *gendisk; -- cgit v1.2.3 From 02c2de8cc835885bdff51a8bfd6c0b659b969f50 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 3 Oct 2006 01:15:47 -0700 Subject: [PATCH] md: remove the working_disks and failed_disks from raid5 state data. They are not needed. conf->failed_disks is the same as mddev->degraded and conf->working_disks is conf->raid_disks - mddev->degraded. Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/raid/raid5.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/raid/raid5.h b/include/linux/raid/raid5.h index f1e28952a82f..f13299a15591 100644 --- a/include/linux/raid/raid5.h +++ b/include/linux/raid/raid5.h @@ -214,7 +214,7 @@ struct raid5_private_data { struct disk_info *spare; int chunk_size, level, algorithm; int max_degraded; - int raid_disks, working_disks, failed_disks; + int raid_disks; int max_nr_stripes; /* used during an expand */ -- cgit v1.2.3 From 76186dd8b73d2b7b9b4c8629b89c845e97009801 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 3 Oct 2006 01:15:48 -0700 Subject: [PATCH] md: remove 'working_disks' from raid10 state It isn't needed as mddev->degraded contains equivalent info. Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/raid/raid10.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/raid/raid10.h b/include/linux/raid/raid10.h index c41e56a7c090..e9091cfeb286 100644 --- a/include/linux/raid/raid10.h +++ b/include/linux/raid/raid10.h @@ -16,7 +16,6 @@ struct r10_private_data_s { mddev_t *mddev; mirror_info_t *mirrors; int raid_disks; - int working_disks; spinlock_t device_lock; /* geometry */ -- cgit v1.2.3 From 9b1d1dac181d8c1b9492e05cee660a985d035a06 Mon Sep 17 00:00:00 2001 From: Paul Clements Date: Tue, 3 Oct 2006 01:15:49 -0700 Subject: [PATCH] md: new sysfs interface for setting bits in the write-intent-bitmap Add a new sysfs interface that allows the bitmap of an array to be dirtied. The interface is write-only, and is used as follows: echo "1000" > /sys/block/md2/md/bitmap (dirty the bit for chunk 1000 [offset 0] in the in-memory and on-disk bitmaps of array md2) echo "1000-2000" > /sys/block/md1/md/bitmap (dirty the bits for chunks 1000-2000 in md1's bitmap) This is useful, for example, in cluster environments where you may need to combine two disjoint bitmaps into one (following a server failure, after a secondary server has taken over the array). By combining the bitmaps on the two servers, a full resync can be avoided (This was discussed on the list back on March 18, 2005, "[PATCH 1/2] md bitmap bug fixes" thread). Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/raid/bitmap.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/raid/bitmap.h b/include/linux/raid/bitmap.h index 63df898fe2e9..84d887751855 100644 --- a/include/linux/raid/bitmap.h +++ b/include/linux/raid/bitmap.h @@ -265,6 +265,8 @@ int bitmap_update_sb(struct bitmap *bitmap); int bitmap_setallbits(struct bitmap *bitmap); void bitmap_write_all(struct bitmap *bitmap); +void bitmap_dirty_bits(struct bitmap *bitmap, unsigned long s, unsigned long e); + /* these are exported */ int bitmap_startwrite(struct bitmap *bitmap, sector_t offset, unsigned long sectors, int behind); -- cgit v1.2.3 From 11ce99e625fe2718ad2682bfdd99070b337e6252 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 3 Oct 2006 01:15:52 -0700 Subject: [PATCH] md: Remove working_disks from raid1 state data It is equivalent to conf->raid_disks - conf->mddev->degraded. Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/raid/raid1.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/raid/raid1.h b/include/linux/raid/raid1.h index 3009c813d83d..0a9ba7c3302e 100644 --- a/include/linux/raid/raid1.h +++ b/include/linux/raid/raid1.h @@ -30,7 +30,6 @@ struct r1_private_data_s { mddev_t *mddev; mirror_info_t *mirrors; int raid_disks; - int working_disks; int last_used; sector_t next_seq_sect; spinlock_t device_lock; -- cgit v1.2.3 From e8703fe1f5cdcff686f7eb0a46487b5a04a9324a Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 3 Oct 2006 01:15:59 -0700 Subject: [PATCH] md: remove MAX_MD_DEVS which is an arbitrary limit Once upon a time we needed to fixed limit to the number of md devices, probably because we preallocated some array. This need no longer exists, but we still have an arbitrary limit. So remove MAX_MD_DEVS and allow as many devices as we can fit into the 'minor' part of a device number. Also remove some useless noise at init time (which reports MAX_MD_DEVS) and remove MD_THREAD_NAME_MAX which hasn't been used for a while. Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/raid/md_k.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/raid/md_k.h b/include/linux/raid/md_k.h index e423dad1a7fd..8245c282168b 100644 --- a/include/linux/raid/md_k.h +++ b/include/linux/raid/md_k.h @@ -31,18 +31,15 @@ #define LEVEL_NONE (-1000000) #define MaxSector (~(sector_t)0) -#define MD_THREAD_NAME_MAX 14 typedef struct mddev_s mddev_t; typedef struct mdk_rdev_s mdk_rdev_t; -#define MAX_MD_DEVS 256 /* Max number of md dev */ - /* * options passed in raidrun: */ -/* Currently this must fix in an 'int' */ +/* Currently this must fit in an 'int' */ #define MAX_CHUNK_SIZE (1<<30) /* -- cgit v1.2.3 From d19c2ee0b8d1cd83f8bc0f1f5e94e6b6ec71ea10 Mon Sep 17 00:00:00 2001 From: Paul Clements Date: Tue, 3 Oct 2006 01:16:02 -0700 Subject: [PATCH] md: allow SET_BITMAP_FILE to work on 64bit kernel with 32bit userspace Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compat_ioctl.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/compat_ioctl.h b/include/linux/compat_ioctl.h index fad3957728a2..4e1663d7691e 100644 --- a/include/linux/compat_ioctl.h +++ b/include/linux/compat_ioctl.h @@ -125,6 +125,7 @@ COMPATIBLE_IOCTL(RUN_ARRAY) COMPATIBLE_IOCTL(STOP_ARRAY) COMPATIBLE_IOCTL(STOP_ARRAY_RO) COMPATIBLE_IOCTL(RESTART_ARRAY_RW) +ULONG_IOCTL(SET_BITMAP_FILE) /* DM */ COMPATIBLE_IOCTL(DM_VERSION_32) COMPATIBLE_IOCTL(DM_REMOVE_ALL_32) -- cgit v1.2.3 From 8b2a1fd1b394c60eaa2587716102dd5e9b4e5990 Mon Sep 17 00:00:00 2001 From: Zach Brown Date: Tue, 3 Oct 2006 01:16:15 -0700 Subject: [PATCH] pr_debug: check pr_debug() arguments check pr_debug() arguments When DEBUG isn't defined pr_debug() is defined away as an empty macro. By throwing away the arguments we allow completely incorrect code to build. Instead let's make it an empty inline which checks arguments and mark it so gcc can check the format specification. This results in a seemingly insignificant code size increase. A x86-64 allyesconfig: text data bss dec hex filename 25354768 7191098 4854720 37400586 23ab00a vmlinux.before 25354945 7191138 4854720 37400803 23ab0e3 vmlinux Signed-off-by: Zach Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 4d00988dad03..80f39cab470a 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -216,8 +216,10 @@ extern void dump_stack(void); #define pr_debug(fmt,arg...) \ printk(KERN_DEBUG fmt,##arg) #else -#define pr_debug(fmt,arg...) \ - do { } while (0) +static inline int __attribute__ ((format (printf, 1, 2))) pr_debug(const char * fmt, ...) +{ + return 0; +} #endif #define pr_info(fmt,arg...) \ -- cgit v1.2.3 From 15a1c5140436c5be7673a4709c5d7e1f3cd7bdd9 Mon Sep 17 00:00:00 2001 From: "Maciej W. Rozycki" Date: Mon, 2 Oct 2006 12:55:09 +0100 Subject: [MIPS] BCM1250: TRDY timeout tweaks for Broadcom SiByte systems It was obesrved that at least one older PCI card predating the requirement for the TRDY signal to respond within 16 clock ticks actually does not meet this rule nor even the power-on defaults of the PCI bridges found in development systems built around the Broadcom SiByte SOCs. Here is a patch that bumps up the timeout to the highest finite value supported by these chips, which is 255 clock ticks. The bridges affected are the SiByte SOC itself and the SP1011. This change does not effectively affect systems only having PCI option cards installed that meet the TRDY requirement of the current PCI spec. The rule was introduced with PCI 2.1, so any older card may make the system affected. If this is the case, performance of the system will suffer in return for the card working at all. If this is a concern, then the solution is not to use such cards. Signed-off-by: Maciej W. Rozycki Signed-off-by: Ralf Baechle --- --- include/linux/pci_ids.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index c9ffbc3843d5..dc7f573d36e4 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1883,6 +1883,8 @@ #define PCI_DEVICE_ID_PANACOM_QUADMODEM 0x0400 #define PCI_DEVICE_ID_PANACOM_DUALMODEM 0x0402 +#define PCI_VENDOR_ID_SIPACKETS 0x14d9 +#define PCI_DEVICE_ID_SP1011 0x0010 #define PCI_VENDOR_ID_AFAVLAB 0x14db #define PCI_DEVICE_ID_AFAVLAB_P028 0x2180 @@ -1997,6 +1999,7 @@ #define PCI_DEVICE_ID_FARSITE_TE1C 0x1612 #define PCI_VENDOR_ID_SIBYTE 0x166d +#define PCI_DEVICE_ID_BCM1250_PCI 0x0001 #define PCI_DEVICE_ID_BCM1250_HT 0x0002 #define PCI_VENDOR_ID_NETCELL 0x169c -- cgit v1.2.3 From af8b128719f5248e542036ea994610a29d0642a6 Mon Sep 17 00:00:00 2001 From: Yoichi Yuasa Date: Mon, 2 Oct 2006 23:19:00 +0900 Subject: [MIPS] Remove IT8172-based platforms, ITE 8172G and Globespan IVR support. As per feature-removal-schedule.txt. Signed-off-by: Yoichi Yuasa Acked-by: Alan Cox Signed-off-by: Ralf Baechle --- include/linux/ite_gpio.h | 66 ------------------------------------------------ include/linux/pci_ids.h | 2 -- 2 files changed, 68 deletions(-) delete mode 100644 include/linux/ite_gpio.h (limited to 'include/linux') diff --git a/include/linux/ite_gpio.h b/include/linux/ite_gpio.h deleted file mode 100644 index b123a14292d3..000000000000 --- a/include/linux/ite_gpio.h +++ /dev/null @@ -1,66 +0,0 @@ -/* - * FILE NAME ite_gpio.h - * - * BRIEF MODULE DESCRIPTION - * Generic gpio. - * - * Author: MontaVista Software, Inc. - * Hai-Pao Fan - * - * Copyright 2001 MontaVista Software Inc. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - * - * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED - * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF - * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN - * NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, - * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT - * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF - * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON - * ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF - * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 675 Mass Ave, Cambridge, MA 02139, USA. - */ - -#ifndef __ITE_GPIO_H -#define __ITE_GPIO_H - -#include - -struct ite_gpio_ioctl_data { - __u32 device; - __u32 mask; - __u32 data; -}; - -#define ITE_GPIO_IOCTL_BASE 'Z' - -#define ITE_GPIO_IN _IOWR(ITE_GPIO_IOCTL_BASE, 0, struct ite_gpio_ioctl_data) -#define ITE_GPIO_OUT _IOW (ITE_GPIO_IOCTL_BASE, 1, struct ite_gpio_ioctl_data) -#define ITE_GPIO_INT_CTRL _IOW (ITE_GPIO_IOCTL_BASE, 2, struct ite_gpio_ioctl_data) -#define ITE_GPIO_IN_STATUS _IOW (ITE_GPIO_IOCTL_BASE, 3, struct ite_gpio_ioctl_data) -#define ITE_GPIO_OUT_STATUS _IOW (ITE_GPIO_IOCTL_BASE, 4, struct ite_gpio_ioctl_data) -#define ITE_GPIO_GEN_CTRL _IOW (ITE_GPIO_IOCTL_BASE, 5, struct ite_gpio_ioctl_data) -#define ITE_GPIO_INT_WAIT _IOW (ITE_GPIO_IOCTL_BASE, 6, struct ite_gpio_ioctl_data) - -#define ITE_GPIO_PORTA 0x01 -#define ITE_GPIO_PORTB 0x02 -#define ITE_GPIO_PORTC 0x04 - -extern int ite_gpio_in(__u32 device, __u32 mask, volatile __u32 *data); -extern int ite_gpio_out(__u32 device, __u32 mask, __u32 data); -extern int ite_gpio_int_ctrl(__u32 device, __u32 mask, __u32 data); -extern int ite_gpio_in_status(__u32 device, __u32 mask, volatile __u32 *data); -extern int ite_gpio_out_status(__u32 device, __u32 mask, __u32 data); -extern int ite_gpio_gen_ctrl(__u32 device, __u32 mask, __u32 data); -extern int ite_gpio_int_wait(__u32 device, __u32 mask, __u32 data); - -#endif diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index dc7f573d36e4..f069df245469 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1615,8 +1615,6 @@ #define PCI_VENDOR_ID_ROCKWELL 0x127A #define PCI_VENDOR_ID_ITE 0x1283 -#define PCI_DEVICE_ID_ITE_IT8172G 0x8172 -#define PCI_DEVICE_ID_ITE_IT8172G_AUDIO 0x0801 #define PCI_DEVICE_ID_ITE_8211 0x8211 #define PCI_DEVICE_ID_ITE_8212 0x8212 #define PCI_DEVICE_ID_ITE_8872 0x8872 -- cgit v1.2.3 From 92b2db08b1150576d295ba9440e172675095c3ae Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Thu, 28 Sep 2006 13:42:05 -0300 Subject: V4L/DVB (4672): Frame format enumeration (1/2) Add VIDIOC_ENUM_FRAMESIZES and VIDIOC_ENUM_FRAMEINTERVALS ioctls to enumerate supported frame sizes and frame intervals. Signed-off-by: Martin Rubli Signed-off-by: Laurent Pinchart Signed-off-by: Mauro Carvalho Chehab --- include/linux/videodev2.h | 75 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 75 insertions(+) (limited to 'include/linux') diff --git a/include/linux/videodev2.h b/include/linux/videodev2.h index 44c59da26ed2..253a7ed3abb3 100644 --- a/include/linux/videodev2.h +++ b/include/linux/videodev2.h @@ -276,6 +276,79 @@ struct v4l2_fmtdesc #define V4L2_FMT_FLAG_COMPRESSED 0x0001 +/* + * F R A M E S I Z E E N U M E R A T I O N + */ +enum v4l2_frmsizetypes +{ + V4L2_FRMSIZE_TYPE_DISCRETE = 1, + V4L2_FRMSIZE_TYPE_CONTINUOUS = 2, + V4L2_FRMSIZE_TYPE_STEPWISE = 3, +}; + +struct v4l2_frmsize_discrete +{ + __u32 width; /* Frame width [pixel] */ + __u32 height; /* Frame height [pixel] */ +}; + +struct v4l2_frmsize_stepwise +{ + __u32 min_width; /* Minimum frame width [pixel] */ + __u32 max_width; /* Maximum frame width [pixel] */ + __u32 step_width; /* Frame width step size [pixel] */ + __u32 min_height; /* Minimum frame height [pixel] */ + __u32 max_height; /* Maximum frame height [pixel] */ + __u32 step_height; /* Frame height step size [pixel] */ +}; + +struct v4l2_frmsizeenum +{ + __u32 index; /* Frame size number */ + __u32 pixel_format; /* Pixel format */ + __u32 type; /* Frame size type the device supports. */ + + union { /* Frame size */ + struct v4l2_frmsize_discrete discrete; + struct v4l2_frmsize_stepwise stepwise; + }; + + __u32 reserved[2]; /* Reserved space for future use */ +}; + +/* + * F R A M E R A T E E N U M E R A T I O N + */ +enum v4l2_frmivaltypes +{ + V4L2_FRMIVAL_TYPE_DISCRETE = 1, + V4L2_FRMIVAL_TYPE_CONTINUOUS = 2, + V4L2_FRMIVAL_TYPE_STEPWISE = 3, +}; + +struct v4l2_frmival_stepwise +{ + struct v4l2_fract min; /* Minimum frame interval [s] */ + struct v4l2_fract max; /* Maximum frame interval [s] */ + struct v4l2_fract step; /* Frame interval step size [s] */ +}; + +struct v4l2_frmivalenum +{ + __u32 index; /* Frame format index */ + __u32 pixel_format; /* Pixel format */ + __u32 width; /* Frame width */ + __u32 height; /* Frame height */ + __u32 type; /* Frame interval type the device supports. */ + + union { /* Frame interval */ + struct v4l2_fract discrete; + struct v4l2_frmival_stepwise stepwise; + }; + + __u32 reserved[2]; /* Reserved space for future use */ +}; + /* * T I M E C O D E */ @@ -1249,6 +1322,8 @@ struct v4l2_streamparm #define VIDIOC_G_EXT_CTRLS _IOWR ('V', 71, struct v4l2_ext_controls) #define VIDIOC_S_EXT_CTRLS _IOWR ('V', 72, struct v4l2_ext_controls) #define VIDIOC_TRY_EXT_CTRLS _IOWR ('V', 73, struct v4l2_ext_controls) +#define VIDIOC_ENUM_FRAMESIZES _IOWR ('V', 74, struct v4l2_frmsizeenum) +#define VIDIOC_ENUM_FRAMEINTERVALS _IOWR ('V', 75, struct v4l2_frmivalenum) #ifdef __OLD_VIDIOC_ /* for compatibility, will go away some day */ -- cgit v1.2.3 From dcc29cbcec8c8482eea249030e0aa65b7451073d Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 28 Sep 2006 13:48:26 -0300 Subject: V4L/DVB (4673): Mark the two newer ioctls as experimental VIDIOC_ENUM_FRAMESIZES and VIDIOC_ENUM_FRAMEINTERVALS ioctls are meant to be used to provide better support for webcams. Currently, it is not yet used on kernel drivers. Better to keep it marked as experimental, until we have several kernel drivers supporting those features. Signed-off-by: Mauro Carvalho Chehab --- include/linux/videodev2.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/videodev2.h b/include/linux/videodev2.h index 253a7ed3abb3..c5fdf6259548 100644 --- a/include/linux/videodev2.h +++ b/include/linux/videodev2.h @@ -276,6 +276,8 @@ struct v4l2_fmtdesc #define V4L2_FMT_FLAG_COMPRESSED 0x0001 +#if 1 + /* Experimental Frame Size and frame rate enumeration */ /* * F R A M E S I Z E E N U M E R A T I O N */ @@ -348,6 +350,7 @@ struct v4l2_frmivalenum __u32 reserved[2]; /* Reserved space for future use */ }; +#endif /* * T I M E C O D E @@ -1322,8 +1325,10 @@ struct v4l2_streamparm #define VIDIOC_G_EXT_CTRLS _IOWR ('V', 71, struct v4l2_ext_controls) #define VIDIOC_S_EXT_CTRLS _IOWR ('V', 72, struct v4l2_ext_controls) #define VIDIOC_TRY_EXT_CTRLS _IOWR ('V', 73, struct v4l2_ext_controls) +#if 1 #define VIDIOC_ENUM_FRAMESIZES _IOWR ('V', 74, struct v4l2_frmsizeenum) #define VIDIOC_ENUM_FRAMEINTERVALS _IOWR ('V', 75, struct v4l2_frmivalenum) +#endif #ifdef __OLD_VIDIOC_ /* for compatibility, will go away some day */ -- cgit v1.2.3 From f30c2269544bffc7bf1b0d7c0abe5be1be83b8cb Mon Sep 17 00:00:00 2001 From: Uwe Zeisberger Date: Tue, 3 Oct 2006 23:01:26 +0200 Subject: fix file specification in comments Many files include the filename at the beginning, serveral used a wrong one. Signed-off-by: Uwe Zeisberger Signed-off-by: Adrian Bunk --- include/linux/aio_abi.h | 2 +- include/linux/awe_voice.h | 2 +- include/linux/harrier_defs.h | 2 +- include/linux/lockd/xdr4.h | 2 +- include/linux/mtd/plat-ram.h | 2 +- include/linux/nfsd/stats.h | 2 +- include/linux/nfsd/xdr.h | 2 +- include/linux/ppdev.h | 2 +- include/linux/slab.h | 2 +- include/linux/sunrpc/auth_gss.h | 2 +- include/linux/sunrpc/gss_api.h | 2 +- include/linux/sunrpc/msg_prot.h | 2 +- include/linux/sunrpc/svcauth_gss.h | 2 +- include/linux/writeback.h | 2 +- 14 files changed, 14 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/aio_abi.h b/include/linux/aio_abi.h index 3466b1d0ffd2..e3ca0a485cc6 100644 --- a/include/linux/aio_abi.h +++ b/include/linux/aio_abi.h @@ -1,4 +1,4 @@ -/* linux/aio_abi.h +/* include/linux/aio_abi.h * * Copyright 2000,2001,2002 Red Hat. * diff --git a/include/linux/awe_voice.h b/include/linux/awe_voice.h index 4bf9f33048e2..bf33f17bea99 100644 --- a/include/linux/awe_voice.h +++ b/include/linux/awe_voice.h @@ -1,5 +1,5 @@ /* - * sound/awe_voice.h + * include/linux/awe_voice.h * * Voice information definitions for the low level driver for the * AWE32/SB32/AWE64 wave table synth. diff --git a/include/linux/harrier_defs.h b/include/linux/harrier_defs.h index 685b252e16cc..efef11db790f 100644 --- a/include/linux/harrier_defs.h +++ b/include/linux/harrier_defs.h @@ -1,5 +1,5 @@ /* - * asm-ppc/harrier_defs.h + * include/linux/harrier_defs.h * * Definitions for Motorola MCG Harrier North Bridge & Memory controller * diff --git a/include/linux/lockd/xdr4.h b/include/linux/lockd/xdr4.h index cee36e7c0548..3cc1ae25009b 100644 --- a/include/linux/lockd/xdr4.h +++ b/include/linux/lockd/xdr4.h @@ -1,5 +1,5 @@ /* - * linux/include/linux/lockd/xdr.h + * linux/include/linux/lockd/xdr4.h * * XDR types for the NLM protocol * diff --git a/include/linux/mtd/plat-ram.h b/include/linux/mtd/plat-ram.h index 2332eda07e0e..9667863bd7e3 100644 --- a/include/linux/mtd/plat-ram.h +++ b/include/linux/mtd/plat-ram.h @@ -1,4 +1,4 @@ -/* linux/include/mtd/plat-ram.h +/* linux/include/linux/mtd/plat-ram.h * * (c) 2004 Simtec Electronics * http://www.simtec.co.uk/products/SWLINUX/ diff --git a/include/linux/nfsd/stats.h b/include/linux/nfsd/stats.h index 28a82fdd922f..7678cfbe9960 100644 --- a/include/linux/nfsd/stats.h +++ b/include/linux/nfsd/stats.h @@ -1,5 +1,5 @@ /* - * linux/include/nfsd/stats.h + * linux/include/linux/nfsd/stats.h * * Statistics for NFS server. * diff --git a/include/linux/nfsd/xdr.h b/include/linux/nfsd/xdr.h index 3f4f7142bbe3..a38f9d776de9 100644 --- a/include/linux/nfsd/xdr.h +++ b/include/linux/nfsd/xdr.h @@ -1,5 +1,5 @@ /* - * linux/inxlude/linux/nfsd/xdr.h + * linux/include/linux/nfsd/xdr.h * * XDR types for nfsd. This is mainly a typing exercise. */ diff --git a/include/linux/ppdev.h b/include/linux/ppdev.h index f376a7598a78..dc18c5d23ebe 100644 --- a/include/linux/ppdev.h +++ b/include/linux/ppdev.h @@ -1,5 +1,5 @@ /* - * linux/drivers/char/ppdev.h + * linux/include/linux/ppdev.h * * User-space parallel port device driver (header file). * diff --git a/include/linux/slab.h b/include/linux/slab.h index a96fd9310d55..70be57d8ae0d 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -1,5 +1,5 @@ /* - * linux/mm/slab.h + * linux/include/linux/slab.h * Written by Mark Hemment, 1996. * (markhe@nextd.demon.co.uk) */ diff --git a/include/linux/sunrpc/auth_gss.h b/include/linux/sunrpc/auth_gss.h index 03084dc4bb6a..97b62e97dd8d 100644 --- a/include/linux/sunrpc/auth_gss.h +++ b/include/linux/sunrpc/auth_gss.h @@ -1,5 +1,5 @@ /* - * linux/include/linux/auth_gss.h + * linux/include/linux/sunrpc/auth_gss.h * * Declarations for RPCSEC_GSS * diff --git a/include/linux/sunrpc/gss_api.h b/include/linux/sunrpc/gss_api.h index 6e112cc5cdda..5eca9e442051 100644 --- a/include/linux/sunrpc/gss_api.h +++ b/include/linux/sunrpc/gss_api.h @@ -1,5 +1,5 @@ /* - * linux/include/linux/gss_api.h + * linux/include/linux/sunrpc/gss_api.h * * Somewhat simplified version of the gss api. * diff --git a/include/linux/sunrpc/msg_prot.h b/include/linux/sunrpc/msg_prot.h index d9f5934ac9fe..8d10d148834e 100644 --- a/include/linux/sunrpc/msg_prot.h +++ b/include/linux/sunrpc/msg_prot.h @@ -1,5 +1,5 @@ /* - * linux/include/net/sunrpc/msg_prot.h + * linux/include/linux/sunrpc/msg_prot.h * * Copyright (C) 1996, Olaf Kirch */ diff --git a/include/linux/sunrpc/svcauth_gss.h b/include/linux/sunrpc/svcauth_gss.h index 3a2206f61de0..5a5db16ab660 100644 --- a/include/linux/sunrpc/svcauth_gss.h +++ b/include/linux/sunrpc/svcauth_gss.h @@ -1,5 +1,5 @@ /* - * linux/include/linux/svcauth_gss.h + * linux/include/linux/sunrpc/svcauth_gss.h * * Bruce Fields * Copyright (c) 2002 The Regents of the Unviersity of Michigan diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 4f4d98addb44..a341c8032866 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -1,5 +1,5 @@ /* - * include/linux/writeback.h. + * include/linux/writeback.h */ #ifndef WRITEBACK_H #define WRITEBACK_H -- cgit v1.2.3 From 9865853851313e0d94a4acde42d6f9d8070bb376 Mon Sep 17 00:00:00 2001 From: Li Yang Date: Tue, 3 Oct 2006 23:10:46 -0500 Subject: [POWERPC] Add QUICC Engine (QE) infrastructure Add QUICC Engine (QE) configuration, header files, and QE management and library code that are used by QE devices drivers. Includes Leo's modifications up to, and including, the platform_device to of_device adaptation: "The series of patches add generic QE infrastructure called qe_lib, and MPC8360EMDS board support. Qe_lib is used by QE device drivers such as ucc_geth driver. This version updates QE interrupt controller to use new irq mapping mechanism, addresses all the comments received with last submission and includes some style fixes. v2: Change to use device tree for BCSR and MURAM; Remove I/O port interrupt handling code as it is not generic enough. v3: Address comments from Kumar; Update definition of several device tree nodes; Copyright style change." In addition, the following changes have been made: o removed typedefs o uint -> u32 conversions o removed following defines: QE_SIZEOF_BD, BD_BUFFER_ARG, BD_BUFFER_CLEAR, BD_BUFFER, BD_STATUS_AND_LENGTH_SET, BD_STATUS_AND_LENGTH, and BD_BUFFER_SET because they hid sizeof/in_be32/out_be32 operations from the reader. o fixed qe_snums_init() serial num assignment to use a const array o made CONFIG_UCC_FAST select UCC_SLOW o reduced NR_QE_IC_INTS from 128 to 64 o remove _IO_BASE, etc. defines (not used) o removed irrelevant comments, added others to resemble removed BD_ defines o realigned struct definitions in headers o various other style fixes including things like pinMask -> pin_mask o fixed a ton of whitespace issues o marked ioregs as __be32/__be16 o removed platform_device code and redundant get_qe_base() o removed redundant comments o added cpu_relax() to qe_reset o uncasted all get_property() assignments o eliminated unneeded casts o eliminated immrbar_phys_to_virt (not used) Signed-off-by: Li Yang Signed-off-by: Shlomi Gridish Signed-off-by: Kim Phillips Signed-off-by: Paul Mackerras --- include/linux/fsl_devices.h | 65 +++++++++++++++++++++++++++++++++++---------- 1 file changed, 51 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsl_devices.h b/include/linux/fsl_devices.h index 16fbe59edeb1..3da29e2d524a 100644 --- a/include/linux/fsl_devices.h +++ b/include/linux/fsl_devices.h @@ -46,18 +46,17 @@ struct gianfar_platform_data { /* device specific information */ - u32 device_flags; - + u32 device_flags; /* board specific information */ - u32 board_flags; - u32 bus_id; - u32 phy_id; - u8 mac_addr[6]; + u32 board_flags; + u32 bus_id; + u32 phy_id; + u8 mac_addr[6]; }; struct gianfar_mdio_data { /* board specific information */ - int irq[32]; + int irq[32]; }; /* Flags related to gianfar device features */ @@ -76,14 +75,13 @@ struct gianfar_mdio_data { struct fsl_i2c_platform_data { /* device specific information */ - u32 device_flags; + u32 device_flags; }; /* Flags related to I2C device features */ #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, @@ -101,9 +99,9 @@ enum fsl_usb2_phy_modes { 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; + 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 */ @@ -121,5 +119,44 @@ struct fsl_spi_platform_data { u32 sysclk; }; -#endif /* _FSL_DEVICE_H_ */ -#endif /* __KERNEL__ */ +/* Ethernet interface (phy management and speed) +*/ +enum enet_interface { + ENET_10_MII, /* 10 Base T, MII interface */ + ENET_10_RMII, /* 10 Base T, RMII interface */ + ENET_10_RGMII, /* 10 Base T, RGMII interface */ + ENET_100_MII, /* 100 Base T, MII interface */ + ENET_100_RMII, /* 100 Base T, RMII interface */ + ENET_100_RGMII, /* 100 Base T, RGMII interface */ + ENET_1000_GMII, /* 1000 Base T, GMII interface */ + ENET_1000_RGMII, /* 1000 Base T, RGMII interface */ + ENET_1000_TBI, /* 1000 Base T, TBI interface */ + ENET_1000_RTBI /* 1000 Base T, RTBI interface */ +}; + +struct ucc_geth_platform_data { + /* device specific information */ + u32 device_flags; + u32 phy_reg_addr; + + /* board specific information */ + u32 board_flags; + u8 rx_clock; + u8 tx_clock; + u32 phy_id; + enum enet_interface phy_interface; + u32 phy_interrupt; + u8 mac_addr[6]; +}; + +/* Flags related to UCC Gigabit Ethernet device features */ +#define FSL_UGETH_DEV_HAS_GIGABIT 0x00000001 +#define FSL_UGETH_DEV_HAS_COALESCE 0x00000002 +#define FSL_UGETH_DEV_HAS_RMON 0x00000004 + +/* Flags in ucc_geth_platform_data */ +#define FSL_UGETH_BRD_HAS_PHY_INTR 0x00000001 + /* if not set use a timer */ + +#endif /* _FSL_DEVICE_H_ */ +#endif /* __KERNEL__ */ -- cgit v1.2.3 From b4c4ed175ff0ee816df48571cfa9b73f521964b6 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Mon, 2 Oct 2006 16:11:13 -0700 Subject: [NETFILTER]: add type parameter to ip_route_me_harder By adding a type parameter to ip_route_me_harder() the expensive call to inet_addr_type() can be avoided in some cases. A followup patch where ip_route_me_harder() is called from within ip_vs_out() is one such example. Signed-off-By: Simon Horman Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter_ipv4.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv4.h b/include/linux/netfilter_ipv4.h index ce02c984f3ba..5b63a231a76b 100644 --- a/include/linux/netfilter_ipv4.h +++ b/include/linux/netfilter_ipv4.h @@ -77,7 +77,7 @@ enum nf_ip_hook_priorities { #define SO_ORIGINAL_DST 80 #ifdef __KERNEL__ -extern int ip_route_me_harder(struct sk_buff **pskb); +extern int ip_route_me_harder(struct sk_buff **pskb, unsigned addr_type); extern int ip_xfrm_me_harder(struct sk_buff **pskb); extern unsigned int nf_ip_checksum(struct sk_buff *skb, unsigned int hook, unsigned int dataoff, u_int8_t protocol); -- cgit v1.2.3 From b18dfa90c008850e0f3bfd63638dd8fbe8e08701 Mon Sep 17 00:00:00 2001 From: Bart De Schuymer Date: Mon, 2 Oct 2006 16:12:52 -0700 Subject: [NETFILTER]: ebt_mark: add or/and/xor action support to mark target The following patch adds or/and/xor functionality for the mark target, while staying backwards compatible. Signed-off-by: Bart De Schuymer Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter_bridge/ebt_mark_t.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter_bridge/ebt_mark_t.h b/include/linux/netfilter_bridge/ebt_mark_t.h index 110fec6a40a2..6270f6f33693 100644 --- a/include/linux/netfilter_bridge/ebt_mark_t.h +++ b/include/linux/netfilter_bridge/ebt_mark_t.h @@ -1,6 +1,18 @@ #ifndef __LINUX_BRIDGE_EBT_MARK_T_H #define __LINUX_BRIDGE_EBT_MARK_T_H +/* The target member is reused for adding new actions, the + * value of the real target is -1 to -NUM_STANDARD_TARGETS. + * For backward compatibility, the 4 lsb (2 would be enough, + * but let's play it safe) are kept to designate this target. + * The remaining bits designate the action. By making the set + * action 0xfffffff0, the result will look ok for older + * versions. [September 2006] */ +#define MARK_SET_VALUE (0xfffffff0) +#define MARK_OR_VALUE (0xffffffe0) +#define MARK_AND_VALUE (0xffffffd0) +#define MARK_XOR_VALUE (0xffffffc0) + struct ebt_mark_t_info { unsigned long mark; -- cgit v1.2.3 From 0a69452cb45add0841c2bc1e75c25f6bd4f1d8d9 Mon Sep 17 00:00:00 2001 From: Diego Beltrami Date: Tue, 3 Oct 2006 23:47:05 -0700 Subject: [XFRM]: BEET mode This patch introduces the BEET mode (Bound End-to-End Tunnel) with as specified by the ietf draft at the following link: http://www.ietf.org/internet-drafts/draft-nikander-esp-beet-mode-06.txt The patch provides only single family support (i.e. inner family = outer family). Signed-off-by: Diego Beltrami Signed-off-by: Miika Komu Signed-off-by: Herbert Xu Signed-off-by: Abhinav Pathak Signed-off-by: Jeff Ahrenholz Signed-off-by: David S. Miller --- include/linux/in.h | 1 + include/linux/ip.h | 9 +++++++++ include/linux/ipsec.h | 3 ++- include/linux/xfrm.h | 3 ++- 4 files changed, 14 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/in.h b/include/linux/in.h index d79fc75fa7c2..2619859f6e1b 100644 --- a/include/linux/in.h +++ b/include/linux/in.h @@ -40,6 +40,7 @@ enum { IPPROTO_ESP = 50, /* Encapsulation Security Payload protocol */ IPPROTO_AH = 51, /* Authentication Header protocol */ + IPPROTO_BEETPH = 94, /* IP option pseudo header for BEET */ IPPROTO_PIM = 103, /* Protocol Independent Multicast */ IPPROTO_COMP = 108, /* Compression Header protocol */ diff --git a/include/linux/ip.h b/include/linux/ip.h index 6b25d36fc54c..ecee9bb27d0e 100644 --- a/include/linux/ip.h +++ b/include/linux/ip.h @@ -80,6 +80,8 @@ #define IPOPT_TS_TSANDADDR 1 /* timestamps and addresses */ #define IPOPT_TS_PRESPEC 3 /* specified modules only */ +#define IPV4_BEET_PHMAXLEN 8 + struct iphdr { #if defined(__LITTLE_ENDIAN_BITFIELD) __u8 ihl:4, @@ -123,4 +125,11 @@ struct ip_comp_hdr { __be16 cpi; }; +struct ip_beet_phdr { + __u8 nexthdr; + __u8 hdrlen; + __u8 padlen; + __u8 reserved; +}; + #endif /* _LINUX_IP_H */ diff --git a/include/linux/ipsec.h b/include/linux/ipsec.h index d3c527616b5e..d17a6302a0e9 100644 --- a/include/linux/ipsec.h +++ b/include/linux/ipsec.h @@ -12,7 +12,8 @@ enum { IPSEC_MODE_ANY = 0, /* We do not support this for SA */ IPSEC_MODE_TRANSPORT = 1, - IPSEC_MODE_TUNNEL = 2 + IPSEC_MODE_TUNNEL = 2, + IPSEC_MODE_BEET = 3 }; enum { diff --git a/include/linux/xfrm.h b/include/linux/xfrm.h index 430afd058269..8ae7f744917b 100644 --- a/include/linux/xfrm.h +++ b/include/linux/xfrm.h @@ -129,7 +129,8 @@ enum #define XFRM_MODE_TUNNEL 1 #define XFRM_MODE_ROUTEOPTIMIZATION 2 #define XFRM_MODE_IN_TRIGGER 3 -#define XFRM_MODE_MAX 4 +#define XFRM_MODE_BEET 4 +#define XFRM_MODE_MAX 5 /* Netlink configuration messages. */ enum { -- cgit v1.2.3 From 038b0a6d8d32db934bba6a24e74e76e4e327a94f Mon Sep 17 00:00:00 2001 From: Dave Jones Date: Wed, 4 Oct 2006 03:38:54 -0400 Subject: Remove all inclusions of kbuild explicitly includes this at build time. Signed-off-by: Dave Jones --- include/linux/config.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/config.h b/include/linux/config.h index a91f5e55b525..479ffb0a22d8 100644 --- a/include/linux/config.h +++ b/include/linux/config.h @@ -3,6 +3,7 @@ /* This file is no longer in use and kept only for backward compatibility. * autoconf.h is now included via -imacros on the commandline */ +#warning Including config.h is deprecated. #include #endif -- cgit v1.2.3 From c8e649ba908954447e9a095677f6a6c8e50a37b2 Mon Sep 17 00:00:00 2001 From: Steve Grubb Date: Fri, 29 Sep 2006 11:56:49 -0400 Subject: [PATCH] message types updated Hi, This patch adds a new type for 3rd party module use and cleans up a deprecated message type. Signed-off-by: Steve Grubb Signed-off-by: Al Viro --- include/linux/audit.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index c3aa09751814..b2ca666d9997 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -75,7 +75,7 @@ #define AUDIT_DAEMON_CONFIG 1203 /* Daemon config change */ #define AUDIT_SYSCALL 1300 /* Syscall event */ -#define AUDIT_FS_WATCH 1301 /* Filesystem watch event */ +/* #define AUDIT_FS_WATCH 1301 * Deprecated */ #define AUDIT_PATH 1302 /* Filename path information */ #define AUDIT_IPC 1303 /* IPC record */ #define AUDIT_SOCKETCALL 1304 /* sys_socketcall arguments */ @@ -88,6 +88,7 @@ #define AUDIT_MQ_SENDRECV 1313 /* POSIX MQ send/receive record type */ #define AUDIT_MQ_NOTIFY 1314 /* POSIX MQ notify record type */ #define AUDIT_MQ_GETSETATTR 1315 /* POSIX MQ get/set attribute record type */ +#define AUDIT_KERNEL_OTHER 1316 /* For use by 3rd party modules */ #define AUDIT_AVC 1400 /* SE Linux avc denial or grant */ #define AUDIT_SELINUX_ERR 1401 /* Internal SE Linux Errors */ -- cgit v1.2.3 From f86e45131f9d41b1617fbaac7aa1ef23e8d0ab48 Mon Sep 17 00:00:00 2001 From: Kyle McMartin Date: Sun, 13 Aug 2006 21:09:31 -0400 Subject: [PATCH] Need forward decl of task_struct in linux/debug_locks.h Signed-off-by: Kyle McMartin --- include/linux/debug_locks.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/debug_locks.h b/include/linux/debug_locks.h index 88dafa246d87..952bee79a8f3 100644 --- a/include/linux/debug_locks.h +++ b/include/linux/debug_locks.h @@ -43,6 +43,8 @@ extern int debug_locks_off(void); # define locking_selftest() do { } while (0) #endif +struct task_struct; + #ifdef CONFIG_LOCKDEP extern void debug_show_all_locks(void); extern void debug_show_held_locks(struct task_struct *task); -- cgit v1.2.3 From b119f13f56a7a47915278ab5eb3c666ca5dbb067 Mon Sep 17 00:00:00 2001 From: Cedric Le Goater Date: Wed, 4 Oct 2006 02:15:19 -0700 Subject: [PATCH] ipc: headers_check fix Fix headers_check #ifdef __KERNEL__ stuff. Signed-off-by: Cedric Le Goater All-the-fault-of: David Woodhouse Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/Kbuild | 2 +- include/linux/ipc.h | 3 ++- include/linux/utsname.h | 17 +++++++++++------ 3 files changed, 14 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/Kbuild b/include/linux/Kbuild index f7a52e19b4be..9e8bcb5fa99c 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -156,7 +156,6 @@ header-y += toshiba.h header-y += ultrasound.h header-y += un.h header-y += utime.h -header-y += utsname.h header-y += video_decoder.h header-y += video_encoder.h header-y += videotext.h @@ -333,6 +332,7 @@ unifdef-y += unistd.h unifdef-y += usb_ch9.h unifdef-y += usbdevice_fs.h unifdef-y += user.h +unifdef-y += utsname.h unifdef-y += videodev2.h unifdef-y += videodev.h unifdef-y += wait.h diff --git a/include/linux/ipc.h b/include/linux/ipc.h index d9e2b3f36c35..636094c29b16 100644 --- a/include/linux/ipc.h +++ b/include/linux/ipc.h @@ -2,7 +2,6 @@ #define _LINUX_IPC_H #include -#include #define IPC_PRIVATE ((__kernel_key_t) 0) @@ -52,6 +51,8 @@ struct ipc_perm #ifdef __KERNEL__ +#include + #define IPCMNI 32768 /* <= MAX_INT limit for ipc arrays (including sysctl changes) */ /* used by in-kernel data structures */ diff --git a/include/linux/utsname.h b/include/linux/utsname.h index 02e4b6972064..a4555fe3754c 100644 --- a/include/linux/utsname.h +++ b/include/linux/utsname.h @@ -1,11 +1,6 @@ #ifndef _LINUX_UTSNAME_H #define _LINUX_UTSNAME_H -#include -#include -#include -#include - #define __OLD_UTS_LEN 8 struct oldold_utsname { @@ -35,6 +30,13 @@ struct new_utsname { char domainname[65]; }; +#ifdef __KERNEL__ + +#include +#include +#include +#include + struct uts_namespace { struct kref kref; struct new_utsname name; @@ -86,4 +88,7 @@ static inline struct new_utsname *init_utsname(void) } extern struct rw_semaphore uts_sem; -#endif + +#endif /* __KERNEL__ */ + +#endif /* _LINUX_UTSNAME_H */ -- cgit v1.2.3 From 1d2c8eea698514cfaa53fc991b960791d09508e1 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 4 Oct 2006 02:15:25 -0700 Subject: [PATCH] slab: clean up leak tracking ifdefs a little bit - rename ____kmalloc to kmalloc_track_caller so that people have a chance to guess what it does just from it's name. Add a comment describing it for those who don't. Also move it after kmalloc in slab.h so people get less confused when they are just looking for kmalloc - move things around in slab.c a little to reduce the ifdef mess. [penberg@cs.helsinki.fi: Fix up reversed #ifdef] Signed-off-by: Christoph Hellwig Signed-off-by: Pekka Enberg Cc: Christoph Lameter Cc: Al Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab.h | 26 ++++++++++++++++++-------- 1 file changed, 18 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 70be57d8ae0d..c4947b8a2c03 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -77,13 +77,6 @@ struct cache_sizes { extern struct cache_sizes malloc_sizes[]; extern void *__kmalloc(size_t, gfp_t); -#ifndef CONFIG_DEBUG_SLAB -#define ____kmalloc(size, flags) __kmalloc(size, flags) -#else -extern void *__kmalloc_track_caller(size_t, gfp_t, void*); -#define ____kmalloc(size, flags) \ - __kmalloc_track_caller(size, flags, __builtin_return_address(0)) -#endif /** * kmalloc - allocate memory @@ -153,6 +146,23 @@ found: return __kmalloc(size, flags); } +/* + * kmalloc_track_caller is a special version of kmalloc that records the + * calling function of the routine calling it for slab leak tracking instead + * of just the calling function (confusing, eh?). + * It's useful when the call to kmalloc comes from a widely-used standard + * allocator where we care about the real place the memory allocation + * request comes from. + */ +#ifndef CONFIG_DEBUG_SLAB +#define kmalloc_track_caller(size, flags) \ + __kmalloc(size, flags) +#else +extern void *__kmalloc_track_caller(size_t, gfp_t, void*); +#define kmalloc_track_caller(size, flags) \ + __kmalloc_track_caller(size, flags, __builtin_return_address(0)) +#endif + extern void *__kzalloc(size_t, gfp_t); /** @@ -271,7 +281,7 @@ static inline void *kcalloc(size_t n, size_t size, gfp_t flags) #define kmem_cache_alloc_node(c, f, n) kmem_cache_alloc(c, f) #define kmalloc_node(s, f, n) kmalloc(s, f) #define kzalloc(s, f) __kzalloc(s, f) -#define ____kmalloc kmalloc +#define kmalloc_track_caller kmalloc #endif /* CONFIG_SLOB */ -- cgit v1.2.3 From 856fe98f168e5b80b053979769af2514aab96d6b Mon Sep 17 00:00:00 2001 From: Jim Cromie Date: Wed, 4 Oct 2006 02:15:35 -0700 Subject: [PATCH] scx200_hrt: fix precedence bug manifesting as 27x clock in 1 MHz mode Fix paren-placement / precedence bug breaking initialization for 1 MHz clock mode. Also fix comment spelling error, and fence-post (off-by-one) error on symbol used in request_region. Addresses http://bugzilla.kernel.org/show_bug.cgi?id=7242 Thanks alexander.krause@erazor-zone.de, dzpost@dedekind.net, for the reports and patch test, and phelps@mantara.com for the independent patch and verification. Signed-off-by: Jim Cromie Cc: Cc: Cc: Acked-by: John Stultz Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/scx200.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/scx200.h b/include/linux/scx200.h index 693c0557e70b..de466e11e271 100644 --- a/include/linux/scx200.h +++ b/include/linux/scx200.h @@ -32,7 +32,7 @@ extern unsigned scx200_cb_base; /* High Resolution Timer */ #define SCx200_TIMER_OFFSET 0x08 -#define SCx200_TIMER_SIZE 0x05 +#define SCx200_TIMER_SIZE 0x06 /* Clock Generators */ #define SCx200_CLOCKGEN_OFFSET 0x10 -- cgit v1.2.3 From 4020f2d7f0b0e68b92bec9a3e1f4a54a7a9dc672 Mon Sep 17 00:00:00 2001 From: Alex Dubov Date: Wed, 4 Oct 2006 02:15:37 -0700 Subject: [PATCH] mmc: driver for TI FlashMedia card reader - source Driver for TI Flash Media card reader. At present, only MMC/SD cards are supported. [akpm@osdl.org: cleanups, build fixes] Signed-off-by: Alex Dubov Cc: Daniel Qarras Acked-by: Pierre Ossman Cc: Russell King Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/tifm.h | 158 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 158 insertions(+) create mode 100644 include/linux/tifm.h (limited to 'include/linux') diff --git a/include/linux/tifm.h b/include/linux/tifm.h new file mode 100644 index 000000000000..203dd5e11ecb --- /dev/null +++ b/include/linux/tifm.h @@ -0,0 +1,158 @@ +/* + * tifm.h - TI FlashMedia driver + * + * Copyright (C) 2006 Alex Dubov + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ + +#ifndef _TIFM_H +#define _TIFM_H + +#include +#include +#include +#include +#include + +/* Host registers (relative to pci base address): */ +enum { + FM_SET_INTERRUPT_ENABLE = 0x008, + FM_CLEAR_INTERRUPT_ENABLE = 0x00c, + FM_INTERRUPT_STATUS = 0x014 }; + +/* Socket registers (relative to socket base address): */ +enum { + SOCK_CONTROL = 0x004, + SOCK_PRESENT_STATE = 0x008, + SOCK_DMA_ADDRESS = 0x00c, + SOCK_DMA_CONTROL = 0x010, + SOCK_DMA_FIFO_INT_ENABLE_SET = 0x014, + SOCK_DMA_FIFO_INT_ENABLE_CLEAR = 0x018, + SOCK_DMA_FIFO_STATUS = 0x020, + SOCK_FIFO_CONTROL = 0x024, + SOCK_FIFO_PAGE_SIZE = 0x028, + SOCK_MMCSD_COMMAND = 0x104, + SOCK_MMCSD_ARG_LOW = 0x108, + SOCK_MMCSD_ARG_HIGH = 0x10c, + SOCK_MMCSD_CONFIG = 0x110, + SOCK_MMCSD_STATUS = 0x114, + SOCK_MMCSD_INT_ENABLE = 0x118, + SOCK_MMCSD_COMMAND_TO = 0x11c, + SOCK_MMCSD_DATA_TO = 0x120, + SOCK_MMCSD_DATA = 0x124, + SOCK_MMCSD_BLOCK_LEN = 0x128, + SOCK_MMCSD_NUM_BLOCKS = 0x12c, + SOCK_MMCSD_BUFFER_CONFIG = 0x130, + SOCK_MMCSD_SPI_CONFIG = 0x134, + SOCK_MMCSD_SDIO_MODE_CONFIG = 0x138, + SOCK_MMCSD_RESPONSE = 0x144, + SOCK_MMCSD_SDIO_SR = 0x164, + SOCK_MMCSD_SYSTEM_CONTROL = 0x168, + SOCK_MMCSD_SYSTEM_STATUS = 0x16c, + SOCK_MS_COMMAND = 0x184, + SOCK_MS_DATA = 0x188, + SOCK_MS_STATUS = 0x18c, + SOCK_MS_SYSTEM = 0x190, + SOCK_FIFO_ACCESS = 0x200 }; + + +#define TIFM_IRQ_ENABLE 0x80000000 +#define TIFM_IRQ_SOCKMASK 0x00000001 +#define TIFM_IRQ_CARDMASK 0x00000100 +#define TIFM_IRQ_FIFOMASK 0x00010000 +#define TIFM_IRQ_SETALL 0xffffffff +#define TIFM_IRQ_SETALLSOCK 0x0000000f + +#define TIFM_CTRL_LED 0x00000040 +#define TIFM_CTRL_FAST_CLK 0x00000100 + +#define TIFM_SOCK_STATE_OCCUPIED 0x00000008 +#define TIFM_SOCK_STATE_POWERED 0x00000080 + +#define TIFM_FIFO_ENABLE 0x00000001 /* Meaning of this constant is unverified */ +#define TIFM_FIFO_INT_SETALL 0x0000ffff +#define TIFM_FIFO_INTMASK 0x00000005 /* Meaning of this constant is unverified */ + +#define TIFM_DMA_RESET 0x00000002 /* Meaning of this constant is unverified */ +#define TIFM_DMA_TX 0x00008000 /* Meaning of this constant is unverified */ +#define TIFM_DMA_EN 0x00000001 /* Meaning of this constant is unverified */ + +typedef enum {FM_NULL = 0, FM_XD = 0x01, FM_MS = 0x02, FM_SD = 0x03} tifm_media_id; + +struct tifm_driver; +struct tifm_dev { + char __iomem *addr; + spinlock_t lock; + tifm_media_id media_id; + char wq_name[KOBJ_NAME_LEN]; + struct workqueue_struct *wq; + + unsigned int (*signal_irq)(struct tifm_dev *sock, + unsigned int sock_irq_status); + + struct tifm_driver *drv; + struct device dev; +}; + +struct tifm_driver { + tifm_media_id *id_table; + int (*probe)(struct tifm_dev *dev); + void (*remove)(struct tifm_dev *dev); + + struct device_driver driver; +}; + +struct tifm_adapter { + char __iomem *addr; + unsigned int irq_status; + unsigned int insert_mask; + unsigned int remove_mask; + spinlock_t lock; + unsigned int id; + unsigned int max_sockets; + char wq_name[KOBJ_NAME_LEN]; + unsigned int inhibit_new_cards; + struct workqueue_struct *wq; + struct work_struct media_inserter; + struct work_struct media_remover; + struct tifm_dev **sockets; + struct class_device cdev; + struct device *dev; + + void (*eject)(struct tifm_adapter *fm, struct tifm_dev *sock); +}; + +struct tifm_adapter *tifm_alloc_adapter(void); +void tifm_free_device(struct device *dev); +void tifm_free_adapter(struct tifm_adapter *fm); +int tifm_add_adapter(struct tifm_adapter *fm); +void tifm_remove_adapter(struct tifm_adapter *fm); +struct tifm_dev *tifm_alloc_device(struct tifm_adapter *fm, unsigned int id); +int tifm_register_driver(struct tifm_driver *drv); +void tifm_unregister_driver(struct tifm_driver *drv); +void tifm_eject(struct tifm_dev *sock); +int tifm_map_sg(struct tifm_dev *sock, struct scatterlist *sg, int nents, + int direction); +void tifm_unmap_sg(struct tifm_dev *sock, struct scatterlist *sg, int nents, + int direction); + + +static inline void *tifm_get_drvdata(struct tifm_dev *dev) +{ + return dev_get_drvdata(&dev->dev); +} + +static inline void tifm_set_drvdata(struct tifm_dev *dev, void *data) +{ + dev_set_drvdata(&dev->dev, data); +} + +struct tifm_device_id { + tifm_media_id media_id; +}; + +#endif -- cgit v1.2.3 From 4452435948424e5322c2a2fefbdc2cf3732cc45d Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Wed, 4 Oct 2006 02:15:46 -0700 Subject: [PATCH] knfsd: Replace two page lists in struct svc_rqst with one We are planning to increase RPCSVC_MAXPAGES from about 8 to about 256. This means we need to be a bit careful about arrays of size RPCSVC_MAXPAGES. struct svc_rqst contains two such arrays. However the there are never more that RPCSVC_MAXPAGES pages in the two arrays together, so only one array is needed. The two arrays are for the pages holding the request, and the pages holding the reply. Instead of two arrays, we can simply keep an index into where the first reply page is. This patch also removes a number of small inline functions that probably server to obscure what is going on rather than clarify it, and opencode the needed functionality. Also remove the 'rq_restailpage' variable as it is *always* 0. i.e. if the response 'xdr' structure has a non-empty tail it is always in the same pages as the head. check counters are initilised and incr properly check for consistant usage of ++ etc maybe extra some inlines for common approach general review Signed-off-by: Neil Brown Cc: Magnus Maatta Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sunrpc/svc.h | 69 +++++++--------------------------------------- 1 file changed, 10 insertions(+), 59 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 4ebcdf91f3b3..3669e91c43b8 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -170,7 +170,6 @@ static inline void svc_putu32(struct kvec *iov, __be32 val) /* * The context of a single thread, including the request currently being * processed. - * NOTE: First two items must be prev/next. */ struct svc_rqst { struct list_head rq_list; /* idle list */ @@ -189,12 +188,9 @@ struct svc_rqst { struct xdr_buf rq_arg; struct xdr_buf rq_res; - struct page * rq_argpages[RPCSVC_MAXPAGES]; - struct page * rq_respages[RPCSVC_MAXPAGES]; - int rq_restailpage; - short rq_argused; /* pages used for argument */ - short rq_arghi; /* pages available in argument page list */ - short rq_resused; /* pages used for result */ + struct page * rq_pages[RPCSVC_MAXPAGES]; + struct page * *rq_respages; /* points into rq_pages */ + int rq_resused; /* number of pages used for result */ __be32 rq_xid; /* transmission id */ u32 rq_prog; /* program number */ @@ -255,63 +251,18 @@ xdr_ressize_check(struct svc_rqst *rqstp, __be32 *p) return vec->iov_len <= PAGE_SIZE; } -static inline struct page * -svc_take_res_page(struct svc_rqst *rqstp) +static inline void svc_free_res_pages(struct svc_rqst *rqstp) { - if (rqstp->rq_arghi <= rqstp->rq_argused) - return NULL; - rqstp->rq_arghi--; - rqstp->rq_respages[rqstp->rq_resused] = - rqstp->rq_argpages[rqstp->rq_arghi]; - return rqstp->rq_respages[rqstp->rq_resused++]; -} - -static inline void svc_take_page(struct svc_rqst *rqstp) -{ - if (rqstp->rq_arghi <= rqstp->rq_argused) { - WARN_ON(1); - return; - } - rqstp->rq_arghi--; - rqstp->rq_respages[rqstp->rq_resused] = - rqstp->rq_argpages[rqstp->rq_arghi]; - rqstp->rq_resused++; -} - -static inline void svc_pushback_allpages(struct svc_rqst *rqstp) -{ - while (rqstp->rq_resused) { - if (rqstp->rq_respages[--rqstp->rq_resused] == NULL) - continue; - rqstp->rq_argpages[rqstp->rq_arghi++] = - rqstp->rq_respages[rqstp->rq_resused]; - rqstp->rq_respages[rqstp->rq_resused] = NULL; - } -} - -static inline void svc_pushback_unused_pages(struct svc_rqst *rqstp) -{ - while (rqstp->rq_resused && - rqstp->rq_res.pages != &rqstp->rq_respages[rqstp->rq_resused]) { - - if (rqstp->rq_respages[--rqstp->rq_resused] != NULL) { - rqstp->rq_argpages[rqstp->rq_arghi++] = - rqstp->rq_respages[rqstp->rq_resused]; - rqstp->rq_respages[rqstp->rq_resused] = NULL; + while (rqstp->rq_resused) { + struct page **pp = (rqstp->rq_respages + + --rqstp->rq_resused); + if (*pp) { + put_page(*pp); + *pp = NULL; } } } -static inline void svc_free_allpages(struct svc_rqst *rqstp) -{ - while (rqstp->rq_resused) { - if (rqstp->rq_respages[--rqstp->rq_resused] == NULL) - continue; - put_page(rqstp->rq_respages[rqstp->rq_resused]); - rqstp->rq_respages[rqstp->rq_resused] = NULL; - } -} - struct svc_deferred_req { u32 prot; /* protocol (UDP or TCP) */ struct sockaddr_in addr; -- cgit v1.2.3 From 3cc03b164cf01c6f36e64720b58610d292fb26f7 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Wed, 4 Oct 2006 02:15:47 -0700 Subject: [PATCH] knfsd: Avoid excess stack usage in svc_tcp_recvfrom .. by allocating the array of 'kvec' in 'struct svc_rqst'. As we plan to increase RPCSVC_MAXPAGES from 8 upto 256, we can no longer allocate an array of this size on the stack. So we allocate it in 'struct svc_rqst'. However svc_rqst contains (indirectly) an array of the same type and size (actually several, but they are in a union). So rather than waste space, we move those arrays out of the separately allocated union and into svc_rqst to share with the kvec moved out of svc_tcp_recvfrom (various arrays are used at different times, so there is no conflict). Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nfsd/xdr.h | 2 -- include/linux/nfsd/xdr3.h | 2 -- include/linux/nfsd/xdr4.h | 2 -- include/linux/sunrpc/svc.h | 2 ++ 4 files changed, 2 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfsd/xdr.h b/include/linux/nfsd/xdr.h index a38f9d776de9..0e53de87d886 100644 --- a/include/linux/nfsd/xdr.h +++ b/include/linux/nfsd/xdr.h @@ -30,7 +30,6 @@ struct nfsd_readargs { struct svc_fh fh; __u32 offset; __u32 count; - struct kvec vec[RPCSVC_MAXPAGES]; int vlen; }; @@ -38,7 +37,6 @@ struct nfsd_writeargs { svc_fh fh; __u32 offset; int len; - struct kvec vec[RPCSVC_MAXPAGES]; int vlen; }; diff --git a/include/linux/nfsd/xdr3.h b/include/linux/nfsd/xdr3.h index a4322741f8b9..474d882dc2f3 100644 --- a/include/linux/nfsd/xdr3.h +++ b/include/linux/nfsd/xdr3.h @@ -33,7 +33,6 @@ struct nfsd3_readargs { struct svc_fh fh; __u64 offset; __u32 count; - struct kvec vec[RPCSVC_MAXPAGES]; int vlen; }; @@ -43,7 +42,6 @@ struct nfsd3_writeargs { __u32 count; int stable; __u32 len; - struct kvec vec[RPCSVC_MAXPAGES]; int vlen; }; diff --git a/include/linux/nfsd/xdr4.h b/include/linux/nfsd/xdr4.h index 77adba7d2281..66e642762a07 100644 --- a/include/linux/nfsd/xdr4.h +++ b/include/linux/nfsd/xdr4.h @@ -241,7 +241,6 @@ struct nfsd4_read { stateid_t rd_stateid; /* request */ u64 rd_offset; /* request */ u32 rd_length; /* request */ - struct kvec rd_iov[RPCSVC_MAXPAGES]; int rd_vlen; struct file *rd_filp; @@ -326,7 +325,6 @@ struct nfsd4_write { u64 wr_offset; /* request */ u32 wr_stable_how; /* request */ u32 wr_buflen; /* request */ - struct kvec wr_vec[RPCSVC_MAXPAGES]; /* request */ int wr_vlen; u32 wr_bytes_written; /* response */ diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 3669e91c43b8..cb0ed9beb227 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -192,6 +192,8 @@ struct svc_rqst { struct page * *rq_respages; /* points into rq_pages */ int rq_resused; /* number of pages used for result */ + struct kvec rq_vec[RPCSVC_MAXPAGES]; /* generally useful.. */ + __be32 rq_xid; /* transmission id */ u32 rq_prog; /* program number */ u32 rq_vers; /* program version */ -- cgit v1.2.3 From 7adae489fe794e3e203ff168595f635d0b845e59 Mon Sep 17 00:00:00 2001 From: Greg Banks Date: Wed, 4 Oct 2006 02:15:47 -0700 Subject: [PATCH] knfsd: Prepare knfsd for support of rsize/wsize of up to 1MB, over TCP The limit over UDP remains at 32K. Also, make some of the apparently arbitrary sizing constants clearer. The biggest change here involves replacing NFSSVC_MAXBLKSIZE by a function of the rqstp. This allows it to be different for different protocols (udp/tcp) and also allows it to depend on the servers declared sv_bufsiz. Note that we don't actually increase sv_bufsz for nfs yet. That comes next. Signed-off-by: Greg Banks Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nfsd/const.h | 15 ++++++++++++++- include/linux/sunrpc/auth.h | 3 --- include/linux/sunrpc/msg_prot.h | 40 ++++++++++++++++++++++++++++++++++++++++ include/linux/sunrpc/svc.h | 23 ++++++++++++++++++++++- include/linux/sunrpc/xprt.h | 8 +------- 5 files changed, 77 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfsd/const.h b/include/linux/nfsd/const.h index b75bb1b38d09..adbddf007898 100644 --- a/include/linux/nfsd/const.h +++ b/include/linux/nfsd/const.h @@ -13,6 +13,7 @@ #include #include #include +#include /* * Maximum protocol version supported by knfsd @@ -23,6 +24,8 @@ * Maximum blocksize supported by daemon currently at 32K */ #define NFSSVC_MAXBLKSIZE (32*1024) +/* NFSv2 is limited by the protocol specification, see RFC 1094 */ +#define NFSSVC_MAXBLKSIZE_V2 (8*1024) #ifdef __KERNEL__ @@ -30,7 +33,17 @@ # define NFS_SUPER_MAGIC 0x6969 #endif -#define NFSD_BUFSIZE (1024 + NFSSVC_MAXBLKSIZE) +/* + * Largest number of bytes we need to allocate for an NFS + * call or reply. Used to control buffer sizes. We use + * the length of v3 WRITE, READDIR and READDIR replies + * which are an RPC header, up to 26 XDR units of reply + * data, and some page data. + * + * Note that accuracy here doesn't matter too much as the + * size is rounded up to a page size when allocating space. + */ +#define NFSD_BUFSIZE ((RPC_MAX_HEADER_WITH_AUTH+26)*XDR_UNIT + NFSSVC_MAXBLKSIZE) #ifdef CONFIG_NFSD_V4 # define NFSSVC_XDRSIZE NFS4_SVC_XDRSIZE diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h index 862c0d8c8381..534cdc7be58d 100644 --- a/include/linux/sunrpc/auth.h +++ b/include/linux/sunrpc/auth.h @@ -20,9 +20,6 @@ /* size of the nodename buffer */ #define UNX_MAXNODENAME 32 -/* Maximum size (in bytes) of an rpc credential or verifier */ -#define RPC_MAX_AUTH_SIZE (400) - /* Work around the lack of a VFS credential */ struct auth_cred { uid_t uid; diff --git a/include/linux/sunrpc/msg_prot.h b/include/linux/sunrpc/msg_prot.h index 8d10d148834e..1e65f2dd80e5 100644 --- a/include/linux/sunrpc/msg_prot.h +++ b/include/linux/sunrpc/msg_prot.h @@ -11,6 +11,9 @@ #define RPC_VERSION 2 +/* size of an XDR encoding unit in bytes, i.e. 32bit */ +#define XDR_UNIT (4) + /* spec defines authentication flavor as an unsigned 32 bit integer */ typedef u32 rpc_authflavor_t; @@ -34,6 +37,9 @@ enum rpc_auth_flavors { RPC_AUTH_GSS_SPKMP = 390011, }; +/* Maximum size (in bytes) of an rpc credential or verifier */ +#define RPC_MAX_AUTH_SIZE (400) + enum rpc_msg_type { RPC_CALL = 0, RPC_REPLY = 1 @@ -101,5 +107,39 @@ typedef __be32 rpc_fraghdr; #define RPC_FRAGMENT_SIZE_MASK (~RPC_LAST_STREAM_FRAGMENT) #define RPC_MAX_FRAGMENT_SIZE ((1U << 31) - 1) +/* + * RPC call and reply header size as number of 32bit words (verifier + * size computed separately, see below) + */ +#define RPC_CALLHDRSIZE (6) +#define RPC_REPHDRSIZE (4) + + +/* + * Maximum RPC header size, including authentication, + * as number of 32bit words (see RFCs 1831, 1832). + * + * xid 1 xdr unit = 4 bytes + * mtype 1 + * rpc_version 1 + * program 1 + * prog_version 1 + * procedure 1 + * cred { + * flavor 1 + * length 1 + * body 100 xdr units = 400 bytes + * } + * verf { + * flavor 1 + * length 1 + * body 100 xdr units = 400 bytes + * } + * TOTAL 210 xdr units = 840 bytes + */ +#define RPC_MAX_HEADER_WITH_AUTH \ + (RPC_CALLHDRSIZE + 2*(2+RPC_MAX_AUTH_SIZE/4)) + + #endif /* __KERNEL__ */ #endif /* _LINUX_SUNRPC_MSGPROT_H_ */ diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index cb0ed9beb227..74e52c245da4 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include @@ -95,8 +96,28 @@ static inline void svc_get(struct svc_serv *serv) * Maximum payload size supported by a kernel RPC server. * This is use to determine the max number of pages nfsd is * willing to return in a single READ operation. + * + * These happen to all be powers of 2, which is not strictly + * necessary but helps enforce the real limitation, which is + * that they should be multiples of PAGE_CACHE_SIZE. + * + * For UDP transports, a block plus NFS,RPC, and UDP headers + * has to fit into the IP datagram limit of 64K. The largest + * feasible number for all known page sizes is probably 48K, + * but we choose 32K here. This is the same as the historical + * Linux limit; someone who cares more about NFS/UDP performance + * can test a larger number. + * + * For TCP transports we have more freedom. A size of 1MB is + * chosen to match the client limit. Other OSes are known to + * have larger limits, but those numbers are probably beyond + * the point of diminishing returns. */ -#define RPCSVC_MAXPAYLOAD (64*1024u) +#define RPCSVC_MAXPAYLOAD (1*1024*1024u) +#define RPCSVC_MAXPAYLOAD_TCP RPCSVC_MAXPAYLOAD +#define RPCSVC_MAXPAYLOAD_UDP (32*1024u) + +extern u32 svc_max_payload(const struct svc_rqst *rqstp); /* * RPC Requsts and replies are stored in one or more pages. diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 6cf626580752..60394fbc4c70 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -15,6 +15,7 @@ #include #include #include +#include extern unsigned int xprt_udp_slot_table_entries; extern unsigned int xprt_tcp_slot_table_entries; @@ -23,13 +24,6 @@ extern unsigned int xprt_tcp_slot_table_entries; #define RPC_DEF_SLOT_TABLE (16U) #define RPC_MAX_SLOT_TABLE (128U) -/* - * RPC call and reply header size as number of 32bit words (verifier - * size computed separately) - */ -#define RPC_CALLHDRSIZE 6 -#define RPC_REPHDRSIZE 4 - /* * Parameters for choosing a free port */ -- cgit v1.2.3 From 596bbe53eb3abfe7326b2f5e8afd614265c319c8 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Wed, 4 Oct 2006 02:15:48 -0700 Subject: [PATCH] knfsd: Allow max size of NFSd payload to be configured The max possible is the maximum RPC payload. The default depends on amount of total memory. The value can be set within reason as long as no nfsd threads are currently running. The value can also be ready, allowing the default to be determined after nfsd has started. Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nfsd/const.h | 4 ++-- include/linux/nfsd/nfsd.h | 1 + 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfsd/const.h b/include/linux/nfsd/const.h index adbddf007898..f478066f9cd5 100644 --- a/include/linux/nfsd/const.h +++ b/include/linux/nfsd/const.h @@ -21,9 +21,9 @@ #define NFSSVC_MAXVERS 3 /* - * Maximum blocksize supported by daemon currently at 32K + * Maximum blocksizes supported by daemon under various circumstances. */ -#define NFSSVC_MAXBLKSIZE (32*1024) +#define NFSSVC_MAXBLKSIZE RPCSVC_MAXPAYLOAD /* NFSv2 is limited by the protocol specification, see RFC 1094 */ #define NFSSVC_MAXBLKSIZE_V2 (8*1024) diff --git a/include/linux/nfsd/nfsd.h b/include/linux/nfsd/nfsd.h index e1dbc86c270b..259841bb2f6c 100644 --- a/include/linux/nfsd/nfsd.h +++ b/include/linux/nfsd/nfsd.h @@ -145,6 +145,7 @@ int nfsd_vers(int vers, enum vers_op change); void nfsd_reset_versions(void); int nfsd_create_serv(void); +extern int nfsd_max_blksize; /* * NFSv4 State -- cgit v1.2.3 From 7b2b1fee30df7e2165525cd03f7d1d01a3a56794 Mon Sep 17 00:00:00 2001 From: Greg Banks Date: Wed, 4 Oct 2006 02:15:50 -0700 Subject: [PATCH] knfsd: knfsd: cache ipmap per TCP socket Speed up high call-rate workloads by caching the struct ip_map for the peer on the connected struct svc_sock instead of looking it up in the ip_map cache hashtable on every call. This helps workloads using AUTH_SYS authentication over TCP. Testing was on a 4 CPU 4 NIC Altix using 4 IRIX clients, each with 16 synthetic client threads simulating an rsync (i.e. recursive directory listing) workload reading from an i386 RH9 install image (161480 regular files in 10841 directories) on the server. That tree is small enough to fill in the server's RAM so no disk traffic was involved. This setup gives a sustained call rate in excess of 60000 calls/sec before being CPU-bound on the server. Profiling showed strcmp(), called from ip_map_match(), was taking 4.8% of each CPU, and ip_map_lookup() was taking 2.9%. This patch drops both contribution into the profile noise. Note that the above result overstates this value of this patch for most workloads. The synthetic clients are all using separate IP addresses, so there are 64 entries in the ip_map cache hash. Because the kernel measured contained the bug fixed in commit commit 1f1e030bf75774b6a283518e1534d598e14147d4 and was running on 64bit little-endian machine, probably all of those 64 entries were on a single chain, thus increasing the cost of ip_map_lookup(). With a modern kernel you would need more clients to see the same amount of performance improvement. This patch has helped to scale knfsd to handle a deployment with 2000 NFS clients. Signed-off-by: Greg Banks Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sunrpc/cache.h | 11 +++++++++++ include/linux/sunrpc/svcauth.h | 1 + include/linux/sunrpc/svcsock.h | 3 +++ 3 files changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h index b5612c958cce..3699dff7db8f 100644 --- a/include/linux/sunrpc/cache.h +++ b/include/linux/sunrpc/cache.h @@ -163,6 +163,17 @@ static inline void cache_put(struct cache_head *h, struct cache_detail *cd) kref_put(&h->ref, cd->cache_put); } +static inline int cache_valid(struct cache_head *h) +{ + /* If an item has been unhashed pending removal when + * the refcount drops to 0, the expiry_time will be + * set to 0. We don't want to consider such items + * valid in this context even though CACHE_VALID is + * set. + */ + return (h->expiry_time != 0 && test_bit(CACHE_VALID, &h->flags)); +} + extern int cache_check(struct cache_detail *detail, struct cache_head *h, struct cache_req *rqstp); extern void cache_flush(void); diff --git a/include/linux/sunrpc/svcauth.h b/include/linux/sunrpc/svcauth.h index a6601650deeb..de92619b0826 100644 --- a/include/linux/sunrpc/svcauth.h +++ b/include/linux/sunrpc/svcauth.h @@ -126,6 +126,7 @@ extern struct auth_domain *auth_domain_find(char *name); extern struct auth_domain *auth_unix_lookup(struct in_addr addr); extern int auth_unix_forget_old(struct auth_domain *dom); extern void svcauth_unix_purge(void); +extern void svcauth_unix_info_release(void *); static inline unsigned long hash_str(char *name, int bits) { diff --git a/include/linux/sunrpc/svcsock.h b/include/linux/sunrpc/svcsock.h index 4c296152cbfa..98b21ad370fd 100644 --- a/include/linux/sunrpc/svcsock.h +++ b/include/linux/sunrpc/svcsock.h @@ -54,6 +54,9 @@ struct svc_sock { int sk_reclen; /* length of record */ int sk_tcplen; /* current read length */ time_t sk_lastrecv; /* time of last received request */ + + /* cache of various info for TCP sockets */ + void *sk_info_authunix; }; /* -- cgit v1.2.3 From cf712c24d72341effcfd28330b83b49f77cb627b Mon Sep 17 00:00:00 2001 From: Olaf Kirch Date: Wed, 4 Oct 2006 02:15:52 -0700 Subject: [PATCH] knfsd: consolidate common code for statd->lockd notification Common code from nlm4svc_proc_sm_notify and nlmsvc_proc_sm_notify is moved into a new nlm_host_rebooted. This is in preparation of a patch that will change the reboot notification handling entirely. Signed-off-by: Olaf Kirch Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/lockd/lockd.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index 47b7dbd647a6..5f886695ac90 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -161,15 +161,16 @@ int nlmclnt_reclaim(struct nlm_host *, struct file_lock *); /* * Host cache */ -struct nlm_host * nlmclnt_lookup_host(struct sockaddr_in *, int, int); +struct nlm_host * nlmclnt_lookup_host(const struct sockaddr_in *, int, int); struct nlm_host * nlmsvc_lookup_host(struct svc_rqst *); -struct nlm_host * nlm_lookup_host(int server, struct sockaddr_in *, int, int); +struct nlm_host * nlm_lookup_host(int server, const struct sockaddr_in *, int, int); struct rpc_clnt * nlm_bind_host(struct nlm_host *); void nlm_rebind_host(struct nlm_host *); struct nlm_host * nlm_get_host(struct nlm_host *); void nlm_release_host(struct nlm_host *); void nlm_shutdown_hosts(void); extern struct nlm_host *nlm_find_client(void); +extern void nlm_host_rebooted(const struct sockaddr_in *, const struct nlm_reboot *); /* -- cgit v1.2.3 From db4e4c9a9e741ee812e1febf5e386d6a24218a71 Mon Sep 17 00:00:00 2001 From: Olaf Kirch Date: Wed, 4 Oct 2006 02:15:52 -0700 Subject: [PATCH] knfsd: when looking up a lockd host, pass hostname & length This patch adds the peer's hostname (and name length) to all calls to nlm*_lookup_host functions. A subsequent patch will make use of these (is requested by a sysctl). Signed-off-by: Olaf Kirch Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/lockd/lockd.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index 5f886695ac90..0f9b236bca7f 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -161,9 +161,9 @@ int nlmclnt_reclaim(struct nlm_host *, struct file_lock *); /* * Host cache */ -struct nlm_host * nlmclnt_lookup_host(const struct sockaddr_in *, int, int); -struct nlm_host * nlmsvc_lookup_host(struct svc_rqst *); -struct nlm_host * nlm_lookup_host(int server, const struct sockaddr_in *, int, int); +struct nlm_host * nlmclnt_lookup_host(const struct sockaddr_in *, int, int, const char *, int); +struct nlm_host * nlmsvc_lookup_host(struct svc_rqst *, const char *, int); +struct nlm_host * nlm_lookup_host(int server, const struct sockaddr_in *, int, int, const char *, int); struct rpc_clnt * nlm_bind_host(struct nlm_host *); void nlm_rebind_host(struct nlm_host *); struct nlm_host * nlm_get_host(struct nlm_host *); -- cgit v1.2.3 From 8dead0dbd478f35fd943f3719591e5af1ac0950d Mon Sep 17 00:00:00 2001 From: Olaf Kirch Date: Wed, 4 Oct 2006 02:15:53 -0700 Subject: [PATCH] knfsd: lockd: introduce nsm_handle This patch introduces the nsm_handle, which is shared by all nlm_host objects referring to the same client. With this patch applied, all nlm_hosts from the same address will share the same nsm_handle. A future patch will add sharing by name. Note: this patch changes h_name so that it is no longer guaranteed to be an IP address of the host. When the host represents an NFS server, h_name will be the name passed in the mount call. When the host represents a client, h_name will be the name presented in the lock request received from the client. A h_name is only used for printing informational messages, this change should not be significant. Signed-off-by: Olaf Kirch Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/lockd/lockd.h | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index 0f9b236bca7f..ab2ffc8a0b44 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -40,14 +40,13 @@ struct nlm_host { struct nlm_host * h_next; /* linked list (hash table) */ struct sockaddr_in h_addr; /* peer address */ struct rpc_clnt * h_rpcclnt; /* RPC client to talk to peer */ - char h_name[20]; /* remote hostname */ + char * h_name; /* remote hostname */ u32 h_version; /* interface version */ unsigned short h_proto; /* transport proto */ unsigned short h_reclaiming : 1, h_server : 1, /* server side, not client side */ h_inuse : 1, - h_killed : 1, - h_monitored : 1; + h_killed : 1; wait_queue_head_t h_gracewait; /* wait while reclaiming */ struct rw_semaphore h_rwsem; /* Reboot recovery lock */ u32 h_state; /* pseudo-state counter */ @@ -61,6 +60,16 @@ struct nlm_host { spinlock_t h_lock; struct list_head h_granted; /* Locks in GRANTED state */ struct list_head h_reclaim; /* Locks in RECLAIM state */ + struct nsm_handle * h_nsmhandle; /* NSM status handle */ +}; + +struct nsm_handle { + struct list_head sm_link; + atomic_t sm_count; + char * sm_name; + struct sockaddr_in sm_addr; + unsigned int sm_monitored : 1, + sm_sticky : 1; /* don't unmonitor */ }; /* @@ -171,6 +180,8 @@ void nlm_release_host(struct nlm_host *); void nlm_shutdown_hosts(void); extern struct nlm_host *nlm_find_client(void); extern void nlm_host_rebooted(const struct sockaddr_in *, const struct nlm_reboot *); +struct nsm_handle *nsm_find(const struct sockaddr_in *, const char *, int); +void nsm_release(struct nsm_handle *); /* -- cgit v1.2.3 From 5c8dd29ca7fc7483690cef4306549742d534f2a2 Mon Sep 17 00:00:00 2001 From: Olaf Kirch Date: Wed, 4 Oct 2006 02:15:55 -0700 Subject: [PATCH] knfsd: lockd: Make nlm_host_rebooted use the nsm_handle This patch makes the SM_NOTIFY handling understand and use the nsm_handle. To make it a bit clear what is happening: nlmclent_prepare_reclaim and nlmclnt_finish_reclaim get open-coded into 'reclaimer' The result is tidied up. Then some of that functionality is moved out into nlm_host_rebooted (which calls nlmclnt_recovery which starts a thread which runs reclaimer). Also host_rebooted now finds an nsm_handle rather than a host, then then iterates over all hosts and deals with each host that shares that nsm_handle. Signed-off-by: Olaf Kirch Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/lockd/lockd.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index ab2ffc8a0b44..a41eb841428b 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -164,7 +164,7 @@ struct nlm_wait * nlmclnt_prepare_block(struct nlm_host *host, struct file_lock void nlmclnt_finish_block(struct nlm_wait *block); int nlmclnt_block(struct nlm_wait *block, struct nlm_rqst *req, long timeout); u32 nlmclnt_grant(const struct sockaddr_in *addr, const struct nlm_lock *); -void nlmclnt_recovery(struct nlm_host *, u32); +void nlmclnt_recovery(struct nlm_host *); int nlmclnt_reclaim(struct nlm_host *, struct file_lock *); /* @@ -179,7 +179,7 @@ struct nlm_host * nlm_get_host(struct nlm_host *); void nlm_release_host(struct nlm_host *); void nlm_shutdown_hosts(void); extern struct nlm_host *nlm_find_client(void); -extern void nlm_host_rebooted(const struct sockaddr_in *, const struct nlm_reboot *); +extern void nlm_host_rebooted(const struct sockaddr_in *, const char *, int, u32); struct nsm_handle *nsm_find(const struct sockaddr_in *, const char *, int); void nsm_release(struct nsm_handle *); -- cgit v1.2.3 From 9502c52259f7038b6c1e31532e22884716a56b1a Mon Sep 17 00:00:00 2001 From: Olaf Kirch Date: Wed, 4 Oct 2006 02:15:56 -0700 Subject: [PATCH] knfsd: lockd: make the nsm upcalls use the nsm_handle This converts the statd upcalls to use the nsm_handle This means that we only register each host once with statd, rather than registering each host/vers/protocol triple. Signed-off-by: Olaf Kirch Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/lockd/sm_inter.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/lockd/sm_inter.h b/include/linux/lockd/sm_inter.h index 1080bb6ae315..d93b074668ce 100644 --- a/include/linux/lockd/sm_inter.h +++ b/include/linux/lockd/sm_inter.h @@ -28,7 +28,6 @@ struct nsm_args { u32 prog; /* RPC callback info */ u32 vers; u32 proc; - u32 proto; /* protocol (udp/tcp) plus server/client flag */ }; /* -- cgit v1.2.3 From 0cea32761a2f954c6d42ca79d7d1e6b9663b1e4a Mon Sep 17 00:00:00 2001 From: Olaf Kirch Date: Wed, 4 Oct 2006 02:15:56 -0700 Subject: [PATCH] knfsd: lockd: make the hash chains use a hlist_node Get rid of the home-grown singly linked lists for the nlm_host hash table. Signed-off-by: Olaf Kirch Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/lockd/lockd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index a41eb841428b..c8635d84d5d2 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -37,7 +37,7 @@ * Lockd host handle (used both by the client and server personality). */ struct nlm_host { - struct nlm_host * h_next; /* linked list (hash table) */ + struct hlist_node h_hash; /* doubly linked list */ struct sockaddr_in h_addr; /* peer address */ struct rpc_clnt * h_rpcclnt; /* RPC client to talk to peer */ char * h_name; /* remote hostname */ -- cgit v1.2.3 From 68a2d76cea4234bc027df23085d9df4f2171f7fc Mon Sep 17 00:00:00 2001 From: Olaf Kirch Date: Wed, 4 Oct 2006 02:15:57 -0700 Subject: [PATCH] knfsd: lockd: Change list of blocked list to list_node This patch changes the nlm_blocked list to use a list_node instead of homegrown linked list handling. Signed-off-by: Olaf Kirch Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/lockd/lockd.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index c8635d84d5d2..2e740f6a2f77 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -109,7 +109,7 @@ struct nlm_file { struct nfs_fh f_handle; /* NFS file handle */ struct file * f_file; /* VFS file pointer */ struct nlm_share * f_shares; /* DOS shares */ - struct nlm_block * f_blocks; /* blocked locks */ + struct list_head f_blocks; /* blocked locks */ unsigned int f_locks; /* guesstimate # of locks */ unsigned int f_count; /* reference count */ struct semaphore f_sema; /* avoid concurrent access */ @@ -123,14 +123,13 @@ struct nlm_file { #define NLM_NEVER (~(unsigned long) 0) struct nlm_block { struct kref b_count; /* Reference count */ - struct nlm_block * b_next; /* linked list (all blocks) */ - struct nlm_block * b_fnext; /* linked list (per file) */ + struct list_head b_list; /* linked list of all blocks */ + struct list_head b_flist; /* linked list (per file) */ struct nlm_rqst * b_call; /* RPC args & callback info */ struct svc_serv * b_daemon; /* NLM service */ struct nlm_host * b_host; /* host handle for RPC clnt */ unsigned long b_when; /* next re-xmit */ unsigned int b_id; /* block id */ - unsigned char b_queued; /* re-queued */ unsigned char b_granted; /* VFS granted lock */ struct nlm_file * b_file; /* file in question */ }; -- cgit v1.2.3 From 07ba80635117c136714084e019375aa508365375 Mon Sep 17 00:00:00 2001 From: Olaf Kirch Date: Wed, 4 Oct 2006 02:15:58 -0700 Subject: [PATCH] knfsd: change nlm_file to use a hlist This changes struct nlm_file and the nlm_files hash table to use a hlist instead of the home-grown lists. This allows us to remove f_hash which was only used to find the right hash chain to delete an entry from. It also increases the size of the nlm_files hash table from 32 to 128. Signed-off-by: Olaf Kirch Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/lockd/lockd.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index 2e740f6a2f77..777a91e1ac8f 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -105,7 +105,7 @@ struct nlm_rqst { * an NFS client. */ struct nlm_file { - struct nlm_file * f_next; /* linked list */ + struct hlist_node f_list; /* linked list */ struct nfs_fh f_handle; /* NFS file handle */ struct file * f_file; /* VFS file pointer */ struct nlm_share * f_shares; /* DOS shares */ @@ -113,7 +113,6 @@ struct nlm_file { unsigned int f_locks; /* guesstimate # of locks */ unsigned int f_count; /* reference count */ struct semaphore f_sema; /* avoid concurrent access */ - int f_hash; /* hash of f_handle */ }; /* -- cgit v1.2.3 From f2af793db02d2c2f677bdb5bf8e0efdcbf9c0256 Mon Sep 17 00:00:00 2001 From: Olaf Kirch Date: Wed, 4 Oct 2006 02:15:59 -0700 Subject: [PATCH] knfsd: lockd: make nlm_traverse_* more flexible This patch makes nlm_traverse{locks,blocks,shares} and friends use a function pointer rather than a "action" enum. This function pointer is given two nlm_hosts (one given by the caller, the other taken from the lock/block/share currently visited), and is free to do with them as it wants. If it returns a non-zero value, the lockd/block/share is released. Signed-off-by: Olaf Kirch Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/lockd/lockd.h | 15 +++++++-------- include/linux/lockd/share.h | 3 ++- 2 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index 777a91e1ac8f..8c1145669d06 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -133,13 +133,6 @@ struct nlm_block { struct nlm_file * b_file; /* file in question */ }; -/* - * Valid actions for nlmsvc_traverse_files - */ -#define NLM_ACT_CHECK 0 /* check for locks */ -#define NLM_ACT_MARK 1 /* mark & sweep */ -#define NLM_ACT_UNLOCK 2 /* release all locks */ - /* * Global variables */ @@ -182,6 +175,12 @@ struct nsm_handle *nsm_find(const struct sockaddr_in *, const char *, int); void nsm_release(struct nsm_handle *); +/* + * This is used in garbage collection and resource reclaim + * A return value != 0 means destroy the lock/block/share + */ +typedef int (*nlm_host_match_fn_t)(struct nlm_host *cur, struct nlm_host *ref); + /* * Server-side lock handling */ @@ -193,7 +192,7 @@ u32 nlmsvc_testlock(struct nlm_file *, struct nlm_lock *, u32 nlmsvc_cancel_blocked(struct nlm_file *, struct nlm_lock *); unsigned long nlmsvc_retry_blocked(void); void nlmsvc_traverse_blocks(struct nlm_host *, struct nlm_file *, - int action); + nlm_host_match_fn_t match); void nlmsvc_grant_reply(struct svc_rqst *, struct nlm_cookie *, u32); /* diff --git a/include/linux/lockd/share.h b/include/linux/lockd/share.h index c75a424ebe4c..cd7816e74c05 100644 --- a/include/linux/lockd/share.h +++ b/include/linux/lockd/share.h @@ -25,6 +25,7 @@ u32 nlmsvc_share_file(struct nlm_host *, struct nlm_file *, struct nlm_args *); u32 nlmsvc_unshare_file(struct nlm_host *, struct nlm_file *, struct nlm_args *); -void nlmsvc_traverse_shares(struct nlm_host *, struct nlm_file *, int); +void nlmsvc_traverse_shares(struct nlm_host *, struct nlm_file *, + nlm_host_match_fn_t); #endif /* LINUX_LOCKD_SHARE_H */ -- cgit v1.2.3 From 350fce8dbf43f7d441b77366851c9ce3cd28d6dc Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Wed, 4 Oct 2006 02:16:00 -0700 Subject: [PATCH] knfsd: simplify nlmsvc_invalidate_all As a result of previous patches, the loop in nlmsvc_invalidate_all just sets h_expires for all client/hosts to 0 (though does it in a very complicated way). This was possibly meant to trigger early garbage collection but half the time '0' is in the future and so it infact delays garbage collection. Pre-aging the 'hosts' is not really needed at this point anyway so we throw out the loop and nlm_find_client which is no longer needed. Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/lockd/lockd.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index 8c1145669d06..1fcf936d75b9 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -45,8 +45,7 @@ struct nlm_host { unsigned short h_proto; /* transport proto */ unsigned short h_reclaiming : 1, h_server : 1, /* server side, not client side */ - h_inuse : 1, - h_killed : 1; + h_inuse : 1; wait_queue_head_t h_gracewait; /* wait while reclaiming */ struct rw_semaphore h_rwsem; /* Reboot recovery lock */ u32 h_state; /* pseudo-state counter */ @@ -169,7 +168,6 @@ void nlm_rebind_host(struct nlm_host *); struct nlm_host * nlm_get_host(struct nlm_host *); void nlm_release_host(struct nlm_host *); void nlm_shutdown_hosts(void); -extern struct nlm_host *nlm_find_client(void); extern void nlm_host_rebooted(const struct sockaddr_in *, const char *, int, u32); struct nsm_handle *nsm_find(const struct sockaddr_in *, const char *, int); void nsm_release(struct nsm_handle *); -- cgit v1.2.3 From abd1f50094cad9dff6d68ada98b495549f52fc30 Mon Sep 17 00:00:00 2001 From: Olaf Kirch Date: Wed, 4 Oct 2006 02:16:01 -0700 Subject: [PATCH] knfsd: lockd: optionally use hostnames for identifying peers This patch adds the nsm_use_hostnames sysctl and module param. If set, lockd will use the client's name (as given in the NLM arguments) to find the NSM handle. This makes recovery work when the NFS peer is multi-homed, and the reboot notification arrives from a different IP than the original lock calls. Signed-off-by: Olaf Kirch Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/lockd/lockd.h | 1 + include/linux/lockd/sm_inter.h | 2 ++ 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index 1fcf936d75b9..7be7aeaeee58 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -142,6 +142,7 @@ extern struct svc_procedure nlmsvc_procedures4[]; #endif extern int nlmsvc_grace_period; extern unsigned long nlmsvc_timeout; +extern int nsm_use_hostnames; /* * Lockd client functions diff --git a/include/linux/lockd/sm_inter.h b/include/linux/lockd/sm_inter.h index d93b074668ce..daef509bb9b3 100644 --- a/include/linux/lockd/sm_inter.h +++ b/include/linux/lockd/sm_inter.h @@ -28,6 +28,8 @@ struct nsm_args { u32 prog; /* RPC callback info */ u32 vers; u32 proc; + + char * mon_name; }; /* -- cgit v1.2.3 From 031d869d0e0be18cfe35526be5608225b8f0a7be Mon Sep 17 00:00:00 2001 From: Olaf Kirch Date: Wed, 4 Oct 2006 02:16:02 -0700 Subject: [PATCH] knfsd: make nlmclnt_next_cookie SMP safe The way we incremented the NLM cookie in nlmclnt_next_cookie was not thread safe. This patch changes the counter to an atomic_t Signed-off-by: Olaf Kirch Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/lockd/lockd.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index 7be7aeaeee58..a345650e5622 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -157,6 +157,7 @@ int nlmclnt_block(struct nlm_wait *block, struct nlm_rqst *req, long timeout) u32 nlmclnt_grant(const struct sockaddr_in *addr, const struct nlm_lock *); void nlmclnt_recovery(struct nlm_host *); int nlmclnt_reclaim(struct nlm_host *, struct file_lock *); +void nlmclnt_next_cookie(struct nlm_cookie *); /* * Host cache -- cgit v1.2.3 From 39be4502cb75dc26007fe1659735b26c8e63fcc6 Mon Sep 17 00:00:00 2001 From: Olaf Kirch Date: Wed, 4 Oct 2006 02:16:03 -0700 Subject: [PATCH] knfsd: match GRANTED_RES replies using cookies When we send a GRANTED_MSG call, we current copy the NLM cookie provided in the original LOCK call - because in 1996, some broken clients seemed to rely on this bug. However, this means the cookies are not unique, so that when the client's GRANTED_RES message comes back, we cannot simply match it based on the cookie, but have to use the client's IP address in addition. Which breaks when you have a multi-homed NFS client. The X/Open spec explicitly mentions that clients should not expect the same cookie; so one may hope that any clients that were broken in 1996 have either been fixed or rendered obsolete. Signed-off-by: Olaf Kirch Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/lockd/lockd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index a345650e5622..5920ecaeed66 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -193,7 +193,7 @@ u32 nlmsvc_cancel_blocked(struct nlm_file *, struct nlm_lock *); unsigned long nlmsvc_retry_blocked(void); void nlmsvc_traverse_blocks(struct nlm_host *, struct nlm_file *, nlm_host_match_fn_t match); -void nlmsvc_grant_reply(struct svc_rqst *, struct nlm_cookie *, u32); +void nlmsvc_grant_reply(struct nlm_cookie *, u32); /* * File handling for the server personality -- cgit v1.2.3 From 460f5cac1e24e947509b6112c99c5bc9ff687b45 Mon Sep 17 00:00:00 2001 From: Olaf Kirch Date: Wed, 4 Oct 2006 02:16:03 -0700 Subject: [PATCH] knfsd: export nsm_local_state to user space via sysctl Every NLM call includes the client's NSM state. Currently, the Linux client always reports 0 - which seems not to cause any problems, but is not what the protocol says. This patch exposes the kernel's internal variable to user space via a sysctl, which can be set at system boot time by statd. Signed-off-by: Olaf Kirch Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/lockd/sm_inter.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/lockd/sm_inter.h b/include/linux/lockd/sm_inter.h index daef509bb9b3..fc61d40964da 100644 --- a/include/linux/lockd/sm_inter.h +++ b/include/linux/lockd/sm_inter.h @@ -42,6 +42,6 @@ struct nsm_res { int nsm_monitor(struct nlm_host *); int nsm_unmonitor(struct nlm_host *); -extern u32 nsm_local_state; +extern int nsm_local_state; #endif /* LINUX_LOCKD_SM_INTER_H */ -- cgit v1.2.3 From bc5fea4299b8bda5f73c6f79dc35d388caf8bced Mon Sep 17 00:00:00 2001 From: Olaf Kirch Date: Wed, 4 Oct 2006 02:16:05 -0700 Subject: [PATCH] knfsd: register all RPC programs with portmapper by default The NFSACL patches introduced support for multiple RPC services listening on the same transport. However, only the first of these services was registered with portmapper. This was perfectly fine for nfsacl, as you traditionally do not want these to show up in a portmapper listing. The patch below changes the default behavior to always register all services listening on a given transport, but retains the old behavior for nfsacl services. Signed-off-by: Olaf Kirch Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sunrpc/svc.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 74e52c245da4..d6288e89fd9d 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -321,6 +321,9 @@ struct svc_version { struct svc_procedure * vs_proc; /* per-procedure info */ u32 vs_xdrsize; /* xdrsize needed for this version */ + unsigned int vs_hidden : 1; /* Don't register with portmapper. + * Only used for nfsacl so far. */ + /* Override dispatch function (e.g. when caching replies). * A return value of 0 means drop the request. * vs_dispatch == NULL means use default dispatcher. -- cgit v1.2.3 From 89e63ef609fb0064a47281e31e38010159c32d57 Mon Sep 17 00:00:00 2001 From: Neil Brown Date: Wed, 4 Oct 2006 02:16:06 -0700 Subject: [PATCH] Convert lockd to use the newer mutex instead of the older semaphore Both the (recently introduces) nsm_sema and the older f_sema are converted over. Cc: Olaf Kirch Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/lockd/lockd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index 5920ecaeed66..2909619c0295 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -111,7 +111,7 @@ struct nlm_file { struct list_head f_blocks; /* blocked locks */ unsigned int f_locks; /* guesstimate # of locks */ unsigned int f_count; /* reference count */ - struct semaphore f_sema; /* avoid concurrent access */ + struct mutex f_mutex; /* avoid concurrent access */ }; /* -- cgit v1.2.3 From b009a873de05c6e0d7613df3584b6dcb2e4280ee Mon Sep 17 00:00:00 2001 From: "J.Bruce Fields" Date: Wed, 4 Oct 2006 02:16:17 -0700 Subject: [PATCH] knfsd: nfsd: store export path in export Store the export path in the svc_export structure instead of storing only the dentry. This will prevent the need for additional d_path calls to provide NFSv4 fs_locations support. Signed-off-by: J. Bruce Fields Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nfsd/export.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfsd/export.h b/include/linux/nfsd/export.h index d2a8abb5011a..47d96684b611 100644 --- a/include/linux/nfsd/export.h +++ b/include/linux/nfsd/export.h @@ -51,6 +51,7 @@ struct svc_export { int ex_flags; struct vfsmount * ex_mnt; struct dentry * ex_dentry; + char * ex_path; uid_t ex_anon_uid; gid_t ex_anon_gid; int ex_fsid; -- cgit v1.2.3 From 933469190ed5915b0568bc564346bb8db718f460 Mon Sep 17 00:00:00 2001 From: Manoj Naik Date: Wed, 4 Oct 2006 02:16:18 -0700 Subject: [PATCH] knfsd: nfsd4: fslocations data structures Define FS locations structures, some functions to manipulate them, and add code to parse FS locations in downcall and add to the exports structure. [bfields@fieldses.org: bunch of fixes and cleanups] Signed-off-by: Manoj Naik Signed-off-by: Fred Isaman Signed-off-by: J. Bruce Fields Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nfsd/export.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfsd/export.h b/include/linux/nfsd/export.h index 47d96684b611..6e78ea969f49 100644 --- a/include/linux/nfsd/export.h +++ b/include/linux/nfsd/export.h @@ -45,6 +45,25 @@ #ifdef __KERNEL__ +/* + * FS Locations + */ + +#define MAX_FS_LOCATIONS 128 + +struct nfsd4_fs_location { + char *hosts; /* colon separated list of hosts */ + char *path; /* slash separated list of path components */ +}; + +struct nfsd4_fs_locations { + uint32_t locations_count; + struct nfsd4_fs_location *locations; +/* If we're not actually serving this data ourselves (only providing a + * list of replicas that do serve it) then we set "migrated": */ + int migrated; +}; + struct svc_export { struct cache_head h; struct auth_domain * ex_client; @@ -55,6 +74,7 @@ struct svc_export { uid_t ex_anon_uid; gid_t ex_anon_gid; int ex_fsid; + struct nfsd4_fs_locations ex_fslocs; }; /* an "export key" (expkey) maps a filehandlefragement to an -- cgit v1.2.3 From 81c3f4130202a1dcb2b28ab56684eb5e9d43d8c1 Mon Sep 17 00:00:00 2001 From: "J.Bruce Fields" Date: Wed, 4 Oct 2006 02:16:19 -0700 Subject: [PATCH] knfsd: nfsd4: xdr encoding for fs_locations Encode fs_locations attribute. Signed-off-by: Manoj Naik Signed-off-by: Fred Isaman Signed-off-by: J. Bruce Fields Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nfsd/nfsd.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfsd/nfsd.h b/include/linux/nfsd/nfsd.h index 259841bb2f6c..8094142d95ea 100644 --- a/include/linux/nfsd/nfsd.h +++ b/include/linux/nfsd/nfsd.h @@ -292,7 +292,6 @@ static inline int is_fsid(struct svc_fh *fh, struct knfsd_fh *reffh) /* * The following attributes are currently not supported by the NFSv4 server: * ARCHIVE (deprecated anyway) - * FS_LOCATIONS (will be supported eventually) * HIDDEN (unlikely to be supported any time soon) * MIMETYPE (unlikely to be supported any time soon) * QUOTA_* (will be supported in a forthcoming patch) @@ -308,7 +307,7 @@ static inline int is_fsid(struct svc_fh *fh, struct knfsd_fh *reffh) | FATTR4_WORD0_ACLSUPPORT | FATTR4_WORD0_CANSETTIME | FATTR4_WORD0_CASE_INSENSITIVE \ | FATTR4_WORD0_CASE_PRESERVING | FATTR4_WORD0_CHOWN_RESTRICTED \ | FATTR4_WORD0_FILEHANDLE | FATTR4_WORD0_FILEID | FATTR4_WORD0_FILES_AVAIL \ - | FATTR4_WORD0_FILES_FREE | FATTR4_WORD0_FILES_TOTAL | FATTR4_WORD0_HOMOGENEOUS \ + | FATTR4_WORD0_FILES_FREE | FATTR4_WORD0_FILES_TOTAL | FATTR4_WORD0_FS_LOCATIONS | FATTR4_WORD0_HOMOGENEOUS \ | FATTR4_WORD0_MAXFILESIZE | FATTR4_WORD0_MAXLINK | FATTR4_WORD0_MAXNAME \ | FATTR4_WORD0_MAXREAD | FATTR4_WORD0_MAXWRITE | FATTR4_WORD0_ACL) -- cgit v1.2.3 From 42ca09938157105c1f573c831a35e9c3e02eb354 Mon Sep 17 00:00:00 2001 From: "J.Bruce Fields" Date: Wed, 4 Oct 2006 02:16:20 -0700 Subject: [PATCH] knfsd: nfsd4: actually use all the pieces to implement referrals Use all the pieces set up so far to implement referral support, allowing return of NFS4ERR_MOVED and fs_locations attribute. Signed-off-by: Manoj Naik Signed-off-by: Fred Isaman Signed-off-by: J. Bruce Fields Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nfsd/nfsd.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfsd/nfsd.h b/include/linux/nfsd/nfsd.h index 8094142d95ea..d0d4aae7085f 100644 --- a/include/linux/nfsd/nfsd.h +++ b/include/linux/nfsd/nfsd.h @@ -216,6 +216,7 @@ void nfsd_lockd_shutdown(void); #define nfserr_clid_inuse __constant_htonl(NFSERR_CLID_INUSE) #define nfserr_stale_clientid __constant_htonl(NFSERR_STALE_CLIENTID) #define nfserr_resource __constant_htonl(NFSERR_RESOURCE) +#define nfserr_moved __constant_htonl(NFSERR_MOVED) #define nfserr_nofilehandle __constant_htonl(NFSERR_NOFILEHANDLE) #define nfserr_minor_vers_mismatch __constant_htonl(NFSERR_MINOR_VERS_MISMATCH) #define nfserr_share_denied __constant_htonl(NFSERR_SHARE_DENIED) -- cgit v1.2.3 From f7aa2638f288f4c67acdb55947472740bd27d27a Mon Sep 17 00:00:00 2001 From: Cedric Le Goater Date: Wed, 4 Oct 2006 02:16:21 -0700 Subject: [PATCH] Fix linux/nfsd/const.h for make headers_check make headers_check fails on linux/nfsd/const.h. Since linux/sunrpc/msg_prot.h does not seem to export anything interesting for userspace, this patch moves it in the __KERNEL__ protected section. Signed-off-by: Cedric Le Goater Cc: David Woodhouse Cc: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nfsd/const.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfsd/const.h b/include/linux/nfsd/const.h index f478066f9cd5..f0cc77790527 100644 --- a/include/linux/nfsd/const.h +++ b/include/linux/nfsd/const.h @@ -13,7 +13,6 @@ #include #include #include -#include /* * Maximum protocol version supported by knfsd @@ -29,6 +28,8 @@ #ifdef __KERNEL__ +#include + #ifndef NFS_SUPER_MAGIC # define NFS_SUPER_MAGIC 0x6969 #endif -- cgit v1.2.3 From a24ceab4f44f21749aa0b6bd38bee37c775e036f Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 4 Oct 2006 02:16:27 -0700 Subject: [PATCH] genirq: irq: convert the move_irq flag from a 32bit word to a single bit The primary aim of this patchset is to remove maintenances problems caused by the irq infrastructure. The two big issues I address are an artificially small cap on the number of irqs, and that MSI assumes vector == irq. My primary focus is on x86_64 but I have touched other architectures where necessary to keep them from breaking. - To increase the number of irqs I modify the code to look at the (cpu, vector) pair instead of just looking at the vector. With a large number of irqs available systems with a large irq count no longer need to compress their irq numbers to fit. Removing a lot of brittle special cases. For acpi guys the result is that irq == gsi. - Addressing the fact that MSI assumes irq == vector takes a few more patches. But suffice it to say when I am done none of the generic irq code even knows what a vector is. In quick testing on a large Unisys x86_64 machine we stumbled over at least one driver that assumed that NR_IRQS could always fit into an 8 bit number. This driver is clearly buggy today. But this has become a class of bugs that it is now much easier to hit. This patch: This is a minor space optimization. In practice I don't think this has any affect because of our alignment constraints and the other fields but there is not point in chewing up an uncessary word and since we already read the flag field this should improve the cache hit ratio of the irq handler. Signed-off-by: Eric W. Biederman Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Benjamin Herrenschmidt Cc: Rajesh Shah Cc: Andi Kleen Cc: "Protasevich, Natalie" Cc: "Luck, Tony" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/irq.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irq.h b/include/linux/irq.h index 48d3cb3b6a47..3eab46f590a9 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -59,6 +59,7 @@ #define IRQ_NOAUTOEN 0x08000000 /* IRQ will not be enabled on request irq */ #define IRQ_DELAYED_DISABLE 0x10000000 /* IRQ disable (masking) happens delayed. */ #define IRQ_WAKEUP 0x20000000 /* IRQ triggers system wakeup */ +#define IRQ_MOVE_PENDING 0x40000000 /* need to re-target IRQ destination */ struct proc_dir_entry; @@ -132,7 +133,6 @@ struct irq_chip { * @affinity: IRQ affinity on SMP * @cpu: cpu index useful for balancing * @pending_mask: pending rebalanced interrupts - * @move_irq: need to re-target IRQ destination * @dir: /proc/irq/ procfs entry * @affinity_entry: /proc/irq/smp_affinity procfs entry on SMP * @@ -159,7 +159,6 @@ struct irq_desc { #endif #if defined(CONFIG_GENERIC_PENDING_IRQ) || defined(CONFIG_IRQBALANCE) cpumask_t pending_mask; - unsigned int move_irq; /* need to re-target IRQ dest */ #endif #ifdef CONFIG_PROC_FS struct proc_dir_entry *dir; -- cgit v1.2.3 From e7b946e98a456077dd6897f726f3d6197bd7e3b9 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 4 Oct 2006 02:16:29 -0700 Subject: [PATCH] genirq: irq: add moved_masked_irq Currently move_native_irq disables and renables the irq we are migrating to ensure we don't take that irq when we are actually doing the migration operation. Disabling the irq needs to happen but sometimes doing the work is move_native_irq is too late. On x86 with ioapics the irq move sequences needs to be: edge_triggered: mask irq. move irq. unmask irq. ack irq. level_triggered: mask irq. ack irq. move irq. unmask irq. We can easily perform the edge triggered sequence, with the current defintion of move_native_irq. However the level triggered case does not map well. For that I have added move_masked_irq, to allow me to disable the irqs around both the ack and the move. Q: Why have we not seen this problem earlier? A: The only symptom I have been able to reproduce is that if we change the vector before acknowleding an irq the wrong irq is acknowledged. Since we currently are not reprogramming the irq vector during migration no problems show up. We have to mask the irq before we acknowledge the irq or else we could hit a window where an irq is asserted just before we acknowledge it. Edge triggered irqs do not have this problem because acknowledgements do not propogate in the same way. Signed-off-by: Eric W. Biederman Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Benjamin Herrenschmidt Cc: Rajesh Shah Cc: Andi Kleen Cc: "Protasevich, Natalie" Cc: "Luck, Tony" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/irq.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irq.h b/include/linux/irq.h index 3eab46f590a9..a31a7d8acdb2 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -205,6 +205,7 @@ static inline void set_native_irq_info(int irq, cpumask_t mask) void set_pending_irq(unsigned int irq, cpumask_t mask); void move_native_irq(int irq); +void move_masked_irq(int irq); #ifdef CONFIG_PCI_MSI /* @@ -246,6 +247,10 @@ static inline void move_native_irq(int irq) { } +static inline void move_masked_irq(int irq) +{ +} + static inline void set_pending_irq(unsigned int irq, cpumask_t mask) { } @@ -261,6 +266,7 @@ static inline void set_irq_info(int irq, cpumask_t mask) #define move_irq(x) #define move_native_irq(x) +#define move_masked_irq(x) #endif /* CONFIG_SMP */ -- cgit v1.2.3 From 0366f8f7137deb072991e4c50769c6da31f8940c Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 4 Oct 2006 02:16:33 -0700 Subject: [PATCH] genirq: msi: implement helper functions read_msi_msg and write_msi_msg In support of this I also add a struct msi_msg that captures the the two address and one data field ina typical msi message, and I remember the pos and if the address is 64bit in struct msi_desc. This makes the code a little more readable and easier to maintain, and paves the way to further simplfications. Signed-off-by: Eric W. Biederman Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Benjamin Herrenschmidt Cc: Rajesh Shah Cc: Andi Kleen Cc: "Protasevich, Natalie" Cc: "Luck, Tony" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pci.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 4431ce4e1e6f..b9bb6c46e056 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -595,6 +595,12 @@ struct msix_entry { u16 entry; /* driver uses to specify entry, OS writes */ }; +struct msi_msg { + u32 address_lo; /* low 32 bits of msi message address */ + u32 address_hi; /* high 32 bits of msi message address */ + u32 data; /* 16 bits of msi message data */ +}; + #ifndef CONFIG_PCI_MSI static inline void pci_scan_msi_device(struct pci_dev *dev) {} static inline int pci_enable_msi(struct pci_dev *dev) {return -1;} -- cgit v1.2.3 From 38bc0361303535c86f6b67b151a541728d7bdae6 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 4 Oct 2006 02:16:34 -0700 Subject: [PATCH] genirq: msi: refactor the msi_ops The current msi_ops are short sighted in a number of ways, this patch attempts to fix the glaring deficiences. - Report in msi_ops if a 64bit address is needed in the msi message, so we can fail 32bit only msi structures. - Send and receive a full struct msi_msg in both setup and target. This is a little cleaner and allows for architectures that need to modify the data to retarget the msi interrupt to a different cpu. - In target pass in the full cpu mask instead of just the first cpu in case we can make use of the full cpu mask. - Operate in terms of irqs and not vectors, currently there is still a 1-1 relationship but on architectures other than ia64 I expect this will change. Signed-off-by: Eric W. Biederman Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Benjamin Herrenschmidt Cc: Rajesh Shah Cc: Andi Kleen Cc: "Protasevich, Natalie" Cc: "Luck, Tony" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pci.h | 62 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 62 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index b9bb6c46e056..2aabe90f1cd2 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -617,6 +617,68 @@ extern int pci_enable_msix(struct pci_dev* dev, struct msix_entry *entries, int nvec); extern void pci_disable_msix(struct pci_dev *dev); extern void msi_remove_pci_irq_vectors(struct pci_dev *dev); + +/* + * MSI operation vector. Used by the msi core code (drivers/pci/msi.c) + * to abstract platform-specific tasks relating to MSI address generation + * and resource management. + */ +struct msi_ops { + int needs_64bit_address; + /** + * setup - generate an MSI bus address and data for a given vector + * @pdev: PCI device context (in) + * @irq: irq allocated by the msi core (in) + * @msg: PCI bus address and data for msi message (out) + * + * Description: The setup op is used to generate a PCI bus addres and + * data which the msi core will program into the card MSI capability + * registers. The setup routine is responsible for picking an initial + * cpu to target the MSI at. The setup routine is responsible for + * examining pdev to determine the MSI capabilities of the card and + * generating a suitable address/data. The setup routine is + * responsible for allocating and tracking any system resources it + * needs to route the MSI to the cpu it picks, and for associating + * those resources with the passed in vector. + * + * Returns 0 if the MSI address/data was successfully setup. + **/ + + int (*setup) (struct pci_dev *pdev, unsigned int irq, + struct msi_msg *msg); + + /** + * teardown - release resources allocated by setup + * @vector: vector context for resources (in) + * + * Description: The teardown op is used to release any resources + * that were allocated in the setup routine associated with the passed + * in vector. + **/ + + void (*teardown) (unsigned int irq); + + /** + * target - retarget an MSI at a different cpu + * @vector: vector context for resources (in) + * @cpu: new cpu to direct vector at (in) + * @addr_hi: new value of PCI bus upper 32 bits (in/out) + * @addr_lo: new value of PCI bus lower 32 bits (in/out) + * + * Description: The target op is used to redirect an MSI vector + * at a different cpu. addr_hi/addr_lo coming in are the existing + * values that the MSI core has programmed into the card. The + * target code is responsible for freeing any resources (if any) + * associated with the old address, and generating a new PCI bus + * addr_hi/addr_lo that will redirect the vector at the indicated cpu. + **/ + + void (*target) (unsigned int irq, cpumask_t cpumask, + struct msi_msg *msg); +}; + +extern int msi_register(struct msi_ops *ops); + #endif extern void pci_block_user_cfg_access(struct pci_dev *dev); -- cgit v1.2.3 From 3a16d713626735f3016da0521b7bf251cd78e836 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 4 Oct 2006 02:16:37 -0700 Subject: [PATCH] genirq: irq: add a dynamic irq creation API With the msi support comes a new concept in irq handling, irqs that are created dynamically at run time. Currently the msi code allocates irqs backwards. First it allocates a platform dependent routing value for an interrupt the ``vector'' and then it figures out from the vector which irq you are on. This msi backwards allocator suffers from two basic problems. The allocator suffers because it is trying to do something that is architecture specific in a generic way making it brittle, inflexible, and tied to tightly to the architecture implementation. The alloctor also suffers from it's very backwards nature as it has tied things together that should have no dependencies. To solve the basic dynamic irq allocation problem two new architecture specific functions are added: create_irq and destroy_irq. create_irq takes no input and returns an unused irq number, that won't be reused until it is returned to the free poll with destroy_irq. The irq then can be used for any purpose although the only initial consumer is the msi code. destroy_irq takes an irq number allocated with create_irq and returns it to the free pool. Making this functionality per architecture increases the simplicity of the irq allocation code and increases it's flexibility. dynamic_irq_init() and dynamic_irq_cleanup() are added to automate the irq_desc initializtion that should happen for dynamic irqs. Signed-off-by: Eric W. Biederman Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Benjamin Herrenschmidt Cc: Rajesh Shah Cc: Andi Kleen Cc: "Protasevich, Natalie" Cc: "Luck, Tony" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/irq.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/irq.h b/include/linux/irq.h index a31a7d8acdb2..82dbb0e8f40b 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -404,8 +404,15 @@ set_irq_chained_handler(unsigned int irq, __set_irq_handler(irq, handle, 1); } -/* Set/get chip/data for an IRQ: */ +/* Handle dynamic irq creation and destruction */ +extern int create_irq(void); +extern void destroy_irq(unsigned int irq); + +/* Dynamic irq helper functions */ +extern void dynamic_irq_init(unsigned int irq); +extern void dynamic_irq_cleanup(unsigned int irq); +/* Set/get chip/data for an IRQ: */ extern int set_irq_chip(unsigned int irq, struct irq_chip *chip); extern int set_irq_data(unsigned int irq, void *data); extern int set_irq_chip_data(unsigned int irq, void *data); -- cgit v1.2.3 From 323a01c50832749d23664954f91df6fc43e73975 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 4 Oct 2006 02:16:48 -0700 Subject: [PATCH] genirq: irq: remove msi hacks Because of the nasty way that CONFIG_PCI_MSI was implemented we wound up with set_irq_info and set_native_irq_info, with move_irq and move_native_irq. Both functions did the same thing but they were built and called under different circumstances. Now that the msi hacks are gone we can kill move_irq and set_irq_info. Signed-off-by: Eric W. Biederman Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Benjamin Herrenschmidt Cc: Rajesh Shah Cc: Andi Kleen Cc: "Protasevich, Natalie" Cc: "Luck, Tony" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/irq.h | 36 ------------------------------------ 1 file changed, 36 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irq.h b/include/linux/irq.h index 82dbb0e8f40b..69855b23dff9 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -207,36 +207,6 @@ void set_pending_irq(unsigned int irq, cpumask_t mask); void move_native_irq(int irq); void move_masked_irq(int irq); -#ifdef CONFIG_PCI_MSI -/* - * Wonder why these are dummies? - * For e.g the set_ioapic_affinity_vector() calls the set_ioapic_affinity_irq() - * counter part after translating the vector to irq info. We need to perform - * this operation on the real irq, when we dont use vector, i.e when - * pci_use_vector() is false. - */ -static inline void move_irq(int irq) -{ -} - -static inline void set_irq_info(int irq, cpumask_t mask) -{ -} - -#else /* CONFIG_PCI_MSI */ - -static inline void move_irq(int irq) -{ - move_native_irq(irq); -} - -static inline void set_irq_info(int irq, cpumask_t mask) -{ - set_native_irq_info(irq, mask); -} - -#endif /* CONFIG_PCI_MSI */ - #else /* CONFIG_GENERIC_PENDING_IRQ || CONFIG_IRQBALANCE */ static inline void move_irq(int irq) @@ -255,16 +225,10 @@ static inline void set_pending_irq(unsigned int irq, cpumask_t mask) { } -static inline void set_irq_info(int irq, cpumask_t mask) -{ - set_native_irq_info(irq, mask); -} - #endif /* CONFIG_GENERIC_PENDING_IRQ */ #else /* CONFIG_SMP */ -#define move_irq(x) #define move_native_irq(x) #define move_masked_irq(x) -- cgit v1.2.3 From 23d0b8b053391afe15c9667d80de77ca88e18b8b Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 4 Oct 2006 02:16:49 -0700 Subject: [PATCH] genirq: irq: generalize the check for HARDIRQ_BITS This patch adds support for systems that cannot receive every interrupt on a single cpu simultaneously, in the check to see if we have enough HARDIRQ_BITS. MAX_HARDIRQS_PER_CPU becomes the count of the maximum number of hardare generated interrupts per cpu. On architectures that support per cpu interrupt delivery this can be a significant space savings and scalability bonus. This patch adds support for systems that cannot receive every interrupt on Signed-off-by: Eric W. Biederman Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Benjamin Herrenschmidt Cc: Rajesh Shah Cc: Andi Kleen Cc: "Protasevich, Natalie" Cc: "Luck, Tony" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hardirq.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h index 50d8b5744cf6..612472aaa79c 100644 --- a/include/linux/hardirq.h +++ b/include/linux/hardirq.h @@ -28,11 +28,16 @@ #ifndef HARDIRQ_BITS #define HARDIRQ_BITS 12 + +#ifndef MAX_HARDIRQS_PER_CPU +#define MAX_HARDIRQS_PER_CPU NR_IRQS +#endif + /* * The hardirq mask has to be large enough to have space for potentially * all IRQ sources in the system nesting on a single CPU. */ -#if (1 << HARDIRQ_BITS) < NR_IRQS +#if (1 << HARDIRQ_BITS) < MAX_HARDIRQS_PER_CPU # error HARDIRQ_BITS is too low! #endif #endif -- cgit v1.2.3 From e78d01693be38bf93dd6bb49b86e143da450de86 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 4 Oct 2006 02:16:54 -0700 Subject: [PATCH] Add Hypertransport capability defines This adds defines for the hypertransport capability subtypes and starts using them a little. [akpm@osdl.org: fix typo] Signed-off-by: Eric W. Biederman Acked-by: Benjamin Herrenschmidt Cc: Greg KH Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pci_regs.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_regs.h b/include/linux/pci_regs.h index 7d0e26cba420..c312a12ad2d6 100644 --- a/include/linux/pci_regs.h +++ b/include/linux/pci_regs.h @@ -12,6 +12,11 @@ * PCI Local Bus Specification * PCI to PCI Bridge Specification * PCI System Design Guide + * + * For hypertransport information, please consult the following manuals + * from http://www.hypertransport.org + * + * The Hypertransport I/O Link Specification */ #ifndef LINUX_PCI_REGS_H @@ -463,4 +468,20 @@ #define PCI_PWR_CAP 12 /* Capability */ #define PCI_PWR_CAP_BUDGET(x) ((x) & 1) /* Included in system budget */ +/* Hypertransport sub capability types */ +#define HT_CAPTYPE_SLAVE 0x00 /* Slave/Primary link configuration */ +#define HT_CAPTYPE_HOST 0x20 /* Host/Secondary link configuration */ +#define HT_CAPTYPE_IRQ 0x80 /* IRQ Configuration */ +#define HT_CAPTYPE_REMAPPING_40 0xA0 /* 40 bit address remapping */ +#define HT_CAPTYPE_REMAPPING_64 0xA2 /* 64 bit address remapping */ +#define HT_CAPTYPE_UNITID_CLUMP 0x90 /* Unit ID clumping */ +#define HT_CAPTYPE_EXTCONF 0x98 /* Extended Configuration Space Access */ +#define HT_CAPTYPE_MSI_MAPPING 0xA8 /* MSI Mapping Capability */ +#define HT_CAPTYPE_DIRECT_ROUTE 0xB0 /* Direct routing configuration */ +#define HT_CAPTYPE_VCSET 0xB8 /* Virtual Channel configuration */ +#define HT_CAPTYPE_ERROR_RETRY 0xC0 /* Retry on error configuration */ +#define HT_CAPTYPE_GEN3 0xD0 /* Generation 3 hypertransport configuration */ +#define HT_CAPTYPE_PM 0xE0 /* Hypertransport powermanagement configuration */ + + #endif /* LINUX_PCI_REGS_H */ -- cgit v1.2.3 From 8b955b0dddb35e398b07e217a81f8bd49400796f Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 4 Oct 2006 02:16:55 -0700 Subject: [PATCH] Initial generic hypertransport interrupt support This patch implements two functions ht_create_irq and ht_destroy_irq for use by drivers. Several other functions are implemented as helpers for arch specific irq_chip handlers. The driver for the card I tested this on isn't yet ready to be merged. However this code is and hypertransport irqs are in use in a few other places in the kernel. Not that any of this will get merged before 2.6.19 Because the ipath-ht400 is slightly out of spec this code will need to be generalized to work there. I think all of the powerpc uses are for a plain interrupt controller in a chipset so support for native hypertransport devices is a little less interesting. However I think this is a half way decent model on how to separate arch specific and generic helper code, and I think this is a functional model of how to get the architecture dependencies out of the msi code. [akpm@osdl.org: Kconfig fix] Signed-off-by: Eric W. Biederman Cc: Greg KH Cc: Andi Kleen Cc: Benjamin Herrenschmidt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pci.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 2aabe90f1cd2..9b34bc8f34e4 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -681,6 +681,23 @@ extern int msi_register(struct msi_ops *ops); #endif +#ifdef CONFIG_HT_IRQ +/* Helper functions.. */ +void write_ht_irq_low(unsigned int irq, u32 data); +void write_ht_irq_high(unsigned int irq, u32 data); +u32 read_ht_irq_low(unsigned int irq); +u32 read_ht_irq_high(unsigned int irq); +void mask_ht_irq(unsigned int irq); +void unmask_ht_irq(unsigned int irq); + +/* The functions a driver should call */ +int ht_create_irq(struct pci_dev *dev, int idx); +void ht_destroy_irq(unsigned int irq); + +/* The arch hook for getting things started */ +int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev); +#endif /* CONFIG_HT_IRQ */ + extern void pci_block_user_cfg_access(struct pci_dev *dev); extern void pci_unblock_user_cfg_access(struct pci_dev *dev); -- cgit v1.2.3 From 1f80025e624bb14fefadfef7e80fbfb9740d4714 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 4 Oct 2006 02:16:56 -0700 Subject: [PATCH] msi: simplify msi sanity checks by adding with generic irq code Currently msi.c is doing sanity checks that make certain before an irq is destroyed it has no more users. By adding irq_has_action I can perform the test is a generic way, instead of relying on a msi specific data structure. By performing the core check in dynamic_irq_cleanup I ensure every user of dynamic irqs has a test present and we don't free resources that are in use. In msi.c this allows me to kill the attrib.state member of msi_desc and all of the assciated code to maintain it. To keep from freeing data structures when irq cleanup code is called to soon changing dyanamic_irq_cleanup is insufficient because there are msi specific data structures that are also not safe to free. Signed-off-by: Eric W. Biederman Cc: Ingo Molnar Cc: Tony Luck Cc: Andi Kleen Cc: Thomas Gleixner Cc: Greg KH Cc: Benjamin Herrenschmidt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/irq.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irq.h b/include/linux/irq.h index 69855b23dff9..6f463606c318 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -372,6 +372,13 @@ set_irq_chained_handler(unsigned int irq, extern int create_irq(void); extern void destroy_irq(unsigned int irq); +/* Test to see if a driver has successfully requested an irq */ +static inline int irq_has_action(unsigned int irq) +{ + struct irq_desc *desc = irq_desc + irq; + return desc->action != NULL; +} + /* Dynamic irq helper functions */ extern void dynamic_irq_init(unsigned int irq); extern void dynamic_irq_cleanup(unsigned int irq); -- cgit v1.2.3 From 3b7d1921f4cdd6d6ddb7899ae7a8d413991c5cf4 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 4 Oct 2006 02:16:59 -0700 Subject: [PATCH] msi: refactor and move the msi irq_chip into the arch code It turns out msi_ops was simply not enough to abstract the architecture specific details of msi. So I have moved the resposibility of constructing the struct irq_chip to the architectures, and have two architecture specific functions arch_setup_msi_irq, and arch_teardown_msi_irq. For simple architectures those functions can do all of the work. For architectures with platform dependencies they can call into the appropriate platform code. With this msi.c is finally free of assuming you have an apic, and this actually takes less code. The helpers for the architecture specific code are declared in the linux/msi.h to keep them separate from the msi functions used by drivers in linux/pci.h Signed-off-by: Eric W. Biederman Cc: Ingo Molnar Cc: Tony Luck Cc: Andi Kleen Cc: Thomas Gleixner Cc: Greg KH Cc: Benjamin Herrenschmidt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/msi.h | 49 +++++++++++++++++++++++++++++++++++++++ include/linux/pci.h | 67 ----------------------------------------------------- 2 files changed, 49 insertions(+), 67 deletions(-) create mode 100644 include/linux/msi.h (limited to 'include/linux') diff --git a/include/linux/msi.h b/include/linux/msi.h new file mode 100644 index 000000000000..c7ef94343673 --- /dev/null +++ b/include/linux/msi.h @@ -0,0 +1,49 @@ +#ifndef LINUX_MSI_H +#define LINUX_MSI_H + +struct msi_msg { + u32 address_lo; /* low 32 bits of msi message address */ + u32 address_hi; /* high 32 bits of msi message address */ + u32 data; /* 16 bits of msi message data */ +}; + +/* Heper functions */ +extern void mask_msi_irq(unsigned int irq); +extern void unmask_msi_irq(unsigned int irq); +extern void read_msi_msg(unsigned int irq, struct msi_msg *msg); + +extern void write_msi_msg(unsigned int irq, struct msi_msg *msg); + +struct msi_desc { + struct { + __u8 type : 5; /* {0: unused, 5h:MSI, 11h:MSI-X} */ + __u8 maskbit : 1; /* mask-pending bit supported ? */ + __u8 unused : 1; + __u8 is_64 : 1; /* Address size: 0=32bit 1=64bit */ + __u8 pos; /* Location of the msi capability */ + __u16 entry_nr; /* specific enabled entry */ + unsigned default_irq; /* default pre-assigned irq */ + }msi_attrib; + + struct { + __u16 head; + __u16 tail; + }link; + + void __iomem *mask_base; + struct pci_dev *dev; + +#ifdef CONFIG_PM + /* PM save area for MSIX address/data */ + struct msi_msg msg_save; +#endif +}; + +/* + * The arch hook for setup up msi irqs + */ +int arch_setup_msi_irq(unsigned int irq, struct pci_dev *dev); +void arch_teardown_msi_irq(unsigned int irq); + + +#endif /* LINUX_MSI_H */ diff --git a/include/linux/pci.h b/include/linux/pci.h index 9b34bc8f34e4..0da5a4a8940f 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -595,11 +595,6 @@ struct msix_entry { u16 entry; /* driver uses to specify entry, OS writes */ }; -struct msi_msg { - u32 address_lo; /* low 32 bits of msi message address */ - u32 address_hi; /* high 32 bits of msi message address */ - u32 data; /* 16 bits of msi message data */ -}; #ifndef CONFIG_PCI_MSI static inline void pci_scan_msi_device(struct pci_dev *dev) {} @@ -617,68 +612,6 @@ extern int pci_enable_msix(struct pci_dev* dev, struct msix_entry *entries, int nvec); extern void pci_disable_msix(struct pci_dev *dev); extern void msi_remove_pci_irq_vectors(struct pci_dev *dev); - -/* - * MSI operation vector. Used by the msi core code (drivers/pci/msi.c) - * to abstract platform-specific tasks relating to MSI address generation - * and resource management. - */ -struct msi_ops { - int needs_64bit_address; - /** - * setup - generate an MSI bus address and data for a given vector - * @pdev: PCI device context (in) - * @irq: irq allocated by the msi core (in) - * @msg: PCI bus address and data for msi message (out) - * - * Description: The setup op is used to generate a PCI bus addres and - * data which the msi core will program into the card MSI capability - * registers. The setup routine is responsible for picking an initial - * cpu to target the MSI at. The setup routine is responsible for - * examining pdev to determine the MSI capabilities of the card and - * generating a suitable address/data. The setup routine is - * responsible for allocating and tracking any system resources it - * needs to route the MSI to the cpu it picks, and for associating - * those resources with the passed in vector. - * - * Returns 0 if the MSI address/data was successfully setup. - **/ - - int (*setup) (struct pci_dev *pdev, unsigned int irq, - struct msi_msg *msg); - - /** - * teardown - release resources allocated by setup - * @vector: vector context for resources (in) - * - * Description: The teardown op is used to release any resources - * that were allocated in the setup routine associated with the passed - * in vector. - **/ - - void (*teardown) (unsigned int irq); - - /** - * target - retarget an MSI at a different cpu - * @vector: vector context for resources (in) - * @cpu: new cpu to direct vector at (in) - * @addr_hi: new value of PCI bus upper 32 bits (in/out) - * @addr_lo: new value of PCI bus lower 32 bits (in/out) - * - * Description: The target op is used to redirect an MSI vector - * at a different cpu. addr_hi/addr_lo coming in are the existing - * values that the MSI core has programmed into the card. The - * target code is responsible for freeing any resources (if any) - * associated with the old address, and generating a new PCI bus - * addr_hi/addr_lo that will redirect the vector at the indicated cpu. - **/ - - void (*target) (unsigned int irq, cpumask_t cpumask, - struct msi_msg *msg); -}; - -extern int msi_register(struct msi_ops *ops); - #endif #ifdef CONFIG_HT_IRQ -- cgit v1.2.3 From 95d77884c77beed676036d2f74d10b470a483c63 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 4 Oct 2006 02:17:01 -0700 Subject: [PATCH] htirq: tidy up the htirq code This moves the declarations for the architecture helpers into include/linux/htirq.h from the generic include/linux/pci.h. Hopefully this will make this distinction clearer. htirq.h is included where it is needed. The dependency on the msi code is fixed and removed. The Makefile is tidied up. Signed-off-by: Eric W. Biederman Cc: Ingo Molnar Cc: Tony Luck Cc: Andi Kleen Cc: Thomas Gleixner Cc: Greg KH Cc: Benjamin Herrenschmidt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/htirq.h | 15 +++++++++++++++ include/linux/pci.h | 11 ----------- 2 files changed, 15 insertions(+), 11 deletions(-) create mode 100644 include/linux/htirq.h (limited to 'include/linux') diff --git a/include/linux/htirq.h b/include/linux/htirq.h new file mode 100644 index 000000000000..1f15ce279a23 --- /dev/null +++ b/include/linux/htirq.h @@ -0,0 +1,15 @@ +#ifndef LINUX_HTIRQ_H +#define LINUX_HTIRQ_H + +/* Helper functions.. */ +void write_ht_irq_low(unsigned int irq, u32 data); +void write_ht_irq_high(unsigned int irq, u32 data); +u32 read_ht_irq_low(unsigned int irq); +u32 read_ht_irq_high(unsigned int irq); +void mask_ht_irq(unsigned int irq); +void unmask_ht_irq(unsigned int irq); + +/* The arch hook for getting things started */ +int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev); + +#endif /* LINUX_HTIRQ_H */ diff --git a/include/linux/pci.h b/include/linux/pci.h index 0da5a4a8940f..5c604f5fad67 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -615,20 +615,9 @@ extern void msi_remove_pci_irq_vectors(struct pci_dev *dev); #endif #ifdef CONFIG_HT_IRQ -/* Helper functions.. */ -void write_ht_irq_low(unsigned int irq, u32 data); -void write_ht_irq_high(unsigned int irq, u32 data); -u32 read_ht_irq_low(unsigned int irq); -u32 read_ht_irq_high(unsigned int irq); -void mask_ht_irq(unsigned int irq); -void unmask_ht_irq(unsigned int irq); - /* The functions a driver should call */ int ht_create_irq(struct pci_dev *dev, int idx); void ht_destroy_irq(unsigned int irq); - -/* The arch hook for getting things started */ -int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev); #endif /* CONFIG_HT_IRQ */ extern void pci_block_user_cfg_access(struct pci_dev *dev); -- cgit v1.2.3 From 621934ee7ed5b073c7fd638b347e632c53572761 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 4 Oct 2006 02:17:02 -0700 Subject: [PATCH] srcu-3: RCU variant permitting read-side blocking Updated patch adding a variant of RCU that permits sleeping in read-side critical sections. SRCU is as follows: o Each use of SRCU creates its own srcu_struct, and each srcu_struct has its own set of grace periods. This is critical, as it prevents one subsystem with a blocking reader from holding up SRCU grace periods for other subsystems. o The SRCU primitives (srcu_read_lock(), srcu_read_unlock(), and synchronize_srcu()) all take a pointer to a srcu_struct. o The SRCU primitives must be called from process context. o srcu_read_lock() returns an int that must be passed to the matching srcu_read_unlock(). Realtime RCU avoids the need for this by storing the state in the task struct, but SRCU needs to allow a given code path to pass through multiple SRCU domains -- storing state in the task struct would therefore require either arbitrary space in the task struct or arbitrary limits on SRCU nesting. So I kicked the state-storage problem up to the caller. Of course, it is not permitted to call synchronize_srcu() while in an SRCU read-side critical section. o There is no call_srcu(). It would not be hard to implement one, but it seems like too easy a way to OOM the system. (Hey, we have enough trouble with call_rcu(), which does -not- permit readers to sleep!!!) So, if you want it, please tell me why... [josht@us.ibm.com: sparse notation] Signed-off-by: Paul E. McKenney Signed-off-by: Josh Triplett Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/srcu.h | 49 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 49 insertions(+) create mode 100644 include/linux/srcu.h (limited to 'include/linux') diff --git a/include/linux/srcu.h b/include/linux/srcu.h new file mode 100644 index 000000000000..947fdab2ddb0 --- /dev/null +++ b/include/linux/srcu.h @@ -0,0 +1,49 @@ +/* + * Sleepable Read-Copy Update mechanism for mutual exclusion + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Copyright (C) IBM Corporation, 2006 + * + * Author: Paul McKenney + * + * For detailed explanation of Read-Copy Update mechanism see - + * Documentation/RCU/ *.txt + * + */ + +struct srcu_struct_array { + int c[2]; +}; + +struct srcu_struct { + int completed; + struct srcu_struct_array *per_cpu_ref; + struct mutex mutex; +}; + +#ifndef CONFIG_PREEMPT +#define srcu_barrier() barrier() +#else /* #ifndef CONFIG_PREEMPT */ +#define srcu_barrier() +#endif /* #else #ifndef CONFIG_PREEMPT */ + +void init_srcu_struct(struct srcu_struct *sp); +void cleanup_srcu_struct(struct srcu_struct *sp); +int srcu_read_lock(struct srcu_struct *sp) __acquires(sp); +void srcu_read_unlock(struct srcu_struct *sp, int idx) __releases(sp); +void synchronize_srcu(struct srcu_struct *sp); +long srcu_batches_completed(struct srcu_struct *sp); +void cleanup_srcu_struct(struct srcu_struct *sp); -- cgit v1.2.3 From eabc069401bcf45bcc3f19e643017bf761780aa8 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Wed, 4 Oct 2006 02:17:04 -0700 Subject: [PATCH] Add SRCU-based notifier chains This patch (as751) adds a new type of notifier chain, based on the SRCU (Sleepable Read-Copy Update) primitives recently added to the kernel. An SRCU notifier chain is much like a blocking notifier chain, in that it must be called in process context and its callout routines are allowed to sleep. The difference is that the chain's links are protected by the SRCU mechanism rather than by an rw-semaphore, so calling the chain has extremely low overhead: no memory barriers and no cache-line bouncing. On the other hand, unregistering from the chain is expensive and the chain head requires special runtime initialization (plus cleanup if it is to be deallocated). SRCU notifiers are appropriate for notifiers that will be called very frequently and for which unregistration occurs very seldom. The proposed "task notifier" scheme qualifies, as may some of the network notifiers. Signed-off-by: Alan Stern Acked-by: Paul E. McKenney Acked-by: Chandra Seetharaman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/notifier.h | 43 ++++++++++++++++++++++++++++++++++++++----- include/linux/srcu.h | 6 +++++- 2 files changed, 43 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/notifier.h b/include/linux/notifier.h index 7ff386a6ae87..10a43ed0527e 100644 --- a/include/linux/notifier.h +++ b/include/linux/notifier.h @@ -12,9 +12,10 @@ #include #include #include +#include /* - * Notifier chains are of three types: + * Notifier chains are of four types: * * Atomic notifier chains: Chain callbacks run in interrupt/atomic * context. Callouts are not allowed to block. @@ -23,13 +24,27 @@ * Raw notifier chains: There are no restrictions on callbacks, * registration, or unregistration. All locking and protection * must be provided by the caller. + * SRCU notifier chains: A variant of blocking notifier chains, with + * the same restrictions. * * atomic_notifier_chain_register() may be called from an atomic context, - * but blocking_notifier_chain_register() must be called from a process - * context. Ditto for the corresponding _unregister() routines. + * but blocking_notifier_chain_register() and srcu_notifier_chain_register() + * must be called from a process context. Ditto for the corresponding + * _unregister() routines. * - * atomic_notifier_chain_unregister() and blocking_notifier_chain_unregister() - * _must not_ be called from within the call chain. + * atomic_notifier_chain_unregister(), blocking_notifier_chain_unregister(), + * and srcu_notifier_chain_unregister() _must not_ be called from within + * the call chain. + * + * SRCU notifier chains are an alternative form of blocking notifier chains. + * They use SRCU (Sleepable Read-Copy Update) instead of rw-semaphores for + * protection of the chain links. This means there is _very_ low overhead + * in srcu_notifier_call_chain(): no cache bounces and no memory barriers. + * As compensation, srcu_notifier_chain_unregister() is rather expensive. + * SRCU notifier chains should be used when the chain will be called very + * often but notifier_blocks will seldom be removed. Also, SRCU notifier + * chains are slightly more difficult to use because they require special + * runtime initialization. */ struct notifier_block { @@ -52,6 +67,12 @@ struct raw_notifier_head { struct notifier_block *head; }; +struct srcu_notifier_head { + struct mutex mutex; + struct srcu_struct srcu; + struct notifier_block *head; +}; + #define ATOMIC_INIT_NOTIFIER_HEAD(name) do { \ spin_lock_init(&(name)->lock); \ (name)->head = NULL; \ @@ -64,6 +85,11 @@ struct raw_notifier_head { (name)->head = NULL; \ } while (0) +/* srcu_notifier_heads must be initialized and cleaned up dynamically */ +extern void srcu_init_notifier_head(struct srcu_notifier_head *nh); +#define srcu_cleanup_notifier_head(name) \ + cleanup_srcu_struct(&(name)->srcu); + #define ATOMIC_NOTIFIER_INIT(name) { \ .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ .head = NULL } @@ -72,6 +98,7 @@ struct raw_notifier_head { .head = NULL } #define RAW_NOTIFIER_INIT(name) { \ .head = NULL } +/* srcu_notifier_heads cannot be initialized statically */ #define ATOMIC_NOTIFIER_HEAD(name) \ struct atomic_notifier_head name = \ @@ -91,6 +118,8 @@ extern int blocking_notifier_chain_register(struct blocking_notifier_head *, struct notifier_block *); extern int raw_notifier_chain_register(struct raw_notifier_head *, struct notifier_block *); +extern int srcu_notifier_chain_register(struct srcu_notifier_head *, + struct notifier_block *); extern int atomic_notifier_chain_unregister(struct atomic_notifier_head *, struct notifier_block *); @@ -98,6 +127,8 @@ extern int blocking_notifier_chain_unregister(struct blocking_notifier_head *, struct notifier_block *); extern int raw_notifier_chain_unregister(struct raw_notifier_head *, struct notifier_block *); +extern int srcu_notifier_chain_unregister(struct srcu_notifier_head *, + struct notifier_block *); extern int atomic_notifier_call_chain(struct atomic_notifier_head *, unsigned long val, void *v); @@ -105,6 +136,8 @@ extern int blocking_notifier_call_chain(struct blocking_notifier_head *, unsigned long val, void *v); extern int raw_notifier_call_chain(struct raw_notifier_head *, unsigned long val, void *v); +extern int srcu_notifier_call_chain(struct srcu_notifier_head *, + unsigned long val, void *v); #define NOTIFY_DONE 0x0000 /* Don't care */ #define NOTIFY_OK 0x0001 /* Suits me */ diff --git a/include/linux/srcu.h b/include/linux/srcu.h index 947fdab2ddb0..8a45367b5f3a 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -24,6 +24,9 @@ * */ +#ifndef _LINUX_SRCU_H +#define _LINUX_SRCU_H + struct srcu_struct_array { int c[2]; }; @@ -46,4 +49,5 @@ int srcu_read_lock(struct srcu_struct *sp) __acquires(sp); void srcu_read_unlock(struct srcu_struct *sp, int idx) __releases(sp); void synchronize_srcu(struct srcu_struct *sp); long srcu_batches_completed(struct srcu_struct *sp); -void cleanup_srcu_struct(struct srcu_struct *sp); + +#endif -- cgit v1.2.3 From e6a92013ba458804161c0c5b6d134d82204dc233 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Wed, 4 Oct 2006 02:17:05 -0700 Subject: [PATCH] SRCU: report out-of-memory errors Currently the init_srcu_struct() routine has no way to report out-of-memory errors. This patch (as761) makes it return -ENOMEM when the per-cpu data allocation fails. The patch also makes srcu_init_notifier_head() report a BUG if a notifier head can't be initialized. Perhaps it should return -ENOMEM instead, but in the most likely cases where this might occur I don't think any recovery is possible. Notifier chains generally are not created dynamically. [akpm@osdl.org: avoid statement-with-side-effect in macro] Signed-off-by: Alan Stern Acked-by: Paul E. McKenney Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/srcu.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/srcu.h b/include/linux/srcu.h index 8a45367b5f3a..aca0eee53930 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -43,7 +43,7 @@ struct srcu_struct { #define srcu_barrier() #endif /* #else #ifndef CONFIG_PREEMPT */ -void init_srcu_struct(struct srcu_struct *sp); +int init_srcu_struct(struct srcu_struct *sp); void cleanup_srcu_struct(struct srcu_struct *sp); int srcu_read_lock(struct srcu_struct *sp) __acquires(sp); void srcu_read_unlock(struct srcu_struct *sp, int idx) __releases(sp); -- cgit v1.2.3 From 20e9751bd9dd6b832fd84ada27840360f7e877f1 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 4 Oct 2006 02:17:17 -0700 Subject: [PATCH] rcu: simplify/improve batch tuning Kill a hard-to-calculate 'rsinterval' boot parameter and per-cpu rcu_data.last_rs_qlen. Instead, it adds adds a flag rcu_ctrlblk.signaled, which records the fact that one of CPUs has sent a resched IPI since the last rcu_start_batch(). Roughly speaking, we need two rcu_start_batch()s in order to move callbacks from ->nxtlist to ->donelist. This means that when ->qlen exceeds qhimark and continues to grow, we should send a resched IPI, and then do it again after we gone through a quiescent state. On the other hand, if it was already sent, we don't need to do it again when another CPU detects overflow of the queue. Signed-off-by: Oleg Nesterov Acked-by: Paul E. McKenney Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rcupdate.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index b4ca73d65891..f6dd71bf8a4b 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -66,6 +66,8 @@ struct rcu_ctrlblk { long completed; /* Number of the last completed batch */ int next_pending; /* Is the next batch already waiting? */ + int signaled; + spinlock_t lock ____cacheline_internodealigned_in_smp; cpumask_t cpumask; /* CPUs that need to switch in order */ /* for current batch to proceed. */ @@ -106,9 +108,6 @@ struct rcu_data { 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 595182bcdf64fbfd7ae22c67ea6081b7d387d246 Mon Sep 17 00:00:00 2001 From: Josh Triplett Date: Wed, 4 Oct 2006 02:17:21 -0700 Subject: [PATCH] RCU: CREDITS and MAINTAINERS Add MAINTAINERS entry for Read-Copy Update (RCU), listing Dipankar Sarma as maintainer, and giving the URL for Paul McKenney's RCU site. Add MAINTAINERS entry for rcutorture, listing myself as maintainer. Add CREDITS entries for developers of RCU, RCU variants, and rcutorture. Use Paul McKenney's preferred email address in include/linux/rcupdate.h . Signed-off-by: Josh Triplett Cc: Paul McKenney Cc: Dipankar Sarma Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rcupdate.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index f6dd71bf8a4b..c6b7485eac7c 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -19,7 +19,7 @@ * * Author: Dipankar Sarma * - * Based on the original work by Paul McKenney + * Based on the original work by Paul McKenney * and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen. * Papers: * http://www.rdrop.com/users/paulmck/paper/rclockpdcsproof.pdf -- cgit v1.2.3 From d56b9b9c464a10ab1ee51a4c6190a2b57b8ef7a6 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Wed, 4 Oct 2006 02:17:22 -0700 Subject: [PATCH] The scheduled removal of some OSS drivers This patch contains the scheduled removal of OSS drivers that: - have ALSA drivers for the same hardware without known regressions and - whose Kconfig options have been removed in 2.6.17. [michal.k.k.piotrowski@gmail.com: build fix] Signed-off-by: Adrian Bunk Signed-off-by: Michal Piotrowski Cc: David Woodhouse Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/Kbuild | 1 - include/linux/ac97_codec.h | 5 - include/linux/sound.h | 2 - include/linux/wavefront.h | 675 --------------------------------------------- 4 files changed, 683 deletions(-) delete mode 100644 include/linux/wavefront.h (limited to 'include/linux') diff --git a/include/linux/Kbuild b/include/linux/Kbuild index 9e8bcb5fa99c..7d564b6fc98f 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -160,7 +160,6 @@ header-y += video_decoder.h header-y += video_encoder.h header-y += videotext.h header-y += vt.h -header-y += wavefront.h header-y += wireless.h header-y += xattr.h header-y += x25.h diff --git a/include/linux/ac97_codec.h b/include/linux/ac97_codec.h index 2ed2fd855133..22eb9367235a 100644 --- a/include/linux/ac97_codec.h +++ b/include/linux/ac97_codec.h @@ -331,8 +331,6 @@ extern int ac97_read_proc (char *page_out, char **start, off_t off, extern int ac97_probe_codec(struct ac97_codec *); extern unsigned int ac97_set_adc_rate(struct ac97_codec *codec, unsigned int rate); extern unsigned int ac97_set_dac_rate(struct ac97_codec *codec, unsigned int rate); -extern int ac97_save_state(struct ac97_codec *codec); -extern int ac97_restore_state(struct ac97_codec *codec); extern struct ac97_codec *ac97_alloc_codec(void); extern void ac97_release_codec(struct ac97_codec *codec); @@ -346,9 +344,6 @@ struct ac97_driver { void (*remove) (struct ac97_codec *codec, struct ac97_driver *driver); }; -extern int ac97_register_driver(struct ac97_driver *driver); -extern void ac97_unregister_driver(struct ac97_driver *driver); - /* quirk types */ enum { AC97_TUNE_DEFAULT = -1, /* use default from quirk list (not valid in list) */ diff --git a/include/linux/sound.h b/include/linux/sound.h index f63d8342ffa3..9e2a94feed6b 100644 --- a/include/linux/sound.h +++ b/include/linux/sound.h @@ -35,10 +35,8 @@ extern int register_sound_special_device(const struct file_operations *fops, int extern int register_sound_mixer(const struct file_operations *fops, int dev); extern int register_sound_midi(const struct file_operations *fops, int dev); extern int register_sound_dsp(const struct file_operations *fops, int dev); -extern int register_sound_synth(const struct file_operations *fops, int dev); extern void unregister_sound_special(int unit); extern void unregister_sound_mixer(int unit); extern void unregister_sound_midi(int unit); extern void unregister_sound_dsp(int unit); -extern void unregister_sound_synth(int unit); diff --git a/include/linux/wavefront.h b/include/linux/wavefront.h deleted file mode 100644 index 51ab3c933acd..000000000000 --- a/include/linux/wavefront.h +++ /dev/null @@ -1,675 +0,0 @@ -#ifndef __wavefront_h__ -#define __wavefront_h__ - -/* WaveFront header file. - * - * Copyright (C) by Paul Barton-Davis 1998 - * - * This program is distributed under the GNU GENERAL PUBLIC LICENSE (GPL) - * Version 2 (June 1991). See the "COPYING" file distributed with this software - * for more info. - */ - -#if (!defined(__GNUC__) && !defined(__GNUG__)) - - You will not be able to compile this file correctly without gcc, because - it is necessary to pack the "wavefront_alias" structure to a size - of 22 bytes, corresponding to 16-bit alignment (as would have been - the case on the original platform, MS-DOS). If this is not done, - then WavePatch-format files cannot be read/written correctly. - The method used to do this here ("__attribute__((packed)") is - completely compiler dependent. - - All other wavefront_* types end up aligned to 32 bit values and - still have the same (correct) size. - -#else - - /* However, note that as of G++ 2.7.3.2, g++ was unable to - correctly parse *type* __attribute__ tags. It will do the - right thing if we use the "packed" attribute on each struct - member, which has the same semantics anyway. - */ - -#endif /* __GNUC__ */ - -/***************************** WARNING ******************************** - PLEASE DO NOT MODIFY THIS FILE IN ANY WAY THAT AFFECTS ITS ABILITY TO - BE USED WITH EITHER C *OR* C++. - **********************************************************************/ - -#ifndef NUM_MIDIKEYS -#define NUM_MIDIKEYS 128 -#endif /* NUM_MIDIKEYS */ - -#ifndef NUM_MIDICHANNELS -#define NUM_MIDICHANNELS 16 -#endif /* NUM_MIDICHANNELS */ - -/* These are very useful/important. the original wavefront interface - was developed on a 16 bit system, where sizeof(int) = 2 - bytes. Defining things like this makes the code much more portable, and - easier to understand without having to toggle back and forth - between a 16-bit view of the world and a 32-bit one. - */ - -typedef short INT16; -typedef unsigned short UINT16; -typedef int INT32; -typedef unsigned int UINT32; -typedef char CHAR8; -typedef unsigned char UCHAR8; - -/* Pseudo-commands not part of the WaveFront command set. - These are used for various driver controls and direct - hardware control. - */ - -#define WFC_DEBUG_DRIVER 0 -#define WFC_FX_IOCTL 1 -#define WFC_PATCH_STATUS 2 -#define WFC_PROGRAM_STATUS 3 -#define WFC_SAMPLE_STATUS 4 -#define WFC_DISABLE_INTERRUPTS 5 -#define WFC_ENABLE_INTERRUPTS 6 -#define WFC_INTERRUPT_STATUS 7 -#define WFC_ROMSAMPLES_RDONLY 8 -#define WFC_IDENTIFY_SLOT_TYPE 9 - -/* Wavefront synth commands - */ - -#define WFC_DOWNLOAD_SAMPLE 0x80 -#define WFC_DOWNLOAD_BLOCK 0x81 -#define WFC_DOWNLOAD_MULTISAMPLE 0x82 -#define WFC_DOWNLOAD_SAMPLE_ALIAS 0x83 -#define WFC_DELETE_SAMPLE 0x84 -#define WFC_REPORT_FREE_MEMORY 0x85 -#define WFC_DOWNLOAD_PATCH 0x86 -#define WFC_DOWNLOAD_PROGRAM 0x87 -#define WFC_SET_SYNTHVOL 0x89 -#define WFC_SET_NVOICES 0x8B -#define WFC_DOWNLOAD_DRUM 0x90 -#define WFC_GET_SYNTHVOL 0x92 -#define WFC_GET_NVOICES 0x94 -#define WFC_DISABLE_CHANNEL 0x9A -#define WFC_ENABLE_CHANNEL 0x9B -#define WFC_MISYNTH_OFF 0x9D -#define WFC_MISYNTH_ON 0x9E -#define WFC_FIRMWARE_VERSION 0x9F -#define WFC_GET_NSAMPLES 0xA0 -#define WFC_DISABLE_DRUM_PROGRAM 0xA2 -#define WFC_UPLOAD_PATCH 0xA3 -#define WFC_UPLOAD_PROGRAM 0xA4 -#define WFC_SET_TUNING 0xA6 -#define WFC_GET_TUNING 0xA7 -#define WFC_VMIDI_ON 0xA8 -#define WFC_VMIDI_OFF 0xA9 -#define WFC_MIDI_STATUS 0xAA -#define WFC_GET_CHANNEL_STATUS 0xAB -#define WFC_DOWNLOAD_SAMPLE_HEADER 0xAC -#define WFC_UPLOAD_SAMPLE_HEADER 0xAD -#define WFC_UPLOAD_MULTISAMPLE 0xAE -#define WFC_UPLOAD_SAMPLE_ALIAS 0xAF -#define WFC_IDENTIFY_SAMPLE_TYPE 0xB0 -#define WFC_DOWNLOAD_EDRUM_PROGRAM 0xB1 -#define WFC_UPLOAD_EDRUM_PROGRAM 0xB2 -#define WFC_SET_EDRUM_CHANNEL 0xB3 -#define WFC_INSTOUT_LEVELS 0xB4 -#define WFC_PEAKOUT_LEVELS 0xB5 -#define WFC_REPORT_CHANNEL_PROGRAMS 0xB6 -#define WFC_HARDWARE_VERSION 0xCF -#define WFC_UPLOAD_SAMPLE_PARAMS 0xD7 -#define WFC_DOWNLOAD_OS 0xF1 -#define WFC_NOOP 0xFF - -#define WF_MAX_SAMPLE 512 -#define WF_MAX_PATCH 256 -#define WF_MAX_PROGRAM 128 - -#define WF_SECTION_MAX 44 /* longest OS section length */ - -/* # of bytes we send to the board when sending it various kinds of - substantive data, such as samples, patches and programs. -*/ - -#define WF_PROGRAM_BYTES 32 -#define WF_PATCH_BYTES 132 -#define WF_SAMPLE_BYTES 27 -#define WF_SAMPLE_HDR_BYTES 25 -#define WF_ALIAS_BYTES 25 -#define WF_DRUM_BYTES 9 -#define WF_MSAMPLE_BYTES 259 /* (MIDI_KEYS * 2) + 3 */ - -#define WF_ACK 0x80 -#define WF_DMA_ACK 0x81 - -/* OR-values for MIDI status bits */ - -#define WF_MIDI_VIRTUAL_ENABLED 0x1 -#define WF_MIDI_VIRTUAL_IS_EXTERNAL 0x2 -#define WF_MIDI_IN_TO_SYNTH_DISABLED 0x4 - -/* slot indexes for struct address_info: makes code a little more mnemonic */ - -#define WF_SYNTH_SLOT 0 -#define WF_INTERNAL_MIDI_SLOT 1 -#define WF_EXTERNAL_MIDI_SLOT 2 - -/* Magic MIDI bytes used to switch I/O streams on the ICS2115 MPU401 - emulation. Note these NEVER show up in output from the device and - should NEVER be used in input unless Virtual MIDI mode has been - disabled. If they do show up as input, the results are unpredictable. -*/ - -#define WF_EXTERNAL_SWITCH 0xFD -#define WF_INTERNAL_SWITCH 0xF9 - -/* Debugging flags */ - -#define WF_DEBUG_CMD 0x1 -#define WF_DEBUG_DATA 0x2 -#define WF_DEBUG_LOAD_PATCH 0x4 -#define WF_DEBUG_IO 0x8 - -/* WavePatch file format stuff */ - -#define WF_WAVEPATCH_VERSION 120; /* Current version number (1.2) */ -#define WF_MAX_COMMENT 64 /* Comment length */ -#define WF_NUM_LAYERS 4 -#define WF_NAME_LENGTH 32 -#define WF_SOURCE_LENGTH 260 - -#define BankFileID "Bank" -#define DrumkitFileID "DrumKit" -#define ProgramFileID "Program" - -struct wf_envelope -{ - UCHAR8 attack_time:7; - UCHAR8 Unused1:1; - - UCHAR8 decay1_time:7; - UCHAR8 Unused2:1; - - UCHAR8 decay2_time:7; - UCHAR8 Unused3:1; - - UCHAR8 sustain_time:7; - UCHAR8 Unused4:1; - - UCHAR8 release_time:7; - UCHAR8 Unused5:1; - - UCHAR8 release2_time:7; - UCHAR8 Unused6:1; - - CHAR8 attack_level; - CHAR8 decay1_level; - CHAR8 decay2_level; - CHAR8 sustain_level; - CHAR8 release_level; - - UCHAR8 attack_velocity:7; - UCHAR8 Unused7:1; - - UCHAR8 volume_velocity:7; - UCHAR8 Unused8:1; - - UCHAR8 keyboard_scaling:7; - UCHAR8 Unused9:1; -}; -typedef struct wf_envelope wavefront_envelope; - -struct wf_lfo -{ - UCHAR8 sample_number; - - UCHAR8 frequency:7; - UCHAR8 Unused1:1; - - UCHAR8 am_src:4; - UCHAR8 fm_src:4; - - CHAR8 fm_amount; - CHAR8 am_amount; - CHAR8 start_level; - CHAR8 end_level; - - UCHAR8 ramp_delay:7; - UCHAR8 wave_restart:1; /* for LFO2 only */ - - UCHAR8 ramp_time:7; - UCHAR8 Unused2:1; -}; -typedef struct wf_lfo wavefront_lfo; - -struct wf_patch -{ - INT16 frequency_bias; /* ** THIS IS IN MOTOROLA FORMAT!! ** */ - - UCHAR8 amplitude_bias:7; - UCHAR8 Unused1:1; - - UCHAR8 portamento:7; - UCHAR8 Unused2:1; - - UCHAR8 sample_number; - - UCHAR8 pitch_bend:4; - UCHAR8 sample_msb:1; - UCHAR8 Unused3:3; - - UCHAR8 mono:1; - UCHAR8 retrigger:1; - UCHAR8 nohold:1; - UCHAR8 restart:1; - UCHAR8 filterconfig:2; /* SDK says "not used" */ - UCHAR8 reuse:1; - UCHAR8 reset_lfo:1; - - UCHAR8 fm_src2:4; - UCHAR8 fm_src1:4; - - CHAR8 fm_amount1; - CHAR8 fm_amount2; - - UCHAR8 am_src:4; - UCHAR8 Unused4:4; - - CHAR8 am_amount; - - UCHAR8 fc1_mode:4; - UCHAR8 fc2_mode:4; - - CHAR8 fc1_mod_amount; - CHAR8 fc1_keyboard_scaling; - CHAR8 fc1_bias; - CHAR8 fc2_mod_amount; - CHAR8 fc2_keyboard_scaling; - CHAR8 fc2_bias; - - UCHAR8 randomizer:7; - UCHAR8 Unused5:1; - - struct wf_envelope envelope1; - struct wf_envelope envelope2; - struct wf_lfo lfo1; - struct wf_lfo lfo2; -}; -typedef struct wf_patch wavefront_patch; - -struct wf_layer -{ - UCHAR8 patch_number; - - UCHAR8 mix_level:7; - UCHAR8 mute:1; - - UCHAR8 split_point:7; - UCHAR8 play_below:1; - - UCHAR8 pan_mod_src:2; - UCHAR8 pan_or_mod:1; - UCHAR8 pan:4; - UCHAR8 split_type:1; -}; -typedef struct wf_layer wavefront_layer; - -struct wf_program -{ - struct wf_layer layer[WF_NUM_LAYERS]; -}; -typedef struct wf_program wavefront_program; - -struct wf_sample_offset -{ - INT32 Fraction:4; - INT32 Integer:20; - INT32 Unused:8; -}; -typedef struct wf_sample_offset wavefront_sample_offset; - -/* Sample slot types */ - -#define WF_ST_SAMPLE 0 -#define WF_ST_MULTISAMPLE 1 -#define WF_ST_ALIAS 2 -#define WF_ST_EMPTY 3 - -/* pseudo's */ - -#define WF_ST_DRUM 4 -#define WF_ST_PROGRAM 5 -#define WF_ST_PATCH 6 -#define WF_ST_SAMPLEHDR 7 - -#define WF_ST_MASK 0xf - -/* Flags for slot status. These occupy the upper bits of the same byte - as a sample type. -*/ - -#define WF_SLOT_USED 0x80 /* XXX don't rely on this being accurate */ -#define WF_SLOT_FILLED 0x40 -#define WF_SLOT_ROM 0x20 - -#define WF_SLOT_MASK 0xf0 - -/* channel constants */ - -#define WF_CH_MONO 0 -#define WF_CH_LEFT 1 -#define WF_CH_RIGHT 2 - -/* Sample formats */ - -#define LINEAR_16BIT 0 -#define WHITE_NOISE 1 -#define LINEAR_8BIT 2 -#define MULAW_8BIT 3 - -#define WF_SAMPLE_IS_8BIT(smpl) ((smpl)->SampleResolution&2) - - -/* - - Because most/all of the sample data we pass in via pointers has - never been copied (just mmap-ed into user space straight from the - disk), it would be nice to allow handling of multi-channel sample - data without forcing user-level extraction of the relevant bytes. - - So, we need a way of specifying which channel to use (the WaveFront - only handles mono samples in a given slot), and the only way to do - this without using some struct other than wavefront_sample as the - interface is the awful hack of using the unused bits in a - wavefront_sample: - - Val Meaning - --- ------- - 0 no channel selection (use channel 1, sample is MONO) - 1 use first channel, and skip one - 2 use second channel, and skip one - 3 use third channel, and skip two - 4 use fourth channel, skip three - 5 use fifth channel, skip four - 6 use six channel, skip five - - - This can handle up to 4 channels, and anyone downloading >4 channels - of sample data just to select one of them needs to find some tools - like sox ... - - NOTE: values 0, 1 and 2 correspond to WF_CH_* above. This is - important. - -*/ - -#define WF_SET_CHANNEL(samp,chn) \ - (samp)->Unused1 = chn & 0x1; \ - (samp)->Unused2 = chn & 0x2; \ - (samp)->Unused3 = chn & 0x4 - -#define WF_GET_CHANNEL(samp) \ - (((samp)->Unused3 << 2)|((samp)->Unused2<<1)|(samp)->Unused1) - -typedef struct wf_sample { - struct wf_sample_offset sampleStartOffset; - struct wf_sample_offset loopStartOffset; - struct wf_sample_offset loopEndOffset; - struct wf_sample_offset sampleEndOffset; - INT16 FrequencyBias; - UCHAR8 SampleResolution:2; /* sample_format */ - UCHAR8 Unused1:1; - UCHAR8 Loop:1; - UCHAR8 Bidirectional:1; - UCHAR8 Unused2:1; - UCHAR8 Reverse:1; - UCHAR8 Unused3:1; -} wavefront_sample; - -typedef struct wf_multisample { - INT16 NumberOfSamples; /* log2 of the number of samples */ - INT16 SampleNumber[NUM_MIDIKEYS]; -} wavefront_multisample; - -typedef struct wf_alias { - INT16 OriginalSample; - - struct wf_sample_offset sampleStartOffset; - struct wf_sample_offset loopStartOffset; - struct wf_sample_offset sampleEndOffset; - struct wf_sample_offset loopEndOffset; - - INT16 FrequencyBias; - - UCHAR8 SampleResolution:2; - UCHAR8 Unused1:1; - UCHAR8 Loop:1; - UCHAR8 Bidirectional:1; - UCHAR8 Unused2:1; - UCHAR8 Reverse:1; - UCHAR8 Unused3:1; - - /* This structure is meant to be padded only to 16 bits on their - original. Of course, whoever wrote their documentation didn't - realize that sizeof(struct) can be >= - sum(sizeof(struct-fields)) and so thought that giving a C level - description of the structs used in WavePatch files was - sufficient. I suppose it was, as long as you remember the - standard 16->32 bit issues. - */ - - UCHAR8 sixteen_bit_padding; -} __attribute__((packed)) wavefront_alias; - -typedef struct wf_drum { - UCHAR8 PatchNumber; - UCHAR8 MixLevel:7; - UCHAR8 Unmute:1; - UCHAR8 Group:4; - UCHAR8 Unused1:4; - UCHAR8 PanModSource:2; - UCHAR8 PanModulated:1; - UCHAR8 PanAmount:4; - UCHAR8 Unused2:1; -} wavefront_drum; - -typedef struct wf_drumkit { - struct wf_drum drum[NUM_MIDIKEYS]; -} wavefront_drumkit; - -typedef struct wf_channel_programs { - UCHAR8 Program[NUM_MIDICHANNELS]; -} wavefront_channel_programs; - -/* How to get MIDI channel status from the data returned by - a WFC_GET_CHANNEL_STATUS command (a struct wf_channel_programs) -*/ - -#define WF_CHANNEL_STATUS(ch,wcp) (wcp)[(ch/7)] & (1<<((ch)%7)) - -typedef union wf_any { - wavefront_sample s; - wavefront_multisample ms; - wavefront_alias a; - wavefront_program pr; - wavefront_patch p; - wavefront_drum d; -} wavefront_any; - -/* Hannu Solvainen hoped that his "patch_info" struct in soundcard.h - might work for other wave-table based patch loading situations. - Alas, his fears were correct. The WaveFront doesn't even come with - just "patches", but several different kind of structures that - control the sound generation process. - */ - -typedef struct wf_patch_info { - - /* the first two fields are used by the OSS "patch loading" interface - only, and are unused by the current user-level library. - */ - - INT16 key; /* Use WAVEFRONT_PATCH here */ - UINT16 devno; /* fill in when sending */ - UCHAR8 subkey; /* WF_ST_{SAMPLE,ALIAS,etc.} */ - -#define WAVEFRONT_FIND_FREE_SAMPLE_SLOT 999 - - UINT16 number; /* patch/sample/prog number */ - - UINT32 size; /* size of any data included in - one of the fields in `hdrptr', or - as `dataptr'. - - NOTE: for actual samples, this is - the size of the *SELECTED CHANNEL* - even if more data is actually available. - - So, a stereo sample (2 channels) of - 6000 bytes total has `size' = 3000. - - See the macros and comments for - WF_{GET,SET}_CHANNEL above. - - */ - wavefront_any __user *hdrptr; /* user-space ptr to hdr bytes */ - UINT16 __user *dataptr; /* actual sample data */ - - wavefront_any hdr; /* kernel-space copy of hdr bytes */ -} wavefront_patch_info; - -/* The maximum number of bytes we will ever move to or from user space - in response to a WFC_* command. This obviously doesn't cover - actual sample data. -*/ - -#define WF_MAX_READ sizeof(wavefront_multisample) -#define WF_MAX_WRITE sizeof(wavefront_multisample) - -/* - This allows us to execute any WF command except the download/upload - ones, which are handled differently due to copyin/copyout issues as - well as data-nybbling to/from the card. - */ - -typedef struct wavefront_control { - int cmd; /* WFC_* */ - char status; /* return status to user-space */ - unsigned char rbuf[WF_MAX_READ]; /* bytes read from card */ - unsigned char wbuf[WF_MAX_WRITE]; /* bytes written to card */ -} wavefront_control; - -#define WFCTL_WFCMD 0x1 -#define WFCTL_LOAD_SPP 0x2 - -/* Modulator table */ - -#define WF_MOD_LFO1 0 -#define WF_MOD_LFO2 1 -#define WF_MOD_ENV1 2 -#define WF_MOD_ENV2 3 -#define WF_MOD_KEYBOARD 4 -#define WF_MOD_LOGKEY 5 -#define WF_MOD_VELOCITY 6 -#define WF_MOD_LOGVEL 7 -#define WF_MOD_RANDOM 8 -#define WF_MOD_PRESSURE 9 -#define WF_MOD_MOD_WHEEL 10 -#define WF_MOD_1 WF_MOD_MOD_WHEEL -#define WF_MOD_BREATH 11 -#define WF_MOD_2 WF_MOD_BREATH -#define WF_MOD_FOOT 12 -#define WF_MOD_4 WF_MOD_FOOT -#define WF_MOD_VOLUME 13 -#define WF_MOD_7 WF_MOD_VOLUME -#define WF_MOD_PAN 14 -#define WF_MOD_10 WF_MOD_PAN -#define WF_MOD_EXPR 15 -#define WF_MOD_11 WF_MOD_EXPR - -/* FX-related material */ - -typedef struct wf_fx_info { - int request; /* see list below */ - int data[4]; /* we don't need much */ -} wavefront_fx_info; - -/* support for each of these will be forthcoming once I or someone - else has figured out which of the addresses on page 6 and page 7 of - the YSS225 control each parameter. Incidentally, these come from - the Windows driver interface, but again, Turtle Beach didn't - document the API to use them. -*/ - -#define WFFX_SETOUTGAIN 0 -#define WFFX_SETSTEREOOUTGAIN 1 -#define WFFX_SETREVERBIN1GAIN 2 -#define WFFX_SETREVERBIN2GAIN 3 -#define WFFX_SETREVERBIN3GAIN 4 -#define WFFX_SETCHORUSINPORT 5 -#define WFFX_SETREVERBIN1PORT 6 -#define WFFX_SETREVERBIN2PORT 7 -#define WFFX_SETREVERBIN3PORT 8 -#define WFFX_SETEFFECTPORT 9 -#define WFFX_SETAUXPORT 10 -#define WFFX_SETREVERBTYPE 11 -#define WFFX_SETREVERBDELAY 12 -#define WFFX_SETCHORUSLFO 13 -#define WFFX_SETCHORUSPMD 14 -#define WFFX_SETCHORUSAMD 15 -#define WFFX_SETEFFECT 16 -#define WFFX_SETBASEALL 17 -#define WFFX_SETREVERBALL 18 -#define WFFX_SETCHORUSALL 20 -#define WFFX_SETREVERBDEF 22 -#define WFFX_SETCHORUSDEF 23 -#define WFFX_DELAYSETINGAIN 24 -#define WFFX_DELAYSETFBGAIN 25 -#define WFFX_DELAYSETFBLPF 26 -#define WFFX_DELAYSETGAIN 27 -#define WFFX_DELAYSETTIME 28 -#define WFFX_DELAYSETFBTIME 29 -#define WFFX_DELAYSETALL 30 -#define WFFX_DELAYSETDEF 32 -#define WFFX_SDELAYSETINGAIN 33 -#define WFFX_SDELAYSETFBGAIN 34 -#define WFFX_SDELAYSETFBLPF 35 -#define WFFX_SDELAYSETGAIN 36 -#define WFFX_SDELAYSETTIME 37 -#define WFFX_SDELAYSETFBTIME 38 -#define WFFX_SDELAYSETALL 39 -#define WFFX_SDELAYSETDEF 41 -#define WFFX_DEQSETINGAIN 42 -#define WFFX_DEQSETFILTER 43 -#define WFFX_DEQSETALL 44 -#define WFFX_DEQSETDEF 46 -#define WFFX_MUTE 47 -#define WFFX_FLANGESETBALANCE 48 -#define WFFX_FLANGESETDELAY 49 -#define WFFX_FLANGESETDWFFX_TH 50 -#define WFFX_FLANGESETFBGAIN 51 -#define WFFX_FLANGESETINGAIN 52 -#define WFFX_FLANGESETLFO 53 -#define WFFX_FLANGESETALL 54 -#define WFFX_FLANGESETDEF 56 -#define WFFX_PITCHSETSHIFT 57 -#define WFFX_PITCHSETBALANCE 58 -#define WFFX_PITCHSETALL 59 -#define WFFX_PITCHSETDEF 61 -#define WFFX_SRSSETINGAIN 62 -#define WFFX_SRSSETSPACE 63 -#define WFFX_SRSSETCENTER 64 -#define WFFX_SRSSETGAIN 65 -#define WFFX_SRSSETMODE 66 -#define WFFX_SRSSETDEF 68 - -/* Allow direct user-space control over FX memory/coefficient data. - In theory this could be used to download the FX microprogram, - but it would be a little slower, and involve some weird code. - */ - -#define WFFX_MEMSET 69 - -#endif /* __wavefront_h__ */ -- cgit v1.2.3 From c4710e65c005339b5979fa258bf89940dc2a700b Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Wed, 4 Oct 2006 17:32:21 +0100 Subject: [MIPS] Remove remaining reference to ite_gpio.h from Kbuild Signed-off-by: David Woodhouse Signed-off-by: Ralf Baechle --- include/linux/Kbuild | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/Kbuild b/include/linux/Kbuild index ea005c0a79fd..5114ff18101d 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -100,7 +100,6 @@ header-y += ipx.h header-y += irda.h header-y += isdn_divertif.h header-y += iso_fs.h -header-y += ite_gpio.h header-y += ixjuser.h header-y += jffs2.h header-y += keyctl.h -- cgit v1.2.3 From 9ab4f88b7ffdf338773e7755f923bc6b9e079834 Mon Sep 17 00:00:00 2001 From: Haavard Skinnemoen Date: Wed, 4 Oct 2006 16:02:06 +0200 Subject: [PATCH] serial: Rename PORT_AT91 -> PORT_ATMEL The at91_serial driver can be used with both AT32 and AT91 devices from Atmel and has therefore been renamed atmel_serial. The only thing left is to rename PORT_AT91 PORT_ATMEL. Signed-off-by: Haavard Skinnemoen Acked-by: Andrew Victor Signed-off-by: Linus Torvalds --- include/linux/serial_core.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index de2e68159d96..b661c19f3f72 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -67,8 +67,8 @@ /* Parisc type numbers. */ #define PORT_MUX 48 -/* Atmel AT91xxx SoC */ -#define PORT_AT91 49 +/* Atmel AT91 / AT32 SoC */ +#define PORT_ATMEL 49 /* Macintosh Zilog type numbers */ #define PORT_MAC_ZILOG 50 /* m68k : not yet implemented */ -- cgit v1.2.3 From f583f4924d669d36de677e0cc2422ee95203d444 Mon Sep 17 00:00:00 2001 From: David C Somayajulu Date: Wed, 4 Oct 2006 08:27:25 +0200 Subject: [PATCH] helper function for retrieving scsi_cmd given host based block layer tag This was necessitated by the need for a function to get back to a scsi_cmnd, when an hba the posts its (corresponding) completion interrupt with a block layer tag as its reference. Signed-off-by: Mike Christie Signed-off-by: David Somayajulu Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 1d79b8d4ca6d..26f7856ff812 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -769,6 +769,14 @@ extern struct blk_queue_tag *blk_init_tags(int); extern void blk_free_tags(struct blk_queue_tag *); extern void blk_congestion_end(int rw); +static inline struct request *blk_map_queue_find_tag(struct blk_queue_tag *bqt, + int tag) +{ + if (unlikely(bqt == NULL || tag >= bqt->real_max_depth)) + return NULL; + return bqt->tag_index[tag]; +} + extern void blk_rq_bio_prep(request_queue_t *, struct request *, struct bio *); extern int blkdev_issue_flush(struct block_device *, sector_t *); -- cgit v1.2.3 From 2c2345c2b4fec30d12e1e1a6ee153a80af101e32 Mon Sep 17 00:00:00 2001 From: Roger Gammans Date: Wed, 4 Oct 2006 13:37:45 +0200 Subject: [PATCH] Document bi_sector and sector_t Signed-Off-By: Roger Gammans Signed-off-by: Jens Axboe --- include/linux/bio.h | 3 ++- include/linux/types.h | 6 +++++- 2 files changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 711c321a7011..092dbd0e7658 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -70,7 +70,8 @@ typedef void (bio_destructor_t) (struct bio *); * stacking drivers) */ struct bio { - sector_t bi_sector; + sector_t bi_sector; /* device address in 512 byte + sectors */ struct bio *bi_next; /* request queue link */ struct block_device *bi_bdev; unsigned long bi_flags; /* status, command, etc */ diff --git a/include/linux/types.h b/include/linux/types.h index 406d4ae57631..750f085fa564 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -129,8 +129,12 @@ typedef __s64 int64_t; /* this is a special 64bit data type that is 8-byte aligned */ #define aligned_u64 unsigned long long __attribute__((aligned(8))) -/* +/** * The type used for indexing onto a disc or disc partition. + * + * Linux always considers sectors to be 512 bytes long independently + * of the devices real block size. + * * If required, asm/types.h can override it and define * HAVE_SECTOR_T */ -- cgit v1.2.3 From ed542bed126caeefc6546b276e4af852d4d34f33 Mon Sep 17 00:00:00 2001 From: Jeff Garzik Date: Wed, 4 Oct 2006 07:05:11 -0400 Subject: [SCSI] raid class: handle component-add errors Signed-off-by: Jeff Garzik Signed-off-by: James Bottomley --- include/linux/raid_class.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/raid_class.h b/include/linux/raid_class.h index d0dd38b3a2fd..d22ad392242a 100644 --- a/include/linux/raid_class.h +++ b/include/linux/raid_class.h @@ -77,5 +77,6 @@ DEFINE_RAID_ATTRIBUTE(enum raid_state, state) struct raid_template *raid_class_attach(struct raid_function_template *); void raid_class_release(struct raid_template *); -void raid_component_add(struct raid_template *, struct device *, - struct device *); +int __must_check raid_component_add(struct raid_template *, struct device *, + struct device *); + -- cgit v1.2.3 From 57a58a9435aef3e0342ba4b2c97e0ddfea6f2c7f Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 5 Oct 2006 13:06:34 +0100 Subject: IRQ: Typedef the IRQ flow handler function type Typedef the IRQ flow handler function type. Signed-Off-By: David Howells (cherry picked from 8e973fbdf5716b93a0a8c0365be33a31ca0fa351 commit) --- include/linux/irq.h | 30 ++++++++++++------------------ 1 file changed, 12 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irq.h b/include/linux/irq.h index 6f463606c318..b947d46e4b18 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -22,6 +22,12 @@ #include #include +struct irq_desc; +typedef void fastcall (*irq_flow_handler_t)(unsigned int irq, + struct irq_desc *desc, + struct pt_regs *regs); + + /* * IRQ line status. * @@ -139,9 +145,7 @@ struct irq_chip { * Pad this out to 32 bytes for cache and indexing reasons. */ struct irq_desc { - void fastcall (*handle_irq)(unsigned int irq, - struct irq_desc *desc, - struct pt_regs *regs); + irq_flow_handler_t handle_irq; struct irq_chip *chip; void *handler_data; void *chip_data; @@ -281,9 +285,7 @@ handle_bad_irq(unsigned int irq, struct irq_desc *desc, struct pt_regs *regs); * Get a descriptive string for the highlevel handler, for * /proc/interrupts output: */ -extern const char * -handle_irq_name(void fastcall (*handle)(unsigned int, struct irq_desc *, - struct pt_regs *)); +extern const char *handle_irq_name(irq_flow_handler_t handle); /* * Monolithic do_IRQ implementation. @@ -335,22 +337,15 @@ extern struct irq_chip dummy_irq_chip; extern void set_irq_chip_and_handler(unsigned int irq, struct irq_chip *chip, - void fastcall (*handle)(unsigned int, - struct irq_desc *, - struct pt_regs *)); + irq_flow_handler_t handle); extern void -__set_irq_handler(unsigned int irq, - void fastcall (*handle)(unsigned int, struct irq_desc *, - struct pt_regs *), - int is_chained); +__set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained); /* * Set a highlevel flow handler for a given IRQ: */ static inline void -set_irq_handler(unsigned int irq, - void fastcall (*handle)(unsigned int, struct irq_desc *, - struct pt_regs *)) +set_irq_handler(unsigned int irq, irq_flow_handler_t handle) { __set_irq_handler(irq, handle, 0); } @@ -362,8 +357,7 @@ set_irq_handler(unsigned int irq, */ static inline void set_irq_chained_handler(unsigned int irq, - void fastcall (*handle)(unsigned int, struct irq_desc *, - struct pt_regs *)) + irq_flow_handler_t handle) { __set_irq_handler(irq, handle, 1); } -- cgit v1.2.3 From da482792a6d1a3fbaaa25fae867b343fb4db3246 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 5 Oct 2006 13:06:34 +0100 Subject: IRQ: Typedef the IRQ handler function type Typedef the IRQ handler function type. Signed-Off-By: David Howells (cherry picked from 1356d1e5fd256997e3d3dce0777ab787d0515c7a commit) --- include/linux/interrupt.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 1f97e3d92639..19782350dcc8 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -64,8 +64,10 @@ #define SA_TRIGGER_RISING IRQF_TRIGGER_RISING #define SA_TRIGGER_MASK IRQF_TRIGGER_MASK +typedef irqreturn_t (*irq_handler_t)(int, void *, struct pt_regs *); + struct irqaction { - irqreturn_t (*handler)(int, void *, struct pt_regs *); + irq_handler_t handler; unsigned long flags; cpumask_t mask; const char *name; @@ -76,8 +78,7 @@ struct irqaction { }; extern irqreturn_t no_action(int cpl, void *dev_id, struct pt_regs *regs); -extern int request_irq(unsigned int, - irqreturn_t (*handler)(int, void *, struct pt_regs *), +extern int request_irq(unsigned int, irq_handler_t handler, unsigned long, const char *, void *); extern void free_irq(unsigned int, void *); -- cgit v1.2.3 From 7d12e780e003f93433d49ce78cfedf4b4c52adc5 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 5 Oct 2006 14:55:46 +0100 Subject: IRQ: Maintain regs pointer globally rather than passing to IRQ handlers Maintain a per-CPU global "struct pt_regs *" variable which can be used instead of passing regs around manually through all ~1800 interrupt handlers in the Linux kernel. The regs pointer is used in few places, but it potentially costs both stack space and code to pass it around. On the FRV arch, removing the regs parameter from all the genirq function results in a 20% speed up of the IRQ exit path (ie: from leaving timer_interrupt() to leaving do_IRQ()). Where appropriate, an arch may override the generic storage facility and do something different with the variable. On FRV, for instance, the address is maintained in GR28 at all times inside the kernel as part of general exception handling. Having looked over the code, it appears that the parameter may be handed down through up to twenty or so layers of functions. Consider a USB character device attached to a USB hub, attached to a USB controller that posts its interrupts through a cascaded auxiliary interrupt controller. A character device driver may want to pass regs to the sysrq handler through the input layer which adds another few layers of parameter passing. I've build this code with allyesconfig for x86_64 and i386. I've runtested the main part of the code on FRV and i386, though I can't test most of the drivers. I've also done partial conversion for powerpc and MIPS - these at least compile with minimal configurations. This will affect all archs. Mostly the changes should be relatively easy. Take do_IRQ(), store the regs pointer at the beginning, saving the old one: struct pt_regs *old_regs = set_irq_regs(regs); And put the old one back at the end: set_irq_regs(old_regs); Don't pass regs through to generic_handle_irq() or __do_IRQ(). In timer_interrupt(), this sort of change will be necessary: - update_process_times(user_mode(regs)); - profile_tick(CPU_PROFILING, regs); + update_process_times(user_mode(get_irq_regs())); + profile_tick(CPU_PROFILING); I'd like to move update_process_times()'s use of get_irq_regs() into itself, except that i386, alone of the archs, uses something other than user_mode(). Some notes on the interrupt handling in the drivers: (*) input_dev() is now gone entirely. The regs pointer is no longer stored in the input_dev struct. (*) finish_unlinks() in drivers/usb/host/ohci-q.c needs checking. It does something different depending on whether it's been supplied with a regs pointer or not. (*) Various IRQ handler function pointers have been moved to type irq_handler_t. Signed-Off-By: David Howells (cherry picked from 1b16e7ac850969f38b375e511e3fa2f474a33867 commit) --- include/linux/adb.h | 4 ++-- include/linux/arcdevice.h | 2 +- include/linux/hiddev.h | 4 ++-- include/linux/ide.h | 2 +- include/linux/input.h | 7 ------- include/linux/interrupt.h | 4 ++-- include/linux/ioc3.h | 2 +- include/linux/irq.h | 40 +++++++++++++++------------------------- include/linux/libata.h | 4 ++-- include/linux/parport.h | 16 +++++++--------- include/linux/profile.h | 2 +- include/linux/rtc.h | 2 +- include/linux/serial_core.h | 7 +++---- include/linux/serio.h | 5 ++--- include/linux/sysrq.h | 6 +++--- include/linux/usb.h | 3 +-- include/linux/usb/serial.h | 12 ++++++------ 17 files changed, 50 insertions(+), 72 deletions(-) (limited to 'include/linux') diff --git a/include/linux/adb.h b/include/linux/adb.h index b7305b178279..64d8878e1444 100644 --- a/include/linux/adb.h +++ b/include/linux/adb.h @@ -90,10 +90,10 @@ extern struct blocking_notifier_head adb_client_list; int adb_request(struct adb_request *req, void (*done)(struct adb_request *), int flags, int nbytes, ...); int adb_register(int default_id,int handler_id,struct adb_ids *ids, - void (*handler)(unsigned char *, int, struct pt_regs *, int)); + void (*handler)(unsigned char *, int, int)); int adb_unregister(int index); void adb_poll(void); -void adb_input(unsigned char *, int, struct pt_regs *, int); +void adb_input(unsigned char *, int, int); int adb_reset_bus(void); int adb_try_handler_change(int address, int new_id); diff --git a/include/linux/arcdevice.h b/include/linux/arcdevice.h index 231ba090ae34..2f85049cfb3d 100644 --- a/include/linux/arcdevice.h +++ b/include/linux/arcdevice.h @@ -334,7 +334,7 @@ void arcnet_dump_skb(struct net_device *dev, struct sk_buff *skb, char *desc); #endif void arcnet_unregister_proto(struct ArcProto *proto); -irqreturn_t arcnet_interrupt(int irq, void *dev_id, struct pt_regs *regs); +irqreturn_t arcnet_interrupt(int irq, void *dev_id); struct net_device *alloc_arcdev(char *name); #endif /* __KERNEL__ */ diff --git a/include/linux/hiddev.h b/include/linux/hiddev.h index 945ba1ad14ac..acbdae6d7ae1 100644 --- a/include/linux/hiddev.h +++ b/include/linux/hiddev.h @@ -222,7 +222,7 @@ struct hid_report; int hiddev_connect(struct hid_device *); void hiddev_disconnect(struct hid_device *); void hiddev_hid_event(struct hid_device *hid, struct hid_field *field, - struct hid_usage *usage, __s32 value, struct pt_regs *regs); + struct hid_usage *usage, __s32 value); void hiddev_report_event(struct hid_device *hid, struct hid_report *report); int __init hiddev_init(void); void hiddev_exit(void); @@ -230,7 +230,7 @@ void hiddev_exit(void); static inline int hiddev_connect(struct hid_device *hid) { return -1; } static inline void hiddev_disconnect(struct hid_device *hid) { } static inline void hiddev_hid_event(struct hid_device *hid, struct hid_field *field, - struct hid_usage *usage, __s32 value, struct pt_regs *regs) { } + struct hid_usage *usage, __s32 value) { } static inline void hiddev_report_event(struct hid_device *hid, struct hid_report *report) { } static inline int hiddev_init(void) { return 0; } static inline void hiddev_exit(void) { } diff --git a/include/linux/ide.h b/include/linux/ide.h index 07d8d725541f..9c2050293f17 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -1185,7 +1185,7 @@ extern void ide_stall_queue(ide_drive_t *drive, unsigned long timeout); extern int ide_spin_wait_hwgroup(ide_drive_t *); extern void ide_timer_expiry(unsigned long); -extern irqreturn_t ide_intr(int irq, void *dev_id, struct pt_regs *regs); +extern irqreturn_t ide_intr(int irq, void *dev_id); extern void do_ide_request(request_queue_t *); void ide_init_disk(struct gendisk *, ide_drive_t *); diff --git a/include/linux/input.h b/include/linux/input.h index 5770105471dd..c38507ba38b5 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -953,7 +953,6 @@ struct input_dev { unsigned int repeat_key; struct timer_list timer; - struct pt_regs *regs; int state; int sync; @@ -1149,15 +1148,9 @@ static inline void input_report_switch(struct input_dev *dev, unsigned int code, input_event(dev, EV_SW, code, !!value); } -static inline void input_regs(struct input_dev *dev, struct pt_regs *regs) -{ - dev->regs = regs; -} - static inline void input_sync(struct input_dev *dev) { input_event(dev, EV_SYN, SYN_REPORT, 0); - dev->regs = NULL; } static inline void input_set_abs_params(struct input_dev *dev, int axis, int min, int max, int fuzz, int flat) diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 19782350dcc8..5b83e7b59621 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -64,7 +64,7 @@ #define SA_TRIGGER_RISING IRQF_TRIGGER_RISING #define SA_TRIGGER_MASK IRQF_TRIGGER_MASK -typedef irqreturn_t (*irq_handler_t)(int, void *, struct pt_regs *); +typedef irqreturn_t (*irq_handler_t)(int, void *); struct irqaction { irq_handler_t handler; @@ -77,7 +77,7 @@ struct irqaction { struct proc_dir_entry *dir; }; -extern irqreturn_t no_action(int cpl, void *dev_id, struct pt_regs *regs); +extern irqreturn_t no_action(int cpl, void *dev_id); extern int request_irq(unsigned int, irq_handler_t handler, unsigned long, const char *, void *); extern void free_irq(unsigned int, void *); diff --git a/include/linux/ioc3.h b/include/linux/ioc3.h index da7c09e4ede6..38b286e9a46c 100644 --- a/include/linux/ioc3.h +++ b/include/linux/ioc3.h @@ -63,7 +63,7 @@ struct ioc3_submodule { /* IRQ stuff */ unsigned int irq_mask; /* IOC3 IRQ mask, leave clear for Ethernet */ int reset_mask; /* non-zero if you want the ioc3.c module to reset interrupts */ - int (*intr) (struct ioc3_submodule *, struct ioc3_driver_data *, unsigned int, struct pt_regs *); + int (*intr) (struct ioc3_submodule *, struct ioc3_driver_data *, unsigned int); /* private submodule data */ void *data; /* assigned by submodule */ }; diff --git a/include/linux/irq.h b/include/linux/irq.h index b947d46e4b18..c64f3cc7e870 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -21,11 +21,11 @@ #include #include +#include struct irq_desc; typedef void fastcall (*irq_flow_handler_t)(unsigned int irq, - struct irq_desc *desc, - struct pt_regs *regs); + struct irq_desc *desc); /* @@ -258,28 +258,18 @@ static inline int select_smp_affinity(unsigned int irq) extern int no_irq_affinity; /* Handle irq action chains: */ -extern int handle_IRQ_event(unsigned int irq, struct pt_regs *regs, - struct irqaction *action); +extern int handle_IRQ_event(unsigned int irq, struct irqaction *action); /* * Built-in IRQ handlers for various IRQ types, * callable via desc->chip->handle_irq() */ -extern void fastcall -handle_level_irq(unsigned int irq, struct irq_desc *desc, struct pt_regs *regs); -extern void fastcall -handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc, - struct pt_regs *regs); -extern void fastcall -handle_edge_irq(unsigned int irq, struct irq_desc *desc, struct pt_regs *regs); -extern void fastcall -handle_simple_irq(unsigned int irq, struct irq_desc *desc, - struct pt_regs *regs); -extern void fastcall -handle_percpu_irq(unsigned int irq, struct irq_desc *desc, - struct pt_regs *regs); -extern void fastcall -handle_bad_irq(unsigned int irq, struct irq_desc *desc, struct pt_regs *regs); +extern void fastcall handle_level_irq(unsigned int irq, struct irq_desc *desc); +extern void fastcall handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc); +extern void fastcall handle_edge_irq(unsigned int irq, struct irq_desc *desc); +extern void fastcall handle_simple_irq(unsigned int irq, struct irq_desc *desc); +extern void fastcall handle_percpu_irq(unsigned int irq, struct irq_desc *desc); +extern void fastcall handle_bad_irq(unsigned int irq, struct irq_desc *desc); /* * Get a descriptive string for the highlevel handler, for @@ -292,7 +282,7 @@ extern const char *handle_irq_name(irq_flow_handler_t handle); * (is an explicit fastcall, because i386 4KSTACKS calls it from assembly) */ #ifndef CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ -extern fastcall unsigned int __do_IRQ(unsigned int irq, struct pt_regs *regs); +extern fastcall unsigned int __do_IRQ(unsigned int irq); #endif /* @@ -301,23 +291,23 @@ extern fastcall unsigned int __do_IRQ(unsigned int irq, struct pt_regs *regs); * irqchip-style controller then we call the ->handle_irq() handler, * and it calls __do_IRQ() if it's attached to an irqtype-style controller. */ -static inline void generic_handle_irq(unsigned int irq, struct pt_regs *regs) +static inline void generic_handle_irq(unsigned int irq) { struct irq_desc *desc = irq_desc + irq; #ifdef CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ - desc->handle_irq(irq, desc, regs); + desc->handle_irq(irq, desc); #else if (likely(desc->handle_irq)) - desc->handle_irq(irq, desc, regs); + desc->handle_irq(irq, desc); else - __do_IRQ(irq, regs); + __do_IRQ(irq); #endif } /* Handling of unhandled and spurious interrupts: */ extern void note_interrupt(unsigned int irq, struct irq_desc *desc, - int action_ret, struct pt_regs *regs); + int action_ret); /* Resending of interrupts :*/ void check_irq_resend(struct irq_desc *desc, unsigned int irq); diff --git a/include/linux/libata.h b/include/linux/libata.h index d1af1dbeaeb4..d0a7ad5ed518 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -628,7 +628,7 @@ struct ata_port_operations { void (*error_handler) (struct ata_port *ap); void (*post_internal_cmd) (struct ata_queued_cmd *qc); - irqreturn_t (*irq_handler)(int, void *, struct pt_regs *); + irq_handler_t irq_handler; void (*irq_clear) (struct ata_port *); u32 (*scr_read) (struct ata_port *ap, unsigned int sc_reg); @@ -769,7 +769,7 @@ extern void ata_exec_command(struct ata_port *ap, const struct ata_taskfile *tf) extern int ata_port_start (struct ata_port *ap); extern void ata_port_stop (struct ata_port *ap); extern void ata_host_stop (struct ata_host *host); -extern irqreturn_t ata_interrupt (int irq, void *dev_instance, struct pt_regs *regs); +extern irqreturn_t ata_interrupt (int irq, void *dev_instance); extern void ata_mmio_data_xfer(struct ata_device *adev, unsigned char *buf, unsigned int buflen, int write_data); extern void ata_pio_data_xfer(struct ata_device *adev, unsigned char *buf, diff --git a/include/linux/parport.h b/include/linux/parport.h index 5bf321e82c99..80682aaa8f18 100644 --- a/include/linux/parport.h +++ b/include/linux/parport.h @@ -229,7 +229,7 @@ struct pardevice { int (*preempt)(void *); void (*wakeup)(void *); void *private; - void (*irq_func)(int, void *, struct pt_regs *); + void (*irq_func)(int, void *); unsigned int flags; struct pardevice *next; struct pardevice *prev; @@ -375,7 +375,7 @@ extern void parport_put_port (struct parport *); struct pardevice *parport_register_device(struct parport *port, const char *name, int (*pf)(void *), void (*kf)(void *), - void (*irq_func)(int, void *, struct pt_regs *), + void (*irq_func)(int, void *), int flags, void *handle); /* parport_unregister unlinks a device from the chain. */ @@ -457,7 +457,7 @@ static __inline__ int parport_yield_blocking(struct pardevice *dev) #define PARPORT_FLAG_EXCL (1<<1) /* EXCL driver registered. */ /* IEEE1284 functions */ -extern void parport_ieee1284_interrupt (int, void *, struct pt_regs *); +extern void parport_ieee1284_interrupt (int, void *); extern int parport_negotiate (struct parport *, int mode); extern ssize_t parport_write (struct parport *, const void *buf, size_t len); extern ssize_t parport_read (struct parport *, void *buf, size_t len); @@ -502,8 +502,7 @@ extern void parport_daisy_fini (struct parport *port); extern struct pardevice *parport_open (int devnum, const char *name, int (*pf) (void *), void (*kf) (void *), - void (*irqf) (int, void *, - struct pt_regs *), + void (*irqf) (int, void *), int flags, void *handle); extern void parport_close (struct pardevice *dev); extern ssize_t parport_device_id (int devnum, char *buffer, size_t len); @@ -512,13 +511,12 @@ extern void parport_daisy_deselect_all (struct parport *port); extern int parport_daisy_select (struct parport *port, int daisy, int mode); /* Lowlevel drivers _can_ call this support function to handle irqs. */ -static __inline__ void parport_generic_irq(int irq, struct parport *port, - struct pt_regs *regs) +static __inline__ void parport_generic_irq(int irq, struct parport *port) { - parport_ieee1284_interrupt (irq, port, regs); + parport_ieee1284_interrupt (irq, port); read_lock(&port->cad_lock); if (port->cad && port->cad->irq_func) - port->cad->irq_func(irq, port->cad->private, regs); + port->cad->irq_func(irq, port->cad->private); read_unlock(&port->cad_lock); } diff --git a/include/linux/profile.h b/include/linux/profile.h index e633004ae052..acce53fd38b6 100644 --- a/include/linux/profile.h +++ b/include/linux/profile.h @@ -17,7 +17,7 @@ struct notifier_block; /* init basic kernel profiler */ void __init profile_init(void); -void profile_tick(int, struct pt_regs *); +void profile_tick(int); void profile_hit(int, void *); #ifdef CONFIG_PROC_FS void create_prof_cpu_mask(struct proc_dir_entry *); diff --git a/include/linux/rtc.h b/include/linux/rtc.h index b89f09357054..09ff4c3e2713 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -208,7 +208,7 @@ int rtc_register(rtc_task_t *task); int rtc_unregister(rtc_task_t *task); int rtc_control(rtc_task_t *t, unsigned int cmd, unsigned long arg); void rtc_get_rtc_time(struct rtc_time *rtc_tm); -irqreturn_t rtc_interrupt(int irq, void *dev_id, struct pt_regs *regs); +irqreturn_t rtc_interrupt(int irq, void *dev_id); #endif /* __KERNEL__ */ diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index b661c19f3f72..463ab953b092 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -409,13 +409,12 @@ int uart_resume_port(struct uart_driver *reg, struct uart_port *port); * The following are helper functions for the low level drivers. */ static inline int -uart_handle_sysrq_char(struct uart_port *port, unsigned int ch, - struct pt_regs *regs) +uart_handle_sysrq_char(struct uart_port *port, unsigned int ch) { #ifdef SUPPORT_SYSRQ if (port->sysrq) { if (ch && time_before(jiffies, port->sysrq)) { - handle_sysrq(ch, regs, port->info->tty); + handle_sysrq(ch, port->info->tty); port->sysrq = 0; return 1; } @@ -425,7 +424,7 @@ uart_handle_sysrq_char(struct uart_port *port, unsigned int ch, return 0; } #ifndef SUPPORT_SYSRQ -#define uart_handle_sysrq_char(port,ch,regs) uart_handle_sysrq_char(port, 0, NULL) +#define uart_handle_sysrq_char(port,ch) uart_handle_sysrq_char(port, 0) #endif /* diff --git a/include/linux/serio.h b/include/linux/serio.h index c9069310b6ac..3a697cc6ecae 100644 --- a/include/linux/serio.h +++ b/include/linux/serio.h @@ -60,8 +60,7 @@ struct serio_driver { unsigned int manual_bind; void (*write_wakeup)(struct serio *); - irqreturn_t (*interrupt)(struct serio *, unsigned char, - unsigned int, struct pt_regs *); + irqreturn_t (*interrupt)(struct serio *, unsigned char, unsigned int); int (*connect)(struct serio *, struct serio_driver *drv); int (*reconnect)(struct serio *); void (*disconnect)(struct serio *); @@ -75,7 +74,7 @@ int serio_open(struct serio *serio, struct serio_driver *drv); void serio_close(struct serio *serio); void serio_rescan(struct serio *serio); void serio_reconnect(struct serio *serio); -irqreturn_t serio_interrupt(struct serio *serio, unsigned char data, unsigned int flags, struct pt_regs *regs); +irqreturn_t serio_interrupt(struct serio *serio, unsigned char data, unsigned int flags); void __serio_register_port(struct serio *serio, struct module *owner); static inline void serio_register_port(struct serio *serio) diff --git a/include/linux/sysrq.h b/include/linux/sysrq.h index e657e523b9bf..9df8833670cb 100644 --- a/include/linux/sysrq.h +++ b/include/linux/sysrq.h @@ -29,7 +29,7 @@ struct tty_struct; #define SYSRQ_ENABLE_RTNICE 0x0100 struct sysrq_key_op { - void (*handler)(int, struct pt_regs *, struct tty_struct *); + void (*handler)(int, struct tty_struct *); char *help_msg; char *action_msg; int enable_mask; @@ -42,8 +42,8 @@ struct sysrq_key_op { * are available -- else NULL's). */ -void handle_sysrq(int, struct pt_regs *, struct tty_struct *); -void __handle_sysrq(int, struct pt_regs *, struct tty_struct *, int check_mask); +void handle_sysrq(int, struct tty_struct *); +void __handle_sysrq(int, struct tty_struct *, int check_mask); int register_sysrq_key(int, struct sysrq_key_op *); int unregister_sysrq_key(int, struct sysrq_key_op *); struct sysrq_key_op *__sysrq_get_key_op(int key); diff --git a/include/linux/usb.h b/include/linux/usb.h index 190cc1b78fe2..5482bfb3303d 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -764,9 +764,8 @@ struct usb_iso_packet_descriptor { }; struct urb; -struct pt_regs; -typedef void (*usb_complete_t)(struct urb *, struct pt_regs *); +typedef void (*usb_complete_t)(struct urb *); /** * struct urb - USB Request Block diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h index 91c983eef899..91b3ea2bbb14 100644 --- a/include/linux/usb/serial.h +++ b/include/linux/usb/serial.h @@ -226,10 +226,10 @@ struct usb_serial_driver { int (*tiocmget) (struct usb_serial_port *port, struct file *file); int (*tiocmset) (struct usb_serial_port *port, struct file *file, unsigned int set, unsigned int clear); - void (*read_int_callback)(struct urb *urb, struct pt_regs *regs); - void (*write_int_callback)(struct urb *urb, struct pt_regs *regs); - void (*read_bulk_callback)(struct urb *urb, struct pt_regs *regs); - void (*write_bulk_callback)(struct urb *urb, struct pt_regs *regs); + void (*read_int_callback)(struct urb *urb); + void (*write_int_callback)(struct urb *urb); + void (*read_bulk_callback)(struct urb *urb); + void (*write_bulk_callback)(struct urb *urb); }; #define to_usb_serial_driver(d) container_of(d, struct usb_serial_driver, driver) @@ -262,8 +262,8 @@ extern int usb_serial_generic_write (struct usb_serial_port *port, const unsigne extern void usb_serial_generic_close (struct usb_serial_port *port, struct file *filp); extern int usb_serial_generic_write_room (struct usb_serial_port *port); extern int usb_serial_generic_chars_in_buffer (struct usb_serial_port *port); -extern void usb_serial_generic_read_bulk_callback (struct urb *urb, struct pt_regs *regs); -extern void usb_serial_generic_write_bulk_callback (struct urb *urb, struct pt_regs *regs); +extern void usb_serial_generic_read_bulk_callback (struct urb *urb); +extern void usb_serial_generic_write_bulk_callback (struct urb *urb); extern void usb_serial_generic_shutdown (struct usb_serial *serial); extern int usb_serial_generic_register (int debug); extern void usb_serial_generic_deregister (void); -- cgit v1.2.3 From 7f7bbbe50b8a28f4dfaa4cea939ddb50198c4a99 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Fri, 6 Oct 2006 00:43:53 -0700 Subject: [PATCH] page fault retry with NOPAGE_REFAULT Add a way for a no_page() handler to request a retry of the faulting instruction. It goes back to userland on page faults and just tries again in get_user_pages(). I added a cond_resched() in the loop in that later case. The problem I have with signal and spufs is an actual bug affecting apps and I don't see other ways of fixing it. In addition, we are having issues with infiniband and 64k pages (related to the way the hypervisor deals with some HV cards) that will require us to muck around with the MMU from within the IB driver's no_page() (it's a pSeries specific driver) and return to the caller the same way using NOPAGE_REFAULT. And to add to this, the graphics folks have been following a new approach of memory management that involves transparently swapping objects between video ram and main meory. To do that, they need installing PTEs from a no_page() handler as well and that also requires returning with NOPAGE_REFAULT. (For the later, they are currently using io_remap_pfn_range to install one PTE from no_page() which is a bit racy, we need to add a check for the PTE having already been installed afer taking the lock, but that's ok, they are only at the proof-of-concept stage. I'll send a patch adding a "clean" function to do that, we can use that from spufs too and get rid of the sparsemem hacks we do to create struct page for SPEs. Basically, that provides a generic solution for being able to have no_page() map hardware devices, which is something that I think sound driver folks have been asking for some time too). All of these things depend on having the NOPAGE_REFAULT exit path from no_page() handlers. Signed-off-by: Benjamin Herrenchmidt Cc: Hugh Dickins Cc: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index b7966ab8cb6a..26146623be2f 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -593,6 +593,7 @@ static inline int page_mapped(struct page *page) */ #define NOPAGE_SIGBUS (NULL) #define NOPAGE_OOM ((struct page *) (-1)) +#define NOPAGE_REFAULT ((struct page *) (-2)) /* Return to userspace, rerun */ /* * Error return values for the *_nopfn functions -- cgit v1.2.3 From 7236e978a3883406ca06ee79e0739743c7c92a85 Mon Sep 17 00:00:00 2001 From: Roman Zippel Date: Fri, 6 Oct 2006 00:43:54 -0700 Subject: [PATCH] provide tickadj define Provide a tickadj compatibility define for archs still using it. Signed-off-by: Roman Zippel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/timex.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/timex.h b/include/linux/timex.h index 049dfe4a11f2..db501dc23c29 100644 --- a/include/linux/timex.h +++ b/include/linux/timex.h @@ -293,6 +293,9 @@ extern void second_overflow(void); extern void update_ntp_one_tick(void); extern int do_adjtimex(struct timex *); +/* Don't use! Compatibility define for existing users. */ +#define tickadj (500/HZ ? : 1) + #endif /* KERNEL */ #endif /* LINUX_TIMEX_H */ -- cgit v1.2.3 From a666ecfbf512dbd63a60f65d2ad6733a9a1b12ee Mon Sep 17 00:00:00 2001 From: Jan Blunck Date: Fri, 6 Oct 2006 00:43:58 -0700 Subject: [PATCH] Fix typo in "syntax error if percpu macros are incorrectly used" patch Trivial typo fix in the "syntax error if percpu macros are incorrectly used" patch. I misspelled "identifier" in all places. D'Oh! Thanks to Dirk Mueller to point this out. Signed-off-by: Jan Blunck Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/percpu.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 46ec72fa2c84..600e3d387ffc 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -19,7 +19,7 @@ * we force a syntax error here if it isn't. */ #define get_cpu_var(var) (*({ \ - extern int simple_indentifier_##var(void); \ + extern int simple_identifier_##var(void); \ preempt_disable(); \ &__get_cpu_var(var); })) #define put_cpu_var(var) preempt_enable() -- cgit v1.2.3 From 3260259f0084e51ce21503b130473b78871e7077 Mon Sep 17 00:00:00 2001 From: Henne Date: Fri, 6 Oct 2006 00:44:01 -0700 Subject: [PATCH] sched: fix a kerneldoc error on is_init() Fix a kerneldoc warning and reorderd the description for is_init(). Signed-off-by: Henrik Kretzschmar Cc: "Randy.Dunlap" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 331f4502e92b..6735c1cf334c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1065,9 +1065,10 @@ static inline int pid_alive(struct task_struct *p) } /** - * is_init - check if a task structure is the first user space - * task the kernel created. - * @p: Task structure to be checked. + * is_init - check if a task structure is init + * @tsk: Task structure to be checked. + * + * Check if a task structure is the first user space task the kernel created. */ static inline int is_init(struct task_struct *tsk) { -- cgit v1.2.3 From ec5a19dd935eb3793e1f6ed491e8035b3d7b1df9 Mon Sep 17 00:00:00 2001 From: Pierre Ossman Date: Fri, 6 Oct 2006 00:44:03 -0700 Subject: [PATCH] mmc: multi sector write transfers SD cards extend the protocol by allowing the host to query a card how many blocks were successfully stored on the medium. This allows us to safely write chunks of blocks at once. Signed-off-by: Pierre Ossman Cc: Russell King Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmc/protocol.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mmc/protocol.h b/include/linux/mmc/protocol.h index 81c3f77f652c..08dec8d9e703 100644 --- a/include/linux/mmc/protocol.h +++ b/include/linux/mmc/protocol.h @@ -83,6 +83,7 @@ /* Application commands */ #define SD_APP_SET_BUS_WIDTH 6 /* ac [1:0] bus width R1 */ +#define SD_APP_SEND_NUM_WR_BLKS 22 /* adtc R1 */ #define SD_APP_OP_COND 41 /* bcr [31:0] OCR R3 */ #define SD_APP_SEND_SCR 51 /* adtc R1 */ -- cgit v1.2.3 From c6b0a9f87b82f25fa35206ec04b5160372eabab4 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Fri, 6 Oct 2006 00:44:05 -0700 Subject: [PATCH] knfsd: tidy up up meaning of 'buffer size' in nfsd/sunrpc There is some confusion about the meaning of 'bufsz' for a sunrpc server. In some cases it is the largest message that can be sent or received. In other cases it is the largest 'payload' that can be included in a NFS message. In either case, it is not possible for both the request and the reply to be this large. One of the request or reply may only be one page long, which fits nicely with NFS. So we remove 'bufsz' and replace it with two numbers: 'max_payload' and 'max_mesg'. Max_payload is the size that the server requests. It is used by the server to check the max size allowed on a particular connection: depending on the protocol a lower limit might be used. max_mesg is the largest single message that can be sent or received. It is calculated as the max_payload, rounded up to a multiple of PAGE_SIZE, and with PAGE_SIZE added to overhead. Only one of the request and reply may be this size. The other must be at most one page. Cc: Greg Banks Cc: "J. Bruce Fields" Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sunrpc/svc.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index d6288e89fd9d..9c9a8ad92477 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -57,7 +57,8 @@ struct svc_serv { struct svc_stat * sv_stats; /* RPC statistics */ spinlock_t sv_lock; unsigned int sv_nrthreads; /* # of server threads */ - unsigned int sv_bufsz; /* datagram buffer size */ + unsigned int sv_max_payload; /* datagram payload size */ + unsigned int sv_max_mesg; /* max_payload + 1 page for overheads */ unsigned int sv_xdrsize; /* XDR buffer size */ struct list_head sv_permsocks; /* all permanent sockets */ -- cgit v1.2.3 From a8f47c45aee6efa5ef7ec209b90681b091bd3d2c Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 8 Oct 2006 15:04:15 +0100 Subject: [PATCH] missing include of scatterlist.h Signed-off-by: Al Viro Signed-off-by: Linus Torvalds --- include/linux/tifm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tifm.h b/include/linux/tifm.h index 203dd5e11ecb..dfb8052eee5e 100644 --- a/include/linux/tifm.h +++ b/include/linux/tifm.h @@ -17,6 +17,7 @@ #include #include #include +#include /* Host registers (relative to pci base address): */ enum { -- cgit v1.2.3 From cb1055fb1b79775d398038ad8dcd2c7581f141d8 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 8 Oct 2006 15:08:45 +0100 Subject: [PATCH] linux/io.h needs types.h Signed-off-by: Al Viro Signed-off-by: Linus Torvalds --- include/linux/io.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/io.h b/include/linux/io.h index aa3f5af670b5..2ad96c3f0e4e 100644 --- a/include/linux/io.h +++ b/include/linux/io.h @@ -18,6 +18,7 @@ #ifndef _LINUX_IO_H #define _LINUX_IO_H +#include #include #include -- cgit v1.2.3 From 659564c8adfe1765476beee8d55cd18986946892 Mon Sep 17 00:00:00 2001 From: Bill Nottingham Date: Mon, 9 Oct 2006 16:10:48 -0400 Subject: [PATCH] Introduce vfs_listxattr This patch moves code out of fs/xattr.c:listxattr into a new function - vfs_listxattr. The code for vfs_listxattr was originally submitted by Bill Nottingham to Unionfs. Sorry about that. The reason for this submission is to make the listxattr code in fs/xattr.c a little cleaner (as well as to clean up some code in Unionfs.) Currently, Unionfs has vfs_listxattr defined in its code. I think that's very ugly, and I'd like to see it (re)moved. The logical place to put it, is along side of all the other vfs_*xattr functions. Overall, I think this patch is benefitial for both kernel.org kernel and Unionfs. Signed-off-by: Josef "Jeff" Sipek Acked-by: Al Viro Signed-off-by: Linus Torvalds --- include/linux/xattr.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/xattr.h b/include/linux/xattr.h index cda8a96e2fa0..0e7f1e20ea45 100644 --- a/include/linux/xattr.h +++ b/include/linux/xattr.h @@ -41,6 +41,7 @@ struct xattr_handler { }; ssize_t vfs_getxattr(struct dentry *, char *, void *, size_t); +ssize_t vfs_listxattr(struct dentry *d, char *list, size_t size); int vfs_setxattr(struct dentry *, char *, void *, size_t, int); int vfs_removexattr(struct dentry *, char *); -- cgit v1.2.3 From b0ac3f50b8f2cd992ffd36d22c82eabdf075e9c4 Mon Sep 17 00:00:00 2001 From: Dave Jones Date: Mon, 9 Oct 2006 19:13:51 -0400 Subject: [HEADERS] Put linux/config.h out of its misery. Signed-off-by: Dave Jones --- include/linux/config.h | 9 --------- 1 file changed, 9 deletions(-) delete mode 100644 include/linux/config.h (limited to 'include/linux') diff --git a/include/linux/config.h b/include/linux/config.h deleted file mode 100644 index 479ffb0a22d8..000000000000 --- a/include/linux/config.h +++ /dev/null @@ -1,9 +0,0 @@ -#ifndef _LINUX_CONFIG_H -#define _LINUX_CONFIG_H -/* This file is no longer in use and kept only for backward compatibility. - * autoconf.h is now included via -imacros on the commandline - */ -#warning Including config.h is deprecated. -#include - -#endif -- cgit v1.2.3 From 1acc04cd4c0b54ada85d0dd5d7c5efc3441261bf Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 10 Oct 2006 22:44:37 +0100 Subject: [PATCH] dccp __user annotations Signed-off-by: Al Viro Acked-by: David S. Miller Signed-off-by: Linus Torvalds --- include/linux/dccp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dccp.h b/include/linux/dccp.h index d6f4ec467a4b..53553c99cad6 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -191,7 +191,7 @@ enum { /* this structure is argument to DCCP_SOCKOPT_CHANGE_X */ struct dccp_so_feat { __u8 dccpsf_feat; - __u8 *dccpsf_val; + __u8 __user *dccpsf_val; __u8 dccpsf_len; }; -- cgit v1.2.3 From ba46df984b8e8114c3cf19c51670fab084bd4196 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 10 Oct 2006 22:46:07 +0100 Subject: [PATCH] __user annotations: futex Signed-off-by: Al Viro Signed-off-by: Linus Torvalds --- include/linux/compat.h | 2 +- include/linux/syscalls.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index ef5cd192784c..f4ebf96f5308 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -163,7 +163,7 @@ asmlinkage long compat_sys_set_robust_list(struct compat_robust_list_head __user *head, compat_size_t len); asmlinkage long -compat_sys_get_robust_list(int pid, compat_uptr_t *head_ptr, +compat_sys_get_robust_list(int pid, compat_uptr_t __user *head_ptr, compat_size_t __user *len_ptr); long compat_sys_semctl(int first, int second, int third, void __user *uptr); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 3efcfc7e9c6c..b0ace3fd7eb9 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -593,7 +593,7 @@ asmlinkage long sys_tee(int fdin, int fdout, size_t len, unsigned int flags); asmlinkage long sys_sync_file_range(int fd, loff_t offset, loff_t nbytes, unsigned int flags); asmlinkage long sys_get_robust_list(int pid, - struct robust_list_head __user **head_ptr, + struct robust_list_head __user * __user *head_ptr, size_t __user *len_ptr); asmlinkage long sys_set_robust_list(struct robust_list_head __user *head, size_t len); -- cgit v1.2.3 From fb136e97840872638cb08588c4c9b9fff7f7c456 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 10 Oct 2006 22:46:47 +0100 Subject: [PATCH] fix misannotation in ioc4.h Signed-off-by: Al Viro Signed-off-by: Linus Torvalds --- include/linux/ioc4.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ioc4.h b/include/linux/ioc4.h index de73a3289cc2..51e2b9fb6372 100644 --- a/include/linux/ioc4.h +++ b/include/linux/ioc4.h @@ -157,7 +157,7 @@ struct ioc4_driver_data { unsigned long idd_bar0; struct pci_dev *idd_pdev; const struct pci_device_id *idd_pci_id; - struct __iomem ioc4_misc_regs *idd_misc_regs; + struct ioc4_misc_regs __iomem *idd_misc_regs; unsigned long count_period; void *idd_serial_data; unsigned int idd_variant; -- cgit v1.2.3 From 29756fa3287ff702535e459e7ca8c6038f6e9ae3 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 10 Oct 2006 22:47:27 +0100 Subject: [PATCH] trivial iomem annotations: istallion Signed-off-by: Al Viro Signed-off-by: Linus Torvalds --- include/linux/istallion.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/istallion.h b/include/linux/istallion.h index 1f996621bc9c..b55e2a035605 100644 --- a/include/linux/istallion.h +++ b/include/linux/istallion.h @@ -100,7 +100,7 @@ typedef struct stlibrd { unsigned int iobase; int iosize; unsigned long memaddr; - void *membase; + void __iomem *membase; int memsize; int pagesize; int hostoffset; @@ -113,7 +113,7 @@ typedef struct stlibrd { void (*enable)(struct stlibrd *brdp); void (*reenable)(struct stlibrd *brdp); void (*disable)(struct stlibrd *brdp); - char *(*getmemptr)(struct stlibrd *brdp, unsigned long offset, int line); + void __iomem *(*getmemptr)(struct stlibrd *brdp, unsigned long offset, int line); void (*intr)(struct stlibrd *brdp); void (*reset)(struct stlibrd *brdp); stliport_t *ports[STL_MAXPORTS]; -- cgit v1.2.3 From 56052d525a05ba9e53d4f11be2d5deee64924514 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Thu, 1 Dec 2005 17:10:40 -0500 Subject: [PATCH] cdrom: add endianness annotations Signed-off-by: Alexey Dobriyan Signed-off-by: Al Viro Signed-off-by: Linus Torvalds --- include/linux/cdrom.h | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h index 3c9b0bc05123..bbbe7b4da0bb 100644 --- a/include/linux/cdrom.h +++ b/include/linux/cdrom.h @@ -749,7 +749,7 @@ struct request_sense { #define MRW_MODE_PC 0x03 struct mrw_feature_desc { - __u16 feature_code; + __be16 feature_code; #if defined(__BIG_ENDIAN_BITFIELD) __u8 reserved1 : 2; __u8 feature_version : 4; @@ -776,7 +776,7 @@ struct mrw_feature_desc { /* cf. mmc4r02g.pdf 5.3.10 Random Writable Feature (0020h) pg 197 of 635 */ struct rwrt_feature_desc { - __u16 feature_code; + __be16 feature_code; #if defined(__BIG_ENDIAN_BITFIELD) __u8 reserved1 : 2; __u8 feature_version : 4; @@ -803,7 +803,7 @@ struct rwrt_feature_desc { }; typedef struct { - __u16 disc_information_length; + __be16 disc_information_length; #if defined(__BIG_ENDIAN_BITFIELD) __u8 reserved1 : 3; __u8 erasable : 1; @@ -849,7 +849,7 @@ typedef struct { } disc_information; typedef struct { - __u16 track_information_length; + __be16 track_information_length; __u8 track_lsb; __u8 session_lsb; __u8 reserved1; @@ -880,12 +880,12 @@ typedef struct { __u8 lra_v : 1; __u8 reserved3 : 6; #endif - __u32 track_start; - __u32 next_writable; - __u32 free_blocks; - __u32 fixed_packet_size; - __u32 track_size; - __u32 last_rec_address; + __be32 track_start; + __be32 next_writable; + __be32 free_blocks; + __be32 fixed_packet_size; + __be32 track_size; + __be32 last_rec_address; } track_information; struct feature_header { @@ -896,12 +896,12 @@ struct feature_header { }; struct mode_page_header { - __u16 mode_data_length; + __be16 mode_data_length; __u8 medium_type; __u8 reserved1; __u8 reserved2; __u8 reserved3; - __u16 desc_length; + __be16 desc_length; }; #ifdef __KERNEL__ @@ -1106,7 +1106,7 @@ typedef struct { #endif __u8 session_format; __u8 reserved6; - __u32 packet_size; + __be32 packet_size; __u16 audio_pause; __u8 mcn[16]; __u8 isrc[16]; @@ -1151,7 +1151,7 @@ typedef struct { } rpc_state_t; struct event_header { - __u16 data_len; + __be16 data_len; #if defined(__BIG_ENDIAN_BITFIELD) __u8 nea : 1; __u8 reserved1 : 4; -- cgit v1.2.3 From 6ca1584173d0320f47464092eb180a17259cc3f9 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 24 Dec 2005 14:32:38 -0500 Subject: [PATCH] smbfs endianness annotations Signed-off-by: Al Viro Signed-off-by: Linus Torvalds --- include/linux/smb_fs.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/smb_fs.h b/include/linux/smb_fs.h index 367d6c3e8ed4..13b3af547864 100644 --- a/include/linux/smb_fs.h +++ b/include/linux/smb_fs.h @@ -43,17 +43,17 @@ static inline struct smb_inode_info *SMB_I(struct inode *inode) /* macro names are short for word, double-word, long value (?) */ #define WVAL(buf,pos) \ - (le16_to_cpu(get_unaligned((u16 *)((u8 *)(buf) + (pos))))) + (le16_to_cpu(get_unaligned((__le16 *)((u8 *)(buf) + (pos))))) #define DVAL(buf,pos) \ - (le32_to_cpu(get_unaligned((u32 *)((u8 *)(buf) + (pos))))) + (le32_to_cpu(get_unaligned((__le32 *)((u8 *)(buf) + (pos))))) #define LVAL(buf,pos) \ - (le64_to_cpu(get_unaligned((u64 *)((u8 *)(buf) + (pos))))) + (le64_to_cpu(get_unaligned((__le64 *)((u8 *)(buf) + (pos))))) #define WSET(buf,pos,val) \ - put_unaligned(cpu_to_le16((u16)(val)), (u16 *)((u8 *)(buf) + (pos))) + put_unaligned(cpu_to_le16((u16)(val)), (__le16 *)((u8 *)(buf) + (pos))) #define DSET(buf,pos,val) \ - put_unaligned(cpu_to_le32((u32)(val)), (u32 *)((u8 *)(buf) + (pos))) + put_unaligned(cpu_to_le32((u32)(val)), (__le32 *)((u8 *)(buf) + (pos))) #define LSET(buf,pos,val) \ - put_unaligned(cpu_to_le64((u64)(val)), (u64 *)((u8 *)(buf) + (pos))) + put_unaligned(cpu_to_le64((u64)(val)), (__le64 *)((u8 *)(buf) + (pos))) /* where to find the base of the SMB packet proper */ #define smb_base(buf) ((u8 *)(((u8 *)(buf))+4)) -- cgit v1.2.3 From d136fe7243081a45a141bb297a7b7a627ab60fa9 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Wed, 28 Dec 2005 22:27:10 +0300 Subject: [PATCH] Finish annotations of struct vlan_ethhdr Signed-off-by: Alexey Dobriyan Signed-off-by: Al Viro Acked-by: David S. Miller Signed-off-by: Linus Torvalds --- include/linux/if_vlan.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index ab2740832742..35cb38573583 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -44,7 +44,7 @@ struct vlan_ethhdr { unsigned char h_source[ETH_ALEN]; /* source ether addr */ __be16 h_vlan_proto; /* Should always be 0x8100 */ __be16 h_vlan_TCI; /* Encapsulates priority and VLAN ID */ - unsigned short h_vlan_encapsulated_proto; /* packet type ID field (or len) */ + __be16 h_vlan_encapsulated_proto; /* packet type ID field (or len) */ }; #include -- cgit v1.2.3 From 44aa5359be589f9cbe9cf0d5c97e22b27a04c7d3 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 13 Aug 2006 01:54:30 -0400 Subject: [PATCH] ufs endianness annotations Signed-off-by: Al Viro Signed-off-by: Linus Torvalds --- include/linux/ufs_fs.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ufs_fs.h b/include/linux/ufs_fs.h index fc62887c5206..61eef508b041 100644 --- a/include/linux/ufs_fs.h +++ b/include/linux/ufs_fs.h @@ -351,6 +351,14 @@ struct ufs2_csum_total { __fs64 cs_spare[3]; /* future expansion */ }; +struct ufs_csum_core { + __u64 cs_ndir; /* number of directories */ + __u64 cs_nbfree; /* number of free blocks */ + __u64 cs_nifree; /* number of free inodes */ + __u64 cs_nffree; /* number of free frags */ + __u64 cs_numclusters; /* number of free clusters */ +}; + /* * File system flags */ @@ -715,7 +723,7 @@ struct ufs_cg_private_info { struct ufs_sb_private_info { struct ufs_buffer_head s_ubh; /* buffer containing super block */ - struct ufs2_csum_total cs_total; + struct ufs_csum_core cs_total; __u32 s_sblkno; /* offset of super-blocks in filesys */ __u32 s_cblkno; /* offset of cg-block in filesys */ __u32 s_iblkno; /* offset of inode-blocks in filesys */ -- cgit v1.2.3 From 4dfbb9d8c6cbfc32faa5c71145bd2a43e1f8237c Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 11 Oct 2006 01:45:14 -0400 Subject: Lockdep: add lockdep_set_class_and_subclass() and lockdep_set_subclass() This annotation makes it possible to assign a subclass on lock init. This annotation is meant to reduce the _nested() annotations by assigning a default subclass. One could do without this annotation and rely on lockdep_set_class() exclusively, but that would require a manual stack of struct lock_class_key objects. Signed-off-by: Peter Zijlstra Signed-off-by: Dmitry Torokhov --- include/linux/lockdep.h | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 1314ca0f29be..14fec2a23b2e 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -202,7 +202,7 @@ extern int lockdep_internal(void); */ extern void lockdep_init_map(struct lockdep_map *lock, const char *name, - struct lock_class_key *key); + struct lock_class_key *key, int subclass); /* * Reinitialize a lock key - for cases where there is special locking or @@ -211,9 +211,14 @@ extern void lockdep_init_map(struct lockdep_map *lock, const char *name, * or they are too narrow (they suffer from a false class-split): */ #define lockdep_set_class(lock, key) \ - lockdep_init_map(&(lock)->dep_map, #key, key) + lockdep_init_map(&(lock)->dep_map, #key, key, 0) #define lockdep_set_class_and_name(lock, key, name) \ - lockdep_init_map(&(lock)->dep_map, name, key) + lockdep_init_map(&(lock)->dep_map, name, key, 0) +#define lockdep_set_class_and_subclass(lock, key, sub) \ + lockdep_init_map(&(lock)->dep_map, #key, key, sub) +#define lockdep_set_subclass(lock, sub) \ + lockdep_init_map(&(lock)->dep_map, #lock, \ + (lock)->dep_map.key, sub) /* * Acquire a lock. @@ -257,10 +262,12 @@ static inline int lockdep_internal(void) # define lock_release(l, n, i) do { } while (0) # define lockdep_init() do { } while (0) # define lockdep_info() do { } while (0) -# define lockdep_init_map(lock, name, key) do { (void)(key); } while (0) +# define lockdep_init_map(lock, name, key, sub) do { (void)(key); } while (0) # define lockdep_set_class(lock, key) do { (void)(key); } while (0) # define lockdep_set_class_and_name(lock, key, name) \ do { (void)(key); } while (0) +#define lockdep_set_class_and_subclass(lock, key, sub) \ + do { (void)(key); } while (0) # define INIT_LOCKDEP # define lockdep_reset() do { debug_locks = 1; } while (0) # define lockdep_free_key_range(start, size) do { } while (0) -- cgit v1.2.3 From 88aa0103e408616e433c209e80169ab8d6eda99e Mon Sep 17 00:00:00 2001 From: Jiri Kosina Date: Wed, 11 Oct 2006 01:45:31 -0400 Subject: Input: serio - add lockdep annotations Signed-off-by: Jiri Kosina Acked-by: Peter Zijlstra Signed-off-by: Dmitry Torokhov --- include/linux/serio.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/serio.h b/include/linux/serio.h index 3a697cc6ecae..b99c5ca9708d 100644 --- a/include/linux/serio.h +++ b/include/linux/serio.h @@ -41,6 +41,7 @@ struct serio { void (*stop)(struct serio *); struct serio *parent, *child; + unsigned int depth; /* level of nesting in serio hierarchy */ struct serio_driver *drv; /* accessed from interrupt, must be protected by serio->lock and serio->sem */ struct mutex drv_mutex; /* protects serio->drv so attributes can pin driver */ -- cgit v1.2.3 From 502717f4e112b18d9c37753a32f675bec9f2838b Mon Sep 17 00:00:00 2001 From: "Chen, Kenneth W" Date: Wed, 11 Oct 2006 01:20:46 -0700 Subject: [PATCH] hugetlb: fix linked list corruption in unmap_hugepage_range() commit fe1668ae5bf0145014c71797febd9ad5670d5d05 causes kernel to oops with libhugetlbfs test suite. The problem is that hugetlb pages can be shared by multiple mappings. Multiple threads can fight over page->lru in the unmap path and bad things happen. We now serialize __unmap_hugepage_range to void concurrent linked list manipulation. Such serialization is also needed for shared page table page on hugetlb area. This patch will fixed the bug and also serve as a prepatch for shared page table. Signed-off-by: Ken Chen Cc: Hugh Dickins Cc: David Gibson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index c25a38d8f600..5081d27bfa27 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -17,6 +17,7 @@ int hugetlb_sysctl_handler(struct ctl_table *, int, struct file *, void __user * int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_area_struct *); int follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *, struct page **, struct vm_area_struct **, unsigned long *, int *, int); void unmap_hugepage_range(struct vm_area_struct *, unsigned long, unsigned long); +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 *); -- cgit v1.2.3 From ac27a0ec112a089f1a5102bc8dffc79c8c815571 Mon Sep 17 00:00:00 2001 From: Dave Kleikamp Date: Wed, 11 Oct 2006 01:20:50 -0700 Subject: [PATCH] ext4: initial copy of files from ext3 Start of the ext4 patch series. See Documentation/filesystems/ext4.txt for details. This is a simple copy of the files in fs/ext3 to fs/ext4 and /usr/incude/linux/ext3* to /usr/include/ex4* Signed-off-by: Dave Kleikamp Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ext4_fs.h | 885 +++++++++++++++++++++++++++++++++++++++++++++ include/linux/ext4_fs_i.h | 147 ++++++++ include/linux/ext4_fs_sb.h | 83 +++++ include/linux/ext4_jbd.h | 268 ++++++++++++++ 4 files changed, 1383 insertions(+) create mode 100644 include/linux/ext4_fs.h create mode 100644 include/linux/ext4_fs_i.h create mode 100644 include/linux/ext4_fs_sb.h create mode 100644 include/linux/ext4_jbd.h (limited to 'include/linux') diff --git a/include/linux/ext4_fs.h b/include/linux/ext4_fs.h new file mode 100644 index 000000000000..11cca1bdc0c7 --- /dev/null +++ b/include/linux/ext4_fs.h @@ -0,0 +1,885 @@ +/* + * linux/include/linux/ext3_fs.h + * + * Copyright (C) 1992, 1993, 1994, 1995 + * Remy Card (card@masi.ibp.fr) + * Laboratoire MASI - Institut Blaise Pascal + * Universite Pierre et Marie Curie (Paris VI) + * + * from + * + * linux/include/linux/minix_fs.h + * + * Copyright (C) 1991, 1992 Linus Torvalds + */ + +#ifndef _LINUX_EXT3_FS_H +#define _LINUX_EXT3_FS_H + +#include +#include + +/* + * The second extended filesystem constants/structures + */ + +/* + * Define EXT3FS_DEBUG to produce debug messages + */ +#undef EXT3FS_DEBUG + +/* + * Define EXT3_RESERVATION to reserve data blocks for expanding files + */ +#define EXT3_DEFAULT_RESERVE_BLOCKS 8 +/*max window size: 1024(direct blocks) + 3([t,d]indirect blocks) */ +#define EXT3_MAX_RESERVE_BLOCKS 1027 +#define EXT3_RESERVE_WINDOW_NOT_ALLOCATED 0 +/* + * Always enable hashed directories + */ +#define CONFIG_EXT3_INDEX + +/* + * Debug code + */ +#ifdef EXT3FS_DEBUG +#define ext3_debug(f, a...) \ + do { \ + printk (KERN_DEBUG "EXT3-fs DEBUG (%s, %d): %s:", \ + __FILE__, __LINE__, __FUNCTION__); \ + printk (KERN_DEBUG f, ## a); \ + } while (0) +#else +#define ext3_debug(f, a...) do {} while (0) +#endif + +/* + * Special inodes numbers + */ +#define EXT3_BAD_INO 1 /* Bad blocks inode */ +#define EXT3_ROOT_INO 2 /* Root inode */ +#define EXT3_BOOT_LOADER_INO 5 /* Boot loader inode */ +#define EXT3_UNDEL_DIR_INO 6 /* Undelete directory inode */ +#define EXT3_RESIZE_INO 7 /* Reserved group descriptors inode */ +#define EXT3_JOURNAL_INO 8 /* Journal inode */ + +/* First non-reserved inode for old ext3 filesystems */ +#define EXT3_GOOD_OLD_FIRST_INO 11 + +/* + * Maximal count of links to a file + */ +#define EXT3_LINK_MAX 32000 + +/* + * Macro-instructions used to manage several block sizes + */ +#define EXT3_MIN_BLOCK_SIZE 1024 +#define EXT3_MAX_BLOCK_SIZE 4096 +#define EXT3_MIN_BLOCK_LOG_SIZE 10 +#ifdef __KERNEL__ +# define EXT3_BLOCK_SIZE(s) ((s)->s_blocksize) +#else +# define EXT3_BLOCK_SIZE(s) (EXT3_MIN_BLOCK_SIZE << (s)->s_log_block_size) +#endif +#define EXT3_ADDR_PER_BLOCK(s) (EXT3_BLOCK_SIZE(s) / sizeof (__u32)) +#ifdef __KERNEL__ +# define EXT3_BLOCK_SIZE_BITS(s) ((s)->s_blocksize_bits) +#else +# define EXT3_BLOCK_SIZE_BITS(s) ((s)->s_log_block_size + 10) +#endif +#ifdef __KERNEL__ +#define EXT3_ADDR_PER_BLOCK_BITS(s) (EXT3_SB(s)->s_addr_per_block_bits) +#define EXT3_INODE_SIZE(s) (EXT3_SB(s)->s_inode_size) +#define EXT3_FIRST_INO(s) (EXT3_SB(s)->s_first_ino) +#else +#define EXT3_INODE_SIZE(s) (((s)->s_rev_level == EXT3_GOOD_OLD_REV) ? \ + EXT3_GOOD_OLD_INODE_SIZE : \ + (s)->s_inode_size) +#define EXT3_FIRST_INO(s) (((s)->s_rev_level == EXT3_GOOD_OLD_REV) ? \ + EXT3_GOOD_OLD_FIRST_INO : \ + (s)->s_first_ino) +#endif + +/* + * Macro-instructions used to manage fragments + */ +#define EXT3_MIN_FRAG_SIZE 1024 +#define EXT3_MAX_FRAG_SIZE 4096 +#define EXT3_MIN_FRAG_LOG_SIZE 10 +#ifdef __KERNEL__ +# define EXT3_FRAG_SIZE(s) (EXT3_SB(s)->s_frag_size) +# define EXT3_FRAGS_PER_BLOCK(s) (EXT3_SB(s)->s_frags_per_block) +#else +# define EXT3_FRAG_SIZE(s) (EXT3_MIN_FRAG_SIZE << (s)->s_log_frag_size) +# define EXT3_FRAGS_PER_BLOCK(s) (EXT3_BLOCK_SIZE(s) / EXT3_FRAG_SIZE(s)) +#endif + +/* + * Structure of a blocks group descriptor + */ +struct ext3_group_desc +{ + __le32 bg_block_bitmap; /* Blocks bitmap block */ + __le32 bg_inode_bitmap; /* Inodes bitmap block */ + __le32 bg_inode_table; /* Inodes table block */ + __le16 bg_free_blocks_count; /* Free blocks count */ + __le16 bg_free_inodes_count; /* Free inodes count */ + __le16 bg_used_dirs_count; /* Directories count */ + __u16 bg_pad; + __le32 bg_reserved[3]; +}; + +/* + * Macro-instructions used to manage group descriptors + */ +#ifdef __KERNEL__ +# define EXT3_BLOCKS_PER_GROUP(s) (EXT3_SB(s)->s_blocks_per_group) +# define EXT3_DESC_PER_BLOCK(s) (EXT3_SB(s)->s_desc_per_block) +# define EXT3_INODES_PER_GROUP(s) (EXT3_SB(s)->s_inodes_per_group) +# define EXT3_DESC_PER_BLOCK_BITS(s) (EXT3_SB(s)->s_desc_per_block_bits) +#else +# define EXT3_BLOCKS_PER_GROUP(s) ((s)->s_blocks_per_group) +# define EXT3_DESC_PER_BLOCK(s) (EXT3_BLOCK_SIZE(s) / sizeof (struct ext3_group_desc)) +# define EXT3_INODES_PER_GROUP(s) ((s)->s_inodes_per_group) +#endif + +/* + * Constants relative to the data blocks + */ +#define EXT3_NDIR_BLOCKS 12 +#define EXT3_IND_BLOCK EXT3_NDIR_BLOCKS +#define EXT3_DIND_BLOCK (EXT3_IND_BLOCK + 1) +#define EXT3_TIND_BLOCK (EXT3_DIND_BLOCK + 1) +#define EXT3_N_BLOCKS (EXT3_TIND_BLOCK + 1) + +/* + * Inode flags + */ +#define EXT3_SECRM_FL 0x00000001 /* Secure deletion */ +#define EXT3_UNRM_FL 0x00000002 /* Undelete */ +#define EXT3_COMPR_FL 0x00000004 /* Compress file */ +#define EXT3_SYNC_FL 0x00000008 /* Synchronous updates */ +#define EXT3_IMMUTABLE_FL 0x00000010 /* Immutable file */ +#define EXT3_APPEND_FL 0x00000020 /* writes to file may only append */ +#define EXT3_NODUMP_FL 0x00000040 /* do not dump file */ +#define EXT3_NOATIME_FL 0x00000080 /* do not update atime */ +/* Reserved for compression usage... */ +#define EXT3_DIRTY_FL 0x00000100 +#define EXT3_COMPRBLK_FL 0x00000200 /* One or more compressed clusters */ +#define EXT3_NOCOMPR_FL 0x00000400 /* Don't compress */ +#define EXT3_ECOMPR_FL 0x00000800 /* Compression error */ +/* End compression flags --- maybe not all used */ +#define EXT3_INDEX_FL 0x00001000 /* hash-indexed directory */ +#define EXT3_IMAGIC_FL 0x00002000 /* AFS directory */ +#define EXT3_JOURNAL_DATA_FL 0x00004000 /* file data should be journaled */ +#define EXT3_NOTAIL_FL 0x00008000 /* file tail should not be merged */ +#define EXT3_DIRSYNC_FL 0x00010000 /* dirsync behaviour (directories only) */ +#define EXT3_TOPDIR_FL 0x00020000 /* Top of directory hierarchies*/ +#define EXT3_RESERVED_FL 0x80000000 /* reserved for ext3 lib */ + +#define EXT3_FL_USER_VISIBLE 0x0003DFFF /* User visible flags */ +#define EXT3_FL_USER_MODIFIABLE 0x000380FF /* User modifiable flags */ + +/* + * Inode dynamic state flags + */ +#define EXT3_STATE_JDATA 0x00000001 /* journaled data exists */ +#define EXT3_STATE_NEW 0x00000002 /* inode is newly created */ +#define EXT3_STATE_XATTR 0x00000004 /* has in-inode xattrs */ + +/* Used to pass group descriptor data when online resize is done */ +struct ext3_new_group_input { + __u32 group; /* Group number for this data */ + __u32 block_bitmap; /* Absolute block number of block bitmap */ + __u32 inode_bitmap; /* Absolute block number of inode bitmap */ + __u32 inode_table; /* Absolute block number of inode table start */ + __u32 blocks_count; /* Total number of blocks in this group */ + __u16 reserved_blocks; /* Number of reserved blocks in this group */ + __u16 unused; +}; + +/* The struct ext3_new_group_input in kernel space, with free_blocks_count */ +struct ext3_new_group_data { + __u32 group; + __u32 block_bitmap; + __u32 inode_bitmap; + __u32 inode_table; + __u32 blocks_count; + __u16 reserved_blocks; + __u16 unused; + __u32 free_blocks_count; +}; + + +/* + * ioctl commands + */ +#define EXT3_IOC_GETFLAGS FS_IOC_GETFLAGS +#define EXT3_IOC_SETFLAGS FS_IOC_SETFLAGS +#define EXT3_IOC_GETVERSION _IOR('f', 3, long) +#define EXT3_IOC_SETVERSION _IOW('f', 4, long) +#define EXT3_IOC_GROUP_EXTEND _IOW('f', 7, unsigned long) +#define EXT3_IOC_GROUP_ADD _IOW('f', 8,struct ext3_new_group_input) +#define EXT3_IOC_GETVERSION_OLD FS_IOC_GETVERSION +#define EXT3_IOC_SETVERSION_OLD FS_IOC_SETVERSION +#ifdef CONFIG_JBD_DEBUG +#define EXT3_IOC_WAIT_FOR_READONLY _IOR('f', 99, long) +#endif +#define EXT3_IOC_GETRSVSZ _IOR('f', 5, long) +#define EXT3_IOC_SETRSVSZ _IOW('f', 6, long) + +/* + * ioctl commands in 32 bit emulation + */ +#define EXT3_IOC32_GETFLAGS FS_IOC32_GETFLAGS +#define EXT3_IOC32_SETFLAGS FS_IOC32_SETFLAGS +#define EXT3_IOC32_GETVERSION _IOR('f', 3, int) +#define EXT3_IOC32_SETVERSION _IOW('f', 4, int) +#define EXT3_IOC32_GETRSVSZ _IOR('f', 5, int) +#define EXT3_IOC32_SETRSVSZ _IOW('f', 6, int) +#define EXT3_IOC32_GROUP_EXTEND _IOW('f', 7, unsigned int) +#ifdef CONFIG_JBD_DEBUG +#define EXT3_IOC32_WAIT_FOR_READONLY _IOR('f', 99, int) +#endif +#define EXT3_IOC32_GETVERSION_OLD FS_IOC32_GETVERSION +#define EXT3_IOC32_SETVERSION_OLD FS_IOC32_SETVERSION + + +/* + * Mount options + */ +struct ext3_mount_options { + unsigned long s_mount_opt; + uid_t s_resuid; + gid_t s_resgid; + unsigned long s_commit_interval; +#ifdef CONFIG_QUOTA + int s_jquota_fmt; + char *s_qf_names[MAXQUOTAS]; +#endif +}; + +/* + * Structure of an inode on the disk + */ +struct ext3_inode { + __le16 i_mode; /* File mode */ + __le16 i_uid; /* Low 16 bits of Owner Uid */ + __le32 i_size; /* Size in bytes */ + __le32 i_atime; /* Access time */ + __le32 i_ctime; /* Creation time */ + __le32 i_mtime; /* Modification time */ + __le32 i_dtime; /* Deletion Time */ + __le16 i_gid; /* Low 16 bits of Group Id */ + __le16 i_links_count; /* Links count */ + __le32 i_blocks; /* Blocks count */ + __le32 i_flags; /* File flags */ + union { + struct { + __u32 l_i_reserved1; + } linux1; + struct { + __u32 h_i_translator; + } hurd1; + struct { + __u32 m_i_reserved1; + } masix1; + } osd1; /* OS dependent 1 */ + __le32 i_block[EXT3_N_BLOCKS];/* Pointers to blocks */ + __le32 i_generation; /* File version (for NFS) */ + __le32 i_file_acl; /* File ACL */ + __le32 i_dir_acl; /* Directory ACL */ + __le32 i_faddr; /* Fragment address */ + union { + struct { + __u8 l_i_frag; /* Fragment number */ + __u8 l_i_fsize; /* Fragment size */ + __u16 i_pad1; + __le16 l_i_uid_high; /* these 2 fields */ + __le16 l_i_gid_high; /* were reserved2[0] */ + __u32 l_i_reserved2; + } linux2; + struct { + __u8 h_i_frag; /* Fragment number */ + __u8 h_i_fsize; /* Fragment size */ + __u16 h_i_mode_high; + __u16 h_i_uid_high; + __u16 h_i_gid_high; + __u32 h_i_author; + } hurd2; + struct { + __u8 m_i_frag; /* Fragment number */ + __u8 m_i_fsize; /* Fragment size */ + __u16 m_pad1; + __u32 m_i_reserved2[2]; + } masix2; + } osd2; /* OS dependent 2 */ + __le16 i_extra_isize; + __le16 i_pad1; +}; + +#define i_size_high i_dir_acl + +#if defined(__KERNEL__) || defined(__linux__) +#define i_reserved1 osd1.linux1.l_i_reserved1 +#define i_frag osd2.linux2.l_i_frag +#define i_fsize osd2.linux2.l_i_fsize +#define i_uid_low i_uid +#define i_gid_low i_gid +#define i_uid_high osd2.linux2.l_i_uid_high +#define i_gid_high osd2.linux2.l_i_gid_high +#define i_reserved2 osd2.linux2.l_i_reserved2 + +#elif defined(__GNU__) + +#define i_translator osd1.hurd1.h_i_translator +#define i_frag osd2.hurd2.h_i_frag; +#define i_fsize osd2.hurd2.h_i_fsize; +#define i_uid_high osd2.hurd2.h_i_uid_high +#define i_gid_high osd2.hurd2.h_i_gid_high +#define i_author osd2.hurd2.h_i_author + +#elif defined(__masix__) + +#define i_reserved1 osd1.masix1.m_i_reserved1 +#define i_frag osd2.masix2.m_i_frag +#define i_fsize osd2.masix2.m_i_fsize +#define i_reserved2 osd2.masix2.m_i_reserved2 + +#endif /* defined(__KERNEL__) || defined(__linux__) */ + +/* + * File system states + */ +#define EXT3_VALID_FS 0x0001 /* Unmounted cleanly */ +#define EXT3_ERROR_FS 0x0002 /* Errors detected */ +#define EXT3_ORPHAN_FS 0x0004 /* Orphans being recovered */ + +/* + * Mount flags + */ +#define EXT3_MOUNT_CHECK 0x00001 /* Do mount-time checks */ +#define EXT3_MOUNT_OLDALLOC 0x00002 /* Don't use the new Orlov allocator */ +#define EXT3_MOUNT_GRPID 0x00004 /* Create files with directory's group */ +#define EXT3_MOUNT_DEBUG 0x00008 /* Some debugging messages */ +#define EXT3_MOUNT_ERRORS_CONT 0x00010 /* Continue on errors */ +#define EXT3_MOUNT_ERRORS_RO 0x00020 /* Remount fs ro on errors */ +#define EXT3_MOUNT_ERRORS_PANIC 0x00040 /* Panic on errors */ +#define EXT3_MOUNT_MINIX_DF 0x00080 /* Mimics the Minix statfs */ +#define EXT3_MOUNT_NOLOAD 0x00100 /* Don't use existing journal*/ +#define EXT3_MOUNT_ABORT 0x00200 /* Fatal error detected */ +#define EXT3_MOUNT_DATA_FLAGS 0x00C00 /* Mode for data writes: */ +#define EXT3_MOUNT_JOURNAL_DATA 0x00400 /* Write data to journal */ +#define EXT3_MOUNT_ORDERED_DATA 0x00800 /* Flush data before commit */ +#define EXT3_MOUNT_WRITEBACK_DATA 0x00C00 /* No data ordering */ +#define EXT3_MOUNT_UPDATE_JOURNAL 0x01000 /* Update the journal format */ +#define EXT3_MOUNT_NO_UID32 0x02000 /* Disable 32-bit UIDs */ +#define EXT3_MOUNT_XATTR_USER 0x04000 /* Extended user attributes */ +#define EXT3_MOUNT_POSIX_ACL 0x08000 /* POSIX Access Control Lists */ +#define EXT3_MOUNT_RESERVATION 0x10000 /* Preallocation */ +#define EXT3_MOUNT_BARRIER 0x20000 /* Use block barriers */ +#define EXT3_MOUNT_NOBH 0x40000 /* No bufferheads */ +#define EXT3_MOUNT_QUOTA 0x80000 /* Some quota option set */ +#define EXT3_MOUNT_USRQUOTA 0x100000 /* "old" user quota */ +#define EXT3_MOUNT_GRPQUOTA 0x200000 /* "old" group quota */ + +/* Compatibility, for having both ext2_fs.h and ext3_fs.h included at once */ +#ifndef _LINUX_EXT2_FS_H +#define clear_opt(o, opt) o &= ~EXT3_MOUNT_##opt +#define set_opt(o, opt) o |= EXT3_MOUNT_##opt +#define test_opt(sb, opt) (EXT3_SB(sb)->s_mount_opt & \ + EXT3_MOUNT_##opt) +#else +#define EXT2_MOUNT_NOLOAD EXT3_MOUNT_NOLOAD +#define EXT2_MOUNT_ABORT EXT3_MOUNT_ABORT +#define EXT2_MOUNT_DATA_FLAGS EXT3_MOUNT_DATA_FLAGS +#endif + +#define ext3_set_bit ext2_set_bit +#define ext3_set_bit_atomic ext2_set_bit_atomic +#define ext3_clear_bit ext2_clear_bit +#define ext3_clear_bit_atomic ext2_clear_bit_atomic +#define ext3_test_bit ext2_test_bit +#define ext3_find_first_zero_bit ext2_find_first_zero_bit +#define ext3_find_next_zero_bit ext2_find_next_zero_bit + +/* + * Maximal mount counts between two filesystem checks + */ +#define EXT3_DFL_MAX_MNT_COUNT 20 /* Allow 20 mounts */ +#define EXT3_DFL_CHECKINTERVAL 0 /* Don't use interval check */ + +/* + * Behaviour when detecting errors + */ +#define EXT3_ERRORS_CONTINUE 1 /* Continue execution */ +#define EXT3_ERRORS_RO 2 /* Remount fs read-only */ +#define EXT3_ERRORS_PANIC 3 /* Panic */ +#define EXT3_ERRORS_DEFAULT EXT3_ERRORS_CONTINUE + +/* + * Structure of the super block + */ +struct ext3_super_block { +/*00*/ __le32 s_inodes_count; /* Inodes count */ + __le32 s_blocks_count; /* Blocks count */ + __le32 s_r_blocks_count; /* Reserved blocks count */ + __le32 s_free_blocks_count; /* Free blocks count */ +/*10*/ __le32 s_free_inodes_count; /* Free inodes count */ + __le32 s_first_data_block; /* First Data Block */ + __le32 s_log_block_size; /* Block size */ + __le32 s_log_frag_size; /* Fragment size */ +/*20*/ __le32 s_blocks_per_group; /* # Blocks per group */ + __le32 s_frags_per_group; /* # Fragments per group */ + __le32 s_inodes_per_group; /* # Inodes per group */ + __le32 s_mtime; /* Mount time */ +/*30*/ __le32 s_wtime; /* Write time */ + __le16 s_mnt_count; /* Mount count */ + __le16 s_max_mnt_count; /* Maximal mount count */ + __le16 s_magic; /* Magic signature */ + __le16 s_state; /* File system state */ + __le16 s_errors; /* Behaviour when detecting errors */ + __le16 s_minor_rev_level; /* minor revision level */ +/*40*/ __le32 s_lastcheck; /* time of last check */ + __le32 s_checkinterval; /* max. time between checks */ + __le32 s_creator_os; /* OS */ + __le32 s_rev_level; /* Revision level */ +/*50*/ __le16 s_def_resuid; /* Default uid for reserved blocks */ + __le16 s_def_resgid; /* Default gid for reserved blocks */ + /* + * These fields are for EXT3_DYNAMIC_REV superblocks only. + * + * Note: the difference between the compatible feature set and + * the incompatible feature set is that if there is a bit set + * in the incompatible feature set that the kernel doesn't + * know about, it should refuse to mount the filesystem. + * + * e2fsck's requirements are more strict; if it doesn't know + * about a feature in either the compatible or incompatible + * feature set, it must abort and not try to meddle with + * things it doesn't understand... + */ + __le32 s_first_ino; /* First non-reserved inode */ + __le16 s_inode_size; /* size of inode structure */ + __le16 s_block_group_nr; /* block group # of this superblock */ + __le32 s_feature_compat; /* compatible feature set */ +/*60*/ __le32 s_feature_incompat; /* incompatible feature set */ + __le32 s_feature_ro_compat; /* readonly-compatible feature set */ +/*68*/ __u8 s_uuid[16]; /* 128-bit uuid for volume */ +/*78*/ char s_volume_name[16]; /* volume name */ +/*88*/ char s_last_mounted[64]; /* directory where last mounted */ +/*C8*/ __le32 s_algorithm_usage_bitmap; /* For compression */ + /* + * Performance hints. Directory preallocation should only + * happen if the EXT3_FEATURE_COMPAT_DIR_PREALLOC flag is on. + */ + __u8 s_prealloc_blocks; /* Nr of blocks to try to preallocate*/ + __u8 s_prealloc_dir_blocks; /* Nr to preallocate for dirs */ + __le16 s_reserved_gdt_blocks; /* Per group desc for online growth */ + /* + * Journaling support valid if EXT3_FEATURE_COMPAT_HAS_JOURNAL set. + */ +/*D0*/ __u8 s_journal_uuid[16]; /* uuid of journal superblock */ +/*E0*/ __le32 s_journal_inum; /* inode number of journal file */ + __le32 s_journal_dev; /* device number of journal file */ + __le32 s_last_orphan; /* start of list of inodes to delete */ + __le32 s_hash_seed[4]; /* HTREE hash seed */ + __u8 s_def_hash_version; /* Default hash version to use */ + __u8 s_reserved_char_pad; + __u16 s_reserved_word_pad; + __le32 s_default_mount_opts; + __le32 s_first_meta_bg; /* First metablock block group */ + __u32 s_reserved[190]; /* Padding to the end of the block */ +}; + +#ifdef __KERNEL__ +#include +#include +static inline struct ext3_sb_info * EXT3_SB(struct super_block *sb) +{ + return sb->s_fs_info; +} +static inline struct ext3_inode_info *EXT3_I(struct inode *inode) +{ + return container_of(inode, struct ext3_inode_info, vfs_inode); +} + +static inline int ext3_valid_inum(struct super_block *sb, unsigned long ino) +{ + return ino == EXT3_ROOT_INO || + ino == EXT3_JOURNAL_INO || + ino == EXT3_RESIZE_INO || + (ino >= EXT3_FIRST_INO(sb) && + ino <= le32_to_cpu(EXT3_SB(sb)->s_es->s_inodes_count)); +} +#else +/* Assume that user mode programs are passing in an ext3fs superblock, not + * a kernel struct super_block. This will allow us to call the feature-test + * macros from user land. */ +#define EXT3_SB(sb) (sb) +#endif + +#define NEXT_ORPHAN(inode) EXT3_I(inode)->i_dtime + +/* + * Codes for operating systems + */ +#define EXT3_OS_LINUX 0 +#define EXT3_OS_HURD 1 +#define EXT3_OS_MASIX 2 +#define EXT3_OS_FREEBSD 3 +#define EXT3_OS_LITES 4 + +/* + * Revision levels + */ +#define EXT3_GOOD_OLD_REV 0 /* The good old (original) format */ +#define EXT3_DYNAMIC_REV 1 /* V2 format w/ dynamic inode sizes */ + +#define EXT3_CURRENT_REV EXT3_GOOD_OLD_REV +#define EXT3_MAX_SUPP_REV EXT3_DYNAMIC_REV + +#define EXT3_GOOD_OLD_INODE_SIZE 128 + +/* + * Feature set definitions + */ + +#define EXT3_HAS_COMPAT_FEATURE(sb,mask) \ + ( EXT3_SB(sb)->s_es->s_feature_compat & cpu_to_le32(mask) ) +#define EXT3_HAS_RO_COMPAT_FEATURE(sb,mask) \ + ( EXT3_SB(sb)->s_es->s_feature_ro_compat & cpu_to_le32(mask) ) +#define EXT3_HAS_INCOMPAT_FEATURE(sb,mask) \ + ( EXT3_SB(sb)->s_es->s_feature_incompat & cpu_to_le32(mask) ) +#define EXT3_SET_COMPAT_FEATURE(sb,mask) \ + EXT3_SB(sb)->s_es->s_feature_compat |= cpu_to_le32(mask) +#define EXT3_SET_RO_COMPAT_FEATURE(sb,mask) \ + EXT3_SB(sb)->s_es->s_feature_ro_compat |= cpu_to_le32(mask) +#define EXT3_SET_INCOMPAT_FEATURE(sb,mask) \ + EXT3_SB(sb)->s_es->s_feature_incompat |= cpu_to_le32(mask) +#define EXT3_CLEAR_COMPAT_FEATURE(sb,mask) \ + EXT3_SB(sb)->s_es->s_feature_compat &= ~cpu_to_le32(mask) +#define EXT3_CLEAR_RO_COMPAT_FEATURE(sb,mask) \ + EXT3_SB(sb)->s_es->s_feature_ro_compat &= ~cpu_to_le32(mask) +#define EXT3_CLEAR_INCOMPAT_FEATURE(sb,mask) \ + EXT3_SB(sb)->s_es->s_feature_incompat &= ~cpu_to_le32(mask) + +#define EXT3_FEATURE_COMPAT_DIR_PREALLOC 0x0001 +#define EXT3_FEATURE_COMPAT_IMAGIC_INODES 0x0002 +#define EXT3_FEATURE_COMPAT_HAS_JOURNAL 0x0004 +#define EXT3_FEATURE_COMPAT_EXT_ATTR 0x0008 +#define EXT3_FEATURE_COMPAT_RESIZE_INODE 0x0010 +#define EXT3_FEATURE_COMPAT_DIR_INDEX 0x0020 + +#define EXT3_FEATURE_RO_COMPAT_SPARSE_SUPER 0x0001 +#define EXT3_FEATURE_RO_COMPAT_LARGE_FILE 0x0002 +#define EXT3_FEATURE_RO_COMPAT_BTREE_DIR 0x0004 + +#define EXT3_FEATURE_INCOMPAT_COMPRESSION 0x0001 +#define EXT3_FEATURE_INCOMPAT_FILETYPE 0x0002 +#define EXT3_FEATURE_INCOMPAT_RECOVER 0x0004 /* Needs recovery */ +#define EXT3_FEATURE_INCOMPAT_JOURNAL_DEV 0x0008 /* Journal device */ +#define EXT3_FEATURE_INCOMPAT_META_BG 0x0010 + +#define EXT3_FEATURE_COMPAT_SUPP EXT2_FEATURE_COMPAT_EXT_ATTR +#define EXT3_FEATURE_INCOMPAT_SUPP (EXT3_FEATURE_INCOMPAT_FILETYPE| \ + EXT3_FEATURE_INCOMPAT_RECOVER| \ + EXT3_FEATURE_INCOMPAT_META_BG) +#define EXT3_FEATURE_RO_COMPAT_SUPP (EXT3_FEATURE_RO_COMPAT_SPARSE_SUPER| \ + EXT3_FEATURE_RO_COMPAT_LARGE_FILE| \ + EXT3_FEATURE_RO_COMPAT_BTREE_DIR) + +/* + * Default values for user and/or group using reserved blocks + */ +#define EXT3_DEF_RESUID 0 +#define EXT3_DEF_RESGID 0 + +/* + * Default mount options + */ +#define EXT3_DEFM_DEBUG 0x0001 +#define EXT3_DEFM_BSDGROUPS 0x0002 +#define EXT3_DEFM_XATTR_USER 0x0004 +#define EXT3_DEFM_ACL 0x0008 +#define EXT3_DEFM_UID16 0x0010 +#define EXT3_DEFM_JMODE 0x0060 +#define EXT3_DEFM_JMODE_DATA 0x0020 +#define EXT3_DEFM_JMODE_ORDERED 0x0040 +#define EXT3_DEFM_JMODE_WBACK 0x0060 + +/* + * Structure of a directory entry + */ +#define EXT3_NAME_LEN 255 + +struct ext3_dir_entry { + __le32 inode; /* Inode number */ + __le16 rec_len; /* Directory entry length */ + __le16 name_len; /* Name length */ + char name[EXT3_NAME_LEN]; /* File name */ +}; + +/* + * The new version of the directory entry. Since EXT3 structures are + * stored in intel byte order, and the name_len field could never be + * bigger than 255 chars, it's safe to reclaim the extra byte for the + * file_type field. + */ +struct ext3_dir_entry_2 { + __le32 inode; /* Inode number */ + __le16 rec_len; /* Directory entry length */ + __u8 name_len; /* Name length */ + __u8 file_type; + char name[EXT3_NAME_LEN]; /* File name */ +}; + +/* + * Ext3 directory file types. Only the low 3 bits are used. The + * other bits are reserved for now. + */ +#define EXT3_FT_UNKNOWN 0 +#define EXT3_FT_REG_FILE 1 +#define EXT3_FT_DIR 2 +#define EXT3_FT_CHRDEV 3 +#define EXT3_FT_BLKDEV 4 +#define EXT3_FT_FIFO 5 +#define EXT3_FT_SOCK 6 +#define EXT3_FT_SYMLINK 7 + +#define EXT3_FT_MAX 8 + +/* + * EXT3_DIR_PAD defines the directory entries boundaries + * + * NOTE: It must be a multiple of 4 + */ +#define EXT3_DIR_PAD 4 +#define EXT3_DIR_ROUND (EXT3_DIR_PAD - 1) +#define EXT3_DIR_REC_LEN(name_len) (((name_len) + 8 + EXT3_DIR_ROUND) & \ + ~EXT3_DIR_ROUND) +/* + * Hash Tree Directory indexing + * (c) Daniel Phillips, 2001 + */ + +#ifdef CONFIG_EXT3_INDEX + #define is_dx(dir) (EXT3_HAS_COMPAT_FEATURE(dir->i_sb, \ + EXT3_FEATURE_COMPAT_DIR_INDEX) && \ + (EXT3_I(dir)->i_flags & EXT3_INDEX_FL)) +#define EXT3_DIR_LINK_MAX(dir) (!is_dx(dir) && (dir)->i_nlink >= EXT3_LINK_MAX) +#define EXT3_DIR_LINK_EMPTY(dir) ((dir)->i_nlink == 2 || (dir)->i_nlink == 1) +#else + #define is_dx(dir) 0 +#define EXT3_DIR_LINK_MAX(dir) ((dir)->i_nlink >= EXT3_LINK_MAX) +#define EXT3_DIR_LINK_EMPTY(dir) ((dir)->i_nlink == 2) +#endif + +/* Legal values for the dx_root hash_version field: */ + +#define DX_HASH_LEGACY 0 +#define DX_HASH_HALF_MD4 1 +#define DX_HASH_TEA 2 + +#ifdef __KERNEL__ + +/* hash info structure used by the directory hash */ +struct dx_hash_info +{ + u32 hash; + u32 minor_hash; + int hash_version; + u32 *seed; +}; + +#define EXT3_HTREE_EOF 0x7fffffff + +/* + * Control parameters used by ext3_htree_next_block + */ +#define HASH_NB_ALWAYS 1 + + +/* + * Describe an inode's exact location on disk and in memory + */ +struct ext3_iloc +{ + struct buffer_head *bh; + unsigned long offset; + unsigned long block_group; +}; + +static inline struct ext3_inode *ext3_raw_inode(struct ext3_iloc *iloc) +{ + return (struct ext3_inode *) (iloc->bh->b_data + iloc->offset); +} + +/* + * This structure is stuffed into the struct file's private_data field + * for directories. It is where we put information so that we can do + * readdir operations in hash tree order. + */ +struct dir_private_info { + struct rb_root root; + struct rb_node *curr_node; + struct fname *extra_fname; + loff_t last_pos; + __u32 curr_hash; + __u32 curr_minor_hash; + __u32 next_hash; +}; + +/* calculate the first block number of the group */ +static inline ext3_fsblk_t +ext3_group_first_block_no(struct super_block *sb, unsigned long group_no) +{ + return group_no * (ext3_fsblk_t)EXT3_BLOCKS_PER_GROUP(sb) + + le32_to_cpu(EXT3_SB(sb)->s_es->s_first_data_block); +} + +/* + * Special error return code only used by dx_probe() and its callers. + */ +#define ERR_BAD_DX_DIR -75000 + +/* + * Function prototypes + */ + +/* + * Ok, these declarations are also in but none of the + * ext3 source programs needs to include it so they are duplicated here. + */ +# define NORET_TYPE /**/ +# define ATTRIB_NORET __attribute__((noreturn)) +# define NORET_AND noreturn, + +/* balloc.c */ +extern int ext3_bg_has_super(struct super_block *sb, int group); +extern unsigned long ext3_bg_num_gdb(struct super_block *sb, int group); +extern ext3_fsblk_t ext3_new_block (handle_t *handle, struct inode *inode, + ext3_fsblk_t goal, int *errp); +extern ext3_fsblk_t ext3_new_blocks (handle_t *handle, struct inode *inode, + ext3_fsblk_t goal, unsigned long *count, int *errp); +extern void ext3_free_blocks (handle_t *handle, struct inode *inode, + ext3_fsblk_t block, unsigned long count); +extern void ext3_free_blocks_sb (handle_t *handle, struct super_block *sb, + ext3_fsblk_t block, unsigned long count, + unsigned long *pdquot_freed_blocks); +extern ext3_fsblk_t ext3_count_free_blocks (struct super_block *); +extern void ext3_check_blocks_bitmap (struct super_block *); +extern struct ext3_group_desc * ext3_get_group_desc(struct super_block * sb, + unsigned int block_group, + struct buffer_head ** bh); +extern int ext3_should_retry_alloc(struct super_block *sb, int *retries); +extern void ext3_init_block_alloc_info(struct inode *); +extern void ext3_rsv_window_add(struct super_block *sb, struct ext3_reserve_window_node *rsv); + +/* dir.c */ +extern int ext3_check_dir_entry(const char *, struct inode *, + struct ext3_dir_entry_2 *, + struct buffer_head *, unsigned long); +extern int ext3_htree_store_dirent(struct file *dir_file, __u32 hash, + __u32 minor_hash, + struct ext3_dir_entry_2 *dirent); +extern void ext3_htree_free_dir_info(struct dir_private_info *p); + +/* fsync.c */ +extern int ext3_sync_file (struct file *, struct dentry *, int); + +/* hash.c */ +extern int ext3fs_dirhash(const char *name, int len, struct + dx_hash_info *hinfo); + +/* ialloc.c */ +extern struct inode * ext3_new_inode (handle_t *, struct inode *, int); +extern void ext3_free_inode (handle_t *, struct inode *); +extern struct inode * ext3_orphan_get (struct super_block *, unsigned long); +extern unsigned long ext3_count_free_inodes (struct super_block *); +extern unsigned long ext3_count_dirs (struct super_block *); +extern void ext3_check_inodes_bitmap (struct super_block *); +extern unsigned long ext3_count_free (struct buffer_head *, unsigned); + + +/* inode.c */ +int ext3_forget(handle_t *handle, int is_metadata, struct inode *inode, + struct buffer_head *bh, ext3_fsblk_t blocknr); +struct buffer_head * ext3_getblk (handle_t *, struct inode *, long, int, int *); +struct buffer_head * ext3_bread (handle_t *, struct inode *, int, int, int *); +int ext3_get_blocks_handle(handle_t *handle, struct inode *inode, + sector_t iblock, unsigned long maxblocks, struct buffer_head *bh_result, + int create, int extend_disksize); + +extern void ext3_read_inode (struct inode *); +extern int ext3_write_inode (struct inode *, int); +extern int ext3_setattr (struct dentry *, struct iattr *); +extern void ext3_delete_inode (struct inode *); +extern int ext3_sync_inode (handle_t *, struct inode *); +extern void ext3_discard_reservation (struct inode *); +extern void ext3_dirty_inode(struct inode *); +extern int ext3_change_inode_journal_flag(struct inode *, int); +extern int ext3_get_inode_loc(struct inode *, struct ext3_iloc *); +extern void ext3_truncate (struct inode *); +extern void ext3_set_inode_flags(struct inode *); +extern void ext3_set_aops(struct inode *inode); + +/* ioctl.c */ +extern int ext3_ioctl (struct inode *, struct file *, unsigned int, + unsigned long); +extern long ext3_compat_ioctl (struct file *, unsigned int, unsigned long); + +/* namei.c */ +extern int ext3_orphan_add(handle_t *, struct inode *); +extern int ext3_orphan_del(handle_t *, struct inode *); +extern int ext3_htree_fill_tree(struct file *dir_file, __u32 start_hash, + __u32 start_minor_hash, __u32 *next_hash); + +/* resize.c */ +extern int ext3_group_add(struct super_block *sb, + struct ext3_new_group_data *input); +extern int ext3_group_extend(struct super_block *sb, + struct ext3_super_block *es, + ext3_fsblk_t n_blocks_count); + +/* super.c */ +extern void ext3_error (struct super_block *, const char *, const char *, ...) + __attribute__ ((format (printf, 3, 4))); +extern void __ext3_std_error (struct super_block *, const char *, int); +extern void ext3_abort (struct super_block *, const char *, const char *, ...) + __attribute__ ((format (printf, 3, 4))); +extern void ext3_warning (struct super_block *, const char *, const char *, ...) + __attribute__ ((format (printf, 3, 4))); +extern void ext3_update_dynamic_rev (struct super_block *sb); + +#define ext3_std_error(sb, errno) \ +do { \ + if ((errno)) \ + __ext3_std_error((sb), __FUNCTION__, (errno)); \ +} while (0) + +/* + * Inodes and files operations + */ + +/* dir.c */ +extern const struct file_operations ext3_dir_operations; + +/* file.c */ +extern struct inode_operations ext3_file_inode_operations; +extern const struct file_operations ext3_file_operations; + +/* namei.c */ +extern struct inode_operations ext3_dir_inode_operations; +extern struct inode_operations ext3_special_inode_operations; + +/* symlink.c */ +extern struct inode_operations ext3_symlink_inode_operations; +extern struct inode_operations ext3_fast_symlink_inode_operations; + + +#endif /* __KERNEL__ */ + +#endif /* _LINUX_EXT3_FS_H */ diff --git a/include/linux/ext4_fs_i.h b/include/linux/ext4_fs_i.h new file mode 100644 index 000000000000..4395e5206746 --- /dev/null +++ b/include/linux/ext4_fs_i.h @@ -0,0 +1,147 @@ +/* + * linux/include/linux/ext3_fs_i.h + * + * Copyright (C) 1992, 1993, 1994, 1995 + * Remy Card (card@masi.ibp.fr) + * Laboratoire MASI - Institut Blaise Pascal + * Universite Pierre et Marie Curie (Paris VI) + * + * from + * + * linux/include/linux/minix_fs_i.h + * + * Copyright (C) 1991, 1992 Linus Torvalds + */ + +#ifndef _LINUX_EXT3_FS_I +#define _LINUX_EXT3_FS_I + +#include +#include +#include +#include + +/* data type for block offset of block group */ +typedef int ext3_grpblk_t; + +/* data type for filesystem-wide blocks number */ +typedef unsigned long ext3_fsblk_t; + +#define E3FSBLK "%lu" + +struct ext3_reserve_window { + ext3_fsblk_t _rsv_start; /* First byte reserved */ + ext3_fsblk_t _rsv_end; /* Last byte reserved or 0 */ +}; + +struct ext3_reserve_window_node { + struct rb_node rsv_node; + __u32 rsv_goal_size; + __u32 rsv_alloc_hit; + struct ext3_reserve_window rsv_window; +}; + +struct ext3_block_alloc_info { + /* information about reservation window */ + struct ext3_reserve_window_node rsv_window_node; + /* + * was i_next_alloc_block in ext3_inode_info + * is the logical (file-relative) number of the + * most-recently-allocated block in this file. + * We use this for detecting linearly ascending allocation requests. + */ + __u32 last_alloc_logical_block; + /* + * Was i_next_alloc_goal in ext3_inode_info + * is the *physical* companion to i_next_alloc_block. + * it the the physical block number of the block which was most-recentl + * allocated to this file. This give us the goal (target) for the next + * allocation when we detect linearly ascending requests. + */ + ext3_fsblk_t last_alloc_physical_block; +}; + +#define rsv_start rsv_window._rsv_start +#define rsv_end rsv_window._rsv_end + +/* + * third extended file system inode data in memory + */ +struct ext3_inode_info { + __le32 i_data[15]; /* unconverted */ + __u32 i_flags; +#ifdef EXT3_FRAGMENTS + __u32 i_faddr; + __u8 i_frag_no; + __u8 i_frag_size; +#endif + ext3_fsblk_t i_file_acl; + __u32 i_dir_acl; + __u32 i_dtime; + + /* + * i_block_group is the number of the block group which contains + * this file's inode. Constant across the lifetime of the inode, + * it is ued for making block allocation decisions - we try to + * place a file's data blocks near its inode block, and new inodes + * near to their parent directory's inode. + */ + __u32 i_block_group; + __u32 i_state; /* Dynamic state flags for ext3 */ + + /* block reservation info */ + struct ext3_block_alloc_info *i_block_alloc_info; + + __u32 i_dir_start_lookup; +#ifdef CONFIG_EXT3_FS_XATTR + /* + * Extended attributes can be read independently of the main file + * data. Taking i_mutex even when reading would cause contention + * between readers of EAs and writers of regular file data, so + * instead we synchronize on xattr_sem when reading or changing + * EAs. + */ + struct rw_semaphore xattr_sem; +#endif +#ifdef CONFIG_EXT3_FS_POSIX_ACL + struct posix_acl *i_acl; + struct posix_acl *i_default_acl; +#endif + + struct list_head i_orphan; /* unlinked but open inodes */ + + /* + * i_disksize keeps track of what the inode size is ON DISK, not + * in memory. During truncate, i_size is set to the new size by + * the VFS prior to calling ext3_truncate(), but the filesystem won't + * set i_disksize to 0 until the truncate is actually under way. + * + * The intent is that i_disksize always represents the blocks which + * are used by this file. This allows recovery to restart truncate + * on orphans if we crash during truncate. We actually write i_disksize + * into the on-disk inode when writing inodes out, instead of i_size. + * + * The only time when i_disksize and i_size may be different is when + * a truncate is in progress. The only things which change i_disksize + * are ext3_get_block (growth) and ext3_truncate (shrinkth). + */ + loff_t i_disksize; + + /* on-disk additional length */ + __u16 i_extra_isize; + + /* + * truncate_mutex is for serialising ext3_truncate() against + * ext3_getblock(). In the 2.4 ext2 design, great chunks of inode's + * data tree are chopped off during truncate. We can't do that in + * ext3 because whenever we perform intermediate commits during + * truncate, the inode and all the metadata blocks *must* be in a + * consistent state which allows truncation of the orphans to restart + * during recovery. Hence we must fix the get_block-vs-truncate race + * by other means, so we have truncate_mutex. + */ + struct mutex truncate_mutex; + struct inode vfs_inode; +}; + +#endif /* _LINUX_EXT3_FS_I */ diff --git a/include/linux/ext4_fs_sb.h b/include/linux/ext4_fs_sb.h new file mode 100644 index 000000000000..f61309c81cc4 --- /dev/null +++ b/include/linux/ext4_fs_sb.h @@ -0,0 +1,83 @@ +/* + * linux/include/linux/ext3_fs_sb.h + * + * Copyright (C) 1992, 1993, 1994, 1995 + * Remy Card (card@masi.ibp.fr) + * Laboratoire MASI - Institut Blaise Pascal + * Universite Pierre et Marie Curie (Paris VI) + * + * from + * + * linux/include/linux/minix_fs_sb.h + * + * Copyright (C) 1991, 1992 Linus Torvalds + */ + +#ifndef _LINUX_EXT3_FS_SB +#define _LINUX_EXT3_FS_SB + +#ifdef __KERNEL__ +#include +#include +#include +#include +#endif +#include + +/* + * third extended-fs super-block data in memory + */ +struct ext3_sb_info { + unsigned long s_frag_size; /* Size of a fragment in bytes */ + unsigned long s_frags_per_block;/* Number of fragments per block */ + unsigned long s_inodes_per_block;/* Number of inodes per block */ + unsigned long s_frags_per_group;/* Number of fragments in a group */ + unsigned long s_blocks_per_group;/* Number of blocks in a group */ + unsigned long s_inodes_per_group;/* Number of inodes in a group */ + unsigned long s_itb_per_group; /* Number of inode table blocks per group */ + unsigned long s_gdb_count; /* Number of group descriptor blocks */ + unsigned long s_desc_per_block; /* Number of group descriptors per block */ + unsigned long s_groups_count; /* Number of groups in the fs */ + struct buffer_head * s_sbh; /* Buffer containing the super block */ + struct ext3_super_block * s_es; /* Pointer to the super block in the buffer */ + struct buffer_head ** s_group_desc; + unsigned long s_mount_opt; + uid_t s_resuid; + gid_t s_resgid; + unsigned short s_mount_state; + unsigned short s_pad; + int s_addr_per_block_bits; + int s_desc_per_block_bits; + int s_inode_size; + int s_first_ino; + spinlock_t s_next_gen_lock; + u32 s_next_generation; + u32 s_hash_seed[4]; + int s_def_hash_version; + struct percpu_counter s_freeblocks_counter; + struct percpu_counter s_freeinodes_counter; + struct percpu_counter s_dirs_counter; + struct blockgroup_lock s_blockgroup_lock; + + /* root of the per fs reservation window tree */ + spinlock_t s_rsv_window_lock; + struct rb_root s_rsv_window_root; + struct ext3_reserve_window_node s_rsv_window_head; + + /* Journaling */ + struct inode * s_journal_inode; + struct journal_s * s_journal; + struct list_head s_orphan; + unsigned long s_commit_interval; + struct block_device *journal_bdev; +#ifdef CONFIG_JBD_DEBUG + struct timer_list turn_ro_timer; /* For turning read-only (crash simulation) */ + wait_queue_head_t ro_wait_queue; /* For people waiting for the fs to go read-only */ +#endif +#ifdef CONFIG_QUOTA + char *s_qf_names[MAXQUOTAS]; /* Names of quota files with journalled quota */ + int s_jquota_fmt; /* Format of quota to use */ +#endif +}; + +#endif /* _LINUX_EXT3_FS_SB */ diff --git a/include/linux/ext4_jbd.h b/include/linux/ext4_jbd.h new file mode 100644 index 000000000000..ce0e6109aff0 --- /dev/null +++ b/include/linux/ext4_jbd.h @@ -0,0 +1,268 @@ +/* + * linux/include/linux/ext3_jbd.h + * + * Written by Stephen C. Tweedie , 1999 + * + * Copyright 1998--1999 Red Hat corp --- All Rights Reserved + * + * This file is part of the Linux kernel and is made available under + * the terms of the GNU General Public License, version 2, or at your + * option, any later version, incorporated herein by reference. + * + * Ext3-specific journaling extensions. + */ + +#ifndef _LINUX_EXT3_JBD_H +#define _LINUX_EXT3_JBD_H + +#include +#include +#include + +#define EXT3_JOURNAL(inode) (EXT3_SB((inode)->i_sb)->s_journal) + +/* Define the number of blocks we need to account to a transaction to + * modify one block of data. + * + * We may have to touch one inode, one bitmap buffer, up to three + * indirection blocks, the group and superblock summaries, and the data + * block to complete the transaction. */ + +#define EXT3_SINGLEDATA_TRANS_BLOCKS 8U + +/* Extended attribute operations touch at most two data buffers, + * two bitmap buffers, and two group summaries, in addition to the inode + * and the superblock, which are already accounted for. */ + +#define EXT3_XATTR_TRANS_BLOCKS 6U + +/* Define the minimum size for a transaction which modifies data. This + * needs to take into account the fact that we may end up modifying two + * quota files too (one for the group, one for the user quota). The + * superblock only gets updated once, of course, so don't bother + * counting that again for the quota updates. */ + +#define EXT3_DATA_TRANS_BLOCKS(sb) (EXT3_SINGLEDATA_TRANS_BLOCKS + \ + EXT3_XATTR_TRANS_BLOCKS - 2 + \ + 2*EXT3_QUOTA_TRANS_BLOCKS(sb)) + +/* Delete operations potentially hit one directory's namespace plus an + * entire inode, plus arbitrary amounts of bitmap/indirection data. Be + * generous. We can grow the delete transaction later if necessary. */ + +#define EXT3_DELETE_TRANS_BLOCKS(sb) (2 * EXT3_DATA_TRANS_BLOCKS(sb) + 64) + +/* Define an arbitrary limit for the amount of data we will anticipate + * writing to any given transaction. For unbounded transactions such as + * write(2) and truncate(2) we can write more than this, but we always + * start off at the maximum transaction size and grow the transaction + * optimistically as we go. */ + +#define EXT3_MAX_TRANS_DATA 64U + +/* We break up a large truncate or write transaction once the handle's + * buffer credits gets this low, we need either to extend the + * transaction or to start a new one. Reserve enough space here for + * inode, bitmap, superblock, group and indirection updates for at least + * one block, plus two quota updates. Quota allocations are not + * needed. */ + +#define EXT3_RESERVE_TRANS_BLOCKS 12U + +#define EXT3_INDEX_EXTRA_TRANS_BLOCKS 8 + +#ifdef CONFIG_QUOTA +/* Amount of blocks needed for quota update - we know that the structure was + * allocated so we need to update only inode+data */ +#define EXT3_QUOTA_TRANS_BLOCKS(sb) (test_opt(sb, QUOTA) ? 2 : 0) +/* Amount of blocks needed for quota insert/delete - we do some block writes + * but inode, sb and group updates are done only once */ +#define EXT3_QUOTA_INIT_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_INIT_ALLOC*\ + (EXT3_SINGLEDATA_TRANS_BLOCKS-3)+3+DQUOT_INIT_REWRITE) : 0) +#define EXT3_QUOTA_DEL_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_DEL_ALLOC*\ + (EXT3_SINGLEDATA_TRANS_BLOCKS-3)+3+DQUOT_DEL_REWRITE) : 0) +#else +#define EXT3_QUOTA_TRANS_BLOCKS(sb) 0 +#define EXT3_QUOTA_INIT_BLOCKS(sb) 0 +#define EXT3_QUOTA_DEL_BLOCKS(sb) 0 +#endif + +int +ext3_mark_iloc_dirty(handle_t *handle, + struct inode *inode, + struct ext3_iloc *iloc); + +/* + * On success, We end up with an outstanding reference count against + * iloc->bh. This _must_ be cleaned up later. + */ + +int ext3_reserve_inode_write(handle_t *handle, struct inode *inode, + struct ext3_iloc *iloc); + +int ext3_mark_inode_dirty(handle_t *handle, struct inode *inode); + +/* + * Wrapper functions with which ext3 calls into JBD. The intent here is + * to allow these to be turned into appropriate stubs so ext3 can control + * ext2 filesystems, so ext2+ext3 systems only nee one fs. This work hasn't + * been done yet. + */ + +void ext3_journal_abort_handle(const char *caller, const char *err_fn, + struct buffer_head *bh, handle_t *handle, int err); + +static inline int +__ext3_journal_get_undo_access(const char *where, handle_t *handle, + struct buffer_head *bh) +{ + int err = journal_get_undo_access(handle, bh); + if (err) + ext3_journal_abort_handle(where, __FUNCTION__, bh, handle,err); + return err; +} + +static inline int +__ext3_journal_get_write_access(const char *where, handle_t *handle, + struct buffer_head *bh) +{ + int err = journal_get_write_access(handle, bh); + if (err) + ext3_journal_abort_handle(where, __FUNCTION__, bh, handle,err); + return err; +} + +static inline void +ext3_journal_release_buffer(handle_t *handle, struct buffer_head *bh) +{ + journal_release_buffer(handle, bh); +} + +static inline int +__ext3_journal_forget(const char *where, handle_t *handle, struct buffer_head *bh) +{ + int err = journal_forget(handle, bh); + if (err) + ext3_journal_abort_handle(where, __FUNCTION__, bh, handle,err); + return err; +} + +static inline int +__ext3_journal_revoke(const char *where, handle_t *handle, + unsigned long blocknr, struct buffer_head *bh) +{ + int err = journal_revoke(handle, blocknr, bh); + if (err) + ext3_journal_abort_handle(where, __FUNCTION__, bh, handle,err); + return err; +} + +static inline int +__ext3_journal_get_create_access(const char *where, + handle_t *handle, struct buffer_head *bh) +{ + int err = journal_get_create_access(handle, bh); + if (err) + ext3_journal_abort_handle(where, __FUNCTION__, bh, handle,err); + return err; +} + +static inline int +__ext3_journal_dirty_metadata(const char *where, + handle_t *handle, struct buffer_head *bh) +{ + int err = journal_dirty_metadata(handle, bh); + if (err) + ext3_journal_abort_handle(where, __FUNCTION__, bh, handle,err); + return err; +} + + +#define ext3_journal_get_undo_access(handle, bh) \ + __ext3_journal_get_undo_access(__FUNCTION__, (handle), (bh)) +#define ext3_journal_get_write_access(handle, bh) \ + __ext3_journal_get_write_access(__FUNCTION__, (handle), (bh)) +#define ext3_journal_revoke(handle, blocknr, bh) \ + __ext3_journal_revoke(__FUNCTION__, (handle), (blocknr), (bh)) +#define ext3_journal_get_create_access(handle, bh) \ + __ext3_journal_get_create_access(__FUNCTION__, (handle), (bh)) +#define ext3_journal_dirty_metadata(handle, bh) \ + __ext3_journal_dirty_metadata(__FUNCTION__, (handle), (bh)) +#define ext3_journal_forget(handle, bh) \ + __ext3_journal_forget(__FUNCTION__, (handle), (bh)) + +int ext3_journal_dirty_data(handle_t *handle, struct buffer_head *bh); + +handle_t *ext3_journal_start_sb(struct super_block *sb, int nblocks); +int __ext3_journal_stop(const char *where, handle_t *handle); + +static inline handle_t *ext3_journal_start(struct inode *inode, int nblocks) +{ + return ext3_journal_start_sb(inode->i_sb, nblocks); +} + +#define ext3_journal_stop(handle) \ + __ext3_journal_stop(__FUNCTION__, (handle)) + +static inline handle_t *ext3_journal_current_handle(void) +{ + return journal_current_handle(); +} + +static inline int ext3_journal_extend(handle_t *handle, int nblocks) +{ + return journal_extend(handle, nblocks); +} + +static inline int ext3_journal_restart(handle_t *handle, int nblocks) +{ + return journal_restart(handle, nblocks); +} + +static inline int ext3_journal_blocks_per_page(struct inode *inode) +{ + return journal_blocks_per_page(inode); +} + +static inline int ext3_journal_force_commit(journal_t *journal) +{ + return journal_force_commit(journal); +} + +/* super.c */ +int ext3_force_commit(struct super_block *sb); + +static inline int ext3_should_journal_data(struct inode *inode) +{ + if (!S_ISREG(inode->i_mode)) + return 1; + if (test_opt(inode->i_sb, DATA_FLAGS) == EXT3_MOUNT_JOURNAL_DATA) + return 1; + if (EXT3_I(inode)->i_flags & EXT3_JOURNAL_DATA_FL) + return 1; + return 0; +} + +static inline int ext3_should_order_data(struct inode *inode) +{ + if (!S_ISREG(inode->i_mode)) + return 0; + if (EXT3_I(inode)->i_flags & EXT3_JOURNAL_DATA_FL) + return 0; + if (test_opt(inode->i_sb, DATA_FLAGS) == EXT3_MOUNT_ORDERED_DATA) + return 1; + return 0; +} + +static inline int ext3_should_writeback_data(struct inode *inode) +{ + if (!S_ISREG(inode->i_mode)) + return 0; + if (EXT3_I(inode)->i_flags & EXT3_JOURNAL_DATA_FL) + return 0; + if (test_opt(inode->i_sb, DATA_FLAGS) == EXT3_MOUNT_WRITEBACK_DATA) + return 1; + return 0; +} + +#endif /* _LINUX_EXT3_JBD_H */ -- cgit v1.2.3 From 617ba13b31fbf505cc21799826639ef24ed94af0 Mon Sep 17 00:00:00 2001 From: Mingming Cao Date: Wed, 11 Oct 2006 01:20:53 -0700 Subject: [PATCH] ext4: rename ext4 symbols to avoid duplication of ext3 symbols Mingming Cao originally did this work, and Shaggy reproduced it using some scripts from her. Signed-off-by: Mingming Cao Signed-off-by: Dave Kleikamp Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ext4_fs.h | 702 ++++++++++++++++++++++----------------------- include/linux/ext4_fs_i.h | 56 ++-- include/linux/ext4_fs_sb.h | 14 +- include/linux/ext4_jbd.h | 160 +++++------ 4 files changed, 466 insertions(+), 466 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ext4_fs.h b/include/linux/ext4_fs.h index 11cca1bdc0c7..f582cd762caf 100644 --- a/include/linux/ext4_fs.h +++ b/include/linux/ext4_fs.h @@ -1,5 +1,5 @@ /* - * linux/include/linux/ext3_fs.h + * linux/include/linux/ext4_fs.h * * Copyright (C) 1992, 1993, 1994, 1995 * Remy Card (card@masi.ibp.fr) @@ -13,8 +13,8 @@ * Copyright (C) 1991, 1992 Linus Torvalds */ -#ifndef _LINUX_EXT3_FS_H -#define _LINUX_EXT3_FS_H +#ifndef _LINUX_EXT4_FS_H +#define _LINUX_EXT4_FS_H #include #include @@ -24,102 +24,102 @@ */ /* - * Define EXT3FS_DEBUG to produce debug messages + * Define EXT4FS_DEBUG to produce debug messages */ -#undef EXT3FS_DEBUG +#undef EXT4FS_DEBUG /* - * Define EXT3_RESERVATION to reserve data blocks for expanding files + * Define EXT4_RESERVATION to reserve data blocks for expanding files */ -#define EXT3_DEFAULT_RESERVE_BLOCKS 8 +#define EXT4_DEFAULT_RESERVE_BLOCKS 8 /*max window size: 1024(direct blocks) + 3([t,d]indirect blocks) */ -#define EXT3_MAX_RESERVE_BLOCKS 1027 -#define EXT3_RESERVE_WINDOW_NOT_ALLOCATED 0 +#define EXT4_MAX_RESERVE_BLOCKS 1027 +#define EXT4_RESERVE_WINDOW_NOT_ALLOCATED 0 /* * Always enable hashed directories */ -#define CONFIG_EXT3_INDEX +#define CONFIG_EXT4_INDEX /* * Debug code */ -#ifdef EXT3FS_DEBUG -#define ext3_debug(f, a...) \ +#ifdef EXT4FS_DEBUG +#define ext4_debug(f, a...) \ do { \ - printk (KERN_DEBUG "EXT3-fs DEBUG (%s, %d): %s:", \ + printk (KERN_DEBUG "EXT4-fs DEBUG (%s, %d): %s:", \ __FILE__, __LINE__, __FUNCTION__); \ printk (KERN_DEBUG f, ## a); \ } while (0) #else -#define ext3_debug(f, a...) do {} while (0) +#define ext4_debug(f, a...) do {} while (0) #endif /* * Special inodes numbers */ -#define EXT3_BAD_INO 1 /* Bad blocks inode */ -#define EXT3_ROOT_INO 2 /* Root inode */ -#define EXT3_BOOT_LOADER_INO 5 /* Boot loader inode */ -#define EXT3_UNDEL_DIR_INO 6 /* Undelete directory inode */ -#define EXT3_RESIZE_INO 7 /* Reserved group descriptors inode */ -#define EXT3_JOURNAL_INO 8 /* Journal inode */ +#define EXT4_BAD_INO 1 /* Bad blocks inode */ +#define EXT4_ROOT_INO 2 /* Root inode */ +#define EXT4_BOOT_LOADER_INO 5 /* Boot loader inode */ +#define EXT4_UNDEL_DIR_INO 6 /* Undelete directory inode */ +#define EXT4_RESIZE_INO 7 /* Reserved group descriptors inode */ +#define EXT4_JOURNAL_INO 8 /* Journal inode */ -/* First non-reserved inode for old ext3 filesystems */ -#define EXT3_GOOD_OLD_FIRST_INO 11 +/* First non-reserved inode for old ext4 filesystems */ +#define EXT4_GOOD_OLD_FIRST_INO 11 /* * Maximal count of links to a file */ -#define EXT3_LINK_MAX 32000 +#define EXT4_LINK_MAX 32000 /* * Macro-instructions used to manage several block sizes */ -#define EXT3_MIN_BLOCK_SIZE 1024 -#define EXT3_MAX_BLOCK_SIZE 4096 -#define EXT3_MIN_BLOCK_LOG_SIZE 10 +#define EXT4_MIN_BLOCK_SIZE 1024 +#define EXT4_MAX_BLOCK_SIZE 4096 +#define EXT4_MIN_BLOCK_LOG_SIZE 10 #ifdef __KERNEL__ -# define EXT3_BLOCK_SIZE(s) ((s)->s_blocksize) +# define EXT4_BLOCK_SIZE(s) ((s)->s_blocksize) #else -# define EXT3_BLOCK_SIZE(s) (EXT3_MIN_BLOCK_SIZE << (s)->s_log_block_size) +# define EXT4_BLOCK_SIZE(s) (EXT4_MIN_BLOCK_SIZE << (s)->s_log_block_size) #endif -#define EXT3_ADDR_PER_BLOCK(s) (EXT3_BLOCK_SIZE(s) / sizeof (__u32)) +#define EXT4_ADDR_PER_BLOCK(s) (EXT4_BLOCK_SIZE(s) / sizeof (__u32)) #ifdef __KERNEL__ -# define EXT3_BLOCK_SIZE_BITS(s) ((s)->s_blocksize_bits) +# define EXT4_BLOCK_SIZE_BITS(s) ((s)->s_blocksize_bits) #else -# define EXT3_BLOCK_SIZE_BITS(s) ((s)->s_log_block_size + 10) +# define EXT4_BLOCK_SIZE_BITS(s) ((s)->s_log_block_size + 10) #endif #ifdef __KERNEL__ -#define EXT3_ADDR_PER_BLOCK_BITS(s) (EXT3_SB(s)->s_addr_per_block_bits) -#define EXT3_INODE_SIZE(s) (EXT3_SB(s)->s_inode_size) -#define EXT3_FIRST_INO(s) (EXT3_SB(s)->s_first_ino) +#define EXT4_ADDR_PER_BLOCK_BITS(s) (EXT4_SB(s)->s_addr_per_block_bits) +#define EXT4_INODE_SIZE(s) (EXT4_SB(s)->s_inode_size) +#define EXT4_FIRST_INO(s) (EXT4_SB(s)->s_first_ino) #else -#define EXT3_INODE_SIZE(s) (((s)->s_rev_level == EXT3_GOOD_OLD_REV) ? \ - EXT3_GOOD_OLD_INODE_SIZE : \ +#define EXT4_INODE_SIZE(s) (((s)->s_rev_level == EXT4_GOOD_OLD_REV) ? \ + EXT4_GOOD_OLD_INODE_SIZE : \ (s)->s_inode_size) -#define EXT3_FIRST_INO(s) (((s)->s_rev_level == EXT3_GOOD_OLD_REV) ? \ - EXT3_GOOD_OLD_FIRST_INO : \ +#define EXT4_FIRST_INO(s) (((s)->s_rev_level == EXT4_GOOD_OLD_REV) ? \ + EXT4_GOOD_OLD_FIRST_INO : \ (s)->s_first_ino) #endif /* * Macro-instructions used to manage fragments */ -#define EXT3_MIN_FRAG_SIZE 1024 -#define EXT3_MAX_FRAG_SIZE 4096 -#define EXT3_MIN_FRAG_LOG_SIZE 10 +#define EXT4_MIN_FRAG_SIZE 1024 +#define EXT4_MAX_FRAG_SIZE 4096 +#define EXT4_MIN_FRAG_LOG_SIZE 10 #ifdef __KERNEL__ -# define EXT3_FRAG_SIZE(s) (EXT3_SB(s)->s_frag_size) -# define EXT3_FRAGS_PER_BLOCK(s) (EXT3_SB(s)->s_frags_per_block) +# define EXT4_FRAG_SIZE(s) (EXT4_SB(s)->s_frag_size) +# define EXT4_FRAGS_PER_BLOCK(s) (EXT4_SB(s)->s_frags_per_block) #else -# define EXT3_FRAG_SIZE(s) (EXT3_MIN_FRAG_SIZE << (s)->s_log_frag_size) -# define EXT3_FRAGS_PER_BLOCK(s) (EXT3_BLOCK_SIZE(s) / EXT3_FRAG_SIZE(s)) +# define EXT4_FRAG_SIZE(s) (EXT4_MIN_FRAG_SIZE << (s)->s_log_frag_size) +# define EXT4_FRAGS_PER_BLOCK(s) (EXT4_BLOCK_SIZE(s) / EXT4_FRAG_SIZE(s)) #endif /* * Structure of a blocks group descriptor */ -struct ext3_group_desc +struct ext4_group_desc { __le32 bg_block_bitmap; /* Blocks bitmap block */ __le32 bg_inode_bitmap; /* Inodes bitmap block */ @@ -135,62 +135,62 @@ struct ext3_group_desc * Macro-instructions used to manage group descriptors */ #ifdef __KERNEL__ -# define EXT3_BLOCKS_PER_GROUP(s) (EXT3_SB(s)->s_blocks_per_group) -# define EXT3_DESC_PER_BLOCK(s) (EXT3_SB(s)->s_desc_per_block) -# define EXT3_INODES_PER_GROUP(s) (EXT3_SB(s)->s_inodes_per_group) -# define EXT3_DESC_PER_BLOCK_BITS(s) (EXT3_SB(s)->s_desc_per_block_bits) +# define EXT4_BLOCKS_PER_GROUP(s) (EXT4_SB(s)->s_blocks_per_group) +# define EXT4_DESC_PER_BLOCK(s) (EXT4_SB(s)->s_desc_per_block) +# define EXT4_INODES_PER_GROUP(s) (EXT4_SB(s)->s_inodes_per_group) +# define EXT4_DESC_PER_BLOCK_BITS(s) (EXT4_SB(s)->s_desc_per_block_bits) #else -# define EXT3_BLOCKS_PER_GROUP(s) ((s)->s_blocks_per_group) -# define EXT3_DESC_PER_BLOCK(s) (EXT3_BLOCK_SIZE(s) / sizeof (struct ext3_group_desc)) -# define EXT3_INODES_PER_GROUP(s) ((s)->s_inodes_per_group) +# define EXT4_BLOCKS_PER_GROUP(s) ((s)->s_blocks_per_group) +# define EXT4_DESC_PER_BLOCK(s) (EXT4_BLOCK_SIZE(s) / sizeof (struct ext4_group_desc)) +# define EXT4_INODES_PER_GROUP(s) ((s)->s_inodes_per_group) #endif /* * Constants relative to the data blocks */ -#define EXT3_NDIR_BLOCKS 12 -#define EXT3_IND_BLOCK EXT3_NDIR_BLOCKS -#define EXT3_DIND_BLOCK (EXT3_IND_BLOCK + 1) -#define EXT3_TIND_BLOCK (EXT3_DIND_BLOCK + 1) -#define EXT3_N_BLOCKS (EXT3_TIND_BLOCK + 1) +#define EXT4_NDIR_BLOCKS 12 +#define EXT4_IND_BLOCK EXT4_NDIR_BLOCKS +#define EXT4_DIND_BLOCK (EXT4_IND_BLOCK + 1) +#define EXT4_TIND_BLOCK (EXT4_DIND_BLOCK + 1) +#define EXT4_N_BLOCKS (EXT4_TIND_BLOCK + 1) /* * Inode flags */ -#define EXT3_SECRM_FL 0x00000001 /* Secure deletion */ -#define EXT3_UNRM_FL 0x00000002 /* Undelete */ -#define EXT3_COMPR_FL 0x00000004 /* Compress file */ -#define EXT3_SYNC_FL 0x00000008 /* Synchronous updates */ -#define EXT3_IMMUTABLE_FL 0x00000010 /* Immutable file */ -#define EXT3_APPEND_FL 0x00000020 /* writes to file may only append */ -#define EXT3_NODUMP_FL 0x00000040 /* do not dump file */ -#define EXT3_NOATIME_FL 0x00000080 /* do not update atime */ +#define EXT4_SECRM_FL 0x00000001 /* Secure deletion */ +#define EXT4_UNRM_FL 0x00000002 /* Undelete */ +#define EXT4_COMPR_FL 0x00000004 /* Compress file */ +#define EXT4_SYNC_FL 0x00000008 /* Synchronous updates */ +#define EXT4_IMMUTABLE_FL 0x00000010 /* Immutable file */ +#define EXT4_APPEND_FL 0x00000020 /* writes to file may only append */ +#define EXT4_NODUMP_FL 0x00000040 /* do not dump file */ +#define EXT4_NOATIME_FL 0x00000080 /* do not update atime */ /* Reserved for compression usage... */ -#define EXT3_DIRTY_FL 0x00000100 -#define EXT3_COMPRBLK_FL 0x00000200 /* One or more compressed clusters */ -#define EXT3_NOCOMPR_FL 0x00000400 /* Don't compress */ -#define EXT3_ECOMPR_FL 0x00000800 /* Compression error */ +#define EXT4_DIRTY_FL 0x00000100 +#define EXT4_COMPRBLK_FL 0x00000200 /* One or more compressed clusters */ +#define EXT4_NOCOMPR_FL 0x00000400 /* Don't compress */ +#define EXT4_ECOMPR_FL 0x00000800 /* Compression error */ /* End compression flags --- maybe not all used */ -#define EXT3_INDEX_FL 0x00001000 /* hash-indexed directory */ -#define EXT3_IMAGIC_FL 0x00002000 /* AFS directory */ -#define EXT3_JOURNAL_DATA_FL 0x00004000 /* file data should be journaled */ -#define EXT3_NOTAIL_FL 0x00008000 /* file tail should not be merged */ -#define EXT3_DIRSYNC_FL 0x00010000 /* dirsync behaviour (directories only) */ -#define EXT3_TOPDIR_FL 0x00020000 /* Top of directory hierarchies*/ -#define EXT3_RESERVED_FL 0x80000000 /* reserved for ext3 lib */ +#define EXT4_INDEX_FL 0x00001000 /* hash-indexed directory */ +#define EXT4_IMAGIC_FL 0x00002000 /* AFS directory */ +#define EXT4_JOURNAL_DATA_FL 0x00004000 /* file data should be journaled */ +#define EXT4_NOTAIL_FL 0x00008000 /* file tail should not be merged */ +#define EXT4_DIRSYNC_FL 0x00010000 /* dirsync behaviour (directories only) */ +#define EXT4_TOPDIR_FL 0x00020000 /* Top of directory hierarchies*/ +#define EXT4_RESERVED_FL 0x80000000 /* reserved for ext4 lib */ -#define EXT3_FL_USER_VISIBLE 0x0003DFFF /* User visible flags */ -#define EXT3_FL_USER_MODIFIABLE 0x000380FF /* User modifiable flags */ +#define EXT4_FL_USER_VISIBLE 0x0003DFFF /* User visible flags */ +#define EXT4_FL_USER_MODIFIABLE 0x000380FF /* User modifiable flags */ /* * Inode dynamic state flags */ -#define EXT3_STATE_JDATA 0x00000001 /* journaled data exists */ -#define EXT3_STATE_NEW 0x00000002 /* inode is newly created */ -#define EXT3_STATE_XATTR 0x00000004 /* has in-inode xattrs */ +#define EXT4_STATE_JDATA 0x00000001 /* journaled data exists */ +#define EXT4_STATE_NEW 0x00000002 /* inode is newly created */ +#define EXT4_STATE_XATTR 0x00000004 /* has in-inode xattrs */ /* Used to pass group descriptor data when online resize is done */ -struct ext3_new_group_input { +struct ext4_new_group_input { __u32 group; /* Group number for this data */ __u32 block_bitmap; /* Absolute block number of block bitmap */ __u32 inode_bitmap; /* Absolute block number of inode bitmap */ @@ -200,8 +200,8 @@ struct ext3_new_group_input { __u16 unused; }; -/* The struct ext3_new_group_input in kernel space, with free_blocks_count */ -struct ext3_new_group_data { +/* The struct ext4_new_group_input in kernel space, with free_blocks_count */ +struct ext4_new_group_data { __u32 group; __u32 block_bitmap; __u32 inode_bitmap; @@ -216,41 +216,41 @@ struct ext3_new_group_data { /* * ioctl commands */ -#define EXT3_IOC_GETFLAGS FS_IOC_GETFLAGS -#define EXT3_IOC_SETFLAGS FS_IOC_SETFLAGS -#define EXT3_IOC_GETVERSION _IOR('f', 3, long) -#define EXT3_IOC_SETVERSION _IOW('f', 4, long) -#define EXT3_IOC_GROUP_EXTEND _IOW('f', 7, unsigned long) -#define EXT3_IOC_GROUP_ADD _IOW('f', 8,struct ext3_new_group_input) -#define EXT3_IOC_GETVERSION_OLD FS_IOC_GETVERSION -#define EXT3_IOC_SETVERSION_OLD FS_IOC_SETVERSION +#define EXT4_IOC_GETFLAGS FS_IOC_GETFLAGS +#define EXT4_IOC_SETFLAGS FS_IOC_SETFLAGS +#define EXT4_IOC_GETVERSION _IOR('f', 3, long) +#define EXT4_IOC_SETVERSION _IOW('f', 4, long) +#define EXT4_IOC_GROUP_EXTEND _IOW('f', 7, unsigned long) +#define EXT4_IOC_GROUP_ADD _IOW('f', 8,struct ext4_new_group_input) +#define EXT4_IOC_GETVERSION_OLD FS_IOC_GETVERSION +#define EXT4_IOC_SETVERSION_OLD FS_IOC_SETVERSION #ifdef CONFIG_JBD_DEBUG -#define EXT3_IOC_WAIT_FOR_READONLY _IOR('f', 99, long) +#define EXT4_IOC_WAIT_FOR_READONLY _IOR('f', 99, long) #endif -#define EXT3_IOC_GETRSVSZ _IOR('f', 5, long) -#define EXT3_IOC_SETRSVSZ _IOW('f', 6, long) +#define EXT4_IOC_GETRSVSZ _IOR('f', 5, long) +#define EXT4_IOC_SETRSVSZ _IOW('f', 6, long) /* * ioctl commands in 32 bit emulation */ -#define EXT3_IOC32_GETFLAGS FS_IOC32_GETFLAGS -#define EXT3_IOC32_SETFLAGS FS_IOC32_SETFLAGS -#define EXT3_IOC32_GETVERSION _IOR('f', 3, int) -#define EXT3_IOC32_SETVERSION _IOW('f', 4, int) -#define EXT3_IOC32_GETRSVSZ _IOR('f', 5, int) -#define EXT3_IOC32_SETRSVSZ _IOW('f', 6, int) -#define EXT3_IOC32_GROUP_EXTEND _IOW('f', 7, unsigned int) +#define EXT4_IOC32_GETFLAGS FS_IOC32_GETFLAGS +#define EXT4_IOC32_SETFLAGS FS_IOC32_SETFLAGS +#define EXT4_IOC32_GETVERSION _IOR('f', 3, int) +#define EXT4_IOC32_SETVERSION _IOW('f', 4, int) +#define EXT4_IOC32_GETRSVSZ _IOR('f', 5, int) +#define EXT4_IOC32_SETRSVSZ _IOW('f', 6, int) +#define EXT4_IOC32_GROUP_EXTEND _IOW('f', 7, unsigned int) #ifdef CONFIG_JBD_DEBUG -#define EXT3_IOC32_WAIT_FOR_READONLY _IOR('f', 99, int) +#define EXT4_IOC32_WAIT_FOR_READONLY _IOR('f', 99, int) #endif -#define EXT3_IOC32_GETVERSION_OLD FS_IOC32_GETVERSION -#define EXT3_IOC32_SETVERSION_OLD FS_IOC32_SETVERSION +#define EXT4_IOC32_GETVERSION_OLD FS_IOC32_GETVERSION +#define EXT4_IOC32_SETVERSION_OLD FS_IOC32_SETVERSION /* * Mount options */ -struct ext3_mount_options { +struct ext4_mount_options { unsigned long s_mount_opt; uid_t s_resuid; gid_t s_resgid; @@ -264,7 +264,7 @@ struct ext3_mount_options { /* * Structure of an inode on the disk */ -struct ext3_inode { +struct ext4_inode { __le16 i_mode; /* File mode */ __le16 i_uid; /* Low 16 bits of Owner Uid */ __le32 i_size; /* Size in bytes */ @@ -287,7 +287,7 @@ struct ext3_inode { __u32 m_i_reserved1; } masix1; } osd1; /* OS dependent 1 */ - __le32 i_block[EXT3_N_BLOCKS];/* Pointers to blocks */ + __le32 i_block[EXT4_N_BLOCKS];/* Pointers to blocks */ __le32 i_generation; /* File version (for NFS) */ __le32 i_file_acl; /* File ACL */ __le32 i_dir_acl; /* Directory ACL */ @@ -353,76 +353,76 @@ struct ext3_inode { /* * File system states */ -#define EXT3_VALID_FS 0x0001 /* Unmounted cleanly */ -#define EXT3_ERROR_FS 0x0002 /* Errors detected */ -#define EXT3_ORPHAN_FS 0x0004 /* Orphans being recovered */ +#define EXT4_VALID_FS 0x0001 /* Unmounted cleanly */ +#define EXT4_ERROR_FS 0x0002 /* Errors detected */ +#define EXT4_ORPHAN_FS 0x0004 /* Orphans being recovered */ /* * Mount flags */ -#define EXT3_MOUNT_CHECK 0x00001 /* Do mount-time checks */ -#define EXT3_MOUNT_OLDALLOC 0x00002 /* Don't use the new Orlov allocator */ -#define EXT3_MOUNT_GRPID 0x00004 /* Create files with directory's group */ -#define EXT3_MOUNT_DEBUG 0x00008 /* Some debugging messages */ -#define EXT3_MOUNT_ERRORS_CONT 0x00010 /* Continue on errors */ -#define EXT3_MOUNT_ERRORS_RO 0x00020 /* Remount fs ro on errors */ -#define EXT3_MOUNT_ERRORS_PANIC 0x00040 /* Panic on errors */ -#define EXT3_MOUNT_MINIX_DF 0x00080 /* Mimics the Minix statfs */ -#define EXT3_MOUNT_NOLOAD 0x00100 /* Don't use existing journal*/ -#define EXT3_MOUNT_ABORT 0x00200 /* Fatal error detected */ -#define EXT3_MOUNT_DATA_FLAGS 0x00C00 /* Mode for data writes: */ -#define EXT3_MOUNT_JOURNAL_DATA 0x00400 /* Write data to journal */ -#define EXT3_MOUNT_ORDERED_DATA 0x00800 /* Flush data before commit */ -#define EXT3_MOUNT_WRITEBACK_DATA 0x00C00 /* No data ordering */ -#define EXT3_MOUNT_UPDATE_JOURNAL 0x01000 /* Update the journal format */ -#define EXT3_MOUNT_NO_UID32 0x02000 /* Disable 32-bit UIDs */ -#define EXT3_MOUNT_XATTR_USER 0x04000 /* Extended user attributes */ -#define EXT3_MOUNT_POSIX_ACL 0x08000 /* POSIX Access Control Lists */ -#define EXT3_MOUNT_RESERVATION 0x10000 /* Preallocation */ -#define EXT3_MOUNT_BARRIER 0x20000 /* Use block barriers */ -#define EXT3_MOUNT_NOBH 0x40000 /* No bufferheads */ -#define EXT3_MOUNT_QUOTA 0x80000 /* Some quota option set */ -#define EXT3_MOUNT_USRQUOTA 0x100000 /* "old" user quota */ -#define EXT3_MOUNT_GRPQUOTA 0x200000 /* "old" group quota */ - -/* Compatibility, for having both ext2_fs.h and ext3_fs.h included at once */ +#define EXT4_MOUNT_CHECK 0x00001 /* Do mount-time checks */ +#define EXT4_MOUNT_OLDALLOC 0x00002 /* Don't use the new Orlov allocator */ +#define EXT4_MOUNT_GRPID 0x00004 /* Create files with directory's group */ +#define EXT4_MOUNT_DEBUG 0x00008 /* Some debugging messages */ +#define EXT4_MOUNT_ERRORS_CONT 0x00010 /* Continue on errors */ +#define EXT4_MOUNT_ERRORS_RO 0x00020 /* Remount fs ro on errors */ +#define EXT4_MOUNT_ERRORS_PANIC 0x00040 /* Panic on errors */ +#define EXT4_MOUNT_MINIX_DF 0x00080 /* Mimics the Minix statfs */ +#define EXT4_MOUNT_NOLOAD 0x00100 /* Don't use existing journal*/ +#define EXT4_MOUNT_ABORT 0x00200 /* Fatal error detected */ +#define EXT4_MOUNT_DATA_FLAGS 0x00C00 /* Mode for data writes: */ +#define EXT4_MOUNT_JOURNAL_DATA 0x00400 /* Write data to journal */ +#define EXT4_MOUNT_ORDERED_DATA 0x00800 /* Flush data before commit */ +#define EXT4_MOUNT_WRITEBACK_DATA 0x00C00 /* No data ordering */ +#define EXT4_MOUNT_UPDATE_JOURNAL 0x01000 /* Update the journal format */ +#define EXT4_MOUNT_NO_UID32 0x02000 /* Disable 32-bit UIDs */ +#define EXT4_MOUNT_XATTR_USER 0x04000 /* Extended user attributes */ +#define EXT4_MOUNT_POSIX_ACL 0x08000 /* POSIX Access Control Lists */ +#define EXT4_MOUNT_RESERVATION 0x10000 /* Preallocation */ +#define EXT4_MOUNT_BARRIER 0x20000 /* Use block barriers */ +#define EXT4_MOUNT_NOBH 0x40000 /* No bufferheads */ +#define EXT4_MOUNT_QUOTA 0x80000 /* Some quota option set */ +#define EXT4_MOUNT_USRQUOTA 0x100000 /* "old" user quota */ +#define EXT4_MOUNT_GRPQUOTA 0x200000 /* "old" group quota */ + +/* Compatibility, for having both ext2_fs.h and ext4_fs.h included at once */ #ifndef _LINUX_EXT2_FS_H -#define clear_opt(o, opt) o &= ~EXT3_MOUNT_##opt -#define set_opt(o, opt) o |= EXT3_MOUNT_##opt -#define test_opt(sb, opt) (EXT3_SB(sb)->s_mount_opt & \ - EXT3_MOUNT_##opt) +#define clear_opt(o, opt) o &= ~EXT4_MOUNT_##opt +#define set_opt(o, opt) o |= EXT4_MOUNT_##opt +#define test_opt(sb, opt) (EXT4_SB(sb)->s_mount_opt & \ + EXT4_MOUNT_##opt) #else -#define EXT2_MOUNT_NOLOAD EXT3_MOUNT_NOLOAD -#define EXT2_MOUNT_ABORT EXT3_MOUNT_ABORT -#define EXT2_MOUNT_DATA_FLAGS EXT3_MOUNT_DATA_FLAGS +#define EXT2_MOUNT_NOLOAD EXT4_MOUNT_NOLOAD +#define EXT2_MOUNT_ABORT EXT4_MOUNT_ABORT +#define EXT2_MOUNT_DATA_FLAGS EXT4_MOUNT_DATA_FLAGS #endif -#define ext3_set_bit ext2_set_bit -#define ext3_set_bit_atomic ext2_set_bit_atomic -#define ext3_clear_bit ext2_clear_bit -#define ext3_clear_bit_atomic ext2_clear_bit_atomic -#define ext3_test_bit ext2_test_bit -#define ext3_find_first_zero_bit ext2_find_first_zero_bit -#define ext3_find_next_zero_bit ext2_find_next_zero_bit +#define ext4_set_bit ext2_set_bit +#define ext4_set_bit_atomic ext2_set_bit_atomic +#define ext4_clear_bit ext2_clear_bit +#define ext4_clear_bit_atomic ext2_clear_bit_atomic +#define ext4_test_bit ext2_test_bit +#define ext4_find_first_zero_bit ext2_find_first_zero_bit +#define ext4_find_next_zero_bit ext2_find_next_zero_bit /* * Maximal mount counts between two filesystem checks */ -#define EXT3_DFL_MAX_MNT_COUNT 20 /* Allow 20 mounts */ -#define EXT3_DFL_CHECKINTERVAL 0 /* Don't use interval check */ +#define EXT4_DFL_MAX_MNT_COUNT 20 /* Allow 20 mounts */ +#define EXT4_DFL_CHECKINTERVAL 0 /* Don't use interval check */ /* * Behaviour when detecting errors */ -#define EXT3_ERRORS_CONTINUE 1 /* Continue execution */ -#define EXT3_ERRORS_RO 2 /* Remount fs read-only */ -#define EXT3_ERRORS_PANIC 3 /* Panic */ -#define EXT3_ERRORS_DEFAULT EXT3_ERRORS_CONTINUE +#define EXT4_ERRORS_CONTINUE 1 /* Continue execution */ +#define EXT4_ERRORS_RO 2 /* Remount fs read-only */ +#define EXT4_ERRORS_PANIC 3 /* Panic */ +#define EXT4_ERRORS_DEFAULT EXT4_ERRORS_CONTINUE /* * Structure of the super block */ -struct ext3_super_block { +struct ext4_super_block { /*00*/ __le32 s_inodes_count; /* Inodes count */ __le32 s_blocks_count; /* Blocks count */ __le32 s_r_blocks_count; /* Reserved blocks count */ @@ -449,7 +449,7 @@ struct ext3_super_block { /*50*/ __le16 s_def_resuid; /* Default uid for reserved blocks */ __le16 s_def_resgid; /* Default gid for reserved blocks */ /* - * These fields are for EXT3_DYNAMIC_REV superblocks only. + * These fields are for EXT4_DYNAMIC_REV superblocks only. * * Note: the difference between the compatible feature set and * the incompatible feature set is that if there is a bit set @@ -473,13 +473,13 @@ struct ext3_super_block { /*C8*/ __le32 s_algorithm_usage_bitmap; /* For compression */ /* * Performance hints. Directory preallocation should only - * happen if the EXT3_FEATURE_COMPAT_DIR_PREALLOC flag is on. + * happen if the EXT4_FEATURE_COMPAT_DIR_PREALLOC flag is on. */ __u8 s_prealloc_blocks; /* Nr of blocks to try to preallocate*/ __u8 s_prealloc_dir_blocks; /* Nr to preallocate for dirs */ __le16 s_reserved_gdt_blocks; /* Per group desc for online growth */ /* - * Journaling support valid if EXT3_FEATURE_COMPAT_HAS_JOURNAL set. + * Journaling support valid if EXT4_FEATURE_COMPAT_HAS_JOURNAL set. */ /*D0*/ __u8 s_journal_uuid[16]; /* uuid of journal superblock */ /*E0*/ __le32 s_journal_inum; /* inode number of journal file */ @@ -495,186 +495,186 @@ struct ext3_super_block { }; #ifdef __KERNEL__ -#include -#include -static inline struct ext3_sb_info * EXT3_SB(struct super_block *sb) +#include +#include +static inline struct ext4_sb_info * EXT4_SB(struct super_block *sb) { return sb->s_fs_info; } -static inline struct ext3_inode_info *EXT3_I(struct inode *inode) +static inline struct ext4_inode_info *EXT4_I(struct inode *inode) { - return container_of(inode, struct ext3_inode_info, vfs_inode); + return container_of(inode, struct ext4_inode_info, vfs_inode); } -static inline int ext3_valid_inum(struct super_block *sb, unsigned long ino) +static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino) { - return ino == EXT3_ROOT_INO || - ino == EXT3_JOURNAL_INO || - ino == EXT3_RESIZE_INO || - (ino >= EXT3_FIRST_INO(sb) && - ino <= le32_to_cpu(EXT3_SB(sb)->s_es->s_inodes_count)); + return ino == EXT4_ROOT_INO || + ino == EXT4_JOURNAL_INO || + ino == EXT4_RESIZE_INO || + (ino >= EXT4_FIRST_INO(sb) && + ino <= le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count)); } #else -/* Assume that user mode programs are passing in an ext3fs superblock, not +/* Assume that user mode programs are passing in an ext4fs superblock, not * a kernel struct super_block. This will allow us to call the feature-test * macros from user land. */ -#define EXT3_SB(sb) (sb) +#define EXT4_SB(sb) (sb) #endif -#define NEXT_ORPHAN(inode) EXT3_I(inode)->i_dtime +#define NEXT_ORPHAN(inode) EXT4_I(inode)->i_dtime /* * Codes for operating systems */ -#define EXT3_OS_LINUX 0 -#define EXT3_OS_HURD 1 -#define EXT3_OS_MASIX 2 -#define EXT3_OS_FREEBSD 3 -#define EXT3_OS_LITES 4 +#define EXT4_OS_LINUX 0 +#define EXT4_OS_HURD 1 +#define EXT4_OS_MASIX 2 +#define EXT4_OS_FREEBSD 3 +#define EXT4_OS_LITES 4 /* * Revision levels */ -#define EXT3_GOOD_OLD_REV 0 /* The good old (original) format */ -#define EXT3_DYNAMIC_REV 1 /* V2 format w/ dynamic inode sizes */ +#define EXT4_GOOD_OLD_REV 0 /* The good old (original) format */ +#define EXT4_DYNAMIC_REV 1 /* V2 format w/ dynamic inode sizes */ -#define EXT3_CURRENT_REV EXT3_GOOD_OLD_REV -#define EXT3_MAX_SUPP_REV EXT3_DYNAMIC_REV +#define EXT4_CURRENT_REV EXT4_GOOD_OLD_REV +#define EXT4_MAX_SUPP_REV EXT4_DYNAMIC_REV -#define EXT3_GOOD_OLD_INODE_SIZE 128 +#define EXT4_GOOD_OLD_INODE_SIZE 128 /* * Feature set definitions */ -#define EXT3_HAS_COMPAT_FEATURE(sb,mask) \ - ( EXT3_SB(sb)->s_es->s_feature_compat & cpu_to_le32(mask) ) -#define EXT3_HAS_RO_COMPAT_FEATURE(sb,mask) \ - ( EXT3_SB(sb)->s_es->s_feature_ro_compat & cpu_to_le32(mask) ) -#define EXT3_HAS_INCOMPAT_FEATURE(sb,mask) \ - ( EXT3_SB(sb)->s_es->s_feature_incompat & cpu_to_le32(mask) ) -#define EXT3_SET_COMPAT_FEATURE(sb,mask) \ - EXT3_SB(sb)->s_es->s_feature_compat |= cpu_to_le32(mask) -#define EXT3_SET_RO_COMPAT_FEATURE(sb,mask) \ - EXT3_SB(sb)->s_es->s_feature_ro_compat |= cpu_to_le32(mask) -#define EXT3_SET_INCOMPAT_FEATURE(sb,mask) \ - EXT3_SB(sb)->s_es->s_feature_incompat |= cpu_to_le32(mask) -#define EXT3_CLEAR_COMPAT_FEATURE(sb,mask) \ - EXT3_SB(sb)->s_es->s_feature_compat &= ~cpu_to_le32(mask) -#define EXT3_CLEAR_RO_COMPAT_FEATURE(sb,mask) \ - EXT3_SB(sb)->s_es->s_feature_ro_compat &= ~cpu_to_le32(mask) -#define EXT3_CLEAR_INCOMPAT_FEATURE(sb,mask) \ - EXT3_SB(sb)->s_es->s_feature_incompat &= ~cpu_to_le32(mask) - -#define EXT3_FEATURE_COMPAT_DIR_PREALLOC 0x0001 -#define EXT3_FEATURE_COMPAT_IMAGIC_INODES 0x0002 -#define EXT3_FEATURE_COMPAT_HAS_JOURNAL 0x0004 -#define EXT3_FEATURE_COMPAT_EXT_ATTR 0x0008 -#define EXT3_FEATURE_COMPAT_RESIZE_INODE 0x0010 -#define EXT3_FEATURE_COMPAT_DIR_INDEX 0x0020 - -#define EXT3_FEATURE_RO_COMPAT_SPARSE_SUPER 0x0001 -#define EXT3_FEATURE_RO_COMPAT_LARGE_FILE 0x0002 -#define EXT3_FEATURE_RO_COMPAT_BTREE_DIR 0x0004 - -#define EXT3_FEATURE_INCOMPAT_COMPRESSION 0x0001 -#define EXT3_FEATURE_INCOMPAT_FILETYPE 0x0002 -#define EXT3_FEATURE_INCOMPAT_RECOVER 0x0004 /* Needs recovery */ -#define EXT3_FEATURE_INCOMPAT_JOURNAL_DEV 0x0008 /* Journal device */ -#define EXT3_FEATURE_INCOMPAT_META_BG 0x0010 - -#define EXT3_FEATURE_COMPAT_SUPP EXT2_FEATURE_COMPAT_EXT_ATTR -#define EXT3_FEATURE_INCOMPAT_SUPP (EXT3_FEATURE_INCOMPAT_FILETYPE| \ - EXT3_FEATURE_INCOMPAT_RECOVER| \ - EXT3_FEATURE_INCOMPAT_META_BG) -#define EXT3_FEATURE_RO_COMPAT_SUPP (EXT3_FEATURE_RO_COMPAT_SPARSE_SUPER| \ - EXT3_FEATURE_RO_COMPAT_LARGE_FILE| \ - EXT3_FEATURE_RO_COMPAT_BTREE_DIR) +#define EXT4_HAS_COMPAT_FEATURE(sb,mask) \ + ( EXT4_SB(sb)->s_es->s_feature_compat & cpu_to_le32(mask) ) +#define EXT4_HAS_RO_COMPAT_FEATURE(sb,mask) \ + ( EXT4_SB(sb)->s_es->s_feature_ro_compat & cpu_to_le32(mask) ) +#define EXT4_HAS_INCOMPAT_FEATURE(sb,mask) \ + ( EXT4_SB(sb)->s_es->s_feature_incompat & cpu_to_le32(mask) ) +#define EXT4_SET_COMPAT_FEATURE(sb,mask) \ + EXT4_SB(sb)->s_es->s_feature_compat |= cpu_to_le32(mask) +#define EXT4_SET_RO_COMPAT_FEATURE(sb,mask) \ + EXT4_SB(sb)->s_es->s_feature_ro_compat |= cpu_to_le32(mask) +#define EXT4_SET_INCOMPAT_FEATURE(sb,mask) \ + EXT4_SB(sb)->s_es->s_feature_incompat |= cpu_to_le32(mask) +#define EXT4_CLEAR_COMPAT_FEATURE(sb,mask) \ + EXT4_SB(sb)->s_es->s_feature_compat &= ~cpu_to_le32(mask) +#define EXT4_CLEAR_RO_COMPAT_FEATURE(sb,mask) \ + EXT4_SB(sb)->s_es->s_feature_ro_compat &= ~cpu_to_le32(mask) +#define EXT4_CLEAR_INCOMPAT_FEATURE(sb,mask) \ + EXT4_SB(sb)->s_es->s_feature_incompat &= ~cpu_to_le32(mask) + +#define EXT4_FEATURE_COMPAT_DIR_PREALLOC 0x0001 +#define EXT4_FEATURE_COMPAT_IMAGIC_INODES 0x0002 +#define EXT4_FEATURE_COMPAT_HAS_JOURNAL 0x0004 +#define EXT4_FEATURE_COMPAT_EXT_ATTR 0x0008 +#define EXT4_FEATURE_COMPAT_RESIZE_INODE 0x0010 +#define EXT4_FEATURE_COMPAT_DIR_INDEX 0x0020 + +#define EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER 0x0001 +#define EXT4_FEATURE_RO_COMPAT_LARGE_FILE 0x0002 +#define EXT4_FEATURE_RO_COMPAT_BTREE_DIR 0x0004 + +#define EXT4_FEATURE_INCOMPAT_COMPRESSION 0x0001 +#define EXT4_FEATURE_INCOMPAT_FILETYPE 0x0002 +#define EXT4_FEATURE_INCOMPAT_RECOVER 0x0004 /* Needs recovery */ +#define EXT4_FEATURE_INCOMPAT_JOURNAL_DEV 0x0008 /* Journal device */ +#define EXT4_FEATURE_INCOMPAT_META_BG 0x0010 + +#define EXT4_FEATURE_COMPAT_SUPP EXT2_FEATURE_COMPAT_EXT_ATTR +#define EXT4_FEATURE_INCOMPAT_SUPP (EXT4_FEATURE_INCOMPAT_FILETYPE| \ + EXT4_FEATURE_INCOMPAT_RECOVER| \ + EXT4_FEATURE_INCOMPAT_META_BG) +#define EXT4_FEATURE_RO_COMPAT_SUPP (EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER| \ + EXT4_FEATURE_RO_COMPAT_LARGE_FILE| \ + EXT4_FEATURE_RO_COMPAT_BTREE_DIR) /* * Default values for user and/or group using reserved blocks */ -#define EXT3_DEF_RESUID 0 -#define EXT3_DEF_RESGID 0 +#define EXT4_DEF_RESUID 0 +#define EXT4_DEF_RESGID 0 /* * Default mount options */ -#define EXT3_DEFM_DEBUG 0x0001 -#define EXT3_DEFM_BSDGROUPS 0x0002 -#define EXT3_DEFM_XATTR_USER 0x0004 -#define EXT3_DEFM_ACL 0x0008 -#define EXT3_DEFM_UID16 0x0010 -#define EXT3_DEFM_JMODE 0x0060 -#define EXT3_DEFM_JMODE_DATA 0x0020 -#define EXT3_DEFM_JMODE_ORDERED 0x0040 -#define EXT3_DEFM_JMODE_WBACK 0x0060 +#define EXT4_DEFM_DEBUG 0x0001 +#define EXT4_DEFM_BSDGROUPS 0x0002 +#define EXT4_DEFM_XATTR_USER 0x0004 +#define EXT4_DEFM_ACL 0x0008 +#define EXT4_DEFM_UID16 0x0010 +#define EXT4_DEFM_JMODE 0x0060 +#define EXT4_DEFM_JMODE_DATA 0x0020 +#define EXT4_DEFM_JMODE_ORDERED 0x0040 +#define EXT4_DEFM_JMODE_WBACK 0x0060 /* * Structure of a directory entry */ -#define EXT3_NAME_LEN 255 +#define EXT4_NAME_LEN 255 -struct ext3_dir_entry { +struct ext4_dir_entry { __le32 inode; /* Inode number */ __le16 rec_len; /* Directory entry length */ __le16 name_len; /* Name length */ - char name[EXT3_NAME_LEN]; /* File name */ + char name[EXT4_NAME_LEN]; /* File name */ }; /* - * The new version of the directory entry. Since EXT3 structures are + * The new version of the directory entry. Since EXT4 structures are * stored in intel byte order, and the name_len field could never be * bigger than 255 chars, it's safe to reclaim the extra byte for the * file_type field. */ -struct ext3_dir_entry_2 { +struct ext4_dir_entry_2 { __le32 inode; /* Inode number */ __le16 rec_len; /* Directory entry length */ __u8 name_len; /* Name length */ __u8 file_type; - char name[EXT3_NAME_LEN]; /* File name */ + char name[EXT4_NAME_LEN]; /* File name */ }; /* - * Ext3 directory file types. Only the low 3 bits are used. The + * Ext4 directory file types. Only the low 3 bits are used. The * other bits are reserved for now. */ -#define EXT3_FT_UNKNOWN 0 -#define EXT3_FT_REG_FILE 1 -#define EXT3_FT_DIR 2 -#define EXT3_FT_CHRDEV 3 -#define EXT3_FT_BLKDEV 4 -#define EXT3_FT_FIFO 5 -#define EXT3_FT_SOCK 6 -#define EXT3_FT_SYMLINK 7 +#define EXT4_FT_UNKNOWN 0 +#define EXT4_FT_REG_FILE 1 +#define EXT4_FT_DIR 2 +#define EXT4_FT_CHRDEV 3 +#define EXT4_FT_BLKDEV 4 +#define EXT4_FT_FIFO 5 +#define EXT4_FT_SOCK 6 +#define EXT4_FT_SYMLINK 7 -#define EXT3_FT_MAX 8 +#define EXT4_FT_MAX 8 /* - * EXT3_DIR_PAD defines the directory entries boundaries + * EXT4_DIR_PAD defines the directory entries boundaries * * NOTE: It must be a multiple of 4 */ -#define EXT3_DIR_PAD 4 -#define EXT3_DIR_ROUND (EXT3_DIR_PAD - 1) -#define EXT3_DIR_REC_LEN(name_len) (((name_len) + 8 + EXT3_DIR_ROUND) & \ - ~EXT3_DIR_ROUND) +#define EXT4_DIR_PAD 4 +#define EXT4_DIR_ROUND (EXT4_DIR_PAD - 1) +#define EXT4_DIR_REC_LEN(name_len) (((name_len) + 8 + EXT4_DIR_ROUND) & \ + ~EXT4_DIR_ROUND) /* * Hash Tree Directory indexing * (c) Daniel Phillips, 2001 */ -#ifdef CONFIG_EXT3_INDEX - #define is_dx(dir) (EXT3_HAS_COMPAT_FEATURE(dir->i_sb, \ - EXT3_FEATURE_COMPAT_DIR_INDEX) && \ - (EXT3_I(dir)->i_flags & EXT3_INDEX_FL)) -#define EXT3_DIR_LINK_MAX(dir) (!is_dx(dir) && (dir)->i_nlink >= EXT3_LINK_MAX) -#define EXT3_DIR_LINK_EMPTY(dir) ((dir)->i_nlink == 2 || (dir)->i_nlink == 1) +#ifdef CONFIG_EXT4_INDEX + #define is_dx(dir) (EXT4_HAS_COMPAT_FEATURE(dir->i_sb, \ + EXT4_FEATURE_COMPAT_DIR_INDEX) && \ + (EXT4_I(dir)->i_flags & EXT4_INDEX_FL)) +#define EXT4_DIR_LINK_MAX(dir) (!is_dx(dir) && (dir)->i_nlink >= EXT4_LINK_MAX) +#define EXT4_DIR_LINK_EMPTY(dir) ((dir)->i_nlink == 2 || (dir)->i_nlink == 1) #else #define is_dx(dir) 0 -#define EXT3_DIR_LINK_MAX(dir) ((dir)->i_nlink >= EXT3_LINK_MAX) -#define EXT3_DIR_LINK_EMPTY(dir) ((dir)->i_nlink == 2) +#define EXT4_DIR_LINK_MAX(dir) ((dir)->i_nlink >= EXT4_LINK_MAX) +#define EXT4_DIR_LINK_EMPTY(dir) ((dir)->i_nlink == 2) #endif /* Legal values for the dx_root hash_version field: */ @@ -694,10 +694,10 @@ struct dx_hash_info u32 *seed; }; -#define EXT3_HTREE_EOF 0x7fffffff +#define EXT4_HTREE_EOF 0x7fffffff /* - * Control parameters used by ext3_htree_next_block + * Control parameters used by ext4_htree_next_block */ #define HASH_NB_ALWAYS 1 @@ -705,16 +705,16 @@ struct dx_hash_info /* * Describe an inode's exact location on disk and in memory */ -struct ext3_iloc +struct ext4_iloc { struct buffer_head *bh; unsigned long offset; unsigned long block_group; }; -static inline struct ext3_inode *ext3_raw_inode(struct ext3_iloc *iloc) +static inline struct ext4_inode *ext4_raw_inode(struct ext4_iloc *iloc) { - return (struct ext3_inode *) (iloc->bh->b_data + iloc->offset); + return (struct ext4_inode *) (iloc->bh->b_data + iloc->offset); } /* @@ -733,11 +733,11 @@ struct dir_private_info { }; /* calculate the first block number of the group */ -static inline ext3_fsblk_t -ext3_group_first_block_no(struct super_block *sb, unsigned long group_no) +static inline ext4_fsblk_t +ext4_group_first_block_no(struct super_block *sb, unsigned long group_no) { - return group_no * (ext3_fsblk_t)EXT3_BLOCKS_PER_GROUP(sb) + - le32_to_cpu(EXT3_SB(sb)->s_es->s_first_data_block); + return group_no * (ext4_fsblk_t)EXT4_BLOCKS_PER_GROUP(sb) + + le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block); } /* @@ -751,113 +751,113 @@ ext3_group_first_block_no(struct super_block *sb, unsigned long group_no) /* * Ok, these declarations are also in but none of the - * ext3 source programs needs to include it so they are duplicated here. + * ext4 source programs needs to include it so they are duplicated here. */ # define NORET_TYPE /**/ # define ATTRIB_NORET __attribute__((noreturn)) # define NORET_AND noreturn, /* balloc.c */ -extern int ext3_bg_has_super(struct super_block *sb, int group); -extern unsigned long ext3_bg_num_gdb(struct super_block *sb, int group); -extern ext3_fsblk_t ext3_new_block (handle_t *handle, struct inode *inode, - ext3_fsblk_t goal, int *errp); -extern ext3_fsblk_t ext3_new_blocks (handle_t *handle, struct inode *inode, - ext3_fsblk_t goal, unsigned long *count, int *errp); -extern void ext3_free_blocks (handle_t *handle, struct inode *inode, - ext3_fsblk_t block, unsigned long count); -extern void ext3_free_blocks_sb (handle_t *handle, struct super_block *sb, - ext3_fsblk_t block, unsigned long count, +extern int ext4_bg_has_super(struct super_block *sb, int group); +extern unsigned long ext4_bg_num_gdb(struct super_block *sb, int group); +extern ext4_fsblk_t ext4_new_block (handle_t *handle, struct inode *inode, + ext4_fsblk_t goal, int *errp); +extern ext4_fsblk_t ext4_new_blocks (handle_t *handle, struct inode *inode, + ext4_fsblk_t goal, unsigned long *count, int *errp); +extern void ext4_free_blocks (handle_t *handle, struct inode *inode, + ext4_fsblk_t block, unsigned long count); +extern void ext4_free_blocks_sb (handle_t *handle, struct super_block *sb, + ext4_fsblk_t block, unsigned long count, unsigned long *pdquot_freed_blocks); -extern ext3_fsblk_t ext3_count_free_blocks (struct super_block *); -extern void ext3_check_blocks_bitmap (struct super_block *); -extern struct ext3_group_desc * ext3_get_group_desc(struct super_block * sb, +extern ext4_fsblk_t ext4_count_free_blocks (struct super_block *); +extern void ext4_check_blocks_bitmap (struct super_block *); +extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb, unsigned int block_group, struct buffer_head ** bh); -extern int ext3_should_retry_alloc(struct super_block *sb, int *retries); -extern void ext3_init_block_alloc_info(struct inode *); -extern void ext3_rsv_window_add(struct super_block *sb, struct ext3_reserve_window_node *rsv); +extern int ext4_should_retry_alloc(struct super_block *sb, int *retries); +extern void ext4_init_block_alloc_info(struct inode *); +extern void ext4_rsv_window_add(struct super_block *sb, struct ext4_reserve_window_node *rsv); /* dir.c */ -extern int ext3_check_dir_entry(const char *, struct inode *, - struct ext3_dir_entry_2 *, +extern int ext4_check_dir_entry(const char *, struct inode *, + struct ext4_dir_entry_2 *, struct buffer_head *, unsigned long); -extern int ext3_htree_store_dirent(struct file *dir_file, __u32 hash, +extern int ext4_htree_store_dirent(struct file *dir_file, __u32 hash, __u32 minor_hash, - struct ext3_dir_entry_2 *dirent); -extern void ext3_htree_free_dir_info(struct dir_private_info *p); + struct ext4_dir_entry_2 *dirent); +extern void ext4_htree_free_dir_info(struct dir_private_info *p); /* fsync.c */ -extern int ext3_sync_file (struct file *, struct dentry *, int); +extern int ext4_sync_file (struct file *, struct dentry *, int); /* hash.c */ -extern int ext3fs_dirhash(const char *name, int len, struct +extern int ext4fs_dirhash(const char *name, int len, struct dx_hash_info *hinfo); /* ialloc.c */ -extern struct inode * ext3_new_inode (handle_t *, struct inode *, int); -extern void ext3_free_inode (handle_t *, struct inode *); -extern struct inode * ext3_orphan_get (struct super_block *, unsigned long); -extern unsigned long ext3_count_free_inodes (struct super_block *); -extern unsigned long ext3_count_dirs (struct super_block *); -extern void ext3_check_inodes_bitmap (struct super_block *); -extern unsigned long ext3_count_free (struct buffer_head *, unsigned); +extern struct inode * ext4_new_inode (handle_t *, struct inode *, int); +extern void ext4_free_inode (handle_t *, struct inode *); +extern struct inode * ext4_orphan_get (struct super_block *, unsigned long); +extern unsigned long ext4_count_free_inodes (struct super_block *); +extern unsigned long ext4_count_dirs (struct super_block *); +extern void ext4_check_inodes_bitmap (struct super_block *); +extern unsigned long ext4_count_free (struct buffer_head *, unsigned); /* inode.c */ -int ext3_forget(handle_t *handle, int is_metadata, struct inode *inode, - struct buffer_head *bh, ext3_fsblk_t blocknr); -struct buffer_head * ext3_getblk (handle_t *, struct inode *, long, int, int *); -struct buffer_head * ext3_bread (handle_t *, struct inode *, int, int, int *); -int ext3_get_blocks_handle(handle_t *handle, struct inode *inode, +int ext4_forget(handle_t *handle, int is_metadata, struct inode *inode, + struct buffer_head *bh, ext4_fsblk_t blocknr); +struct buffer_head * ext4_getblk (handle_t *, struct inode *, long, int, int *); +struct buffer_head * ext4_bread (handle_t *, struct inode *, int, int, int *); +int ext4_get_blocks_handle(handle_t *handle, struct inode *inode, sector_t iblock, unsigned long maxblocks, struct buffer_head *bh_result, int create, int extend_disksize); -extern void ext3_read_inode (struct inode *); -extern int ext3_write_inode (struct inode *, int); -extern int ext3_setattr (struct dentry *, struct iattr *); -extern void ext3_delete_inode (struct inode *); -extern int ext3_sync_inode (handle_t *, struct inode *); -extern void ext3_discard_reservation (struct inode *); -extern void ext3_dirty_inode(struct inode *); -extern int ext3_change_inode_journal_flag(struct inode *, int); -extern int ext3_get_inode_loc(struct inode *, struct ext3_iloc *); -extern void ext3_truncate (struct inode *); -extern void ext3_set_inode_flags(struct inode *); -extern void ext3_set_aops(struct inode *inode); +extern void ext4_read_inode (struct inode *); +extern int ext4_write_inode (struct inode *, int); +extern int ext4_setattr (struct dentry *, struct iattr *); +extern void ext4_delete_inode (struct inode *); +extern int ext4_sync_inode (handle_t *, struct inode *); +extern void ext4_discard_reservation (struct inode *); +extern void ext4_dirty_inode(struct inode *); +extern int ext4_change_inode_journal_flag(struct inode *, int); +extern int ext4_get_inode_loc(struct inode *, struct ext4_iloc *); +extern void ext4_truncate (struct inode *); +extern void ext4_set_inode_flags(struct inode *); +extern void ext4_set_aops(struct inode *inode); /* ioctl.c */ -extern int ext3_ioctl (struct inode *, struct file *, unsigned int, +extern int ext4_ioctl (struct inode *, struct file *, unsigned int, unsigned long); -extern long ext3_compat_ioctl (struct file *, unsigned int, unsigned long); +extern long ext4_compat_ioctl (struct file *, unsigned int, unsigned long); /* namei.c */ -extern int ext3_orphan_add(handle_t *, struct inode *); -extern int ext3_orphan_del(handle_t *, struct inode *); -extern int ext3_htree_fill_tree(struct file *dir_file, __u32 start_hash, +extern int ext4_orphan_add(handle_t *, struct inode *); +extern int ext4_orphan_del(handle_t *, struct inode *); +extern int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash, __u32 start_minor_hash, __u32 *next_hash); /* resize.c */ -extern int ext3_group_add(struct super_block *sb, - struct ext3_new_group_data *input); -extern int ext3_group_extend(struct super_block *sb, - struct ext3_super_block *es, - ext3_fsblk_t n_blocks_count); +extern int ext4_group_add(struct super_block *sb, + struct ext4_new_group_data *input); +extern int ext4_group_extend(struct super_block *sb, + struct ext4_super_block *es, + ext4_fsblk_t n_blocks_count); /* super.c */ -extern void ext3_error (struct super_block *, const char *, const char *, ...) +extern void ext4_error (struct super_block *, const char *, const char *, ...) __attribute__ ((format (printf, 3, 4))); -extern void __ext3_std_error (struct super_block *, const char *, int); -extern void ext3_abort (struct super_block *, const char *, const char *, ...) +extern void __ext4_std_error (struct super_block *, const char *, int); +extern void ext4_abort (struct super_block *, const char *, const char *, ...) __attribute__ ((format (printf, 3, 4))); -extern void ext3_warning (struct super_block *, const char *, const char *, ...) +extern void ext4_warning (struct super_block *, const char *, const char *, ...) __attribute__ ((format (printf, 3, 4))); -extern void ext3_update_dynamic_rev (struct super_block *sb); +extern void ext4_update_dynamic_rev (struct super_block *sb); -#define ext3_std_error(sb, errno) \ +#define ext4_std_error(sb, errno) \ do { \ if ((errno)) \ - __ext3_std_error((sb), __FUNCTION__, (errno)); \ + __ext4_std_error((sb), __FUNCTION__, (errno)); \ } while (0) /* @@ -865,21 +865,21 @@ do { \ */ /* dir.c */ -extern const struct file_operations ext3_dir_operations; +extern const struct file_operations ext4_dir_operations; /* file.c */ -extern struct inode_operations ext3_file_inode_operations; -extern const struct file_operations ext3_file_operations; +extern struct inode_operations ext4_file_inode_operations; +extern const struct file_operations ext4_file_operations; /* namei.c */ -extern struct inode_operations ext3_dir_inode_operations; -extern struct inode_operations ext3_special_inode_operations; +extern struct inode_operations ext4_dir_inode_operations; +extern struct inode_operations ext4_special_inode_operations; /* symlink.c */ -extern struct inode_operations ext3_symlink_inode_operations; -extern struct inode_operations ext3_fast_symlink_inode_operations; +extern struct inode_operations ext4_symlink_inode_operations; +extern struct inode_operations ext4_fast_symlink_inode_operations; #endif /* __KERNEL__ */ -#endif /* _LINUX_EXT3_FS_H */ +#endif /* _LINUX_EXT4_FS_H */ diff --git a/include/linux/ext4_fs_i.h b/include/linux/ext4_fs_i.h index 4395e5206746..18a6ce98537f 100644 --- a/include/linux/ext4_fs_i.h +++ b/include/linux/ext4_fs_i.h @@ -1,5 +1,5 @@ /* - * linux/include/linux/ext3_fs_i.h + * linux/include/linux/ext4_fs_i.h * * Copyright (C) 1992, 1993, 1994, 1995 * Remy Card (card@masi.ibp.fr) @@ -13,8 +13,8 @@ * Copyright (C) 1991, 1992 Linus Torvalds */ -#ifndef _LINUX_EXT3_FS_I -#define _LINUX_EXT3_FS_I +#ifndef _LINUX_EXT4_FS_I +#define _LINUX_EXT4_FS_I #include #include @@ -22,43 +22,43 @@ #include /* data type for block offset of block group */ -typedef int ext3_grpblk_t; +typedef int ext4_grpblk_t; /* data type for filesystem-wide blocks number */ -typedef unsigned long ext3_fsblk_t; +typedef unsigned long ext4_fsblk_t; #define E3FSBLK "%lu" -struct ext3_reserve_window { - ext3_fsblk_t _rsv_start; /* First byte reserved */ - ext3_fsblk_t _rsv_end; /* Last byte reserved or 0 */ +struct ext4_reserve_window { + ext4_fsblk_t _rsv_start; /* First byte reserved */ + ext4_fsblk_t _rsv_end; /* Last byte reserved or 0 */ }; -struct ext3_reserve_window_node { +struct ext4_reserve_window_node { struct rb_node rsv_node; __u32 rsv_goal_size; __u32 rsv_alloc_hit; - struct ext3_reserve_window rsv_window; + struct ext4_reserve_window rsv_window; }; -struct ext3_block_alloc_info { +struct ext4_block_alloc_info { /* information about reservation window */ - struct ext3_reserve_window_node rsv_window_node; + struct ext4_reserve_window_node rsv_window_node; /* - * was i_next_alloc_block in ext3_inode_info + * was i_next_alloc_block in ext4_inode_info * is the logical (file-relative) number of the * most-recently-allocated block in this file. * We use this for detecting linearly ascending allocation requests. */ __u32 last_alloc_logical_block; /* - * Was i_next_alloc_goal in ext3_inode_info + * Was i_next_alloc_goal in ext4_inode_info * is the *physical* companion to i_next_alloc_block. * it the the physical block number of the block which was most-recentl * allocated to this file. This give us the goal (target) for the next * allocation when we detect linearly ascending requests. */ - ext3_fsblk_t last_alloc_physical_block; + ext4_fsblk_t last_alloc_physical_block; }; #define rsv_start rsv_window._rsv_start @@ -67,15 +67,15 @@ struct ext3_block_alloc_info { /* * third extended file system inode data in memory */ -struct ext3_inode_info { +struct ext4_inode_info { __le32 i_data[15]; /* unconverted */ __u32 i_flags; -#ifdef EXT3_FRAGMENTS +#ifdef EXT4_FRAGMENTS __u32 i_faddr; __u8 i_frag_no; __u8 i_frag_size; #endif - ext3_fsblk_t i_file_acl; + ext4_fsblk_t i_file_acl; __u32 i_dir_acl; __u32 i_dtime; @@ -87,13 +87,13 @@ struct ext3_inode_info { * near to their parent directory's inode. */ __u32 i_block_group; - __u32 i_state; /* Dynamic state flags for ext3 */ + __u32 i_state; /* Dynamic state flags for ext4 */ /* block reservation info */ - struct ext3_block_alloc_info *i_block_alloc_info; + struct ext4_block_alloc_info *i_block_alloc_info; __u32 i_dir_start_lookup; -#ifdef CONFIG_EXT3_FS_XATTR +#ifdef CONFIG_EXT4DEV_FS_XATTR /* * Extended attributes can be read independently of the main file * data. Taking i_mutex even when reading would cause contention @@ -103,7 +103,7 @@ struct ext3_inode_info { */ struct rw_semaphore xattr_sem; #endif -#ifdef CONFIG_EXT3_FS_POSIX_ACL +#ifdef CONFIG_EXT4DEV_FS_POSIX_ACL struct posix_acl *i_acl; struct posix_acl *i_default_acl; #endif @@ -113,7 +113,7 @@ struct ext3_inode_info { /* * i_disksize keeps track of what the inode size is ON DISK, not * in memory. During truncate, i_size is set to the new size by - * the VFS prior to calling ext3_truncate(), but the filesystem won't + * the VFS prior to calling ext4_truncate(), but the filesystem won't * set i_disksize to 0 until the truncate is actually under way. * * The intent is that i_disksize always represents the blocks which @@ -123,7 +123,7 @@ struct ext3_inode_info { * * The only time when i_disksize and i_size may be different is when * a truncate is in progress. The only things which change i_disksize - * are ext3_get_block (growth) and ext3_truncate (shrinkth). + * are ext4_get_block (growth) and ext4_truncate (shrinkth). */ loff_t i_disksize; @@ -131,10 +131,10 @@ struct ext3_inode_info { __u16 i_extra_isize; /* - * truncate_mutex is for serialising ext3_truncate() against - * ext3_getblock(). In the 2.4 ext2 design, great chunks of inode's + * truncate_mutex is for serialising ext4_truncate() against + * ext4_getblock(). In the 2.4 ext2 design, great chunks of inode's * data tree are chopped off during truncate. We can't do that in - * ext3 because whenever we perform intermediate commits during + * ext4 because whenever we perform intermediate commits during * truncate, the inode and all the metadata blocks *must* be in a * consistent state which allows truncation of the orphans to restart * during recovery. Hence we must fix the get_block-vs-truncate race @@ -144,4 +144,4 @@ struct ext3_inode_info { struct inode vfs_inode; }; -#endif /* _LINUX_EXT3_FS_I */ +#endif /* _LINUX_EXT4_FS_I */ diff --git a/include/linux/ext4_fs_sb.h b/include/linux/ext4_fs_sb.h index f61309c81cc4..ce4856d70100 100644 --- a/include/linux/ext4_fs_sb.h +++ b/include/linux/ext4_fs_sb.h @@ -1,5 +1,5 @@ /* - * linux/include/linux/ext3_fs_sb.h + * linux/include/linux/ext4_fs_sb.h * * Copyright (C) 1992, 1993, 1994, 1995 * Remy Card (card@masi.ibp.fr) @@ -13,8 +13,8 @@ * Copyright (C) 1991, 1992 Linus Torvalds */ -#ifndef _LINUX_EXT3_FS_SB -#define _LINUX_EXT3_FS_SB +#ifndef _LINUX_EXT4_FS_SB +#define _LINUX_EXT4_FS_SB #ifdef __KERNEL__ #include @@ -27,7 +27,7 @@ /* * third extended-fs super-block data in memory */ -struct ext3_sb_info { +struct ext4_sb_info { unsigned long s_frag_size; /* Size of a fragment in bytes */ unsigned long s_frags_per_block;/* Number of fragments per block */ unsigned long s_inodes_per_block;/* Number of inodes per block */ @@ -39,7 +39,7 @@ struct ext3_sb_info { unsigned long s_desc_per_block; /* Number of group descriptors per block */ unsigned long s_groups_count; /* Number of groups in the fs */ struct buffer_head * s_sbh; /* Buffer containing the super block */ - struct ext3_super_block * s_es; /* Pointer to the super block in the buffer */ + struct ext4_super_block * s_es; /* Pointer to the super block in the buffer */ struct buffer_head ** s_group_desc; unsigned long s_mount_opt; uid_t s_resuid; @@ -62,7 +62,7 @@ struct ext3_sb_info { /* root of the per fs reservation window tree */ spinlock_t s_rsv_window_lock; struct rb_root s_rsv_window_root; - struct ext3_reserve_window_node s_rsv_window_head; + struct ext4_reserve_window_node s_rsv_window_head; /* Journaling */ struct inode * s_journal_inode; @@ -80,4 +80,4 @@ struct ext3_sb_info { #endif }; -#endif /* _LINUX_EXT3_FS_SB */ +#endif /* _LINUX_EXT4_FS_SB */ diff --git a/include/linux/ext4_jbd.h b/include/linux/ext4_jbd.h index ce0e6109aff0..3dbf6c779037 100644 --- a/include/linux/ext4_jbd.h +++ b/include/linux/ext4_jbd.h @@ -1,5 +1,5 @@ /* - * linux/include/linux/ext3_jbd.h + * linux/include/linux/ext4_jbd.h * * Written by Stephen C. Tweedie , 1999 * @@ -9,17 +9,17 @@ * the terms of the GNU General Public License, version 2, or at your * option, any later version, incorporated herein by reference. * - * Ext3-specific journaling extensions. + * Ext4-specific journaling extensions. */ -#ifndef _LINUX_EXT3_JBD_H -#define _LINUX_EXT3_JBD_H +#ifndef _LINUX_EXT4_JBD_H +#define _LINUX_EXT4_JBD_H #include #include -#include +#include -#define EXT3_JOURNAL(inode) (EXT3_SB((inode)->i_sb)->s_journal) +#define EXT4_JOURNAL(inode) (EXT4_SB((inode)->i_sb)->s_journal) /* Define the number of blocks we need to account to a transaction to * modify one block of data. @@ -28,13 +28,13 @@ * indirection blocks, the group and superblock summaries, and the data * block to complete the transaction. */ -#define EXT3_SINGLEDATA_TRANS_BLOCKS 8U +#define EXT4_SINGLEDATA_TRANS_BLOCKS 8U /* Extended attribute operations touch at most two data buffers, * two bitmap buffers, and two group summaries, in addition to the inode * and the superblock, which are already accounted for. */ -#define EXT3_XATTR_TRANS_BLOCKS 6U +#define EXT4_XATTR_TRANS_BLOCKS 6U /* Define the minimum size for a transaction which modifies data. This * needs to take into account the fact that we may end up modifying two @@ -42,15 +42,15 @@ * superblock only gets updated once, of course, so don't bother * counting that again for the quota updates. */ -#define EXT3_DATA_TRANS_BLOCKS(sb) (EXT3_SINGLEDATA_TRANS_BLOCKS + \ - EXT3_XATTR_TRANS_BLOCKS - 2 + \ - 2*EXT3_QUOTA_TRANS_BLOCKS(sb)) +#define EXT4_DATA_TRANS_BLOCKS(sb) (EXT4_SINGLEDATA_TRANS_BLOCKS + \ + EXT4_XATTR_TRANS_BLOCKS - 2 + \ + 2*EXT4_QUOTA_TRANS_BLOCKS(sb)) /* Delete operations potentially hit one directory's namespace plus an * entire inode, plus arbitrary amounts of bitmap/indirection data. Be * generous. We can grow the delete transaction later if necessary. */ -#define EXT3_DELETE_TRANS_BLOCKS(sb) (2 * EXT3_DATA_TRANS_BLOCKS(sb) + 64) +#define EXT4_DELETE_TRANS_BLOCKS(sb) (2 * EXT4_DATA_TRANS_BLOCKS(sb) + 64) /* Define an arbitrary limit for the amount of data we will anticipate * writing to any given transaction. For unbounded transactions such as @@ -58,7 +58,7 @@ * start off at the maximum transaction size and grow the transaction * optimistically as we go. */ -#define EXT3_MAX_TRANS_DATA 64U +#define EXT4_MAX_TRANS_DATA 64U /* We break up a large truncate or write transaction once the handle's * buffer credits gets this low, we need either to extend the @@ -67,202 +67,202 @@ * one block, plus two quota updates. Quota allocations are not * needed. */ -#define EXT3_RESERVE_TRANS_BLOCKS 12U +#define EXT4_RESERVE_TRANS_BLOCKS 12U -#define EXT3_INDEX_EXTRA_TRANS_BLOCKS 8 +#define EXT4_INDEX_EXTRA_TRANS_BLOCKS 8 #ifdef CONFIG_QUOTA /* Amount of blocks needed for quota update - we know that the structure was * allocated so we need to update only inode+data */ -#define EXT3_QUOTA_TRANS_BLOCKS(sb) (test_opt(sb, QUOTA) ? 2 : 0) +#define EXT4_QUOTA_TRANS_BLOCKS(sb) (test_opt(sb, QUOTA) ? 2 : 0) /* Amount of blocks needed for quota insert/delete - we do some block writes * but inode, sb and group updates are done only once */ -#define EXT3_QUOTA_INIT_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_INIT_ALLOC*\ - (EXT3_SINGLEDATA_TRANS_BLOCKS-3)+3+DQUOT_INIT_REWRITE) : 0) -#define EXT3_QUOTA_DEL_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_DEL_ALLOC*\ - (EXT3_SINGLEDATA_TRANS_BLOCKS-3)+3+DQUOT_DEL_REWRITE) : 0) +#define EXT4_QUOTA_INIT_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_INIT_ALLOC*\ + (EXT4_SINGLEDATA_TRANS_BLOCKS-3)+3+DQUOT_INIT_REWRITE) : 0) +#define EXT4_QUOTA_DEL_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_DEL_ALLOC*\ + (EXT4_SINGLEDATA_TRANS_BLOCKS-3)+3+DQUOT_DEL_REWRITE) : 0) #else -#define EXT3_QUOTA_TRANS_BLOCKS(sb) 0 -#define EXT3_QUOTA_INIT_BLOCKS(sb) 0 -#define EXT3_QUOTA_DEL_BLOCKS(sb) 0 +#define EXT4_QUOTA_TRANS_BLOCKS(sb) 0 +#define EXT4_QUOTA_INIT_BLOCKS(sb) 0 +#define EXT4_QUOTA_DEL_BLOCKS(sb) 0 #endif int -ext3_mark_iloc_dirty(handle_t *handle, +ext4_mark_iloc_dirty(handle_t *handle, struct inode *inode, - struct ext3_iloc *iloc); + struct ext4_iloc *iloc); /* * On success, We end up with an outstanding reference count against * iloc->bh. This _must_ be cleaned up later. */ -int ext3_reserve_inode_write(handle_t *handle, struct inode *inode, - struct ext3_iloc *iloc); +int ext4_reserve_inode_write(handle_t *handle, struct inode *inode, + struct ext4_iloc *iloc); -int ext3_mark_inode_dirty(handle_t *handle, struct inode *inode); +int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode); /* - * Wrapper functions with which ext3 calls into JBD. The intent here is - * to allow these to be turned into appropriate stubs so ext3 can control - * ext2 filesystems, so ext2+ext3 systems only nee one fs. This work hasn't + * Wrapper functions with which ext4 calls into JBD. The intent here is + * to allow these to be turned into appropriate stubs so ext4 can control + * ext2 filesystems, so ext2+ext4 systems only nee one fs. This work hasn't * been done yet. */ -void ext3_journal_abort_handle(const char *caller, const char *err_fn, +void ext4_journal_abort_handle(const char *caller, const char *err_fn, struct buffer_head *bh, handle_t *handle, int err); static inline int -__ext3_journal_get_undo_access(const char *where, handle_t *handle, +__ext4_journal_get_undo_access(const char *where, handle_t *handle, struct buffer_head *bh) { int err = journal_get_undo_access(handle, bh); if (err) - ext3_journal_abort_handle(where, __FUNCTION__, bh, handle,err); + ext4_journal_abort_handle(where, __FUNCTION__, bh, handle,err); return err; } static inline int -__ext3_journal_get_write_access(const char *where, handle_t *handle, +__ext4_journal_get_write_access(const char *where, handle_t *handle, struct buffer_head *bh) { int err = journal_get_write_access(handle, bh); if (err) - ext3_journal_abort_handle(where, __FUNCTION__, bh, handle,err); + ext4_journal_abort_handle(where, __FUNCTION__, bh, handle,err); return err; } static inline void -ext3_journal_release_buffer(handle_t *handle, struct buffer_head *bh) +ext4_journal_release_buffer(handle_t *handle, struct buffer_head *bh) { journal_release_buffer(handle, bh); } static inline int -__ext3_journal_forget(const char *where, handle_t *handle, struct buffer_head *bh) +__ext4_journal_forget(const char *where, handle_t *handle, struct buffer_head *bh) { int err = journal_forget(handle, bh); if (err) - ext3_journal_abort_handle(where, __FUNCTION__, bh, handle,err); + ext4_journal_abort_handle(where, __FUNCTION__, bh, handle,err); return err; } static inline int -__ext3_journal_revoke(const char *where, handle_t *handle, +__ext4_journal_revoke(const char *where, handle_t *handle, unsigned long blocknr, struct buffer_head *bh) { int err = journal_revoke(handle, blocknr, bh); if (err) - ext3_journal_abort_handle(where, __FUNCTION__, bh, handle,err); + ext4_journal_abort_handle(where, __FUNCTION__, bh, handle,err); return err; } static inline int -__ext3_journal_get_create_access(const char *where, +__ext4_journal_get_create_access(const char *where, handle_t *handle, struct buffer_head *bh) { int err = journal_get_create_access(handle, bh); if (err) - ext3_journal_abort_handle(where, __FUNCTION__, bh, handle,err); + ext4_journal_abort_handle(where, __FUNCTION__, bh, handle,err); return err; } static inline int -__ext3_journal_dirty_metadata(const char *where, +__ext4_journal_dirty_metadata(const char *where, handle_t *handle, struct buffer_head *bh) { int err = journal_dirty_metadata(handle, bh); if (err) - ext3_journal_abort_handle(where, __FUNCTION__, bh, handle,err); + ext4_journal_abort_handle(where, __FUNCTION__, bh, handle,err); return err; } -#define ext3_journal_get_undo_access(handle, bh) \ - __ext3_journal_get_undo_access(__FUNCTION__, (handle), (bh)) -#define ext3_journal_get_write_access(handle, bh) \ - __ext3_journal_get_write_access(__FUNCTION__, (handle), (bh)) -#define ext3_journal_revoke(handle, blocknr, bh) \ - __ext3_journal_revoke(__FUNCTION__, (handle), (blocknr), (bh)) -#define ext3_journal_get_create_access(handle, bh) \ - __ext3_journal_get_create_access(__FUNCTION__, (handle), (bh)) -#define ext3_journal_dirty_metadata(handle, bh) \ - __ext3_journal_dirty_metadata(__FUNCTION__, (handle), (bh)) -#define ext3_journal_forget(handle, bh) \ - __ext3_journal_forget(__FUNCTION__, (handle), (bh)) +#define ext4_journal_get_undo_access(handle, bh) \ + __ext4_journal_get_undo_access(__FUNCTION__, (handle), (bh)) +#define ext4_journal_get_write_access(handle, bh) \ + __ext4_journal_get_write_access(__FUNCTION__, (handle), (bh)) +#define ext4_journal_revoke(handle, blocknr, bh) \ + __ext4_journal_revoke(__FUNCTION__, (handle), (blocknr), (bh)) +#define ext4_journal_get_create_access(handle, bh) \ + __ext4_journal_get_create_access(__FUNCTION__, (handle), (bh)) +#define ext4_journal_dirty_metadata(handle, bh) \ + __ext4_journal_dirty_metadata(__FUNCTION__, (handle), (bh)) +#define ext4_journal_forget(handle, bh) \ + __ext4_journal_forget(__FUNCTION__, (handle), (bh)) -int ext3_journal_dirty_data(handle_t *handle, struct buffer_head *bh); +int ext4_journal_dirty_data(handle_t *handle, struct buffer_head *bh); -handle_t *ext3_journal_start_sb(struct super_block *sb, int nblocks); -int __ext3_journal_stop(const char *where, handle_t *handle); +handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks); +int __ext4_journal_stop(const char *where, handle_t *handle); -static inline handle_t *ext3_journal_start(struct inode *inode, int nblocks) +static inline handle_t *ext4_journal_start(struct inode *inode, int nblocks) { - return ext3_journal_start_sb(inode->i_sb, nblocks); + return ext4_journal_start_sb(inode->i_sb, nblocks); } -#define ext3_journal_stop(handle) \ - __ext3_journal_stop(__FUNCTION__, (handle)) +#define ext4_journal_stop(handle) \ + __ext4_journal_stop(__FUNCTION__, (handle)) -static inline handle_t *ext3_journal_current_handle(void) +static inline handle_t *ext4_journal_current_handle(void) { return journal_current_handle(); } -static inline int ext3_journal_extend(handle_t *handle, int nblocks) +static inline int ext4_journal_extend(handle_t *handle, int nblocks) { return journal_extend(handle, nblocks); } -static inline int ext3_journal_restart(handle_t *handle, int nblocks) +static inline int ext4_journal_restart(handle_t *handle, int nblocks) { return journal_restart(handle, nblocks); } -static inline int ext3_journal_blocks_per_page(struct inode *inode) +static inline int ext4_journal_blocks_per_page(struct inode *inode) { return journal_blocks_per_page(inode); } -static inline int ext3_journal_force_commit(journal_t *journal) +static inline int ext4_journal_force_commit(journal_t *journal) { return journal_force_commit(journal); } /* super.c */ -int ext3_force_commit(struct super_block *sb); +int ext4_force_commit(struct super_block *sb); -static inline int ext3_should_journal_data(struct inode *inode) +static inline int ext4_should_journal_data(struct inode *inode) { if (!S_ISREG(inode->i_mode)) return 1; - if (test_opt(inode->i_sb, DATA_FLAGS) == EXT3_MOUNT_JOURNAL_DATA) + if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) return 1; - if (EXT3_I(inode)->i_flags & EXT3_JOURNAL_DATA_FL) + if (EXT4_I(inode)->i_flags & EXT4_JOURNAL_DATA_FL) return 1; return 0; } -static inline int ext3_should_order_data(struct inode *inode) +static inline int ext4_should_order_data(struct inode *inode) { if (!S_ISREG(inode->i_mode)) return 0; - if (EXT3_I(inode)->i_flags & EXT3_JOURNAL_DATA_FL) + if (EXT4_I(inode)->i_flags & EXT4_JOURNAL_DATA_FL) return 0; - if (test_opt(inode->i_sb, DATA_FLAGS) == EXT3_MOUNT_ORDERED_DATA) + if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA) return 1; return 0; } -static inline int ext3_should_writeback_data(struct inode *inode) +static inline int ext4_should_writeback_data(struct inode *inode) { if (!S_ISREG(inode->i_mode)) return 0; - if (EXT3_I(inode)->i_flags & EXT3_JOURNAL_DATA_FL) + if (EXT4_I(inode)->i_flags & EXT4_JOURNAL_DATA_FL) return 0; - if (test_opt(inode->i_sb, DATA_FLAGS) == EXT3_MOUNT_WRITEBACK_DATA) + if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA) return 1; return 0; } -#endif /* _LINUX_EXT3_JBD_H */ +#endif /* _LINUX_EXT4_JBD_H */ -- cgit v1.2.3 From 02ea2104c55b625cf5b5d9ba8586a4fc17920f5c Mon Sep 17 00:00:00 2001 From: Mingming Cao Date: Wed, 11 Oct 2006 01:20:56 -0700 Subject: [PATCH] ext4: enable building of ext4 Originally part of a patch from Mingming Cao and Randy Dunlap. Reorganized by Shaggy. Signed-off-by: Randy Dunlap Signed-off-by: Mingming Cao Signed-off-by: Dave Kleikamp Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/magic.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/magic.h b/include/linux/magic.h index 22036dd2ba36..156c40fc664e 100644 --- a/include/linux/magic.h +++ b/include/linux/magic.h @@ -8,6 +8,7 @@ #define EFS_SUPER_MAGIC 0x414A53 #define EXT2_SUPER_MAGIC 0xEF53 #define EXT3_SUPER_MAGIC 0xEF53 +#define EXT4_SUPER_MAGIC 0xEF53 #define HPFS_SUPER_MAGIC 0xf995e849 #define ISOFS_SUPER_MAGIC 0x9660 #define JFFS2_SUPER_MAGIC 0x72b6 -- cgit v1.2.3 From 470decc613ab2048b619a01028072d932d9086ee Mon Sep 17 00:00:00 2001 From: Dave Kleikamp Date: Wed, 11 Oct 2006 01:20:57 -0700 Subject: [PATCH] jbd2: initial copy of files from jbd This is a simple copy of the files in fs/jbd to fs/jbd2 and /usr/incude/linux/[ext4_]jbd.h to /usr/include/[ext4_]jbd2.h Signed-off-by: Dave Kleikamp Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ext4_jbd2.h | 268 +++++++++++ include/linux/jbd2.h | 1098 +++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 1366 insertions(+) create mode 100644 include/linux/ext4_jbd2.h create mode 100644 include/linux/jbd2.h (limited to 'include/linux') diff --git a/include/linux/ext4_jbd2.h b/include/linux/ext4_jbd2.h new file mode 100644 index 000000000000..3dbf6c779037 --- /dev/null +++ b/include/linux/ext4_jbd2.h @@ -0,0 +1,268 @@ +/* + * linux/include/linux/ext4_jbd.h + * + * Written by Stephen C. Tweedie , 1999 + * + * Copyright 1998--1999 Red Hat corp --- All Rights Reserved + * + * This file is part of the Linux kernel and is made available under + * the terms of the GNU General Public License, version 2, or at your + * option, any later version, incorporated herein by reference. + * + * Ext4-specific journaling extensions. + */ + +#ifndef _LINUX_EXT4_JBD_H +#define _LINUX_EXT4_JBD_H + +#include +#include +#include + +#define EXT4_JOURNAL(inode) (EXT4_SB((inode)->i_sb)->s_journal) + +/* Define the number of blocks we need to account to a transaction to + * modify one block of data. + * + * We may have to touch one inode, one bitmap buffer, up to three + * indirection blocks, the group and superblock summaries, and the data + * block to complete the transaction. */ + +#define EXT4_SINGLEDATA_TRANS_BLOCKS 8U + +/* Extended attribute operations touch at most two data buffers, + * two bitmap buffers, and two group summaries, in addition to the inode + * and the superblock, which are already accounted for. */ + +#define EXT4_XATTR_TRANS_BLOCKS 6U + +/* Define the minimum size for a transaction which modifies data. This + * needs to take into account the fact that we may end up modifying two + * quota files too (one for the group, one for the user quota). The + * superblock only gets updated once, of course, so don't bother + * counting that again for the quota updates. */ + +#define EXT4_DATA_TRANS_BLOCKS(sb) (EXT4_SINGLEDATA_TRANS_BLOCKS + \ + EXT4_XATTR_TRANS_BLOCKS - 2 + \ + 2*EXT4_QUOTA_TRANS_BLOCKS(sb)) + +/* Delete operations potentially hit one directory's namespace plus an + * entire inode, plus arbitrary amounts of bitmap/indirection data. Be + * generous. We can grow the delete transaction later if necessary. */ + +#define EXT4_DELETE_TRANS_BLOCKS(sb) (2 * EXT4_DATA_TRANS_BLOCKS(sb) + 64) + +/* Define an arbitrary limit for the amount of data we will anticipate + * writing to any given transaction. For unbounded transactions such as + * write(2) and truncate(2) we can write more than this, but we always + * start off at the maximum transaction size and grow the transaction + * optimistically as we go. */ + +#define EXT4_MAX_TRANS_DATA 64U + +/* We break up a large truncate or write transaction once the handle's + * buffer credits gets this low, we need either to extend the + * transaction or to start a new one. Reserve enough space here for + * inode, bitmap, superblock, group and indirection updates for at least + * one block, plus two quota updates. Quota allocations are not + * needed. */ + +#define EXT4_RESERVE_TRANS_BLOCKS 12U + +#define EXT4_INDEX_EXTRA_TRANS_BLOCKS 8 + +#ifdef CONFIG_QUOTA +/* Amount of blocks needed for quota update - we know that the structure was + * allocated so we need to update only inode+data */ +#define EXT4_QUOTA_TRANS_BLOCKS(sb) (test_opt(sb, QUOTA) ? 2 : 0) +/* Amount of blocks needed for quota insert/delete - we do some block writes + * but inode, sb and group updates are done only once */ +#define EXT4_QUOTA_INIT_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_INIT_ALLOC*\ + (EXT4_SINGLEDATA_TRANS_BLOCKS-3)+3+DQUOT_INIT_REWRITE) : 0) +#define EXT4_QUOTA_DEL_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_DEL_ALLOC*\ + (EXT4_SINGLEDATA_TRANS_BLOCKS-3)+3+DQUOT_DEL_REWRITE) : 0) +#else +#define EXT4_QUOTA_TRANS_BLOCKS(sb) 0 +#define EXT4_QUOTA_INIT_BLOCKS(sb) 0 +#define EXT4_QUOTA_DEL_BLOCKS(sb) 0 +#endif + +int +ext4_mark_iloc_dirty(handle_t *handle, + struct inode *inode, + struct ext4_iloc *iloc); + +/* + * On success, We end up with an outstanding reference count against + * iloc->bh. This _must_ be cleaned up later. + */ + +int ext4_reserve_inode_write(handle_t *handle, struct inode *inode, + struct ext4_iloc *iloc); + +int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode); + +/* + * Wrapper functions with which ext4 calls into JBD. The intent here is + * to allow these to be turned into appropriate stubs so ext4 can control + * ext2 filesystems, so ext2+ext4 systems only nee one fs. This work hasn't + * been done yet. + */ + +void ext4_journal_abort_handle(const char *caller, const char *err_fn, + struct buffer_head *bh, handle_t *handle, int err); + +static inline int +__ext4_journal_get_undo_access(const char *where, handle_t *handle, + struct buffer_head *bh) +{ + int err = journal_get_undo_access(handle, bh); + if (err) + ext4_journal_abort_handle(where, __FUNCTION__, bh, handle,err); + return err; +} + +static inline int +__ext4_journal_get_write_access(const char *where, handle_t *handle, + struct buffer_head *bh) +{ + int err = journal_get_write_access(handle, bh); + if (err) + ext4_journal_abort_handle(where, __FUNCTION__, bh, handle,err); + return err; +} + +static inline void +ext4_journal_release_buffer(handle_t *handle, struct buffer_head *bh) +{ + journal_release_buffer(handle, bh); +} + +static inline int +__ext4_journal_forget(const char *where, handle_t *handle, struct buffer_head *bh) +{ + int err = journal_forget(handle, bh); + if (err) + ext4_journal_abort_handle(where, __FUNCTION__, bh, handle,err); + return err; +} + +static inline int +__ext4_journal_revoke(const char *where, handle_t *handle, + unsigned long blocknr, struct buffer_head *bh) +{ + int err = journal_revoke(handle, blocknr, bh); + if (err) + ext4_journal_abort_handle(where, __FUNCTION__, bh, handle,err); + return err; +} + +static inline int +__ext4_journal_get_create_access(const char *where, + handle_t *handle, struct buffer_head *bh) +{ + int err = journal_get_create_access(handle, bh); + if (err) + ext4_journal_abort_handle(where, __FUNCTION__, bh, handle,err); + return err; +} + +static inline int +__ext4_journal_dirty_metadata(const char *where, + handle_t *handle, struct buffer_head *bh) +{ + int err = journal_dirty_metadata(handle, bh); + if (err) + ext4_journal_abort_handle(where, __FUNCTION__, bh, handle,err); + return err; +} + + +#define ext4_journal_get_undo_access(handle, bh) \ + __ext4_journal_get_undo_access(__FUNCTION__, (handle), (bh)) +#define ext4_journal_get_write_access(handle, bh) \ + __ext4_journal_get_write_access(__FUNCTION__, (handle), (bh)) +#define ext4_journal_revoke(handle, blocknr, bh) \ + __ext4_journal_revoke(__FUNCTION__, (handle), (blocknr), (bh)) +#define ext4_journal_get_create_access(handle, bh) \ + __ext4_journal_get_create_access(__FUNCTION__, (handle), (bh)) +#define ext4_journal_dirty_metadata(handle, bh) \ + __ext4_journal_dirty_metadata(__FUNCTION__, (handle), (bh)) +#define ext4_journal_forget(handle, bh) \ + __ext4_journal_forget(__FUNCTION__, (handle), (bh)) + +int ext4_journal_dirty_data(handle_t *handle, struct buffer_head *bh); + +handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks); +int __ext4_journal_stop(const char *where, handle_t *handle); + +static inline handle_t *ext4_journal_start(struct inode *inode, int nblocks) +{ + return ext4_journal_start_sb(inode->i_sb, nblocks); +} + +#define ext4_journal_stop(handle) \ + __ext4_journal_stop(__FUNCTION__, (handle)) + +static inline handle_t *ext4_journal_current_handle(void) +{ + return journal_current_handle(); +} + +static inline int ext4_journal_extend(handle_t *handle, int nblocks) +{ + return journal_extend(handle, nblocks); +} + +static inline int ext4_journal_restart(handle_t *handle, int nblocks) +{ + return journal_restart(handle, nblocks); +} + +static inline int ext4_journal_blocks_per_page(struct inode *inode) +{ + return journal_blocks_per_page(inode); +} + +static inline int ext4_journal_force_commit(journal_t *journal) +{ + return journal_force_commit(journal); +} + +/* super.c */ +int ext4_force_commit(struct super_block *sb); + +static inline int ext4_should_journal_data(struct inode *inode) +{ + if (!S_ISREG(inode->i_mode)) + return 1; + if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) + return 1; + if (EXT4_I(inode)->i_flags & EXT4_JOURNAL_DATA_FL) + return 1; + return 0; +} + +static inline int ext4_should_order_data(struct inode *inode) +{ + if (!S_ISREG(inode->i_mode)) + return 0; + if (EXT4_I(inode)->i_flags & EXT4_JOURNAL_DATA_FL) + return 0; + if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA) + return 1; + return 0; +} + +static inline int ext4_should_writeback_data(struct inode *inode) +{ + if (!S_ISREG(inode->i_mode)) + return 0; + if (EXT4_I(inode)->i_flags & EXT4_JOURNAL_DATA_FL) + return 0; + if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA) + return 1; + return 0; +} + +#endif /* _LINUX_EXT4_JBD_H */ diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h new file mode 100644 index 000000000000..fe89444b1c6f --- /dev/null +++ b/include/linux/jbd2.h @@ -0,0 +1,1098 @@ +/* + * linux/include/linux/jbd.h + * + * Written by Stephen C. Tweedie + * + * Copyright 1998-2000 Red Hat, Inc --- All Rights Reserved + * + * This file is part of the Linux kernel and is made available under + * the terms of the GNU General Public License, version 2, or at your + * option, any later version, incorporated herein by reference. + * + * Definitions for transaction data structures for the buffer cache + * filesystem journaling support. + */ + +#ifndef _LINUX_JBD_H +#define _LINUX_JBD_H + +/* Allow this file to be included directly into e2fsprogs */ +#ifndef __KERNEL__ +#include "jfs_compat.h" +#define JFS_DEBUG +#define jfs_debug jbd_debug +#else + +#include +#include +#include +#include +#include +#include +#include + +#include +#endif + +#define journal_oom_retry 1 + +/* + * Define JBD_PARANIOD_IOFAIL to cause a kernel BUG() if ext3 finds + * certain classes of error which can occur due to failed IOs. Under + * normal use we want ext3 to continue after such errors, because + * hardware _can_ fail, but for debugging purposes when running tests on + * known-good hardware we may want to trap these errors. + */ +#undef JBD_PARANOID_IOFAIL + +/* + * The default maximum commit age, in seconds. + */ +#define JBD_DEFAULT_MAX_COMMIT_AGE 5 + +#ifdef CONFIG_JBD_DEBUG +/* + * Define JBD_EXPENSIVE_CHECKING to enable more expensive internal + * consistency checks. By default we don't do this unless + * CONFIG_JBD_DEBUG is on. + */ +#define JBD_EXPENSIVE_CHECKING +extern int journal_enable_debug; + +#define jbd_debug(n, f, a...) \ + do { \ + if ((n) <= journal_enable_debug) { \ + printk (KERN_DEBUG "(%s, %d): %s: ", \ + __FILE__, __LINE__, __FUNCTION__); \ + printk (f, ## a); \ + } \ + } while (0) +#else +#define jbd_debug(f, a...) /**/ +#endif + +extern void * __jbd_kmalloc (const char *where, size_t size, gfp_t flags, int retry); +extern void * jbd_slab_alloc(size_t size, gfp_t flags); +extern void jbd_slab_free(void *ptr, size_t size); + +#define jbd_kmalloc(size, flags) \ + __jbd_kmalloc(__FUNCTION__, (size), (flags), journal_oom_retry) +#define jbd_rep_kmalloc(size, flags) \ + __jbd_kmalloc(__FUNCTION__, (size), (flags), 1) + +#define JFS_MIN_JOURNAL_BLOCKS 1024 + +#ifdef __KERNEL__ + +/** + * typedef handle_t - The handle_t type represents a single atomic update being performed by some process. + * + * All filesystem modifications made by the process go + * through this handle. Recursive operations (such as quota operations) + * are gathered into a single update. + * + * The buffer credits field is used to account for journaled buffers + * being modified by the running process. To ensure that there is + * enough log space for all outstanding operations, we need to limit the + * number of outstanding buffers possible at any time. When the + * operation completes, any buffer credits not used are credited back to + * the transaction, so that at all times we know how many buffers the + * outstanding updates on a transaction might possibly touch. + * + * This is an opaque datatype. + **/ +typedef struct handle_s handle_t; /* Atomic operation type */ + + +/** + * typedef journal_t - The journal_t maintains all of the journaling state information for a single filesystem. + * + * journal_t is linked to from the fs superblock structure. + * + * We use the journal_t to keep track of all outstanding transaction + * activity on the filesystem, and to manage the state of the log + * writing process. + * + * This is an opaque datatype. + **/ +typedef struct journal_s journal_t; /* Journal control structure */ +#endif + +/* + * Internal structures used by the logging mechanism: + */ + +#define JFS_MAGIC_NUMBER 0xc03b3998U /* The first 4 bytes of /dev/random! */ + +/* + * On-disk structures + */ + +/* + * Descriptor block types: + */ + +#define JFS_DESCRIPTOR_BLOCK 1 +#define JFS_COMMIT_BLOCK 2 +#define JFS_SUPERBLOCK_V1 3 +#define JFS_SUPERBLOCK_V2 4 +#define JFS_REVOKE_BLOCK 5 + +/* + * Standard header for all descriptor blocks: + */ +typedef struct journal_header_s +{ + __be32 h_magic; + __be32 h_blocktype; + __be32 h_sequence; +} journal_header_t; + + +/* + * The block tag: used to describe a single buffer in the journal + */ +typedef struct journal_block_tag_s +{ + __be32 t_blocknr; /* The on-disk block number */ + __be32 t_flags; /* See below */ +} journal_block_tag_t; + +/* + * The revoke descriptor: used on disk to describe a series of blocks to + * be revoked from the log + */ +typedef struct journal_revoke_header_s +{ + journal_header_t r_header; + __be32 r_count; /* Count of bytes used in the block */ +} journal_revoke_header_t; + + +/* Definitions for the journal tag flags word: */ +#define JFS_FLAG_ESCAPE 1 /* on-disk block is escaped */ +#define JFS_FLAG_SAME_UUID 2 /* block has same uuid as previous */ +#define JFS_FLAG_DELETED 4 /* block deleted by this transaction */ +#define JFS_FLAG_LAST_TAG 8 /* last tag in this descriptor block */ + + +/* + * The journal superblock. All fields are in big-endian byte order. + */ +typedef struct journal_superblock_s +{ +/* 0x0000 */ + journal_header_t s_header; + +/* 0x000C */ + /* Static information describing the journal */ + __be32 s_blocksize; /* journal device blocksize */ + __be32 s_maxlen; /* total blocks in journal file */ + __be32 s_first; /* first block of log information */ + +/* 0x0018 */ + /* Dynamic information describing the current state of the log */ + __be32 s_sequence; /* first commit ID expected in log */ + __be32 s_start; /* blocknr of start of log */ + +/* 0x0020 */ + /* Error value, as set by journal_abort(). */ + __be32 s_errno; + +/* 0x0024 */ + /* Remaining fields are only valid in a version-2 superblock */ + __be32 s_feature_compat; /* compatible feature set */ + __be32 s_feature_incompat; /* incompatible feature set */ + __be32 s_feature_ro_compat; /* readonly-compatible feature set */ +/* 0x0030 */ + __u8 s_uuid[16]; /* 128-bit uuid for journal */ + +/* 0x0040 */ + __be32 s_nr_users; /* Nr of filesystems sharing log */ + + __be32 s_dynsuper; /* Blocknr of dynamic superblock copy*/ + +/* 0x0048 */ + __be32 s_max_transaction; /* Limit of journal blocks per trans.*/ + __be32 s_max_trans_data; /* Limit of data blocks per trans. */ + +/* 0x0050 */ + __u32 s_padding[44]; + +/* 0x0100 */ + __u8 s_users[16*48]; /* ids of all fs'es sharing the log */ +/* 0x0400 */ +} journal_superblock_t; + +#define JFS_HAS_COMPAT_FEATURE(j,mask) \ + ((j)->j_format_version >= 2 && \ + ((j)->j_superblock->s_feature_compat & cpu_to_be32((mask)))) +#define JFS_HAS_RO_COMPAT_FEATURE(j,mask) \ + ((j)->j_format_version >= 2 && \ + ((j)->j_superblock->s_feature_ro_compat & cpu_to_be32((mask)))) +#define JFS_HAS_INCOMPAT_FEATURE(j,mask) \ + ((j)->j_format_version >= 2 && \ + ((j)->j_superblock->s_feature_incompat & cpu_to_be32((mask)))) + +#define JFS_FEATURE_INCOMPAT_REVOKE 0x00000001 + +/* Features known to this kernel version: */ +#define JFS_KNOWN_COMPAT_FEATURES 0 +#define JFS_KNOWN_ROCOMPAT_FEATURES 0 +#define JFS_KNOWN_INCOMPAT_FEATURES JFS_FEATURE_INCOMPAT_REVOKE + +#ifdef __KERNEL__ + +#include +#include + +#define JBD_ASSERTIONS +#ifdef JBD_ASSERTIONS +#define J_ASSERT(assert) \ +do { \ + if (!(assert)) { \ + printk (KERN_EMERG \ + "Assertion failure in %s() at %s:%d: \"%s\"\n", \ + __FUNCTION__, __FILE__, __LINE__, # assert); \ + BUG(); \ + } \ +} while (0) + +#if defined(CONFIG_BUFFER_DEBUG) +void buffer_assertion_failure(struct buffer_head *bh); +#define J_ASSERT_BH(bh, expr) \ + do { \ + if (!(expr)) \ + buffer_assertion_failure(bh); \ + J_ASSERT(expr); \ + } while (0) +#define J_ASSERT_JH(jh, expr) J_ASSERT_BH(jh2bh(jh), expr) +#else +#define J_ASSERT_BH(bh, expr) J_ASSERT(expr) +#define J_ASSERT_JH(jh, expr) J_ASSERT(expr) +#endif + +#else +#define J_ASSERT(assert) do { } while (0) +#endif /* JBD_ASSERTIONS */ + +#if defined(JBD_PARANOID_IOFAIL) +#define J_EXPECT(expr, why...) J_ASSERT(expr) +#define J_EXPECT_BH(bh, expr, why...) J_ASSERT_BH(bh, expr) +#define J_EXPECT_JH(jh, expr, why...) J_ASSERT_JH(jh, expr) +#else +#define __journal_expect(expr, why...) \ + ({ \ + int val = (expr); \ + if (!val) { \ + printk(KERN_ERR \ + "EXT3-fs unexpected failure: %s;\n",# expr); \ + printk(KERN_ERR why "\n"); \ + } \ + val; \ + }) +#define J_EXPECT(expr, why...) __journal_expect(expr, ## why) +#define J_EXPECT_BH(bh, expr, why...) __journal_expect(expr, ## why) +#define J_EXPECT_JH(jh, expr, why...) __journal_expect(expr, ## why) +#endif + +enum jbd_state_bits { + BH_JBD /* Has an attached ext3 journal_head */ + = BH_PrivateStart, + BH_JWrite, /* Being written to log (@@@ DEBUGGING) */ + BH_Freed, /* Has been freed (truncated) */ + BH_Revoked, /* Has been revoked from the log */ + BH_RevokeValid, /* Revoked flag is valid */ + BH_JBDDirty, /* Is dirty but journaled */ + BH_State, /* Pins most journal_head state */ + BH_JournalHead, /* Pins bh->b_private and jh->b_bh */ + BH_Unshadow, /* Dummy bit, for BJ_Shadow wakeup filtering */ +}; + +BUFFER_FNS(JBD, jbd) +BUFFER_FNS(JWrite, jwrite) +BUFFER_FNS(JBDDirty, jbddirty) +TAS_BUFFER_FNS(JBDDirty, jbddirty) +BUFFER_FNS(Revoked, revoked) +TAS_BUFFER_FNS(Revoked, revoked) +BUFFER_FNS(RevokeValid, revokevalid) +TAS_BUFFER_FNS(RevokeValid, revokevalid) +BUFFER_FNS(Freed, freed) + +static inline struct buffer_head *jh2bh(struct journal_head *jh) +{ + return jh->b_bh; +} + +static inline struct journal_head *bh2jh(struct buffer_head *bh) +{ + return bh->b_private; +} + +static inline void jbd_lock_bh_state(struct buffer_head *bh) +{ + bit_spin_lock(BH_State, &bh->b_state); +} + +static inline int jbd_trylock_bh_state(struct buffer_head *bh) +{ + return bit_spin_trylock(BH_State, &bh->b_state); +} + +static inline int jbd_is_locked_bh_state(struct buffer_head *bh) +{ + return bit_spin_is_locked(BH_State, &bh->b_state); +} + +static inline void jbd_unlock_bh_state(struct buffer_head *bh) +{ + bit_spin_unlock(BH_State, &bh->b_state); +} + +static inline void jbd_lock_bh_journal_head(struct buffer_head *bh) +{ + bit_spin_lock(BH_JournalHead, &bh->b_state); +} + +static inline void jbd_unlock_bh_journal_head(struct buffer_head *bh) +{ + bit_spin_unlock(BH_JournalHead, &bh->b_state); +} + +struct jbd_revoke_table_s; + +/** + * struct handle_s - The handle_s type is the concrete type associated with + * handle_t. + * @h_transaction: Which compound transaction is this update a part of? + * @h_buffer_credits: Number of remaining buffers we are allowed to dirty. + * @h_ref: Reference count on this handle + * @h_err: Field for caller's use to track errors through large fs operations + * @h_sync: flag for sync-on-close + * @h_jdata: flag to force data journaling + * @h_aborted: flag indicating fatal error on handle + **/ + +/* Docbook can't yet cope with the bit fields, but will leave the documentation + * in so it can be fixed later. + */ + +struct handle_s +{ + /* Which compound transaction is this update a part of? */ + transaction_t *h_transaction; + + /* Number of remaining buffers we are allowed to dirty: */ + int h_buffer_credits; + + /* Reference count on this handle */ + int h_ref; + + /* Field for caller's use to track errors through large fs */ + /* operations */ + int h_err; + + /* Flags [no locking] */ + unsigned int h_sync: 1; /* sync-on-close */ + unsigned int h_jdata: 1; /* force data journaling */ + unsigned int h_aborted: 1; /* fatal error on handle */ +}; + + +/* The transaction_t type is the guts of the journaling mechanism. It + * tracks a compound transaction through its various states: + * + * RUNNING: accepting new updates + * LOCKED: Updates still running but we don't accept new ones + * RUNDOWN: Updates are tidying up but have finished requesting + * new buffers to modify (state not used for now) + * FLUSH: All updates complete, but we are still writing to disk + * COMMIT: All data on disk, writing commit record + * FINISHED: We still have to keep the transaction for checkpointing. + * + * The transaction keeps track of all of the buffers modified by a + * running transaction, and all of the buffers committed but not yet + * flushed to home for finished transactions. + */ + +/* + * Lock ranking: + * + * j_list_lock + * ->jbd_lock_bh_journal_head() (This is "innermost") + * + * j_state_lock + * ->jbd_lock_bh_state() + * + * jbd_lock_bh_state() + * ->j_list_lock + * + * j_state_lock + * ->t_handle_lock + * + * j_state_lock + * ->j_list_lock (journal_unmap_buffer) + * + */ + +struct transaction_s +{ + /* Pointer to the journal for this transaction. [no locking] */ + journal_t *t_journal; + + /* Sequence number for this transaction [no locking] */ + tid_t t_tid; + + /* + * Transaction's current state + * [no locking - only kjournald alters this] + * FIXME: needs barriers + * KLUDGE: [use j_state_lock] + */ + enum { + T_RUNNING, + T_LOCKED, + T_RUNDOWN, + T_FLUSH, + T_COMMIT, + T_FINISHED + } t_state; + + /* + * Where in the log does this transaction's commit start? [no locking] + */ + unsigned long t_log_start; + + /* Number of buffers on the t_buffers list [j_list_lock] */ + int t_nr_buffers; + + /* + * Doubly-linked circular list of all buffers reserved but not yet + * modified by this transaction [j_list_lock] + */ + struct journal_head *t_reserved_list; + + /* + * Doubly-linked circular list of all buffers under writeout during + * commit [j_list_lock] + */ + struct journal_head *t_locked_list; + + /* + * Doubly-linked circular list of all metadata buffers owned by this + * transaction [j_list_lock] + */ + struct journal_head *t_buffers; + + /* + * Doubly-linked circular list of all data buffers still to be + * flushed before this transaction can be committed [j_list_lock] + */ + struct journal_head *t_sync_datalist; + + /* + * Doubly-linked circular list of all forget buffers (superseded + * buffers which we can un-checkpoint once this transaction commits) + * [j_list_lock] + */ + struct journal_head *t_forget; + + /* + * Doubly-linked circular list of all buffers still to be flushed before + * this transaction can be checkpointed. [j_list_lock] + */ + struct journal_head *t_checkpoint_list; + + /* + * Doubly-linked circular list of all buffers submitted for IO while + * checkpointing. [j_list_lock] + */ + struct journal_head *t_checkpoint_io_list; + + /* + * Doubly-linked circular list of temporary buffers currently undergoing + * IO in the log [j_list_lock] + */ + struct journal_head *t_iobuf_list; + + /* + * Doubly-linked circular list of metadata buffers being shadowed by log + * IO. The IO buffers on the iobuf list and the shadow buffers on this + * list match each other one for one at all times. [j_list_lock] + */ + struct journal_head *t_shadow_list; + + /* + * Doubly-linked circular list of control buffers being written to the + * log. [j_list_lock] + */ + struct journal_head *t_log_list; + + /* + * Protects info related to handles + */ + spinlock_t t_handle_lock; + + /* + * Number of outstanding updates running on this transaction + * [t_handle_lock] + */ + int t_updates; + + /* + * Number of buffers reserved for use by all handles in this transaction + * handle but not yet modified. [t_handle_lock] + */ + int t_outstanding_credits; + + /* + * Forward and backward links for the circular list of all transactions + * awaiting checkpoint. [j_list_lock] + */ + transaction_t *t_cpnext, *t_cpprev; + + /* + * When will the transaction expire (become due for commit), in jiffies? + * [no locking] + */ + unsigned long t_expires; + + /* + * How many handles used this transaction? [t_handle_lock] + */ + int t_handle_count; + +}; + +/** + * struct journal_s - The journal_s type is the concrete type associated with + * journal_t. + * @j_flags: General journaling state flags + * @j_errno: Is there an outstanding uncleared error on the journal (from a + * prior abort)? + * @j_sb_buffer: First part of superblock buffer + * @j_superblock: Second part of superblock buffer + * @j_format_version: Version of the superblock format + * @j_state_lock: Protect the various scalars in the journal + * @j_barrier_count: Number of processes waiting to create a barrier lock + * @j_barrier: The barrier lock itself + * @j_running_transaction: The current running transaction.. + * @j_committing_transaction: the transaction we are pushing to disk + * @j_checkpoint_transactions: a linked circular list of all transactions + * waiting for checkpointing + * @j_wait_transaction_locked: Wait queue for waiting for a locked transaction + * to start committing, or for a barrier lock to be released + * @j_wait_logspace: Wait queue for waiting for checkpointing to complete + * @j_wait_done_commit: Wait queue for waiting for commit to complete + * @j_wait_checkpoint: Wait queue to trigger checkpointing + * @j_wait_commit: Wait queue to trigger commit + * @j_wait_updates: Wait queue to wait for updates to complete + * @j_checkpoint_mutex: Mutex for locking against concurrent checkpoints + * @j_head: Journal head - identifies the first unused block in the journal + * @j_tail: Journal tail - identifies the oldest still-used block in the + * journal. + * @j_free: Journal free - how many free blocks are there in the journal? + * @j_first: The block number of the first usable block + * @j_last: The block number one beyond the last usable block + * @j_dev: Device where we store the journal + * @j_blocksize: blocksize for the location where we store the journal. + * @j_blk_offset: starting block offset for into the device where we store the + * journal + * @j_fs_dev: Device which holds the client fs. For internal journal this will + * be equal to j_dev + * @j_maxlen: Total maximum capacity of the journal region on disk. + * @j_list_lock: Protects the buffer lists and internal buffer state. + * @j_inode: Optional inode where we store the journal. If present, all journal + * block numbers are mapped into this inode via bmap(). + * @j_tail_sequence: Sequence number of the oldest transaction in the log + * @j_transaction_sequence: Sequence number of the next transaction to grant + * @j_commit_sequence: Sequence number of the most recently committed + * transaction + * @j_commit_request: Sequence number of the most recent transaction wanting + * commit + * @j_uuid: Uuid of client object. + * @j_task: Pointer to the current commit thread for this journal + * @j_max_transaction_buffers: Maximum number of metadata buffers to allow in a + * single compound commit transaction + * @j_commit_interval: What is the maximum transaction lifetime before we begin + * a commit? + * @j_commit_timer: The timer used to wakeup the commit thread + * @j_revoke_lock: Protect the revoke table + * @j_revoke: The revoke table - maintains the list of revoked blocks in the + * current transaction. + * @j_revoke_table: alternate revoke tables for j_revoke + * @j_wbuf: array of buffer_heads for journal_commit_transaction + * @j_wbufsize: maximum number of buffer_heads allowed in j_wbuf, the + * number that will fit in j_blocksize + * @j_last_sync_writer: most recent pid which did a synchronous write + * @j_private: An opaque pointer to fs-private information. + */ + +struct journal_s +{ + /* General journaling state flags [j_state_lock] */ + unsigned long j_flags; + + /* + * Is there an outstanding uncleared error on the journal (from a prior + * abort)? [j_state_lock] + */ + int j_errno; + + /* The superblock buffer */ + struct buffer_head *j_sb_buffer; + journal_superblock_t *j_superblock; + + /* Version of the superblock format */ + int j_format_version; + + /* + * Protect the various scalars in the journal + */ + spinlock_t j_state_lock; + + /* + * Number of processes waiting to create a barrier lock [j_state_lock] + */ + int j_barrier_count; + + /* The barrier lock itself */ + struct mutex j_barrier; + + /* + * Transactions: The current running transaction... + * [j_state_lock] [caller holding open handle] + */ + transaction_t *j_running_transaction; + + /* + * the transaction we are pushing to disk + * [j_state_lock] [caller holding open handle] + */ + transaction_t *j_committing_transaction; + + /* + * ... and a linked circular list of all transactions waiting for + * checkpointing. [j_list_lock] + */ + transaction_t *j_checkpoint_transactions; + + /* + * Wait queue for waiting for a locked transaction to start committing, + * or for a barrier lock to be released + */ + wait_queue_head_t j_wait_transaction_locked; + + /* Wait queue for waiting for checkpointing to complete */ + wait_queue_head_t j_wait_logspace; + + /* Wait queue for waiting for commit to complete */ + wait_queue_head_t j_wait_done_commit; + + /* Wait queue to trigger checkpointing */ + wait_queue_head_t j_wait_checkpoint; + + /* Wait queue to trigger commit */ + wait_queue_head_t j_wait_commit; + + /* Wait queue to wait for updates to complete */ + wait_queue_head_t j_wait_updates; + + /* Semaphore for locking against concurrent checkpoints */ + struct mutex j_checkpoint_mutex; + + /* + * Journal head: identifies the first unused block in the journal. + * [j_state_lock] + */ + unsigned long j_head; + + /* + * Journal tail: identifies the oldest still-used block in the journal. + * [j_state_lock] + */ + unsigned long j_tail; + + /* + * Journal free: how many free blocks are there in the journal? + * [j_state_lock] + */ + unsigned long j_free; + + /* + * Journal start and end: the block numbers of the first usable block + * and one beyond the last usable block in the journal. [j_state_lock] + */ + unsigned long j_first; + unsigned long j_last; + + /* + * Device, blocksize and starting block offset for the location where we + * store the journal. + */ + struct block_device *j_dev; + int j_blocksize; + unsigned long j_blk_offset; + + /* + * Device which holds the client fs. For internal journal this will be + * equal to j_dev. + */ + struct block_device *j_fs_dev; + + /* Total maximum capacity of the journal region on disk. */ + unsigned int j_maxlen; + + /* + * Protects the buffer lists and internal buffer state. + */ + spinlock_t j_list_lock; + + /* Optional inode where we store the journal. If present, all */ + /* journal block numbers are mapped into this inode via */ + /* bmap(). */ + struct inode *j_inode; + + /* + * Sequence number of the oldest transaction in the log [j_state_lock] + */ + tid_t j_tail_sequence; + + /* + * Sequence number of the next transaction to grant [j_state_lock] + */ + tid_t j_transaction_sequence; + + /* + * Sequence number of the most recently committed transaction + * [j_state_lock]. + */ + tid_t j_commit_sequence; + + /* + * Sequence number of the most recent transaction wanting commit + * [j_state_lock] + */ + tid_t j_commit_request; + + /* + * Journal uuid: identifies the object (filesystem, LVM volume etc) + * backed by this journal. This will eventually be replaced by an array + * of uuids, allowing us to index multiple devices within a single + * journal and to perform atomic updates across them. + */ + __u8 j_uuid[16]; + + /* Pointer to the current commit thread for this journal */ + struct task_struct *j_task; + + /* + * Maximum number of metadata buffers to allow in a single compound + * commit transaction + */ + int j_max_transaction_buffers; + + /* + * What is the maximum transaction lifetime before we begin a commit? + */ + unsigned long j_commit_interval; + + /* The timer used to wakeup the commit thread: */ + struct timer_list j_commit_timer; + + /* + * The revoke table: maintains the list of revoked blocks in the + * current transaction. [j_revoke_lock] + */ + spinlock_t j_revoke_lock; + struct jbd_revoke_table_s *j_revoke; + struct jbd_revoke_table_s *j_revoke_table[2]; + + /* + * array of bhs for journal_commit_transaction + */ + struct buffer_head **j_wbuf; + int j_wbufsize; + + pid_t j_last_sync_writer; + + /* + * An opaque pointer to fs-private information. ext3 puts its + * superblock pointer here + */ + void *j_private; +}; + +/* + * Journal flag definitions + */ +#define JFS_UNMOUNT 0x001 /* Journal thread is being destroyed */ +#define JFS_ABORT 0x002 /* Journaling has been aborted for errors. */ +#define JFS_ACK_ERR 0x004 /* The errno in the sb has been acked */ +#define JFS_FLUSHED 0x008 /* The journal superblock has been flushed */ +#define JFS_LOADED 0x010 /* The journal superblock has been loaded */ +#define JFS_BARRIER 0x020 /* Use IDE barriers */ + +/* + * Function declarations for the journaling transaction and buffer + * management + */ + +/* Filing buffers */ +extern void __journal_temp_unlink_buffer(struct journal_head *jh); +extern void journal_unfile_buffer(journal_t *, struct journal_head *); +extern void __journal_unfile_buffer(struct journal_head *); +extern void __journal_refile_buffer(struct journal_head *); +extern void journal_refile_buffer(journal_t *, struct journal_head *); +extern void __journal_file_buffer(struct journal_head *, transaction_t *, int); +extern void __journal_free_buffer(struct journal_head *bh); +extern void journal_file_buffer(struct journal_head *, transaction_t *, int); +extern void __journal_clean_data_list(transaction_t *transaction); + +/* Log buffer allocation */ +extern struct journal_head * journal_get_descriptor_buffer(journal_t *); +int journal_next_log_block(journal_t *, unsigned long *); + +/* Commit management */ +extern void journal_commit_transaction(journal_t *); + +/* Checkpoint list management */ +int __journal_clean_checkpoint_list(journal_t *journal); +int __journal_remove_checkpoint(struct journal_head *); +void __journal_insert_checkpoint(struct journal_head *, transaction_t *); + +/* Buffer IO */ +extern int +journal_write_metadata_buffer(transaction_t *transaction, + struct journal_head *jh_in, + struct journal_head **jh_out, + unsigned long blocknr); + +/* Transaction locking */ +extern void __wait_on_journal (journal_t *); + +/* + * Journal locking. + * + * We need to lock the journal during transaction state changes so that nobody + * ever tries to take a handle on the running transaction while we are in the + * middle of moving it to the commit phase. j_state_lock does this. + * + * Note that the locking is completely interrupt unsafe. We never touch + * journal structures from interrupts. + */ + +static inline handle_t *journal_current_handle(void) +{ + return current->journal_info; +} + +/* The journaling code user interface: + * + * Create and destroy handles + * Register buffer modifications against the current transaction. + */ + +extern handle_t *journal_start(journal_t *, int nblocks); +extern int journal_restart (handle_t *, int nblocks); +extern int journal_extend (handle_t *, int nblocks); +extern int journal_get_write_access(handle_t *, struct buffer_head *); +extern int journal_get_create_access (handle_t *, struct buffer_head *); +extern int journal_get_undo_access(handle_t *, struct buffer_head *); +extern int journal_dirty_data (handle_t *, struct buffer_head *); +extern int journal_dirty_metadata (handle_t *, struct buffer_head *); +extern void journal_release_buffer (handle_t *, struct buffer_head *); +extern int journal_forget (handle_t *, struct buffer_head *); +extern void journal_sync_buffer (struct buffer_head *); +extern void journal_invalidatepage(journal_t *, + struct page *, unsigned long); +extern int journal_try_to_free_buffers(journal_t *, struct page *, gfp_t); +extern int journal_stop(handle_t *); +extern int journal_flush (journal_t *); +extern void journal_lock_updates (journal_t *); +extern void journal_unlock_updates (journal_t *); + +extern journal_t * journal_init_dev(struct block_device *bdev, + struct block_device *fs_dev, + int start, int len, int bsize); +extern journal_t * journal_init_inode (struct inode *); +extern int journal_update_format (journal_t *); +extern int journal_check_used_features + (journal_t *, unsigned long, unsigned long, unsigned long); +extern int journal_check_available_features + (journal_t *, unsigned long, unsigned long, unsigned long); +extern int journal_set_features + (journal_t *, unsigned long, unsigned long, unsigned long); +extern int journal_create (journal_t *); +extern int journal_load (journal_t *journal); +extern void journal_destroy (journal_t *); +extern int journal_recover (journal_t *journal); +extern int journal_wipe (journal_t *, int); +extern int journal_skip_recovery (journal_t *); +extern void journal_update_superblock (journal_t *, int); +extern void __journal_abort_hard (journal_t *); +extern void journal_abort (journal_t *, int); +extern int journal_errno (journal_t *); +extern void journal_ack_err (journal_t *); +extern int journal_clear_err (journal_t *); +extern int journal_bmap(journal_t *, unsigned long, unsigned long *); +extern int journal_force_commit(journal_t *); + +/* + * journal_head management + */ +struct journal_head *journal_add_journal_head(struct buffer_head *bh); +struct journal_head *journal_grab_journal_head(struct buffer_head *bh); +void journal_remove_journal_head(struct buffer_head *bh); +void journal_put_journal_head(struct journal_head *jh); + +/* + * handle management + */ +extern kmem_cache_t *jbd_handle_cache; + +static inline handle_t *jbd_alloc_handle(gfp_t gfp_flags) +{ + return kmem_cache_alloc(jbd_handle_cache, gfp_flags); +} + +static inline void jbd_free_handle(handle_t *handle) +{ + kmem_cache_free(jbd_handle_cache, handle); +} + +/* Primary revoke support */ +#define JOURNAL_REVOKE_DEFAULT_HASH 256 +extern int journal_init_revoke(journal_t *, int); +extern void journal_destroy_revoke_caches(void); +extern int journal_init_revoke_caches(void); + +extern void journal_destroy_revoke(journal_t *); +extern int journal_revoke (handle_t *, + unsigned long, struct buffer_head *); +extern int journal_cancel_revoke(handle_t *, struct journal_head *); +extern void journal_write_revoke_records(journal_t *, transaction_t *); + +/* Recovery revoke support */ +extern int journal_set_revoke(journal_t *, unsigned long, tid_t); +extern int journal_test_revoke(journal_t *, unsigned long, tid_t); +extern void journal_clear_revoke(journal_t *); +extern void journal_switch_revoke_table(journal_t *journal); + +/* + * The log thread user interface: + * + * Request space in the current transaction, and force transaction commit + * transitions on demand. + */ + +int __log_space_left(journal_t *); /* Called with journal locked */ +int log_start_commit(journal_t *journal, tid_t tid); +int __log_start_commit(journal_t *journal, tid_t tid); +int journal_start_commit(journal_t *journal, tid_t *tid); +int journal_force_commit_nested(journal_t *journal); +int log_wait_commit(journal_t *journal, tid_t tid); +int log_do_checkpoint(journal_t *journal); + +void __log_wait_for_space(journal_t *journal); +extern void __journal_drop_transaction(journal_t *, transaction_t *); +extern int cleanup_journal_tail(journal_t *); + +/* Debugging code only: */ + +#define jbd_ENOSYS() \ +do { \ + printk (KERN_ERR "JBD unimplemented function %s\n", __FUNCTION__); \ + current->state = TASK_UNINTERRUPTIBLE; \ + schedule(); \ +} while (1) + +/* + * is_journal_abort + * + * Simple test wrapper function to test the JFS_ABORT state flag. This + * bit, when set, indicates that we have had a fatal error somewhere, + * either inside the journaling layer or indicated to us by the client + * (eg. ext3), and that we and should not commit any further + * transactions. + */ + +static inline int is_journal_aborted(journal_t *journal) +{ + return journal->j_flags & JFS_ABORT; +} + +static inline int is_handle_aborted(handle_t *handle) +{ + if (handle->h_aborted) + return 1; + return is_journal_aborted(handle->h_transaction->t_journal); +} + +static inline void journal_abort_handle(handle_t *handle) +{ + handle->h_aborted = 1; +} + +#endif /* __KERNEL__ */ + +/* Comparison functions for transaction IDs: perform comparisons using + * modulo arithmetic so that they work over sequence number wraps. */ + +static inline int tid_gt(tid_t x, tid_t y) +{ + int difference = (x - y); + return (difference > 0); +} + +static inline int tid_geq(tid_t x, tid_t y) +{ + int difference = (x - y); + return (difference >= 0); +} + +extern int journal_blocks_per_page(struct inode *inode); + +/* + * Return the minimum number of blocks which must be free in the journal + * before a new transaction may be started. Must be called under j_state_lock. + */ +static inline int jbd_space_needed(journal_t *journal) +{ + int nblocks = journal->j_max_transaction_buffers; + if (journal->j_committing_transaction) + nblocks += journal->j_committing_transaction-> + t_outstanding_credits; + return nblocks; +} + +/* + * Definitions which augment the buffer_head layer + */ + +/* journaling buffer types */ +#define BJ_None 0 /* Not journaled */ +#define BJ_SyncData 1 /* Normal data: flush before commit */ +#define BJ_Metadata 2 /* Normal journaled metadata */ +#define BJ_Forget 3 /* Buffer superseded by this transaction */ +#define BJ_IO 4 /* Buffer is for temporary IO use */ +#define BJ_Shadow 5 /* Buffer contents being shadowed to the log */ +#define BJ_LogCtl 6 /* Buffer contains log descriptors */ +#define BJ_Reserved 7 /* Buffer is reserved for access by journal */ +#define BJ_Locked 8 /* Locked for I/O during commit */ +#define BJ_Types 9 + +extern int jbd_blocks_per_page(struct inode *inode); + +#ifdef __KERNEL__ + +#define buffer_trace_init(bh) do {} while (0) +#define print_buffer_fields(bh) do {} while (0) +#define print_buffer_trace(bh) do {} while (0) +#define BUFFER_TRACE(bh, info) do {} while (0) +#define BUFFER_TRACE2(bh, bh2, info) do {} while (0) +#define JBUFFER_TRACE(jh, info) do {} while (0) + +#endif /* __KERNEL__ */ + +#endif /* _LINUX_JBD_H */ -- cgit v1.2.3 From f7f4bccb729844a0fa873e224e3a6f7eeed095bb Mon Sep 17 00:00:00 2001 From: Mingming Cao Date: Wed, 11 Oct 2006 01:20:59 -0700 Subject: [PATCH] jbd2: rename jbd2 symbols to avoid duplication of jbd symbols Mingming Cao originally did this work, and Shaggy reproduced it using some scripts from her. Signed-off-by: Mingming Cao Signed-off-by: Dave Kleikamp Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ext4_jbd2.h | 26 ++--- include/linux/jbd2.h | 248 +++++++++++++++++++++++----------------------- 2 files changed, 137 insertions(+), 137 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ext4_jbd2.h b/include/linux/ext4_jbd2.h index 3dbf6c779037..99d37557cbb4 100644 --- a/include/linux/ext4_jbd2.h +++ b/include/linux/ext4_jbd2.h @@ -1,5 +1,5 @@ /* - * linux/include/linux/ext4_jbd.h + * linux/include/linux/ext4_jbd2.h * * Written by Stephen C. Tweedie , 1999 * @@ -16,7 +16,7 @@ #define _LINUX_EXT4_JBD_H #include -#include +#include #include #define EXT4_JOURNAL(inode) (EXT4_SB((inode)->i_sb)->s_journal) @@ -116,7 +116,7 @@ static inline int __ext4_journal_get_undo_access(const char *where, handle_t *handle, struct buffer_head *bh) { - int err = journal_get_undo_access(handle, bh); + int err = jbd2_journal_get_undo_access(handle, bh); if (err) ext4_journal_abort_handle(where, __FUNCTION__, bh, handle,err); return err; @@ -126,7 +126,7 @@ static inline int __ext4_journal_get_write_access(const char *where, handle_t *handle, struct buffer_head *bh) { - int err = journal_get_write_access(handle, bh); + int err = jbd2_journal_get_write_access(handle, bh); if (err) ext4_journal_abort_handle(where, __FUNCTION__, bh, handle,err); return err; @@ -135,13 +135,13 @@ __ext4_journal_get_write_access(const char *where, handle_t *handle, static inline void ext4_journal_release_buffer(handle_t *handle, struct buffer_head *bh) { - journal_release_buffer(handle, bh); + jbd2_journal_release_buffer(handle, bh); } static inline int __ext4_journal_forget(const char *where, handle_t *handle, struct buffer_head *bh) { - int err = journal_forget(handle, bh); + int err = jbd2_journal_forget(handle, bh); if (err) ext4_journal_abort_handle(where, __FUNCTION__, bh, handle,err); return err; @@ -151,7 +151,7 @@ static inline int __ext4_journal_revoke(const char *where, handle_t *handle, unsigned long blocknr, struct buffer_head *bh) { - int err = journal_revoke(handle, blocknr, bh); + int err = jbd2_journal_revoke(handle, blocknr, bh); if (err) ext4_journal_abort_handle(where, __FUNCTION__, bh, handle,err); return err; @@ -161,7 +161,7 @@ static inline int __ext4_journal_get_create_access(const char *where, handle_t *handle, struct buffer_head *bh) { - int err = journal_get_create_access(handle, bh); + int err = jbd2_journal_get_create_access(handle, bh); if (err) ext4_journal_abort_handle(where, __FUNCTION__, bh, handle,err); return err; @@ -171,7 +171,7 @@ static inline int __ext4_journal_dirty_metadata(const char *where, handle_t *handle, struct buffer_head *bh) { - int err = journal_dirty_metadata(handle, bh); + int err = jbd2_journal_dirty_metadata(handle, bh); if (err) ext4_journal_abort_handle(where, __FUNCTION__, bh, handle,err); return err; @@ -211,22 +211,22 @@ static inline handle_t *ext4_journal_current_handle(void) static inline int ext4_journal_extend(handle_t *handle, int nblocks) { - return journal_extend(handle, nblocks); + return jbd2_journal_extend(handle, nblocks); } static inline int ext4_journal_restart(handle_t *handle, int nblocks) { - return journal_restart(handle, nblocks); + return jbd2_journal_restart(handle, nblocks); } static inline int ext4_journal_blocks_per_page(struct inode *inode) { - return journal_blocks_per_page(inode); + return jbd2_journal_blocks_per_page(inode); } static inline int ext4_journal_force_commit(journal_t *journal) { - return journal_force_commit(journal); + return jbd2_journal_force_commit(journal); } /* super.c */ diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index fe89444b1c6f..3251f7abb57d 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1,5 +1,5 @@ /* - * linux/include/linux/jbd.h + * linux/include/linux/jbd2.h * * Written by Stephen C. Tweedie * @@ -19,7 +19,7 @@ /* Allow this file to be included directly into e2fsprogs */ #ifndef __KERNEL__ #include "jfs_compat.h" -#define JFS_DEBUG +#define JBD2_DEBUG #define jfs_debug jbd_debug #else @@ -57,11 +57,11 @@ * CONFIG_JBD_DEBUG is on. */ #define JBD_EXPENSIVE_CHECKING -extern int journal_enable_debug; +extern int jbd2_journal_enable_debug; #define jbd_debug(n, f, a...) \ do { \ - if ((n) <= journal_enable_debug) { \ + if ((n) <= jbd2_journal_enable_debug) { \ printk (KERN_DEBUG "(%s, %d): %s: ", \ __FILE__, __LINE__, __FUNCTION__); \ printk (f, ## a); \ @@ -71,16 +71,16 @@ extern int journal_enable_debug; #define jbd_debug(f, a...) /**/ #endif -extern void * __jbd_kmalloc (const char *where, size_t size, gfp_t flags, int retry); -extern void * jbd_slab_alloc(size_t size, gfp_t flags); -extern void jbd_slab_free(void *ptr, size_t size); +extern void * __jbd2_kmalloc (const char *where, size_t size, gfp_t flags, int retry); +extern void * jbd2_slab_alloc(size_t size, gfp_t flags); +extern void jbd2_slab_free(void *ptr, size_t size); #define jbd_kmalloc(size, flags) \ - __jbd_kmalloc(__FUNCTION__, (size), (flags), journal_oom_retry) + __jbd2_kmalloc(__FUNCTION__, (size), (flags), journal_oom_retry) #define jbd_rep_kmalloc(size, flags) \ - __jbd_kmalloc(__FUNCTION__, (size), (flags), 1) + __jbd2_kmalloc(__FUNCTION__, (size), (flags), 1) -#define JFS_MIN_JOURNAL_BLOCKS 1024 +#define JBD2_MIN_JOURNAL_BLOCKS 1024 #ifdef __KERNEL__ @@ -122,7 +122,7 @@ typedef struct journal_s journal_t; /* Journal control structure */ * Internal structures used by the logging mechanism: */ -#define JFS_MAGIC_NUMBER 0xc03b3998U /* The first 4 bytes of /dev/random! */ +#define JBD2_MAGIC_NUMBER 0xc03b3998U /* The first 4 bytes of /dev/random! */ /* * On-disk structures @@ -132,11 +132,11 @@ typedef struct journal_s journal_t; /* Journal control structure */ * Descriptor block types: */ -#define JFS_DESCRIPTOR_BLOCK 1 -#define JFS_COMMIT_BLOCK 2 -#define JFS_SUPERBLOCK_V1 3 -#define JFS_SUPERBLOCK_V2 4 -#define JFS_REVOKE_BLOCK 5 +#define JBD2_DESCRIPTOR_BLOCK 1 +#define JBD2_COMMIT_BLOCK 2 +#define JBD2_SUPERBLOCK_V1 3 +#define JBD2_SUPERBLOCK_V2 4 +#define JBD2_REVOKE_BLOCK 5 /* * Standard header for all descriptor blocks: @@ -162,18 +162,18 @@ typedef struct journal_block_tag_s * The revoke descriptor: used on disk to describe a series of blocks to * be revoked from the log */ -typedef struct journal_revoke_header_s +typedef struct jbd2_journal_revoke_header_s { journal_header_t r_header; __be32 r_count; /* Count of bytes used in the block */ -} journal_revoke_header_t; +} jbd2_journal_revoke_header_t; /* Definitions for the journal tag flags word: */ -#define JFS_FLAG_ESCAPE 1 /* on-disk block is escaped */ -#define JFS_FLAG_SAME_UUID 2 /* block has same uuid as previous */ -#define JFS_FLAG_DELETED 4 /* block deleted by this transaction */ -#define JFS_FLAG_LAST_TAG 8 /* last tag in this descriptor block */ +#define JBD2_FLAG_ESCAPE 1 /* on-disk block is escaped */ +#define JBD2_FLAG_SAME_UUID 2 /* block has same uuid as previous */ +#define JBD2_FLAG_DELETED 4 /* block deleted by this transaction */ +#define JBD2_FLAG_LAST_TAG 8 /* last tag in this descriptor block */ /* @@ -196,7 +196,7 @@ typedef struct journal_superblock_s __be32 s_start; /* blocknr of start of log */ /* 0x0020 */ - /* Error value, as set by journal_abort(). */ + /* Error value, as set by jbd2_journal_abort(). */ __be32 s_errno; /* 0x0024 */ @@ -224,22 +224,22 @@ typedef struct journal_superblock_s /* 0x0400 */ } journal_superblock_t; -#define JFS_HAS_COMPAT_FEATURE(j,mask) \ +#define JBD2_HAS_COMPAT_FEATURE(j,mask) \ ((j)->j_format_version >= 2 && \ ((j)->j_superblock->s_feature_compat & cpu_to_be32((mask)))) -#define JFS_HAS_RO_COMPAT_FEATURE(j,mask) \ +#define JBD2_HAS_RO_COMPAT_FEATURE(j,mask) \ ((j)->j_format_version >= 2 && \ ((j)->j_superblock->s_feature_ro_compat & cpu_to_be32((mask)))) -#define JFS_HAS_INCOMPAT_FEATURE(j,mask) \ +#define JBD2_HAS_INCOMPAT_FEATURE(j,mask) \ ((j)->j_format_version >= 2 && \ ((j)->j_superblock->s_feature_incompat & cpu_to_be32((mask)))) -#define JFS_FEATURE_INCOMPAT_REVOKE 0x00000001 +#define JBD2_FEATURE_INCOMPAT_REVOKE 0x00000001 /* Features known to this kernel version: */ -#define JFS_KNOWN_COMPAT_FEATURES 0 -#define JFS_KNOWN_ROCOMPAT_FEATURES 0 -#define JFS_KNOWN_INCOMPAT_FEATURES JFS_FEATURE_INCOMPAT_REVOKE +#define JBD2_KNOWN_COMPAT_FEATURES 0 +#define JBD2_KNOWN_ROCOMPAT_FEATURES 0 +#define JBD2_KNOWN_INCOMPAT_FEATURES JBD2_FEATURE_INCOMPAT_REVOKE #ifdef __KERNEL__ @@ -359,7 +359,7 @@ static inline void jbd_unlock_bh_journal_head(struct buffer_head *bh) bit_spin_unlock(BH_JournalHead, &bh->b_state); } -struct jbd_revoke_table_s; +struct jbd2_revoke_table_s; /** * struct handle_s - The handle_s type is the concrete type associated with @@ -445,7 +445,7 @@ struct transaction_s /* * Transaction's current state - * [no locking - only kjournald alters this] + * [no locking - only kjournald2 alters this] * FIXME: needs barriers * KLUDGE: [use j_state_lock] */ @@ -621,7 +621,7 @@ struct transaction_s * @j_revoke: The revoke table - maintains the list of revoked blocks in the * current transaction. * @j_revoke_table: alternate revoke tables for j_revoke - * @j_wbuf: array of buffer_heads for journal_commit_transaction + * @j_wbuf: array of buffer_heads for jbd2_journal_commit_transaction * @j_wbufsize: maximum number of buffer_heads allowed in j_wbuf, the * number that will fit in j_blocksize * @j_last_sync_writer: most recent pid which did a synchronous write @@ -805,11 +805,11 @@ struct journal_s * current transaction. [j_revoke_lock] */ spinlock_t j_revoke_lock; - struct jbd_revoke_table_s *j_revoke; - struct jbd_revoke_table_s *j_revoke_table[2]; + struct jbd2_revoke_table_s *j_revoke; + struct jbd2_revoke_table_s *j_revoke_table[2]; /* - * array of bhs for journal_commit_transaction + * array of bhs for jbd2_journal_commit_transaction */ struct buffer_head **j_wbuf; int j_wbufsize; @@ -826,12 +826,12 @@ struct journal_s /* * Journal flag definitions */ -#define JFS_UNMOUNT 0x001 /* Journal thread is being destroyed */ -#define JFS_ABORT 0x002 /* Journaling has been aborted for errors. */ -#define JFS_ACK_ERR 0x004 /* The errno in the sb has been acked */ -#define JFS_FLUSHED 0x008 /* The journal superblock has been flushed */ -#define JFS_LOADED 0x010 /* The journal superblock has been loaded */ -#define JFS_BARRIER 0x020 /* Use IDE barriers */ +#define JBD2_UNMOUNT 0x001 /* Journal thread is being destroyed */ +#define JBD2_ABORT 0x002 /* Journaling has been aborted for errors. */ +#define JBD2_ACK_ERR 0x004 /* The errno in the sb has been acked */ +#define JBD2_FLUSHED 0x008 /* The journal superblock has been flushed */ +#define JBD2_LOADED 0x010 /* The journal superblock has been loaded */ +#define JBD2_BARRIER 0x020 /* Use IDE barriers */ /* * Function declarations for the journaling transaction and buffer @@ -839,31 +839,31 @@ struct journal_s */ /* Filing buffers */ -extern void __journal_temp_unlink_buffer(struct journal_head *jh); -extern void journal_unfile_buffer(journal_t *, struct journal_head *); -extern void __journal_unfile_buffer(struct journal_head *); -extern void __journal_refile_buffer(struct journal_head *); -extern void journal_refile_buffer(journal_t *, struct journal_head *); -extern void __journal_file_buffer(struct journal_head *, transaction_t *, int); +extern void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh); +extern void jbd2_journal_unfile_buffer(journal_t *, struct journal_head *); +extern void __jbd2_journal_unfile_buffer(struct journal_head *); +extern void __jbd2_journal_refile_buffer(struct journal_head *); +extern void jbd2_journal_refile_buffer(journal_t *, struct journal_head *); +extern void __jbd2_journal_file_buffer(struct journal_head *, transaction_t *, int); extern void __journal_free_buffer(struct journal_head *bh); -extern void journal_file_buffer(struct journal_head *, transaction_t *, int); +extern void jbd2_journal_file_buffer(struct journal_head *, transaction_t *, int); extern void __journal_clean_data_list(transaction_t *transaction); /* Log buffer allocation */ -extern struct journal_head * journal_get_descriptor_buffer(journal_t *); -int journal_next_log_block(journal_t *, unsigned long *); +extern struct journal_head * jbd2_journal_get_descriptor_buffer(journal_t *); +int jbd2_journal_next_log_block(journal_t *, unsigned long *); /* Commit management */ -extern void journal_commit_transaction(journal_t *); +extern void jbd2_journal_commit_transaction(journal_t *); /* Checkpoint list management */ -int __journal_clean_checkpoint_list(journal_t *journal); -int __journal_remove_checkpoint(struct journal_head *); -void __journal_insert_checkpoint(struct journal_head *, transaction_t *); +int __jbd2_journal_clean_checkpoint_list(journal_t *journal); +int __jbd2_journal_remove_checkpoint(struct journal_head *); +void __jbd2_journal_insert_checkpoint(struct journal_head *, transaction_t *); /* Buffer IO */ extern int -journal_write_metadata_buffer(transaction_t *transaction, +jbd2_journal_write_metadata_buffer(transaction_t *transaction, struct journal_head *jh_in, struct journal_head **jh_out, unsigned long blocknr); @@ -893,91 +893,91 @@ static inline handle_t *journal_current_handle(void) * Register buffer modifications against the current transaction. */ -extern handle_t *journal_start(journal_t *, int nblocks); -extern int journal_restart (handle_t *, int nblocks); -extern int journal_extend (handle_t *, int nblocks); -extern int journal_get_write_access(handle_t *, struct buffer_head *); -extern int journal_get_create_access (handle_t *, struct buffer_head *); -extern int journal_get_undo_access(handle_t *, struct buffer_head *); -extern int journal_dirty_data (handle_t *, struct buffer_head *); -extern int journal_dirty_metadata (handle_t *, struct buffer_head *); -extern void journal_release_buffer (handle_t *, struct buffer_head *); -extern int journal_forget (handle_t *, struct buffer_head *); +extern handle_t *jbd2_journal_start(journal_t *, int nblocks); +extern int jbd2_journal_restart (handle_t *, int nblocks); +extern int jbd2_journal_extend (handle_t *, int nblocks); +extern int jbd2_journal_get_write_access(handle_t *, struct buffer_head *); +extern int jbd2_journal_get_create_access (handle_t *, struct buffer_head *); +extern int jbd2_journal_get_undo_access(handle_t *, struct buffer_head *); +extern int jbd2_journal_dirty_data (handle_t *, struct buffer_head *); +extern int jbd2_journal_dirty_metadata (handle_t *, struct buffer_head *); +extern void jbd2_journal_release_buffer (handle_t *, struct buffer_head *); +extern int jbd2_journal_forget (handle_t *, struct buffer_head *); extern void journal_sync_buffer (struct buffer_head *); -extern void journal_invalidatepage(journal_t *, +extern void jbd2_journal_invalidatepage(journal_t *, struct page *, unsigned long); -extern int journal_try_to_free_buffers(journal_t *, struct page *, gfp_t); -extern int journal_stop(handle_t *); -extern int journal_flush (journal_t *); -extern void journal_lock_updates (journal_t *); -extern void journal_unlock_updates (journal_t *); +extern int jbd2_journal_try_to_free_buffers(journal_t *, struct page *, gfp_t); +extern int jbd2_journal_stop(handle_t *); +extern int jbd2_journal_flush (journal_t *); +extern void jbd2_journal_lock_updates (journal_t *); +extern void jbd2_journal_unlock_updates (journal_t *); -extern journal_t * journal_init_dev(struct block_device *bdev, +extern journal_t * jbd2_journal_init_dev(struct block_device *bdev, struct block_device *fs_dev, int start, int len, int bsize); -extern journal_t * journal_init_inode (struct inode *); -extern int journal_update_format (journal_t *); -extern int journal_check_used_features +extern journal_t * jbd2_journal_init_inode (struct inode *); +extern int jbd2_journal_update_format (journal_t *); +extern int jbd2_journal_check_used_features (journal_t *, unsigned long, unsigned long, unsigned long); -extern int journal_check_available_features +extern int jbd2_journal_check_available_features (journal_t *, unsigned long, unsigned long, unsigned long); -extern int journal_set_features +extern int jbd2_journal_set_features (journal_t *, unsigned long, unsigned long, unsigned long); -extern int journal_create (journal_t *); -extern int journal_load (journal_t *journal); -extern void journal_destroy (journal_t *); -extern int journal_recover (journal_t *journal); -extern int journal_wipe (journal_t *, int); -extern int journal_skip_recovery (journal_t *); -extern void journal_update_superblock (journal_t *, int); -extern void __journal_abort_hard (journal_t *); -extern void journal_abort (journal_t *, int); -extern int journal_errno (journal_t *); -extern void journal_ack_err (journal_t *); -extern int journal_clear_err (journal_t *); -extern int journal_bmap(journal_t *, unsigned long, unsigned long *); -extern int journal_force_commit(journal_t *); +extern int jbd2_journal_create (journal_t *); +extern int jbd2_journal_load (journal_t *journal); +extern void jbd2_journal_destroy (journal_t *); +extern int jbd2_journal_recover (journal_t *journal); +extern int jbd2_journal_wipe (journal_t *, int); +extern int jbd2_journal_skip_recovery (journal_t *); +extern void jbd2_journal_update_superblock (journal_t *, int); +extern void __jbd2_journal_abort_hard (journal_t *); +extern void jbd2_journal_abort (journal_t *, int); +extern int jbd2_journal_errno (journal_t *); +extern void jbd2_journal_ack_err (journal_t *); +extern int jbd2_journal_clear_err (journal_t *); +extern int jbd2_journal_bmap(journal_t *, unsigned long, unsigned long *); +extern int jbd2_journal_force_commit(journal_t *); /* * journal_head management */ -struct journal_head *journal_add_journal_head(struct buffer_head *bh); -struct journal_head *journal_grab_journal_head(struct buffer_head *bh); -void journal_remove_journal_head(struct buffer_head *bh); -void journal_put_journal_head(struct journal_head *jh); +struct journal_head *jbd2_journal_add_journal_head(struct buffer_head *bh); +struct journal_head *jbd2_journal_grab_journal_head(struct buffer_head *bh); +void jbd2_journal_remove_journal_head(struct buffer_head *bh); +void jbd2_journal_put_journal_head(struct journal_head *jh); /* * handle management */ -extern kmem_cache_t *jbd_handle_cache; +extern kmem_cache_t *jbd2_handle_cache; static inline handle_t *jbd_alloc_handle(gfp_t gfp_flags) { - return kmem_cache_alloc(jbd_handle_cache, gfp_flags); + return kmem_cache_alloc(jbd2_handle_cache, gfp_flags); } static inline void jbd_free_handle(handle_t *handle) { - kmem_cache_free(jbd_handle_cache, handle); + kmem_cache_free(jbd2_handle_cache, handle); } /* Primary revoke support */ #define JOURNAL_REVOKE_DEFAULT_HASH 256 -extern int journal_init_revoke(journal_t *, int); -extern void journal_destroy_revoke_caches(void); -extern int journal_init_revoke_caches(void); +extern int jbd2_journal_init_revoke(journal_t *, int); +extern void jbd2_journal_destroy_revoke_caches(void); +extern int jbd2_journal_init_revoke_caches(void); -extern void journal_destroy_revoke(journal_t *); -extern int journal_revoke (handle_t *, +extern void jbd2_journal_destroy_revoke(journal_t *); +extern int jbd2_journal_revoke (handle_t *, unsigned long, struct buffer_head *); -extern int journal_cancel_revoke(handle_t *, struct journal_head *); -extern void journal_write_revoke_records(journal_t *, transaction_t *); +extern int jbd2_journal_cancel_revoke(handle_t *, struct journal_head *); +extern void jbd2_journal_write_revoke_records(journal_t *, transaction_t *); /* Recovery revoke support */ -extern int journal_set_revoke(journal_t *, unsigned long, tid_t); -extern int journal_test_revoke(journal_t *, unsigned long, tid_t); -extern void journal_clear_revoke(journal_t *); -extern void journal_switch_revoke_table(journal_t *journal); +extern int jbd2_journal_set_revoke(journal_t *, unsigned long, tid_t); +extern int jbd2_journal_test_revoke(journal_t *, unsigned long, tid_t); +extern void jbd2_journal_clear_revoke(journal_t *); +extern void jbd2_journal_switch_revoke_table(journal_t *journal); /* * The log thread user interface: @@ -986,17 +986,17 @@ extern void journal_switch_revoke_table(journal_t *journal); * transitions on demand. */ -int __log_space_left(journal_t *); /* Called with journal locked */ -int log_start_commit(journal_t *journal, tid_t tid); -int __log_start_commit(journal_t *journal, tid_t tid); -int journal_start_commit(journal_t *journal, tid_t *tid); -int journal_force_commit_nested(journal_t *journal); -int log_wait_commit(journal_t *journal, tid_t tid); -int log_do_checkpoint(journal_t *journal); +int __jbd2_log_space_left(journal_t *); /* Called with journal locked */ +int jbd2_log_start_commit(journal_t *journal, tid_t tid); +int __jbd2_log_start_commit(journal_t *journal, tid_t tid); +int jbd2_journal_start_commit(journal_t *journal, tid_t *tid); +int jbd2_journal_force_commit_nested(journal_t *journal); +int jbd2_log_wait_commit(journal_t *journal, tid_t tid); +int jbd2_log_do_checkpoint(journal_t *journal); -void __log_wait_for_space(journal_t *journal); -extern void __journal_drop_transaction(journal_t *, transaction_t *); -extern int cleanup_journal_tail(journal_t *); +void __jbd2_log_wait_for_space(journal_t *journal); +extern void __jbd2_journal_drop_transaction(journal_t *, transaction_t *); +extern int jbd2_cleanup_journal_tail(journal_t *); /* Debugging code only: */ @@ -1010,7 +1010,7 @@ do { \ /* * is_journal_abort * - * Simple test wrapper function to test the JFS_ABORT state flag. This + * Simple test wrapper function to test the JBD2_ABORT state flag. This * bit, when set, indicates that we have had a fatal error somewhere, * either inside the journaling layer or indicated to us by the client * (eg. ext3), and that we and should not commit any further @@ -1019,7 +1019,7 @@ do { \ static inline int is_journal_aborted(journal_t *journal) { - return journal->j_flags & JFS_ABORT; + return journal->j_flags & JBD2_ABORT; } static inline int is_handle_aborted(handle_t *handle) @@ -1029,7 +1029,7 @@ static inline int is_handle_aborted(handle_t *handle) return is_journal_aborted(handle->h_transaction->t_journal); } -static inline void journal_abort_handle(handle_t *handle) +static inline void jbd2_journal_abort_handle(handle_t *handle) { handle->h_aborted = 1; } @@ -1051,7 +1051,7 @@ static inline int tid_geq(tid_t x, tid_t y) return (difference >= 0); } -extern int journal_blocks_per_page(struct inode *inode); +extern int jbd2_journal_blocks_per_page(struct inode *inode); /* * Return the minimum number of blocks which must be free in the journal -- cgit v1.2.3 From c3fcc8137ce4296ad6ab94f88bd60cbe03d21527 Mon Sep 17 00:00:00 2001 From: Dave Kleikamp Date: Wed, 11 Oct 2006 01:21:02 -0700 Subject: [PATCH] jbd2: cleanup ext4_jbd.h To allow ext4 to build during the transition from jbd to jbd2, we have both ext4_jbd.h and ext4_jbd2.h in the tree. We no longer need the former. Signed-off-by: Dave Kleikamp Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ext4_jbd.h | 268 ----------------------------------------------- 1 file changed, 268 deletions(-) delete mode 100644 include/linux/ext4_jbd.h (limited to 'include/linux') diff --git a/include/linux/ext4_jbd.h b/include/linux/ext4_jbd.h deleted file mode 100644 index 3dbf6c779037..000000000000 --- a/include/linux/ext4_jbd.h +++ /dev/null @@ -1,268 +0,0 @@ -/* - * linux/include/linux/ext4_jbd.h - * - * Written by Stephen C. Tweedie , 1999 - * - * Copyright 1998--1999 Red Hat corp --- All Rights Reserved - * - * This file is part of the Linux kernel and is made available under - * the terms of the GNU General Public License, version 2, or at your - * option, any later version, incorporated herein by reference. - * - * Ext4-specific journaling extensions. - */ - -#ifndef _LINUX_EXT4_JBD_H -#define _LINUX_EXT4_JBD_H - -#include -#include -#include - -#define EXT4_JOURNAL(inode) (EXT4_SB((inode)->i_sb)->s_journal) - -/* Define the number of blocks we need to account to a transaction to - * modify one block of data. - * - * We may have to touch one inode, one bitmap buffer, up to three - * indirection blocks, the group and superblock summaries, and the data - * block to complete the transaction. */ - -#define EXT4_SINGLEDATA_TRANS_BLOCKS 8U - -/* Extended attribute operations touch at most two data buffers, - * two bitmap buffers, and two group summaries, in addition to the inode - * and the superblock, which are already accounted for. */ - -#define EXT4_XATTR_TRANS_BLOCKS 6U - -/* Define the minimum size for a transaction which modifies data. This - * needs to take into account the fact that we may end up modifying two - * quota files too (one for the group, one for the user quota). The - * superblock only gets updated once, of course, so don't bother - * counting that again for the quota updates. */ - -#define EXT4_DATA_TRANS_BLOCKS(sb) (EXT4_SINGLEDATA_TRANS_BLOCKS + \ - EXT4_XATTR_TRANS_BLOCKS - 2 + \ - 2*EXT4_QUOTA_TRANS_BLOCKS(sb)) - -/* Delete operations potentially hit one directory's namespace plus an - * entire inode, plus arbitrary amounts of bitmap/indirection data. Be - * generous. We can grow the delete transaction later if necessary. */ - -#define EXT4_DELETE_TRANS_BLOCKS(sb) (2 * EXT4_DATA_TRANS_BLOCKS(sb) + 64) - -/* Define an arbitrary limit for the amount of data we will anticipate - * writing to any given transaction. For unbounded transactions such as - * write(2) and truncate(2) we can write more than this, but we always - * start off at the maximum transaction size and grow the transaction - * optimistically as we go. */ - -#define EXT4_MAX_TRANS_DATA 64U - -/* We break up a large truncate or write transaction once the handle's - * buffer credits gets this low, we need either to extend the - * transaction or to start a new one. Reserve enough space here for - * inode, bitmap, superblock, group and indirection updates for at least - * one block, plus two quota updates. Quota allocations are not - * needed. */ - -#define EXT4_RESERVE_TRANS_BLOCKS 12U - -#define EXT4_INDEX_EXTRA_TRANS_BLOCKS 8 - -#ifdef CONFIG_QUOTA -/* Amount of blocks needed for quota update - we know that the structure was - * allocated so we need to update only inode+data */ -#define EXT4_QUOTA_TRANS_BLOCKS(sb) (test_opt(sb, QUOTA) ? 2 : 0) -/* Amount of blocks needed for quota insert/delete - we do some block writes - * but inode, sb and group updates are done only once */ -#define EXT4_QUOTA_INIT_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_INIT_ALLOC*\ - (EXT4_SINGLEDATA_TRANS_BLOCKS-3)+3+DQUOT_INIT_REWRITE) : 0) -#define EXT4_QUOTA_DEL_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_DEL_ALLOC*\ - (EXT4_SINGLEDATA_TRANS_BLOCKS-3)+3+DQUOT_DEL_REWRITE) : 0) -#else -#define EXT4_QUOTA_TRANS_BLOCKS(sb) 0 -#define EXT4_QUOTA_INIT_BLOCKS(sb) 0 -#define EXT4_QUOTA_DEL_BLOCKS(sb) 0 -#endif - -int -ext4_mark_iloc_dirty(handle_t *handle, - struct inode *inode, - struct ext4_iloc *iloc); - -/* - * On success, We end up with an outstanding reference count against - * iloc->bh. This _must_ be cleaned up later. - */ - -int ext4_reserve_inode_write(handle_t *handle, struct inode *inode, - struct ext4_iloc *iloc); - -int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode); - -/* - * Wrapper functions with which ext4 calls into JBD. The intent here is - * to allow these to be turned into appropriate stubs so ext4 can control - * ext2 filesystems, so ext2+ext4 systems only nee one fs. This work hasn't - * been done yet. - */ - -void ext4_journal_abort_handle(const char *caller, const char *err_fn, - struct buffer_head *bh, handle_t *handle, int err); - -static inline int -__ext4_journal_get_undo_access(const char *where, handle_t *handle, - struct buffer_head *bh) -{ - int err = journal_get_undo_access(handle, bh); - if (err) - ext4_journal_abort_handle(where, __FUNCTION__, bh, handle,err); - return err; -} - -static inline int -__ext4_journal_get_write_access(const char *where, handle_t *handle, - struct buffer_head *bh) -{ - int err = journal_get_write_access(handle, bh); - if (err) - ext4_journal_abort_handle(where, __FUNCTION__, bh, handle,err); - return err; -} - -static inline void -ext4_journal_release_buffer(handle_t *handle, struct buffer_head *bh) -{ - journal_release_buffer(handle, bh); -} - -static inline int -__ext4_journal_forget(const char *where, handle_t *handle, struct buffer_head *bh) -{ - int err = journal_forget(handle, bh); - if (err) - ext4_journal_abort_handle(where, __FUNCTION__, bh, handle,err); - return err; -} - -static inline int -__ext4_journal_revoke(const char *where, handle_t *handle, - unsigned long blocknr, struct buffer_head *bh) -{ - int err = journal_revoke(handle, blocknr, bh); - if (err) - ext4_journal_abort_handle(where, __FUNCTION__, bh, handle,err); - return err; -} - -static inline int -__ext4_journal_get_create_access(const char *where, - handle_t *handle, struct buffer_head *bh) -{ - int err = journal_get_create_access(handle, bh); - if (err) - ext4_journal_abort_handle(where, __FUNCTION__, bh, handle,err); - return err; -} - -static inline int -__ext4_journal_dirty_metadata(const char *where, - handle_t *handle, struct buffer_head *bh) -{ - int err = journal_dirty_metadata(handle, bh); - if (err) - ext4_journal_abort_handle(where, __FUNCTION__, bh, handle,err); - return err; -} - - -#define ext4_journal_get_undo_access(handle, bh) \ - __ext4_journal_get_undo_access(__FUNCTION__, (handle), (bh)) -#define ext4_journal_get_write_access(handle, bh) \ - __ext4_journal_get_write_access(__FUNCTION__, (handle), (bh)) -#define ext4_journal_revoke(handle, blocknr, bh) \ - __ext4_journal_revoke(__FUNCTION__, (handle), (blocknr), (bh)) -#define ext4_journal_get_create_access(handle, bh) \ - __ext4_journal_get_create_access(__FUNCTION__, (handle), (bh)) -#define ext4_journal_dirty_metadata(handle, bh) \ - __ext4_journal_dirty_metadata(__FUNCTION__, (handle), (bh)) -#define ext4_journal_forget(handle, bh) \ - __ext4_journal_forget(__FUNCTION__, (handle), (bh)) - -int ext4_journal_dirty_data(handle_t *handle, struct buffer_head *bh); - -handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks); -int __ext4_journal_stop(const char *where, handle_t *handle); - -static inline handle_t *ext4_journal_start(struct inode *inode, int nblocks) -{ - return ext4_journal_start_sb(inode->i_sb, nblocks); -} - -#define ext4_journal_stop(handle) \ - __ext4_journal_stop(__FUNCTION__, (handle)) - -static inline handle_t *ext4_journal_current_handle(void) -{ - return journal_current_handle(); -} - -static inline int ext4_journal_extend(handle_t *handle, int nblocks) -{ - return journal_extend(handle, nblocks); -} - -static inline int ext4_journal_restart(handle_t *handle, int nblocks) -{ - return journal_restart(handle, nblocks); -} - -static inline int ext4_journal_blocks_per_page(struct inode *inode) -{ - return journal_blocks_per_page(inode); -} - -static inline int ext4_journal_force_commit(journal_t *journal) -{ - return journal_force_commit(journal); -} - -/* super.c */ -int ext4_force_commit(struct super_block *sb); - -static inline int ext4_should_journal_data(struct inode *inode) -{ - if (!S_ISREG(inode->i_mode)) - return 1; - if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) - return 1; - if (EXT4_I(inode)->i_flags & EXT4_JOURNAL_DATA_FL) - return 1; - return 0; -} - -static inline int ext4_should_order_data(struct inode *inode) -{ - if (!S_ISREG(inode->i_mode)) - return 0; - if (EXT4_I(inode)->i_flags & EXT4_JOURNAL_DATA_FL) - return 0; - if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA) - return 1; - return 0; -} - -static inline int ext4_should_writeback_data(struct inode *inode) -{ - if (!S_ISREG(inode->i_mode)) - return 0; - if (EXT4_I(inode)->i_flags & EXT4_JOURNAL_DATA_FL) - return 0; - if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA) - return 1; - return 0; -} - -#endif /* _LINUX_EXT4_JBD_H */ -- cgit v1.2.3 From a86c61812637c7dd0c57e29880cffd477b62f2e7 Mon Sep 17 00:00:00 2001 From: Alex Tomas Date: Wed, 11 Oct 2006 01:21:03 -0700 Subject: [PATCH] ext3: add extent map support On disk extents format: /* * this is extent on-disk structure * it's used at the bottom of the tree */ struct ext3_extent { __le32 ee_block; /* first logical block extent covers */ __le16 ee_len; /* number of blocks covered by extent */ __le16 ee_start_hi; /* high 16 bits of physical block */ __le32 ee_start; /* low 32 bigs of physical block */ }; Signed-off-by: Alex Tomas Signed-off-by: Dave Kleikamp Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ext4_fs.h | 33 ++++++- include/linux/ext4_fs_extents.h | 196 ++++++++++++++++++++++++++++++++++++++++ include/linux/ext4_fs_i.h | 13 +++ include/linux/ext4_fs_sb.h | 10 ++ include/linux/ext4_jbd2.h | 15 ++- 5 files changed, 260 insertions(+), 7 deletions(-) create mode 100644 include/linux/ext4_fs_extents.h (limited to 'include/linux') diff --git a/include/linux/ext4_fs.h b/include/linux/ext4_fs.h index f582cd762caf..b61181aadcbb 100644 --- a/include/linux/ext4_fs.h +++ b/include/linux/ext4_fs.h @@ -178,8 +178,9 @@ struct ext4_group_desc #define EXT4_DIRSYNC_FL 0x00010000 /* dirsync behaviour (directories only) */ #define EXT4_TOPDIR_FL 0x00020000 /* Top of directory hierarchies*/ #define EXT4_RESERVED_FL 0x80000000 /* reserved for ext4 lib */ +#define EXT4_EXTENTS_FL 0x00080000 /* Inode uses extents */ -#define EXT4_FL_USER_VISIBLE 0x0003DFFF /* User visible flags */ +#define EXT4_FL_USER_VISIBLE 0x000BDFFF /* User visible flags */ #define EXT4_FL_USER_MODIFIABLE 0x000380FF /* User modifiable flags */ /* @@ -384,6 +385,7 @@ struct ext4_inode { #define EXT4_MOUNT_QUOTA 0x80000 /* Some quota option set */ #define EXT4_MOUNT_USRQUOTA 0x100000 /* "old" user quota */ #define EXT4_MOUNT_GRPQUOTA 0x200000 /* "old" group quota */ +#define EXT4_MOUNT_EXTENTS 0x400000 /* Extents support */ /* Compatibility, for having both ext2_fs.h and ext4_fs.h included at once */ #ifndef _LINUX_EXT2_FS_H @@ -582,11 +584,13 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino) #define EXT4_FEATURE_INCOMPAT_RECOVER 0x0004 /* Needs recovery */ #define EXT4_FEATURE_INCOMPAT_JOURNAL_DEV 0x0008 /* Journal device */ #define EXT4_FEATURE_INCOMPAT_META_BG 0x0010 +#define EXT4_FEATURE_INCOMPAT_EXTENTS 0x0040 /* extents support */ #define EXT4_FEATURE_COMPAT_SUPP EXT2_FEATURE_COMPAT_EXT_ATTR #define EXT4_FEATURE_INCOMPAT_SUPP (EXT4_FEATURE_INCOMPAT_FILETYPE| \ EXT4_FEATURE_INCOMPAT_RECOVER| \ - EXT4_FEATURE_INCOMPAT_META_BG) + EXT4_FEATURE_INCOMPAT_META_BG| \ + EXT4_FEATURE_INCOMPAT_EXTENTS) #define EXT4_FEATURE_RO_COMPAT_SUPP (EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER| \ EXT4_FEATURE_RO_COMPAT_LARGE_FILE| \ EXT4_FEATURE_RO_COMPAT_BTREE_DIR) @@ -825,6 +829,9 @@ extern int ext4_get_inode_loc(struct inode *, struct ext4_iloc *); extern void ext4_truncate (struct inode *); extern void ext4_set_inode_flags(struct inode *); extern void ext4_set_aops(struct inode *inode); +extern int ext4_writepage_trans_blocks(struct inode *); +extern int ext4_block_truncate_page(handle_t *handle, struct page *page, + struct address_space *mapping, loff_t from); /* ioctl.c */ extern int ext4_ioctl (struct inode *, struct file *, unsigned int, @@ -879,6 +886,28 @@ extern struct inode_operations ext4_special_inode_operations; extern struct inode_operations ext4_symlink_inode_operations; extern struct inode_operations ext4_fast_symlink_inode_operations; +/* extents.c */ +extern int ext4_ext_tree_init(handle_t *handle, struct inode *); +extern int ext4_ext_writepage_trans_blocks(struct inode *, int); +extern int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, + ext4_fsblk_t iblock, + unsigned long max_blocks, struct buffer_head *bh_result, + int create, int extend_disksize); +extern void ext4_ext_truncate(struct inode *, struct page *); +extern void ext4_ext_init(struct super_block *); +extern void ext4_ext_release(struct super_block *); +static inline int +ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block, + unsigned long max_blocks, struct buffer_head *bh, + int create, int extend_disksize) +{ + if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) + return ext4_ext_get_blocks(handle, inode, block, max_blocks, + bh, create, extend_disksize); + return ext4_get_blocks_handle(handle, inode, block, max_blocks, bh, + create, extend_disksize); +} + #endif /* __KERNEL__ */ diff --git a/include/linux/ext4_fs_extents.h b/include/linux/ext4_fs_extents.h new file mode 100644 index 000000000000..8029879e29e2 --- /dev/null +++ b/include/linux/ext4_fs_extents.h @@ -0,0 +1,196 @@ +/* + * Copyright (c) 2003-2006, Cluster File Systems, Inc, info@clusterfs.com + * Written by Alex Tomas + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public Licens + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111- + */ + +#ifndef _LINUX_EXT4_EXTENTS +#define _LINUX_EXT4_EXTENTS + +#include + +/* + * with AGRESSIVE_TEST defined capacity of index/leaf blocks + * become very little, so index split, in-depth growing and + * other hard changes happens much more often + * this is for debug purposes only + */ +#define AGRESSIVE_TEST_ + +/* + * with EXTENTS_STATS defined number of blocks and extents + * are collected in truncate path. they'll be showed at + * umount time + */ +#define EXTENTS_STATS__ + +/* + * if CHECK_BINSEARCH defined, then results of binary search + * will be checked by linear search + */ +#define CHECK_BINSEARCH__ + +/* + * if EXT_DEBUG is defined you can use 'extdebug' mount option + * to get lots of info what's going on + */ +#define EXT_DEBUG__ +#ifdef EXT_DEBUG +#define ext_debug(a...) printk(a) +#else +#define ext_debug(a...) +#endif + +/* + * if EXT_STATS is defined then stats numbers are collected + * these number will be displayed at umount time + */ +#define EXT_STATS_ + + +/* + * ext4_inode has i_block array (60 bytes total) + * first 12 bytes store ext4_extent_header + * the remain stores array of ext4_extent + */ + +/* + * this is extent on-disk structure + * it's used at the bottom of the tree + */ +struct ext4_extent { + __le32 ee_block; /* first logical block extent covers */ + __le16 ee_len; /* number of blocks covered by extent */ + __le16 ee_start_hi; /* high 16 bits of physical block */ + __le32 ee_start; /* low 32 bigs of physical block */ +}; + +/* + * this is index on-disk structure + * it's used at all the levels, but the bottom + */ +struct ext4_extent_idx { + __le32 ei_block; /* index covers logical blocks from 'block' */ + __le32 ei_leaf; /* pointer to the physical block of the next * + * level. leaf or next index could bet here */ + __le16 ei_leaf_hi; /* high 16 bits of physical block */ + __u16 ei_unused; +}; + +/* + * each block (leaves and indexes), even inode-stored has header + */ +struct ext4_extent_header { + __le16 eh_magic; /* probably will support different formats */ + __le16 eh_entries; /* number of valid entries */ + __le16 eh_max; /* capacity of store in entries */ + __le16 eh_depth; /* has tree real underlaying blocks? */ + __le32 eh_generation; /* generation of the tree */ +}; + +#define EXT4_EXT_MAGIC cpu_to_le16(0xf30a) + +/* + * array of ext4_ext_path contains path to some extent + * creation/lookup routines use it for traversal/splitting/etc + * truncate uses it to simulate recursive walking + */ +struct ext4_ext_path { + __u32 p_block; + __u16 p_depth; + struct ext4_extent *p_ext; + struct ext4_extent_idx *p_idx; + struct ext4_extent_header *p_hdr; + struct buffer_head *p_bh; +}; + +/* + * structure for external API + */ + +#define EXT4_EXT_CACHE_NO 0 +#define EXT4_EXT_CACHE_GAP 1 +#define EXT4_EXT_CACHE_EXTENT 2 + +/* + * to be called by ext4_ext_walk_space() + * negative retcode - error + * positive retcode - signal for ext4_ext_walk_space(), see below + * callback must return valid extent (passed or newly created) + */ +typedef int (*ext_prepare_callback)(struct inode *, struct ext4_ext_path *, + struct ext4_ext_cache *, + void *); + +#define EXT_CONTINUE 0 +#define EXT_BREAK 1 +#define EXT_REPEAT 2 + + +#define EXT_MAX_BLOCK 0xffffffff + + +#define EXT_FIRST_EXTENT(__hdr__) \ + ((struct ext4_extent *) (((char *) (__hdr__)) + \ + sizeof(struct ext4_extent_header))) +#define EXT_FIRST_INDEX(__hdr__) \ + ((struct ext4_extent_idx *) (((char *) (__hdr__)) + \ + sizeof(struct ext4_extent_header))) +#define EXT_HAS_FREE_INDEX(__path__) \ + (le16_to_cpu((__path__)->p_hdr->eh_entries) \ + < le16_to_cpu((__path__)->p_hdr->eh_max)) +#define EXT_LAST_EXTENT(__hdr__) \ + (EXT_FIRST_EXTENT((__hdr__)) + le16_to_cpu((__hdr__)->eh_entries) - 1) +#define EXT_LAST_INDEX(__hdr__) \ + (EXT_FIRST_INDEX((__hdr__)) + le16_to_cpu((__hdr__)->eh_entries) - 1) +#define EXT_MAX_EXTENT(__hdr__) \ + (EXT_FIRST_EXTENT((__hdr__)) + le16_to_cpu((__hdr__)->eh_max) - 1) +#define EXT_MAX_INDEX(__hdr__) \ + (EXT_FIRST_INDEX((__hdr__)) + le16_to_cpu((__hdr__)->eh_max) - 1) + +static inline struct ext4_extent_header *ext_inode_hdr(struct inode *inode) +{ + return (struct ext4_extent_header *) EXT4_I(inode)->i_data; +} + +static inline struct ext4_extent_header *ext_block_hdr(struct buffer_head *bh) +{ + return (struct ext4_extent_header *) bh->b_data; +} + +static inline unsigned short ext_depth(struct inode *inode) +{ + return le16_to_cpu(ext_inode_hdr(inode)->eh_depth); +} + +static inline void ext4_ext_tree_changed(struct inode *inode) +{ + EXT4_I(inode)->i_ext_generation++; +} + +static inline void +ext4_ext_invalidate_cache(struct inode *inode) +{ + EXT4_I(inode)->i_cached_extent.ec_type = EXT4_EXT_CACHE_NO; +} + +extern int ext4_extent_tree_init(handle_t *, struct inode *); +extern int ext4_ext_calc_credits_for_insert(struct inode *, struct ext4_ext_path *); +extern int ext4_ext_insert_extent(handle_t *, struct inode *, struct ext4_ext_path *, struct ext4_extent *); +extern int ext4_ext_walk_space(struct inode *, unsigned long, unsigned long, ext_prepare_callback, void *); +extern struct ext4_ext_path * ext4_ext_find_extent(struct inode *, int, struct ext4_ext_path *); + +#endif /* _LINUX_EXT4_EXTENTS */ + diff --git a/include/linux/ext4_fs_i.h b/include/linux/ext4_fs_i.h index 18a6ce98537f..40ce04a52b04 100644 --- a/include/linux/ext4_fs_i.h +++ b/include/linux/ext4_fs_i.h @@ -64,6 +64,16 @@ struct ext4_block_alloc_info { #define rsv_start rsv_window._rsv_start #define rsv_end rsv_window._rsv_end +/* + * storage for cached extent + */ +struct ext4_ext_cache { + __u32 ec_start; + __u32 ec_block; + __u32 ec_len; /* must be 32bit to return holes */ + __u32 ec_type; +}; + /* * third extended file system inode data in memory */ @@ -142,6 +152,9 @@ struct ext4_inode_info { */ struct mutex truncate_mutex; struct inode vfs_inode; + + unsigned long i_ext_generation; + struct ext4_ext_cache i_cached_extent; }; #endif /* _LINUX_EXT4_FS_I */ diff --git a/include/linux/ext4_fs_sb.h b/include/linux/ext4_fs_sb.h index ce4856d70100..ce7a844d6703 100644 --- a/include/linux/ext4_fs_sb.h +++ b/include/linux/ext4_fs_sb.h @@ -78,6 +78,16 @@ struct ext4_sb_info { char *s_qf_names[MAXQUOTAS]; /* Names of quota files with journalled quota */ int s_jquota_fmt; /* Format of quota to use */ #endif + +#ifdef EXTENTS_STATS + /* ext4 extents stats */ + unsigned long s_ext_min; + unsigned long s_ext_max; + unsigned long s_depth_max; + spinlock_t s_ext_stats_lock; + unsigned long s_ext_blocks; + unsigned long s_ext_extents; +#endif }; #endif /* _LINUX_EXT4_FS_SB */ diff --git a/include/linux/ext4_jbd2.h b/include/linux/ext4_jbd2.h index 99d37557cbb4..aa273f024ad0 100644 --- a/include/linux/ext4_jbd2.h +++ b/include/linux/ext4_jbd2.h @@ -26,9 +26,14 @@ * * We may have to touch one inode, one bitmap buffer, up to three * indirection blocks, the group and superblock summaries, and the data - * block to complete the transaction. */ + * block to complete the transaction. + * + * For extents-enabled fs we may have to allocate and modify upto + * 5 levels of tree + root which is stored in inode. */ -#define EXT4_SINGLEDATA_TRANS_BLOCKS 8U +#define EXT4_SINGLEDATA_TRANS_BLOCKS(sb) \ + (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS) \ + || test_opt(sb, EXTENTS) ? 27U : 8U) /* Extended attribute operations touch at most two data buffers, * two bitmap buffers, and two group summaries, in addition to the inode @@ -42,7 +47,7 @@ * superblock only gets updated once, of course, so don't bother * counting that again for the quota updates. */ -#define EXT4_DATA_TRANS_BLOCKS(sb) (EXT4_SINGLEDATA_TRANS_BLOCKS + \ +#define EXT4_DATA_TRANS_BLOCKS(sb) (EXT4_SINGLEDATA_TRANS_BLOCKS(sb) + \ EXT4_XATTR_TRANS_BLOCKS - 2 + \ 2*EXT4_QUOTA_TRANS_BLOCKS(sb)) @@ -78,9 +83,9 @@ /* Amount of blocks needed for quota insert/delete - we do some block writes * but inode, sb and group updates are done only once */ #define EXT4_QUOTA_INIT_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_INIT_ALLOC*\ - (EXT4_SINGLEDATA_TRANS_BLOCKS-3)+3+DQUOT_INIT_REWRITE) : 0) + (EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)+3+DQUOT_INIT_REWRITE) : 0) #define EXT4_QUOTA_DEL_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_DEL_ALLOC*\ - (EXT4_SINGLEDATA_TRANS_BLOCKS-3)+3+DQUOT_DEL_REWRITE) : 0) + (EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)+3+DQUOT_DEL_REWRITE) : 0) #else #define EXT4_QUOTA_TRANS_BLOCKS(sb) 0 #define EXT4_QUOTA_INIT_BLOCKS(sb) 0 -- cgit v1.2.3 From 3a5b2ecdd1fa63a8f25bd769223bc1c2564ce45d Mon Sep 17 00:00:00 2001 From: Mingming Cao Date: Wed, 11 Oct 2006 01:21:05 -0700 Subject: [PATCH] ext4: switch fsblk to sector_t Redefine ext3 in-kernel filesystem block type (ext3_fsblk_t) from unsigned long to sector_t, to allow kernel to handle >32 bit ext3 blocks. Signed-off-by: Mingming Cao Signed-off-by: Dave Kleikamp Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ext4_fs.h | 26 ++++++++++++++++++++++++++ include/linux/ext4_fs_i.h | 6 +++++- 2 files changed, 31 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ext4_fs.h b/include/linux/ext4_fs.h index b61181aadcbb..e952c6db9690 100644 --- a/include/linux/ext4_fs.h +++ b/include/linux/ext4_fs.h @@ -17,6 +17,7 @@ #define _LINUX_EXT4_FS_H #include +#include #include /* @@ -749,6 +750,27 @@ ext4_group_first_block_no(struct super_block *sb, unsigned long group_no) */ #define ERR_BAD_DX_DIR -75000 +/* + * This function calculate the block group number and offset, + * given a block number + */ + +static inline void ext4_get_group_no_and_offset(struct super_block * sb, + ext4_fsblk_t blocknr, unsigned long* blockgrpp, + ext4_grpblk_t *offsetp) +{ + struct ext4_super_block *es = EXT4_SB(sb)->s_es; + ext4_grpblk_t offset; + + blocknr = blocknr - le32_to_cpu(es->s_first_data_block); + offset = sector_div(blocknr, EXT4_BLOCKS_PER_GROUP(sb)); + if (offsetp) + *offsetp = offset; + if (blockgrpp) + *blockgrpp = blocknr; + +} + /* * Function prototypes */ @@ -762,6 +784,10 @@ ext4_group_first_block_no(struct super_block *sb, unsigned long group_no) # define NORET_AND noreturn, /* balloc.c */ +extern unsigned int ext4_block_group(struct super_block *sb, + ext4_fsblk_t blocknr); +extern ext4_grpblk_t ext4_block_group_offset(struct super_block *sb, + ext4_fsblk_t blocknr); extern int ext4_bg_has_super(struct super_block *sb, int group); extern unsigned long ext4_bg_num_gdb(struct super_block *sb, int group); extern ext4_fsblk_t ext4_new_block (handle_t *handle, struct inode *inode, diff --git a/include/linux/ext4_fs_i.h b/include/linux/ext4_fs_i.h index 40ce04a52b04..b2ccd9876bd1 100644 --- a/include/linux/ext4_fs_i.h +++ b/include/linux/ext4_fs_i.h @@ -25,9 +25,13 @@ typedef int ext4_grpblk_t; /* data type for filesystem-wide blocks number */ -typedef unsigned long ext4_fsblk_t; +typedef sector_t ext4_fsblk_t; +#if BITS_PER_LONG == 64 #define E3FSBLK "%lu" +#else +#define E3FSBLK "%llu" +#endif struct ext4_reserve_window { ext4_fsblk_t _rsv_start; /* First byte reserved */ -- cgit v1.2.3 From f65e6fba163dfd0f962efb7d8f5528b6872e2b15 Mon Sep 17 00:00:00 2001 From: Alex Tomas Date: Wed, 11 Oct 2006 01:21:05 -0700 Subject: [PATCH] ext4: 48bit physical block number support in extents Signed-off-by: Alex Tomas Signed-off-by: Dave Kleikamp Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ext4_fs_extents.h | 2 +- include/linux/ext4_fs_i.h | 8 ++++---- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ext4_fs_extents.h b/include/linux/ext4_fs_extents.h index 8029879e29e2..facc76684d4f 100644 --- a/include/linux/ext4_fs_extents.h +++ b/include/linux/ext4_fs_extents.h @@ -108,7 +108,7 @@ struct ext4_extent_header { * truncate uses it to simulate recursive walking */ struct ext4_ext_path { - __u32 p_block; + ext4_fsblk_t p_block; __u16 p_depth; struct ext4_extent *p_ext; struct ext4_extent_idx *p_idx; diff --git a/include/linux/ext4_fs_i.h b/include/linux/ext4_fs_i.h index b2ccd9876bd1..2bed0effdcae 100644 --- a/include/linux/ext4_fs_i.h +++ b/include/linux/ext4_fs_i.h @@ -72,10 +72,10 @@ struct ext4_block_alloc_info { * storage for cached extent */ struct ext4_ext_cache { - __u32 ec_start; - __u32 ec_block; - __u32 ec_len; /* must be 32bit to return holes */ - __u32 ec_type; + ext4_fsblk_t ec_start; + __u32 ec_block; + __u32 ec_len; /* must be 32bit to return holes */ + __u32 ec_type; }; /* -- cgit v1.2.3 From 471d4011a9862efff02094388b8fe8cd67683c38 Mon Sep 17 00:00:00 2001 From: Suparna Bhattacharya Date: Wed, 11 Oct 2006 01:21:06 -0700 Subject: [PATCH] ext4: uninitialised extent handling Make it possible to add file preallocation support in future as an RO_COMPAT feature by recognizing uninitialized extents as holes and limiting extent length to keep the top bit of ee_len free for marking uninitialized extents. Signed-off-by: Suparna Bhattacharya Signed-off-by: Mingming Cao Signed-off-by: Dave Kleikamp Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ext4_fs_extents.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ext4_fs_extents.h b/include/linux/ext4_fs_extents.h index facc76684d4f..0eba0acf6ba6 100644 --- a/include/linux/ext4_fs_extents.h +++ b/include/linux/ext4_fs_extents.h @@ -141,6 +141,8 @@ typedef int (*ext_prepare_callback)(struct inode *, struct ext4_ext_path *, #define EXT_MAX_BLOCK 0xffffffff +#define EXT_MAX_LEN ((1UL << 15) - 1) + #define EXT_FIRST_EXTENT(__hdr__) \ ((struct ext4_extent *) (((char *) (__hdr__)) + \ -- cgit v1.2.3 From d0d856e8bd6e697cb44b2b4dd038f3bec576a70e Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 11 Oct 2006 01:21:07 -0700 Subject: [PATCH] ext4: clean up comments in ext4-extents patch Signed-off-by: Randy Dunlap Signed-off-by: Dave Kleikamp Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ext4_fs_extents.h | 54 ++++++++++++++++++++--------------------- include/linux/ext4_jbd2.h | 4 +-- 2 files changed, 29 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ext4_fs_extents.h b/include/linux/ext4_fs_extents.h index 0eba0acf6ba6..a41cc24568ca 100644 --- a/include/linux/ext4_fs_extents.h +++ b/include/linux/ext4_fs_extents.h @@ -22,29 +22,29 @@ #include /* - * with AGRESSIVE_TEST defined capacity of index/leaf blocks - * become very little, so index split, in-depth growing and - * other hard changes happens much more often - * this is for debug purposes only + * With AGRESSIVE_TEST defined, the capacity of index/leaf blocks + * becomes very small, so index split, in-depth growing and + * other hard changes happen much more often. + * This is for debug purposes only. */ #define AGRESSIVE_TEST_ /* - * with EXTENTS_STATS defined number of blocks and extents - * are collected in truncate path. they'll be showed at - * umount time + * With EXTENTS_STATS defined, the number of blocks and extents + * are collected in the truncate path. They'll be shown at + * umount time. */ #define EXTENTS_STATS__ /* - * if CHECK_BINSEARCH defined, then results of binary search - * will be checked by linear search + * If CHECK_BINSEARCH is defined, then the results of the binary search + * will also be checked by linear search. */ #define CHECK_BINSEARCH__ /* - * if EXT_DEBUG is defined you can use 'extdebug' mount option - * to get lots of info what's going on + * If EXT_DEBUG is defined you can use the 'extdebug' mount option + * to get lots of info about what's going on. */ #define EXT_DEBUG__ #ifdef EXT_DEBUG @@ -54,58 +54,58 @@ #endif /* - * if EXT_STATS is defined then stats numbers are collected - * these number will be displayed at umount time + * If EXT_STATS is defined then stats numbers are collected. + * These number will be displayed at umount time. */ #define EXT_STATS_ /* - * ext4_inode has i_block array (60 bytes total) - * first 12 bytes store ext4_extent_header - * the remain stores array of ext4_extent + * ext4_inode has i_block array (60 bytes total). + * The first 12 bytes store ext4_extent_header; + * the remainder stores an array of ext4_extent. */ /* - * this is extent on-disk structure - * it's used at the bottom of the tree + * This is the extent on-disk structure. + * It's used at the bottom of the tree. */ struct ext4_extent { __le32 ee_block; /* first logical block extent covers */ __le16 ee_len; /* number of blocks covered by extent */ __le16 ee_start_hi; /* high 16 bits of physical block */ - __le32 ee_start; /* low 32 bigs of physical block */ + __le32 ee_start; /* low 32 bits of physical block */ }; /* - * this is index on-disk structure - * it's used at all the levels, but the bottom + * This is index on-disk structure. + * It's used at all the levels except the bottom. */ struct ext4_extent_idx { __le32 ei_block; /* index covers logical blocks from 'block' */ __le32 ei_leaf; /* pointer to the physical block of the next * - * level. leaf or next index could bet here */ + * level. leaf or next index could be there */ __le16 ei_leaf_hi; /* high 16 bits of physical block */ __u16 ei_unused; }; /* - * each block (leaves and indexes), even inode-stored has header + * Each block (leaves and indexes), even inode-stored has header. */ struct ext4_extent_header { __le16 eh_magic; /* probably will support different formats */ __le16 eh_entries; /* number of valid entries */ __le16 eh_max; /* capacity of store in entries */ - __le16 eh_depth; /* has tree real underlaying blocks? */ + __le16 eh_depth; /* has tree real underlying blocks? */ __le32 eh_generation; /* generation of the tree */ }; #define EXT4_EXT_MAGIC cpu_to_le16(0xf30a) /* - * array of ext4_ext_path contains path to some extent - * creation/lookup routines use it for traversal/splitting/etc - * truncate uses it to simulate recursive walking + * Array of ext4_ext_path contains path to some extent. + * Creation/lookup routines use it for traversal/splitting/etc. + * Truncate uses it to simulate recursive walking. */ struct ext4_ext_path { ext4_fsblk_t p_block; diff --git a/include/linux/ext4_jbd2.h b/include/linux/ext4_jbd2.h index aa273f024ad0..f69af60d7692 100644 --- a/include/linux/ext4_jbd2.h +++ b/include/linux/ext4_jbd2.h @@ -28,8 +28,8 @@ * indirection blocks, the group and superblock summaries, and the data * block to complete the transaction. * - * For extents-enabled fs we may have to allocate and modify upto - * 5 levels of tree + root which is stored in inode. */ + * For extents-enabled fs we may have to allocate and modify up to + * 5 levels of tree + root which are stored in the inode. */ #define EXT4_SINGLEDATA_TRANS_BLOCKS(sb) \ (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS) \ -- cgit v1.2.3 From b517bea1c74e4773482b3f41b3f493522a8c8e30 Mon Sep 17 00:00:00 2001 From: Zach Brown Date: Wed, 11 Oct 2006 01:21:08 -0700 Subject: [PATCH] 64-bit jbd2 core Here is the patch to JBD to handle 64 bit block numbers, originally from Zach Brown. This patch is useful only after adding support for 64-bit block numbers in the filesystem. Signed-off-by: Badari Pulavarty Signed-off-by: Zach Brown Signed-off-by: Dave Kleikamp Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/jbd2.h | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 3251f7abb57d..5e5aa64f1261 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -150,14 +150,21 @@ typedef struct journal_header_s /* - * The block tag: used to describe a single buffer in the journal + * The block tag: used to describe a single buffer in the journal. + * t_blocknr_high is only used if INCOMPAT_64BIT is set, so this + * raw struct shouldn't be used for pointer math or sizeof() - use + * journal_tag_bytes(journal) instead to compute this. */ typedef struct journal_block_tag_s { __be32 t_blocknr; /* The on-disk block number */ __be32 t_flags; /* See below */ + __be32 t_blocknr_high; /* most-significant high 32bits. */ } journal_block_tag_t; +#define JBD_TAG_SIZE32 (offsetof(journal_block_tag_t, t_blocknr_high)) +#define JBD_TAG_SIZE64 (sizeof(journal_block_tag_t)) + /* * The revoke descriptor: used on disk to describe a series of blocks to * be revoked from the log @@ -235,11 +242,13 @@ typedef struct journal_superblock_s ((j)->j_superblock->s_feature_incompat & cpu_to_be32((mask)))) #define JBD2_FEATURE_INCOMPAT_REVOKE 0x00000001 +#define JBD2_FEATURE_INCOMPAT_64BIT 0x00000002 /* Features known to this kernel version: */ #define JBD2_KNOWN_COMPAT_FEATURES 0 #define JBD2_KNOWN_ROCOMPAT_FEATURES 0 -#define JBD2_KNOWN_INCOMPAT_FEATURES JBD2_FEATURE_INCOMPAT_REVOKE +#define JBD2_KNOWN_INCOMPAT_FEATURES (JBD2_FEATURE_INCOMPAT_REVOKE | \ + JBD2_FEATURE_INCOMPAT_64BIT) #ifdef __KERNEL__ @@ -1052,6 +1061,7 @@ static inline int tid_geq(tid_t x, tid_t y) } extern int jbd2_journal_blocks_per_page(struct inode *inode); +extern size_t journal_tag_bytes(journal_t *journal); /* * Return the minimum number of blocks which must be free in the journal -- cgit v1.2.3 From 299717696d48531d70aeb4614c3939e4a28456c1 Mon Sep 17 00:00:00 2001 From: Mingming Cao Date: Wed, 11 Oct 2006 01:21:09 -0700 Subject: [PATCH] jbd2: sector_t conversion JBD layer in-kernel block varibles type fixes to support >32 bit block number and convert to sector_t type. Signed-off-by: Mingming Cao Signed-off-by: Dave Kleikamp Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ext4_jbd2.h | 2 +- include/linux/jbd2.h | 17 ++++++++--------- 2 files changed, 9 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ext4_jbd2.h b/include/linux/ext4_jbd2.h index f69af60d7692..72dd631912e4 100644 --- a/include/linux/ext4_jbd2.h +++ b/include/linux/ext4_jbd2.h @@ -154,7 +154,7 @@ __ext4_journal_forget(const char *where, handle_t *handle, struct buffer_head *b static inline int __ext4_journal_revoke(const char *where, handle_t *handle, - unsigned long blocknr, struct buffer_head *bh) + ext4_fsblk_t blocknr, struct buffer_head *bh) { int err = jbd2_journal_revoke(handle, blocknr, bh); if (err) diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 5e5aa64f1261..3c939c844a7d 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -741,7 +741,7 @@ struct journal_s */ struct block_device *j_dev; int j_blocksize; - unsigned long j_blk_offset; + sector_t j_blk_offset; /* * Device which holds the client fs. For internal journal this will be @@ -860,7 +860,7 @@ extern void __journal_clean_data_list(transaction_t *transaction); /* Log buffer allocation */ extern struct journal_head * jbd2_journal_get_descriptor_buffer(journal_t *); -int jbd2_journal_next_log_block(journal_t *, unsigned long *); +int jbd2_journal_next_log_block(journal_t *, sector_t *); /* Commit management */ extern void jbd2_journal_commit_transaction(journal_t *); @@ -875,7 +875,7 @@ extern int jbd2_journal_write_metadata_buffer(transaction_t *transaction, struct journal_head *jh_in, struct journal_head **jh_out, - unsigned long blocknr); + sector_t blocknr); /* Transaction locking */ extern void __wait_on_journal (journal_t *); @@ -923,7 +923,7 @@ extern void jbd2_journal_unlock_updates (journal_t *); extern journal_t * jbd2_journal_init_dev(struct block_device *bdev, struct block_device *fs_dev, - int start, int len, int bsize); + sector_t start, int len, int bsize); extern journal_t * jbd2_journal_init_inode (struct inode *); extern int jbd2_journal_update_format (journal_t *); extern int jbd2_journal_check_used_features @@ -944,7 +944,7 @@ extern void jbd2_journal_abort (journal_t *, int); extern int jbd2_journal_errno (journal_t *); extern void jbd2_journal_ack_err (journal_t *); extern int jbd2_journal_clear_err (journal_t *); -extern int jbd2_journal_bmap(journal_t *, unsigned long, unsigned long *); +extern int jbd2_journal_bmap(journal_t *, unsigned long, sector_t *); extern int jbd2_journal_force_commit(journal_t *); /* @@ -977,14 +977,13 @@ extern void jbd2_journal_destroy_revoke_caches(void); extern int jbd2_journal_init_revoke_caches(void); extern void jbd2_journal_destroy_revoke(journal_t *); -extern int jbd2_journal_revoke (handle_t *, - unsigned long, struct buffer_head *); +extern int jbd2_journal_revoke (handle_t *, sector_t, struct buffer_head *); extern int jbd2_journal_cancel_revoke(handle_t *, struct journal_head *); extern void jbd2_journal_write_revoke_records(journal_t *, transaction_t *); /* Recovery revoke support */ -extern int jbd2_journal_set_revoke(journal_t *, unsigned long, tid_t); -extern int jbd2_journal_test_revoke(journal_t *, unsigned long, tid_t); +extern int jbd2_journal_set_revoke(journal_t *, sector_t, tid_t); +extern int jbd2_journal_test_revoke(journal_t *, sector_t, tid_t); extern void jbd2_journal_clear_revoke(journal_t *); extern void jbd2_journal_switch_revoke_table(journal_t *journal); -- cgit v1.2.3 From a1ddeb7eaecea6a924e3a79aa386797020cb436f Mon Sep 17 00:00:00 2001 From: Badari Pulavarty Date: Wed, 11 Oct 2006 01:21:09 -0700 Subject: [PATCH] ext4: 48bit i_file_acl As we are planning to support 48-bit block numbers for ext4, we need to support 48-bit block numbers for extended attributes. In the short term, we can do this by reuse (on-disk) 16-bit padding (linux2.i_pad1 currently used only by "hurd") as high order bits for xattr. This patch basically does that. Signed-off-by: Badari Pulavarty Signed-off-by: Dave Kleikamp Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ext4_fs.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ext4_fs.h b/include/linux/ext4_fs.h index e952c6db9690..63ed89f5b27b 100644 --- a/include/linux/ext4_fs.h +++ b/include/linux/ext4_fs.h @@ -298,7 +298,7 @@ struct ext4_inode { struct { __u8 l_i_frag; /* Fragment number */ __u8 l_i_fsize; /* Fragment size */ - __u16 i_pad1; + __le16 l_i_file_acl_high; __le16 l_i_uid_high; /* these 2 fields */ __le16 l_i_gid_high; /* were reserved2[0] */ __u32 l_i_reserved2; @@ -314,7 +314,7 @@ struct ext4_inode { struct { __u8 m_i_frag; /* Fragment number */ __u8 m_i_fsize; /* Fragment size */ - __u16 m_pad1; + __le16 m_i_file_acl_high; __u32 m_i_reserved2[2]; } masix2; } osd2; /* OS dependent 2 */ @@ -328,6 +328,7 @@ struct ext4_inode { #define i_reserved1 osd1.linux1.l_i_reserved1 #define i_frag osd2.linux2.l_i_frag #define i_fsize osd2.linux2.l_i_fsize +#define i_file_acl_high osd2.linux2.l_i_file_acl_high #define i_uid_low i_uid #define i_gid_low i_gid #define i_uid_high osd2.linux2.l_i_uid_high @@ -348,6 +349,7 @@ struct ext4_inode { #define i_reserved1 osd1.masix1.m_i_reserved1 #define i_frag osd2.masix2.m_i_frag #define i_fsize osd2.masix2.m_i_fsize +#define i_file_acl_high osd2.masix2.m_i_file_acl_high #define i_reserved2 osd2.masix2.m_i_reserved2 #endif /* defined(__KERNEL__) || defined(__linux__) */ -- cgit v1.2.3 From bd81d8eec043094d3ff729a8ff6d5b3a06d3c4b1 Mon Sep 17 00:00:00 2001 From: Laurent Vivier Date: Wed, 11 Oct 2006 01:21:10 -0700 Subject: [PATCH] ext4: 64bit metadata In-kernel super block changes to support >32 bit free blocks numbers. Signed-off-by: Laurent Vivier Signed-off-by: Dave Kleikamp Signed-off-by: Alexandre Ratchov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ext4_fs.h | 86 +++++++++++++++++++++++++++++++++++++++++-------- 1 file changed, 73 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ext4_fs.h b/include/linux/ext4_fs.h index 63ed89f5b27b..8e5009ee4ad8 100644 --- a/include/linux/ext4_fs.h +++ b/include/linux/ext4_fs.h @@ -128,10 +128,17 @@ struct ext4_group_desc __le16 bg_free_blocks_count; /* Free blocks count */ __le16 bg_free_inodes_count; /* Free inodes count */ __le16 bg_used_dirs_count; /* Directories count */ - __u16 bg_pad; - __le32 bg_reserved[3]; + __u16 bg_flags; + __le16 bg_block_bitmap_hi; /* Blocks bitmap block MSB */ + __le16 bg_inode_bitmap_hi; /* Inodes bitmap block MSB */ + __le16 bg_inode_table_hi; /* Inodes table block MSB */ + __u16 bg_reserved[3]; }; +#ifdef __KERNEL__ +#include +#include +#endif /* * Macro-instructions used to manage group descriptors */ @@ -194,9 +201,9 @@ struct ext4_group_desc /* Used to pass group descriptor data when online resize is done */ struct ext4_new_group_input { __u32 group; /* Group number for this data */ - __u32 block_bitmap; /* Absolute block number of block bitmap */ - __u32 inode_bitmap; /* Absolute block number of inode bitmap */ - __u32 inode_table; /* Absolute block number of inode table start */ + __u64 block_bitmap; /* Absolute block number of block bitmap */ + __u64 inode_bitmap; /* Absolute block number of inode bitmap */ + __u64 inode_table; /* Absolute block number of inode table start */ __u32 blocks_count; /* Total number of blocks in this group */ __u16 reserved_blocks; /* Number of reserved blocks in this group */ __u16 unused; @@ -205,9 +212,9 @@ struct ext4_new_group_input { /* The struct ext4_new_group_input in kernel space, with free_blocks_count */ struct ext4_new_group_data { __u32 group; - __u32 block_bitmap; - __u32 inode_bitmap; - __u32 inode_table; + __u64 block_bitmap; + __u64 inode_bitmap; + __u64 inode_table; __u32 blocks_count; __u16 reserved_blocks; __u16 unused; @@ -494,14 +501,18 @@ struct ext4_super_block { __u8 s_def_hash_version; /* Default hash version to use */ __u8 s_reserved_char_pad; __u16 s_reserved_word_pad; - __le32 s_default_mount_opts; +/*100*/ __le32 s_default_mount_opts; __le32 s_first_meta_bg; /* First metablock block group */ - __u32 s_reserved[190]; /* Padding to the end of the block */ + __le32 s_mkfs_time; /* When the filesystem was created */ + __le32 s_jnl_blocks[17]; /* Backup of the journal inode */ + /* 64bit support valid if EXT4_FEATURE_COMPAT_64BIT */ +/*150*/ __le32 s_blocks_count_hi; /* Blocks count */ + __le32 s_r_blocks_count_hi; /* Reserved blocks count */ + __le32 s_free_blocks_count_hi; /* Free blocks count */ + __u32 s_reserved[169]; /* Padding to the end of the block */ }; #ifdef __KERNEL__ -#include -#include static inline struct ext4_sb_info * EXT4_SB(struct super_block *sb) { return sb->s_fs_info; @@ -588,12 +599,14 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino) #define EXT4_FEATURE_INCOMPAT_JOURNAL_DEV 0x0008 /* Journal device */ #define EXT4_FEATURE_INCOMPAT_META_BG 0x0010 #define EXT4_FEATURE_INCOMPAT_EXTENTS 0x0040 /* extents support */ +#define EXT4_FEATURE_INCOMPAT_64BIT 0x0080 #define EXT4_FEATURE_COMPAT_SUPP EXT2_FEATURE_COMPAT_EXT_ATTR #define EXT4_FEATURE_INCOMPAT_SUPP (EXT4_FEATURE_INCOMPAT_FILETYPE| \ EXT4_FEATURE_INCOMPAT_RECOVER| \ EXT4_FEATURE_INCOMPAT_META_BG| \ - EXT4_FEATURE_INCOMPAT_EXTENTS) + EXT4_FEATURE_INCOMPAT_EXTENTS| \ + EXT4_FEATURE_INCOMPAT_64BIT) #define EXT4_FEATURE_RO_COMPAT_SUPP (EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER| \ EXT4_FEATURE_RO_COMPAT_LARGE_FILE| \ EXT4_FEATURE_RO_COMPAT_BTREE_DIR) @@ -888,6 +901,53 @@ extern void ext4_abort (struct super_block *, const char *, const char *, ...) extern void ext4_warning (struct super_block *, const char *, const char *, ...) __attribute__ ((format (printf, 3, 4))); extern void ext4_update_dynamic_rev (struct super_block *sb); +extern ext4_fsblk_t ext4_block_bitmap(struct ext4_group_desc *bg); +extern ext4_fsblk_t ext4_inode_bitmap(struct ext4_group_desc *bg); +extern ext4_fsblk_t ext4_inode_table(struct ext4_group_desc *bg); +extern void ext4_block_bitmap_set(struct ext4_group_desc *bg, ext4_fsblk_t blk); +extern void ext4_inode_bitmap_set(struct ext4_group_desc *bg, ext4_fsblk_t blk); +extern void ext4_inode_table_set(struct ext4_group_desc *bg, ext4_fsblk_t blk); + +static inline ext4_fsblk_t ext4_blocks_count(struct ext4_super_block *es) +{ + return ((ext4_fsblk_t)le32_to_cpu(es->s_blocks_count_hi) << 32) | + le32_to_cpu(es->s_blocks_count); +} + +static inline ext4_fsblk_t ext4_r_blocks_count(struct ext4_super_block *es) +{ + return ((ext4_fsblk_t)le32_to_cpu(es->s_r_blocks_count_hi) << 32) | + le32_to_cpu(es->s_r_blocks_count); +} + +static inline ext4_fsblk_t ext4_free_blocks_count(struct ext4_super_block *es) +{ + return ((ext4_fsblk_t)le32_to_cpu(es->s_free_blocks_count_hi) << 32) | + le32_to_cpu(es->s_free_blocks_count); +} + +static inline void ext4_blocks_count_set(struct ext4_super_block *es, + ext4_fsblk_t blk) +{ + es->s_blocks_count = cpu_to_le32((u32)blk); + es->s_blocks_count_hi = cpu_to_le32(blk >> 32); +} + +static inline void ext4_free_blocks_count_set(struct ext4_super_block *es, + ext4_fsblk_t blk) +{ + es->s_free_blocks_count = cpu_to_le32((u32)blk); + es->s_free_blocks_count_hi = cpu_to_le32(blk >> 32); +} + +static inline void ext4_r_blocks_count_set(struct ext4_super_block *es, + ext4_fsblk_t blk) +{ + es->s_r_blocks_count = cpu_to_le32((u32)blk); + es->s_r_blocks_count_hi = cpu_to_le32(blk >> 32); +} + + #define ext4_std_error(sb, errno) \ do { \ -- cgit v1.2.3 From 2ae0210760aed9d626eaede5b63db95e198f7c8e Mon Sep 17 00:00:00 2001 From: Mingming Cao Date: Wed, 11 Oct 2006 01:21:11 -0700 Subject: [PATCH] ext4: blk_type from sector_t to unsigned long long Change ext4 in-kernel block type (ext4_fsblk_t) from sector_t to unsigned long long. Remove ext4 block type string micro E3FSBLK, replaced with "%llu" [akpm@osdl.org: build fix] Signed-off-by: Mingming Cao Signed-off-by: Dave Kleikamp Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ext4_fs_i.h | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ext4_fs_i.h b/include/linux/ext4_fs_i.h index 2bed0effdcae..bb42379cb7fd 100644 --- a/include/linux/ext4_fs_i.h +++ b/include/linux/ext4_fs_i.h @@ -25,13 +25,7 @@ typedef int ext4_grpblk_t; /* data type for filesystem-wide blocks number */ -typedef sector_t ext4_fsblk_t; - -#if BITS_PER_LONG == 64 -#define E3FSBLK "%lu" -#else -#define E3FSBLK "%llu" -#endif +typedef unsigned long long ext4_fsblk_t; struct ext4_reserve_window { ext4_fsblk_t _rsv_start; /* First byte reserved */ -- cgit v1.2.3 From 18eba7aae080d4a5c0d850ea810e83d11f0a8d77 Mon Sep 17 00:00:00 2001 From: Mingming Cao Date: Wed, 11 Oct 2006 01:21:13 -0700 Subject: [PATCH] jbd2: switch blks_type from sector_t to ull Similar to ext4, change blocks in JBD2 from sector_t to unsigned long long. Signed-off-by: Mingming Cao Signed-off-by: Dave Kleikamp Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/jbd2.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 3c939c844a7d..ddb128795781 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -741,7 +741,7 @@ struct journal_s */ struct block_device *j_dev; int j_blocksize; - sector_t j_blk_offset; + unsigned long long j_blk_offset; /* * Device which holds the client fs. For internal journal this will be @@ -860,7 +860,7 @@ extern void __journal_clean_data_list(transaction_t *transaction); /* Log buffer allocation */ extern struct journal_head * jbd2_journal_get_descriptor_buffer(journal_t *); -int jbd2_journal_next_log_block(journal_t *, sector_t *); +int jbd2_journal_next_log_block(journal_t *, unsigned long long *); /* Commit management */ extern void jbd2_journal_commit_transaction(journal_t *); @@ -875,7 +875,7 @@ extern int jbd2_journal_write_metadata_buffer(transaction_t *transaction, struct journal_head *jh_in, struct journal_head **jh_out, - sector_t blocknr); + unsigned long long blocknr); /* Transaction locking */ extern void __wait_on_journal (journal_t *); @@ -923,7 +923,7 @@ extern void jbd2_journal_unlock_updates (journal_t *); extern journal_t * jbd2_journal_init_dev(struct block_device *bdev, struct block_device *fs_dev, - sector_t start, int len, int bsize); + unsigned long long start, int len, int bsize); extern journal_t * jbd2_journal_init_inode (struct inode *); extern int jbd2_journal_update_format (journal_t *); extern int jbd2_journal_check_used_features @@ -944,7 +944,7 @@ extern void jbd2_journal_abort (journal_t *, int); extern int jbd2_journal_errno (journal_t *); extern void jbd2_journal_ack_err (journal_t *); extern int jbd2_journal_clear_err (journal_t *); -extern int jbd2_journal_bmap(journal_t *, unsigned long, sector_t *); +extern int jbd2_journal_bmap(journal_t *, unsigned long, unsigned long long *); extern int jbd2_journal_force_commit(journal_t *); /* @@ -977,13 +977,13 @@ extern void jbd2_journal_destroy_revoke_caches(void); extern int jbd2_journal_init_revoke_caches(void); extern void jbd2_journal_destroy_revoke(journal_t *); -extern int jbd2_journal_revoke (handle_t *, sector_t, struct buffer_head *); +extern int jbd2_journal_revoke (handle_t *, unsigned long long, struct buffer_head *); extern int jbd2_journal_cancel_revoke(handle_t *, struct journal_head *); extern void jbd2_journal_write_revoke_records(journal_t *, transaction_t *); /* Recovery revoke support */ -extern int jbd2_journal_set_revoke(journal_t *, sector_t, tid_t); -extern int jbd2_journal_test_revoke(journal_t *, sector_t, tid_t); +extern int jbd2_journal_set_revoke(journal_t *, unsigned long long, tid_t); +extern int jbd2_journal_test_revoke(journal_t *, unsigned long long, tid_t); extern void jbd2_journal_clear_revoke(journal_t *); extern void jbd2_journal_switch_revoke_table(journal_t *journal); -- cgit v1.2.3 From 0d1ee42f27d30eed1659f3e85bcbbc7b3711f61f Mon Sep 17 00:00:00 2001 From: Alexandre Ratchov Date: Wed, 11 Oct 2006 01:21:14 -0700 Subject: [PATCH] ext4: allow larger descriptor size make block group descriptor larger. Signed-off-by: Alexandre Ratchov Signed-off-by: Dave Kleikamp Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ext4_fs.h | 9 ++++++--- include/linux/ext4_fs_sb.h | 1 + 2 files changed, 7 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ext4_fs.h b/include/linux/ext4_fs.h index 8e5009ee4ad8..a3df2afc004b 100644 --- a/include/linux/ext4_fs.h +++ b/include/linux/ext4_fs.h @@ -142,6 +142,9 @@ struct ext4_group_desc /* * Macro-instructions used to manage group descriptors */ +#define EXT4_MIN_DESC_SIZE 32 +#define EXT4_MAX_DESC_SIZE EXT4_MIN_BLOCK_SIZE +#define EXT4_DESC_SIZE(s) (EXT4_SB(s)->s_desc_size) #ifdef __KERNEL__ # define EXT4_BLOCKS_PER_GROUP(s) (EXT4_SB(s)->s_blocks_per_group) # define EXT4_DESC_PER_BLOCK(s) (EXT4_SB(s)->s_desc_per_block) @@ -149,7 +152,7 @@ struct ext4_group_desc # define EXT4_DESC_PER_BLOCK_BITS(s) (EXT4_SB(s)->s_desc_per_block_bits) #else # define EXT4_BLOCKS_PER_GROUP(s) ((s)->s_blocks_per_group) -# define EXT4_DESC_PER_BLOCK(s) (EXT4_BLOCK_SIZE(s) / sizeof (struct ext4_group_desc)) +# define EXT4_DESC_PER_BLOCK(s) (EXT4_BLOCK_SIZE(s) / EXT4_DESC_SIZE(s)) # define EXT4_INODES_PER_GROUP(s) ((s)->s_inodes_per_group) #endif @@ -474,7 +477,7 @@ struct ext4_super_block { * things it doesn't understand... */ __le32 s_first_ino; /* First non-reserved inode */ - __le16 s_inode_size; /* size of inode structure */ + __le16 s_inode_size; /* size of inode structure */ __le16 s_block_group_nr; /* block group # of this superblock */ __le32 s_feature_compat; /* compatible feature set */ /*60*/ __le32 s_feature_incompat; /* incompatible feature set */ @@ -500,7 +503,7 @@ struct ext4_super_block { __le32 s_hash_seed[4]; /* HTREE hash seed */ __u8 s_def_hash_version; /* Default hash version to use */ __u8 s_reserved_char_pad; - __u16 s_reserved_word_pad; + __le16 s_desc_size; /* size of group descriptor */ /*100*/ __le32 s_default_mount_opts; __le32 s_first_meta_bg; /* First metablock block group */ __le32 s_mkfs_time; /* When the filesystem was created */ diff --git a/include/linux/ext4_fs_sb.h b/include/linux/ext4_fs_sb.h index ce7a844d6703..691a713139ce 100644 --- a/include/linux/ext4_fs_sb.h +++ b/include/linux/ext4_fs_sb.h @@ -29,6 +29,7 @@ */ struct ext4_sb_info { unsigned long s_frag_size; /* Size of a fragment in bytes */ + unsigned long s_desc_size; /* Size of a group descriptor in bytes */ unsigned long s_frags_per_block;/* Number of fragments per block */ unsigned long s_inodes_per_block;/* Number of inodes per block */ unsigned long s_frags_per_group;/* Number of fragments in a group */ -- cgit v1.2.3 From 8fadc14323684c547f74cf2f4d13517c6c264731 Mon Sep 17 00:00:00 2001 From: Alexandre Ratchov Date: Wed, 11 Oct 2006 01:21:15 -0700 Subject: [PATCH] ext4: move block number hi bits move '_hi' bits of block numbers in the larger part of the block group descriptor structure Signed-off-by: Alexandre Ratchov Signed-off-by: Dave Kleikamp Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ext4_fs.h | 27 +++++++++++++++++---------- 1 file changed, 17 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ext4_fs.h b/include/linux/ext4_fs.h index a3df2afc004b..296609b9242d 100644 --- a/include/linux/ext4_fs.h +++ b/include/linux/ext4_fs.h @@ -129,10 +129,10 @@ struct ext4_group_desc __le16 bg_free_inodes_count; /* Free inodes count */ __le16 bg_used_dirs_count; /* Directories count */ __u16 bg_flags; - __le16 bg_block_bitmap_hi; /* Blocks bitmap block MSB */ - __le16 bg_inode_bitmap_hi; /* Inodes bitmap block MSB */ - __le16 bg_inode_table_hi; /* Inodes table block MSB */ - __u16 bg_reserved[3]; + __u32 bg_reserved[3]; + __le32 bg_block_bitmap_hi; /* Blocks bitmap block MSB */ + __le32 bg_inode_bitmap_hi; /* Inodes bitmap block MSB */ + __le32 bg_inode_table_hi; /* Inodes table block MSB */ }; #ifdef __KERNEL__ @@ -143,6 +143,7 @@ struct ext4_group_desc * Macro-instructions used to manage group descriptors */ #define EXT4_MIN_DESC_SIZE 32 +#define EXT4_MIN_DESC_SIZE_64BIT 64 #define EXT4_MAX_DESC_SIZE EXT4_MIN_BLOCK_SIZE #define EXT4_DESC_SIZE(s) (EXT4_SB(s)->s_desc_size) #ifdef __KERNEL__ @@ -904,12 +905,18 @@ extern void ext4_abort (struct super_block *, const char *, const char *, ...) extern void ext4_warning (struct super_block *, const char *, const char *, ...) __attribute__ ((format (printf, 3, 4))); extern void ext4_update_dynamic_rev (struct super_block *sb); -extern ext4_fsblk_t ext4_block_bitmap(struct ext4_group_desc *bg); -extern ext4_fsblk_t ext4_inode_bitmap(struct ext4_group_desc *bg); -extern ext4_fsblk_t ext4_inode_table(struct ext4_group_desc *bg); -extern void ext4_block_bitmap_set(struct ext4_group_desc *bg, ext4_fsblk_t blk); -extern void ext4_inode_bitmap_set(struct ext4_group_desc *bg, ext4_fsblk_t blk); -extern void ext4_inode_table_set(struct ext4_group_desc *bg, ext4_fsblk_t blk); +extern ext4_fsblk_t ext4_block_bitmap(struct super_block *sb, + struct ext4_group_desc *bg); +extern ext4_fsblk_t ext4_inode_bitmap(struct super_block *sb, + struct ext4_group_desc *bg); +extern ext4_fsblk_t ext4_inode_table(struct super_block *sb, + struct ext4_group_desc *bg); +extern void ext4_block_bitmap_set(struct super_block *sb, + struct ext4_group_desc *bg, ext4_fsblk_t blk); +extern void ext4_inode_bitmap_set(struct super_block *sb, + struct ext4_group_desc *bg, ext4_fsblk_t blk); +extern void ext4_inode_table_set(struct super_block *sb, + struct ext4_group_desc *bg, ext4_fsblk_t blk); static inline ext4_fsblk_t ext4_blocks_count(struct ext4_super_block *es) { -- cgit v1.2.3 From 72b64b594081ef0a0717f6aad77e891c72ed4afa Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Wed, 11 Oct 2006 01:21:18 -0700 Subject: [PATCH] ext4 uninline ext4_get_group_no_and_offset() Way too big to inline. Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ext4_fs.h | 22 ++-------------------- 1 file changed, 2 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ext4_fs.h b/include/linux/ext4_fs.h index 296609b9242d..498503ee613d 100644 --- a/include/linux/ext4_fs.h +++ b/include/linux/ext4_fs.h @@ -769,26 +769,8 @@ ext4_group_first_block_no(struct super_block *sb, unsigned long group_no) */ #define ERR_BAD_DX_DIR -75000 -/* - * This function calculate the block group number and offset, - * given a block number - */ - -static inline void ext4_get_group_no_and_offset(struct super_block * sb, - ext4_fsblk_t blocknr, unsigned long* blockgrpp, - ext4_grpblk_t *offsetp) -{ - struct ext4_super_block *es = EXT4_SB(sb)->s_es; - ext4_grpblk_t offset; - - blocknr = blocknr - le32_to_cpu(es->s_first_data_block); - offset = sector_div(blocknr, EXT4_BLOCKS_PER_GROUP(sb)); - if (offsetp) - *offsetp = offset; - if (blockgrpp) - *blockgrpp = blocknr; - -} +void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr, + unsigned long *blockgrpp, ext4_grpblk_t *offsetp); /* * Function prototypes -- cgit v1.2.3 From 9858db504caedb2424b9a32744c23f9a81ec1731 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Wed, 11 Oct 2006 01:21:30 -0700 Subject: [PATCH] mm: locks_freed fix Move the lock debug checks below the page reserved checks. Also, having debug_check_no_locks_freed in kernel_map_pages is wrong. Signed-off-by: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 26146623be2f..5a6068ff5556 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1103,12 +1103,7 @@ static inline void vm_stat_account(struct mm_struct *mm, #ifndef CONFIG_DEBUG_PAGEALLOC static inline void -kernel_map_pages(struct page *page, int numpages, int enable) -{ - if (!PageHighMem(page) && !enable) - debug_check_no_locks_freed(page_address(page), - numpages * PAGE_SIZE); -} +kernel_map_pages(struct page *page, int numpages, int enable) {} #endif extern struct vm_area_struct *get_gate_vma(struct task_struct *tsk); -- cgit v1.2.3 From b611967de4dc5c52049676c4369dcac622a7cdfe Mon Sep 17 00:00:00 2001 From: Davide Libenzi Date: Wed, 11 Oct 2006 01:21:44 -0700 Subject: [PATCH] epoll_pwait() Implement the epoll_pwait system call, that extend the event wait mechanism with the same logic ppoll and pselect do. The definition of epoll_pwait is: int epoll_pwait(int epfd, struct epoll_event *events, int maxevents, int timeout, const sigset_t *sigmask, size_t sigsetsize); The difference between the vanilla epoll_wait and epoll_pwait is that the latter allows the caller to specify a signal mask to be set while waiting for events. Hence epoll_pwait will wait until either one monitored event, or an unmasked signal happen. If sigmask is NULL, the epoll_pwait system call will act exactly like epoll_wait. For the POSIX definition of pselect, information is available here: http://www.opengroup.org/onlinepubs/009695399/functions/select.html Signed-off-by: Davide Libenzi Cc: David Woodhouse Cc: Andi Kleen Cc: Michael Kerrisk Cc: Ulrich Drepper Cc: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/syscalls.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index b0ace3fd7eb9..1912c6cbef55 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -431,6 +431,10 @@ asmlinkage long sys_epoll_ctl(int epfd, int op, int fd, struct epoll_event __user *event); asmlinkage long sys_epoll_wait(int epfd, struct epoll_event __user *events, int maxevents, int timeout); +asmlinkage long sys_epoll_pwait(int epfd, struct epoll_event __user *events, + int maxevents, int timeout, + const sigset_t __user *sigmask, + size_t sigsetsize); asmlinkage long sys_gethostname(char __user *name, int len); asmlinkage long sys_sethostname(char __user *name, int len); asmlinkage long sys_setdomainname(char __user *name, int len); -- cgit v1.2.3 From e0ab2928cc2202f13f0574d4c6f567f166d307eb Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Wed, 11 Oct 2006 01:21:45 -0700 Subject: [PATCH] Add carta_random32() library routine This is a follow-up patch based on the review for perfmon2. This patch adds the carta_random32() library routine + carta_random32.h header file. This is fast, simple, and efficient pseudo number generator algorithm. We use it in perfmon2 to randomize the sampling periods. In this context, we do not need any fancy randomizer. Signed-off-by: stephane eranian Cc: David Mosberger Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/carta_random32.h | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) create mode 100644 include/linux/carta_random32.h (limited to 'include/linux') diff --git a/include/linux/carta_random32.h b/include/linux/carta_random32.h new file mode 100644 index 000000000000..f6f3bd9f20b5 --- /dev/null +++ b/include/linux/carta_random32.h @@ -0,0 +1,29 @@ +/* + * Fast, simple, yet decent quality random number generator based on + * a paper by David G. Carta ("Two Fast Implementations of the + * `Minimal Standard' Random Number Generator," Communications of the + * ACM, January, 1990). + * + * Copyright (c) 2002-2006 Hewlett-Packard Development Company, L.P. + * Contributed by Stephane Eranian + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA + * 02111-1307 USA + */ +#ifndef _LINUX_CARTA_RANDOM32_H_ +#define _LINUX_CARTA_RANDOM32_H_ + +u64 carta_random32(u64 seed); + +#endif /* _LINUX_CARTA_RANDOM32_H_ */ -- cgit v1.2.3 From fa3ba2e81ea23416272a22009bba95954c81969c Mon Sep 17 00:00:00 2001 From: Florin Malita Date: Wed, 11 Oct 2006 01:21:48 -0700 Subject: [PATCH] fix Module taint flags listing in Oops/panic Module taint flags listing in Oops/panic has a couple of issues: * taint_flags() doesn't null-terminate the buffer after printing the flags * per-module taints are only set if the kernel is not already tainted (with that particular flag) => only the first offending module gets its taint info correctly updated Some additional changes: * 'license_gplok' is no longer needed - equivalent to !(taints & TAINT_PROPRIETARY_MODULE) - so we can drop it from struct module * exporting module taint info via /proc/module: pwc 88576 0 - Live 0xf8c32000 evilmod 6784 1 pwc, Live 0xf8bbf000 (PF) Signed-off-by: Florin Malita Cc: "Randy.Dunlap" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/module.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index 4b2d8091a410..d1d00ce8f4ed 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -317,9 +317,6 @@ struct module /* Am I unsafe to unload? */ int unsafe; - /* Am I GPL-compatible */ - int license_gplok; - unsigned int taints; /* same bits as kernel:tainted */ #ifdef CONFIG_MODULE_UNLOAD -- cgit v1.2.3 From 39484e53bb00f55b6303a908070db133608ef2a5 Mon Sep 17 00:00:00 2001 From: "Maciej W. Rozycki" Date: Wed, 11 Oct 2006 01:21:54 -0700 Subject: [PATCH] 32-bit compatibility HDIO IOCTLs A couple of HDIO IOCTLs are not yet handled and a few others are marked as using a pointer rather than an unsigned long. The formers include: HDIO_GET_WCACHE, HDIO_GET_ACOUSTIC, HDIO_GET_ADDRESS and HDIO_GET_BUSSTATE. The latters are: HDIO_SET_MULTCOUNT, HDIO_SET_UNMASKINTR, HDIO_SET_KEEPSETTINGS, HDIO_SET_32BIT, HDIO_SET_NOWERR, HDIO_SET_DMA, HDIO_SET_PIO_MODE and HDIO_SET_NICE. Additionally 0x330 used to be HDIO_GETGEO_BIG and may be issued by 32-bit `hdparm' run on a 64-bit kernel making Linux complain loudly. This is a fix for these issues. Signed-off-by: Maciej W. Rozycki Cc: Alan Cox Acked-by: Arnd Bergmann Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compat_ioctl.h | 24 +++++++++++++++--------- 1 file changed, 15 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compat_ioctl.h b/include/linux/compat_ioctl.h index 4e1663d7691e..cfdb4f6a89d4 100644 --- a/include/linux/compat_ioctl.h +++ b/include/linux/compat_ioctl.h @@ -61,17 +61,23 @@ COMPATIBLE_IOCTL(FIGETBSZ) * Some need translations, these do not. */ COMPATIBLE_IOCTL(HDIO_GET_IDENTITY) -COMPATIBLE_IOCTL(HDIO_SET_DMA) -COMPATIBLE_IOCTL(HDIO_SET_UNMASKINTR) -COMPATIBLE_IOCTL(HDIO_SET_NOWERR) -COMPATIBLE_IOCTL(HDIO_SET_32BIT) -COMPATIBLE_IOCTL(HDIO_SET_MULTCOUNT) -COMPATIBLE_IOCTL(HDIO_DRIVE_CMD) COMPATIBLE_IOCTL(HDIO_DRIVE_TASK) -COMPATIBLE_IOCTL(HDIO_SET_PIO_MODE) -COMPATIBLE_IOCTL(HDIO_SET_NICE) -COMPATIBLE_IOCTL(HDIO_SET_KEEPSETTINGS) +COMPATIBLE_IOCTL(HDIO_DRIVE_CMD) +ULONG_IOCTL(HDIO_SET_MULTCOUNT) +ULONG_IOCTL(HDIO_SET_UNMASKINTR) +ULONG_IOCTL(HDIO_SET_KEEPSETTINGS) +ULONG_IOCTL(HDIO_SET_32BIT) +ULONG_IOCTL(HDIO_SET_NOWERR) +ULONG_IOCTL(HDIO_SET_DMA) +ULONG_IOCTL(HDIO_SET_PIO_MODE) +ULONG_IOCTL(HDIO_SET_NICE) +ULONG_IOCTL(HDIO_SET_WCACHE) +ULONG_IOCTL(HDIO_SET_ACOUSTIC) +ULONG_IOCTL(HDIO_SET_BUSSTATE) +ULONG_IOCTL(HDIO_SET_ADDRESS) COMPATIBLE_IOCTL(HDIO_SCAN_HWIF) +/* 0x330 is reserved -- it used to be HDIO_GETGEO_BIG */ +COMPATIBLE_IOCTL(0x330) /* 0x02 -- Floppy ioctls */ COMPATIBLE_IOCTL(FDMSGON) COMPATIBLE_IOCTL(FDMSGOFF) -- cgit v1.2.3 From 01a3ee2b203e511e20f98b85a9172fd32c53e87c Mon Sep 17 00:00:00 2001 From: Reinette Chatre Date: Wed, 11 Oct 2006 01:21:55 -0700 Subject: [PATCH] bitmap: parse input from kernel and user buffers lib/bitmap.c:bitmap_parse() is a library function that received as input a user buffer. This seemed to have originated from the way the write_proc function of the /proc filesystem operates. This has been reworked to not use kmalloc and eliminates a lot of get_user() overhead by performing one access_ok before using __get_user(). We need to test if we are in kernel or user space (is_user) and access the buffer differently. We cannot use __get_user() to access kernel addresses in all cases, for example in architectures with separate address space for kernel and user. This function will be useful for other uses as well; for example, taking input for /sysfs instead of /proc, so it was changed to accept kernel buffers. We have this use for the Linux UWB project, as part as the upcoming bandwidth allocator code. Only a few routines used this function and they were changed too. Signed-off-by: Reinette Chatre Signed-off-by: Inaky Perez-Gonzalez Cc: Paul Jackson Cc: Joe Korty Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bitmap.h | 13 +++++++++++-- include/linux/cpumask.h | 14 +++++++------- include/linux/nodemask.h | 14 +++++++------- 3 files changed, 25 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index dcc5de7cc487..64b4641904fe 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -46,7 +46,8 @@ * bitmap_remap(dst, src, old, new, nbits) *dst = map(old, new)(src) * bitmap_bitremap(oldbit, old, new, nbits) newbit = map(old, new)(oldbit) * bitmap_scnprintf(buf, len, src, nbits) Print bitmap src to buf - * bitmap_parse(ubuf, ulen, dst, nbits) Parse bitmap dst from user buf + * bitmap_parse(buf, buflen, dst, nbits) Parse bitmap dst from kernel buf + * bitmap_parse_user(ubuf, ulen, dst, nbits) Parse bitmap dst from user buf * bitmap_scnlistprintf(buf, len, src, nbits) Print bitmap src as list to buf * bitmap_parselist(buf, dst, nbits) Parse bitmap dst from list * bitmap_find_free_region(bitmap, bits, order) Find and allocate bit region @@ -106,7 +107,9 @@ extern int __bitmap_weight(const unsigned long *bitmap, int bits); extern int bitmap_scnprintf(char *buf, unsigned int len, const unsigned long *src, int nbits); -extern int bitmap_parse(const char __user *ubuf, unsigned int ulen, +extern int __bitmap_parse(const char *buf, unsigned int buflen, int is_user, + unsigned long *dst, int nbits); +extern int bitmap_parse_user(const char __user *ubuf, unsigned int ulen, unsigned long *dst, int nbits); extern int bitmap_scnlistprintf(char *buf, unsigned int len, const unsigned long *src, int nbits); @@ -270,6 +273,12 @@ static inline void bitmap_shift_left(unsigned long *dst, __bitmap_shift_left(dst, src, n, nbits); } +static inline int bitmap_parse(const char *buf, unsigned int buflen, + unsigned long *maskp, int nmaskbits) +{ + return __bitmap_parse(buf, buflen, 0, maskp, nmaskbits); +} + #endif /* __ASSEMBLY__ */ #endif /* __LINUX_BITMAP_H */ diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index b268a3c0c376..d0e8c8b0e34d 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -8,8 +8,8 @@ * See detailed comments in the file linux/bitmap.h describing the * data type on which these cpumasks are based. * - * For details of cpumask_scnprintf() and cpumask_parse(), - * see bitmap_scnprintf() and bitmap_parse() in lib/bitmap.c. + * For details of cpumask_scnprintf() and cpumask_parse_user(), + * see bitmap_scnprintf() and bitmap_parse_user() in lib/bitmap.c. * For details of cpulist_scnprintf() and cpulist_parse(), see * bitmap_scnlistprintf() and bitmap_parselist(), also in bitmap.c. * For details of cpu_remap(), see bitmap_bitremap in lib/bitmap.c @@ -49,7 +49,7 @@ * unsigned long *cpus_addr(mask) Array of unsigned long's in mask * * int cpumask_scnprintf(buf, len, mask) Format cpumask for printing - * int cpumask_parse(ubuf, ulen, mask) Parse ascii string as cpumask + * int cpumask_parse_user(ubuf, ulen, mask) Parse ascii string as cpumask * int cpulist_scnprintf(buf, len, mask) Format cpumask as list for printing * int cpulist_parse(buf, map) Parse ascii string as cpulist * int cpu_remap(oldbit, old, new) newbit = map(old, new)(oldbit) @@ -273,12 +273,12 @@ static inline int __cpumask_scnprintf(char *buf, int len, return bitmap_scnprintf(buf, len, srcp->bits, nbits); } -#define cpumask_parse(ubuf, ulen, dst) \ - __cpumask_parse((ubuf), (ulen), &(dst), NR_CPUS) -static inline int __cpumask_parse(const char __user *buf, int len, +#define cpumask_parse_user(ubuf, ulen, dst) \ + __cpumask_parse_user((ubuf), (ulen), &(dst), NR_CPUS) +static inline int __cpumask_parse_user(const char __user *buf, int len, cpumask_t *dstp, int nbits) { - return bitmap_parse(buf, len, dstp->bits, nbits); + return bitmap_parse_user(buf, len, dstp->bits, nbits); } #define cpulist_scnprintf(buf, len, src) \ diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index 5dce5c21822c..b1063e9cdb1b 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -8,8 +8,8 @@ * See detailed comments in the file linux/bitmap.h describing the * data type on which these nodemasks are based. * - * For details of nodemask_scnprintf() and nodemask_parse(), - * see bitmap_scnprintf() and bitmap_parse() in lib/bitmap.c. + * For details of nodemask_scnprintf() and nodemask_parse_user(), + * see bitmap_scnprintf() and bitmap_parse_user() in lib/bitmap.c. * For details of nodelist_scnprintf() and nodelist_parse(), see * bitmap_scnlistprintf() and bitmap_parselist(), also in bitmap.c. * For details of node_remap(), see bitmap_bitremap in lib/bitmap.c. @@ -51,7 +51,7 @@ * unsigned long *nodes_addr(mask) Array of unsigned long's in mask * * int nodemask_scnprintf(buf, len, mask) Format nodemask for printing - * int nodemask_parse(ubuf, ulen, mask) Parse ascii string as nodemask + * int nodemask_parse_user(ubuf, ulen, mask) Parse ascii string as nodemask * int nodelist_scnprintf(buf, len, mask) Format nodemask as list for printing * int nodelist_parse(buf, map) Parse ascii string as nodelist * int node_remap(oldbit, old, new) newbit = map(old, new)(oldbit) @@ -288,12 +288,12 @@ static inline int __nodemask_scnprintf(char *buf, int len, return bitmap_scnprintf(buf, len, srcp->bits, nbits); } -#define nodemask_parse(ubuf, ulen, dst) \ - __nodemask_parse((ubuf), (ulen), &(dst), MAX_NUMNODES) -static inline int __nodemask_parse(const char __user *buf, int len, +#define nodemask_parse_user(ubuf, ulen, dst) \ + __nodemask_parse_user((ubuf), (ulen), &(dst), MAX_NUMNODES) +static inline int __nodemask_parse_user(const char __user *buf, int len, nodemask_t *dstp, int nbits) { - return bitmap_parse(buf, len, dstp->bits, nbits); + return bitmap_parse_user(buf, len, dstp->bits, nbits); } #define nodelist_scnprintf(buf, len, src) \ -- cgit v1.2.3 From e50190a8341485b413f599033cb74649f849d939 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 11 Oct 2006 01:22:02 -0700 Subject: [PATCH] Consolidate check_signature There's nothing arch-specific about check_signature(), so move it to . Use a cross between the Alpha and i386 implementations as the generic one. Signed-off-by: Matthew Wilcox Acked-by: Alan Cox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/io.h | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) (limited to 'include/linux') diff --git a/include/linux/io.h b/include/linux/io.h index 2ad96c3f0e4e..81877ea39309 100644 --- a/include/linux/io.h +++ b/include/linux/io.h @@ -28,4 +28,31 @@ void __iowrite64_copy(void __iomem *to, const void *from, size_t count); int ioremap_page_range(unsigned long addr, unsigned long end, unsigned long phys_addr, pgprot_t prot); +/** + * check_signature - find BIOS signatures + * @io_addr: mmio address to check + * @signature: signature block + * @length: length of signature + * + * Perform a signature comparison with the mmio address io_addr. This + * address should have been obtained by ioremap. + * Returns 1 on a match. + */ + +static inline int check_signature(const volatile void __iomem *io_addr, + const unsigned char *signature, int length) +{ + int retval = 0; + do { + if (readb(io_addr) != *signature) + goto out; + io_addr++; + signature++; + length--; + } while (length); + retval = 1; +out: + return retval; +} + #endif /* _LINUX_IO_H */ -- cgit v1.2.3 From c751c1dbb1289d220a8a175ba0df47706ce95a7e Mon Sep 17 00:00:00 2001 From: Mike Frysinger Date: Wed, 11 Oct 2006 01:22:11 -0700 Subject: [PATCH] include linux/types.h in linux/nbd.h The nbd header uses __be32 and such types but doesn't actually include the header that defines these things (linux/types.h); so let's include it. Signed-off-by: Mike Frysinger Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nbd.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nbd.h b/include/linux/nbd.h index e712e7d47cc2..d6b6dc09ad97 100644 --- a/include/linux/nbd.h +++ b/include/linux/nbd.h @@ -15,6 +15,8 @@ #ifndef LINUX_NBD_H #define LINUX_NBD_H +#include + #define NBD_SET_SOCK _IO( 0xab, 0 ) #define NBD_SET_BLKSIZE _IO( 0xab, 1 ) #define NBD_SET_SIZE _IO( 0xab, 2 ) -- cgit v1.2.3 From c636ebdb186bf37f98d3839f69293597723edb36 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 11 Oct 2006 01:22:19 -0700 Subject: [PATCH] VFS: Destroy the dentries contributed by a superblock on unmounting The attached patch destroys all the dentries attached to a superblock in one go by: (1) Destroying the tree rooted at s_root. (2) Destroying every entry in the anon list, one at a time. (3) Each entry in the anon list has its subtree consumed from the leaves inwards. This reduces the amount of work generic_shutdown_super() does, and avoids iterating through the dentry_unused list. Note that locking is almost entirely absent in the shrink_dcache_for_umount*() functions added by this patch. This is because: (1) at the point the filesystem calls generic_shutdown_super(), it is not permitted to further touch the superblock's set of dentries, and nor may it remove aliases from inodes; (2) the dcache memory shrinker now skips dentries that are being unmounted; and (3) the superblock no longer has any external references through which the VFS can reach it. Given these points, the only locking we need to do is when we remove dentries from the unused list and the name hashes, which we do a directory's worth at a time. We also don't need to guard against reference counts going to zero unexpectedly and removing bits of the tree we're working on as nothing else can call dput(). A cut down version of dentry_iput() has been folded into shrink_dcache_for_umount_subtree() function. Apart from not needing to unlock things, it also doesn't need to check for inotify watches. In this version of the patch, the complaint about a dentry still being in use has been expanded from a single BUG_ON() and now gives much more information. Signed-off-by: David Howells Acked-by: NeilBrown Acked-by: Ian Kent Cc: Trond Myklebust Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/dcache.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 44605be59409..63f64a9a5bf7 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -230,6 +230,7 @@ extern struct dentry * d_alloc_anon(struct inode *); extern struct dentry * d_splice_alias(struct inode *, struct dentry *); extern void shrink_dcache_sb(struct super_block *); extern void shrink_dcache_parent(struct dentry *); +extern void shrink_dcache_for_umount(struct super_block *); extern int d_invalidate(struct dentry *); /* only used at mount-time */ -- cgit v1.2.3 From 07646e217f473a3e6213f8228336a9046833d6aa Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Wed, 11 Oct 2006 23:45:23 -0400 Subject: Lockdep: fix compile error in drivers/input/serio/serio.c lockdep_set_subclass() was missing in !LOCKDEP case Signed-off-by: Andrew Morton Signed-off-by: Dmitry Torokhov --- include/linux/lockdep.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 14fec2a23b2e..819f08f1310d 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -268,6 +268,8 @@ static inline int lockdep_internal(void) do { (void)(key); } while (0) #define lockdep_set_class_and_subclass(lock, key, sub) \ do { (void)(key); } while (0) +#define lockdep_set_subclass(lock, sub) do { } while (0) + # define INIT_LOCKDEP # define lockdep_reset() do { debug_locks = 1; } while (0) # define lockdep_free_key_range(start, size) do { } while (0) -- cgit v1.2.3 From 5b368e61c2bcb2666bb66e2acf1d6d85ba6f474d Mon Sep 17 00:00:00 2001 From: Venkat Yekkirala Date: Thu, 5 Oct 2006 15:42:18 -0500 Subject: IPsec: correct semantics for SELinux policy matching Currently when an IPSec policy rule doesn't specify a security context, it is assumed to be "unlabeled" by SELinux, and so the IPSec policy rule fails to match to a flow that it would otherwise match to, unless one has explicitly added an SELinux policy rule allowing the flow to "polmatch" to the "unlabeled" IPSec policy rules. In the absence of such an explicitly added SELinux policy rule, the IPSec policy rule fails to match and so the packet(s) flow in clear text without the otherwise applicable xfrm(s) applied. The above SELinux behavior violates the SELinux security notion of "deny by default" which should actually translate to "encrypt by default" in the above case. This was first reported by Evgeniy Polyakov and the way James Morris was seeing the problem was when connecting via IPsec to a confined service on an SELinux box (vsftpd), which did not have the appropriate SELinux policy permissions to send packets via IPsec. With this patch applied, SELinux "polmatching" of flows Vs. IPSec policy rules will only come into play when there's a explicit context specified for the IPSec policy rule (which also means there's corresponding SELinux policy allowing appropriate domains/flows to polmatch to this context). Secondly, when a security module is loaded (in this case, SELinux), the security_xfrm_policy_lookup() hook can return errors other than access denied, such as -EINVAL. We were not handling that correctly, and in fact inverting the return logic and propagating a false "ok" back up to xfrm_lookup(), which then allowed packets to pass as if they were not associated with an xfrm policy. The solution for this is to first ensure that errno values are correctly propagated all the way back up through the various call chains from security_xfrm_policy_lookup(), and handled correctly. Then, flow_cache_lookup() is modified, so that if the policy resolver fails (typically a permission denied via the security module), the flow cache entry is killed rather than having a null policy assigned (which indicates that the packet can pass freely). This also forces any future lookups for the same flow to consult the security module (e.g. SELinux) for current security policy (rather than, say, caching the error on the flow cache entry). This patch: Fix the selinux side of things. This makes sure SELinux polmatching of flow contexts to IPSec policy rules comes into play only when an explicit context is associated with the IPSec policy rule. Also, this no longer defaults the context of a socket policy to the context of the socket since the "no explicit context" case is now handled properly. Signed-off-by: Venkat Yekkirala Signed-off-by: James Morris --- include/linux/security.h | 24 +++++++++--------------- 1 file changed, 9 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index 9b5fea81f55e..b200b9856f32 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -882,7 +882,8 @@ struct request_sock; * Check permission when a flow selects a xfrm_policy for processing * XFRMs on a packet. The hook is called when selecting either a * per-socket policy or a generic xfrm policy. - * Return 0 if permission is granted. + * Return 0 if permission is granted, -ESRCH otherwise, or -errno + * on other errors. * @xfrm_state_pol_flow_match: * @x contains the state to match. * @xp contains the policy to check for a match. @@ -891,6 +892,7 @@ struct request_sock; * @xfrm_flow_state_match: * @fl contains the flow key to match. * @xfrm points to the xfrm_state to match. + * @xp points to the xfrm_policy to match. * Return 1 if there is a match. * @xfrm_decode_session: * @skb points to skb to decode. @@ -1388,7 +1390,8 @@ struct security_operations { int (*xfrm_policy_lookup)(struct xfrm_policy *xp, u32 fl_secid, u8 dir); int (*xfrm_state_pol_flow_match)(struct xfrm_state *x, struct xfrm_policy *xp, struct flowi *fl); - int (*xfrm_flow_state_match)(struct flowi *fl, struct xfrm_state *xfrm); + int (*xfrm_flow_state_match)(struct flowi *fl, struct xfrm_state *xfrm, + struct xfrm_policy *xp); int (*xfrm_decode_session)(struct sk_buff *skb, u32 *secid, int ckall); #endif /* CONFIG_SECURITY_NETWORK_XFRM */ @@ -3120,11 +3123,6 @@ static inline int security_xfrm_policy_alloc(struct xfrm_policy *xp, struct xfrm return security_ops->xfrm_policy_alloc_security(xp, sec_ctx, NULL); } -static inline int security_xfrm_sock_policy_alloc(struct xfrm_policy *xp, struct sock *sk) -{ - return security_ops->xfrm_policy_alloc_security(xp, NULL, sk); -} - static inline int security_xfrm_policy_clone(struct xfrm_policy *old, struct xfrm_policy *new) { return security_ops->xfrm_policy_clone_security(old, new); @@ -3175,9 +3173,10 @@ static inline int security_xfrm_state_pol_flow_match(struct xfrm_state *x, return security_ops->xfrm_state_pol_flow_match(x, xp, fl); } -static inline int security_xfrm_flow_state_match(struct flowi *fl, struct xfrm_state *xfrm) +static inline int security_xfrm_flow_state_match(struct flowi *fl, + struct xfrm_state *xfrm, struct xfrm_policy *xp) { - return security_ops->xfrm_flow_state_match(fl, xfrm); + return security_ops->xfrm_flow_state_match(fl, xfrm, xp); } static inline int security_xfrm_decode_session(struct sk_buff *skb, u32 *secid) @@ -3197,11 +3196,6 @@ static inline int security_xfrm_policy_alloc(struct xfrm_policy *xp, struct xfrm return 0; } -static inline int security_xfrm_sock_policy_alloc(struct xfrm_policy *xp, struct sock *sk) -{ - return 0; -} - static inline int security_xfrm_policy_clone(struct xfrm_policy *old, struct xfrm_policy *new) { return 0; @@ -3249,7 +3243,7 @@ static inline int security_xfrm_state_pol_flow_match(struct xfrm_state *x, } static inline int security_xfrm_flow_state_match(struct flowi *fl, - struct xfrm_state *xfrm) + struct xfrm_state *xfrm, struct xfrm_policy *xp) { return 1; } -- cgit v1.2.3 From 2b1191af683d16a899c2b81b87b605841ceffdec Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 9 Oct 2006 13:04:35 +0200 Subject: [PATCH] elevator: elevator_type member not used elevator_type field in elevator_type structure is useless: it isn't used anywhere in kernel sources. Signed-off-by: Vasily Tarasov Signed-off-by: Jens Axboe --- include/linux/elevator.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/elevator.h b/include/linux/elevator.h index b3370ef5164d..2fa9f1144228 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -70,7 +70,6 @@ struct elevator_type { struct list_head list; struct elevator_ops ops; - struct elevator_type *elevator_type; struct elv_fs_entry *elevator_attrs; char elevator_name[ELV_NAME_MAX]; struct module *elevator_owner; -- cgit v1.2.3 From cea2885a2e989d1dc19af1fc991717b33b7d1456 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 12 Oct 2006 15:08:45 +0200 Subject: [PATCH] ide-cd: fix breakage with internally queued commands We still need to maintain a private PC style command, since it isn't completely unified with REQ_TYPE_BLOCK_PC yet. Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 26f7856ff812..d370d2cfe138 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -157,6 +157,7 @@ enum rq_cmd_type_bits { REQ_TYPE_ATA_CMD, REQ_TYPE_ATA_TASK, REQ_TYPE_ATA_TASKFILE, + REQ_TYPE_ATA_PC, }; /* -- cgit v1.2.3 From 5011915cbb139a331c083e65a61c82e9174f9813 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Fri, 13 Oct 2006 05:12:42 -0300 Subject: V4L/DVB (4746): HM12 is YUV 4:2:0, not YUV 4:1:1 Fix comment in videodev2.h Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/linux/videodev2.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/videodev2.h b/include/linux/videodev2.h index c5fdf6259548..df5c4654360d 100644 --- a/include/linux/videodev2.h +++ b/include/linux/videodev2.h @@ -243,7 +243,7 @@ struct v4l2_pix_format #define V4L2_PIX_FMT_YUV420 v4l2_fourcc('Y','U','1','2') /* 12 YUV 4:2:0 */ #define V4L2_PIX_FMT_YYUV v4l2_fourcc('Y','Y','U','V') /* 16 YUV 4:2:2 */ #define V4L2_PIX_FMT_HI240 v4l2_fourcc('H','I','2','4') /* 8 8-bit color */ -#define V4L2_PIX_FMT_HM12 v4l2_fourcc('H','M','1','2') /* 8 YUV 4:1:1 16x16 macroblocks */ +#define V4L2_PIX_FMT_HM12 v4l2_fourcc('H','M','1','2') /* 8 YUV 4:2:0 16x16 macroblocks */ /* see http://www.siliconimaging.com/RGB%20Bayer.htm */ #define V4L2_PIX_FMT_SBGGR8 v4l2_fourcc('B','A','8','1') /* 8 BGBG.. GRGR.. */ -- cgit v1.2.3 From d7a76e4cb3b4469b1eccb6204c053e3ebcd4c196 Mon Sep 17 00:00:00 2001 From: Lennart Poettering Date: Tue, 5 Sep 2006 12:12:24 -0400 Subject: ACPI: consolidate functions in acpi ec driver Unify the following functions: acpi_ec_poll_read() acpi_ec_poll_write() acpi_ec_poll_query() acpi_ec_intr_read() acpi_ec_intr_write() acpi_ec_intr_query() into: acpi_ec_poll_transaction() acpi_ec_intr_transaction() These new functions take as arguments an ACPI EC command, a few bytes to write to the EC data register and a buffer for a few bytes to read from the EC data register. The old _read(), _write(), _query() are just special cases of these functions. Then unified the code in acpi_ec_poll_transaction() and acpi_ec_intr_transaction() a little more. Both functions are now just wrappers around the new acpi_ec_transaction_unlocked() function. The latter contains the EC access logic, the two original function now just do their special way of locking and call the the new function for the actual work. This saves a lot of very similar code. The primary reason for doing this, however, is that my driver for MSI 270 laptops needs to issue some non-standard EC commands in a safe way. Due to this I added a new exported function similar to ec_write()/ec_write() which is called ec_transaction() and is essentially just a wrapper around acpi_ec_{poll,intr}_transaction(). Signed-off-by: Lennart Poettering Acked-by: Luming Yu Signed-off-by: Andrew Morton Signed-off-by: Len Brown --- include/linux/acpi.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 88b5dfd8ee12..2b0c955590fe 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -494,6 +494,9 @@ void acpi_pci_unregister_driver(struct acpi_pci_driver *driver); extern int ec_read(u8 addr, u8 *val); extern int ec_write(u8 addr, u8 val); +extern int ec_transaction(u8 command, + const u8 *wdata, unsigned wdata_len, + u8 *rdata, unsigned rdata_len); #endif /*CONFIG_ACPI_EC*/ -- cgit v1.2.3 From aaa248f6c9c81b2683db7dbb0689cd5ed1c86d88 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Tue, 17 Oct 2006 00:09:42 -0700 Subject: [PATCH] rename net_random to random32 Make net_random() more widely available by calling it random32 akpm: hopefully this will permit the removal of carta_random32. That needs confirmation from Stephane - this code looks somewhat more computationally expensive, and has a different (ie: callee-stateful) interface. [akpm@osdl.org: lots of build fixes, cleanups] Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller Cc: Stephane Eranian Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/net.h | 7 ++++--- include/linux/random.h | 3 +++ 2 files changed, 7 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/net.h b/include/linux/net.h index c257f716e00f..15c733b816f0 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -19,6 +19,7 @@ #define _LINUX_NET_H #include +#include #include struct poll_table_struct; @@ -193,9 +194,9 @@ extern int sock_map_fd(struct socket *sock); extern struct socket *sockfd_lookup(int fd, int *err); #define sockfd_put(sock) fput(sock->file) extern int net_ratelimit(void); -extern unsigned long net_random(void); -extern void net_srandom(unsigned long); -extern void net_random_init(void); + +#define net_random() random32() +#define net_srandom(seed) srandom32(seed) extern int kernel_sendmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t len); diff --git a/include/linux/random.h b/include/linux/random.h index 5d6456bcdeba..0248b30e306d 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -69,6 +69,9 @@ extern struct file_operations random_fops, urandom_fops; unsigned int get_random_int(void); unsigned long randomize_range(unsigned long start, unsigned long end, unsigned long len); +u32 random32(void); +void srandom32(u32 seed); + #endif /* __KERNEL___ */ #endif /* _LINUX_RANDOM_H */ -- cgit v1.2.3 From a460e745e8f9c75a0525ff94154a0629f9d3e05d Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Tue, 17 Oct 2006 00:10:03 -0700 Subject: [PATCH] genirq: clean up irq-flow-type naming Introduce desc->name and eliminate the handle_irq_name() hack. Add set_irq_chip_and_handler_name() to set the flow type and name at once. Signed-off-by: Ingo Molnar Acked-by: Thomas Gleixner Cc: "Eric W. Biederman" Cc: Matthew Wilcox Cc: Kyle McMartin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/irq.h | 22 ++++++++++------------ 1 file changed, 10 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irq.h b/include/linux/irq.h index c64f3cc7e870..775f5a7da493 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -141,6 +141,7 @@ struct irq_chip { * @pending_mask: pending rebalanced interrupts * @dir: /proc/irq/ procfs entry * @affinity_entry: /proc/irq/smp_affinity procfs entry on SMP + * @name: flow handler name for /proc/interrupts output * * Pad this out to 32 bytes for cache and indexing reasons. */ @@ -165,8 +166,9 @@ struct irq_desc { cpumask_t pending_mask; #endif #ifdef CONFIG_PROC_FS - struct proc_dir_entry *dir; + struct proc_dir_entry *dir; #endif + const char *name; } ____cacheline_aligned; extern struct irq_desc irq_desc[NR_IRQS]; @@ -271,12 +273,6 @@ extern void fastcall handle_simple_irq(unsigned int irq, struct irq_desc *desc); extern void fastcall handle_percpu_irq(unsigned int irq, struct irq_desc *desc); extern void fastcall handle_bad_irq(unsigned int irq, struct irq_desc *desc); -/* - * Get a descriptive string for the highlevel handler, for - * /proc/interrupts output: - */ -extern const char *handle_irq_name(irq_flow_handler_t handle); - /* * Monolithic do_IRQ implementation. * (is an explicit fastcall, because i386 4KSTACKS calls it from assembly) @@ -326,10 +322,12 @@ extern struct irq_chip no_irq_chip; extern struct irq_chip dummy_irq_chip; extern void -set_irq_chip_and_handler(unsigned int irq, struct irq_chip *chip, - irq_flow_handler_t handle); +set_irq_chip_and_handler_name(unsigned int irq, struct irq_chip *chip, + irq_flow_handler_t handle, const char *name); + extern void -__set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained); +__set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained, + const char *name); /* * Set a highlevel flow handler for a given IRQ: @@ -337,7 +335,7 @@ __set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained); static inline void set_irq_handler(unsigned int irq, irq_flow_handler_t handle) { - __set_irq_handler(irq, handle, 0); + __set_irq_handler(irq, handle, 0, NULL); } /* @@ -349,7 +347,7 @@ static inline void set_irq_chained_handler(unsigned int irq, irq_flow_handler_t handle) { - __set_irq_handler(irq, handle, 1); + __set_irq_handler(irq, handle, 1, NULL); } /* Handle dynamic irq creation and destruction */ -- cgit v1.2.3 From 7762f5a0b709b415fda132258ad37b9f2a1db994 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Tue, 17 Oct 2006 00:10:07 -0700 Subject: [PATCH] document i_size_write locking rules Unless someone reads the documentation for write_seqcount_{begin,end} it is not obvious, that i_size_write() needs locking. Especially, that lack of such locking can result in a system hang. Signed-off-by: Miklos Szeredi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 34406ed467c3..661c7c572149 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -656,7 +656,11 @@ static inline loff_t i_size_read(struct inode *inode) #endif } - +/* + * NOTE: unlike i_size_read(), i_size_write() does need locking around it + * (normally i_mutex), otherwise on 32bit/SMP an update of i_size_seqcount + * can be lost, resulting in subsequent i_size_read() calls spinning forever. + */ static inline void i_size_write(struct inode *inode, loff_t i_size) { #if BITS_PER_LONG==32 && defined(CONFIG_SMP) -- cgit v1.2.3 From d343fce148a4eee24a907a05c4101d3268045aae Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 17 Oct 2006 00:10:18 -0700 Subject: [PATCH] knfsd: Allow lockd to drop replies as appropriate It is possible for the ->fopen callback from lockd into nfsd to find that an answer cannot be given straight away (an upcall is needed) and so the request has to be 'dropped', to be retried later. That error status is not currently propagated back. So: Change nlm_fopen to return nlm error codes (rather than a private protocol) and define a new nlm_drop_reply code. Cause nlm_drop_reply to cause the rpc request to get rpc_drop_reply when this error comes back. Cause svc_process to drop a request which returns a status of rpc_drop_reply. [akpm@osdl.org: fix warning storm] Cc: Marc Eshel Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/lockd/bind.h | 5 +++++ include/linux/lockd/xdr.h | 4 ++++ include/linux/sunrpc/msg_prot.h | 4 +++- include/linux/sunrpc/xdr.h | 1 + 4 files changed, 13 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/lockd/bind.h b/include/linux/lockd/bind.h index 81e3a185f951..aa50d89eacd7 100644 --- a/include/linux/lockd/bind.h +++ b/include/linux/lockd/bind.h @@ -10,6 +10,11 @@ #define LINUX_LOCKD_BIND_H #include +/* need xdr-encoded error codes too, so... */ +#include +#ifdef CONFIG_LOCKD_V4 +#include +#endif /* Dummy declarations */ struct svc_rqst; diff --git a/include/linux/lockd/xdr.h b/include/linux/lockd/xdr.h index bb0a0f1caa91..66fdae3b490c 100644 --- a/include/linux/lockd/xdr.h +++ b/include/linux/lockd/xdr.h @@ -13,6 +13,8 @@ #include #include +struct svc_rqst; + #define NLM_MAXCOOKIELEN 32 #define NLM_MAXSTRLEN 1024 @@ -22,6 +24,8 @@ #define nlm_lck_blocked __constant_htonl(NLM_LCK_BLOCKED) #define nlm_lck_denied_grace_period __constant_htonl(NLM_LCK_DENIED_GRACE_PERIOD) +#define nlm_drop_reply __constant_htonl(30000) + /* Lock info passed via NLM */ struct nlm_lock { char * caller; diff --git a/include/linux/sunrpc/msg_prot.h b/include/linux/sunrpc/msg_prot.h index 1e65f2dd80e5..606cb2165232 100644 --- a/include/linux/sunrpc/msg_prot.h +++ b/include/linux/sunrpc/msg_prot.h @@ -56,7 +56,9 @@ enum rpc_accept_stat { RPC_PROG_MISMATCH = 2, RPC_PROC_UNAVAIL = 3, RPC_GARBAGE_ARGS = 4, - RPC_SYSTEM_ERR = 5 + RPC_SYSTEM_ERR = 5, + /* internal use only */ + RPC_DROP_REPLY = 60000, }; enum rpc_reject_stat { diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 953723b09bc6..ac69e5511606 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -74,6 +74,7 @@ struct xdr_buf { #define rpc_proc_unavail __constant_htonl(RPC_PROC_UNAVAIL) #define rpc_garbage_args __constant_htonl(RPC_GARBAGE_ARGS) #define rpc_system_err __constant_htonl(RPC_SYSTEM_ERR) +#define rpc_drop_reply __constant_htonl(RPC_DROP_REPLY) #define rpc_auth_ok __constant_htonl(RPC_AUTH_OK) #define rpc_autherr_badcred __constant_htonl(RPC_AUTH_BADCRED) -- cgit v1.2.3 From 58ff407bee5a55f9c1188a3f9d70ffc79485183c Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 17 Oct 2006 00:10:19 -0700 Subject: [PATCH] Fix IO error reporting on fsync() When IO error happens on metadata buffer, buffer is freed from memory and later fsync() is called, filesystems like ext2 fail to report EIO. We solve the problem by introducing a pointer to associated address space into the buffer_head. When a buffer is removed from a list of metadata buffers associated with an address space, IO error is transferred from the buffer to the address space, so that fsync can later report it. Signed-off-by: Jan Kara Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/buffer_head.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 131ffd37e716..5d9fb0e94156 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -69,6 +69,8 @@ struct buffer_head { bh_end_io_t *b_end_io; /* I/O completion */ void *b_private; /* reserved for b_end_io */ struct list_head b_assoc_buffers; /* associated with another mapping */ + struct address_space *b_assoc_map; /* mapping this buffer is + associated with */ atomic_t b_count; /* users using this buffer_head */ }; -- cgit v1.2.3 From 74d919465a93b6c2b928b29a8ed3e5e41adbfa93 Mon Sep 17 00:00:00 2001 From: Ben Collins Date: Wed, 18 Oct 2006 08:55:54 -0400 Subject: [pci_ids] Add Quicknet XJ vendor/device ID's. Signed-off-by: Ben Collins --- 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 f069df245469..f3a168f3c9df 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2351,3 +2351,5 @@ #define PCI_DEVICE_ID_RME_DIGI32_PRO 0x9897 #define PCI_DEVICE_ID_RME_DIGI32_8 0x9898 +#define PCI_VENDOR_ID_QUICKNET 0x15E2 +#define PCI_DEVICE_ID_QUICKNET_XJ 0x0500 -- cgit v1.2.3 From 29f3eb64634cf96903a3cdb56b1f9a80bebad17d Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Mon, 16 Oct 2006 16:20:21 -0700 Subject: pci: Additional search functions In order to finish converting to pci_get_* interfaces we need to add a couple of bits of missing functionaility pci_get_bus_and_slot() provides the equivalent to pci_find_slot() (pci_get_slot is already taken as a name for something similar but not the same) pci_get_device_reverse() is the equivalent of pci_find_device_reverse but refcounting Signed-off-by: Alan Cox Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- include/linux/pci.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 5c604f5fad67..09bf88fc80c5 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -452,13 +452,14 @@ struct pci_dev *pci_find_slot (unsigned int bus, unsigned int devfn); int pci_find_capability (struct pci_dev *dev, int cap); int pci_find_next_capability (struct pci_dev *dev, u8 pos, int cap); int pci_find_ext_capability (struct pci_dev *dev, int cap); -struct pci_bus * pci_find_next_bus(const struct pci_bus *from); +struct pci_bus *pci_find_next_bus(const struct pci_bus *from); struct pci_dev *pci_get_device (unsigned int vendor, unsigned int device, struct pci_dev *from); struct pci_dev *pci_get_subsys (unsigned int vendor, unsigned int device, unsigned int ss_vendor, unsigned int ss_device, struct pci_dev *from); struct pci_dev *pci_get_slot (struct pci_bus *bus, unsigned int devfn); +struct pci_dev *pci_get_bus_and_slot (unsigned int bus, unsigned int devfn); struct pci_dev *pci_get_class (unsigned int class, struct pci_dev *from); int pci_dev_present(const struct pci_device_id *ids); -- cgit v1.2.3 From 6b4b78fed47e7380dfe9280b154e8b9bfcd4c86c Mon Sep 17 00:00:00 2001 From: Matt Domsch Date: Fri, 29 Sep 2006 15:23:23 -0500 Subject: PCI: optionally sort device lists breadth-first Problem: New Dell PowerEdge servers have 2 embedded ethernet ports, which are labeled NIC1 and NIC2 on the chassis, in the BIOS setup screens, and in the printed documentation. Assuming no other add-in ethernet ports in the system, Linux 2.4 kernels name these eth0 and eth1 respectively. Many people have come to expect this naming. Linux 2.6 kernels name these eth1 and eth0 respectively (backwards from expectations). I also have reports that various Sun and HP servers have similar behavior. Root cause: Linux 2.4 kernels walk the pci_devices list, which happens to be sorted in breadth-first order (or pcbios_find_device order on i386, which most often is breadth-first also). 2.6 kernels have both the pci_devices list and the pci_bus_type.klist_devices list, the latter is what is walked at driver load time to match the pci_id tables; this klist happens to be in depth-first order. On systems where, for physical routing reasons, NIC1 appears on a lower bus number than NIC2, but NIC2's bridge is discovered first in the depth-first ordering, NIC2 will be discovered before NIC1. If the list were sorted breadth-first, NIC1 would be discovered before NIC2. A PowerEdge 1955 system has the following topology which easily exhibits the difference between depth-first and breadth-first device lists. -[0000:00]-+-00.0 Intel Corporation 5000P Chipset Memory Controller Hub +-02.0-[0000:03-08]--+-00.0-[0000:04-07]--+-00.0-[0000:05-06]----00.0-[0000:06]----00.0 Broadcom Corporation NetXtreme II BCM5708S Gigabit Ethernet (labeled NIC2, 2.4 kernel name eth1, 2.6 kernel name eth0) +-1c.0-[0000:01-02]----00.0-[0000:02]----00.0 Broadcom Corporation NetXtreme II BCM5708S Gigabit Ethernet (labeled NIC1, 2.4 kernel name eth0, 2.6 kernel name eth1) Other factors, such as device driver load order and the presence of PCI slots at various points in the bus hierarchy further complicate this problem; I'm not trying to solve those here, just restore the device order, and thus basic behavior, that 2.4 kernels had. Solution: The solution can come in multiple steps. Suggested fix #1: kernel Patch below optionally sorts the two device lists into breadth-first ordering to maintain compatibility with 2.4 kernels. It adds two new command line options: pci=bfsort pci=nobfsort to force the sort order, or not, as you wish. It also adds DMI checks for the specific Dell systems which exhibit "backwards" ordering, to make them "right". Suggested fix #2: udev rules from userland Many people also have the expectation that embedded NICs are always discovered before add-in NICs (which this patch does not try to do). Using the PCI IRQ Routing Table provided by system BIOS, it's easy to determine which PCI devices are embedded, or if add-in, which PCI slot they're in. I'm working on a tool that would allow udev to name ethernet devices in ascending embedded, slot 1 .. slot N order, subsort by PCI bus/dev/fn breadth-first. It'll be possible to use it independent of udev as well for those distributions that don't use udev in their installers. Suggested fix #3: system board routing rules One can constrain the system board layout to put NIC1 ahead of NIC2 regardless of breadth-first or depth-first discovery order. This adds a significant level of complexity to board routing, and may not be possible in all instances (witness the above systems from several major manufacturers). I don't want to encourage this particular train of thought too far, at the expense of not doing #1 or #2 above. Feedback appreciated. Patch tested on a Dell PowerEdge 1955 blade with 2.6.18. You'll also note I took some liberty and temporarily break the klist abstraction to simplify and speed up the sort algorithm. I think that's both safe and appropriate in this instance. Signed-off-by: Matt Domsch Signed-off-by: Greg Kroah-Hartman --- include/linux/pci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 09bf88fc80c5..4689e2a699c0 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -443,6 +443,7 @@ extern void pci_remove_bus(struct pci_bus *b); extern void pci_remove_bus_device(struct pci_dev *dev); extern void pci_stop_bus_device(struct pci_dev *dev); void pci_setup_cardbus(struct pci_bus *bus); +extern void pci_sort_breadthfirst(void); /* Generic PCI functions exported to card drivers */ -- cgit v1.2.3 From 7a54f25cef6c763f16c9fd49ae382de162147873 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 13 Oct 2006 20:05:19 -0700 Subject: PCI Hotplug: move pci_hotplug.h to include/linux/ This makes it possible to build pci hotplug drivers outside of the main kernel tree, and Sam keeps telling me to move local header files to their proper places... Signed-off-by: Greg Kroah-Hartman --- include/linux/pci_hotplug.h | 236 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 236 insertions(+) create mode 100644 include/linux/pci_hotplug.h (limited to 'include/linux') diff --git a/include/linux/pci_hotplug.h b/include/linux/pci_hotplug.h new file mode 100644 index 000000000000..a675a05c4091 --- /dev/null +++ b/include/linux/pci_hotplug.h @@ -0,0 +1,236 @@ +/* + * PCI HotPlug Core Functions + * + * Copyright (C) 1995,2001 Compaq Computer Corporation + * Copyright (C) 2001 Greg Kroah-Hartman (greg@kroah.com) + * Copyright (C) 2001 IBM Corp. + * + * All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or (at + * your option) any later version. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for more + * details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. + * + * Send feedback to + * + */ +#ifndef _PCI_HOTPLUG_H +#define _PCI_HOTPLUG_H + + +/* These values come from the PCI Hotplug Spec */ +enum pci_bus_speed { + PCI_SPEED_33MHz = 0x00, + PCI_SPEED_66MHz = 0x01, + PCI_SPEED_66MHz_PCIX = 0x02, + PCI_SPEED_100MHz_PCIX = 0x03, + PCI_SPEED_133MHz_PCIX = 0x04, + PCI_SPEED_66MHz_PCIX_ECC = 0x05, + PCI_SPEED_100MHz_PCIX_ECC = 0x06, + PCI_SPEED_133MHz_PCIX_ECC = 0x07, + PCI_SPEED_66MHz_PCIX_266 = 0x09, + PCI_SPEED_100MHz_PCIX_266 = 0x0a, + PCI_SPEED_133MHz_PCIX_266 = 0x0b, + PCI_SPEED_66MHz_PCIX_533 = 0x11, + PCI_SPEED_100MHz_PCIX_533 = 0x12, + PCI_SPEED_133MHz_PCIX_533 = 0x13, + PCI_SPEED_UNKNOWN = 0xff, +}; + +/* These values come from the PCI Express Spec */ +enum pcie_link_width { + PCIE_LNK_WIDTH_RESRV = 0x00, + PCIE_LNK_X1 = 0x01, + PCIE_LNK_X2 = 0x02, + PCIE_LNK_X4 = 0x04, + PCIE_LNK_X8 = 0x08, + PCIE_LNK_X12 = 0x0C, + PCIE_LNK_X16 = 0x10, + PCIE_LNK_X32 = 0x20, + PCIE_LNK_WIDTH_UNKNOWN = 0xFF, +}; + +enum pcie_link_speed { + PCIE_2PT5GB = 0x14, + PCIE_LNK_SPEED_UNKNOWN = 0xFF, +}; + +struct hotplug_slot; +struct hotplug_slot_attribute { + struct attribute attr; + ssize_t (*show)(struct hotplug_slot *, char *); + ssize_t (*store)(struct hotplug_slot *, const char *, size_t); +}; +#define to_hotplug_attr(n) container_of(n, struct hotplug_slot_attribute, attr); + +/** + * struct hotplug_slot_ops -the callbacks that the hotplug pci core can use + * @owner: The module owner of this structure + * @enable_slot: Called when the user wants to enable a specific pci slot + * @disable_slot: Called when the user wants to disable a specific pci slot + * @set_attention_status: Called to set the specific slot's attention LED to + * the specified value + * @hardware_test: Called to run a specified hardware test on the specified + * slot. + * @get_power_status: Called to get the current power status of a slot. + * If this field is NULL, the value passed in the struct hotplug_slot_info + * will be used when this value is requested by a user. + * @get_attention_status: Called to get the current attention status of a slot. + * If this field is NULL, the value passed in the struct hotplug_slot_info + * will be used when this value is requested by a user. + * @get_latch_status: Called to get the current latch status of a slot. + * If this field is NULL, the value passed in the struct hotplug_slot_info + * will be used when this value is requested by a user. + * @get_adapter_status: Called to get see if an adapter is present in the slot or not. + * If this field is NULL, the value passed in the struct hotplug_slot_info + * will be used when this value is requested by a user. + * @get_address: Called to get pci address of a slot. + * If this field is NULL, the value passed in the struct hotplug_slot_info + * will be used when this value is requested by a user. + * @get_max_bus_speed: Called to get the max bus speed for a slot. + * If this field is NULL, the value passed in the struct hotplug_slot_info + * will be used when this value is requested by a user. + * @get_cur_bus_speed: Called to get the current bus speed for a slot. + * If this field is NULL, the value passed in the struct hotplug_slot_info + * will be used when this value is requested by a user. + * + * The table of function pointers that is passed to the hotplug pci core by a + * hotplug pci driver. These functions are called by the hotplug pci core when + * the user wants to do something to a specific slot (query it for information, + * set an LED, enable / disable power, etc.) + */ +struct hotplug_slot_ops { + struct module *owner; + int (*enable_slot) (struct hotplug_slot *slot); + int (*disable_slot) (struct hotplug_slot *slot); + int (*set_attention_status) (struct hotplug_slot *slot, u8 value); + int (*hardware_test) (struct hotplug_slot *slot, u32 value); + int (*get_power_status) (struct hotplug_slot *slot, u8 *value); + int (*get_attention_status) (struct hotplug_slot *slot, u8 *value); + int (*get_latch_status) (struct hotplug_slot *slot, u8 *value); + int (*get_adapter_status) (struct hotplug_slot *slot, u8 *value); + int (*get_address) (struct hotplug_slot *slot, u32 *value); + int (*get_max_bus_speed) (struct hotplug_slot *slot, enum pci_bus_speed *value); + int (*get_cur_bus_speed) (struct hotplug_slot *slot, enum pci_bus_speed *value); +}; + +/** + * struct hotplug_slot_info - used to notify the hotplug pci core of the state of the slot + * @power: if power is enabled or not (1/0) + * @attention_status: if the attention light is enabled or not (1/0) + * @latch_status: if the latch (if any) is open or closed (1/0) + * @adapter_present: if there is a pci board present in the slot or not (1/0) + * @address: (domain << 16 | bus << 8 | dev) + * + * Used to notify the hotplug pci core of the status of a specific slot. + */ +struct hotplug_slot_info { + u8 power_status; + u8 attention_status; + u8 latch_status; + u8 adapter_status; + u32 address; + enum pci_bus_speed max_bus_speed; + enum pci_bus_speed cur_bus_speed; +}; + +/** + * struct hotplug_slot - used to register a physical slot with the hotplug pci core + * @name: the name of the slot being registered. This string must + * be unique amoung slots registered on this system. + * @ops: pointer to the &struct hotplug_slot_ops to be used for this slot + * @info: pointer to the &struct hotplug_slot_info for the initial values for + * this slot. + * @release: called during pci_hp_deregister to free memory allocated in a + * hotplug_slot structure. + * @private: used by the hotplug pci controller driver to store whatever it + * needs. + */ +struct hotplug_slot { + char *name; + struct hotplug_slot_ops *ops; + struct hotplug_slot_info *info; + void (*release) (struct hotplug_slot *slot); + void *private; + + /* Variables below this are for use only by the hotplug pci core. */ + struct list_head slot_list; + struct kobject kobj; +}; +#define to_hotplug_slot(n) container_of(n, struct hotplug_slot, kobj) + +extern int pci_hp_register (struct hotplug_slot *slot); +extern int pci_hp_deregister (struct hotplug_slot *slot); +extern int __must_check pci_hp_change_slot_info (struct hotplug_slot *slot, + struct hotplug_slot_info *info); +extern struct subsystem pci_hotplug_slots_subsys; + +/* PCI Setting Record (Type 0) */ +struct hpp_type0 { + u32 revision; + u8 cache_line_size; + u8 latency_timer; + u8 enable_serr; + u8 enable_perr; +}; + +/* PCI-X Setting Record (Type 1) */ +struct hpp_type1 { + u32 revision; + u8 max_mem_read; + u8 avg_max_split; + u16 tot_max_split; +}; + +/* PCI Express Setting Record (Type 2) */ +struct hpp_type2 { + u32 revision; + u32 unc_err_mask_and; + u32 unc_err_mask_or; + u32 unc_err_sever_and; + u32 unc_err_sever_or; + u32 cor_err_mask_and; + u32 cor_err_mask_or; + u32 adv_err_cap_and; + u32 adv_err_cap_or; + u16 pci_exp_devctl_and; + u16 pci_exp_devctl_or; + u16 pci_exp_lnkctl_and; + u16 pci_exp_lnkctl_or; + u32 sec_unc_err_sever_and; + u32 sec_unc_err_sever_or; + u32 sec_unc_err_mask_and; + u32 sec_unc_err_mask_or; +}; + +struct hotplug_params { + struct hpp_type0 *t0; /* Type0: NULL if not available */ + struct hpp_type1 *t1; /* Type1: NULL if not available */ + struct hpp_type2 *t2; /* Type2: NULL if not available */ + struct hpp_type0 type0_data; + struct hpp_type1 type1_data; + struct hpp_type2 type2_data; +}; + +#ifdef CONFIG_ACPI +#include +#include +#include +extern acpi_status acpi_run_oshp(acpi_handle handle); +extern acpi_status acpi_get_hp_params_from_firmware(struct pci_bus *bus, + struct hotplug_params *hpp); +int acpi_root_bridge(acpi_handle handle); +#endif +#endif + -- cgit v1.2.3 From eb409460b1abec0e2a1f9c9d07019f4157a6d6bc Mon Sep 17 00:00:00 2001 From: Lijun Chen Date: Mon, 16 Oct 2006 21:59:42 -0700 Subject: [TIPC]: Added subscription cancellation capability This patch allows a TIPC application to cancel an existing topology service subscription by re-requesting the subscription with the TIPC_SUB_CANCEL filter bit set. (All other bits of the cancel request must match the original subscription request.) Signed-off-by: Allan Stephens Signed-off-by: Per Liden Signed-off-by: David S. Miller --- include/linux/tipc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tipc.h b/include/linux/tipc.h index 243a15f54002..bea469455a0c 100644 --- a/include/linux/tipc.h +++ b/include/linux/tipc.h @@ -129,6 +129,7 @@ static inline unsigned int tipc_node(__u32 addr) #define TIPC_SUB_PORTS 0x01 /* filter for port availability */ #define TIPC_SUB_SERVICE 0x02 /* filter for service availability */ +#define TIPC_SUB_CANCEL 0x04 /* cancel a subscription */ #if 0 /* The following filter options are not currently implemented */ #define TIPC_SUB_NO_BIND_EVTS 0x04 /* filter out "publish" events */ -- cgit v1.2.3 From ae8064ac32d07f609114d73928cdef803be87134 Mon Sep 17 00:00:00 2001 From: John Heffner Date: Wed, 18 Oct 2006 20:36:48 -0700 Subject: [TCP]: Bound TSO defer time This patch limits the amount of time you will defer sending a TSO segment to less than two clock ticks, or the time between two acks, whichever is longer. On slow links, deferring causes significant bursts. See attached plots, which show RTT through a 1 Mbps link with a 100 ms RTT and ~100 ms queue for (a) non-TSO, (b) currnet TSO, and (c) patched TSO. This burstiness causes significant jitter, tends to overflow queues early (bad for short queues), and makes delay-based congestion control more difficult. Deferring by a couple clock ticks I believe will have a relatively small impact on performance. Signed-off-by: John Heffner Signed-off-by: David S. Miller --- include/linux/tcp.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 0e058a2d1c6d..2d36f6db3706 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -342,6 +342,8 @@ struct tcp_sock { unsigned long last_synq_overflow; + __u32 tso_deferred; + /* Receiver side RTT estimation */ struct { __u32 rtt; -- cgit v1.2.3 From 62752ee198dca9209b7dee504763e51b11e9e0ca Mon Sep 17 00:00:00 2001 From: Mark Fasheh Date: Tue, 17 Oct 2006 10:31:38 +0200 Subject: [PATCH] Take i_mutex in splice_from_pipe() The splice_actor may be calling ->prepare_write() and ->commit_write(). We want i_mutex on the inode being written to before calling those so that we don't race i_size changes. The double locking behavior is done elsewhere in splice.c, and if we eventually want _nolock variants of generic_file_splice_write(), fs modules might have to replicate the nasty locking code. We introduce inode_double_lock() and inode_double_unlock() to consolidate the locking rules into one set of functions. Signed-off-by: Mark Fasheh Signed-off-by: Jens Axboe --- include/linux/fs.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 661c7c572149..853a02f23936 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -623,6 +623,9 @@ enum inode_i_mutex_lock_class I_MUTEX_QUOTA }; +extern void inode_double_lock(struct inode *inode1, struct inode *inode2); +extern void inode_double_unlock(struct inode *inode1, struct inode *inode2); + /* * NOTE: in a 32bit arch with a preemptable kernel and * an UP compile the i_size_read/write must be atomic -- cgit v1.2.3 From 6da61809822c22634a3de2dcb3c60283b836a88a Mon Sep 17 00:00:00 2001 From: Mark Fasheh Date: Tue, 17 Oct 2006 18:43:07 +0200 Subject: [PATCH] Introduce generic_file_splice_write_nolock() This allows file systems to manage their own i_mutex locking while still re-using the generic_file_splice_write() logic. OCFS2 in particular wants this so that it can order cluster locks within i_mutex. Signed-off-by: Mark Fasheh Signed-off-by: Jens Axboe --- 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 853a02f23936..d695ba2346a3 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1758,6 +1758,8 @@ extern ssize_t generic_file_splice_read(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int); extern ssize_t generic_file_splice_write(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int); +extern ssize_t generic_file_splice_write_nolock(struct pipe_inode_info *, + struct file *, loff_t *, size_t, unsigned int); extern ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe, struct file *out, loff_t *, size_t len, unsigned int flags); extern long do_splice_direct(struct file *in, loff_t *ppos, struct file *out, -- cgit v1.2.3 From 01de85e057328ecbef36e108673b1e81059d54c1 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 17 Oct 2006 19:50:36 +0200 Subject: [PATCH] Add lockless helpers for remove_suid() Right now users have to grab i_mutex before calling remove_suid(), in the unlikely event that a call to ->setattr() may be needed. Split up the function in two parts: - One to check if we need to remove suid - One to actually remove it The first we can call lockless. Signed-off-by: Jens Axboe --- 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 d695ba2346a3..2fe6e3f900ba 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1712,6 +1712,8 @@ extern void __iget(struct inode * inode); extern void clear_inode(struct inode *); extern void destroy_inode(struct inode *); extern struct inode *new_inode(struct super_block *); +extern int __remove_suid(struct dentry *, int); +extern int should_remove_suid(struct dentry *); extern int remove_suid(struct dentry *); extern void remove_dquot_ref(struct super_block *, int, struct list_head *); -- cgit v1.2.3 From 79e2de4bc53d7ca2a8eedee49e4a92479b4b530e Mon Sep 17 00:00:00 2001 From: Thomas Maier Date: Thu, 19 Oct 2006 23:28:15 -0700 Subject: [PATCH] export clear_queue_congested and set_queue_congested Export the clear_queue_congested() and set_queue_congested() functions located in ll_rw_blk.c The functions are renamed to blk_clear_queue_congested() and blk_set_queue_congested(). (needed in the pktcdvd driver's bio write congestion control) Signed-off-by: Thomas Maier Cc: Peter Osterlund Cc: Jens Axboe Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- 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 d370d2cfe138..9575e3a5ff2a 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -651,6 +651,8 @@ extern void blk_recount_segments(request_queue_t *, struct bio *); extern int scsi_cmd_ioctl(struct file *, struct gendisk *, unsigned int, void __user *); extern int sg_scsi_ioctl(struct file *, struct request_queue *, struct gendisk *, struct scsi_ioctl_command __user *); +extern void blk_clear_queue_congested(request_queue_t *q, int rw); +extern void blk_set_queue_congested(request_queue_t *q, int rw); extern void blk_start_queue(request_queue_t *q); extern void blk_stop_queue(request_queue_t *q); extern void blk_sync_queue(struct request_queue *q); -- cgit v1.2.3 From 3fcfab16c5b86eaa3db3a9a31adba550c5b67141 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Thu, 19 Oct 2006 23:28:16 -0700 Subject: [PATCH] separate bdi congestion functions from queue congestion functions Separate out the concept of "queue congestion" from "backing-dev congestion". Congestion is a backing-dev concept, not a queue concept. The blk_* congestion functions are retained, as wrappers around the core backing-dev congestion functions. This proper layering is needed so that NFS can cleanly use the congestion functions, and so that CONFIG_BLOCK=n actually links. Cc: "Thomas Maier" Cc: "Jens Axboe" Cc: Trond Myklebust Cc: David Howells Cc: Peter Osterlund Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/backing-dev.h | 7 +++++++ include/linux/blkdev.h | 24 ++++++++++++++++++++---- include/linux/writeback.h | 1 - 3 files changed, 27 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index f7a1390d67f5..7011d6255593 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -10,6 +10,8 @@ #include +struct page; + /* * Bits in backing_dev_info.state */ @@ -88,6 +90,11 @@ static inline int bdi_rw_congested(struct backing_dev_info *bdi) (1 << BDI_write_congested)); } +void clear_bdi_congested(struct backing_dev_info *bdi, int rw); +void set_bdi_congested(struct backing_dev_info *bdi, int rw); +long congestion_wait(int rw, long timeout); +void congestion_end(int rw); + #define bdi_cap_writeback_dirty(bdi) \ (!((bdi)->capabilities & BDI_CAP_NO_WRITEBACK)) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 9575e3a5ff2a..7bfcde2d5578 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -651,8 +651,26 @@ extern void blk_recount_segments(request_queue_t *, struct bio *); extern int scsi_cmd_ioctl(struct file *, struct gendisk *, unsigned int, void __user *); extern int sg_scsi_ioctl(struct file *, struct request_queue *, struct gendisk *, struct scsi_ioctl_command __user *); -extern void blk_clear_queue_congested(request_queue_t *q, int rw); -extern void blk_set_queue_congested(request_queue_t *q, int rw); + +/* + * A queue has just exitted congestion. Note this in the global counter of + * congested queues, and wake up anyone who was waiting for requests to be + * put back. + */ +static inline void blk_clear_queue_congested(request_queue_t *q, int rw) +{ + clear_bdi_congested(&q->backing_dev_info, rw); +} + +/* + * A queue has just entered congestion. Flag that in the queue's VM-visible + * state flags and increment the global gounter of congested queues. + */ +static inline void blk_set_queue_congested(request_queue_t *q, int rw) +{ + set_bdi_congested(&q->backing_dev_info, rw); +} + extern void blk_start_queue(request_queue_t *q); extern void blk_stop_queue(request_queue_t *q); extern void blk_sync_queue(struct request_queue *q); @@ -767,10 +785,8 @@ extern int blk_queue_init_tags(request_queue_t *, int, struct blk_queue_tag *); extern void blk_queue_free_tags(request_queue_t *); extern int blk_queue_resize_tags(request_queue_t *, int); extern void blk_queue_invalidate_tags(request_queue_t *); -extern long blk_congestion_wait(int rw, long timeout); extern struct blk_queue_tag *blk_init_tags(int); extern void blk_free_tags(struct blk_queue_tag *); -extern void blk_congestion_end(int rw); static inline struct request *blk_map_queue_find_tag(struct blk_queue_tag *bqt, int tag) diff --git a/include/linux/writeback.h b/include/linux/writeback.h index a341c8032866..fc35e6bdfb93 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -85,7 +85,6 @@ int wakeup_pdflush(long nr_pages); void laptop_io_completion(void); void laptop_sync_completion(void); void throttle_vm_writeout(void); -void writeback_congestion_end(void); /* These are exported to sysctl. */ extern int dirty_background_ratio; -- cgit v1.2.3 From 34e856e6a522a8fc0feba7497f5b05aeaa13d473 Mon Sep 17 00:00:00 2001 From: Ralf Baechle Date: Thu, 19 Oct 2006 23:28:17 -0700 Subject: [PATCH] Make userspace proof contains the constants for personality(2) but also some defintions that are useless or even harmful in userspace such as the personality() macro. Signed-off-by: Ralf Baechle Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/personality.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/personality.h b/include/linux/personality.h index 80d780e5a8f5..bf4cf2080e5c 100644 --- a/include/linux/personality.h +++ b/include/linux/personality.h @@ -1,6 +1,8 @@ #ifndef _LINUX_PERSONALITY_H #define _LINUX_PERSONALITY_H +#ifdef __KERNEL__ + /* * Handling of different ABIs (personalities). */ @@ -12,6 +14,8 @@ extern int register_exec_domain(struct exec_domain *); extern int unregister_exec_domain(struct exec_domain *); extern int __set_personality(unsigned long); +#endif /* __KERNEL__ */ + /* * Flags for bug emulation. * @@ -71,6 +75,7 @@ enum { PER_MASK = 0x00ff, }; +#ifdef __KERNEL__ /* * Description of an execution domain. @@ -111,4 +116,6 @@ struct exec_domain { #define set_personality(pers) \ ((current->personality == pers) ? 0 : __set_personality(pers)) +#endif /* __KERNEL__ */ + #endif /* _LINUX_PERSONALITY_H */ -- cgit v1.2.3 From 145fc655a1ceabda76cf2ad74f7cf96863c65b65 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Thu, 19 Oct 2006 23:28:28 -0700 Subject: [PATCH] genirq: clean up irq-flow-type naming, fix Re-add the set_irq_chip_and_handler() prototype, it's still widely used. Signed-off-by: Ingo Molnar Cc: Olaf Hering Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/irq.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irq.h b/include/linux/irq.h index 775f5a7da493..52fc4052a0ae 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -321,6 +321,9 @@ extern int can_request_irq(unsigned int irq, unsigned long irqflags); extern struct irq_chip no_irq_chip; extern struct irq_chip dummy_irq_chip; +extern void +set_irq_chip_and_handler(unsigned int irq, struct irq_chip *chip, + irq_flow_handler_t handle); extern void set_irq_chip_and_handler_name(unsigned int irq, struct irq_chip *chip, irq_flow_handler_t handle, const char *name); -- cgit v1.2.3 From 8ac773b4f73afa6fd66695131103944b975d5d5c Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Thu, 19 Oct 2006 23:28:32 -0700 Subject: [PATCH] OOM killer meets userspace headers Despite mm.h is not being exported header, it does contain one thing which is part of userspace ABI -- value disabling OOM killer for given process. So, a) create and export include/linux/oom.h b) move OOM_DISABLE define there. c) turn bounding values of /proc/$PID/oom_adj into defines and export them too. Note: mass __KERNEL__ removal will be done later. Signed-off-by: Alexey Dobriyan Cc: Nick Piggin Cc: David Woodhouse Cc: Christoph Hellwig Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/Kbuild | 1 + include/linux/mm.h | 3 --- include/linux/oom.h | 10 ++++++++++ 3 files changed, 11 insertions(+), 3 deletions(-) create mode 100644 include/linux/oom.h (limited to 'include/linux') diff --git a/include/linux/Kbuild b/include/linux/Kbuild index 5114ff18101d..a1155a2beb32 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -120,6 +120,7 @@ header-y += netrom.h header-y += nfs2.h header-y += nfs4_mount.h header-y += nfs_mount.h +header-y += oom.h header-y += param.h header-y += pci_ids.h header-y += pci_regs.h diff --git a/include/linux/mm.h b/include/linux/mm.h index 5a6068ff5556..d538de901965 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1115,9 +1115,6 @@ int in_gate_area_no_task(unsigned long addr); #define in_gate_area(task, addr) ({(void)task; in_gate_area_no_task(addr);}) #endif /* __HAVE_ARCH_GATE_AREA */ -/* /proc//oom_adj set to -17 protects from the oom-killer */ -#define OOM_DISABLE -17 - int drop_caches_sysctl_handler(struct ctl_table *, int, struct file *, void __user *, size_t *, loff_t *); unsigned long shrink_slab(unsigned long scanned, gfp_t gfp_mask, diff --git a/include/linux/oom.h b/include/linux/oom.h new file mode 100644 index 000000000000..ad76463629a0 --- /dev/null +++ b/include/linux/oom.h @@ -0,0 +1,10 @@ +#ifndef __INCLUDE_LINUX_OOM_H +#define __INCLUDE_LINUX_OOM_H + +/* /proc//oom_adj set to -17 protects from the oom-killer */ +#define OOM_DISABLE (-17) +/* inclusive */ +#define OOM_ADJUST_MIN (-16) +#define OOM_ADJUST_MAX 15 + +#endif -- cgit v1.2.3 From cd9ae2b6a75bb1fa0d370929c2d7a7da1ed719d9 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 19 Oct 2006 23:28:40 -0700 Subject: [PATCH] NFS: Deal with failure of invalidate_inode_pages2() If invalidate_inode_pages2() fails, then it should in principle just be because the current process was signalled. In that case, we just want to ensure that the inode's page cache remains marked as invalid. Also add a helper to allow the O_DIRECT code to simply mark the page cache as invalid once it is finished writing, instead of calling invalidate_inode_pages2() itself. Signed-off-by: Trond Myklebust Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nfs_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 76ff54846ada..6b2de1be5815 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -290,6 +290,7 @@ static inline int nfs_verify_change_attribute(struct inode *inode, unsigned long * linux/fs/nfs/inode.c */ extern int nfs_sync_mapping(struct address_space *mapping); +extern void nfs_zap_mapping(struct inode *inode, struct address_space *mapping); extern void nfs_zap_caches(struct inode *); extern struct inode *nfs_fhget(struct super_block *, struct nfs_fh *, struct nfs_fattr *); -- cgit v1.2.3 From 7111c66e4e70588c9602035a4996c9cdc2087d2d Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 19 Oct 2006 23:28:45 -0700 Subject: [PATCH] fix svc_procfunc declaration svc_procfunc instances return __be32, not int Signed-off-by: Al Viro Acked-by: Trond Myklebust Acked-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sunrpc/svc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 9c9a8ad92477..965d6c20086e 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -335,7 +335,7 @@ struct svc_version { /* * RPC procedure info */ -typedef int (*svc_procfunc)(struct svc_rqst *, void *argp, void *resp); +typedef __be32 (*svc_procfunc)(struct svc_rqst *, void *argp, void *resp); struct svc_procedure { svc_procfunc pc_func; /* process the request */ kxdrproc_t pc_decode; /* XDR decode args */ -- cgit v1.2.3 From 52921e02a4f4163a7b1f4b5dde71e1debc71de4a Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 19 Oct 2006 23:28:46 -0700 Subject: [PATCH] lockd endianness annotations Signed-off-by: Alexey Dobriyan Signed-off-by: Al Viro Acked-by: Trond Myklebust Acked-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/lockd/lockd.h | 12 ++++++------ include/linux/lockd/share.h | 4 ++-- include/linux/lockd/xdr.h | 26 +++++++++++++------------- include/linux/lockd/xdr4.h | 26 +++++++++++++------------- 4 files changed, 34 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index 2909619c0295..862d9730a60d 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -154,7 +154,7 @@ int nlm_async_reply(struct nlm_rqst *, u32, const struct rpc_call_ops *); struct nlm_wait * nlmclnt_prepare_block(struct nlm_host *host, struct file_lock *fl); void nlmclnt_finish_block(struct nlm_wait *block); int nlmclnt_block(struct nlm_wait *block, struct nlm_rqst *req, long timeout); -u32 nlmclnt_grant(const struct sockaddr_in *addr, const struct nlm_lock *); +__be32 nlmclnt_grant(const struct sockaddr_in *addr, const struct nlm_lock *); void nlmclnt_recovery(struct nlm_host *); int nlmclnt_reclaim(struct nlm_host *, struct file_lock *); void nlmclnt_next_cookie(struct nlm_cookie *); @@ -184,12 +184,12 @@ typedef int (*nlm_host_match_fn_t)(struct nlm_host *cur, struct nlm_host *ref) /* * Server-side lock handling */ -u32 nlmsvc_lock(struct svc_rqst *, struct nlm_file *, +__be32 nlmsvc_lock(struct svc_rqst *, struct nlm_file *, struct nlm_lock *, int, struct nlm_cookie *); -u32 nlmsvc_unlock(struct nlm_file *, struct nlm_lock *); -u32 nlmsvc_testlock(struct nlm_file *, struct nlm_lock *, +__be32 nlmsvc_unlock(struct nlm_file *, struct nlm_lock *); +__be32 nlmsvc_testlock(struct nlm_file *, struct nlm_lock *, struct nlm_lock *); -u32 nlmsvc_cancel_blocked(struct nlm_file *, struct nlm_lock *); +__be32 nlmsvc_cancel_blocked(struct nlm_file *, struct nlm_lock *); unsigned long nlmsvc_retry_blocked(void); void nlmsvc_traverse_blocks(struct nlm_host *, struct nlm_file *, nlm_host_match_fn_t match); @@ -198,7 +198,7 @@ void nlmsvc_grant_reply(struct nlm_cookie *, u32); /* * File handling for the server personality */ -u32 nlm_lookup_file(struct svc_rqst *, struct nlm_file **, +__be32 nlm_lookup_file(struct svc_rqst *, struct nlm_file **, struct nfs_fh *); void nlm_release_file(struct nlm_file *); void nlmsvc_mark_resources(void); diff --git a/include/linux/lockd/share.h b/include/linux/lockd/share.h index cd7816e74c05..630c5bf69b07 100644 --- a/include/linux/lockd/share.h +++ b/include/linux/lockd/share.h @@ -21,9 +21,9 @@ struct nlm_share { u32 s_mode; /* deny mode */ }; -u32 nlmsvc_share_file(struct nlm_host *, struct nlm_file *, +__be32 nlmsvc_share_file(struct nlm_host *, struct nlm_file *, struct nlm_args *); -u32 nlmsvc_unshare_file(struct nlm_host *, struct nlm_file *, +__be32 nlmsvc_unshare_file(struct nlm_host *, struct nlm_file *, struct nlm_args *); void nlmsvc_traverse_shares(struct nlm_host *, struct nlm_file *, nlm_host_match_fn_t); diff --git a/include/linux/lockd/xdr.h b/include/linux/lockd/xdr.h index 66fdae3b490c..29e7d9fc9dad 100644 --- a/include/linux/lockd/xdr.h +++ b/include/linux/lockd/xdr.h @@ -90,19 +90,19 @@ struct nlm_reboot { */ #define NLMSVC_XDRSIZE sizeof(struct nlm_args) -int nlmsvc_decode_testargs(struct svc_rqst *, u32 *, struct nlm_args *); -int nlmsvc_encode_testres(struct svc_rqst *, u32 *, struct nlm_res *); -int nlmsvc_decode_lockargs(struct svc_rqst *, u32 *, struct nlm_args *); -int nlmsvc_decode_cancargs(struct svc_rqst *, u32 *, struct nlm_args *); -int nlmsvc_decode_unlockargs(struct svc_rqst *, u32 *, struct nlm_args *); -int nlmsvc_encode_res(struct svc_rqst *, u32 *, struct nlm_res *); -int nlmsvc_decode_res(struct svc_rqst *, u32 *, struct nlm_res *); -int nlmsvc_encode_void(struct svc_rqst *, u32 *, void *); -int nlmsvc_decode_void(struct svc_rqst *, u32 *, void *); -int nlmsvc_decode_shareargs(struct svc_rqst *, u32 *, struct nlm_args *); -int nlmsvc_encode_shareres(struct svc_rqst *, u32 *, struct nlm_res *); -int nlmsvc_decode_notify(struct svc_rqst *, u32 *, struct nlm_args *); -int nlmsvc_decode_reboot(struct svc_rqst *, u32 *, struct nlm_reboot *); +int nlmsvc_decode_testargs(struct svc_rqst *, __be32 *, struct nlm_args *); +int nlmsvc_encode_testres(struct svc_rqst *, __be32 *, struct nlm_res *); +int nlmsvc_decode_lockargs(struct svc_rqst *, __be32 *, struct nlm_args *); +int nlmsvc_decode_cancargs(struct svc_rqst *, __be32 *, struct nlm_args *); +int nlmsvc_decode_unlockargs(struct svc_rqst *, __be32 *, struct nlm_args *); +int nlmsvc_encode_res(struct svc_rqst *, __be32 *, struct nlm_res *); +int nlmsvc_decode_res(struct svc_rqst *, __be32 *, struct nlm_res *); +int nlmsvc_encode_void(struct svc_rqst *, __be32 *, void *); +int nlmsvc_decode_void(struct svc_rqst *, __be32 *, void *); +int nlmsvc_decode_shareargs(struct svc_rqst *, __be32 *, struct nlm_args *); +int nlmsvc_encode_shareres(struct svc_rqst *, __be32 *, struct nlm_res *); +int nlmsvc_decode_notify(struct svc_rqst *, __be32 *, struct nlm_args *); +int nlmsvc_decode_reboot(struct svc_rqst *, __be32 *, struct nlm_reboot *); /* int nlmclt_encode_testargs(struct rpc_rqst *, u32 *, struct nlm_args *); int nlmclt_encode_lockargs(struct rpc_rqst *, u32 *, struct nlm_args *); diff --git a/include/linux/lockd/xdr4.h b/include/linux/lockd/xdr4.h index 3cc1ae25009b..dd12b4c9e613 100644 --- a/include/linux/lockd/xdr4.h +++ b/include/linux/lockd/xdr4.h @@ -23,19 +23,19 @@ -int nlm4svc_decode_testargs(struct svc_rqst *, u32 *, struct nlm_args *); -int nlm4svc_encode_testres(struct svc_rqst *, u32 *, struct nlm_res *); -int nlm4svc_decode_lockargs(struct svc_rqst *, u32 *, struct nlm_args *); -int nlm4svc_decode_cancargs(struct svc_rqst *, u32 *, struct nlm_args *); -int nlm4svc_decode_unlockargs(struct svc_rqst *, u32 *, struct nlm_args *); -int nlm4svc_encode_res(struct svc_rqst *, u32 *, struct nlm_res *); -int nlm4svc_decode_res(struct svc_rqst *, u32 *, struct nlm_res *); -int nlm4svc_encode_void(struct svc_rqst *, u32 *, void *); -int nlm4svc_decode_void(struct svc_rqst *, u32 *, void *); -int nlm4svc_decode_shareargs(struct svc_rqst *, u32 *, struct nlm_args *); -int nlm4svc_encode_shareres(struct svc_rqst *, u32 *, struct nlm_res *); -int nlm4svc_decode_notify(struct svc_rqst *, u32 *, struct nlm_args *); -int nlm4svc_decode_reboot(struct svc_rqst *, u32 *, struct nlm_reboot *); +int nlm4svc_decode_testargs(struct svc_rqst *, __be32 *, struct nlm_args *); +int nlm4svc_encode_testres(struct svc_rqst *, __be32 *, struct nlm_res *); +int nlm4svc_decode_lockargs(struct svc_rqst *, __be32 *, struct nlm_args *); +int nlm4svc_decode_cancargs(struct svc_rqst *, __be32 *, struct nlm_args *); +int nlm4svc_decode_unlockargs(struct svc_rqst *, __be32 *, struct nlm_args *); +int nlm4svc_encode_res(struct svc_rqst *, __be32 *, struct nlm_res *); +int nlm4svc_decode_res(struct svc_rqst *, __be32 *, struct nlm_res *); +int nlm4svc_encode_void(struct svc_rqst *, __be32 *, void *); +int nlm4svc_decode_void(struct svc_rqst *, __be32 *, void *); +int nlm4svc_decode_shareargs(struct svc_rqst *, __be32 *, struct nlm_args *); +int nlm4svc_encode_shareres(struct svc_rqst *, __be32 *, struct nlm_res *); +int nlm4svc_decode_notify(struct svc_rqst *, __be32 *, struct nlm_args *); +int nlm4svc_decode_reboot(struct svc_rqst *, __be32 *, struct nlm_reboot *); /* int nlmclt_encode_testargs(struct rpc_rqst *, u32 *, struct nlm_args *); int nlmclt_encode_lockargs(struct rpc_rqst *, u32 *, struct nlm_args *); -- cgit v1.2.3 From 0dbb4c6799cf8fa8c5ba1926153a30960117477d Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 19 Oct 2006 23:28:49 -0700 Subject: [PATCH] xdr annotations: NFS readdir entries on-the-wire data is big-endian [in large part pulled from Alexey's patch] Signed-off-by: Al Viro Acked-by: Trond Myklebust Acked-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nfs_xdr.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index dc5397d9d23c..ac8058bc8f94 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -811,7 +811,7 @@ struct nfs_rpc_ops { int (*pathconf) (struct nfs_server *, struct nfs_fh *, struct nfs_pathconf *); int (*set_capabilities)(struct nfs_server *, struct nfs_fh *); - u32 * (*decode_dirent)(u32 *, struct nfs_entry *, int plus); + __be32 *(*decode_dirent)(__be32 *, struct nfs_entry *, int plus); void (*read_setup) (struct nfs_read_data *); int (*read_done) (struct rpc_task *, struct nfs_read_data *); void (*write_setup) (struct nfs_write_data *, int how); -- cgit v1.2.3 From bc4785cd475a11ba125df7af674e16c6ea1cfc30 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 19 Oct 2006 23:28:51 -0700 Subject: [PATCH] nfs: verifier is network-endian Signed-off-by: Al Viro Acked-by: Trond Myklebust Acked-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nfs_fs.h | 2 +- include/linux/nfs_xdr.h | 8 ++++---- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 6b2de1be5815..45228c1a1195 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -157,7 +157,7 @@ struct nfs_inode { * This is the cookie verifier used for NFSv3 readdir * operations */ - __u32 cookieverf[2]; + __be32 cookieverf[2]; /* * This is the list of dirty unwritten pages. diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index ac8058bc8f94..768c1ad5ff6f 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -266,7 +266,7 @@ struct nfs_writeargs { struct nfs_writeverf { enum nfs3_stable_how committed; - __u32 verifier[2]; + __be32 verifier[2]; }; struct nfs_writeres { @@ -420,7 +420,7 @@ struct nfs3_createargs { unsigned int len; struct iattr * sattr; enum nfs3_createmode createmode; - __u32 verifier[2]; + __be32 verifier[2]; }; struct nfs3_mkdirargs { @@ -467,7 +467,7 @@ struct nfs3_linkargs { struct nfs3_readdirargs { struct nfs_fh * fh; __u64 cookie; - __u32 verf[2]; + __be32 verf[2]; int plus; unsigned int count; struct page ** pages; @@ -503,7 +503,7 @@ struct nfs3_linkres { struct nfs3_readdirres { struct nfs_fattr * dir_attr; - __u32 * verf; + __be32 * verf; int plus; }; -- cgit v1.2.3 From 63f103111fdfc3cba00e4c94921d32362f375d93 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 19 Oct 2006 23:28:54 -0700 Subject: [PATCH] nfsd: nfserrno() endianness annotations Signed-off-by: Al Viro Acked-by: Trond Myklebust Acked-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nfsd/export.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfsd/export.h b/include/linux/nfsd/export.h index 6e78ea969f49..27666f5b8b53 100644 --- a/include/linux/nfsd/export.h +++ b/include/linux/nfsd/export.h @@ -118,7 +118,7 @@ struct svc_export * exp_parent(struct auth_domain *clp, int exp_rootfh(struct auth_domain *, char *path, struct knfsd_fh *, int maxsize); int exp_pseudoroot(struct auth_domain *, struct svc_fh *fhp, struct cache_req *creq); -int nfserrno(int errno); +__be32 nfserrno(int errno); extern struct cache_detail svc_export_cache; -- cgit v1.2.3 From 83b11340d683a67a77e35a5ffb5ad4afbf0be4e5 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 19 Oct 2006 23:28:55 -0700 Subject: [PATCH] nfsfh simple endianness annotations Signed-off-by: Al Viro Acked-by: Trond Myklebust Acked-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nfsd/nfsfh.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfsd/nfsfh.h b/include/linux/nfsd/nfsfh.h index 069257ea99a0..749bad1ca16f 100644 --- a/include/linux/nfsd/nfsfh.h +++ b/include/linux/nfsd/nfsfh.h @@ -209,9 +209,9 @@ extern char * SVCFH_fmt(struct svc_fh *fhp); /* * Function prototypes */ -u32 fh_verify(struct svc_rqst *, struct svc_fh *, int, int); -int fh_compose(struct svc_fh *, struct svc_export *, struct dentry *, struct svc_fh *); -int fh_update(struct svc_fh *); +__be32 fh_verify(struct svc_rqst *, struct svc_fh *, int, int); +__be32 fh_compose(struct svc_fh *, struct svc_export *, struct dentry *, struct svc_fh *); +__be32 fh_update(struct svc_fh *); void fh_put(struct svc_fh *); static __inline__ struct svc_fh * -- cgit v1.2.3 From 131a21c2177c267ab259fcd06947c6f593a7de8e Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 19 Oct 2006 23:28:56 -0700 Subject: [PATCH] xdr annotations: NFSv2 server Signed-off-by: Al Viro Acked-by: Trond Myklebust Acked-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nfsd/nfsd.h | 2 +- include/linux/nfsd/xdr.h | 50 +++++++++++++++++++++++------------------------ 2 files changed, 26 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfsd/nfsd.h b/include/linux/nfsd/nfsd.h index d0d4aae7085f..2f75160a5824 100644 --- a/include/linux/nfsd/nfsd.h +++ b/include/linux/nfsd/nfsd.h @@ -50,7 +50,7 @@ * Callback function for readdir */ struct readdir_cd { - int err; /* 0, nfserr, or nfserr_eof */ + __be32 err; /* 0, nfserr, or nfserr_eof */ }; typedef int (*encode_dent_fn)(struct readdir_cd *, const char *, int, loff_t, ino_t, unsigned int); diff --git a/include/linux/nfsd/xdr.h b/include/linux/nfsd/xdr.h index 0e53de87d886..877192d3ae79 100644 --- a/include/linux/nfsd/xdr.h +++ b/include/linux/nfsd/xdr.h @@ -81,7 +81,7 @@ struct nfsd_readdirargs { struct svc_fh fh; __u32 cookie; __u32 count; - u32 * buffer; + __be32 * buffer; }; struct nfsd_attrstat { @@ -108,9 +108,9 @@ struct nfsd_readdirres { int count; struct readdir_cd common; - u32 * buffer; + __be32 * buffer; int buflen; - u32 * offset; + __be32 * offset; }; struct nfsd_statfsres { @@ -135,43 +135,43 @@ union nfsd_xdrstore { #define NFS2_SVC_XDRSIZE sizeof(union nfsd_xdrstore) -int nfssvc_decode_void(struct svc_rqst *, u32 *, void *); -int nfssvc_decode_fhandle(struct svc_rqst *, u32 *, struct nfsd_fhandle *); -int nfssvc_decode_sattrargs(struct svc_rqst *, u32 *, +int nfssvc_decode_void(struct svc_rqst *, __be32 *, void *); +int nfssvc_decode_fhandle(struct svc_rqst *, __be32 *, struct nfsd_fhandle *); +int nfssvc_decode_sattrargs(struct svc_rqst *, __be32 *, struct nfsd_sattrargs *); -int nfssvc_decode_diropargs(struct svc_rqst *, u32 *, +int nfssvc_decode_diropargs(struct svc_rqst *, __be32 *, struct nfsd_diropargs *); -int nfssvc_decode_readargs(struct svc_rqst *, u32 *, +int nfssvc_decode_readargs(struct svc_rqst *, __be32 *, struct nfsd_readargs *); -int nfssvc_decode_writeargs(struct svc_rqst *, u32 *, +int nfssvc_decode_writeargs(struct svc_rqst *, __be32 *, struct nfsd_writeargs *); -int nfssvc_decode_createargs(struct svc_rqst *, u32 *, +int nfssvc_decode_createargs(struct svc_rqst *, __be32 *, struct nfsd_createargs *); -int nfssvc_decode_renameargs(struct svc_rqst *, u32 *, +int nfssvc_decode_renameargs(struct svc_rqst *, __be32 *, struct nfsd_renameargs *); -int nfssvc_decode_readlinkargs(struct svc_rqst *, u32 *, +int nfssvc_decode_readlinkargs(struct svc_rqst *, __be32 *, struct nfsd_readlinkargs *); -int nfssvc_decode_linkargs(struct svc_rqst *, u32 *, +int nfssvc_decode_linkargs(struct svc_rqst *, __be32 *, struct nfsd_linkargs *); -int nfssvc_decode_symlinkargs(struct svc_rqst *, u32 *, +int nfssvc_decode_symlinkargs(struct svc_rqst *, __be32 *, struct nfsd_symlinkargs *); -int nfssvc_decode_readdirargs(struct svc_rqst *, u32 *, +int nfssvc_decode_readdirargs(struct svc_rqst *, __be32 *, struct nfsd_readdirargs *); -int nfssvc_encode_void(struct svc_rqst *, u32 *, void *); -int nfssvc_encode_attrstat(struct svc_rqst *, u32 *, struct nfsd_attrstat *); -int nfssvc_encode_diropres(struct svc_rqst *, u32 *, struct nfsd_diropres *); -int nfssvc_encode_readlinkres(struct svc_rqst *, u32 *, struct nfsd_readlinkres *); -int nfssvc_encode_readres(struct svc_rqst *, u32 *, struct nfsd_readres *); -int nfssvc_encode_statfsres(struct svc_rqst *, u32 *, struct nfsd_statfsres *); -int nfssvc_encode_readdirres(struct svc_rqst *, u32 *, struct nfsd_readdirres *); +int nfssvc_encode_void(struct svc_rqst *, __be32 *, void *); +int nfssvc_encode_attrstat(struct svc_rqst *, __be32 *, struct nfsd_attrstat *); +int nfssvc_encode_diropres(struct svc_rqst *, __be32 *, struct nfsd_diropres *); +int nfssvc_encode_readlinkres(struct svc_rqst *, __be32 *, struct nfsd_readlinkres *); +int nfssvc_encode_readres(struct svc_rqst *, __be32 *, struct nfsd_readres *); +int nfssvc_encode_statfsres(struct svc_rqst *, __be32 *, struct nfsd_statfsres *); +int nfssvc_encode_readdirres(struct svc_rqst *, __be32 *, struct nfsd_readdirres *); int nfssvc_encode_entry(struct readdir_cd *, const char *name, int namlen, loff_t offset, ino_t ino, unsigned int); -int nfssvc_release_fhandle(struct svc_rqst *, u32 *, struct nfsd_fhandle *); +int nfssvc_release_fhandle(struct svc_rqst *, __be32 *, struct nfsd_fhandle *); /* Helper functions for NFSv2 ACL code */ -u32 *nfs2svc_encode_fattr(struct svc_rqst *rqstp, u32 *p, struct svc_fh *fhp); -u32 *nfs2svc_decode_fh(u32 *p, struct svc_fh *fhp); +__be32 *nfs2svc_encode_fattr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp); +__be32 *nfs2svc_decode_fh(__be32 *p, struct svc_fh *fhp); #endif /* LINUX_NFSD_H */ -- cgit v1.2.3 From 91f07168cef8e99dd16f608fbc703e7a5af0237f Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 19 Oct 2006 23:28:57 -0700 Subject: [PATCH] xdr annotations: NFSv3 server Signed-off-by: Al Viro Acked-by: Trond Myklebust Acked-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nfsd/xdr3.h | 114 +++++++++++++++++++++++----------------------- 1 file changed, 57 insertions(+), 57 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfsd/xdr3.h b/include/linux/nfsd/xdr3.h index 474d882dc2f3..79963867b0d7 100644 --- a/include/linux/nfsd/xdr3.h +++ b/include/linux/nfsd/xdr3.h @@ -51,7 +51,7 @@ struct nfsd3_createargs { int len; int createmode; struct iattr attrs; - __u32 * verf; + __be32 * verf; }; struct nfsd3_mknodargs { @@ -98,8 +98,8 @@ struct nfsd3_readdirargs { __u64 cookie; __u32 dircount; __u32 count; - __u32 * verf; - u32 * buffer; + __be32 * verf; + __be32 * buffer; }; struct nfsd3_commitargs { @@ -122,79 +122,79 @@ struct nfsd3_setaclargs { }; struct nfsd3_attrstat { - __u32 status; + __be32 status; struct svc_fh fh; struct kstat stat; }; /* LOOKUP, CREATE, MKDIR, SYMLINK, MKNOD */ struct nfsd3_diropres { - __u32 status; + __be32 status; struct svc_fh dirfh; struct svc_fh fh; }; struct nfsd3_accessres { - __u32 status; + __be32 status; struct svc_fh fh; __u32 access; }; struct nfsd3_readlinkres { - __u32 status; + __be32 status; struct svc_fh fh; __u32 len; }; struct nfsd3_readres { - __u32 status; + __be32 status; struct svc_fh fh; unsigned long count; int eof; }; struct nfsd3_writeres { - __u32 status; + __be32 status; struct svc_fh fh; unsigned long count; int committed; }; struct nfsd3_renameres { - __u32 status; + __be32 status; struct svc_fh ffh; struct svc_fh tfh; }; struct nfsd3_linkres { - __u32 status; + __be32 status; struct svc_fh tfh; struct svc_fh fh; }; struct nfsd3_readdirres { - __u32 status; + __be32 status; struct svc_fh fh; int count; - __u32 verf[2]; + __be32 verf[2]; struct readdir_cd common; - u32 * buffer; + __be32 * buffer; int buflen; - u32 * offset; - u32 * offset1; + __be32 * offset; + __be32 * offset1; struct svc_rqst * rqstp; }; struct nfsd3_fsstatres { - __u32 status; + __be32 status; struct kstatfs stats; __u32 invarsec; }; struct nfsd3_fsinfores { - __u32 status; + __be32 status; __u32 f_rtmax; __u32 f_rtpref; __u32 f_rtmult; @@ -207,7 +207,7 @@ struct nfsd3_fsinfores { }; struct nfsd3_pathconfres { - __u32 status; + __be32 status; __u32 p_link_max; __u32 p_name_max; __u32 p_no_trunc; @@ -217,12 +217,12 @@ struct nfsd3_pathconfres { }; struct nfsd3_commitres { - __u32 status; + __be32 status; struct svc_fh fh; }; struct nfsd3_getaclres { - __u32 status; + __be32 status; struct svc_fh fh; int mask; struct posix_acl *acl_access; @@ -266,70 +266,70 @@ union nfsd3_xdrstore { #define NFS3_SVC_XDRSIZE sizeof(union nfsd3_xdrstore) -int nfs3svc_decode_fhandle(struct svc_rqst *, u32 *, struct nfsd_fhandle *); -int nfs3svc_decode_sattrargs(struct svc_rqst *, u32 *, +int nfs3svc_decode_fhandle(struct svc_rqst *, __be32 *, struct nfsd_fhandle *); +int nfs3svc_decode_sattrargs(struct svc_rqst *, __be32 *, struct nfsd3_sattrargs *); -int nfs3svc_decode_diropargs(struct svc_rqst *, u32 *, +int nfs3svc_decode_diropargs(struct svc_rqst *, __be32 *, struct nfsd3_diropargs *); -int nfs3svc_decode_accessargs(struct svc_rqst *, u32 *, +int nfs3svc_decode_accessargs(struct svc_rqst *, __be32 *, struct nfsd3_accessargs *); -int nfs3svc_decode_readargs(struct svc_rqst *, u32 *, +int nfs3svc_decode_readargs(struct svc_rqst *, __be32 *, struct nfsd3_readargs *); -int nfs3svc_decode_writeargs(struct svc_rqst *, u32 *, +int nfs3svc_decode_writeargs(struct svc_rqst *, __be32 *, struct nfsd3_writeargs *); -int nfs3svc_decode_createargs(struct svc_rqst *, u32 *, +int nfs3svc_decode_createargs(struct svc_rqst *, __be32 *, struct nfsd3_createargs *); -int nfs3svc_decode_mkdirargs(struct svc_rqst *, u32 *, +int nfs3svc_decode_mkdirargs(struct svc_rqst *, __be32 *, struct nfsd3_createargs *); -int nfs3svc_decode_mknodargs(struct svc_rqst *, u32 *, +int nfs3svc_decode_mknodargs(struct svc_rqst *, __be32 *, struct nfsd3_mknodargs *); -int nfs3svc_decode_renameargs(struct svc_rqst *, u32 *, +int nfs3svc_decode_renameargs(struct svc_rqst *, __be32 *, struct nfsd3_renameargs *); -int nfs3svc_decode_readlinkargs(struct svc_rqst *, u32 *, +int nfs3svc_decode_readlinkargs(struct svc_rqst *, __be32 *, struct nfsd3_readlinkargs *); -int nfs3svc_decode_linkargs(struct svc_rqst *, u32 *, +int nfs3svc_decode_linkargs(struct svc_rqst *, __be32 *, struct nfsd3_linkargs *); -int nfs3svc_decode_symlinkargs(struct svc_rqst *, u32 *, +int nfs3svc_decode_symlinkargs(struct svc_rqst *, __be32 *, struct nfsd3_symlinkargs *); -int nfs3svc_decode_readdirargs(struct svc_rqst *, u32 *, +int nfs3svc_decode_readdirargs(struct svc_rqst *, __be32 *, struct nfsd3_readdirargs *); -int nfs3svc_decode_readdirplusargs(struct svc_rqst *, u32 *, +int nfs3svc_decode_readdirplusargs(struct svc_rqst *, __be32 *, struct nfsd3_readdirargs *); -int nfs3svc_decode_commitargs(struct svc_rqst *, u32 *, +int nfs3svc_decode_commitargs(struct svc_rqst *, __be32 *, struct nfsd3_commitargs *); -int nfs3svc_encode_voidres(struct svc_rqst *, u32 *, void *); -int nfs3svc_encode_attrstat(struct svc_rqst *, u32 *, +int nfs3svc_encode_voidres(struct svc_rqst *, __be32 *, void *); +int nfs3svc_encode_attrstat(struct svc_rqst *, __be32 *, struct nfsd3_attrstat *); -int nfs3svc_encode_wccstat(struct svc_rqst *, u32 *, +int nfs3svc_encode_wccstat(struct svc_rqst *, __be32 *, struct nfsd3_attrstat *); -int nfs3svc_encode_diropres(struct svc_rqst *, u32 *, +int nfs3svc_encode_diropres(struct svc_rqst *, __be32 *, struct nfsd3_diropres *); -int nfs3svc_encode_accessres(struct svc_rqst *, u32 *, +int nfs3svc_encode_accessres(struct svc_rqst *, __be32 *, struct nfsd3_accessres *); -int nfs3svc_encode_readlinkres(struct svc_rqst *, u32 *, +int nfs3svc_encode_readlinkres(struct svc_rqst *, __be32 *, struct nfsd3_readlinkres *); -int nfs3svc_encode_readres(struct svc_rqst *, u32 *, struct nfsd3_readres *); -int nfs3svc_encode_writeres(struct svc_rqst *, u32 *, struct nfsd3_writeres *); -int nfs3svc_encode_createres(struct svc_rqst *, u32 *, +int nfs3svc_encode_readres(struct svc_rqst *, __be32 *, struct nfsd3_readres *); +int nfs3svc_encode_writeres(struct svc_rqst *, __be32 *, struct nfsd3_writeres *); +int nfs3svc_encode_createres(struct svc_rqst *, __be32 *, struct nfsd3_diropres *); -int nfs3svc_encode_renameres(struct svc_rqst *, u32 *, +int nfs3svc_encode_renameres(struct svc_rqst *, __be32 *, struct nfsd3_renameres *); -int nfs3svc_encode_linkres(struct svc_rqst *, u32 *, +int nfs3svc_encode_linkres(struct svc_rqst *, __be32 *, struct nfsd3_linkres *); -int nfs3svc_encode_readdirres(struct svc_rqst *, u32 *, +int nfs3svc_encode_readdirres(struct svc_rqst *, __be32 *, struct nfsd3_readdirres *); -int nfs3svc_encode_fsstatres(struct svc_rqst *, u32 *, +int nfs3svc_encode_fsstatres(struct svc_rqst *, __be32 *, struct nfsd3_fsstatres *); -int nfs3svc_encode_fsinfores(struct svc_rqst *, u32 *, +int nfs3svc_encode_fsinfores(struct svc_rqst *, __be32 *, struct nfsd3_fsinfores *); -int nfs3svc_encode_pathconfres(struct svc_rqst *, u32 *, +int nfs3svc_encode_pathconfres(struct svc_rqst *, __be32 *, struct nfsd3_pathconfres *); -int nfs3svc_encode_commitres(struct svc_rqst *, u32 *, +int nfs3svc_encode_commitres(struct svc_rqst *, __be32 *, struct nfsd3_commitres *); -int nfs3svc_release_fhandle(struct svc_rqst *, u32 *, +int nfs3svc_release_fhandle(struct svc_rqst *, __be32 *, struct nfsd3_attrstat *); -int nfs3svc_release_fhandle2(struct svc_rqst *, u32 *, +int nfs3svc_release_fhandle2(struct svc_rqst *, __be32 *, struct nfsd3_fhandle_pair *); int nfs3svc_encode_entry(struct readdir_cd *, const char *name, int namlen, loff_t offset, ino_t ino, @@ -338,9 +338,9 @@ int nfs3svc_encode_entry_plus(struct readdir_cd *, const char *name, int namlen, loff_t offset, ino_t ino, unsigned int); /* Helper functions for NFSv3 ACL code */ -u32 *nfs3svc_encode_post_op_attr(struct svc_rqst *rqstp, u32 *p, +__be32 *nfs3svc_encode_post_op_attr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp); -u32 *nfs3svc_decode_fh(u32 *p, struct svc_fh *fhp); +__be32 *nfs3svc_decode_fh(__be32 *p, struct svc_fh *fhp); #endif /* _LINUX_NFSD_XDR3_H */ -- cgit v1.2.3 From 2ebbc012a9433a252be7ab4ce54e94bf7b21e506 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 19 Oct 2006 23:28:58 -0700 Subject: [PATCH] xdr annotations: NFSv4 server Signed-off-by: Al Viro Acked-by: Trond Myklebust Acked-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nfsd/xdr4.h | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfsd/xdr4.h b/include/linux/nfsd/xdr4.h index 66e642762a07..003193fe6fc6 100644 --- a/include/linux/nfsd/xdr4.h +++ b/include/linux/nfsd/xdr4.h @@ -258,9 +258,9 @@ struct nfsd4_readdir { struct svc_fh * rd_fhp; /* response */ struct readdir_cd common; - u32 * buffer; + __be32 * buffer; int buflen; - u32 * offset; + __be32 * offset; }; struct nfsd4_release_lockowner { @@ -371,12 +371,12 @@ struct nfsd4_op { struct nfsd4_compoundargs { /* scratch variables for XDR decode */ - u32 * p; - u32 * end; + __be32 * p; + __be32 * end; struct page ** pagelist; int pagelen; - u32 tmp[8]; - u32 * tmpp; + __be32 tmp[8]; + __be32 * tmpp; struct tmpbuf { struct tmpbuf *next; void (*release)(const void *); @@ -395,15 +395,15 @@ struct nfsd4_compoundargs { struct nfsd4_compoundres { /* scratch variables for XDR encode */ - u32 * p; - u32 * end; + __be32 * p; + __be32 * end; struct xdr_buf * xbuf; struct svc_rqst * rqstp; u32 taglen; char * tag; u32 opcnt; - u32 * tagp; /* where to encode tag and opcount */ + __be32 * tagp; /* where to encode tag and opcount */ }; #define NFS4_SVC_XDRSIZE sizeof(struct nfsd4_compoundargs) @@ -419,10 +419,10 @@ set_change_info(struct nfsd4_change_info *cinfo, struct svc_fh *fhp) cinfo->after_ctime_nsec = fhp->fh_post_ctime.tv_nsec; } -int nfs4svc_encode_voidres(struct svc_rqst *, u32 *, void *); -int nfs4svc_decode_compoundargs(struct svc_rqst *, u32 *, +int nfs4svc_encode_voidres(struct svc_rqst *, __be32 *, void *); +int nfs4svc_decode_compoundargs(struct svc_rqst *, __be32 *, struct nfsd4_compoundargs *); -int nfs4svc_encode_compoundres(struct svc_rqst *, u32 *, +int nfs4svc_encode_compoundres(struct svc_rqst *, __be32 *, struct nfsd4_compoundres *); void nfsd4_encode_operation(struct nfsd4_compoundres *, struct nfsd4_op *); void nfsd4_encode_replay(struct nfsd4_compoundres *resp, struct nfsd4_op *op); -- cgit v1.2.3 From 6264d69d7df654ca64f625e9409189a0e50734e9 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 19 Oct 2006 23:28:58 -0700 Subject: [PATCH] nfsd: vfs.c endianness annotations don't use the same variable to store NFS and host error values Signed-off-by: Al Viro Acked-by: Trond Myklebust Acked-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nfsd/nfsd.h | 38 +++++++++++++++++++------------------- 1 file changed, 19 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfsd/nfsd.h b/include/linux/nfsd/nfsd.h index 2f75160a5824..19a3c83d496e 100644 --- a/include/linux/nfsd/nfsd.h +++ b/include/linux/nfsd/nfsd.h @@ -72,57 +72,57 @@ int nfsd_racache_init(int); void nfsd_racache_shutdown(void); int nfsd_cross_mnt(struct svc_rqst *rqstp, struct dentry **dpp, struct svc_export **expp); -int nfsd_lookup(struct svc_rqst *, struct svc_fh *, +__be32 nfsd_lookup(struct svc_rqst *, struct svc_fh *, const char *, int, struct svc_fh *); -int nfsd_setattr(struct svc_rqst *, struct svc_fh *, +__be32 nfsd_setattr(struct svc_rqst *, struct svc_fh *, struct iattr *, int, time_t); #ifdef CONFIG_NFSD_V4 -int nfsd4_set_nfs4_acl(struct svc_rqst *, struct svc_fh *, +__be32 nfsd4_set_nfs4_acl(struct svc_rqst *, struct svc_fh *, struct nfs4_acl *); int nfsd4_get_nfs4_acl(struct svc_rqst *, struct dentry *, struct nfs4_acl **); #endif /* CONFIG_NFSD_V4 */ -int nfsd_create(struct svc_rqst *, struct svc_fh *, +__be32 nfsd_create(struct svc_rqst *, struct svc_fh *, char *name, int len, struct iattr *attrs, int type, dev_t rdev, struct svc_fh *res); #ifdef CONFIG_NFSD_V3 -int nfsd_access(struct svc_rqst *, struct svc_fh *, u32 *, u32 *); -int nfsd_create_v3(struct svc_rqst *, struct svc_fh *, +__be32 nfsd_access(struct svc_rqst *, struct svc_fh *, u32 *, u32 *); +__be32 nfsd_create_v3(struct svc_rqst *, struct svc_fh *, char *name, int len, struct iattr *attrs, struct svc_fh *res, int createmode, u32 *verifier, int *truncp); -int nfsd_commit(struct svc_rqst *, struct svc_fh *, +__be32 nfsd_commit(struct svc_rqst *, struct svc_fh *, loff_t, unsigned long); #endif /* CONFIG_NFSD_V3 */ -int nfsd_open(struct svc_rqst *, struct svc_fh *, int, +__be32 nfsd_open(struct svc_rqst *, struct svc_fh *, int, int, struct file **); void nfsd_close(struct file *); -int nfsd_read(struct svc_rqst *, struct svc_fh *, struct file *, +__be32 nfsd_read(struct svc_rqst *, struct svc_fh *, struct file *, loff_t, struct kvec *, int, unsigned long *); -int nfsd_write(struct svc_rqst *, struct svc_fh *,struct file *, +__be32 nfsd_write(struct svc_rqst *, struct svc_fh *,struct file *, loff_t, struct kvec *,int, unsigned long, int *); -int nfsd_readlink(struct svc_rqst *, struct svc_fh *, +__be32 nfsd_readlink(struct svc_rqst *, struct svc_fh *, char *, int *); -int nfsd_symlink(struct svc_rqst *, struct svc_fh *, +__be32 nfsd_symlink(struct svc_rqst *, struct svc_fh *, char *name, int len, char *path, int plen, struct svc_fh *res, struct iattr *); -int nfsd_link(struct svc_rqst *, struct svc_fh *, +__be32 nfsd_link(struct svc_rqst *, struct svc_fh *, char *, int, struct svc_fh *); -int nfsd_rename(struct svc_rqst *, +__be32 nfsd_rename(struct svc_rqst *, struct svc_fh *, char *, int, struct svc_fh *, char *, int); -int nfsd_remove(struct svc_rqst *, +__be32 nfsd_remove(struct svc_rqst *, struct svc_fh *, char *, int); -int nfsd_unlink(struct svc_rqst *, struct svc_fh *, int type, +__be32 nfsd_unlink(struct svc_rqst *, struct svc_fh *, int type, char *name, int len); int nfsd_truncate(struct svc_rqst *, struct svc_fh *, unsigned long size); -int nfsd_readdir(struct svc_rqst *, struct svc_fh *, +__be32 nfsd_readdir(struct svc_rqst *, struct svc_fh *, loff_t *, struct readdir_cd *, encode_dent_fn); -int nfsd_statfs(struct svc_rqst *, struct svc_fh *, +__be32 nfsd_statfs(struct svc_rqst *, struct svc_fh *, struct kstatfs *); int nfsd_notify_change(struct inode *, struct iattr *); -int nfsd_permission(struct svc_export *, struct dentry *, int); +__be32 nfsd_permission(struct svc_export *, struct dentry *, int); int nfsd_sync_dir(struct dentry *dp); #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) -- cgit v1.2.3 From b37ad28bcaa7c486a4ff0fb6c3bdaaacd67b86ce Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 19 Oct 2006 23:28:59 -0700 Subject: [PATCH] nfsd: nfs4 code returns error values in net-endian Signed-off-by: Al Viro Acked-by: Trond Myklebust Acked-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nfsd/state.h | 10 +++++----- include/linux/nfsd/xdr4.h | 30 +++++++++++++++--------------- 2 files changed, 20 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfsd/state.h b/include/linux/nfsd/state.h index 8bf23cf8b603..a597e2e72469 100644 --- a/include/linux/nfsd/state.h +++ b/include/linux/nfsd/state.h @@ -164,7 +164,7 @@ update_stateid(stateid_t *stateid) * is cached. */ struct nfs4_replay { - u32 rp_status; + __be32 rp_status; unsigned int rp_buflen; char *rp_buf; unsigned intrp_allocated; @@ -273,19 +273,19 @@ struct nfs4_stateid { ((err) != nfserr_stale_stateid) && \ ((err) != nfserr_bad_stateid)) -extern int nfsd4_renew(clientid_t *clid); -extern int nfs4_preprocess_stateid_op(struct svc_fh *current_fh, +extern __be32 nfsd4_renew(clientid_t *clid); +extern __be32 nfs4_preprocess_stateid_op(struct svc_fh *current_fh, stateid_t *stateid, int flags, struct file **filp); extern void nfs4_lock_state(void); extern void nfs4_unlock_state(void); extern int nfs4_in_grace(void); -extern int nfs4_check_open_reclaim(clientid_t *clid); +extern __be32 nfs4_check_open_reclaim(clientid_t *clid); extern void put_nfs4_client(struct nfs4_client *clp); extern void nfs4_free_stateowner(struct kref *kref); extern void nfsd4_probe_callback(struct nfs4_client *clp); extern void nfsd4_cb_recall(struct nfs4_delegation *dp); extern void nfs4_put_delegation(struct nfs4_delegation *dp); -extern int nfs4_make_rec_clidname(char *clidname, struct xdr_netobj *clname); +extern __be32 nfs4_make_rec_clidname(char *clidname, struct xdr_netobj *clname); extern void nfsd4_init_recdir(char *recdir_name); extern int nfsd4_recdir_load(void); extern void nfsd4_shutdown_recdir(void); diff --git a/include/linux/nfsd/xdr4.h b/include/linux/nfsd/xdr4.h index 003193fe6fc6..45ca01b5f844 100644 --- a/include/linux/nfsd/xdr4.h +++ b/include/linux/nfsd/xdr4.h @@ -334,7 +334,7 @@ struct nfsd4_write { struct nfsd4_op { int opnum; - int status; + __be32 status; union { struct nfsd4_access access; struct nfsd4_close close; @@ -426,38 +426,38 @@ int nfs4svc_encode_compoundres(struct svc_rqst *, __be32 *, struct nfsd4_compoundres *); void nfsd4_encode_operation(struct nfsd4_compoundres *, struct nfsd4_op *); void nfsd4_encode_replay(struct nfsd4_compoundres *resp, struct nfsd4_op *op); -int nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp, - struct dentry *dentry, u32 *buffer, int *countp, +__be32 nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp, + struct dentry *dentry, __be32 *buffer, int *countp, u32 *bmval, struct svc_rqst *); -extern int nfsd4_setclientid(struct svc_rqst *rqstp, +extern __be32 nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_setclientid *setclid); -extern int nfsd4_setclientid_confirm(struct svc_rqst *rqstp, +extern __be32 nfsd4_setclientid_confirm(struct svc_rqst *rqstp, struct nfsd4_setclientid_confirm *setclientid_confirm); -extern int nfsd4_process_open1(struct nfsd4_open *open); -extern int nfsd4_process_open2(struct svc_rqst *rqstp, +extern __be32 nfsd4_process_open1(struct nfsd4_open *open); +extern __be32 nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_open *open); -extern int nfsd4_open_confirm(struct svc_rqst *rqstp, +extern __be32 nfsd4_open_confirm(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_open_confirm *oc, struct nfs4_stateowner **); -extern int nfsd4_close(struct svc_rqst *rqstp, struct svc_fh *current_fh, +extern __be32 nfsd4_close(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_close *close, struct nfs4_stateowner **replay_owner); -extern int nfsd4_open_downgrade(struct svc_rqst *rqstp, +extern __be32 nfsd4_open_downgrade(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_open_downgrade *od, struct nfs4_stateowner **replay_owner); -extern int nfsd4_lock(struct svc_rqst *rqstp, struct svc_fh *current_fh, +extern __be32 nfsd4_lock(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_lock *lock, struct nfs4_stateowner **replay_owner); -extern int nfsd4_lockt(struct svc_rqst *rqstp, struct svc_fh *current_fh, +extern __be32 nfsd4_lockt(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_lockt *lockt); -extern int nfsd4_locku(struct svc_rqst *rqstp, struct svc_fh *current_fh, +extern __be32 nfsd4_locku(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_locku *locku, struct nfs4_stateowner **replay_owner); -extern int +extern __be32 nfsd4_release_lockowner(struct svc_rqst *rqstp, struct nfsd4_release_lockowner *rlockowner); extern void nfsd4_release_compoundargs(struct nfsd4_compoundargs *); -extern int nfsd4_delegreturn(struct svc_rqst *rqstp, +extern __be32 nfsd4_delegreturn(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_delegreturn *dr); #endif -- cgit v1.2.3 From c7afef1f963bec198b186cc34b9e8c9b9ce2e266 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 19 Oct 2006 23:29:02 -0700 Subject: [PATCH] nfsd: misc endianness annotations Signed-off-by: Al Viro Acked-by: Trond Myklebust Acked-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nfsd/cache.h | 6 +++--- include/linux/nfsd/export.h | 2 +- include/linux/nfsd/nfsd.h | 2 +- include/linux/nfsd/nfsfh.h | 2 +- include/linux/nfsd/state.h | 2 +- 5 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfsd/cache.h b/include/linux/nfsd/cache.h index c3a3557c2a5b..007480cd6a60 100644 --- a/include/linux/nfsd/cache.h +++ b/include/linux/nfsd/cache.h @@ -26,14 +26,14 @@ struct svc_cacherep { c_type, /* status, buffer */ c_secure : 1; /* req came from port < 1024 */ struct sockaddr_in c_addr; - u32 c_xid; + __be32 c_xid; u32 c_prot; u32 c_proc; u32 c_vers; unsigned long c_timestamp; union { struct kvec u_vec; - u32 u_status; + __be32 u_status; } c_u; }; @@ -75,7 +75,7 @@ enum { void nfsd_cache_init(void); void nfsd_cache_shutdown(void); int nfsd_cache_lookup(struct svc_rqst *, int); -void nfsd_cache_update(struct svc_rqst *, int, u32 *); +void nfsd_cache_update(struct svc_rqst *, int, __be32 *); #endif /* __KERNEL__ */ #endif /* NFSCACHE_H */ diff --git a/include/linux/nfsd/export.h b/include/linux/nfsd/export.h index 27666f5b8b53..045e38cdbe64 100644 --- a/include/linux/nfsd/export.h +++ b/include/linux/nfsd/export.h @@ -117,7 +117,7 @@ struct svc_export * exp_parent(struct auth_domain *clp, struct cache_req *reqp); int exp_rootfh(struct auth_domain *, char *path, struct knfsd_fh *, int maxsize); -int exp_pseudoroot(struct auth_domain *, struct svc_fh *fhp, struct cache_req *creq); +__be32 exp_pseudoroot(struct auth_domain *, struct svc_fh *fhp, struct cache_req *creq); __be32 nfserrno(int errno); extern struct cache_detail svc_export_cache; diff --git a/include/linux/nfsd/nfsd.h b/include/linux/nfsd/nfsd.h index 19a3c83d496e..68d29b66c6e2 100644 --- a/include/linux/nfsd/nfsd.h +++ b/include/linux/nfsd/nfsd.h @@ -64,7 +64,7 @@ extern struct svc_serv *nfsd_serv; * Function prototypes. */ int nfsd_svc(unsigned short port, int nrservs); -int nfsd_dispatch(struct svc_rqst *rqstp, u32 *statp); +int nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp); /* nfsd/vfs.c */ int fh_lock_parent(struct svc_fh *, struct dentry *); diff --git a/include/linux/nfsd/nfsfh.h b/include/linux/nfsd/nfsfh.h index 749bad1ca16f..f3b51d62ec7d 100644 --- a/include/linux/nfsd/nfsfh.h +++ b/include/linux/nfsd/nfsfh.h @@ -157,7 +157,7 @@ typedef struct svc_fh { __u64 fh_post_size; /* i_size */ unsigned long fh_post_blocks; /* i_blocks */ unsigned long fh_post_blksize;/* i_blksize */ - __u32 fh_post_rdev[2];/* i_rdev */ + __be32 fh_post_rdev[2];/* i_rdev */ struct timespec fh_post_atime; /* i_atime */ struct timespec fh_post_mtime; /* i_mtime */ struct timespec fh_post_ctime; /* i_ctime */ diff --git a/include/linux/nfsd/state.h b/include/linux/nfsd/state.h index a597e2e72469..c3673f487e84 100644 --- a/include/linux/nfsd/state.h +++ b/include/linux/nfsd/state.h @@ -125,7 +125,7 @@ struct nfs4_client { char cl_recdir[HEXDIR_LEN]; /* recovery dir */ nfs4_verifier cl_verifier; /* generated by client */ time_t cl_time; /* time of last lease renewal */ - u32 cl_addr; /* client ipaddress */ + __be32 cl_addr; /* client ipaddress */ struct svc_cred cl_cred; /* setclientid principal */ clientid_t cl_clientid; /* generated by server */ nfs4_verifier cl_confirm; /* generated by server */ -- cgit v1.2.3 From a90b061c0bf712961cea40d9c916b300073d12e5 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 19 Oct 2006 23:29:03 -0700 Subject: [PATCH] nfsd: nfs_replay_me We are using NFS_REPLAY_ME as a special error value that is never leaked to clients. That works fine; the only problem is mixing host- and network- endian values in the same objects. Network-endian equivalent would work just as fine; switch to it. Signed-off-by: Al Viro Acked-by: Trond Myklebust Acked-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nfsd/nfsd.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfsd/nfsd.h b/include/linux/nfsd/nfsd.h index 68d29b66c6e2..eb231143d579 100644 --- a/include/linux/nfsd/nfsd.h +++ b/include/linux/nfsd/nfsd.h @@ -238,6 +238,7 @@ void nfsd_lockd_shutdown(void); #define nfserr_badname __constant_htonl(NFSERR_BADNAME) #define nfserr_cb_path_down __constant_htonl(NFSERR_CB_PATH_DOWN) #define nfserr_locked __constant_htonl(NFSERR_LOCKED) +#define nfserr_replay_me __constant_htonl(NFSERR_REPLAY_ME) /* error codes for internal use */ /* if a request fails due to kmalloc failure, it gets dropped. -- cgit v1.2.3 From 690a973f48b6ba2954465992c08e65059c8374fe Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Sat, 21 Oct 2006 18:37:01 +0200 Subject: [PATCH] x86-64: Speed up dwarf2 unwinder This changes the dwarf2 unwinder to do a binary search for CIEs instead of a linear work. The linker is unfortunately not able to build a proper lookup table at link time, instead it creates one at runtime as soon as the bootmem allocator is usable (so you'll continue using the linear lookup for the first [hopefully] few calls). The code should be ready to utilize a build-time created table once a fixed linker becomes available. Signed-off-by: Jan Beulich Signed-off-by: Andi Kleen --- include/linux/unwind.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/unwind.h b/include/linux/unwind.h index 73e1751d03dd..749928c161fb 100644 --- a/include/linux/unwind.h +++ b/include/linux/unwind.h @@ -26,6 +26,7 @@ struct module; * Initialize unwind support. */ extern void unwind_init(void); +extern void unwind_setup(void); #ifdef CONFIG_MODULES @@ -73,6 +74,7 @@ extern int unwind_to_user(struct unwind_frame_info *); struct unwind_frame_info {}; static inline void unwind_init(void) {} +static inline void unwind_setup(void) {} #ifdef CONFIG_MODULES -- cgit v1.2.3 From a1bae67243512ca30ceda48e3e24e25b543f8ab7 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Sat, 21 Oct 2006 18:37:02 +0200 Subject: [PATCH] i386: Disable nmi watchdog on all ThinkPads Even newer Thinkpads have bugs in SMM code that causes hangs with NMI watchdog. Signed-off-by: Andi Kleen --- include/linux/dmi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dmi.h b/include/linux/dmi.h index 38dc403be70b..904bf3d2d90b 100644 --- a/include/linux/dmi.h +++ b/include/linux/dmi.h @@ -69,6 +69,7 @@ extern struct dmi_device * dmi_find_device(int type, const char *name, struct dmi_device *from); extern void dmi_scan_machine(void); extern int dmi_get_year(int field); +extern int dmi_name_in_vendors(char *str); #else @@ -77,6 +78,7 @@ static inline char * dmi_get_system_info(int field) { return NULL; } static inline struct dmi_device * dmi_find_device(int type, const char *name, struct dmi_device *from) { return NULL; } static inline int dmi_get_year(int year) { return 0; } +static inline int dmi_name_in_vendors(char *s) { return 0; } #endif -- cgit v1.2.3 From 3343571d9f88a0de542d33aea9ab881f00ff866d Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 19 Oct 2006 14:44:53 +0900 Subject: [PATCH] libata: typo fix Typo fix in commment. 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 d0a7ad5ed518..b03d5a340dc8 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -143,7 +143,7 @@ enum { ATA_DFLAG_CFG_MASK = (1 << 8) - 1, ATA_DFLAG_PIO = (1 << 8), /* device limited to PIO mode */ - ATA_DFLAG_NCQ_OFF = (1 << 9), /* devied limited to non-NCQ mode */ + ATA_DFLAG_NCQ_OFF = (1 << 9), /* device limited to non-NCQ mode */ ATA_DFLAG_SUSPENDED = (1 << 10), /* device suspended */ ATA_DFLAG_INIT_MASK = (1 << 16) - 1, -- cgit v1.2.3 From da3ed32fe568148ede256975d40825ffcdac767b Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Sat, 21 Oct 2006 10:24:08 -0700 Subject: [PATCH] md: add another COMPAT_IOCTL for md .. so that you can use bitmaps with 32bit userspace on a 64 bit kernel. Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compat_ioctl.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/compat_ioctl.h b/include/linux/compat_ioctl.h index cfdb4f6a89d4..c26c3adcfacf 100644 --- a/include/linux/compat_ioctl.h +++ b/include/linux/compat_ioctl.h @@ -131,6 +131,7 @@ COMPATIBLE_IOCTL(RUN_ARRAY) COMPATIBLE_IOCTL(STOP_ARRAY) COMPATIBLE_IOCTL(STOP_ARRAY_RO) COMPATIBLE_IOCTL(RESTART_ARRAY_RW) +COMPATIBLE_IOCTL(GET_BITMAP_FILE) ULONG_IOCTL(SET_BITMAP_FILE) /* DM */ COMPATIBLE_IOCTL(DM_VERSION_32) -- cgit v1.2.3 From 1c05b4bc22cd640d3a534bd2851a8413d5df3709 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Sat, 21 Oct 2006 10:24:08 -0700 Subject: [PATCH] md: endian annotation for v1 superblock access Includes a couple of bugfixes found by sparse. Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/raid/md_p.h | 56 +++++++++++++++++++++++------------------------ 1 file changed, 28 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/include/linux/raid/md_p.h b/include/linux/raid/md_p.h index b6ebc69bae54..3f2cd98c508b 100644 --- a/include/linux/raid/md_p.h +++ b/include/linux/raid/md_p.h @@ -206,52 +206,52 @@ static inline __u64 md_event(mdp_super_t *sb) { */ struct mdp_superblock_1 { /* constant array information - 128 bytes */ - __u32 magic; /* MD_SB_MAGIC: 0xa92b4efc - little endian */ - __u32 major_version; /* 1 */ - __u32 feature_map; /* bit 0 set if 'bitmap_offset' is meaningful */ - __u32 pad0; /* always set to 0 when writing */ + __le32 magic; /* MD_SB_MAGIC: 0xa92b4efc - little endian */ + __le32 major_version; /* 1 */ + __le32 feature_map; /* bit 0 set if 'bitmap_offset' is meaningful */ + __le32 pad0; /* always set to 0 when writing */ __u8 set_uuid[16]; /* user-space generated. */ char set_name[32]; /* set and interpreted by user-space */ - __u64 ctime; /* lo 40 bits are seconds, top 24 are microseconds or 0*/ - __u32 level; /* -4 (multipath), -1 (linear), 0,1,4,5 */ - __u32 layout; /* only for raid5 and raid10 currently */ - __u64 size; /* used size of component devices, in 512byte sectors */ + __le64 ctime; /* lo 40 bits are seconds, top 24 are microseconds or 0*/ + __le32 level; /* -4 (multipath), -1 (linear), 0,1,4,5 */ + __le32 layout; /* only for raid5 and raid10 currently */ + __le64 size; /* used size of component devices, in 512byte sectors */ - __u32 chunksize; /* in 512byte sectors */ - __u32 raid_disks; - __u32 bitmap_offset; /* sectors after start of superblock that bitmap starts + __le32 chunksize; /* in 512byte sectors */ + __le32 raid_disks; + __le32 bitmap_offset; /* sectors after start of superblock that bitmap starts * NOTE: signed, so bitmap can be before superblock * only meaningful of feature_map[0] is set. */ /* These are only valid with feature bit '4' */ - __u32 new_level; /* new level we are reshaping to */ - __u64 reshape_position; /* next address in array-space for reshape */ - __u32 delta_disks; /* change in number of raid_disks */ - __u32 new_layout; /* new layout */ - __u32 new_chunk; /* new chunk size (bytes) */ + __le32 new_level; /* new level we are reshaping to */ + __le64 reshape_position; /* next address in array-space for reshape */ + __le32 delta_disks; /* change in number of raid_disks */ + __le32 new_layout; /* new layout */ + __le32 new_chunk; /* new chunk size (bytes) */ __u8 pad1[128-124]; /* set to 0 when written */ /* constant this-device information - 64 bytes */ - __u64 data_offset; /* sector start of data, often 0 */ - __u64 data_size; /* sectors in this device that can be used for data */ - __u64 super_offset; /* sector start of this superblock */ - __u64 recovery_offset;/* sectors before this offset (from data_offset) have been recovered */ - __u32 dev_number; /* permanent identifier of this device - not role in raid */ - __u32 cnt_corrected_read; /* number of read errors that were corrected by re-writing */ + __le64 data_offset; /* sector start of data, often 0 */ + __le64 data_size; /* sectors in this device that can be used for data */ + __le64 super_offset; /* sector start of this superblock */ + __le64 recovery_offset;/* sectors before this offset (from data_offset) have been recovered */ + __le32 dev_number; /* permanent identifier of this device - not role in raid */ + __le32 cnt_corrected_read; /* number of read errors that were corrected by re-writing */ __u8 device_uuid[16]; /* user-space setable, ignored by kernel */ __u8 devflags; /* per-device flags. Only one defined...*/ #define WriteMostly1 1 /* mask for writemostly flag in above */ __u8 pad2[64-57]; /* set to 0 when writing */ /* array state information - 64 bytes */ - __u64 utime; /* 40 bits second, 24 btes microseconds */ - __u64 events; /* incremented when superblock updated */ - __u64 resync_offset; /* data before this offset (from data_offset) known to be in sync */ - __u32 sb_csum; /* checksum upto devs[max_dev] */ - __u32 max_dev; /* size of devs[] array to consider */ + __le64 utime; /* 40 bits second, 24 btes microseconds */ + __le64 events; /* incremented when superblock updated */ + __le64 resync_offset; /* data before this offset (from data_offset) known to be in sync */ + __le32 sb_csum; /* checksum upto devs[max_dev] */ + __le32 max_dev; /* size of devs[] array to consider */ __u8 pad3[64-32]; /* set to 0 when writing */ /* device state information. Indexed by dev_number. @@ -260,7 +260,7 @@ struct mdp_superblock_1 { * into the 'roles' value. If a device is spare or faulty, then it doesn't * have a meaningful role. */ - __u16 dev_roles[0]; /* role in array, or 0xffff for a spare, or 0xfffe for faulty */ + __le16 dev_roles[0]; /* role in array, or 0xffff for a spare, or 0xfffe for faulty */ }; /* feature_map bits */ -- cgit v1.2.3 From 4f2e639af4bd5e152fc79256e333643d3dd6c10f Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Sat, 21 Oct 2006 10:24:09 -0700 Subject: [PATCH] md: endian annotations for the bitmap superblock And a couple of bug fixes found by sparse. Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/raid/bitmap.h | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/raid/bitmap.h b/include/linux/raid/bitmap.h index 84d887751855..ebd42a3710b4 100644 --- a/include/linux/raid/bitmap.h +++ b/include/linux/raid/bitmap.h @@ -146,16 +146,16 @@ enum bitmap_state { /* the superblock at the front of the bitmap file -- little endian */ typedef struct bitmap_super_s { - __u32 magic; /* 0 BITMAP_MAGIC */ - __u32 version; /* 4 the bitmap major for now, could change... */ - __u8 uuid[16]; /* 8 128 bit uuid - must match md device uuid */ - __u64 events; /* 24 event counter for the bitmap (1)*/ - __u64 events_cleared;/*32 event counter when last bit cleared (2) */ - __u64 sync_size; /* 40 the size of the md device's sync range(3) */ - __u32 state; /* 48 bitmap state information */ - __u32 chunksize; /* 52 the bitmap chunk size in bytes */ - __u32 daemon_sleep; /* 56 seconds between disk flushes */ - __u32 write_behind; /* 60 number of outstanding write-behind writes */ + __le32 magic; /* 0 BITMAP_MAGIC */ + __le32 version; /* 4 the bitmap major for now, could change... */ + __u8 uuid[16]; /* 8 128 bit uuid - must match md device uuid */ + __le64 events; /* 24 event counter for the bitmap (1)*/ + __le64 events_cleared;/*32 event counter when last bit cleared (2) */ + __le64 sync_size; /* 40 the size of the md device's sync range(3) */ + __le32 state; /* 48 bitmap state information */ + __le32 chunksize; /* 52 the bitmap chunk size in bytes */ + __le32 daemon_sleep; /* 56 seconds between disk flushes */ + __le32 write_behind; /* 60 number of outstanding write-behind writes */ __u8 pad[256 - 64]; /* set to zero */ } bitmap_super_t; -- cgit v1.2.3 From d42552c3ace1fa1f16ae02ce642f4c733cec40ca Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Sat, 21 Oct 2006 10:24:12 -0700 Subject: [PATCH] pci: declare pci_get_device_reverse() We seem to have lost the declaration of pci_get_device_reverse(), if we ever had one. Add a CONFIG_PCI=0 stub too. Acked-by: Alan Cox Cc: Greg KH Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pci.h | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 4689e2a699c0..09be0f81b27b 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -455,7 +455,11 @@ int pci_find_next_capability (struct pci_dev *dev, u8 pos, int cap); int pci_find_ext_capability (struct pci_dev *dev, int cap); struct pci_bus *pci_find_next_bus(const struct pci_bus *from); -struct pci_dev *pci_get_device (unsigned int vendor, unsigned int device, struct pci_dev *from); +struct pci_dev *pci_get_device(unsigned int vendor, unsigned int device, + struct pci_dev *from); +struct pci_dev *pci_get_device_reverse(unsigned int vendor, unsigned int device, + struct pci_dev *from); + struct pci_dev *pci_get_subsys (unsigned int vendor, unsigned int device, unsigned int ss_vendor, unsigned int ss_device, struct pci_dev *from); @@ -660,7 +664,12 @@ static inline struct pci_dev *pci_find_device(unsigned int vendor, unsigned int static inline struct pci_dev *pci_find_slot(unsigned int bus, unsigned int devfn) { return NULL; } -static inline struct pci_dev *pci_get_device (unsigned int vendor, unsigned int device, struct pci_dev *from) +static inline struct pci_dev *pci_get_device(unsigned int vendor, + unsigned int device, struct pci_dev *from) +{ return NULL; } + +static inline struct pci_dev *pci_get_device_reverse(unsigned int vendor, + unsigned int device, struct pci_dev *from) { return NULL; } static inline struct pci_dev *pci_get_subsys (unsigned int vendor, unsigned int device, -- cgit v1.2.3 From 7516795739bd53175629b90fab0ad488d7a6a9f7 Mon Sep 17 00:00:00 2001 From: Andy Whitcroft Date: Sat, 21 Oct 2006 10:24:14 -0700 Subject: [PATCH] Reintroduce NODES_SPAN_OTHER_NODES for powerpc Reintroduce NODES_SPAN_OTHER_NODES for powerpc Revert "[PATCH] Remove SPAN_OTHER_NODES config definition" This reverts commit f62859bb6871c5e4a8e591c60befc8caaf54db8c. Revert "[PATCH] mm: remove arch independent NODES_SPAN_OTHER_NODES" This reverts commit a94b3ab7eab4edcc9b2cb474b188f774c331adf7. Also update the comments to indicate that this is still required and where its used. Signed-off-by: Andy Whitcroft Cc: Paul Mackerras Cc: Mike Kravetz Cc: Benjamin Herrenschmidt Acked-by: Mel Gorman Acked-by: Will Schmidt Cc: Christoph Lameter Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 59855b8718a0..ed0762b283a9 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -674,6 +674,12 @@ void sparse_init(void); #define sparse_index_init(_sec, _nid) do {} while (0) #endif /* CONFIG_SPARSEMEM */ +#ifdef CONFIG_NODES_SPAN_OTHER_NODES +#define early_pfn_in_nid(pfn, nid) (early_pfn_to_nid(pfn) == (nid)) +#else +#define early_pfn_in_nid(pfn, nid) (1) +#endif + #ifndef early_pfn_valid #define early_pfn_valid(pfn) (1) #endif -- cgit v1.2.3 From faf6bbcf94caee10ba34adb86db4ecca96bfd3bf Mon Sep 17 00:00:00 2001 From: Paul Jackson Date: Sat, 21 Oct 2006 10:24:17 -0700 Subject: [PATCH] cpuset: mempolicy migration typo fix Mistyped an ifdef CONFIG_CPUSETS - fixed. I doubt that anyone ever noticed. The impact of this typo was that if someone: 1) was using MPOL_BIND to force off node allocations 2) while using cpusets to constrain memory placement 3) when that cpuset was migrating that jobs memory 4) while the tasks in that job were actively forking then there was a rare chance that future allocations using that MPOL_BIND policy would be node local, not off node. Signed-off-by: Paul Jackson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mempolicy.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 09f0f575ddff..daabb3aa1ec6 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -150,7 +150,7 @@ extern void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new); extern void mpol_fix_fork_child_flag(struct task_struct *p); #define set_cpuset_being_rebound(x) (cpuset_being_rebound = (x)) -#ifdef CONFIG_CPUSET +#ifdef CONFIG_CPUSETS #define current_cpuset_is_being_rebound() \ (cpuset_being_rebound == current->cpuset) #else -- cgit v1.2.3 From 04fed361dadb7921507a470947ac23d2f26352cf Mon Sep 17 00:00:00 2001 From: Russell King Date: Sun, 22 Oct 2006 15:57:18 +0100 Subject: [PATCH] Remove __must_check for device_for_each_child() Eliminate more __must_check madness. The return code from device_for_each_child() depends on the values which the helper function returns. If the helper function always returns zero, it's utterly pointless to check the return code from device_for_each_child(). The only code which knows if the return value should be checked is the caller itself, so forcing the return code to always be checked is silly. Hence, remove the __must_check annotation. Signed-off-by: Russell King Signed-off-by: Linus Torvalds --- 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 662e6a10144e..9d4f6a963936 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -393,7 +393,7 @@ extern void device_unregister(struct device * dev); extern void device_initialize(struct device * dev); extern int __must_check device_add(struct device * dev); extern void device_del(struct device * dev); -extern int __must_check device_for_each_child(struct device *, void *, +extern int device_for_each_child(struct device *, void *, int (*fn)(struct device *, void *)); extern int device_rename(struct device *dev, char *new_name); -- cgit v1.2.3 From 0344c6c5387ba335bba5a66fd44714b94c98573f Mon Sep 17 00:00:00 2001 From: Christian Krafft Date: Tue, 24 Oct 2006 18:31:24 +0200 Subject: [POWERPC] sysfs: add support for adding/removing spu sysfs attributes This patch adds two functions to create and remove sysfs attributes and attribute_group to all cpus. That allows to register sysfs attributes in a subdirectory like: /sys/devices/system/cpu/cpuX/group_name/what_ever This will be used by cbe_thermal to group all attributes dealing with thermal support in one directory. Signed-of-by: Christian Krafft Signed-off-by: Paul Mackerras --- include/linux/cpu.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 3fef7d67aedc..f02d71bf6894 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -33,6 +33,14 @@ struct cpu { extern int register_cpu(struct cpu *cpu, int num); extern struct sys_device *get_cpu_sysdev(unsigned cpu); + +extern int cpu_add_sysdev_attr(struct sysdev_attribute *attr); +extern void cpu_remove_sysdev_attr(struct sysdev_attribute *attr); + +extern int cpu_add_sysdev_attr_group(struct attribute_group *attrs); +extern void cpu_remove_sysdev_attr_group(struct attribute_group *attrs); + + #ifdef CONFIG_HOTPLUG_CPU extern void unregister_cpu(struct cpu *cpu); #endif -- cgit v1.2.3 From 735a7ffb739b6efeaeb1e720306ba308eaaeb20e Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Fri, 27 Oct 2006 11:42:37 -0700 Subject: [PATCH] drivers: wait for threaded probes between initcall levels The multithreaded-probing code has a problem: after one initcall level (eg, core_initcall) has been processed, we will then start processing the next level (postcore_initcall) while the kernel threads which are handling core_initcall are still executing. This breaks the guarantees which the layered initcalls previously gave us. IOW, we want to be multithreaded _within_ an initcall level, but not between different levels. Fix that up by causing the probing code to wait for all outstanding probes at one level to complete before we start processing the next level. Cc: Greg KH Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/init.h | 28 +++++++++++++++++++--------- 1 file changed, 19 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/init.h b/include/linux/init.h index e92b1455d7af..ff40ea118e3a 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -84,19 +84,29 @@ extern void setup_arch(char **); * by link order. * For backwards compatibility, initcall() puts the call in * the device init subsection. + * + * The `id' arg to __define_initcall() is needed so that multiple initcalls + * can point at the same handler without causing duplicate-symbol build errors. */ -#define __define_initcall(level,fn) \ - static initcall_t __initcall_##fn __attribute_used__ \ +#define __define_initcall(level,fn,id) \ + static initcall_t __initcall_##fn##id __attribute_used__ \ __attribute__((__section__(".initcall" level ".init"))) = fn -#define core_initcall(fn) __define_initcall("1",fn) -#define postcore_initcall(fn) __define_initcall("2",fn) -#define arch_initcall(fn) __define_initcall("3",fn) -#define subsys_initcall(fn) __define_initcall("4",fn) -#define fs_initcall(fn) __define_initcall("5",fn) -#define device_initcall(fn) __define_initcall("6",fn) -#define late_initcall(fn) __define_initcall("7",fn) +#define core_initcall(fn) __define_initcall("1",fn,1) +#define core_initcall_sync(fn) __define_initcall("1s",fn,1s) +#define postcore_initcall(fn) __define_initcall("2",fn,2) +#define postcore_initcall_sync(fn) __define_initcall("2s",fn,2s) +#define arch_initcall(fn) __define_initcall("3",fn,3) +#define arch_initcall_sync(fn) __define_initcall("3s",fn,3s) +#define subsys_initcall(fn) __define_initcall("4",fn,4) +#define subsys_initcall_sync(fn) __define_initcall("4s",fn,4s) +#define fs_initcall(fn) __define_initcall("5",fn,5) +#define fs_initcall_sync(fn) __define_initcall("5s",fn,5s) +#define device_initcall(fn) __define_initcall("6",fn,6) +#define device_initcall_sync(fn) __define_initcall("6s",fn,6s) +#define late_initcall(fn) __define_initcall("7",fn,7) +#define late_initcall_sync(fn) __define_initcall("7s",fn,7s) #define __initcall(fn) device_initcall(fn) -- cgit v1.2.3 From 2ae88149a27cadf2840e0ab8155bef13be285c03 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Sat, 28 Oct 2006 10:38:23 -0700 Subject: [PATCH] mm: clean up pagecache allocation - Consolidate page_cache_alloc - Fix splice: only the pagecache pages and filesystem data need to use mapping_gfp_mask. - Fix grab_cache_page_nowait: same as splice, also honour NUMA placement. Signed-off-by: Nick Piggin Cc: Jens Axboe Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 64f950925151..c3e255bf8594 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -52,19 +52,23 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) void release_pages(struct page **pages, int nr, int cold); #ifdef CONFIG_NUMA -extern struct page *page_cache_alloc(struct address_space *x); -extern struct page *page_cache_alloc_cold(struct address_space *x); +extern struct page *__page_cache_alloc(gfp_t gfp); #else +static inline struct page *__page_cache_alloc(gfp_t gfp) +{ + return alloc_pages(gfp, 0); +} +#endif + static inline struct page *page_cache_alloc(struct address_space *x) { - return alloc_pages(mapping_gfp_mask(x), 0); + return __page_cache_alloc(mapping_gfp_mask(x)); } static inline struct page *page_cache_alloc_cold(struct address_space *x) { - return alloc_pages(mapping_gfp_mask(x)|__GFP_COLD, 0); + return __page_cache_alloc(mapping_gfp_mask(x)|__GFP_COLD); } -#endif typedef int filler_t(void *, struct page *); -- cgit v1.2.3 From 3bb1a852ab6c9cdf211a2f4a2f502340c8c38eca Mon Sep 17 00:00:00 2001 From: Martin Bligh Date: Sat, 28 Oct 2006 10:38:24 -0700 Subject: [PATCH] vmscan: Fix temp_priority race The temp_priority field in zone is racy, as we can walk through a reclaim path, and just before we copy it into prev_priority, it can be overwritten (say with DEF_PRIORITY) by another reclaimer. The same bug is contained in both try_to_free_pages and balance_pgdat, but it is fixed slightly differently. In balance_pgdat, we keep a separate priority record per zone in a local array. In try_to_free_pages there is no need to do this, as the priority level is the same for all zones that we reclaim from. Impact of this bug is that temp_priority is copied into prev_priority, and setting this artificially high causes reclaimers to set distress artificially low. They then fail to reclaim mapped pages, when they are, in fact, under severe memory pressure (their priority may be as low as 0). This causes the OOM killer to fire incorrectly. From: Andrew Morton __zone_reclaim() isn't modifying zone->prev_priority. But zone->prev_priority is used in the decision whether or not to bring mapped pages onto the inactive list. Hence there's a risk here that __zone_reclaim() will fail because zone->prev_priority ir large (ie: low urgency) and lots of mapped pages end up stuck on the active list. Fix that up by decreasing (ie making more urgent) zone->prev_priority as __zone_reclaim() scans the zone's pages. This bug perhaps explains why ZONE_RECLAIM_PRIORITY was created. It should be possible to remove that now, and to just start out at DEF_PRIORITY? Cc: Nick Piggin Cc: Christoph Lameter Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index ed0762b283a9..e06683e2bea3 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -218,13 +218,9 @@ struct zone { * under - it drives the swappiness decision: whether to unmap mapped * pages. * - * temp_priority is used to remember the scanning priority at which - * this zone was successfully refilled to free_pages == pages_high. - * - * Access to both these fields is quite racy even on uniprocessor. But + * Access to both this field is quite racy even on uniprocessor. But * it is expected to average out OK. */ - int temp_priority; int prev_priority; -- cgit v1.2.3 From 52fd24ca1db3a741f144bbc229beefe044202cac Mon Sep 17 00:00:00 2001 From: Giridhar Pemmasani Date: Sat, 28 Oct 2006 10:38:34 -0700 Subject: [PATCH] __vmalloc with GFP_ATOMIC causes 'sleeping from invalid context' If __vmalloc is called to allocate memory with GFP_ATOMIC in atomic context, the chain of calls results in __get_vm_area_node allocating memory for vm_struct with GFP_KERNEL, causing the 'sleeping from invalid context' warning. This patch fixes it by passing the gfp flags along so __get_vm_area_node allocates memory for vm_struct with the same flags. Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index ce5f1482e6be..dc9a29d84abc 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -60,7 +60,8 @@ extern struct vm_struct *get_vm_area(unsigned long size, unsigned long flags); extern struct vm_struct *__get_vm_area(unsigned long size, unsigned long flags, unsigned long start, unsigned long end); extern struct vm_struct *get_vm_area_node(unsigned long size, - unsigned long flags, int node); + unsigned long flags, int node, + gfp_t gfp_mask); extern struct vm_struct *remove_vm_area(void *addr); extern int map_vm_area(struct vm_struct *area, pgprot_t prot, struct page ***pages); -- cgit v1.2.3 From 5fa3839a64203b2ab727dcb37da9b2d7079fca28 Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Sat, 28 Oct 2006 10:38:46 -0700 Subject: [PATCH] Constify compat_get_bitmap argument This means we can call it when the bitmap we want to fetch is declared const. Signed-off-by: Stephen Rothwell Cc: Christoph Lameter Cc: Paul Jackson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compat.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index f4ebf96f5308..f1553196826f 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -196,7 +196,7 @@ asmlinkage long compat_sys_select(int n, compat_ulong_t __user *inp, #define BITS_TO_COMPAT_LONGS(bits) \ (((bits)+BITS_PER_COMPAT_LONG-1)/BITS_PER_COMPAT_LONG) -long compat_get_bitmap(unsigned long *mask, compat_ulong_t __user *umask, +long compat_get_bitmap(unsigned long *mask, const compat_ulong_t __user *umask, unsigned long bitmap_size); long compat_put_bitmap(compat_ulong_t __user *umask, unsigned long *mask, unsigned long bitmap_size); -- cgit v1.2.3 From 093a8e8aecd77b2799934996a55a6838e1e2b8f3 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Sat, 28 Oct 2006 10:38:51 -0700 Subject: [PATCH] taskstats_tgid_free: fix usage taskstats_tgid_free() is called on copy_process's error path. This is wrong. IF (clone_flags & CLONE_THREAD) We should not clear ->signal->taskstats, current uses it, it probably has a valid accumulated info. ELSE taskstats_tgid_init() set ->signal->taskstats = NULL, there is nothing to free. Move the callsite to __exit_signal(). We don't need any locking, entire thread group is exiting, nobody should have a reference to soon to be released ->signal. Signed-off-by: Oleg Nesterov Cc: Shailabh Nagar Cc: Balbir Singh Cc: Jay Lan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/taskstats_kern.h | 13 ++----------- 1 file changed, 2 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/taskstats_kern.h b/include/linux/taskstats_kern.h index 16894b7edcc8..a437ca0d226b 100644 --- a/include/linux/taskstats_kern.h +++ b/include/linux/taskstats_kern.h @@ -49,17 +49,8 @@ static inline void taskstats_tgid_alloc(struct signal_struct *sig) static inline void taskstats_tgid_free(struct signal_struct *sig) { - struct taskstats *stats = NULL; - unsigned long flags; - - spin_lock_irqsave(&sig->stats_lock, flags); - if (sig->stats) { - stats = sig->stats; - sig->stats = NULL; - } - spin_unlock_irqrestore(&sig->stats_lock, flags); - if (stats) - kmem_cache_free(taskstats_cache, stats); + if (sig->stats) + kmem_cache_free(taskstats_cache, sig->stats); } extern void taskstats_exit_alloc(struct taskstats **, unsigned int *); -- cgit v1.2.3 From 17b02695b254aa2ef0e53df9c8e6548f86e66a9d Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Sat, 28 Oct 2006 10:38:52 -0700 Subject: [PATCH] taskstats_tgid_alloc: optimization Every subthread (except first) does unneeded kmem_cache_alloc/kmem_cache_free. Signed-off-by: Oleg Nesterov Cc: Shailabh Nagar Cc: Balbir Singh Cc: Jay Lan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/taskstats_kern.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/taskstats_kern.h b/include/linux/taskstats_kern.h index a437ca0d226b..664224008fb2 100644 --- a/include/linux/taskstats_kern.h +++ b/include/linux/taskstats_kern.h @@ -32,6 +32,9 @@ static inline void taskstats_tgid_alloc(struct signal_struct *sig) struct taskstats *stats; unsigned long flags; + if (sig->stats != NULL) + return; + stats = kmem_cache_zalloc(taskstats_cache, SLAB_KERNEL); if (!stats) return; -- cgit v1.2.3 From b8534d7bd89df0cd41cd47bcd6733a05ea9a691a Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Sat, 28 Oct 2006 10:38:53 -0700 Subject: [PATCH] taskstats: kill ->taskstats_lock in favor of ->siglock signal_struct is (mostly) protected by ->sighand->siglock, I think we don't need ->taskstats_lock to protect ->stats. This also allows us to simplify the locking in fill_tgid(). Signed-off-by: Oleg Nesterov Cc: Shailabh Nagar Cc: Balbir Singh Cc: Jay Lan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 1 - include/linux/taskstats_kern.h | 15 ++++++--------- 2 files changed, 6 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 6735c1cf334c..eafe4a7b8237 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -466,7 +466,6 @@ struct signal_struct { struct pacct_struct pacct; /* per-process accounting information */ #endif #ifdef CONFIG_TASKSTATS - spinlock_t stats_lock; struct taskstats *stats; #endif }; diff --git a/include/linux/taskstats_kern.h b/include/linux/taskstats_kern.h index 664224008fb2..6562a2050a25 100644 --- a/include/linux/taskstats_kern.h +++ b/include/linux/taskstats_kern.h @@ -23,28 +23,26 @@ static inline void taskstats_exit_free(struct taskstats *tidstats) static inline void taskstats_tgid_init(struct signal_struct *sig) { - spin_lock_init(&sig->stats_lock); sig->stats = NULL; } -static inline void taskstats_tgid_alloc(struct signal_struct *sig) +static inline void taskstats_tgid_alloc(struct task_struct *tsk) { + struct signal_struct *sig = tsk->signal; struct taskstats *stats; - unsigned long flags; if (sig->stats != NULL) return; + /* No problem if kmem_cache_zalloc() fails */ stats = kmem_cache_zalloc(taskstats_cache, SLAB_KERNEL); - if (!stats) - return; - spin_lock_irqsave(&sig->stats_lock, flags); + spin_lock_irq(&tsk->sighand->siglock); if (!sig->stats) { sig->stats = stats; stats = NULL; } - spin_unlock_irqrestore(&sig->stats_lock, flags); + spin_unlock_irq(&tsk->sighand->siglock); if (stats) kmem_cache_free(taskstats_cache, stats); @@ -59,7 +57,6 @@ static inline void taskstats_tgid_free(struct signal_struct *sig) extern void taskstats_exit_alloc(struct taskstats **, unsigned int *); extern void taskstats_exit_send(struct task_struct *, struct taskstats *, int, unsigned int); extern void taskstats_init_early(void); -extern void taskstats_tgid_alloc(struct signal_struct *); #else static inline void taskstats_exit_alloc(struct taskstats **ptidstats, unsigned int *mycpu) {} @@ -71,7 +68,7 @@ static inline void taskstats_exit_send(struct task_struct *tsk, {} static inline void taskstats_tgid_init(struct signal_struct *sig) {} -static inline void taskstats_tgid_alloc(struct signal_struct *sig) +static inline void taskstats_tgid_alloc(struct task_struct *tsk) {} static inline void taskstats_tgid_free(struct signal_struct *sig) {} -- cgit v1.2.3 From 7259f0d05d595b73ef312a082e628627c6414969 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Sun, 29 Oct 2006 22:46:36 -0800 Subject: [PATCH] lockdep: annotate DECLARE_WAIT_QUEUE_HEAD kernel: INFO: trying to register non-static key. kernel: the code is fine but needs lockdep annotation. kernel: turning off the locking correctness validator. kernel: [] show_trace_log_lvl+0x58/0x16a kernel: [] show_trace+0xd/0x10 kernel: [] dump_stack+0x19/0x1b kernel: [] __lock_acquire+0xf0/0x90d kernel: [] lock_acquire+0x4b/0x6b kernel: [] _spin_lock_irqsave+0x22/0x32 kernel: [] prepare_to_wait+0x17/0x4b kernel: [] lpfc_do_work+0xdd/0xcc2 [lpfc] kernel: [] kthread+0xc3/0xf2 kernel: [] kernel_thread_helper+0x5/0xb Another case of non-static lockdep keys; duplicate the paradigm set by DECLARE_COMPLETION_ONSTACK and introduce DECLARE_WAIT_QUEUE_HEAD_ONSTACK. Signed-off-by: Peter Zijlstra Cc: Greg KH Cc: Markus Lidel Acked-by: Ingo Molnar Cc: Arjan van de Ven Cc: James Bottomley Cc: Marcel Holtmann Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/wait.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/wait.h b/include/linux/wait.h index b3b9048421d8..e820d00e1383 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -79,6 +79,15 @@ struct task_struct; extern void init_waitqueue_head(wait_queue_head_t *q); +#ifdef CONFIG_LOCKDEP +# define __WAIT_QUEUE_HEAD_INIT_ONSTACK(name) \ + ({ init_waitqueue_head(&name); name; }) +# define DECLARE_WAIT_QUEUE_HEAD_ONSTACK(name) \ + wait_queue_head_t name = __WAIT_QUEUE_HEAD_INIT_ONSTACK(name) +#else +# define DECLARE_WAIT_QUEUE_HEAD_ONSTACK(name) DECLARE_WAIT_QUEUE_HEAD(name) +#endif + static inline void init_waitqueue_entry(wait_queue_t *q, struct task_struct *p) { q->flags = 0; -- cgit v1.2.3 From 351edd240d0ba8620789ca9e24f5a38b62157f23 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 29 Oct 2006 22:46:40 -0800 Subject: [PATCH] MTD: fix last kernel-doc warning Fix the last current kernel-doc warning: Warning(/var/linsrc/linux-2619-rc3g5//include/linux/mtd/nand.h:416): No description found for parameter 'write_page' Signed-off-by: Randy Dunlap Cc: David Woodhouse Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mtd/nand.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 70420bbae82b..8b3ef4187219 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -355,7 +355,7 @@ struct nand_buffers { * @priv: [OPTIONAL] pointer to private chip date * @errstat: [OPTIONAL] hardware specific function to perform additional error status checks * (determine if errors are correctable) - * @write_page [REPLACEABLE] High-level page write function + * @write_page: [REPLACEABLE] High-level page write function */ struct nand_chip { -- cgit v1.2.3 From 6e42acc4115bc376b8523acbcba2b2b7cc27d016 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 27 Oct 2006 19:08:42 -0700 Subject: [PATCH] libata: unexport ata_dev_revalidate() ata_dev_revalidate() isn't used outside of libata core. Unexport it. Signed-off-by: Tejun Heo Signed-off-by: Andrew Morton 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 b03d5a340dc8..abd2debebca2 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -702,7 +702,6 @@ extern int ata_std_prereset(struct ata_port *ap); extern int ata_std_softreset(struct ata_port *ap, unsigned int *classes); extern int sata_std_hardreset(struct ata_port *ap, unsigned int *class); extern void ata_std_postreset(struct ata_port *ap, unsigned int *classes); -extern int ata_dev_revalidate(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 4fa2eeeac5e13a8579ee45bc172eed690d28fbb7 Mon Sep 17 00:00:00 2001 From: Peer Chen Date: Thu, 2 Nov 2006 18:55:48 -0500 Subject: pci_ids.h: Add NVIDIA PCI ID Signed-off-by: Jeff Garzik --- 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 f3a168f3c9df..fa4e1d799782 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1213,6 +1213,7 @@ #define PCI_DEVICE_ID_NVIDIA_NVENET_21 0x0451 #define PCI_DEVICE_ID_NVIDIA_NVENET_22 0x0452 #define PCI_DEVICE_ID_NVIDIA_NVENET_23 0x0453 +#define PCI_DEVICE_ID_NVIDIA_NFORCE_MCP67_IDE 0x0560 #define PCI_VENDOR_ID_IMS 0x10e0 #define PCI_DEVICE_ID_IMS_TT128 0x9128 -- cgit v1.2.3 From 86f4f0f9ba6e35fbbc409dfc3d8615c1a9822482 Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Thu, 2 Nov 2006 22:07:05 -0800 Subject: [PATCH] fix UFS superblock alignment issues ufs2 fails to mount on x86_64, claiming bad magic. This is because ufs_super_block_third's fs_un1 member is padded out by 4 bytes for 8-byte alignment, pushing down the rest of the struct. Forcing this to be packed solves it. I took a quick look over other on-disk structures and didn't immediately find other problems. I was able to mount & ls a populated ufs2 filesystem w/ this change. Signed-off-by: Eric Sandeen Cc: Evgeniy Dushistov Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ufs_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ufs_fs.h b/include/linux/ufs_fs.h index 61eef508b041..28967eda9d7b 100644 --- a/include/linux/ufs_fs.h +++ b/include/linux/ufs_fs.h @@ -908,7 +908,7 @@ struct ufs_super_block_third { __fs64 fs_csaddr; /* blk addr of cyl grp summary area */ __fs64 fs_pendingblocks;/* blocks in process of being freed */ __fs32 fs_pendinginodes;/*inodes in process of being freed */ - } fs_u2; + } __attribute__ ((packed)) fs_u2; } fs_un1; union { struct { -- cgit v1.2.3 From f46c483357c2d87606bbefb511321e3efd4baae0 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Thu, 2 Nov 2006 22:07:16 -0800 Subject: [PATCH] Add printk_timed_ratelimit() printk_ratelimit() has global state which makes it not useful for callers which wish to perform ratelimiting at a particular frequency. Add a printk_timed_ratelimit() which utilises caller-provided state storage to permit more flexibility. This function can in fact be used for things other than printk ratelimiting and is perhaps poorly named. Cc: Ulrich Drepper Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Rusty Russell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 80f39cab470a..24b611147adb 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -171,6 +171,8 @@ __attribute_const__ roundup_pow_of_two(unsigned long x) extern int printk_ratelimit(void); extern int __printk_ratelimit(int ratelimit_jiffies, int ratelimit_burst); +extern bool printk_timed_ratelimit(unsigned long *caller_jiffies, + unsigned int interval_msec); static inline void console_silent(void) { -- cgit v1.2.3 From b918f6e62cd46774f9fc0a3fbba6bd10ad85ee14 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 2 Nov 2006 22:07:19 -0800 Subject: [PATCH] swsusp: debugging Add a swsusp debugging mode. This does everything that's needed for a suspend except for actually suspending. So we can look in the log messages and work out a) what code is being slow and b) which drivers are misbehaving. (1) # echo testproc > /sys/power/disk # echo disk > /sys/power/state This should turn off the non-boot CPU, freeze all processes, wait for 5 seconds and then thaw the processes and the CPU. (2) # echo test > /sys/power/disk # echo disk > /sys/power/state This should turn off the non-boot CPU, freeze all processes, shrink memory, suspend all devices, wait for 5 seconds, resume the devices etc. Cc: Pavel Machek Cc: Stefan Seyfried Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pm.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pm.h b/include/linux/pm.h index 6b27e07aef19..070394e846d0 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -116,7 +116,9 @@ typedef int __bitwise suspend_disk_method_t; #define PM_DISK_PLATFORM ((__force suspend_disk_method_t) 2) #define PM_DISK_SHUTDOWN ((__force suspend_disk_method_t) 3) #define PM_DISK_REBOOT ((__force suspend_disk_method_t) 4) -#define PM_DISK_MAX ((__force suspend_disk_method_t) 5) +#define PM_DISK_TEST ((__force suspend_disk_method_t) 5) +#define PM_DISK_TESTPROC ((__force suspend_disk_method_t) 6) +#define PM_DISK_MAX ((__force suspend_disk_method_t) 7) struct pm_ops { suspend_disk_method_t pm_disk_mode; -- cgit v1.2.3 From 3fd593979802f81ff6452596ac61e3840f917589 Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Thu, 2 Nov 2006 22:07:24 -0800 Subject: [PATCH] Create compat_sys_migrate_pages This is needed on bigendian 64bit architectures. Signed-off-by: Stephen Rothwell Acked-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compat.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index f1553196826f..80b17f440ec1 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -230,5 +230,9 @@ asmlinkage long compat_sys_adjtimex(struct compat_timex __user *utp); extern int compat_printk(const char *fmt, ...); extern void sigset_from_compat(sigset_t *set, compat_sigset_t *compat); +asmlinkage long compat_sys_migrate_pages(compat_pid_t pid, + compat_ulong_t maxnode, const compat_ulong_t __user *old_nodes, + const compat_ulong_t __user *new_nodes); + #endif /* CONFIG_COMPAT */ #endif /* _LINUX_COMPAT_H */ -- cgit v1.2.3 From 4833ed094097323f5f219820f6ebdc8dd66f501f Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 3 Nov 2006 00:27:06 -0800 Subject: [IPX]: Trivial parts of endianness annotations Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/ipx.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ipx.h b/include/linux/ipx.h index 4f29c60964c4..eb19b4ea84f4 100644 --- a/include/linux/ipx.h +++ b/include/linux/ipx.h @@ -7,8 +7,8 @@ struct sockaddr_ipx { sa_family_t sipx_family; - __u16 sipx_port; - __u32 sipx_network; + __be16 sipx_port; + __be32 sipx_network; unsigned char sipx_node[IPX_NODE_LEN]; __u8 sipx_type; unsigned char sipx_zero; /* 16 byte fill */ @@ -23,13 +23,13 @@ struct sockaddr_ipx { #define IPX_CRTITF 1 struct ipx_route_definition { - __u32 ipx_network; - __u32 ipx_router_network; + __be32 ipx_network; + __be32 ipx_router_network; unsigned char ipx_router_node[IPX_NODE_LEN]; }; struct ipx_interface_definition { - __u32 ipx_network; + __be32 ipx_network; unsigned char ipx_device[16]; unsigned char ipx_dlink_type; #define IPX_FRAME_NONE 0 @@ -55,8 +55,8 @@ struct ipx_config_data { */ struct ipx_route_def { - __u32 ipx_network; - __u32 ipx_router_network; + __be32 ipx_network; + __be32 ipx_router_network; #define IPX_ROUTE_NO_ROUTER 0 unsigned char ipx_router_node[IPX_NODE_LEN]; unsigned char ipx_device[16]; -- cgit v1.2.3 From d99f160ac53e51090f015a8f0617cea25f81a191 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 5 Nov 2006 23:52:12 -0800 Subject: [PATCH] sysctl: allow a zero ctl_name in the middle of a sysctl table Since it is becoming clear that there are just enough users of the binary sysctl interface that completely removing the binary interface from the kernel will not be an option for foreseeable future, we need to find a way to address the sysctl maintenance issues. The basic problem is that sysctl requires one central authority to allocate sysctl numbers, or else conflicts and ABI breakage occur. The proc interface to sysctl does not have that problem, as names are not densely allocated. By not terminating a sysctl table until I have neither a ctl_name nor a procname, it becomes simple to add sysctl entries that don't show up in the binary sysctl interface. Which allows people to avoid allocating a binary sysctl value when not needed. I have audited the kernel code and in my reading I have not found a single sysctl table that wasn't terminated by a completely zero filled entry. So this change in behavior should not affect anything. I think this mechanism eases the pain enough that combined with a little disciple we can solve the reoccurring sysctl ABI breakage. Signed-off-by: Eric W. Biederman Acked-by: Alan Cox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sysctl.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 1b24bd45e080..c184732a70fc 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -961,8 +961,8 @@ extern ctl_handler sysctl_ms_jiffies; /* * Register a set of sysctl names by calling register_sysctl_table * with an initialised array of ctl_table's. An entry with zero - * ctl_name terminates the table. table->de will be set up by the - * registration and need not be initialised in advance. + * ctl_name and NULL procname terminates the table. table->de will be + * set up by the registration and need not be initialised in advance. * * sysctl names can be mirrored automatically under /proc/sys. The * procname supplied controls /proc naming. @@ -973,7 +973,10 @@ extern ctl_handler sysctl_ms_jiffies; * Leaf nodes in the sysctl tree will be represented by a single file * under /proc; non-leaf nodes will be represented by directories. A * null procname disables /proc mirroring at this node. - * + * + * sysctl entries with a zero ctl_name will not be available through + * the binary sysctl interface. + * * sysctl(2) can automatically manage read and write requests through * the sysctl table. The data and maxlen fields of the ctl_table * struct enable minimal validation of the values being written to be -- cgit v1.2.3 From 7cc13edc139108bb527b692f0548dce6bc648572 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 5 Nov 2006 23:52:13 -0800 Subject: [PATCH] sysctl: implement CTL_UNNUMBERED This patch takes the CTL_UNNUMBERD concept from NFS and makes it available to all new sysctl users. At the same time the sysctl binary interface maintenance documentation is updated to mention and to describe what is needed to successfully maintain the sysctl binary interface. Signed-off-by: Eric W. Biederman Acked-by: Alan Cox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sysctl.h | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index c184732a70fc..d98562f1df76 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -6,10 +6,17 @@ **************************************************************** **************************************************************** ** + ** WARNING: ** The values in this file are exported to user space via - ** the sysctl() binary interface. However this interface - ** is unstable and deprecated and will be removed in the future. - ** For a stable interface use /proc/sys. + ** the sysctl() binary interface. Do *NOT* change the + ** numbering of any existing values here, and do not change + ** any numbers within any one set of values. If you have to + ** have to redefine an existing interface, use a new number for it. + ** The kernel will then return -ENOTDIR to any application using + ** the old binary interface. + ** + ** For new interfaces unless you really need a binary number + ** please use CTL_UNNUMBERED. ** **************************************************************** **************************************************************** @@ -48,6 +55,7 @@ struct __sysctl_args { #ifdef __KERNEL__ #define CTL_ANY -1 /* Matches any name */ #define CTL_NONE 0 +#define CTL_UNNUMBERED CTL_NONE /* sysctl without a binary number */ #endif enum -- cgit v1.2.3 From 81ac95c5569d7a60ab5db6c1ccec56c12b3ebcb5 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Wed, 8 Nov 2006 17:44:40 -0800 Subject: [PATCH] nfsd4: fix open-create permissions In the case where an open creates the file, we shouldn't be rechecking permissions to open the file; the open succeeds regardless of what the new file's mode bits say. This patch fixes the problem, but only by introducing yet another parameter to nfsd_create_v3. This is ugly. This will be fixed by later patches. Signed-off-by: J. Bruce Fields Acked-by: Neil Brown Cc: Jeff Garzik Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nfsd/nfsd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfsd/nfsd.h b/include/linux/nfsd/nfsd.h index eb231143d579..edb54c3171b3 100644 --- a/include/linux/nfsd/nfsd.h +++ b/include/linux/nfsd/nfsd.h @@ -89,7 +89,7 @@ __be32 nfsd_access(struct svc_rqst *, struct svc_fh *, u32 *, u32 *); __be32 nfsd_create_v3(struct svc_rqst *, struct svc_fh *, char *name, int len, struct iattr *attrs, struct svc_fh *res, int createmode, - u32 *verifier, int *truncp); + u32 *verifier, int *truncp, int *created); __be32 nfsd_commit(struct svc_rqst *, struct svc_fh *, loff_t, unsigned long); #endif /* CONFIG_NFSD_V3 */ -- cgit v1.2.3 From 46d52b09fa6a2d1e313cb75ca352d6f466e67bd1 Mon Sep 17 00:00:00 2001 From: Corey Minyard Date: Wed, 8 Nov 2006 17:44:55 -0800 Subject: [PATCH] IPMI: retry messages on certain error returns Some more errors from the IPMI send message command are retryable, but are not being retried by the IPMI code. Make sure they get retried. Signed-off-by: Corey Minyard Cc: Frederic Lelievre Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ipmi_msgdefs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ipmi_msgdefs.h b/include/linux/ipmi_msgdefs.h index 22f5e2afda4f..4d04d8b58a0a 100644 --- a/include/linux/ipmi_msgdefs.h +++ b/include/linux/ipmi_msgdefs.h @@ -75,6 +75,8 @@ #define IPMI_INVALID_COMMAND_ERR 0xc1 #define IPMI_ERR_MSG_TRUNCATED 0xc6 #define IPMI_LOST_ARBITRATION_ERR 0x81 +#define IPMI_BUS_ERR 0x82 +#define IPMI_NAK_ON_WRITE_ERR 0x83 #define IPMI_ERR_UNSPECIFIED 0xff #define IPMI_CHANNEL_PROTOCOL_IPMB 1 -- cgit v1.2.3 From ec68307cc5a8dc499e48693843bb42f6b6028458 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 8 Nov 2006 17:44:57 -0800 Subject: [PATCH] htirq: refactor so we only have one function that writes to the chip This refactoring actually optimizes the code a little by caching the value that we think the device is programmed with instead of reading it back from the hardware. Which simplifies the code a little and should speed things up a bit. This patch introduces the concept of a ht_irq_msg and modifies the architecture read/write routines to update this code. There is a minor consistency fix here as well as x86_64 forgot to initialize the htirq as masked. Signed-off-by: Eric W. Biederman Cc: Andi Kleen Acked-by: Bryan O'Sullivan Cc: Cc: Roland Dreier Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/htirq.h | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/htirq.h b/include/linux/htirq.h index 1f15ce279a23..108f0d91e11e 100644 --- a/include/linux/htirq.h +++ b/include/linux/htirq.h @@ -1,11 +1,14 @@ #ifndef LINUX_HTIRQ_H #define LINUX_HTIRQ_H +struct ht_irq_msg { + u32 address_lo; /* low 32 bits of the ht irq message */ + u32 address_hi; /* high 32 bits of the it irq message */ +}; + /* Helper functions.. */ -void write_ht_irq_low(unsigned int irq, u32 data); -void write_ht_irq_high(unsigned int irq, u32 data); -u32 read_ht_irq_low(unsigned int irq); -u32 read_ht_irq_high(unsigned int irq); +void fetch_ht_irq_msg(unsigned int irq, struct ht_irq_msg *msg); +void write_ht_irq_msg(unsigned int irq, struct ht_irq_msg *msg); void mask_ht_irq(unsigned int irq); void unmask_ht_irq(unsigned int irq); -- cgit v1.2.3 From 43539c38cd8edb915d1f0e1f55dcb70638b4cc8e Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 8 Nov 2006 17:44:57 -0800 Subject: [PATCH] htirq: allow buggy drivers of buggy hardware to write the registers This patch adds a variant of ht_create_irq __ht_create_irq that takes an aditional parameter update that is a function that is called whenever we want to write to a drivers htirq configuration registers. This is needed to support the ipath_iba6110 because it's registers in the proper location are not actually conected to the hardware that controlls interrupt delivery. [bos@serpentine.com: fixes] Signed-off-by: Eric W. Biederman Cc: Andi Kleen Cc: Cc: Roland Dreier Signed-off-by: Bryan O'Sullivan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/htirq.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/htirq.h b/include/linux/htirq.h index 108f0d91e11e..c96ea46737d0 100644 --- a/include/linux/htirq.h +++ b/include/linux/htirq.h @@ -15,4 +15,9 @@ void unmask_ht_irq(unsigned int irq); /* The arch hook for getting things started */ int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev); +/* For drivers of buggy hardware */ +typedef void (ht_irq_update_t)(struct pci_dev *dev, int irq, + struct ht_irq_msg *msg); +int __ht_create_irq(struct pci_dev *dev, int idx, ht_irq_update_t *update); + #endif /* LINUX_HTIRQ_H */ -- cgit v1.2.3 From a9b14973a8c42b2aecc968851372203c6567e196 Mon Sep 17 00:00:00 2001 From: Andy Fleming Date: Thu, 19 Oct 2006 19:52:26 -0500 Subject: [PATCH] Slight refactor of interrupt mapping for FSL parts * Cleaned up interrupt mapping a little by adding a helper function which parses the irq out of the device-tree, and puts it into a resource. * Changed the arch/ppc platform files to specify PHY_POLL, instead of -1 * Changed the fixed phy to use PHY_IGNORE_INTERRUPT * Added ethtool.h and mii.h to phy.h includes Signed-off-by: Paul Mackerras --- include/linux/phy.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 9447a57ee8a9..892d6abe57e5 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -20,6 +20,9 @@ #include #include +#include +#include +#include #define PHY_BASIC_FEATURES (SUPPORTED_10baseT_Half | \ SUPPORTED_10baseT_Full | \ -- cgit v1.2.3 From 2b4ac44e7c7e16cf9411b81693ff3e604f332bf1 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 10 Nov 2006 12:27:48 -0800 Subject: [PATCH] vmalloc: optimization, cleanup, bugfixes - reorder 'struct vm_struct' to speedup lookups on CPUS with small cache lines. The fields 'next,addr,size' should be now in the same cache line, to speedup lookups. - One minor cleanup in __get_vm_area_node() - Bugfixes in vmalloc_user() and vmalloc_32_user() NULL returns from __vmalloc() and __find_vm_area() were not tested. [akpm@osdl.org: remove redundant BUG_ONs] Signed-off-by: Eric Dumazet Cc: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index dc9a29d84abc..924e502905d4 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -23,13 +23,14 @@ struct vm_area_struct; #endif struct vm_struct { + /* keep next,addr,size together to speedup lookups */ + struct vm_struct *next; void *addr; unsigned long size; unsigned long flags; struct page **pages; unsigned int nr_pages; unsigned long phys_addr; - struct vm_struct *next; }; /* -- cgit v1.2.3 From d8b295f29091310d746509bb6d5828aaf4907a18 Mon Sep 17 00:00:00 2001 From: Russell King Date: Fri, 10 Nov 2006 12:27:53 -0800 Subject: [PATCH] Fix missing parens in set_personality() If you call set_personality() with an expression such as: set_personality(foo ? PERS_FOO1 : PERS_FOO2); then this evaluates to: ((current->personality == foo ? PERS_FOO1 : PERS_FOO2) ? ... which is obviously not the intended result. Add the missing parents to ensure this gets evaluated as expected: ((current->personality == (foo ? PERS_FOO1 : PERS_FOO2)) ? ... Signed-off-by: Russell King Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/personality.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/personality.h b/include/linux/personality.h index bf4cf2080e5c..012cd558189b 100644 --- a/include/linux/personality.h +++ b/include/linux/personality.h @@ -114,7 +114,7 @@ struct exec_domain { * Change personality of the currently running process. */ #define set_personality(pers) \ - ((current->personality == pers) ? 0 : __set_personality(pers)) + ((current->personality == (pers)) ? 0 : __set_personality(pers)) #endif /* __KERNEL__ */ -- cgit v1.2.3 From 68589bc353037f233fe510ad9ff432338c95db66 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Tue, 14 Nov 2006 02:03:32 -0800 Subject: [PATCH] hugetlb: prepare_hugepage_range check offset too (David:) If hugetlbfs_file_mmap() returns a failure to do_mmap_pgoff() - for example, because the given file offset is not hugepage aligned - then do_mmap_pgoff will go to the unmap_and_free_vma backout path. But at this stage the vma hasn't been marked as hugepage, and the backout path will call unmap_region() on it. That will eventually call down to the non-hugepage version of unmap_page_range(). On ppc64, at least, that will cause serious problems if there are any existing hugepage pagetable entries in the vicinity - for example if there are any other hugepage mappings under the same PUD. unmap_page_range() will trigger a bad_pud() on the hugepage pud entries. I suspect this will also cause bad problems on ia64, though I don't have a machine to test it on. (Hugh:) prepare_hugepage_range() should check file offset alignment when it checks virtual address and length, to stop MAP_FIXED with a bad huge offset from unmapping before it fails further down. PowerPC should apply the same prepare_hugepage_range alignment checks as ia64 and all the others do. Then none of the alignment checks in hugetlbfs_file_mmap are required (nor is the check for too small a mapping); but even so, move up setting of VM_HUGETLB and add a comment to warn of what David Gibson discovered - if hugetlbfs_file_mmap fails before setting it, do_mmap_pgoff's unmap_region when unwinding from error will go the non-huge way, which may cause bad behaviour on architectures (powerpc and ia64) which segregate their huge mappings into a separate region of the address space. Signed-off-by: Hugh Dickins Cc: "Luck, Tony" Cc: "David S. Miller" Acked-by: Adam Litke Acked-by: David Gibson Cc: Paul Mackerras Cc: Benjamin Herrenschmidt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 5081d27bfa27..ace64e57e17f 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -60,8 +60,11 @@ void hugetlb_free_pgd_range(struct mmu_gather **tlb, unsigned long addr, * 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) +static inline int prepare_hugepage_range(unsigned long addr, unsigned long len, + pgoff_t pgoff) { + if (pgoff & (~HPAGE_MASK >> PAGE_SHIFT)) + return -EINVAL; if (len & ~HPAGE_MASK) return -EINVAL; if (addr & ~HPAGE_MASK) @@ -69,7 +72,8 @@ static inline int prepare_hugepage_range(unsigned long addr, unsigned long len) return 0; } #else -int prepare_hugepage_range(unsigned long addr, unsigned long len); +int prepare_hugepage_range(unsigned long addr, unsigned long len, + pgoff_t pgoff); #endif #ifndef ARCH_HAS_SETCLEAR_HUGE_PTE @@ -107,7 +111,7 @@ 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 prepare_hugepage_range(addr, len) (-EINVAL) +#define prepare_hugepage_range(addr,len,pgoff) (-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) ({BUG(); 0; }) -- cgit v1.2.3 From b96e7ecbd052a0916b6078e7600604d7e276a336 Mon Sep 17 00:00:00 2001 From: Yasuyuki Kozakai Date: Tue, 14 Nov 2006 19:48:48 -0800 Subject: [NETFILTER]: ip6_tables: fixed conflicted optname for getsockopt 66 and 67 for getsockopt on IPv6 socket is doubly used for IPv6 Advanced API and ip6tables. This moves numbers for ip6tables to 68 and 69. This also kills XT_SO_* because {ip,ip6,arp}_tables doesn't have so much common numbers now. The old userland tools keep to behave as ever, because old kernel always calls functions of IPv6 Advanced API for their numbers. Signed-off-by: Yasuyuki Kozakai Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/in6.h | 12 +++++++++++- include/linux/netfilter/x_tables.h | 16 ---------------- include/linux/netfilter_arp/arp_tables.h | 25 +++++++++++++------------ include/linux/netfilter_ipv4/ip_tables.h | 27 +++++++++++++++------------ include/linux/netfilter_ipv6/ip6_tables.h | 27 +++++++++++++++------------ 5 files changed, 54 insertions(+), 53 deletions(-) (limited to 'include/linux') diff --git a/include/linux/in6.h b/include/linux/in6.h index 9be6a4756f0b..f28621f638e0 100644 --- a/include/linux/in6.h +++ b/include/linux/in6.h @@ -225,7 +225,7 @@ struct in6_flowlabel_req #endif /* - * Netfilter + * Netfilter (1) * * Following socket options are used in ip6_tables; * see include/linux/netfilter_ipv6/ip6_tables.h. @@ -240,4 +240,14 @@ struct in6_flowlabel_req #define IPV6_RECVTCLASS 66 #define IPV6_TCLASS 67 +/* + * Netfilter (2) + * + * Following socket options are used in ip6_tables; + * see include/linux/netfilter_ipv6/ip6_tables.h. + * + * IP6T_SO_GET_REVISION_MATCH 68 + * IP6T_SO_GET_REVISION_TARGET 69 + */ + #endif diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 04319a76103a..022edfa97ed9 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -96,22 +96,6 @@ struct _xt_align /* Error verdict. */ #define XT_ERROR_TARGET "ERROR" -/* - * New IP firewall options for [gs]etsockopt at the RAW IP level. - * Unlike BSD Linux inherits IP options so you don't have to use a raw - * socket for this. Instead we check rights in the calls. */ -#define XT_BASE_CTL 64 /* base for firewall socket options */ - -#define XT_SO_SET_REPLACE (XT_BASE_CTL) -#define XT_SO_SET_ADD_COUNTERS (XT_BASE_CTL + 1) -#define XT_SO_SET_MAX XT_SO_SET_ADD_COUNTERS - -#define XT_SO_GET_INFO (XT_BASE_CTL) -#define XT_SO_GET_ENTRIES (XT_BASE_CTL + 1) -#define XT_SO_GET_REVISION_MATCH (XT_BASE_CTL + 2) -#define XT_SO_GET_REVISION_TARGET (XT_BASE_CTL + 3) -#define XT_SO_GET_MAX XT_SO_GET_REVISION_TARGET - #define SET_COUNTER(c,b,p) do { (c).bcnt = (b); (c).pcnt = (p); } while(0) #define ADD_COUNTER(c,b,p) do { (c).bcnt += (b); (c).pcnt += (p); } while(0) diff --git a/include/linux/netfilter_arp/arp_tables.h b/include/linux/netfilter_arp/arp_tables.h index 44e39b61d9e7..0be235418a2f 100644 --- a/include/linux/netfilter_arp/arp_tables.h +++ b/include/linux/netfilter_arp/arp_tables.h @@ -112,19 +112,20 @@ struct arpt_entry * New IP firewall options for [gs]etsockopt at the RAW IP level. * Unlike BSD Linux inherits IP options so you don't have to use a raw * socket for this. Instead we check rights in the calls. + * + * ATTENTION: check linux/in.h before adding new number here. */ -#define ARPT_CTL_OFFSET 32 -#define ARPT_BASE_CTL (XT_BASE_CTL+ARPT_CTL_OFFSET) - -#define ARPT_SO_SET_REPLACE (XT_SO_SET_REPLACE+ARPT_CTL_OFFSET) -#define ARPT_SO_SET_ADD_COUNTERS (XT_SO_SET_ADD_COUNTERS+ARPT_CTL_OFFSET) -#define ARPT_SO_SET_MAX (XT_SO_SET_MAX+ARPT_CTL_OFFSET) - -#define ARPT_SO_GET_INFO (XT_SO_GET_INFO+ARPT_CTL_OFFSET) -#define ARPT_SO_GET_ENTRIES (XT_SO_GET_ENTRIES+ARPT_CTL_OFFSET) -/* #define ARPT_SO_GET_REVISION_MATCH XT_SO_GET_REVISION_MATCH */ -#define ARPT_SO_GET_REVISION_TARGET (XT_SO_GET_REVISION_TARGET+ARPT_CTL_OFFSET) -#define ARPT_SO_GET_MAX (XT_SO_GET_REVISION_TARGET+ARPT_CTL_OFFSET) +#define ARPT_BASE_CTL 96 + +#define ARPT_SO_SET_REPLACE (ARPT_BASE_CTL) +#define ARPT_SO_SET_ADD_COUNTERS (ARPT_BASE_CTL + 1) +#define ARPT_SO_SET_MAX ARPT_SO_SET_ADD_COUNTERS + +#define ARPT_SO_GET_INFO (ARPT_BASE_CTL) +#define ARPT_SO_GET_ENTRIES (ARPT_BASE_CTL + 1) +/* #define ARPT_SO_GET_REVISION_MATCH (APRT_BASE_CTL + 2) */ +#define ARPT_SO_GET_REVISION_TARGET (ARPT_BASE_CTL + 3) +#define ARPT_SO_GET_MAX (ARPT_SO_GET_REVISION_TARGET) /* CONTINUE verdict for targets */ #define ARPT_CONTINUE XT_CONTINUE diff --git a/include/linux/netfilter_ipv4/ip_tables.h b/include/linux/netfilter_ipv4/ip_tables.h index a536bbdef145..4f06dad0bde9 100644 --- a/include/linux/netfilter_ipv4/ip_tables.h +++ b/include/linux/netfilter_ipv4/ip_tables.h @@ -101,18 +101,21 @@ struct ipt_entry /* * New IP firewall options for [gs]etsockopt at the RAW IP level. * Unlike BSD Linux inherits IP options so you don't have to use a raw - * socket for this. Instead we check rights in the calls. */ -#define IPT_BASE_CTL XT_BASE_CTL - -#define IPT_SO_SET_REPLACE XT_SO_SET_REPLACE -#define IPT_SO_SET_ADD_COUNTERS XT_SO_SET_ADD_COUNTERS -#define IPT_SO_SET_MAX XT_SO_SET_MAX - -#define IPT_SO_GET_INFO XT_SO_GET_INFO -#define IPT_SO_GET_ENTRIES XT_SO_GET_ENTRIES -#define IPT_SO_GET_REVISION_MATCH XT_SO_GET_REVISION_MATCH -#define IPT_SO_GET_REVISION_TARGET XT_SO_GET_REVISION_TARGET -#define IPT_SO_GET_MAX XT_SO_GET_REVISION_TARGET + * socket for this. Instead we check rights in the calls. + * + * ATTENTION: check linux/in.h before adding new number here. + */ +#define IPT_BASE_CTL 64 + +#define IPT_SO_SET_REPLACE (IPT_BASE_CTL) +#define IPT_SO_SET_ADD_COUNTERS (IPT_BASE_CTL + 1) +#define IPT_SO_SET_MAX IPT_SO_SET_ADD_COUNTERS + +#define IPT_SO_GET_INFO (IPT_BASE_CTL) +#define IPT_SO_GET_ENTRIES (IPT_BASE_CTL + 1) +#define IPT_SO_GET_REVISION_MATCH (IPT_BASE_CTL + 2) +#define IPT_SO_GET_REVISION_TARGET (IPT_BASE_CTL + 3) +#define IPT_SO_GET_MAX IPT_SO_GET_REVISION_TARGET #define IPT_CONTINUE XT_CONTINUE #define IPT_RETURN XT_RETURN diff --git a/include/linux/netfilter_ipv6/ip6_tables.h b/include/linux/netfilter_ipv6/ip6_tables.h index d7a8e9c0dad0..4aed340401db 100644 --- a/include/linux/netfilter_ipv6/ip6_tables.h +++ b/include/linux/netfilter_ipv6/ip6_tables.h @@ -107,18 +107,21 @@ struct ip6t_entry /* * New IP firewall options for [gs]etsockopt at the RAW IP level. * Unlike BSD Linux inherits IP options so you don't have to use - * a raw socket for this. Instead we check rights in the calls. */ -#define IP6T_BASE_CTL XT_BASE_CTL - -#define IP6T_SO_SET_REPLACE XT_SO_SET_REPLACE -#define IP6T_SO_SET_ADD_COUNTERS XT_SO_SET_ADD_COUNTERS -#define IP6T_SO_SET_MAX XT_SO_SET_MAX - -#define IP6T_SO_GET_INFO XT_SO_GET_INFO -#define IP6T_SO_GET_ENTRIES XT_SO_GET_ENTRIES -#define IP6T_SO_GET_REVISION_MATCH XT_SO_GET_REVISION_MATCH -#define IP6T_SO_GET_REVISION_TARGET XT_SO_GET_REVISION_TARGET -#define IP6T_SO_GET_MAX XT_SO_GET_REVISION_TARGET + * a raw socket for this. Instead we check rights in the calls. + * + * ATTENTION: check linux/in6.h before adding new number here. + */ +#define IP6T_BASE_CTL 64 + +#define IP6T_SO_SET_REPLACE (IP6T_BASE_CTL) +#define IP6T_SO_SET_ADD_COUNTERS (IP6T_BASE_CTL + 1) +#define IP6T_SO_SET_MAX IP6T_SO_SET_ADD_COUNTERS + +#define IP6T_SO_GET_INFO (IP6T_BASE_CTL) +#define IP6T_SO_GET_ENTRIES (IP6T_BASE_CTL + 1) +#define IP6T_SO_GET_REVISION_MATCH (IP6T_BASE_CTL + 4) +#define IP6T_SO_GET_REVISION_TARGET (IP6T_BASE_CTL + 5) +#define IP6T_SO_GET_MAX IP6T_SO_GET_REVISION_TARGET /* CONTINUE verdict for targets */ #define IP6T_CONTINUE XT_CONTINUE -- cgit v1.2.3 From c7835a77c86422d276b0d1a4c70924d933014c13 Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Wed, 15 Nov 2006 21:14:42 -0800 Subject: [TG3]: Disable TSO on 5906 if CLKREQ is enabled. Due to hardware errata, TSO must be disabled if the PCI Express clock request is enabled on 5906. The chip may hang when transmitting TSO frames if CLKREQ is enabled. Update version to 3.69. Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- include/linux/pci_regs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci_regs.h b/include/linux/pci_regs.h index c312a12ad2d6..c321316f1bc7 100644 --- a/include/linux/pci_regs.h +++ b/include/linux/pci_regs.h @@ -371,6 +371,7 @@ #define PCI_EXP_DEVSTA_TRPND 0x20 /* Transactions Pending */ #define PCI_EXP_LNKCAP 12 /* Link Capabilities */ #define PCI_EXP_LNKCTL 16 /* Link Control */ +#define PCI_EXP_LNKCTL_CLKREQ_EN 0x100 /* Enable clkreq */ #define PCI_EXP_LNKSTA 18 /* Link Status */ #define PCI_EXP_SLTCAP 20 /* Slot Capabilities */ #define PCI_EXP_SLTCTL 24 /* Slot Control */ -- cgit v1.2.3 From da63fc7ce63b43426dc3c69c05e28de2872c159a Mon Sep 17 00:00:00 2001 From: OGAWA Hirofumi Date: Thu, 16 Nov 2006 01:19:28 -0800 Subject: [PATCH] fat: add fat_getattr() This adds fat_getattr() for setting stat->blksize. (FAT uses the size of cluster for proper I/O) Signed-off-by: OGAWA Hirofumi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/msdos_fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/msdos_fs.h b/include/linux/msdos_fs.h index ce6c85815cbd..24a9ef1506b6 100644 --- a/include/linux/msdos_fs.h +++ b/include/linux/msdos_fs.h @@ -402,6 +402,8 @@ extern const struct file_operations fat_file_operations; extern struct inode_operations fat_file_inode_operations; extern int fat_notify_change(struct dentry * dentry, struct iattr * attr); extern void fat_truncate(struct inode *inode); +extern int fat_getattr(struct vfsmount *mnt, struct dentry *dentry, + struct kstat *stat); /* fat/inode.c */ extern void fat_attach(struct inode *inode, loff_t i_pos); -- cgit v1.2.3 From 9d92fe17b652f5496c97bc83fdfe925f3182f602 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Fri, 17 Nov 2006 01:07:39 -0500 Subject: Input: serio - remove serio_unregister_port_delayed() Now that i8042 reserves IRQs early there are no more users of this function and it should be removed. Signed-off-by: Dmitry Torokhov --- include/linux/serio.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/serio.h b/include/linux/serio.h index b99c5ca9708d..8f52228390ab 100644 --- a/include/linux/serio.h +++ b/include/linux/serio.h @@ -85,11 +85,6 @@ static inline void serio_register_port(struct serio *serio) void serio_unregister_port(struct serio *serio); void serio_unregister_child_port(struct serio *serio); -void __serio_unregister_port_delayed(struct serio *serio, struct module *owner); -static inline void serio_unregister_port_delayed(struct serio *serio) -{ - __serio_unregister_port_delayed(serio, THIS_MODULE); -} void __serio_register_driver(struct serio_driver *drv, struct module *owner); static inline void serio_register_driver(struct serio_driver *drv) -- cgit v1.2.3 From 610a5b742e9df4e59047f22d13d8bd83cafce388 Mon Sep 17 00:00:00 2001 From: Yoichi Yuasa Date: Fri, 17 Nov 2006 11:51:41 +1100 Subject: [CRYPTO] api: Remove one too many semicolon This patch has removed one too many semicolon in crypto.h. Signed-off-by: Yoichi Yuasa Signed-off-by: Herbert Xu --- include/linux/crypto.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index 8f2ffa4caabf..6485e9716b36 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -245,7 +245,7 @@ int crypto_alg_available(const char *name, u32 flags) __deprecated_for_modules; int crypto_has_alg(const char *name, u32 type, u32 mask); #else -static int crypto_alg_available(const char *name, u32 flags); +static int crypto_alg_available(const char *name, u32 flags) __deprecated_for_modules; static inline int crypto_alg_available(const char *name, u32 flags) { -- cgit v1.2.3 From b3438f8266cb1f5010085ac47d7ad6a36a212164 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 20 Nov 2006 11:47:18 -0800 Subject: Add "pure_initcall" for static variable initialization This is a quick hack to overcome the fact that SRCU currently does not allow static initializers, and we need to sometimes initialize those things before any other initializers (even "core" ones) can do so. Currently we don't allow this at all for modules, and the only user that needs is right now is cpufreq. As reported by Thomas Gleixner: "Commit b4dfdbb3c707474a2254c5b4d7e62be31a4b7da9 ("[PATCH] cpufreq: make the transition_notifier chain use SRCU breaks cpu frequency notification users, which register the callback > on core_init level." Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Arjan van de Ven Cc: Andrew Morton , Signed-off-by: Linus Torvalds --- include/linux/init.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/init.h b/include/linux/init.h index ff40ea118e3a..5eb5d24b7680 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -93,6 +93,14 @@ extern void setup_arch(char **); static initcall_t __initcall_##fn##id __attribute_used__ \ __attribute__((__section__(".initcall" level ".init"))) = fn +/* + * A "pure" initcall has no dependencies on anything else, and purely + * initializes variables that couldn't be statically initialized. + * + * This only exists for built-in code, not for modules. + */ +#define pure_initcall(fn) __define_initcall("0",fn,1) + #define core_initcall(fn) __define_initcall("1",fn,1) #define core_initcall_sync(fn) __define_initcall("1s",fn,1s) #define postcore_initcall(fn) __define_initcall("2",fn,2) -- cgit v1.2.3 From fb47ddb2db9c18664bd7b06c201a2398885b64fc Mon Sep 17 00:00:00 2001 From: David L Stevens Date: Sun, 19 Nov 2006 10:38:39 -0800 Subject: [IGMP]: Fix IGMPV3_EXP() normalization bit shift value. The IGMPV3_EXP() macro doesn't correctly shift the normalization bit, so time-out values are longer than they should be. Thanks to Dirk Ooms for finding the problem in IGMPv3 - MLDv2 had a similar problem that was already fixed a year ago. :-( Signed-off-by: David L Stevens Signed-off-by: David S. Miller --- include/linux/igmp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/igmp.h b/include/linux/igmp.h index 03f43e2893a4..21dd56905271 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -191,7 +191,7 @@ struct ip_mc_list #define IGMPV3_MASK(value, nb) ((nb)>=32 ? (value) : ((1<<(nb))-1) & (value)) #define IGMPV3_EXP(thresh, nbmant, nbexp, value) \ ((value) < (thresh) ? (value) : \ - ((IGMPV3_MASK(value, nbmant) | (1<<(nbmant+nbexp))) << \ + ((IGMPV3_MASK(value, nbmant) | (1<<(nbmant))) << \ (IGMPV3_MASK((value) >> (nbmant), nbexp) + (nbexp)))) #define IGMPV3_QQIC(value) IGMPV3_EXP(0x80, 4, 3, value) -- cgit v1.2.3 From 52bad64d95bd89e08c49ec5a071fa6dcbe5a1a9c Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 22 Nov 2006 14:54:01 +0000 Subject: WorkStruct: Separate delayable and non-delayable events. Separate delayable work items from non-delayable work items be splitting them into a separate structure (delayed_work), which incorporates a work_struct and the timer_list removed from work_struct. The work_struct struct is huge, and this limits it's usefulness. On a 64-bit architecture it's nearly 100 bytes in size. This reduces that by half for the non-delayable type of event. Signed-Off-By: David Howells --- include/linux/aio.h | 2 +- include/linux/kbd_kern.h | 2 +- include/linux/libata.h | 4 ++-- include/linux/nfs_fs_sb.h | 2 +- include/linux/sunrpc/rpc_pipe_fs.h | 2 +- include/linux/sunrpc/xprt.h | 2 +- include/linux/tty.h | 2 +- include/linux/workqueue.h | 44 +++++++++++++++++++++++++++----------- 8 files changed, 40 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/aio.h b/include/linux/aio.h index 0d71c0041f13..9e350fd44d77 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -194,7 +194,7 @@ struct kioctx { struct aio_ring_info ring_info; - struct work_struct wq; + struct delayed_work wq; }; /* prototypes */ diff --git a/include/linux/kbd_kern.h b/include/linux/kbd_kern.h index efe0ee4cc80b..06c58c423fe1 100644 --- a/include/linux/kbd_kern.h +++ b/include/linux/kbd_kern.h @@ -158,7 +158,7 @@ static inline void con_schedule_flip(struct tty_struct *t) if (t->buf.tail != NULL) t->buf.tail->commit = t->buf.tail->used; spin_unlock_irqrestore(&t->buf.lock, flags); - schedule_work(&t->buf.work); + schedule_delayed_work(&t->buf.work, 0); } #endif diff --git a/include/linux/libata.h b/include/linux/libata.h index abd2debebca2..5f04006e8dd2 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -568,8 +568,8 @@ struct ata_port { struct ata_host *host; struct device *dev; - struct work_struct port_task; - struct work_struct hotplug_task; + struct delayed_work port_task; + struct delayed_work hotplug_task; struct work_struct scsi_rescan_task; unsigned int hsm_task_state; diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 7ccfc7ef0a83..95796e6924f1 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -51,7 +51,7 @@ struct nfs_client { unsigned long cl_lease_time; unsigned long cl_last_renewal; - struct work_struct cl_renewd; + struct delayed_work cl_renewd; struct rpc_wait_queue cl_rpcwaitq; diff --git a/include/linux/sunrpc/rpc_pipe_fs.h b/include/linux/sunrpc/rpc_pipe_fs.h index a2eb9b4a9de3..4a68125b6de6 100644 --- a/include/linux/sunrpc/rpc_pipe_fs.h +++ b/include/linux/sunrpc/rpc_pipe_fs.h @@ -30,7 +30,7 @@ struct rpc_inode { #define RPC_PIPE_WAIT_FOR_OPEN 1 int flags; struct rpc_pipe_ops *ops; - struct work_struct queue_timeout; + struct delayed_work queue_timeout; }; static inline struct rpc_inode * diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 60394fbc4c70..3e04c1512fc4 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -177,7 +177,7 @@ struct rpc_xprt { unsigned long connect_timeout, bind_timeout, reestablish_timeout; - struct work_struct connect_worker; + struct delayed_work connect_worker; unsigned short port; /* diff --git a/include/linux/tty.h b/include/linux/tty.h index 44091c0db0b4..c1f716446161 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -53,7 +53,7 @@ struct tty_buffer { }; struct tty_bufhead { - struct work_struct work; + struct delayed_work work; struct semaphore pty_sem; spinlock_t lock; struct tty_buffer *head; /* Queue head */ diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 9bca3539a1e5..9faaccae570e 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -17,6 +17,10 @@ struct work_struct { void (*func)(void *); void *data; void *wq_data; +}; + +struct delayed_work { + struct work_struct work; struct timer_list timer; }; @@ -28,32 +32,48 @@ struct execute_work { .entry = { &(n).entry, &(n).entry }, \ .func = (f), \ .data = (d), \ + } + +#define __DELAYED_WORK_INITIALIZER(n, f, d) { \ + .work = __WORK_INITIALIZER((n).work, (f), (d)), \ .timer = TIMER_INITIALIZER(NULL, 0, 0), \ } #define DECLARE_WORK(n, f, d) \ struct work_struct n = __WORK_INITIALIZER(n, f, d) +#define DECLARE_DELAYED_WORK(n, f, d) \ + struct delayed_work n = __DELAYED_WORK_INITIALIZER(n, f, d) + /* - * initialize a work-struct's func and data pointers: + * initialize a work item's function and data pointers */ #define PREPARE_WORK(_work, _func, _data) \ do { \ - (_work)->func = _func; \ - (_work)->data = _data; \ + (_work)->func = (_func); \ + (_work)->data = (_data); \ } while (0) +#define PREPARE_DELAYED_WORK(_work, _func, _data) \ + PREPARE_WORK(&(_work)->work, (_func), (_data)) + /* - * initialize all of a work-struct: + * initialize all of a work item in one go */ #define INIT_WORK(_work, _func, _data) \ do { \ INIT_LIST_HEAD(&(_work)->entry); \ (_work)->pending = 0; \ PREPARE_WORK((_work), (_func), (_data)); \ + } while (0) + +#define INIT_DELAYED_WORK(_work, _func, _data) \ + do { \ + INIT_WORK(&(_work)->work, (_func), (_data)); \ init_timer(&(_work)->timer); \ } while (0) + extern struct workqueue_struct *__create_workqueue(const char *name, int singlethread); #define create_workqueue(name) __create_workqueue((name), 0) @@ -62,24 +82,24 @@ extern struct workqueue_struct *__create_workqueue(const char *name, extern void destroy_workqueue(struct workqueue_struct *wq); extern int FASTCALL(queue_work(struct workqueue_struct *wq, struct work_struct *work)); -extern int FASTCALL(queue_delayed_work(struct workqueue_struct *wq, struct work_struct *work, unsigned long delay)); +extern int FASTCALL(queue_delayed_work(struct workqueue_struct *wq, struct delayed_work *work, unsigned long delay)); extern int queue_delayed_work_on(int cpu, struct workqueue_struct *wq, - struct work_struct *work, unsigned long delay); + struct delayed_work *work, unsigned long delay); extern void FASTCALL(flush_workqueue(struct workqueue_struct *wq)); extern int FASTCALL(schedule_work(struct work_struct *work)); -extern int FASTCALL(schedule_delayed_work(struct work_struct *work, unsigned long delay)); +extern int FASTCALL(schedule_delayed_work(struct delayed_work *work, unsigned long delay)); -extern int schedule_delayed_work_on(int cpu, struct work_struct *work, unsigned long delay); +extern int schedule_delayed_work_on(int cpu, struct delayed_work *work, unsigned long delay); extern int schedule_on_each_cpu(void (*func)(void *info), void *info); extern void flush_scheduled_work(void); extern int current_is_keventd(void); extern int keventd_up(void); extern void init_workqueues(void); -void cancel_rearming_delayed_work(struct work_struct *work); +void cancel_rearming_delayed_work(struct delayed_work *work); void cancel_rearming_delayed_workqueue(struct workqueue_struct *, - struct work_struct *); + struct delayed_work *); int execute_in_process_context(void (*fn)(void *), void *, struct execute_work *); @@ -88,13 +108,13 @@ int execute_in_process_context(void (*fn)(void *), void *, * function may still be running on return from cancel_delayed_work(). Run * flush_scheduled_work() to wait on it. */ -static inline int cancel_delayed_work(struct work_struct *work) +static inline int cancel_delayed_work(struct delayed_work *work) { int ret; ret = del_timer_sync(&work->timer); if (ret) - clear_bit(0, &work->pending); + clear_bit(0, &work->work.pending); return ret; } -- cgit v1.2.3 From 6bb49e5965c1fc399b4d3cd2b5cf2da535b330c0 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 22 Nov 2006 14:54:45 +0000 Subject: WorkStruct: Typedef the work function prototype Define a type for the work function prototype. It's not only kept in the work_struct struct, it's also passed as an argument to several functions. This makes it easier to change it. Signed-Off-By: David Howells --- include/linux/workqueue.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 9faaccae570e..cef40b22ff9a 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -11,10 +11,12 @@ struct workqueue_struct; +typedef void (*work_func_t)(void *data); + struct work_struct { unsigned long pending; struct list_head entry; - void (*func)(void *); + work_func_t func; void *data; void *wq_data; }; @@ -91,7 +93,7 @@ extern int FASTCALL(schedule_work(struct work_struct *work)); extern int FASTCALL(schedule_delayed_work(struct delayed_work *work, unsigned long delay)); extern int schedule_delayed_work_on(int cpu, struct delayed_work *work, unsigned long delay); -extern int schedule_on_each_cpu(void (*func)(void *info), void *info); +extern int schedule_on_each_cpu(work_func_t func, void *info); extern void flush_scheduled_work(void); extern int current_is_keventd(void); extern int keventd_up(void); @@ -100,8 +102,7 @@ extern void init_workqueues(void); void cancel_rearming_delayed_work(struct delayed_work *work); void cancel_rearming_delayed_workqueue(struct workqueue_struct *, struct delayed_work *); -int execute_in_process_context(void (*fn)(void *), void *, - struct execute_work *); +int execute_in_process_context(work_func_t fn, void *, struct execute_work *); /* * Kill off a pending schedule_delayed_work(). Note that the work callback -- cgit v1.2.3 From 365970a1ea76d81cb1ad2f652acb605f06dae256 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 22 Nov 2006 14:54:49 +0000 Subject: WorkStruct: Merge the pending bit into the wq_data pointer Reclaim a word from the size of the work_struct by folding the pending bit and the wq_data pointer together. This shouldn't cause misalignment problems as all pointers should be at least 4-byte aligned. Signed-Off-By: David Howells --- include/linux/workqueue.h | 27 +++++++++++++++++++++++---- 1 file changed, 23 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index cef40b22ff9a..ecc017d24cf3 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -14,11 +14,15 @@ struct workqueue_struct; typedef void (*work_func_t)(void *data); struct work_struct { - unsigned long pending; + /* the first word is the work queue pointer and the pending flag + * rolled into one */ + unsigned long management; +#define WORK_STRUCT_PENDING 0 /* T if work item pending execution */ +#define WORK_STRUCT_FLAG_MASK (3UL) +#define WORK_STRUCT_WQ_DATA_MASK (~WORK_STRUCT_FLAG_MASK) struct list_head entry; work_func_t func; void *data; - void *wq_data; }; struct delayed_work { @@ -65,7 +69,7 @@ struct execute_work { #define INIT_WORK(_work, _func, _data) \ do { \ INIT_LIST_HEAD(&(_work)->entry); \ - (_work)->pending = 0; \ + (_work)->management = 0; \ PREPARE_WORK((_work), (_func), (_data)); \ } while (0) @@ -75,6 +79,21 @@ struct execute_work { init_timer(&(_work)->timer); \ } while (0) +/** + * work_pending - Find out whether a work item is currently pending + * @work: The work item in question + */ +#define work_pending(work) \ + test_bit(WORK_STRUCT_PENDING, &(work)->management) + +/** + * delayed_work_pending - Find out whether a delayable work item is currently + * pending + * @work: The work item in question + */ +#define delayed_work_pending(work) \ + test_bit(WORK_STRUCT_PENDING, &(work)->work.management) + extern struct workqueue_struct *__create_workqueue(const char *name, int singlethread); @@ -115,7 +134,7 @@ static inline int cancel_delayed_work(struct delayed_work *work) ret = del_timer_sync(&work->timer); if (ret) - clear_bit(0, &work->work.pending); + clear_bit(WORK_STRUCT_PENDING, &work->work.management); return ret; } -- cgit v1.2.3 From 65f27f38446e1976cc98fd3004b110fedcddd189 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 22 Nov 2006 14:55:48 +0000 Subject: WorkStruct: Pass the work_struct pointer instead of context data Pass the work_struct pointer to the work function rather than context data. The work function can use container_of() to work out the data. For the cases where the container of the work_struct may go away the moment the pending bit is cleared, it is made possible to defer the release of the structure by deferring the clearing of the pending bit. To make this work, an extra flag is introduced into the management side of the work_struct. This governs auto-release of the structure upon execution. Ordinarily, the work queue executor would release the work_struct for further scheduling or deallocation by clearing the pending bit prior to jumping to the work function. This means that, unless the driver makes some guarantee itself that the work_struct won't go away, the work function may not access anything else in the work_struct or its container lest they be deallocated.. This is a problem if the auxiliary data is taken away (as done by the last patch). However, if the pending bit is *not* cleared before jumping to the work function, then the work function *may* access the work_struct and its container with no problems. But then the work function must itself release the work_struct by calling work_release(). In most cases, automatic release is fine, so this is the default. Special initiators exist for the non-auto-release case (ending in _NAR). Signed-Off-By: David Howells --- include/linux/libata.h | 3 +- include/linux/workqueue.h | 99 +++++++++++++++++++++++++++++++++++------------ 2 files changed, 77 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 5f04006e8dd2..b3f32eadbef5 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -568,6 +568,7 @@ struct ata_port { struct ata_host *host; struct device *dev; + void *port_task_data; struct delayed_work port_task; struct delayed_work hotplug_task; struct work_struct scsi_rescan_task; @@ -747,7 +748,7 @@ 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 *), +extern void ata_port_queue_task(struct ata_port *ap, work_func_t fn, void *data, unsigned long delay); extern u32 ata_wait_register(void __iomem *reg, u32 mask, u32 val, unsigned long interval_msec, diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index ecc017d24cf3..4a3ea83c6d16 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -11,18 +11,19 @@ struct workqueue_struct; -typedef void (*work_func_t)(void *data); +struct work_struct; +typedef void (*work_func_t)(struct work_struct *work); struct work_struct { - /* the first word is the work queue pointer and the pending flag - * rolled into one */ + /* the first word is the work queue pointer and the flags rolled into + * one */ unsigned long management; #define WORK_STRUCT_PENDING 0 /* T if work item pending execution */ +#define WORK_STRUCT_NOAUTOREL 1 /* F if work item automatically released on exec */ #define WORK_STRUCT_FLAG_MASK (3UL) #define WORK_STRUCT_WQ_DATA_MASK (~WORK_STRUCT_FLAG_MASK) struct list_head entry; work_func_t func; - void *data; }; struct delayed_work { @@ -34,48 +35,77 @@ struct execute_work { struct work_struct work; }; -#define __WORK_INITIALIZER(n, f, d) { \ +#define __WORK_INITIALIZER(n, f) { \ + .management = 0, \ .entry = { &(n).entry, &(n).entry }, \ .func = (f), \ - .data = (d), \ } -#define __DELAYED_WORK_INITIALIZER(n, f, d) { \ - .work = __WORK_INITIALIZER((n).work, (f), (d)), \ +#define __WORK_INITIALIZER_NAR(n, f) { \ + .management = (1 << WORK_STRUCT_NOAUTOREL), \ + .entry = { &(n).entry, &(n).entry }, \ + .func = (f), \ + } + +#define __DELAYED_WORK_INITIALIZER(n, f) { \ + .work = __WORK_INITIALIZER((n).work, (f)), \ + .timer = TIMER_INITIALIZER(NULL, 0, 0), \ + } + +#define __DELAYED_WORK_INITIALIZER_NAR(n, f) { \ + .work = __WORK_INITIALIZER_NAR((n).work, (f)), \ .timer = TIMER_INITIALIZER(NULL, 0, 0), \ } -#define DECLARE_WORK(n, f, d) \ - struct work_struct n = __WORK_INITIALIZER(n, f, d) +#define DECLARE_WORK(n, f) \ + struct work_struct n = __WORK_INITIALIZER(n, f) + +#define DECLARE_WORK_NAR(n, f) \ + struct work_struct n = __WORK_INITIALIZER_NAR(n, f) -#define DECLARE_DELAYED_WORK(n, f, d) \ - struct delayed_work n = __DELAYED_WORK_INITIALIZER(n, f, d) +#define DECLARE_DELAYED_WORK(n, f) \ + struct delayed_work n = __DELAYED_WORK_INITIALIZER(n, f) + +#define DECLARE_DELAYED_WORK_NAR(n, f) \ + struct dwork_struct n = __DELAYED_WORK_INITIALIZER_NAR(n, f) /* - * initialize a work item's function and data pointers + * initialize a work item's function pointer */ -#define PREPARE_WORK(_work, _func, _data) \ +#define PREPARE_WORK(_work, _func) \ do { \ (_work)->func = (_func); \ - (_work)->data = (_data); \ } while (0) -#define PREPARE_DELAYED_WORK(_work, _func, _data) \ - PREPARE_WORK(&(_work)->work, (_func), (_data)) +#define PREPARE_DELAYED_WORK(_work, _func) \ + PREPARE_WORK(&(_work)->work, (_func)) /* * initialize all of a work item in one go */ -#define INIT_WORK(_work, _func, _data) \ +#define INIT_WORK(_work, _func) \ do { \ - INIT_LIST_HEAD(&(_work)->entry); \ (_work)->management = 0; \ - PREPARE_WORK((_work), (_func), (_data)); \ + INIT_LIST_HEAD(&(_work)->entry); \ + PREPARE_WORK((_work), (_func)); \ + } while (0) + +#define INIT_WORK_NAR(_work, _func) \ + do { \ + (_work)->management = (1 << WORK_STRUCT_NOAUTOREL); \ + INIT_LIST_HEAD(&(_work)->entry); \ + PREPARE_WORK((_work), (_func)); \ + } while (0) + +#define INIT_DELAYED_WORK(_work, _func) \ + do { \ + INIT_WORK(&(_work)->work, (_func)); \ + init_timer(&(_work)->timer); \ } while (0) -#define INIT_DELAYED_WORK(_work, _func, _data) \ +#define INIT_DELAYED_WORK_NAR(_work, _func) \ do { \ - INIT_WORK(&(_work)->work, (_func), (_data)); \ + INIT_WORK_NAR(&(_work)->work, (_func)); \ init_timer(&(_work)->timer); \ } while (0) @@ -94,6 +124,27 @@ struct execute_work { #define delayed_work_pending(work) \ test_bit(WORK_STRUCT_PENDING, &(work)->work.management) +/** + * work_release - Release a work item under execution + * @work: The work item to release + * + * This is used to release a work item that has been initialised with automatic + * release mode disabled (WORK_STRUCT_NOAUTOREL is set). This gives the work + * function the opportunity to grab auxiliary data from the container of the + * work_struct before clearing the pending bit as the work_struct may be + * subject to deallocation the moment the pending bit is cleared. + * + * In such a case, this should be called in the work function after it has + * fetched any data it may require from the containter of the work_struct. + * After this function has been called, the work_struct may be scheduled for + * further execution or it may be deallocated unless other precautions are + * taken. + * + * This should also be used to release a delayed work item. + */ +#define work_release(work) \ + clear_bit(WORK_STRUCT_PENDING, &(work)->management) + extern struct workqueue_struct *__create_workqueue(const char *name, int singlethread); @@ -112,7 +163,7 @@ extern int FASTCALL(schedule_work(struct work_struct *work)); extern int FASTCALL(schedule_delayed_work(struct delayed_work *work, unsigned long delay)); extern int schedule_delayed_work_on(int cpu, struct delayed_work *work, unsigned long delay); -extern int schedule_on_each_cpu(work_func_t func, void *info); +extern int schedule_on_each_cpu(work_func_t func); extern void flush_scheduled_work(void); extern int current_is_keventd(void); extern int keventd_up(void); @@ -121,7 +172,7 @@ extern void init_workqueues(void); void cancel_rearming_delayed_work(struct delayed_work *work); void cancel_rearming_delayed_workqueue(struct workqueue_struct *, struct delayed_work *); -int execute_in_process_context(work_func_t fn, void *, struct execute_work *); +int execute_in_process_context(work_func_t fn, struct execute_work *); /* * Kill off a pending schedule_delayed_work(). Note that the work callback -- cgit v1.2.3 From c4028958b6ecad064b1a6303a6a5906d4fe48d73 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 22 Nov 2006 14:57:56 +0000 Subject: WorkStruct: make allyesconfig Fix up for make allyesconfig. Signed-Off-By: David Howells --- include/linux/connector.h | 4 ++-- include/linux/i2o.h | 2 +- include/linux/mmc/host.h | 2 +- include/linux/ncp_fs_sb.h | 8 ++++---- include/linux/reiserfs_fs_sb.h | 3 ++- include/linux/relay.h | 2 +- include/linux/usb.h | 2 +- 7 files changed, 12 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/connector.h b/include/linux/connector.h index 4c02119c6ab9..3ea1cd58de97 100644 --- a/include/linux/connector.h +++ b/include/linux/connector.h @@ -133,7 +133,7 @@ struct cn_callback_data { struct cn_callback_entry { struct list_head callback_entry; struct cn_callback *cb; - struct work_struct work; + struct delayed_work work; struct cn_queue_dev *pdev; struct cn_callback_id id; @@ -170,7 +170,7 @@ void cn_queue_free_dev(struct cn_queue_dev *dev); int cn_cb_equal(struct cb_id *, struct cb_id *); -void cn_queue_wrapper(void *data); +void cn_queue_wrapper(struct work_struct *work); extern int cn_already_initialized; diff --git a/include/linux/i2o.h b/include/linux/i2o.h index c115e9e840b4..1fb02e17f6f6 100644 --- a/include/linux/i2o.h +++ b/include/linux/i2o.h @@ -461,7 +461,7 @@ struct i2o_driver { int (*reply) (struct i2o_controller *, u32, struct i2o_message *); /* Event handler */ - void (*event) (struct i2o_event *); + work_func_t event; struct workqueue_struct *event_queue; /* Event queue */ diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 587264a58d56..8b08ef3820f2 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -110,7 +110,7 @@ struct mmc_host { struct mmc_card *card_busy; /* the MMC card claiming host */ struct mmc_card *card_selected; /* the selected MMC card */ - struct work_struct detect; + struct delayed_work detect; unsigned long private[0] ____cacheline_aligned; }; diff --git a/include/linux/ncp_fs_sb.h b/include/linux/ncp_fs_sb.h index b089d9506283..a503052138bd 100644 --- a/include/linux/ncp_fs_sb.h +++ b/include/linux/ncp_fs_sb.h @@ -127,10 +127,10 @@ struct ncp_server { } unexpected_packet; }; -extern void ncp_tcp_rcv_proc(void *server); -extern void ncp_tcp_tx_proc(void *server); -extern void ncpdgram_rcv_proc(void *server); -extern void ncpdgram_timeout_proc(void *server); +extern void ncp_tcp_rcv_proc(struct work_struct *work); +extern void ncp_tcp_tx_proc(struct work_struct *work); +extern void ncpdgram_rcv_proc(struct work_struct *work); +extern void ncpdgram_timeout_proc(struct work_struct *work); extern void ncpdgram_timeout_call(unsigned long server); extern void ncp_tcp_data_ready(struct sock* sk, int len); extern void ncp_tcp_write_space(struct sock* sk); diff --git a/include/linux/reiserfs_fs_sb.h b/include/linux/reiserfs_fs_sb.h index 73e0becec086..6610103f23e1 100644 --- a/include/linux/reiserfs_fs_sb.h +++ b/include/linux/reiserfs_fs_sb.h @@ -249,7 +249,8 @@ struct reiserfs_journal { int j_errno; /* when flushing ordered buffers, throttle new ordered writers */ - struct work_struct j_work; + struct delayed_work j_work; + struct super_block *j_work_sb; atomic_t j_async_throttle; }; diff --git a/include/linux/relay.h b/include/linux/relay.h index 24accb483849..0e3d91b76996 100644 --- a/include/linux/relay.h +++ b/include/linux/relay.h @@ -38,7 +38,7 @@ struct rchan_buf size_t subbufs_consumed; /* count of sub-buffers consumed */ struct rchan *chan; /* associated channel */ wait_queue_head_t read_wait; /* reader wait queue */ - struct work_struct wake_readers; /* reader wake-up work struct */ + struct delayed_work wake_readers; /* reader wake-up work struct */ struct dentry *dentry; /* channel file dentry */ struct kref kref; /* channel buffer refcount */ struct page **page_array; /* array of current buffer pages */ diff --git a/include/linux/usb.h b/include/linux/usb.h index 5482bfb3303d..06ce7a626040 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -382,7 +382,7 @@ struct usb_device { int pm_usage_cnt; /* usage counter for autosuspend */ #ifdef CONFIG_PM - struct work_struct autosuspend; /* for delayed autosuspends */ + struct delayed_work autosuspend; /* for delayed autosuspends */ struct mutex pm_mutex; /* protects PM operations */ unsigned auto_pm:1; /* autosuspend/resume in progress */ -- cgit v1.2.3 From ed7b1f6d6ea1054ea4fe293a7fd8015fc3803d93 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Thu, 23 Nov 2006 23:34:49 -0500 Subject: Input: serio - make serio_register_driver() return errors Perform actual driver registration right in serio_register_driver() instead of offloading it to kseriod and return proper error code to callers if driver registration fails. Note that driver <-> port matching is still done by kseriod to speed up boot process since probing for PS/2 mice and keyboards is pretty slow. Signed-off-by: Dmitry Torokhov --- include/linux/serio.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/serio.h b/include/linux/serio.h index 8f52228390ab..0f478a8791a2 100644 --- a/include/linux/serio.h +++ b/include/linux/serio.h @@ -86,12 +86,7 @@ static inline void serio_register_port(struct serio *serio) void serio_unregister_port(struct serio *serio); void serio_unregister_child_port(struct serio *serio); -void __serio_register_driver(struct serio_driver *drv, struct module *owner); -static inline void serio_register_driver(struct serio_driver *drv) -{ - __serio_register_driver(drv, THIS_MODULE); -} - +int serio_register_driver(struct serio_driver *drv); void serio_unregister_driver(struct serio_driver *drv); static inline int serio_write(struct serio *serio, unsigned char data) -- cgit v1.2.3 From e4477d2d1bc3e6c76e83926f7fa8c8f94ba42615 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Fri, 24 Nov 2006 00:43:09 -0500 Subject: Input: add to kernel-api docbook Add input subsystem to kernel-api docbook. Enhance some function and parameter comments. Signed-off-by: Randy Dunlap Signed-off-by: Dmitry Torokhov --- include/linux/input.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/input.h b/include/linux/input.h index c38507ba38b5..4e61158b06a0 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -663,7 +663,7 @@ struct input_absinfo { #define BUS_GSC 0x1A /* - * Values describing the status of an effect + * Values describing the status of a force-feedback effect */ #define FF_STATUS_STOPPED 0x00 #define FF_STATUS_PLAYING 0x01 @@ -680,7 +680,7 @@ struct input_absinfo { */ /** - * struct ff_replay - defines scheduling of the effect + * struct ff_replay - defines scheduling of the force-feedback effect * @length: duration of the effect * @delay: delay before effect should start playing */ @@ -690,7 +690,7 @@ struct ff_replay { }; /** - * struct ff_trigger - defines what triggers the effect + * struct ff_trigger - defines what triggers the force-feedback effect * @button: number of the button triggering the effect * @interval: controls how soon the effect can be re-triggered */ @@ -700,7 +700,7 @@ struct ff_trigger { }; /** - * struct ff_envelope - generic effect envelope + * struct ff_envelope - generic force-feedback effect envelope * @attack_length: duration of the attack (ms) * @attack_level: level at the beginning of the attack * @fade_length: duration of fade (ms) @@ -719,7 +719,7 @@ struct ff_envelope { }; /** - * struct ff_constant_effect - defines parameters of a constant effect + * struct ff_constant_effect - defines parameters of a constant force-feedback effect * @level: strength of the effect; may be negative * @envelope: envelope data */ @@ -729,7 +729,7 @@ struct ff_constant_effect { }; /** - * struct ff_ramp_effect - defines parameters of a ramp effect + * struct ff_ramp_effect - defines parameters of a ramp force-feedback effect * @start_level: beginning strength of the effect; may be negative * @end_level: final strength of the effect; may be negative * @envelope: envelope data @@ -741,7 +741,7 @@ struct ff_ramp_effect { }; /** - * struct ff_condition_effect - defines a spring or friction effect + * struct ff_condition_effect - defines a spring or friction force-feedback effect * @right_saturation: maximum level when joystick moved all way to the right * @left_saturation: same for the left side * @right_coeff: controls how fast the force grows when the joystick moves @@ -762,7 +762,7 @@ struct ff_condition_effect { }; /** - * struct ff_periodic_effect - defines parameters of a periodic effect + * struct ff_periodic_effect - defines parameters of a periodic force-feedback effect * @waveform: kind of the effect (wave) * @period: period of the wave (ms) * @magnitude: peak value @@ -793,7 +793,7 @@ struct ff_periodic_effect { }; /** - * struct ff_rumble_effect - defines parameters of a periodic effect + * struct ff_rumble_effect - defines parameters of a periodic force-feedback effect * @strong_magnitude: magnitude of the heavy motor * @weak_magnitude: magnitude of the light one * -- cgit v1.2.3 From 701e054e0c2db82359f0454c7ed4fd24346d52eb Mon Sep 17 00:00:00 2001 From: Vasily Tarasov Date: Sat, 25 Nov 2006 11:09:22 -0800 Subject: [PATCH] mounstats NULL pointer dereference OpenVZ developers team has encountered the following problem in 2.6.19-rc6 kernel. After some seconds of running script while [[ 1 ]] do find /proc -name mountstats | xargs cat done this Oops appears: BUG: unable to handle kernel NULL pointer dereference at virtual address 00000010 printing eip: c01a6b70 *pde = 00000000 Oops: 0000 [#1] SMP Modules linked in: xt_length ipt_ttl xt_tcpmss ipt_TCPMSS iptable_mangle iptable_filter xt_multiport xt_limit ipt_tos ipt_REJECT ip_tables x_tables parport_pc lp parport sunrpc af_packet thermal processor fan button battery asus_acpi ac ohci_hcd ehci_hcd usbcore i2c_nforce2 i2c_core tg3 floppy pata_amd ide_cd cdrom sata_nv libata CPU: 1 EIP: 0060:[] Not tainted VLI EFLAGS: 00010246 (2.6.19-rc6 #2) EIP is at mountstats_open+0x70/0xf0 eax: 00000000 ebx: e6247030 ecx: e62470f8 edx: 00000000 esi: 00000000 edi: c01a6b00 ebp: c33b83c0 esp: f4105eb4 ds: 007b es: 007b ss: 0068 Process cat (pid: 6044, ti=f4105000 task=f4104a70 task.ti=f4105000) Stack: c33b83c0 c04ee940 f46a4a80 c33b83c0 e4df31b4 c01a6b00 f4105000 c0169231 e4df31b4 c33b83c0 c33b83c0 f4105f20 00000003 f4105000 c0169445 f2503cf0 f7f8c4c0 00008000 c33b83c0 00000000 00008000 c0169350 f4105f20 00008000 Call Trace: [] mountstats_open+0x0/0xf0 [] __dentry_open+0x181/0x250 [] nameidata_to_filp+0x35/0x50 [] do_filp_open+0x50/0x60 [] seq_read+0xc6/0x300 [] get_unused_fd+0x31/0xc0 [] do_sys_open+0x63/0x110 [] sys_open+0x27/0x30 [] sysenter_past_esp+0x56/0x79 ======================= Code: 45 74 8b 54 24 20 89 44 24 08 8b 42 f0 31 d2 e8 47 cb f8 ff 85 c0 89 c3 74 51 8d 80 a0 04 00 00 e8 46 06 2c 00 8b 83 48 04 00 00 <8b> 78 10 85 ff 74 03 f0 ff 07 b0 01 86 83 a0 04 00 00 f0 ff 4b EIP: [] mountstats_open+0x70/0xf0 SS:ESP 0068:f4105eb4 The problem is that task->nsproxy can be equal NULL for some time during task exit. This patch fixes the BUG. Signed-off-by: Vasily Tarasov Cc: Herbert Poetzl Cc: "Serge E. Hallyn" Cc: "Eric W. Biederman" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nsproxy.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nsproxy.h b/include/linux/nsproxy.h index f6baecdeecd6..971d1c6dfc4b 100644 --- a/include/linux/nsproxy.h +++ b/include/linux/nsproxy.h @@ -45,8 +45,10 @@ static inline void exit_task_namespaces(struct task_struct *p) { struct nsproxy *ns = p->nsproxy; if (ns) { - put_nsproxy(ns); + task_lock(p); p->nsproxy = NULL; + task_unlock(p); + put_nsproxy(ns); } } #endif -- cgit v1.2.3 From ee3ce191e8eaa4cc15c51a28b34143b36404c4f5 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Sat, 25 Nov 2006 11:09:36 -0800 Subject: [PATCH] Enforce "unsigned long flags;" when spinlocking Make it break or warn if you pass to spin_lock_irqsave() and friends something different from "unsigned long flags;". Suprisingly large amount of these was caught by recent commit c53421b18f205c5f97c604ae55c6a921f034b0f6 and others. Idea is largely from FRV typechecking. Suggestions from Andrew Morton. All stupid typos in first version fixed. Passes allmodconfig on i386, x86_64, alpha, arm as well as my usual config. Note #1: checking with sparse is still needed, because a driver can save and pass around flags or something. So far patch is very intrusive. Note #2: techically, we should break only if sizeof(flags) < sizeof(unsigned long), however, the more pain for getting suspicious code into kernel, the better. Signed-off-by: Alexey Dobriyan Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/irqflags.h | 37 ++++++++++++++++++++++++++++----- include/linux/spinlock.h | 53 ++++++++++++++++++++++++++++++++++++++++-------- 2 files changed, 76 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index 412e025bc5c7..4fe740bf4eae 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -11,6 +11,12 @@ #ifndef _LINUX_TRACE_IRQFLAGS_H #define _LINUX_TRACE_IRQFLAGS_H +#define BUILD_CHECK_IRQ_FLAGS(flags) \ + do { \ + BUILD_BUG_ON(sizeof(flags) != sizeof(unsigned long)); \ + typecheck(unsigned long, flags); \ + } while (0) + #ifdef CONFIG_TRACE_IRQFLAGS extern void trace_hardirqs_on(void); extern void trace_hardirqs_off(void); @@ -50,10 +56,15 @@ #define local_irq_disable() \ do { raw_local_irq_disable(); trace_hardirqs_off(); } while (0) #define local_irq_save(flags) \ - do { raw_local_irq_save(flags); trace_hardirqs_off(); } while (0) + do { \ + BUILD_CHECK_IRQ_FLAGS(flags); \ + raw_local_irq_save(flags); \ + trace_hardirqs_off(); \ + } while (0) #define local_irq_restore(flags) \ do { \ + BUILD_CHECK_IRQ_FLAGS(flags); \ if (raw_irqs_disabled_flags(flags)) { \ raw_local_irq_restore(flags); \ trace_hardirqs_off(); \ @@ -69,8 +80,16 @@ */ # define raw_local_irq_disable() local_irq_disable() # define raw_local_irq_enable() local_irq_enable() -# define raw_local_irq_save(flags) local_irq_save(flags) -# define raw_local_irq_restore(flags) local_irq_restore(flags) +# define raw_local_irq_save(flags) \ + do { \ + BUILD_CHECK_IRQ_FLAGS(flags); \ + local_irq_save(flags); \ + } while (0) +# define raw_local_irq_restore(flags) \ + do { \ + BUILD_CHECK_IRQ_FLAGS(flags); \ + local_irq_restore(flags); \ + } while (0) #endif /* CONFIG_TRACE_IRQFLAGS_SUPPORT */ #ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT @@ -80,7 +99,11 @@ raw_safe_halt(); \ } while (0) -#define local_save_flags(flags) raw_local_save_flags(flags) +#define local_save_flags(flags) \ + do { \ + BUILD_CHECK_IRQ_FLAGS(flags); \ + raw_local_save_flags(flags); \ + } while (0) #define irqs_disabled() \ ({ \ @@ -90,7 +113,11 @@ raw_irqs_disabled_flags(flags); \ }) -#define irqs_disabled_flags(flags) raw_irqs_disabled_flags(flags) +#define irqs_disabled_flags(flags) \ +({ \ + BUILD_CHECK_IRQ_FLAGS(flags); \ + raw_irqs_disabled_flags(flags); \ +}) #endif /* CONFIG_X86 */ #endif diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index b800d2d68b32..54ad37089c49 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -52,6 +52,7 @@ #include #include #include +#include #include @@ -183,13 +184,37 @@ do { \ #define read_lock(lock) _read_lock(lock) #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) -#define spin_lock_irqsave(lock, flags) flags = _spin_lock_irqsave(lock) -#define read_lock_irqsave(lock, flags) flags = _read_lock_irqsave(lock) -#define write_lock_irqsave(lock, flags) flags = _write_lock_irqsave(lock) +#define spin_lock_irqsave(lock, flags) \ + do { \ + BUILD_CHECK_IRQ_FLAGS(flags); \ + flags = _spin_lock_irqsave(lock); \ + } while (0) +#define read_lock_irqsave(lock, flags) \ + do { \ + BUILD_CHECK_IRQ_FLAGS(flags); \ + flags = _read_lock_irqsave(lock); \ + } while (0) +#define write_lock_irqsave(lock, flags) \ + do { \ + BUILD_CHECK_IRQ_FLAGS(flags); \ + flags = _write_lock_irqsave(lock); \ + } while (0) #else -#define spin_lock_irqsave(lock, flags) _spin_lock_irqsave(lock, flags) -#define read_lock_irqsave(lock, flags) _read_lock_irqsave(lock, flags) -#define write_lock_irqsave(lock, flags) _write_lock_irqsave(lock, flags) +#define spin_lock_irqsave(lock, flags) \ + do { \ + BUILD_CHECK_IRQ_FLAGS(flags); \ + _spin_lock_irqsave(lock, flags); \ + } while (0) +#define read_lock_irqsave(lock, flags) \ + do { \ + BUILD_CHECK_IRQ_FLAGS(flags); \ + _read_lock_irqsave(lock, flags); \ + } while (0) +#define write_lock_irqsave(lock, flags) \ + do { \ + BUILD_CHECK_IRQ_FLAGS(flags); \ + _write_lock_irqsave(lock, flags); \ + } while (0) #endif #define spin_lock_irq(lock) _spin_lock_irq(lock) @@ -225,15 +250,24 @@ do { \ #endif #define spin_unlock_irqrestore(lock, flags) \ - _spin_unlock_irqrestore(lock, flags) + do { \ + BUILD_CHECK_IRQ_FLAGS(flags); \ + _spin_unlock_irqrestore(lock, flags); \ + } while (0) #define spin_unlock_bh(lock) _spin_unlock_bh(lock) #define read_unlock_irqrestore(lock, flags) \ - _read_unlock_irqrestore(lock, flags) + do { \ + BUILD_CHECK_IRQ_FLAGS(flags); \ + _read_unlock_irqrestore(lock, flags); \ + } while (0) #define read_unlock_bh(lock) _read_unlock_bh(lock) #define write_unlock_irqrestore(lock, flags) \ - _write_unlock_irqrestore(lock, flags) + do { \ + BUILD_CHECK_IRQ_FLAGS(flags); \ + _write_unlock_irqrestore(lock, flags); \ + } while (0) #define write_unlock_bh(lock) _write_unlock_bh(lock) #define spin_trylock_bh(lock) __cond_lock(lock, _spin_trylock_bh(lock)) @@ -247,6 +281,7 @@ do { \ #define spin_trylock_irqsave(lock, flags) \ ({ \ + BUILD_CHECK_IRQ_FLAGS(flags); \ local_irq_save(flags); \ spin_trylock(lock) ? \ 1 : ({ local_irq_restore(flags); 0; }); \ -- cgit v1.2.3 From cfd3ef2346f924d6c0e82236c20fdb3a8840136a Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Sat, 25 Nov 2006 11:09:37 -0800 Subject: [PATCH] lockdep: spin_lock_irqsave_nested() Introduce spin_lock_irqsave_nested(); implementation from: http://lkml.org/lkml/2006/6/1/122 Patch from: http://lkml.org/lkml/2006/9/13/258 [akpm@osdl.org: two compile fixes] Signed-off-by: Arjan van de Ven Signed-off-by: Jiri Kosina Signed-off-by: Peter Zijlstra Acked-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/spinlock.h | 18 ++++++++++++++++++ include/linux/spinlock_api_smp.h | 2 ++ 2 files changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index 54ad37089c49..57f670d78f7c 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -199,6 +199,21 @@ do { \ BUILD_CHECK_IRQ_FLAGS(flags); \ flags = _write_lock_irqsave(lock); \ } while (0) + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +#define spin_lock_irqsave_nested(lock, flags, subclass) \ + do { \ + BUILD_CHECK_IRQ_FLAGS(flags); \ + flags = _spin_lock_irqsave_nested(lock, subclass); \ + } while (0) +#else +#define spin_lock_irqsave_nested(lock, flags, subclass) \ + do { \ + BUILD_CHECK_IRQ_FLAGS(flags); \ + flags = _spin_lock_irqsave(lock); \ + } while (0) +#endif + #else #define spin_lock_irqsave(lock, flags) \ do { \ @@ -215,6 +230,9 @@ do { \ BUILD_CHECK_IRQ_FLAGS(flags); \ _write_lock_irqsave(lock, flags); \ } while (0) +#define spin_lock_irqsave_nested(lock, flags, subclass) \ + spin_lock_irqsave(lock, flags) + #endif #define spin_lock_irq(lock) _spin_lock_irq(lock) diff --git a/include/linux/spinlock_api_smp.h b/include/linux/spinlock_api_smp.h index 8828b8155e9c..8a2307ce7296 100644 --- a/include/linux/spinlock_api_smp.h +++ b/include/linux/spinlock_api_smp.h @@ -32,6 +32,8 @@ void __lockfunc _read_lock_irq(rwlock_t *lock) __acquires(lock); void __lockfunc _write_lock_irq(rwlock_t *lock) __acquires(lock); unsigned long __lockfunc _spin_lock_irqsave(spinlock_t *lock) __acquires(lock); +unsigned long __lockfunc _spin_lock_irqsave_nested(spinlock_t *lock, int subclass) + __acquires(lock); unsigned long __lockfunc _read_lock_irqsave(rwlock_t *lock) __acquires(lock); unsigned long __lockfunc _write_lock_irqsave(rwlock_t *lock) -- cgit v1.2.3 From b8e6ec865fd1d8838b6ce9516977b65e9f08f876 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 26 Nov 2006 16:27:17 -0800 Subject: Revert "[PATCH] Enforce "unsigned long flags;" when spinlocking" This reverts commit ee3ce191e8eaa4cc15c51a28b34143b36404c4f5, since it broke on at least ARM, MIPS and PA-RISC due to complicated header file dependencies. Conflicts in include/linux/spinlock.h (due to the "nested" variety fixes) fixed up by hand. Cc: Alexey Dobriyan Cc: Ralf Baechle Cc: Kyle McMartin Cc: Russell King Signed-off-by: Linus Torvalds --- include/linux/irqflags.h | 37 ++++---------------------- include/linux/spinlock.h | 69 +++++++++++------------------------------------- 2 files changed, 20 insertions(+), 86 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index 4fe740bf4eae..412e025bc5c7 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -11,12 +11,6 @@ #ifndef _LINUX_TRACE_IRQFLAGS_H #define _LINUX_TRACE_IRQFLAGS_H -#define BUILD_CHECK_IRQ_FLAGS(flags) \ - do { \ - BUILD_BUG_ON(sizeof(flags) != sizeof(unsigned long)); \ - typecheck(unsigned long, flags); \ - } while (0) - #ifdef CONFIG_TRACE_IRQFLAGS extern void trace_hardirqs_on(void); extern void trace_hardirqs_off(void); @@ -56,15 +50,10 @@ #define local_irq_disable() \ do { raw_local_irq_disable(); trace_hardirqs_off(); } while (0) #define local_irq_save(flags) \ - do { \ - BUILD_CHECK_IRQ_FLAGS(flags); \ - raw_local_irq_save(flags); \ - trace_hardirqs_off(); \ - } while (0) + do { raw_local_irq_save(flags); trace_hardirqs_off(); } while (0) #define local_irq_restore(flags) \ do { \ - BUILD_CHECK_IRQ_FLAGS(flags); \ if (raw_irqs_disabled_flags(flags)) { \ raw_local_irq_restore(flags); \ trace_hardirqs_off(); \ @@ -80,16 +69,8 @@ */ # define raw_local_irq_disable() local_irq_disable() # define raw_local_irq_enable() local_irq_enable() -# define raw_local_irq_save(flags) \ - do { \ - BUILD_CHECK_IRQ_FLAGS(flags); \ - local_irq_save(flags); \ - } while (0) -# define raw_local_irq_restore(flags) \ - do { \ - BUILD_CHECK_IRQ_FLAGS(flags); \ - local_irq_restore(flags); \ - } while (0) +# define raw_local_irq_save(flags) local_irq_save(flags) +# define raw_local_irq_restore(flags) local_irq_restore(flags) #endif /* CONFIG_TRACE_IRQFLAGS_SUPPORT */ #ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT @@ -99,11 +80,7 @@ raw_safe_halt(); \ } while (0) -#define local_save_flags(flags) \ - do { \ - BUILD_CHECK_IRQ_FLAGS(flags); \ - raw_local_save_flags(flags); \ - } while (0) +#define local_save_flags(flags) raw_local_save_flags(flags) #define irqs_disabled() \ ({ \ @@ -113,11 +90,7 @@ raw_irqs_disabled_flags(flags); \ }) -#define irqs_disabled_flags(flags) \ -({ \ - BUILD_CHECK_IRQ_FLAGS(flags); \ - raw_irqs_disabled_flags(flags); \ -}) +#define irqs_disabled_flags(flags) raw_irqs_disabled_flags(flags) #endif /* CONFIG_X86 */ #endif diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index 57f670d78f7c..8451052ca66f 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -52,7 +52,6 @@ #include #include #include -#include #include @@ -184,52 +183,24 @@ do { \ #define read_lock(lock) _read_lock(lock) #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) -#define spin_lock_irqsave(lock, flags) \ - do { \ - BUILD_CHECK_IRQ_FLAGS(flags); \ - flags = _spin_lock_irqsave(lock); \ - } while (0) -#define read_lock_irqsave(lock, flags) \ - do { \ - BUILD_CHECK_IRQ_FLAGS(flags); \ - flags = _read_lock_irqsave(lock); \ - } while (0) -#define write_lock_irqsave(lock, flags) \ - do { \ - BUILD_CHECK_IRQ_FLAGS(flags); \ - flags = _write_lock_irqsave(lock); \ - } while (0) + +#define spin_lock_irqsave(lock, flags) flags = _spin_lock_irqsave(lock) +#define read_lock_irqsave(lock, flags) flags = _read_lock_irqsave(lock) +#define write_lock_irqsave(lock, flags) flags = _write_lock_irqsave(lock) #ifdef CONFIG_DEBUG_LOCK_ALLOC -#define spin_lock_irqsave_nested(lock, flags, subclass) \ - do { \ - BUILD_CHECK_IRQ_FLAGS(flags); \ - flags = _spin_lock_irqsave_nested(lock, subclass); \ - } while (0) +#define spin_lock_irqsave_nested(lock, flags, subclass) \ + flags = _spin_lock_irqsave_nested(lock, subclass) #else -#define spin_lock_irqsave_nested(lock, flags, subclass) \ - do { \ - BUILD_CHECK_IRQ_FLAGS(flags); \ - flags = _spin_lock_irqsave(lock); \ - } while (0) +#define spin_lock_irqsave_nested(lock, flags, subclass) \ + flags = _spin_lock_irqsave(lock) #endif #else -#define spin_lock_irqsave(lock, flags) \ - do { \ - BUILD_CHECK_IRQ_FLAGS(flags); \ - _spin_lock_irqsave(lock, flags); \ - } while (0) -#define read_lock_irqsave(lock, flags) \ - do { \ - BUILD_CHECK_IRQ_FLAGS(flags); \ - _read_lock_irqsave(lock, flags); \ - } while (0) -#define write_lock_irqsave(lock, flags) \ - do { \ - BUILD_CHECK_IRQ_FLAGS(flags); \ - _write_lock_irqsave(lock, flags); \ - } while (0) + +#define spin_lock_irqsave(lock, flags) _spin_lock_irqsave(lock, flags) +#define read_lock_irqsave(lock, flags) _read_lock_irqsave(lock, flags) +#define write_lock_irqsave(lock, flags) _write_lock_irqsave(lock, flags) #define spin_lock_irqsave_nested(lock, flags, subclass) \ spin_lock_irqsave(lock, flags) @@ -268,24 +239,15 @@ do { \ #endif #define spin_unlock_irqrestore(lock, flags) \ - do { \ - BUILD_CHECK_IRQ_FLAGS(flags); \ - _spin_unlock_irqrestore(lock, flags); \ - } while (0) + _spin_unlock_irqrestore(lock, flags) #define spin_unlock_bh(lock) _spin_unlock_bh(lock) #define read_unlock_irqrestore(lock, flags) \ - do { \ - BUILD_CHECK_IRQ_FLAGS(flags); \ - _read_unlock_irqrestore(lock, flags); \ - } while (0) + _read_unlock_irqrestore(lock, flags) #define read_unlock_bh(lock) _read_unlock_bh(lock) #define write_unlock_irqrestore(lock, flags) \ - do { \ - BUILD_CHECK_IRQ_FLAGS(flags); \ - _write_unlock_irqrestore(lock, flags); \ - } while (0) + _write_unlock_irqrestore(lock, flags) #define write_unlock_bh(lock) _write_unlock_bh(lock) #define spin_trylock_bh(lock) __cond_lock(lock, _spin_trylock_bh(lock)) @@ -299,7 +261,6 @@ do { \ #define spin_trylock_irqsave(lock, flags) \ ({ \ - BUILD_CHECK_IRQ_FLAGS(flags); \ local_irq_save(flags); \ spin_trylock(lock) ? \ 1 : ({ local_irq_restore(flags); 0; }); \ -- cgit v1.2.3 From 2ea5814472c3c910aed5c5b60f1f3b1000e353f1 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 26 Nov 2006 19:05:22 -0800 Subject: Fix 'ALIGN()' macro, take 2 You wouldn't think that doing an ALIGN() macro that aligns something up to a power-of-two boundary would be likely to have bugs, would you? But hey, in the wonderful world of mixing integer types, you have to be careful. This just makes sure that the alignment is interpreted in the same type as the thing to be aligned. Thanks to Roland Dreier, who noticed that the amso1100 driver got broken by the previous fix (that just extended the mask to "unsigned long", but was still broken in "unsigned long long" - it just happened to be the same on 64-bit architectures). See commit 4c8bd7eeee4c8f157fb61fb64b57500990b42e0e for the history of bugs here... Acked-by: Roland Dreier Cc: Andrew Morton Cc: David Miller Cc: Al Viro Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 24b611147adb..b9b5e4ba166a 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -30,8 +30,10 @@ extern const char linux_banner[]; #define STACK_MAGIC 0xdeadbeef +#define ALIGN(x,a) __ALIGN_MASK(x,(typeof(x))(a)-1) +#define __ALIGN_MASK(x,mask) (((x)+(mask))&~(mask)) + #define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) -#define ALIGN(x,a) (((x)+(a)-1UL)&~((a)-1UL)) #define FIELD_SIZEOF(t, f) (sizeof(((t*)0)->f)) #define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d)) #define roundup(x, y) ((((x) + ((y) - 1)) / (y)) * (y)) -- cgit v1.2.3 From e81c73596704793e73e6dbb478f41686f15a4b34 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 28 Nov 2006 20:53:39 -0800 Subject: [NET]: Fix MAX_HEADER setting. MAX_HEADER is either set to LL_MAX_HEADER or LL_MAX_HEADER + 48, and this is controlled by a set of CONFIG_* ifdef tests. It is trying to use LL_MAX_HEADER + 48 when any of the tunnels are enabled which set hard_header_len like this: dev->hard_header_len = LL_MAX_HEADER + sizeof(struct xxx); The correct set of tunnel drivers which do this are: ipip ip_gre ip6_tunnel sit so make the ifdef test match. Noticed by Patrick McHardy and with help from Herbert Xu. 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 9264139bd8df..83b8c4f1d69d 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -93,8 +93,10 @@ struct netpoll_info; #endif #endif -#if !defined(CONFIG_NET_IPIP) && \ - !defined(CONFIG_IPV6) && !defined(CONFIG_IPV6_MODULE) +#if !defined(CONFIG_NET_IPIP) && !defined(CONFIG_NET_IPIP_MODULE) && \ + !defined(CONFIG_NET_IPGRE) && !defined(CONFIG_NET_IPGRE_MODULE) && \ + !defined(CONFIG_IPV6_SIT) && !defined(CONFIG_IPV6_SIT_MODULE) && \ + !defined(CONFIG_IPV6_TUNNEL) && !defined(CONFIG_IPV6_TUNNEL_MODULE) #define MAX_HEADER LL_MAX_HEADER #else #define MAX_HEADER (LL_MAX_HEADER + 48) -- cgit v1.2.3 From 583bb86fbb9e85287f020fe4eb5352a0ec3c66a3 Mon Sep 17 00:00:00 2001 From: Nicolas Schichan Date: Wed, 18 Oct 2006 15:14:55 +0200 Subject: [MIPS] Add support for kexec A tiny userland application loading the kernel and invoking kexec_load for mips is available here: http://chac.le-poulpe.net/~nico/kexec/kexec-2006-10-18.tar.gz Signed-off-by: Ralf Baechle --- include/linux/kexec.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 6427949ddf99..a4ede62b339d 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -122,6 +122,8 @@ extern struct kimage *kexec_crash_image; #define KEXEC_ARCH_IA_64 (50 << 16) #define KEXEC_ARCH_S390 (22 << 16) #define KEXEC_ARCH_SH (42 << 16) +#define KEXEC_ARCH_MIPS_LE (10 << 16) +#define KEXEC_ARCH_MIPS ( 8 << 16) #define KEXEC_FLAGS (KEXEC_ON_CRASH) /* List of defined/legal kexec flags */ -- cgit v1.2.3 From 139a7bdc2b9391a4d0362190d9e5625dcf580105 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Thu, 30 Nov 2006 04:40:22 +0100 Subject: mqueue.h: don't include linux/types.h This #include is not required. Signed-off-by: Alexey Dobriyan Signed-off-by: Adrian Bunk --- include/linux/mqueue.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mqueue.h b/include/linux/mqueue.h index 8db9d75541a6..8b5a79615fbf 100644 --- a/include/linux/mqueue.h +++ b/include/linux/mqueue.h @@ -18,8 +18,6 @@ #ifndef _LINUX_MQUEUE_H #define _LINUX_MQUEUE_H -#include - #define MQ_PRIO_MAX 32768 /* per-uid limit of kernel memory used by mqueue, in bytes */ #define MQ_BYTES_MAX 819200 -- cgit v1.2.3 From e20ec9911bfef897459b9f8aeaf6eadb0920299a Mon Sep 17 00:00:00 2001 From: Jim Cromie Date: Thu, 30 Nov 2006 04:46:13 +0100 Subject: fix spelling error in include/linux/kernel.h Signed-off-by: Adrian Bunk --- include/linux/kernel.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index b9b5e4ba166a..6738283ac385 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -65,7 +65,7 @@ struct user; * context (spinlock, irq-handler, ...). * * This is a useful debugging help to be able to catch problems early and not - * be biten later when the calling function happens to sleep when it is not + * be bitten later when the calling function happens to sleep when it is not * supposed to. */ #ifdef CONFIG_PREEMPT_VOLUNTARY -- cgit v1.2.3 From 98c4f0c336afe4318c12397bc74910d86ee036a2 Mon Sep 17 00:00:00 2001 From: Chase Venters Date: Thu, 30 Nov 2006 04:53:49 +0100 Subject: Fix jiffies.h comment jiffies.h includes a comment informing that jiffies_64 must be read with the assistance of the xtime_lock seqlock. The comment text, however, calls jiffies_64 "not volatile", which should probably read "not atomic". Signed-off-by: Chase Venters Signed-off-by: Adrian Bunk --- include/linux/jiffies.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h index c8d5f207c3d4..0ec6e28bccd2 100644 --- a/include/linux/jiffies.h +++ b/include/linux/jiffies.h @@ -74,7 +74,7 @@ #define __jiffy_data __attribute__((section(".data"))) /* - * The 64-bit value is not volatile - you MUST NOT read it + * The 64-bit value is not atomic - you MUST NOT read it * without sampling the sequence number in xtime_lock. * get_jiffies_64() will do this for you as appropriate. */ -- cgit v1.2.3 From 0779bf2d2ecc4d9b1e9437ae659f50e6776a7666 Mon Sep 17 00:00:00 2001 From: Matt LaPlante Date: Thu, 30 Nov 2006 05:24:39 +0100 Subject: Fix misc .c/.h comment typos Fix various .c/.h typos in comments (no code changes). Signed-off-by: Matt LaPlante Signed-off-by: Adrian Bunk --- include/linux/ixjuser.h | 2 +- include/linux/reiserfs_fs_sb.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ixjuser.h b/include/linux/ixjuser.h index fd1756d3a47e..88b45895746d 100644 --- a/include/linux/ixjuser.h +++ b/include/linux/ixjuser.h @@ -315,7 +315,7 @@ typedef struct { * structures. If the freq0 variable is non-zero, the tone table contents * for the tone_index are updated to the frequencies and gains defined. It * should be noted that DTMF tones cannot be reassigned, so if DTMF tone -* table indexs are used in a cadence the frequency and gain variables will +* table indexes are used in a cadence the frequency and gain variables will * be ignored. * * If the array elements contain frequency parameters the driver will diff --git a/include/linux/reiserfs_fs_sb.h b/include/linux/reiserfs_fs_sb.h index 73e0becec086..62a7169aed8b 100644 --- a/include/linux/reiserfs_fs_sb.h +++ b/include/linux/reiserfs_fs_sb.h @@ -429,7 +429,7 @@ enum reiserfs_mount_options { /* -o hash={tea, rupasov, r5, detect} is meant for properly mounting ** reiserfs disks from 3.5.19 or earlier. 99% of the time, this option ** is not required. If the normal autodection code can't determine which -** hash to use (because both hases had the same value for a file) +** hash to use (because both hashes had the same value for a file) ** use this option to force a specific hash. It won't allow you to override ** the existing hash on the FS, so if you have a tea hash disk, and mount ** with -o hash=rupasov, the mount will fail. -- cgit v1.2.3 From 03a67a46af8647b2c7825107045ecae641e103d3 Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Thu, 30 Nov 2006 05:32:19 +0100 Subject: Fix typos in doc and comments Changes persistant -> persistent. www.dictionary.com does not know persistant (with an A), but should it be one of those things you can spell in more than one correct way, let me know. Signed-off-by: Jan Engelhardt Signed-off-by: Adrian Bunk --- include/linux/textsearch.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/textsearch.h b/include/linux/textsearch.h index 7dac8f04d28e..004808a6df1d 100644 --- a/include/linux/textsearch.h +++ b/include/linux/textsearch.h @@ -20,7 +20,7 @@ struct ts_config; /** * struct ts_state - search state * @offset: offset for next match - * @cb: control buffer, for persistant variables of get_next_block() + * @cb: control buffer, for persistent variables of get_next_block() */ struct ts_state { @@ -71,7 +71,7 @@ struct ts_config * Called repeatedly until 0 is returned. Must assign the * head of the next block of data to &*dst and return the length * of the block or 0 if at the end. consumed == 0 indicates - * a new search. May store/read persistant values in state->cb. + * a new search. May store/read persistent values in state->cb. */ unsigned int (*get_next_block)(unsigned int consumed, const u8 **dst, -- cgit v1.2.3 From beea494d5e09f9e2172894ec84324b94244826a9 Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 7 Nov 2006 21:03:20 +0000 Subject: [ARM] Remove EEPROM slave emulation from i2c-pxa driver. The i2c-pxa driver should not contain EEPROM slave-mode emulation; this is something the platform should provide where required. Remove it. Signed-off-by: Russell King --- include/linux/i2c-pxa.h | 31 ------------------------------- 1 file changed, 31 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c-pxa.h b/include/linux/i2c-pxa.h index 5f3eaf802223..41dcdfe7f625 100644 --- a/include/linux/i2c-pxa.h +++ b/include/linux/i2c-pxa.h @@ -1,29 +1,6 @@ #ifndef _LINUX_I2C_ALGO_PXA_H #define _LINUX_I2C_ALGO_PXA_H -struct i2c_eeprom_emu_watcher { - void (*write)(void *, unsigned int addr, unsigned char newval); -}; - -struct i2c_eeprom_emu_watch { - struct list_head node; - unsigned int start; - unsigned int end; - struct i2c_eeprom_emu_watcher *ops; - void *data; -}; - -#define I2C_EEPROM_EMU_SIZE (256) - -struct i2c_eeprom_emu { - unsigned int size; - unsigned int ptr; - unsigned int seen_start; - struct list_head watch; - - unsigned char bytes[I2C_EEPROM_EMU_SIZE]; -}; - typedef enum i2c_slave_event_e { I2C_SLAVE_EVENT_START_READ, I2C_SLAVE_EVENT_START_WRITE, @@ -37,12 +14,4 @@ struct i2c_slave_client { void (*write)(void *ptr, unsigned int val); }; -extern int i2c_eeprom_emu_addwatcher(struct i2c_eeprom_emu *, void *data, - unsigned int addr, unsigned int size, - struct i2c_eeprom_emu_watcher *); - -extern void i2c_eeprom_emu_delwatcher(struct i2c_eeprom_emu *, void *data, struct i2c_eeprom_emu_watcher *watcher); - -extern struct i2c_eeprom_emu *i2c_pxa_get_eeprom(void); - #endif /* _LINUX_I2C_ALGO_PXA_H */ -- cgit v1.2.3 From 3ca68df6ee61e1a2034f3307b9edb9b3d87e5ca1 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 13 Oct 2006 20:11:25 -0400 Subject: [GFS2] split gfs2_dinode into on-disk and host variants The latter is used as part of gfs2-private part of struct inode. It actually stores a lot of fields differently; for now the declaration is just cloned, inode field is swtiched and changes propagated. Signed-off-by: Al Viro Signed-off-by: Steven Whitehouse --- include/linux/gfs2_ondisk.h | 48 ++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 45 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfs2_ondisk.h b/include/linux/gfs2_ondisk.h index a7ae7c177cac..f334b4bd2915 100644 --- a/include/linux/gfs2_ondisk.h +++ b/include/linux/gfs2_ondisk.h @@ -270,6 +270,48 @@ struct gfs2_dinode { __u8 di_reserved[56]; }; +struct gfs2_dinode_host { + struct gfs2_meta_header di_header; + + struct gfs2_inum di_num; + + __be32 di_mode; /* mode of file */ + __be32 di_uid; /* owner's user id */ + __be32 di_gid; /* owner's group id */ + __be32 di_nlink; /* number of links to this file */ + __be64 di_size; /* number of bytes in file */ + __be64 di_blocks; /* number of blocks in file */ + __be64 di_atime; /* time last accessed */ + __be64 di_mtime; /* time last modified */ + __be64 di_ctime; /* time last changed */ + __be32 di_major; /* device major number */ + __be32 di_minor; /* device minor number */ + + /* This section varies from gfs1. Padding added to align with + * remainder of dinode + */ + __be64 di_goal_meta; /* rgrp to alloc from next */ + __be64 di_goal_data; /* data block goal */ + __be64 di_generation; /* generation number for NFS */ + + __be32 di_flags; /* GFS2_DIF_... */ + __be32 di_payload_format; /* GFS2_FORMAT_... */ + __u16 __pad1; /* Was ditype in gfs1 */ + __be16 di_height; /* height of metadata */ + __u32 __pad2; /* Unused incarnation number from gfs1 */ + + /* These only apply to directories */ + __u16 __pad3; /* Padding */ + __be16 di_depth; /* Number of bits in the table */ + __be32 di_entries; /* The number of entries in the directory */ + + struct gfs2_inum __pad4; /* Unused even in current gfs1 */ + + __be64 di_eattr; /* extended attribute block number */ + + __u8 di_reserved[56]; +}; + /* * directory structure - many of these per directory file */ @@ -422,8 +464,8 @@ extern void gfs2_rgrp_in(struct gfs2_rgrp *rg, const void *buf); extern void gfs2_rgrp_out(const struct gfs2_rgrp *rg, void *buf); extern void gfs2_quota_in(struct gfs2_quota *qu, const void *buf); extern void gfs2_quota_out(const struct gfs2_quota *qu, void *buf); -extern void gfs2_dinode_in(struct gfs2_dinode *di, const void *buf); -extern void gfs2_dinode_out(const struct gfs2_dinode *di, void *buf); +extern void gfs2_dinode_in(struct gfs2_dinode_host *di, const void *buf); +extern void gfs2_dinode_out(const struct gfs2_dinode_host *di, void *buf); extern void gfs2_ea_header_in(struct gfs2_ea_header *ea, const void *buf); extern void gfs2_ea_header_out(const struct gfs2_ea_header *ea, void *buf); extern void gfs2_log_header_in(struct gfs2_log_header *lh, const void *buf); @@ -436,7 +478,7 @@ extern void gfs2_quota_change_in(struct gfs2_quota_change *qc, const void *buf); /* Printing functions */ extern void gfs2_rindex_print(const struct gfs2_rindex *ri); -extern void gfs2_dinode_print(const struct gfs2_dinode *di); +extern void gfs2_dinode_print(const struct gfs2_dinode_host *di); #endif /* __KERNEL__ */ -- cgit v1.2.3 From 5c6edb576f3800723bb65dbfaff82517089e32d0 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 13 Oct 2006 20:33:01 -0400 Subject: [GFS2] gfs2_dinode_host fields are host-endian Annotated scalar fields, dropped unused ones. Note that it's not at all obvious that we want to convert all of them to host-endian... Signed-off-by: Al Viro Signed-off-by: Steven Whitehouse --- include/linux/gfs2_ondisk.h | 47 +++++++++++++++++++-------------------------- 1 file changed, 20 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfs2_ondisk.h b/include/linux/gfs2_ondisk.h index f334b4bd2915..0e67a89a9699 100644 --- a/include/linux/gfs2_ondisk.h +++ b/include/linux/gfs2_ondisk.h @@ -275,41 +275,34 @@ struct gfs2_dinode_host { struct gfs2_inum di_num; - __be32 di_mode; /* mode of file */ - __be32 di_uid; /* owner's user id */ - __be32 di_gid; /* owner's group id */ - __be32 di_nlink; /* number of links to this file */ - __be64 di_size; /* number of bytes in file */ - __be64 di_blocks; /* number of blocks in file */ - __be64 di_atime; /* time last accessed */ - __be64 di_mtime; /* time last modified */ - __be64 di_ctime; /* time last changed */ - __be32 di_major; /* device major number */ - __be32 di_minor; /* device minor number */ + __u32 di_mode; /* mode of file */ + __u32 di_uid; /* owner's user id */ + __u32 di_gid; /* owner's group id */ + __u32 di_nlink; /* number of links to this file */ + __u64 di_size; /* number of bytes in file */ + __u64 di_blocks; /* number of blocks in file */ + __u64 di_atime; /* time last accessed */ + __u64 di_mtime; /* time last modified */ + __u64 di_ctime; /* time last changed */ + __u32 di_major; /* device major number */ + __u32 di_minor; /* device minor number */ /* This section varies from gfs1. Padding added to align with * remainder of dinode */ - __be64 di_goal_meta; /* rgrp to alloc from next */ - __be64 di_goal_data; /* data block goal */ - __be64 di_generation; /* generation number for NFS */ + __u64 di_goal_meta; /* rgrp to alloc from next */ + __u64 di_goal_data; /* data block goal */ + __u64 di_generation; /* generation number for NFS */ - __be32 di_flags; /* GFS2_DIF_... */ - __be32 di_payload_format; /* GFS2_FORMAT_... */ - __u16 __pad1; /* Was ditype in gfs1 */ - __be16 di_height; /* height of metadata */ - __u32 __pad2; /* Unused incarnation number from gfs1 */ + __u32 di_flags; /* GFS2_DIF_... */ + __u32 di_payload_format; /* GFS2_FORMAT_... */ + __u16 di_height; /* height of metadata */ /* These only apply to directories */ - __u16 __pad3; /* Padding */ - __be16 di_depth; /* Number of bits in the table */ - __be32 di_entries; /* The number of entries in the directory */ - - struct gfs2_inum __pad4; /* Unused even in current gfs1 */ + __u16 di_depth; /* Number of bits in the table */ + __u32 di_entries; /* The number of entries in the directory */ - __be64 di_eattr; /* extended attribute block number */ - - __u8 di_reserved[56]; + __u64 di_eattr; /* extended attribute block number */ }; /* -- cgit v1.2.3 From f50dfaf78c01df3cc2d8819f07d6661915567bae Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 13 Oct 2006 20:45:02 -0400 Subject: [GFS2] split gfs2_sb Signed-off-by: Al Viro Signed-off-by: Steven Whitehouse --- include/linux/gfs2_ondisk.h | 22 +++++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/gfs2_ondisk.h b/include/linux/gfs2_ondisk.h index 0e67a89a9699..b7bdfef82e4e 100644 --- a/include/linux/gfs2_ondisk.h +++ b/include/linux/gfs2_ondisk.h @@ -128,6 +128,26 @@ struct gfs2_sb { /* In gfs1, quota and license dinodes followed */ }; +struct gfs2_sb_host { + struct gfs2_meta_header sb_header; + + __be32 sb_fs_format; + __be32 sb_multihost_format; + __u32 __pad0; /* Was superblock flags in gfs1 */ + + __be32 sb_bsize; + __be32 sb_bsize_shift; + __u32 __pad1; /* Was journal segment size in gfs1 */ + + struct gfs2_inum sb_master_dir; /* Was jindex dinode in gfs1 */ + struct gfs2_inum __pad2; /* Was rindex dinode in gfs1 */ + struct gfs2_inum sb_root_dir; + + char sb_lockproto[GFS2_LOCKNAME_LEN]; + char sb_locktable[GFS2_LOCKNAME_LEN]; + /* In gfs1, quota and license dinodes followed */ +}; + /* * resource index structure */ @@ -450,7 +470,7 @@ struct gfs2_quota_change { extern void gfs2_inum_in(struct gfs2_inum *no, const void *buf); extern void gfs2_inum_out(const struct gfs2_inum *no, void *buf); -extern void gfs2_sb_in(struct gfs2_sb *sb, const void *buf); +extern void gfs2_sb_in(struct gfs2_sb_host *sb, const void *buf); extern void gfs2_rindex_in(struct gfs2_rindex *ri, const void *buf); extern void gfs2_rindex_out(const struct gfs2_rindex *ri, void *buf); extern void gfs2_rgrp_in(struct gfs2_rgrp *rg, const void *buf); -- cgit v1.2.3 From bc558c87bb7e50c4f728d32684a9f4f4c73ebde3 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 13 Oct 2006 21:02:41 -0400 Subject: [GFS2] fields of gfs2_sb_host are host-endian ... and several could be killed, but that's another story. Annotate scalar ones, kill completely unused. Signed-off-by: Al Viro Signed-off-by: Steven Whitehouse --- include/linux/gfs2_ondisk.h | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfs2_ondisk.h b/include/linux/gfs2_ondisk.h index b7bdfef82e4e..a5d36cdc46e9 100644 --- a/include/linux/gfs2_ondisk.h +++ b/include/linux/gfs2_ondisk.h @@ -131,16 +131,13 @@ struct gfs2_sb { struct gfs2_sb_host { struct gfs2_meta_header sb_header; - __be32 sb_fs_format; - __be32 sb_multihost_format; - __u32 __pad0; /* Was superblock flags in gfs1 */ + __u32 sb_fs_format; + __u32 sb_multihost_format; - __be32 sb_bsize; - __be32 sb_bsize_shift; - __u32 __pad1; /* Was journal segment size in gfs1 */ + __u32 sb_bsize; + __u32 sb_bsize_shift; struct gfs2_inum sb_master_dir; /* Was jindex dinode in gfs1 */ - struct gfs2_inum __pad2; /* Was rindex dinode in gfs1 */ struct gfs2_inum sb_root_dir; char sb_lockproto[GFS2_LOCKNAME_LEN]; -- cgit v1.2.3 From 68826664d12827d7a732192e2f00ba46fb899414 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 13 Oct 2006 21:07:22 -0400 Subject: [GFS2] split and annotate gfs2_rgrp Signed-off-by: Al Viro Signed-off-by: Steven Whitehouse --- include/linux/gfs2_ondisk.h | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfs2_ondisk.h b/include/linux/gfs2_ondisk.h index a5d36cdc46e9..e4ca6e4176bb 100644 --- a/include/linux/gfs2_ondisk.h +++ b/include/linux/gfs2_ondisk.h @@ -193,6 +193,15 @@ struct gfs2_rgrp { __u8 rg_reserved[80]; /* Several fields from gfs1 now reserved */ }; +struct gfs2_rgrp_host { + struct gfs2_meta_header rg_header; + + __u32 rg_flags; + __u32 rg_free; + __u32 rg_dinodes; + __u64 rg_igeneration; +}; + /* * quota structure */ @@ -470,8 +479,8 @@ extern void gfs2_inum_out(const struct gfs2_inum *no, void *buf); extern void gfs2_sb_in(struct gfs2_sb_host *sb, const void *buf); extern void gfs2_rindex_in(struct gfs2_rindex *ri, const void *buf); extern void gfs2_rindex_out(const struct gfs2_rindex *ri, void *buf); -extern void gfs2_rgrp_in(struct gfs2_rgrp *rg, const void *buf); -extern void gfs2_rgrp_out(const struct gfs2_rgrp *rg, void *buf); +extern void gfs2_rgrp_in(struct gfs2_rgrp_host *rg, const void *buf); +extern void gfs2_rgrp_out(const struct gfs2_rgrp_host *rg, void *buf); extern void gfs2_quota_in(struct gfs2_quota *qu, const void *buf); extern void gfs2_quota_out(const struct gfs2_quota *qu, void *buf); extern void gfs2_dinode_in(struct gfs2_dinode_host *di, const void *buf); -- cgit v1.2.3 From e697264709c86040271cdd7abee781d7adbb7f91 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 13 Oct 2006 21:29:46 -0400 Subject: [GFS2] split and annotate gfs2_inum_range Signed-off-by: Al Viro Signed-off-by: Steven Whitehouse --- include/linux/gfs2_ondisk.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfs2_ondisk.h b/include/linux/gfs2_ondisk.h index e4ca6e4176bb..c035587d066e 100644 --- a/include/linux/gfs2_ondisk.h +++ b/include/linux/gfs2_ondisk.h @@ -445,6 +445,11 @@ struct gfs2_inum_range { __be64 ir_length; }; +struct gfs2_inum_range_host { + __u64 ir_start; + __u64 ir_length; +}; + /* * Statfs change * Describes an change to the pool of free and allocated @@ -488,8 +493,8 @@ extern void gfs2_dinode_out(const struct gfs2_dinode_host *di, void *buf); extern void gfs2_ea_header_in(struct gfs2_ea_header *ea, const void *buf); extern void gfs2_ea_header_out(const struct gfs2_ea_header *ea, void *buf); extern void gfs2_log_header_in(struct gfs2_log_header *lh, const void *buf); -extern void gfs2_inum_range_in(struct gfs2_inum_range *ir, const void *buf); -extern void gfs2_inum_range_out(const struct gfs2_inum_range *ir, void *buf); +extern void gfs2_inum_range_in(struct gfs2_inum_range_host *ir, const void *buf); +extern void gfs2_inum_range_out(const struct gfs2_inum_range_host *ir, void *buf); extern void gfs2_statfs_change_in(struct gfs2_statfs_change *sc, const void *buf); extern void gfs2_statfs_change_out(const struct gfs2_statfs_change *sc, void *buf); extern void gfs2_quota_change_in(struct gfs2_quota_change *qc, const void *buf); -- cgit v1.2.3 From 551676226163379c217e8ec54bd287eab9b8521e Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 13 Oct 2006 21:47:13 -0400 Subject: [GFS2] split and annotate gfs2_log_head Signed-off-by: Al Viro Signed-off-by: Steven Whitehouse --- include/linux/gfs2_ondisk.h | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/gfs2_ondisk.h b/include/linux/gfs2_ondisk.h index c035587d066e..fb69a64c70cd 100644 --- a/include/linux/gfs2_ondisk.h +++ b/include/linux/gfs2_ondisk.h @@ -405,6 +405,16 @@ struct gfs2_log_header { __be32 lh_hash; }; +struct gfs2_log_header_host { + struct gfs2_meta_header lh_header; + + __u64 lh_sequence; /* Sequence number of this transaction */ + __u32 lh_flags; /* GFS2_LOG_HEAD_... */ + __u32 lh_tail; /* Block number of log tail */ + __u32 lh_blkno; + __u32 lh_hash; +}; + /* * Log type descriptor */ @@ -492,7 +502,7 @@ extern void gfs2_dinode_in(struct gfs2_dinode_host *di, const void *buf); extern void gfs2_dinode_out(const struct gfs2_dinode_host *di, void *buf); extern void gfs2_ea_header_in(struct gfs2_ea_header *ea, const void *buf); extern void gfs2_ea_header_out(const struct gfs2_ea_header *ea, void *buf); -extern void gfs2_log_header_in(struct gfs2_log_header *lh, const void *buf); +extern void gfs2_log_header_in(struct gfs2_log_header_host *lh, const void *buf); extern void gfs2_inum_range_in(struct gfs2_inum_range_host *ir, const void *buf); extern void gfs2_inum_range_out(const struct gfs2_inum_range_host *ir, void *buf); extern void gfs2_statfs_change_in(struct gfs2_statfs_change *sc, const void *buf); -- cgit v1.2.3 From e928a76f959e89884f6186bb6f846c533847d5df Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 13 Oct 2006 21:57:23 -0400 Subject: [GFS2] split and annotate gfs2_meta_header Signed-off-by: Al Viro Signed-off-by: Steven Whitehouse --- include/linux/gfs2_ondisk.h | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfs2_ondisk.h b/include/linux/gfs2_ondisk.h index fb69a64c70cd..76eb9e1bb773 100644 --- a/include/linux/gfs2_ondisk.h +++ b/include/linux/gfs2_ondisk.h @@ -89,6 +89,12 @@ struct gfs2_meta_header { __be32 __pad1; /* Was incarnation number in gfs1 */ }; +struct gfs2_meta_header_host { + __u32 mh_magic; + __u32 mh_type; + __u32 mh_format; +}; + /* * super-block structure * @@ -129,7 +135,7 @@ struct gfs2_sb { }; struct gfs2_sb_host { - struct gfs2_meta_header sb_header; + struct gfs2_meta_header_host sb_header; __u32 sb_fs_format; __u32 sb_multihost_format; @@ -194,7 +200,7 @@ struct gfs2_rgrp { }; struct gfs2_rgrp_host { - struct gfs2_meta_header rg_header; + struct gfs2_meta_header_host rg_header; __u32 rg_flags; __u32 rg_free; @@ -297,7 +303,7 @@ struct gfs2_dinode { }; struct gfs2_dinode_host { - struct gfs2_meta_header di_header; + struct gfs2_meta_header_host di_header; struct gfs2_inum di_num; @@ -406,7 +412,7 @@ struct gfs2_log_header { }; struct gfs2_log_header_host { - struct gfs2_meta_header lh_header; + struct gfs2_meta_header_host lh_header; __u64 lh_sequence; /* Sequence number of this transaction */ __u32 lh_flags; /* GFS2_LOG_HEAD_... */ -- cgit v1.2.3 From 1e81c4c3e0f55c95b6278a827262b80debd0dc7e Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 13 Oct 2006 22:51:24 -0400 Subject: [GFS2] split and annotate gfs_rindex Signed-off-by: Al Viro Signed-off-by: Steven Whitehouse --- include/linux/gfs2_ondisk.h | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfs2_ondisk.h b/include/linux/gfs2_ondisk.h index 76eb9e1bb773..7dd5e4c18a66 100644 --- a/include/linux/gfs2_ondisk.h +++ b/include/linux/gfs2_ondisk.h @@ -168,6 +168,14 @@ struct gfs2_rindex { __u8 ri_reserved[64]; }; +struct gfs2_rindex_host { + __u64 ri_addr; /* grp block disk address */ + __u64 ri_data0; /* first data location */ + __u32 ri_length; /* length of rgrp header in fs blocks */ + __u32 ri_data; /* num of data blocks in rgrp */ + __u32 ri_bitbytes; /* number of bytes in data bitmaps */ +}; + /* * resource group header structure */ @@ -498,8 +506,8 @@ struct gfs2_quota_change { extern void gfs2_inum_in(struct gfs2_inum *no, const void *buf); extern void gfs2_inum_out(const struct gfs2_inum *no, void *buf); extern void gfs2_sb_in(struct gfs2_sb_host *sb, const void *buf); -extern void gfs2_rindex_in(struct gfs2_rindex *ri, const void *buf); -extern void gfs2_rindex_out(const struct gfs2_rindex *ri, void *buf); +extern void gfs2_rindex_in(struct gfs2_rindex_host *ri, const void *buf); +extern void gfs2_rindex_out(const struct gfs2_rindex_host *ri, void *buf); extern void gfs2_rgrp_in(struct gfs2_rgrp_host *rg, const void *buf); extern void gfs2_rgrp_out(const struct gfs2_rgrp_host *rg, void *buf); extern void gfs2_quota_in(struct gfs2_quota *qu, const void *buf); @@ -517,7 +525,7 @@ extern void gfs2_quota_change_in(struct gfs2_quota_change *qc, const void *buf); /* Printing functions */ -extern void gfs2_rindex_print(const struct gfs2_rindex *ri); +extern void gfs2_rindex_print(const struct gfs2_rindex_host *ri); extern void gfs2_dinode_print(const struct gfs2_dinode_host *di); #endif /* __KERNEL__ */ -- cgit v1.2.3 From 629a21e7ecedf779c68dcaa9a186069f57a7c652 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 13 Oct 2006 22:51:24 -0400 Subject: [GFS2] split and annotate gfs2_inum Signed-off-by: Al Viro Signed-off-by: Steven Whitehouse --- include/linux/gfs2_ondisk.h | 19 ++++++++++++------- 1 file changed, 12 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfs2_ondisk.h b/include/linux/gfs2_ondisk.h index 7dd5e4c18a66..b16df6e8f55c 100644 --- a/include/linux/gfs2_ondisk.h +++ b/include/linux/gfs2_ondisk.h @@ -54,8 +54,13 @@ struct gfs2_inum { __be64 no_addr; }; -static inline int gfs2_inum_equal(const struct gfs2_inum *ino1, - const struct gfs2_inum *ino2) +struct gfs2_inum_host { + __u64 no_formal_ino; + __u64 no_addr; +}; + +static inline int gfs2_inum_equal(const struct gfs2_inum_host *ino1, + const struct gfs2_inum_host *ino2) { return ino1->no_formal_ino == ino2->no_formal_ino && ino1->no_addr == ino2->no_addr; @@ -143,8 +148,8 @@ struct gfs2_sb_host { __u32 sb_bsize; __u32 sb_bsize_shift; - struct gfs2_inum sb_master_dir; /* Was jindex dinode in gfs1 */ - struct gfs2_inum sb_root_dir; + struct gfs2_inum_host sb_master_dir; /* Was jindex dinode in gfs1 */ + struct gfs2_inum_host sb_root_dir; char sb_lockproto[GFS2_LOCKNAME_LEN]; char sb_locktable[GFS2_LOCKNAME_LEN]; @@ -313,7 +318,7 @@ struct gfs2_dinode { struct gfs2_dinode_host { struct gfs2_meta_header_host di_header; - struct gfs2_inum di_num; + struct gfs2_inum_host di_num; __u32 di_mode; /* mode of file */ __u32 di_uid; /* owner's user id */ @@ -503,8 +508,8 @@ struct gfs2_quota_change { #ifdef __KERNEL__ /* Translation functions */ -extern void gfs2_inum_in(struct gfs2_inum *no, const void *buf); -extern void gfs2_inum_out(const struct gfs2_inum *no, void *buf); +extern void gfs2_inum_in(struct gfs2_inum_host *no, const void *buf); +extern void gfs2_inum_out(const struct gfs2_inum_host *no, void *buf); extern void gfs2_sb_in(struct gfs2_sb_host *sb, const void *buf); extern void gfs2_rindex_in(struct gfs2_rindex_host *ri, const void *buf); extern void gfs2_rindex_out(const struct gfs2_rindex_host *ri, void *buf); -- cgit v1.2.3 From b5bc9e8b065dbcd4c675e8c158d6e524f221b8e1 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 13 Oct 2006 23:31:55 -0400 Subject: [GFS2] split and annotate gfs2_quota Signed-off-by: Al Viro Signed-off-by: Steven Whitehouse --- include/linux/gfs2_ondisk.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfs2_ondisk.h b/include/linux/gfs2_ondisk.h index b16df6e8f55c..431e03b85458 100644 --- a/include/linux/gfs2_ondisk.h +++ b/include/linux/gfs2_ondisk.h @@ -232,6 +232,12 @@ struct gfs2_quota { __u8 qu_reserved[64]; }; +struct gfs2_quota_host { + __u64 qu_limit; + __u64 qu_warn; + __u64 qu_value; +}; + /* * dinode structure */ @@ -515,8 +521,7 @@ extern void gfs2_rindex_in(struct gfs2_rindex_host *ri, const void *buf); extern void gfs2_rindex_out(const struct gfs2_rindex_host *ri, void *buf); extern void gfs2_rgrp_in(struct gfs2_rgrp_host *rg, const void *buf); extern void gfs2_rgrp_out(const struct gfs2_rgrp_host *rg, void *buf); -extern void gfs2_quota_in(struct gfs2_quota *qu, const void *buf); -extern void gfs2_quota_out(const struct gfs2_quota *qu, void *buf); +extern void gfs2_quota_in(struct gfs2_quota_host *qu, const void *buf); extern void gfs2_dinode_in(struct gfs2_dinode_host *di, const void *buf); extern void gfs2_dinode_out(const struct gfs2_dinode_host *di, void *buf); extern void gfs2_ea_header_in(struct gfs2_ea_header *ea, const void *buf); -- cgit v1.2.3 From bd209cc017f231e8536550bdab1bf5da93c32798 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 13 Oct 2006 23:43:19 -0400 Subject: [GFS2] split and annotate gfs2_statfs_change Signed-off-by: Al Viro Signed-off-by: Steven Whitehouse --- include/linux/gfs2_ondisk.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfs2_ondisk.h b/include/linux/gfs2_ondisk.h index 431e03b85458..3ce3a47b720a 100644 --- a/include/linux/gfs2_ondisk.h +++ b/include/linux/gfs2_ondisk.h @@ -497,6 +497,12 @@ struct gfs2_statfs_change { __be64 sc_dinodes; }; +struct gfs2_statfs_change_host { + __u64 sc_total; + __u64 sc_free; + __u64 sc_dinodes; +}; + /* * Quota change * Describes an allocation change for a particular @@ -529,8 +535,8 @@ extern void gfs2_ea_header_out(const struct gfs2_ea_header *ea, void *buf); extern void gfs2_log_header_in(struct gfs2_log_header_host *lh, const void *buf); extern void gfs2_inum_range_in(struct gfs2_inum_range_host *ir, const void *buf); extern void gfs2_inum_range_out(const struct gfs2_inum_range_host *ir, void *buf); -extern void gfs2_statfs_change_in(struct gfs2_statfs_change *sc, const void *buf); -extern void gfs2_statfs_change_out(const struct gfs2_statfs_change *sc, void *buf); +extern void gfs2_statfs_change_in(struct gfs2_statfs_change_host *sc, const void *buf); +extern void gfs2_statfs_change_out(const struct gfs2_statfs_change_host *sc, void *buf); extern void gfs2_quota_change_in(struct gfs2_quota_change *qc, const void *buf); /* Printing functions */ -- cgit v1.2.3 From b62f963e1fdf838fed91faec21228d421a834f2d Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 13 Oct 2006 23:46:46 -0400 Subject: [GFS2] split and annotate gfs2_quota_change Signed-off-by: Al Viro Signed-off-by: Steven Whitehouse --- include/linux/gfs2_ondisk.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/gfs2_ondisk.h b/include/linux/gfs2_ondisk.h index 3ce3a47b720a..10a507dfd834 100644 --- a/include/linux/gfs2_ondisk.h +++ b/include/linux/gfs2_ondisk.h @@ -517,6 +517,12 @@ struct gfs2_quota_change { __be32 qc_id; }; +struct gfs2_quota_change_host { + __u64 qc_change; + __u32 qc_flags; /* GFS2_QCF_... */ + __u32 qc_id; +}; + #ifdef __KERNEL__ /* Translation functions */ @@ -537,7 +543,7 @@ extern void gfs2_inum_range_in(struct gfs2_inum_range_host *ir, const void *buf) extern void gfs2_inum_range_out(const struct gfs2_inum_range_host *ir, void *buf); extern void gfs2_statfs_change_in(struct gfs2_statfs_change_host *sc, const void *buf); extern void gfs2_statfs_change_out(const struct gfs2_statfs_change_host *sc, void *buf); -extern void gfs2_quota_change_in(struct gfs2_quota_change *qc, const void *buf); +extern void gfs2_quota_change_in(struct gfs2_quota_change_host *qc, const void *buf); /* Printing functions */ -- cgit v1.2.3 From 539e5d6b7ae8612c0393fe940d2da5b591318d3d Mon Sep 17 00:00:00 2001 From: Steven Whitehouse Date: Tue, 31 Oct 2006 15:07:05 -0500 Subject: [GFS2] Change argument of gfs2_dinode_out Everywhere this was called, a struct gfs2_inode was available, but despite that, it was always called with a struct gfs2_dinode as an argument. By making this change it paves the way to start eliminating fields duplicated between the kernel's struct inode and the struct gfs2_dinode. Signed-off-by: Steven Whitehouse --- include/linux/gfs2_ondisk.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/gfs2_ondisk.h b/include/linux/gfs2_ondisk.h index 10a507dfd834..550effaf0c2b 100644 --- a/include/linux/gfs2_ondisk.h +++ b/include/linux/gfs2_ondisk.h @@ -535,7 +535,8 @@ extern void gfs2_rgrp_in(struct gfs2_rgrp_host *rg, const void *buf); extern void gfs2_rgrp_out(const struct gfs2_rgrp_host *rg, void *buf); extern void gfs2_quota_in(struct gfs2_quota_host *qu, const void *buf); extern void gfs2_dinode_in(struct gfs2_dinode_host *di, const void *buf); -extern void gfs2_dinode_out(const struct gfs2_dinode_host *di, void *buf); +struct gfs2_inode; +extern void gfs2_dinode_out(const struct gfs2_inode *ip, void *buf); extern void gfs2_ea_header_in(struct gfs2_ea_header *ea, const void *buf); extern void gfs2_ea_header_out(const struct gfs2_ea_header *ea, void *buf); extern void gfs2_log_header_in(struct gfs2_log_header_host *lh, const void *buf); -- cgit v1.2.3 From 891ea14712da68e282de8583e5fa14f0d3f3731e Mon Sep 17 00:00:00 2001 From: Steven Whitehouse Date: Tue, 31 Oct 2006 15:22:10 -0500 Subject: [GFS2] Change argument to gfs2_dinode_in This is a preliminary patch to enable the removal of fields in gfs2_dinode_host which are duplicated in struct inode. Signed-off-by: Steven Whitehouse --- include/linux/gfs2_ondisk.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/gfs2_ondisk.h b/include/linux/gfs2_ondisk.h index 550effaf0c2b..08d8240ba533 100644 --- a/include/linux/gfs2_ondisk.h +++ b/include/linux/gfs2_ondisk.h @@ -534,8 +534,8 @@ extern void gfs2_rindex_out(const struct gfs2_rindex_host *ri, void *buf); extern void gfs2_rgrp_in(struct gfs2_rgrp_host *rg, const void *buf); extern void gfs2_rgrp_out(const struct gfs2_rgrp_host *rg, void *buf); extern void gfs2_quota_in(struct gfs2_quota_host *qu, const void *buf); -extern void gfs2_dinode_in(struct gfs2_dinode_host *di, const void *buf); struct gfs2_inode; +extern void gfs2_dinode_in(struct gfs2_inode *ip, const void *buf); extern void gfs2_dinode_out(const struct gfs2_inode *ip, void *buf); extern void gfs2_ea_header_in(struct gfs2_ea_header *ea, const void *buf); extern void gfs2_ea_header_out(const struct gfs2_ea_header *ea, void *buf); -- cgit v1.2.3 From ea744d01c6a5acf1f6171b4c6e1658a742063613 Mon Sep 17 00:00:00 2001 From: Steven Whitehouse Date: Tue, 31 Oct 2006 15:28:00 -0500 Subject: [GFS2] Move gfs2_dinode_in to inode.c gfs2_dinode_in() is only ever called from one place, so move it to that place (in inode.c) and make it static. Signed-off-by: Steven Whitehouse --- include/linux/gfs2_ondisk.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/gfs2_ondisk.h b/include/linux/gfs2_ondisk.h index 08d8240ba533..4fc297a1ef95 100644 --- a/include/linux/gfs2_ondisk.h +++ b/include/linux/gfs2_ondisk.h @@ -528,6 +528,7 @@ struct gfs2_quota_change_host { extern void gfs2_inum_in(struct gfs2_inum_host *no, const void *buf); extern void gfs2_inum_out(const struct gfs2_inum_host *no, void *buf); +extern void gfs2_meta_header_in(struct gfs2_meta_header_host *mh, const void *buf); extern void gfs2_sb_in(struct gfs2_sb_host *sb, const void *buf); extern void gfs2_rindex_in(struct gfs2_rindex_host *ri, const void *buf); extern void gfs2_rindex_out(const struct gfs2_rindex_host *ri, void *buf); @@ -535,7 +536,6 @@ extern void gfs2_rgrp_in(struct gfs2_rgrp_host *rg, const void *buf); extern void gfs2_rgrp_out(const struct gfs2_rgrp_host *rg, void *buf); extern void gfs2_quota_in(struct gfs2_quota_host *qu, const void *buf); struct gfs2_inode; -extern void gfs2_dinode_in(struct gfs2_inode *ip, const void *buf); extern void gfs2_dinode_out(const struct gfs2_inode *ip, void *buf); extern void gfs2_ea_header_in(struct gfs2_ea_header *ea, const void *buf); extern void gfs2_ea_header_out(const struct gfs2_ea_header *ea, void *buf); -- cgit v1.2.3 From 4cc14f0b88bf3e0b508143e091eb5a8dff3e3b9c Mon Sep 17 00:00:00 2001 From: Steven Whitehouse Date: Tue, 31 Oct 2006 19:00:24 -0500 Subject: [GFS2] Change argument to gfs2_dinode_print Change argument for gfs2_dinode_print in order to prepare for removal of duplicate fields between struct inode and struct gfs2_dinode_host. Signed-off-by: Steven Whitehouse --- include/linux/gfs2_ondisk.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/gfs2_ondisk.h b/include/linux/gfs2_ondisk.h index 4fc297a1ef95..cf4c655d0d5f 100644 --- a/include/linux/gfs2_ondisk.h +++ b/include/linux/gfs2_ondisk.h @@ -549,7 +549,7 @@ extern void gfs2_quota_change_in(struct gfs2_quota_change_host *qc, const void * /* Printing functions */ extern void gfs2_rindex_print(const struct gfs2_rindex_host *ri); -extern void gfs2_dinode_print(const struct gfs2_dinode_host *di); +extern void gfs2_dinode_print(const struct gfs2_inode *ip); #endif /* __KERNEL__ */ -- cgit v1.2.3 From af339c0241d0dd3b35f9097b4f4999bb22ffe502 Mon Sep 17 00:00:00 2001 From: Steven Whitehouse Date: Wed, 1 Nov 2006 10:34:15 -0500 Subject: [GFS2] Shrink gfs2_inode (1) - di_header/di_num The metadata header doesn't need to be stored in the incore struct gfs2_inode since its constant, and this patch removes it. Also, there is already a field for the inode's number in the struct gfs2_inode, so we don't need one in struct gfs2_dinode_host as well. This saves 28 bytes of space in the struct gfs2_inode. Signed-off-by: Steven Whitehouse --- include/linux/gfs2_ondisk.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfs2_ondisk.h b/include/linux/gfs2_ondisk.h index cf4c655d0d5f..c0e76fc718c7 100644 --- a/include/linux/gfs2_ondisk.h +++ b/include/linux/gfs2_ondisk.h @@ -322,10 +322,6 @@ struct gfs2_dinode { }; struct gfs2_dinode_host { - struct gfs2_meta_header_host di_header; - - struct gfs2_inum_host di_num; - __u32 di_mode; /* mode of file */ __u32 di_uid; /* owner's user id */ __u32 di_gid; /* owner's group id */ @@ -528,7 +524,6 @@ struct gfs2_quota_change_host { extern void gfs2_inum_in(struct gfs2_inum_host *no, const void *buf); extern void gfs2_inum_out(const struct gfs2_inum_host *no, void *buf); -extern void gfs2_meta_header_in(struct gfs2_meta_header_host *mh, const void *buf); extern void gfs2_sb_in(struct gfs2_sb_host *sb, const void *buf); extern void gfs2_rindex_in(struct gfs2_rindex_host *ri, const void *buf); extern void gfs2_rindex_out(const struct gfs2_rindex_host *ri, void *buf); -- cgit v1.2.3 From e7f14f4d094ea1a9ce1953375f5bc1500c760c79 Mon Sep 17 00:00:00 2001 From: Steven Whitehouse Date: Tue, 31 Oct 2006 21:45:08 -0500 Subject: [GFS2] Shrink gfs2_inode (2) - di_major/di_minor This removes the device numbers from this structure by using inode->i_rdev instead. It also cleans up the code in gfs2_mknod. It results in shrinking the gfs2_inode by 8 bytes. Signed-off-by: Steven Whitehouse --- include/linux/gfs2_ondisk.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfs2_ondisk.h b/include/linux/gfs2_ondisk.h index c0e76fc718c7..5bcf895b2731 100644 --- a/include/linux/gfs2_ondisk.h +++ b/include/linux/gfs2_ondisk.h @@ -331,8 +331,6 @@ struct gfs2_dinode_host { __u64 di_atime; /* time last accessed */ __u64 di_mtime; /* time last modified */ __u64 di_ctime; /* time last changed */ - __u32 di_major; /* device major number */ - __u32 di_minor; /* device minor number */ /* This section varies from gfs1. Padding added to align with * remainder of dinode -- cgit v1.2.3 From b60623c238b6a819bd04090139704e2cb57a751f Mon Sep 17 00:00:00 2001 From: Steven Whitehouse Date: Wed, 1 Nov 2006 12:22:46 -0500 Subject: [GFS2] Shrink gfs2_inode (3) - di_mode This removes the duplicate di_mode field in favour of using the inode->i_mode field. This saves 4 bytes. Signed-off-by: Steven Whitehouse --- include/linux/gfs2_ondisk.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/gfs2_ondisk.h b/include/linux/gfs2_ondisk.h index 5bcf895b2731..f1ea0b48060b 100644 --- a/include/linux/gfs2_ondisk.h +++ b/include/linux/gfs2_ondisk.h @@ -322,7 +322,6 @@ struct gfs2_dinode { }; struct gfs2_dinode_host { - __u32 di_mode; /* mode of file */ __u32 di_uid; /* owner's user id */ __u32 di_gid; /* owner's group id */ __u32 di_nlink; /* number of links to this file */ -- cgit v1.2.3 From 2933f9254a6af33db25270778c998a42029da668 Mon Sep 17 00:00:00 2001 From: Steven Whitehouse Date: Wed, 1 Nov 2006 13:23:29 -0500 Subject: [GFS2] Shrink gfs2_inode (4) - di_uid/di_gid Remove duplicate di_uid/di_gid fields in favour of using inode->i_uid/inode->i_gid instead. This saves 8 bytes. Signed-off-by: Steven Whitehouse --- include/linux/gfs2_ondisk.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfs2_ondisk.h b/include/linux/gfs2_ondisk.h index f1ea0b48060b..896c7f81a637 100644 --- a/include/linux/gfs2_ondisk.h +++ b/include/linux/gfs2_ondisk.h @@ -322,8 +322,6 @@ struct gfs2_dinode { }; struct gfs2_dinode_host { - __u32 di_uid; /* owner's user id */ - __u32 di_gid; /* owner's group id */ __u32 di_nlink; /* number of links to this file */ __u64 di_size; /* number of bytes in file */ __u64 di_blocks; /* number of blocks in file */ -- cgit v1.2.3 From 4f56110a00af5fb2e22fbccfcaf944d62cae8fcf Mon Sep 17 00:00:00 2001 From: Steven Whitehouse Date: Wed, 1 Nov 2006 14:04:17 -0500 Subject: [GFS2] Shrink gfs2_inode (5) - di_nlink Remove the di_nlink field in favour of inode->i_nlink and update the nlink handling to use the proper macros. This saves 4 bytes. Signed-off-by: Steven Whitehouse --- include/linux/gfs2_ondisk.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/gfs2_ondisk.h b/include/linux/gfs2_ondisk.h index 896c7f81a637..c61517b35b2e 100644 --- a/include/linux/gfs2_ondisk.h +++ b/include/linux/gfs2_ondisk.h @@ -322,7 +322,6 @@ struct gfs2_dinode { }; struct gfs2_dinode_host { - __u32 di_nlink; /* number of links to this file */ __u64 di_size; /* number of bytes in file */ __u64 di_blocks; /* number of blocks in file */ __u64 di_atime; /* time last accessed */ -- cgit v1.2.3 From 1a7b1eed5802502fd649e04784becd58557fdcf1 Mon Sep 17 00:00:00 2001 From: Steven Whitehouse Date: Wed, 1 Nov 2006 14:35:17 -0500 Subject: [GFS2] Shrink gfs2_inode (6) - di_atime/di_mtime/di_ctime Remove the di_[amc]time fields and use inode->i_[amc]time fields instead. This saves 24 bytes from the gfs2_inode. Signed-off-by: Steven Whitehouse --- include/linux/gfs2_ondisk.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfs2_ondisk.h b/include/linux/gfs2_ondisk.h index c61517b35b2e..7f5a4a16224b 100644 --- a/include/linux/gfs2_ondisk.h +++ b/include/linux/gfs2_ondisk.h @@ -324,9 +324,6 @@ struct gfs2_dinode { struct gfs2_dinode_host { __u64 di_size; /* number of bytes in file */ __u64 di_blocks; /* number of blocks in file */ - __u64 di_atime; /* time last accessed */ - __u64 di_mtime; /* time last modified */ - __u64 di_ctime; /* time last changed */ /* This section varies from gfs1. Padding added to align with * remainder of dinode -- cgit v1.2.3 From a9583c7983cbba9726bfe64ee46613d654fc9e26 Mon Sep 17 00:00:00 2001 From: Steven Whitehouse Date: Wed, 1 Nov 2006 20:09:14 -0500 Subject: [GFS2] Shrink gfs2_inode (7) - di_payload_format This is almost never used. Its there for backward compatibility with GFS1. It doesn't need its own field since it can always be calculated from the inode mode & flags. This saves a bit more space in the gfs2_inode. Signed-off-by: Steven Whitehouse --- include/linux/gfs2_ondisk.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/gfs2_ondisk.h b/include/linux/gfs2_ondisk.h index 7f5a4a16224b..536575efb62a 100644 --- a/include/linux/gfs2_ondisk.h +++ b/include/linux/gfs2_ondisk.h @@ -333,7 +333,6 @@ struct gfs2_dinode_host { __u64 di_generation; /* generation number for NFS */ __u32 di_flags; /* GFS2_DIF_... */ - __u32 di_payload_format; /* GFS2_FORMAT_... */ __u16 di_height; /* height of metadata */ /* These only apply to directories */ -- cgit v1.2.3 From f6e58f01e8dc869803b9f73b2aa9d5bc3f32ca05 Mon Sep 17 00:00:00 2001 From: Steven Whitehouse Date: Tue, 7 Nov 2006 15:14:58 -0500 Subject: [GFS2] Don't copy meta_header for rgrp in and out The meta_header for an ondisk rgrp never changes, so there is no point copying it in and back out to disk. Also there is no reason to keep a copy for each rgrp in memory. The code already checks to ensure that the header is correct before it calls the routine to copy the data in, so that we don't even need to check whether its correct on disk in the functions in ondisk.c Signed-off-by: Steven Whitehouse --- include/linux/gfs2_ondisk.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfs2_ondisk.h b/include/linux/gfs2_ondisk.h index 536575efb62a..8b7e4c1e32ae 100644 --- a/include/linux/gfs2_ondisk.h +++ b/include/linux/gfs2_ondisk.h @@ -213,8 +213,6 @@ struct gfs2_rgrp { }; struct gfs2_rgrp_host { - struct gfs2_meta_header_host rg_header; - __u32 rg_flags; __u32 rg_free; __u32 rg_dinodes; -- cgit v1.2.3 From be1c63411addba3ad750eb4fdfc50b97bc82825e Mon Sep 17 00:00:00 2001 From: Olaf Kirch Date: Fri, 1 Dec 2006 10:39:12 +0100 Subject: [PATCH] blktrace: add timestamp message This adds a new timestamp message to blktrace, giving the timeofday when we starting tracing. This helps user space correlate block trace events with eg an application strace. This requires a (compatible) update to blkparse. The changed blkparse is still able to process traces generated by older kernels, and older versions of blkparse should silently ignore the new records (because they have a pid of 0). Signed-off-by: Olaf Kirch Signed-off-by: Jens Axboe --- include/linux/blktrace_api.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index b99a714fcac6..3680ff9a30ed 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -49,6 +49,15 @@ enum blktrace_act { __BLK_TA_REMAP, /* bio was remapped */ }; +/* + * Notify events. + */ +enum blktrace_notify { + __BLK_TN_PROCESS = 0, /* establish pid/name mapping */ + __BLK_TN_TIMESTAMP, /* include system clock */ +}; + + /* * Trace actions in full. Additionally, read or write is masked */ @@ -68,6 +77,9 @@ enum blktrace_act { #define BLK_TA_BOUNCE (__BLK_TA_BOUNCE) #define BLK_TA_REMAP (__BLK_TA_REMAP | BLK_TC_ACT(BLK_TC_QUEUE)) +#define BLK_TN_PROCESS (__BLK_TN_PROCESS | BLK_TC_ACT(BLK_TC_NOTIFY)) +#define BLK_TN_TIMESTAMP (__BLK_TN_TIMESTAMP | BLK_TC_ACT(BLK_TC_NOTIFY)) + #define BLK_IO_TRACE_MAGIC 0x65617400 #define BLK_IO_TRACE_VERSION 0x07 -- cgit v1.2.3 From 0e75f9063f5c55fb0b0b546a7c356f8ec186825e Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Fri, 1 Dec 2006 10:40:55 +0100 Subject: [PATCH] block: support larger block pc requests This patch modifies blk_rq_map/unmap_user() and the cdrom and scsi_ioctl.c users so that it supports requests larger than bio by chaining them together. Signed-off-by: Mike Christie Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 7bfcde2d5578..e1c7286165ff 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -678,10 +678,11 @@ extern void __blk_stop_queue(request_queue_t *q); extern void blk_run_queue(request_queue_t *); extern void blk_start_queueing(request_queue_t *); extern void blk_queue_activity_fn(request_queue_t *, activity_fn *, void *); -extern int blk_rq_map_user(request_queue_t *, struct request *, void __user *, unsigned int); -extern int blk_rq_unmap_user(struct bio *, unsigned int); +extern int blk_rq_map_user(request_queue_t *, struct request *, void __user *, unsigned long); +extern int blk_rq_unmap_user(struct request *); extern int blk_rq_map_kern(request_queue_t *, struct request *, void *, unsigned int, gfp_t); -extern int blk_rq_map_user_iov(request_queue_t *, struct request *, struct sg_iovec *, int); +extern int blk_rq_map_user_iov(request_queue_t *, struct request *, + struct sg_iovec *, int, unsigned int); extern int blk_execute_rq(request_queue_t *, struct gendisk *, struct request *, int); extern void blk_execute_rq_nowait(request_queue_t *, struct gendisk *, -- cgit v1.2.3 From bb37b94c68e7b37eecea8576039ae9396ca07839 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 1 Dec 2006 10:42:33 +0100 Subject: [BLOCK] Cleanup unused variable passing - ->init_queue() does not need the elevator passed in - ->put_request() is a hot path and need not have the queue passed in - cfq_update_io_seektime() does not need cfqd passed in Signed-off-by: Jens Axboe --- include/linux/elevator.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 2fa9f1144228..a24931d24404 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -21,11 +21,11 @@ typedef void (elevator_completed_req_fn) (request_queue_t *, struct request *); typedef int (elevator_may_queue_fn) (request_queue_t *, int); typedef int (elevator_set_req_fn) (request_queue_t *, struct request *, gfp_t); -typedef void (elevator_put_req_fn) (request_queue_t *, struct request *); +typedef void (elevator_put_req_fn) (struct request *); typedef void (elevator_activate_req_fn) (request_queue_t *, struct request *); typedef void (elevator_deactivate_req_fn) (request_queue_t *, struct request *); -typedef void *(elevator_init_fn) (request_queue_t *, elevator_t *); +typedef void *(elevator_init_fn) (request_queue_t *); typedef void (elevator_exit_fn) (elevator_t *); struct elevator_ops -- cgit v1.2.3 From bce40a36de574376f41f1ff3c4d212a7da2a3c90 Mon Sep 17 00:00:00 2001 From: Philip Langdale Date: Sat, 21 Oct 2006 12:35:02 +0200 Subject: [PATCH] mmc: Add support for mmc v4 high speed mode This adds support for the high-speed modes defined by mmc v4 (assuming the host controller is up to it). On a TI sdhci controller, it improves read speed from 1.3MBps to 2.3MBps. The TI controller can only go up to 24MHz, but everything helps. Another person has taken this basic patch and used it on a Nokia 770 to get a bigger boost because that controller can run at 48MHZ. Signed-off-by: Philip Langdale Signed-off-by: Pierre Ossman --- include/linux/mmc/card.h | 8 ++++++++ include/linux/mmc/protocol.h | 47 +++++++++++++++++++++++++++++++++++++++++--- 2 files changed, 52 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index 991a37382a22..ce25256f80d5 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -39,6 +39,10 @@ struct mmc_csd { write_misalign:1; }; +struct mmc_ext_csd { + unsigned int hs_max_dtr; +}; + struct sd_scr { unsigned char sda_vsn; unsigned char bus_widths; @@ -62,11 +66,13 @@ struct mmc_card { #define MMC_STATE_BAD (1<<2) /* unrecognised device */ #define MMC_STATE_SDCARD (1<<3) /* is an SD card */ #define MMC_STATE_READONLY (1<<4) /* card is read-only */ +#define MMC_STATE_HIGHSPEED (1<<5) /* card is in mmc4 highspeed mode */ u32 raw_cid[4]; /* raw card CID */ u32 raw_csd[4]; /* raw card CSD */ u32 raw_scr[2]; /* raw card SCR */ struct mmc_cid cid; /* card identification */ struct mmc_csd csd; /* card specific */ + struct mmc_ext_csd ext_csd; /* mmc v4 extended card specific */ struct sd_scr scr; /* extra SD information */ }; @@ -75,12 +81,14 @@ struct mmc_card { #define mmc_card_bad(c) ((c)->state & MMC_STATE_BAD) #define mmc_card_sd(c) ((c)->state & MMC_STATE_SDCARD) #define mmc_card_readonly(c) ((c)->state & MMC_STATE_READONLY) +#define mmc_card_highspeed(c) ((c)->state & MMC_STATE_HIGHSPEED) #define mmc_card_set_present(c) ((c)->state |= MMC_STATE_PRESENT) #define mmc_card_set_dead(c) ((c)->state |= MMC_STATE_DEAD) #define mmc_card_set_bad(c) ((c)->state |= MMC_STATE_BAD) #define mmc_card_set_sd(c) ((c)->state |= MMC_STATE_SDCARD) #define mmc_card_set_readonly(c) ((c)->state |= MMC_STATE_READONLY) +#define mmc_card_set_highspeed(c) ((c)->state |= MMC_STATE_HIGHSPEED) #define mmc_card_name(c) ((c)->cid.prod_name) #define mmc_card_id(c) ((c)->dev.bus_id) diff --git a/include/linux/mmc/protocol.h b/include/linux/mmc/protocol.h index 08dec8d9e703..311b6547f561 100644 --- a/include/linux/mmc/protocol.h +++ b/include/linux/mmc/protocol.h @@ -25,14 +25,16 @@ #ifndef MMC_MMC_PROTOCOL_H #define MMC_MMC_PROTOCOL_H -/* Standard MMC commands (3.1) type argument response */ +/* Standard MMC commands (4.1) type argument response */ /* class 1 */ #define MMC_GO_IDLE_STATE 0 /* bc */ #define MMC_SEND_OP_COND 1 /* bcr [31:0] OCR R3 */ #define MMC_ALL_SEND_CID 2 /* bcr R2 */ #define MMC_SET_RELATIVE_ADDR 3 /* ac [31:16] RCA R1 */ #define MMC_SET_DSR 4 /* bc [31:16] RCA */ +#define MMC_SWITCH 6 /* ac [31:0] See below R1b */ #define MMC_SELECT_CARD 7 /* ac [31:16] RCA R1 */ +#define MMC_SEND_EXT_CSD 8 /* adtc R1 */ #define MMC_SEND_CSD 9 /* ac [31:16] RCA R2 */ #define MMC_SEND_CID 10 /* ac [31:16] RCA R2 */ #define MMC_READ_DAT_UNTIL_STOP 11 /* adtc [31:0] dadr R1 */ @@ -87,6 +89,17 @@ #define SD_APP_OP_COND 41 /* bcr [31:0] OCR R3 */ #define SD_APP_SEND_SCR 51 /* adtc R1 */ +/* + * MMC_SWITCH argument format: + * + * [31:26] Always 0 + * [25:24] Access Mode + * [23:16] Location of target Byte in EXT_CSD + * [15:08] Value Byte + * [07:03] Always 0 + * [02:00] Command Set + */ + /* MMC status in R1 Type @@ -230,13 +243,41 @@ struct _mmc_csd { #define CSD_STRUCT_VER_1_0 0 /* Valid for system specification 1.0 - 1.2 */ #define CSD_STRUCT_VER_1_1 1 /* Valid for system specification 1.4 - 2.2 */ -#define CSD_STRUCT_VER_1_2 2 /* Valid for system specification 3.1 */ +#define CSD_STRUCT_VER_1_2 2 /* Valid for system specification 3.1 - 3.2 - 3.31 - 4.0 - 4.1 */ +#define CSD_STRUCT_EXT_CSD 3 /* Version is coded in CSD_STRUCTURE in EXT_CSD */ #define CSD_SPEC_VER_0 0 /* Implements system specification 1.0 - 1.2 */ #define CSD_SPEC_VER_1 1 /* Implements system specification 1.4 */ #define CSD_SPEC_VER_2 2 /* Implements system specification 2.0 - 2.2 */ -#define CSD_SPEC_VER_3 3 /* Implements system specification 3.1 */ +#define CSD_SPEC_VER_3 3 /* Implements system specification 3.1 - 3.2 - 3.31 */ +#define CSD_SPEC_VER_4 4 /* Implements system specification 4.0 - 4.1 */ + +/* + * EXT_CSD fields + */ + +#define EXT_CSD_HS_TIMING 185 /* R/W */ +#define EXT_CSD_CARD_TYPE 196 /* RO */ + +/* + * EXT_CSD field definitions + */ + +#define EXT_CSD_CMD_SET_NORMAL (1<<0) +#define EXT_CSD_CMD_SET_SECURE (1<<1) +#define EXT_CSD_CMD_SET_CPSECURE (1<<2) + +#define EXT_CSD_CARD_TYPE_26 (1<<0) /* Card can run at 26MHz */ +#define EXT_CSD_CARD_TYPE_52 (1<<1) /* Card can run at 52MHz */ + +/* + * MMC_SWITCH access modes + */ +#define MMC_SWITCH_MODE_CMD_SET 0x00 /* Change the command set */ +#define MMC_SWITCH_MODE_SET_BITS 0x01 /* Set bits which are 1 in value */ +#define MMC_SWITCH_MODE_CLEAR_BITS 0x02 /* Clear bits which are 1 in value */ +#define MMC_SWITCH_MODE_WRITE_BYTE 0x03 /* Set target to value */ /* * SD bus widths -- cgit v1.2.3 From e45a1bd20fa5b920901879e85cdf5eda21f78d7c Mon Sep 17 00:00:00 2001 From: Philip Langdale Date: Sun, 29 Oct 2006 10:14:19 +0100 Subject: mmc: Add support for mmc v4 wide-bus modes This change adds support for the mmc4 4-bit wide-bus mode. The mmc4 spec defines 8-bit and 4-bit transfer modes. As we do not support any 8-bit hardware, this patch only adds support for the 4-bit mode, but it can easily be built upon when the time comes. The 4-bit mode is electrically compatible with SD's 4-bit mode but the procedure for turning it on is different. This patch implements only the essential parts of the procedure as defined by the spec. Two additional steps are recommended but not compulsory. I am documenting them here so that there's a record. 1) A bus-test mechanism is implemented using dedicated mmc commands which allow for testing the functionality of the data bus at the electrical level. This is pretty paranoid and they way the commands work is not compatible with the mmc subsystem (they don't set valid CRC values). 2) MMC v4 cards can indicate they would like to draw more than the default amount of current in wide-bus modes. We currently will never switch the card into a higher draw mode. Supposedly, allowing the card to draw more current will let it perform better, but the specs seem to indicate that the card will function correctly without the mode change. Empirical testing supports this interpretation. Signed-off-by: Philip Langdale Signed-off-by: Pierre Ossman --- include/linux/mmc/protocol.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/protocol.h b/include/linux/mmc/protocol.h index 311b6547f561..45c51fd85786 100644 --- a/include/linux/mmc/protocol.h +++ b/include/linux/mmc/protocol.h @@ -256,6 +256,7 @@ struct _mmc_csd { * EXT_CSD fields */ +#define EXT_CSD_BUS_WIDTH 183 /* R/W */ #define EXT_CSD_HS_TIMING 185 /* R/W */ #define EXT_CSD_CARD_TYPE 196 /* RO */ @@ -270,6 +271,10 @@ struct _mmc_csd { #define EXT_CSD_CARD_TYPE_26 (1<<0) /* Card can run at 26MHz */ #define EXT_CSD_CARD_TYPE_52 (1<<1) /* Card can run at 52MHz */ +#define EXT_CSD_BUS_WIDTH_1 0 /* Card is in 1 bit mode */ +#define EXT_CSD_BUS_WIDTH_4 1 /* Card is in 4 bit mode */ +#define EXT_CSD_BUS_WIDTH_8 2 /* Card is in 8 bit mode */ + /* * MMC_SWITCH access modes */ -- cgit v1.2.3 From 7ccd266e676a3f0c6f8f897f58b684cac3dd1650 Mon Sep 17 00:00:00 2001 From: Pierre Ossman Date: Wed, 8 Nov 2006 23:03:10 +0100 Subject: mmc: Support for high speed SD cards Modern SD cards support a clock speed of 50 MHz. Make sure we test for this capability and do the song and dance required to activate it. Activating high speed support actually modifies the TRAN_SPEED field of the CSD. But as the spec says that the cards must report 50 MHz, we might as well skip re-reading the CSD. Signed-off-by: Pierre Ossman --- include/linux/mmc/card.h | 7 ++++++- include/linux/mmc/protocol.h | 22 ++++++++++++++++++++++ 2 files changed, 28 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index ce25256f80d5..d0e6a5497614 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -50,6 +50,10 @@ struct sd_scr { #define SD_SCR_BUS_WIDTH_4 (1<<2) }; +struct sd_switch_caps { + unsigned int hs_max_dtr; +}; + struct mmc_host; /* @@ -66,7 +70,7 @@ struct mmc_card { #define MMC_STATE_BAD (1<<2) /* unrecognised device */ #define MMC_STATE_SDCARD (1<<3) /* is an SD card */ #define MMC_STATE_READONLY (1<<4) /* card is read-only */ -#define MMC_STATE_HIGHSPEED (1<<5) /* card is in mmc4 highspeed mode */ +#define MMC_STATE_HIGHSPEED (1<<5) /* card is in high speed mode */ u32 raw_cid[4]; /* raw card CID */ u32 raw_csd[4]; /* raw card CSD */ u32 raw_scr[2]; /* raw card SCR */ @@ -74,6 +78,7 @@ struct mmc_card { struct mmc_csd csd; /* card specific */ struct mmc_ext_csd ext_csd; /* mmc v4 extended card specific */ struct sd_scr scr; /* extra SD information */ + struct sd_switch_caps sw_caps; /* switch (CMD6) caps */ }; #define mmc_card_present(c) ((c)->state & MMC_STATE_PRESENT) diff --git a/include/linux/mmc/protocol.h b/include/linux/mmc/protocol.h index 45c51fd85786..2dce60c43f4b 100644 --- a/include/linux/mmc/protocol.h +++ b/include/linux/mmc/protocol.h @@ -82,6 +82,7 @@ /* class 8 */ /* This is basically the same command as for MMC with some quirks. */ #define SD_SEND_RELATIVE_ADDR 3 /* bcr R6 */ +#define SD_SWITCH 6 /* adtc [31:0] See below R1 */ /* Application commands */ #define SD_APP_SET_BUS_WIDTH 6 /* ac [1:0] bus width R1 */ @@ -100,6 +101,19 @@ * [02:00] Command Set */ +/* + * SD_SWITCH argument format: + * + * [31] Check (0) or switch (1) + * [30:24] Reserved (0) + * [23:20] Function group 6 + * [19:16] Function group 5 + * [15:12] Function group 4 + * [11:8] Function group 3 + * [7:4] Function group 2 + * [3:0] Function group 1 + */ + /* MMC status in R1 Type @@ -284,6 +298,14 @@ struct _mmc_csd { #define MMC_SWITCH_MODE_CLEAR_BITS 0x02 /* Clear bits which are 1 in value */ #define MMC_SWITCH_MODE_WRITE_BYTE 0x03 /* Set target to value */ +/* + * SCR field definitions + */ + +#define SCR_SPEC_VER_0 0 /* Implements system specification 1.0 - 1.01 */ +#define SCR_SPEC_VER_1 1 /* Implements system specification 1.10 */ +#define SCR_SPEC_VER_2 2 /* Implements system specification 2.00 */ + /* * SD bus widths */ -- cgit v1.2.3 From 437052516779fea608261a50682b124315f48f01 Mon Sep 17 00:00:00 2001 From: "inaky@linux.intel.com" Date: Wed, 11 Oct 2006 20:05:58 -0700 Subject: usb/hub: allow hubs up to 31 children Current Wireless USB host hardware (Intel i1480 for example) allows up to 22 devices to connect, thus bringing up the max number of children in the WUSB Host Controller to 22 'fake' ports. Upcoming hardware might raise that limit. Makes almost no difference to go to 31, as the bit arrays are byte-aligned (plus an extra bit in general), so 22 bits fit in 4 bytes as 31 do. As well, the only other array that depends on USB_MAXCHILDREN is 'struct usb_hub->indicator'. By declaring it 'u8' instead of 'enum hub_led_mode', we reduce the size of each entry from 4 bytes (in i386) to 1, which will add as we when are doubling USB_MAXCHILDREN (with 16 the size of that array is 64 bytes, with 31 would be 128; by using u8 that goes down to 31 bytes). Signed-off-by: Inaky Perez-Gonzalez Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index 5482bfb3303d..e5cb1690975a 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -313,8 +313,13 @@ struct usb_bus { /* This is arbitrary. * From USB 2.0 spec Table 11-13, offset 7, a hub can * have up to 255 ports. The most yet reported is 10. + * + * Current Wireless USB host hardware (Intel i1480 for example) allows + * up to 22 devices to connect. Upcoming hardware might raise that + * limit. Because the arrays need to add a bit for hub status data, we + * do 31, so plus one evens out to four bytes. */ -#define USB_MAXCHILDREN (16) +#define USB_MAXCHILDREN (31) struct usb_tt; -- cgit v1.2.3 From 0c1ac4f25f894f9df0ffe9b912c165fb6a185a3c Mon Sep 17 00:00:00 2001 From: "Luiz Fernando N. Capitulino" Date: Mon, 30 Oct 2006 14:53:03 -0300 Subject: USB: makes usb_endpoint_* functions inline. We have no benefits of having the usb_endpoint_* functions as functions, but making them inline saves text and data segment sizes: text data bss dec hex filename 14893634 3108770 1108840 19111244 1239d4c vmlinux.func 14893185 3108566 1108840 19110591 1239abf vmlinux.inline This is the result of a 2.6.19-rc3 kernel compiled with GCC 4.1.1 without CONFIG_MODULES, CONFIG_CC_OPTIMIZE_FOR_SIZE, CONFIG_REGPARM options set. USB support is fully enabled (while most of the other drivers are not), and that kernel has most of the USB code ported to use the endpoint functions. That happens because a call to those functions are expensive (in terms of bytes), while the function's size is smaller or have the same 'size' of the call. Signed-off-by: Luiz Fernando N. Capitulino Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 142 ++++++++++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 131 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index e5cb1690975a..e732e024a141 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -495,17 +495,137 @@ static inline int usb_make_path (struct usb_device *dev, char *buf, /*-------------------------------------------------------------------------*/ -extern int usb_endpoint_dir_in(const struct usb_endpoint_descriptor *epd); -extern int usb_endpoint_dir_out(const struct usb_endpoint_descriptor *epd); -extern int usb_endpoint_xfer_bulk(const struct usb_endpoint_descriptor *epd); -extern int usb_endpoint_xfer_int(const struct usb_endpoint_descriptor *epd); -extern int usb_endpoint_xfer_isoc(const struct usb_endpoint_descriptor *epd); -extern int usb_endpoint_is_bulk_in(const struct usb_endpoint_descriptor *epd); -extern int usb_endpoint_is_bulk_out(const struct usb_endpoint_descriptor *epd); -extern int usb_endpoint_is_int_in(const struct usb_endpoint_descriptor *epd); -extern int usb_endpoint_is_int_out(const struct usb_endpoint_descriptor *epd); -extern int usb_endpoint_is_isoc_in(const struct usb_endpoint_descriptor *epd); -extern int usb_endpoint_is_isoc_out(const struct usb_endpoint_descriptor *epd); +/** + * usb_endpoint_dir_in - check if the endpoint has IN direction + * @epd: endpoint to be checked + * + * Returns true if the endpoint is of type IN, otherwise it returns false. + */ +static inline int usb_endpoint_dir_in(const struct usb_endpoint_descriptor *epd) +{ + return ((epd->bEndpointAddress & USB_ENDPOINT_DIR_MASK) == USB_DIR_IN); +} + +/** + * usb_endpoint_dir_out - check if the endpoint has OUT direction + * @epd: endpoint to be checked + * + * Returns true if the endpoint is of type OUT, otherwise it returns false. + */ +static inline int usb_endpoint_dir_out(const struct usb_endpoint_descriptor *epd) +{ + return ((epd->bEndpointAddress & USB_ENDPOINT_DIR_MASK) == USB_DIR_OUT); +} + +/** + * usb_endpoint_xfer_bulk - check if the endpoint has bulk transfer type + * @epd: endpoint to be checked + * + * Returns true if the endpoint is of type bulk, otherwise it returns false. + */ +static inline int usb_endpoint_xfer_bulk(const struct usb_endpoint_descriptor *epd) +{ + return ((epd->bmAttributes & USB_ENDPOINT_XFERTYPE_MASK) == + USB_ENDPOINT_XFER_BULK); +} + +/** + * usb_endpoint_xfer_int - check if the endpoint has interrupt transfer type + * @epd: endpoint to be checked + * + * Returns true if the endpoint is of type interrupt, otherwise it returns + * false. + */ +static inline int usb_endpoint_xfer_int(const struct usb_endpoint_descriptor *epd) +{ + return ((epd->bmAttributes & USB_ENDPOINT_XFERTYPE_MASK) == + USB_ENDPOINT_XFER_INT); +} + +/** + * usb_endpoint_xfer_isoc - check if the endpoint has isochronous transfer type + * @epd: endpoint to be checked + * + * Returns true if the endpoint is of type isochronous, otherwise it returns + * false. + */ +static inline int usb_endpoint_xfer_isoc(const struct usb_endpoint_descriptor *epd) +{ + return ((epd->bmAttributes & USB_ENDPOINT_XFERTYPE_MASK) == + USB_ENDPOINT_XFER_ISOC); +} + +/** + * usb_endpoint_is_bulk_in - check if the endpoint is bulk IN + * @epd: endpoint to be checked + * + * Returns true if the endpoint has bulk transfer type and IN direction, + * otherwise it returns false. + */ +static inline int usb_endpoint_is_bulk_in(const struct usb_endpoint_descriptor *epd) +{ + return (usb_endpoint_xfer_bulk(epd) && usb_endpoint_dir_in(epd)); +} + +/** + * usb_endpoint_is_bulk_out - check if the endpoint is bulk OUT + * @epd: endpoint to be checked + * + * Returns true if the endpoint has bulk transfer type and OUT direction, + * otherwise it returns false. + */ +static inline int usb_endpoint_is_bulk_out(const struct usb_endpoint_descriptor *epd) +{ + return (usb_endpoint_xfer_bulk(epd) && usb_endpoint_dir_out(epd)); +} + +/** + * usb_endpoint_is_int_in - check if the endpoint is interrupt IN + * @epd: endpoint to be checked + * + * Returns true if the endpoint has interrupt transfer type and IN direction, + * otherwise it returns false. + */ +static inline int usb_endpoint_is_int_in(const struct usb_endpoint_descriptor *epd) +{ + return (usb_endpoint_xfer_int(epd) && usb_endpoint_dir_in(epd)); +} + +/** + * usb_endpoint_is_int_out - check if the endpoint is interrupt OUT + * @epd: endpoint to be checked + * + * Returns true if the endpoint has interrupt transfer type and OUT direction, + * otherwise it returns false. + */ +static inline int usb_endpoint_is_int_out(const struct usb_endpoint_descriptor *epd) +{ + return (usb_endpoint_xfer_int(epd) && usb_endpoint_dir_out(epd)); +} + +/** + * usb_endpoint_is_isoc_in - check if the endpoint is isochronous IN + * @epd: endpoint to be checked + * + * Returns true if the endpoint has isochronous transfer type and IN direction, + * otherwise it returns false. + */ +static inline int usb_endpoint_is_isoc_in(const struct usb_endpoint_descriptor *epd) +{ + return (usb_endpoint_xfer_isoc(epd) && usb_endpoint_dir_in(epd)); +} + +/** + * usb_endpoint_is_isoc_out - check if the endpoint is isochronous OUT + * @epd: endpoint to be checked + * + * Returns true if the endpoint has isochronous transfer type and OUT direction, + * otherwise it returns false. + */ +static inline int usb_endpoint_is_isoc_out(const struct usb_endpoint_descriptor *epd) +{ + return (usb_endpoint_xfer_isoc(epd) && usb_endpoint_dir_out(epd)); +} /*-------------------------------------------------------------------------*/ -- cgit v1.2.3 From 692a186c9d5f12d43cef28d40c25247dc4f302f0 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Mon, 30 Oct 2006 17:07:51 -0500 Subject: USB: expand autosuspend/autoresume API This patch (as814) adds usb_autopm_set_interface() to the autosuspend API. It also provides convenient wrapper routines, usb_autopm_enable() and usb_autopm_disable(), for drivers that want to specify directly whether autosuspend should be allowed. Signed-off-by: Alan Stern Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 29 ++++++++++++++++++++++++++--- 1 file changed, 26 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index e732e024a141..864c6c21c21e 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -415,14 +415,37 @@ extern struct usb_device *usb_find_device(u16 vendor_id, u16 product_id); /* USB autosuspend and autoresume */ #ifdef CONFIG_USB_SUSPEND +extern int usb_autopm_set_interface(struct usb_interface *intf); extern int usb_autopm_get_interface(struct usb_interface *intf); extern void usb_autopm_put_interface(struct usb_interface *intf); +static inline void usb_autopm_enable(struct usb_interface *intf) +{ + intf->pm_usage_cnt = 0; + usb_autopm_set_interface(intf); +} + +static inline void usb_autopm_disable(struct usb_interface *intf) +{ + intf->pm_usage_cnt = 1; + usb_autopm_set_interface(intf); +} + #else -#define usb_autopm_get_interface(intf) 0 -#define usb_autopm_put_interface(intf) do {} while (0) -#endif +static inline int usb_autopm_set_interface(struct usb_interface *intf) +{ return 0; } + +static inline int usb_autopm_get_interface(struct usb_interface *intf) +{ return 0; } + +static inline void usb_autopm_put_interface(struct usb_interface *intf) +{ } +static inline void usb_autopm_enable(struct usb_interface *intf) +{ } +static inline void usb_autopm_disable(struct usb_interface *intf) +{ } +#endif /*-------------------------------------------------------------------------*/ -- cgit v1.2.3 From ce3615879ae85373c03744b45b7c2d7ae5e29b2a Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Mon, 20 Nov 2006 11:12:22 -0500 Subject: USB: struct usb_device: change flag to bitflag This patch (as816) changes an existing flag in the usb_device structure to a bitflag, preparing the way for more bitflags to come in the future. Signed-off-by: Alan Stern Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index 864c6c21c21e..5634a2d91ec0 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -362,7 +362,7 @@ struct usb_device { u8 portnum; /* Parent port number (origin 1) */ u8 level; /* Number of USB hub ancestors */ - int have_langid; /* whether string_langid is valid */ + unsigned have_langid:1; /* whether string_langid is valid */ int string_langid; /* language ID for strings */ /* static strings from the device */ -- cgit v1.2.3 From ee49fb5dc89d34f1794ac9362fa97c1a640f7ddd Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Wed, 22 Nov 2006 16:55:54 -0500 Subject: USB: keep count of unsuspended children This patch (as818b) simplifies autosuspend processing by keeping track of the number of unsuspended children of each USB hub. This will permit us to avoid a good deal of unnecessary work all the time; we will no longer have to create a bunch of workqueue entries to carry out autosuspend requests, only to have them fail because one of the hub's children isn't suspended. The basic idea is simple. There already is a usage counter in the usb_device structure for preventing autosuspends. The patch just increments that counter for every unsuspended child. There's only one tricky part: When a device disconnects we need to remember whether it was suspended at the time (leave the counter alone) or not (decrement the counter). Signed-off-by: Alan Stern Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index 5634a2d91ec0..0cd73edeef13 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -362,6 +362,7 @@ struct usb_device { u8 portnum; /* Parent port number (origin 1) */ u8 level; /* Number of USB hub ancestors */ + unsigned discon_suspended:1; /* Disconnected while suspended */ unsigned have_langid:1; /* whether string_langid is valid */ int string_langid; /* language ID for strings */ -- cgit v1.2.3 From e65e5fb5ceb02aaea7b65bf8b3b0d0c9057718b6 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Tue, 7 Nov 2006 18:21:21 +1100 Subject: PCI: Make some MSI-X #defines generic Move some MSI-X #defines into pci_regs.h so they can be used outside of drivers/pci. Signed-off-by: Michael Ellerman Signed-off-by: Greg Kroah-Hartman --- include/linux/pci_regs.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_regs.h b/include/linux/pci_regs.h index c321316f1bc7..064b1dc71c22 100644 --- a/include/linux/pci_regs.h +++ b/include/linux/pci_regs.h @@ -292,6 +292,12 @@ #define PCI_MSI_DATA_64 12 /* 16 bits of data for 64-bit devices */ #define PCI_MSI_MASK_BIT 16 /* Mask bits register */ +/* MSI-X registers (these are at offset PCI_MSI_FLAGS) */ +#define PCI_MSIX_FLAGS_QSIZE 0x7FF +#define PCI_MSIX_FLAGS_ENABLE (1 << 15) +#define PCI_MSIX_FLAGS_BIRMASK (7 << 0) +#define PCI_MSIX_FLAGS_BITMASK (1 << 0) + /* CompactPCI Hotswap Register */ #define PCI_CHSWP_CSR 2 /* Control and Status Register */ -- cgit v1.2.3 From a2302c68d923537436b1114aa207787c1a31bd50 Mon Sep 17 00:00:00 2001 From: John Keller Date: Wed, 4 Oct 2006 16:49:52 -0500 Subject: Altix: Initial ACPI support - ROM shadowing. Support a shadowed ROM when running with an ACPI capable PROM. Define a new dev.resource flag IORESOURCE_ROM_BIOS_COPY to describe the case of a BIOS shadowed ROM, which can then be used to avoid pci_map_rom() making an unneeded call to pci_enable_rom(). Signed-off-by: John Keller Signed-off-by: Greg Kroah-Hartman --- include/linux/ioport.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ioport.h b/include/linux/ioport.h index d42c83399071..cf8696d4a138 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -89,6 +89,7 @@ struct resource_list { #define IORESOURCE_ROM_ENABLE (1<<0) /* ROM is enabled, same as PCI_ROM_ADDRESS_ENABLE */ #define IORESOURCE_ROM_SHADOW (1<<1) /* ROM is copy at C000:0 */ #define IORESOURCE_ROM_COPY (1<<2) /* ROM is alloc'd copy, resource field overlaid */ +#define IORESOURCE_ROM_BIOS_COPY (1<<3) /* ROM is BIOS copy, resource field overlaid */ /* PC/ISA/whatever - the normal PC address spaces: IO and memory */ extern struct resource ioport_resource; -- cgit v1.2.3 From bae94d02371c402408a4edfb95e71e88dbd3e973 Mon Sep 17 00:00:00 2001 From: Inaky Perez-Gonzalez Date: Wed, 22 Nov 2006 12:40:31 -0800 Subject: PCI: switch pci_{enable,disable}_device() to be nestable Changes the pci_{enable,disable}_device() functions to work in a nested basis, so that eg, three calls to enable_device() require three calls to disable_device(). The reason for this is to simplify PCI drivers for multi-interface/capability devices. These are devices that cram more than one interface in a single function. A relevant example of that is the Wireless [USB] Host Controller Interface (similar to EHCI) [see http://www.intel.com/technology/comms/wusb/whci.htm]. In these kind of devices, multiple interfaces are accessed through a single bar and IRQ line. For that, the drivers map only the smallest area of the bar to access their register banks and use shared IRQ handlers. However, because the order at which those drivers load cannot be known ahead of time, the sequence in which the calls to pci_enable_device() and pci_disable_device() cannot be predicted. Thus: 1. driverA starts pci_enable_device() 2. driverB starts pci_enable_device() 3. driverA shutdown pci_disable_device() 4. driverB shutdown pci_disable_device() between steps 3 and 4, driver B would loose access to it's device, even if it didn't intend to. By using this modification, the device won't be disabled until all the callers to enable() have called disable(). This is implemented by replacing 'struct pci_dev->is_enabled' from a bitfield to an atomic use count. Each caller to enable increments it, each caller to disable decrements it. When the count increments from 0 to 1, __pci_enable_device() is called to actually enable the device. When it drops to zero, pci_disable_device() actually does the disabling. We keep the backend __pci_enable_device() for pci_default_resume() to use and also change the sysfs method implementation, so that userspace enabling/disabling the device doesn't disable it one time too much. Signed-off-by: Inaky Perez-Gonzalez Signed-off-by: Greg Kroah-Hartman --- include/linux/pci.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 09be0f81b27b..01c707261f9c 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -51,6 +51,7 @@ #include #include #include +#include #include /* File state for mmap()s on /proc/bus/pci/X/Y */ @@ -159,7 +160,6 @@ struct pci_dev { unsigned int transparent:1; /* Transparent PCI bridge */ unsigned int multifunction:1;/* Part of multi-function device */ /* keep track of device state */ - unsigned int is_enabled:1; /* pci_enable_device has been called */ unsigned int is_busmaster:1; /* device is busmaster */ unsigned int no_msi:1; /* device may not use msi */ unsigned int no_d1d2:1; /* only allow d0 or d3 */ @@ -167,6 +167,7 @@ struct pci_dev { unsigned int broken_parity_status:1; /* Device generates false positive parity */ unsigned int msi_enabled:1; unsigned int msix_enabled:1; + atomic_t enable_cnt; /* pci_enable_device has been called */ u32 saved_config_space[16]; /* config space saved at suspend time */ struct hlist_head saved_cap_space; -- cgit v1.2.3 From 3b59d52d8c7925e7a9a396f2e31a66eb060c6c37 Mon Sep 17 00:00:00 2001 From: Jason Gaston Date: Wed, 22 Nov 2006 15:15:08 -0800 Subject: PCI: irq: irq and pci_ids patch for Intel ICH9 This updated patch adds the Intel ICH9 LPC and SMBus Controller DID's. Signed-off-by: Jason Gaston Signed-off-by: Greg Kroah-Hartman --- include/linux/pci_ids.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index fa4e1d799782..e060a7637947 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2211,6 +2211,13 @@ #define PCI_DEVICE_ID_INTEL_ICH8_4 0x2815 #define PCI_DEVICE_ID_INTEL_ICH8_5 0x283e #define PCI_DEVICE_ID_INTEL_ICH8_6 0x2850 +#define PCI_DEVICE_ID_INTEL_ICH9_0 0x2910 +#define PCI_DEVICE_ID_INTEL_ICH9_1 0x2911 +#define PCI_DEVICE_ID_INTEL_ICH9_2 0x2912 +#define PCI_DEVICE_ID_INTEL_ICH9_3 0x2913 +#define PCI_DEVICE_ID_INTEL_ICH9_4 0x2914 +#define PCI_DEVICE_ID_INTEL_ICH9_5 0x2915 +#define PCI_DEVICE_ID_INTEL_ICH9_6 0x2930 #define PCI_DEVICE_ID_INTEL_82855PM_HB 0x3340 #define PCI_DEVICE_ID_INTEL_82830_HB 0x3575 #define PCI_DEVICE_ID_INTEL_82830_CGC 0x3577 -- cgit v1.2.3 From 116af378201ef793424cd10508ccf18b06d8a021 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Wed, 25 Oct 2006 13:44:59 +1000 Subject: Driver core: add notification of bus events I finally did as you suggested and added the notifier to the struct bus_type itself. There are still problems to be expected is something attaches to a bus type where the code can hook in different struct device sub-classes (which is imho a big bogosity but I won't even try to argue that case now) but it will solve nicely a number of issues I've had so far. That also means that clients interested in registering for such notifications have to do it before devices are added and after bus types are registered. Fortunately, most bus types that matter for the various usage scenarios I have in mind are registerd at postcore_initcall time, which means I have a really nice spot at arch_initcall time to add my notifiers. There are 4 notifications provided. Device being added (before hooked to the bus) and removed (failure of previous case or after being unhooked from the bus), along with driver being bound to a device and about to be unbound. The usage I have for these are: - The 2 first ones are used to maintain a struct device_ext that is hooked to struct device.firmware_data. This structure contains for now a pointer to the Open Firmware node related to the device (if any), the NUMA node ID (for quick access to it) and the DMA operations pointers & iommu table instance for DMA to/from this device. For bus types I own (like IBM VIO or EBUS), I just maintain that structure directly from the bus code when creating the devices. But for bus types managed by generic code like PCI or platform (actually, of_platform which is a variation of platform linked to Open Firmware device-tree), I need this notifier. - The other two ones have a completely different usage scenario. I have cases where multiple devices and their drivers depend on each other. For example, the IBM EMAC network driver needs to attach to a MAL DMA engine which is a separate device, and a PHY interface which is also a separate device. They are all of_platform_device's (well, about to be with my upcoming patches) but there is no say in what precise order the core will "probe" them and instanciate the various modules. The solution I found for that is to have the drivers for emac to use multithread_probe, and wait for a driver to be bound to the target MAL and PHY control devices (the device-tree contains reference to the MAL and PHY interface nodes, which I can then match to of_platform_devices). Right now, I've been polling, but with that notifier, I can more cleanly wait (with a timeout of course). Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 9d4f6a963936..b00e02711393 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -42,6 +42,8 @@ struct bus_type { struct klist klist_devices; struct klist klist_drivers; + struct blocking_notifier_head bus_notifier; + struct bus_attribute * bus_attrs; struct device_attribute * dev_attrs; struct driver_attribute * drv_attrs; @@ -75,6 +77,29 @@ int __must_check bus_for_each_drv(struct bus_type *bus, struct device_driver *start, void *data, int (*fn)(struct device_driver *, void *)); +/* + * Bus notifiers: Get notified of addition/removal of devices + * and binding/unbinding of drivers to devices. + * In the long run, it should be a replacement for the platform + * notify hooks. + */ +struct notifier_block; + +extern int bus_register_notifier(struct bus_type *bus, + struct notifier_block *nb); +extern int bus_unregister_notifier(struct bus_type *bus, + struct notifier_block *nb); + +/* All 4 notifers below get called with the target struct device * + * as an argument. Note that those functions are likely to be called + * with the device semaphore held in the core, so be careful. + */ +#define BUS_NOTIFY_ADD_DEVICE 0x00000001 /* device added */ +#define BUS_NOTIFY_DEL_DEVICE 0x00000002 /* device removed */ +#define BUS_NOTIFY_BOUND_DRIVER 0x00000003 /* driver bound to device */ +#define BUS_NOTIFY_UNBIND_DRIVER 0x00000004 /* driver about to be + unbound */ + /* driverfs interface for exporting bus attributes */ struct bus_attribute { -- cgit v1.2.3 From f0ee61a6cecd100301a60d99feb187776533b2a2 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 23 Oct 2006 10:40:54 -0700 Subject: Driver Core: Move virtual_device_parent() to core.c It doesn't need to be global or in device.h Cc: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index b00e02711393..00b29e0c5ce0 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -440,8 +440,6 @@ extern struct device *device_create(struct class *cls, struct device *parent, __attribute__((format(printf,4,5))); extern void device_destroy(struct class *cls, dev_t devt); -extern int virtual_device_parent(struct device *dev); - /* * Platform "fixup" functions - allow the platform to have their say * about devices and actions that the general device layer doesn't -- cgit v1.2.3 From 94fbcded4ea0dc14cbfb222a5c68372f150d1476 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 27 Jul 2006 16:16:04 -0700 Subject: Driver core: change misc class_devices to be real devices This also ment that some of the misc drivers had to also be fixed up as they were assuming the device was a class_device. Signed-off-by: Greg Kroah-Hartman --- include/linux/miscdevice.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/miscdevice.h b/include/linux/miscdevice.h index b03cfb91e228..326da7d500c7 100644 --- a/include/linux/miscdevice.h +++ b/include/linux/miscdevice.h @@ -31,15 +31,14 @@ #define HPET_MINOR 228 struct device; -struct class_device; struct miscdevice { int minor; const char *name; const struct file_operations *fops; struct list_head list; - struct device *dev; - struct class_device *class; + struct device *parent; + struct device *this_device; }; extern int misc_register(struct miscdevice * misc); -- cgit v1.2.3 From 01107d343076c34b9e1ce5d073292bd7f3097fda Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 7 Aug 2006 22:19:37 -0700 Subject: Driver core: convert tty core to use struct device Converts from using struct "class_device" to "struct device" making everything show up properly in /sys/devices/ with symlinks from the /sys/class directory. Also fixes up the isdn drivers that were putting something in the class device's directory. Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 44091c0db0b4..65321f911c1e 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -276,9 +276,8 @@ extern int tty_register_ldisc(int disc, struct tty_ldisc *new_ldisc); extern int tty_unregister_ldisc(int disc); extern int tty_register_driver(struct tty_driver *driver); extern int tty_unregister_driver(struct tty_driver *driver); -extern struct class_device *tty_register_device(struct tty_driver *driver, - unsigned index, - struct device *dev); +extern struct device *tty_register_device(struct tty_driver *driver, + unsigned index, struct device *dev); extern void tty_unregister_device(struct tty_driver *driver, unsigned index); extern int tty_read_raw_data(struct tty_struct *tty, unsigned char *bufp, int buflen); -- cgit v1.2.3 From fcaf71fd51f9cfc504455d3e19ec242e4b2073ed Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 12 Sep 2006 17:00:10 +0200 Subject: Driver core: convert mmc code to use struct device Converts from using struct "class_device" to "struct device" making everything show up properly in /sys/devices/ with symlinks from the /sys/class directory. Signed-off-by: Greg Kroah-Hartman --- include/linux/mmc/host.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 587264a58d56..528e7d3fecb1 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -74,8 +74,8 @@ struct mmc_card; struct device; struct mmc_host { - struct device *dev; - struct class_device class_dev; + struct device *parent; + struct device class_dev; int index; const struct mmc_host_ops *ops; unsigned int f_min; @@ -125,8 +125,8 @@ static inline void *mmc_priv(struct mmc_host *host) return (void *)host->private; } -#define mmc_dev(x) ((x)->dev) -#define mmc_hostname(x) ((x)->class_dev.class_id) +#define mmc_dev(x) ((x)->parent) +#define mmc_hostname(x) ((x)->class_dev.bus_id) extern int mmc_suspend_host(struct mmc_host *, pm_message_t); extern int mmc_resume_host(struct mmc_host *); -- cgit v1.2.3 From 78cde0887930f5d11a56fc51b013f2672fba0e6f Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 14 Sep 2006 07:30:59 -0700 Subject: Driver core: convert fb code to use struct device Converts from using struct "class_device" to "struct device" making everything show up properly in /sys/devices/ with symlinks from the /sys/class directory. Signed-off-by: Greg Kroah-Hartman --- include/linux/fb.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fb.h b/include/linux/fb.h index 3e69241e6a81..fa23e0671bb3 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -774,8 +774,8 @@ struct fb_info { #endif struct fb_ops *fbops; - struct device *device; - struct class_device *class_device; /* sysfs per device attrs */ + struct device *device; /* This is the parent */ + struct device *dev; /* This is this fb device */ int class_flag; /* private sysfs flags */ #ifdef CONFIG_FB_TILEBLITTING struct fb_tile_ops *tileops; /* Tile Blitting */ @@ -910,8 +910,8 @@ static inline void __fb_pad_aligned_buffer(u8 *dst, u32 d_pitch, /* drivers/video/fbsysfs.c */ extern struct fb_info *framebuffer_alloc(size_t size, struct device *dev); extern void framebuffer_release(struct fb_info *info); -extern int fb_init_class_device(struct fb_info *fb_info); -extern void fb_cleanup_class_device(struct fb_info *head); +extern int fb_init_device(struct fb_info *fb_info); +extern void fb_cleanup_device(struct fb_info *head); extern void fb_bl_default_curve(struct fb_info *fb_info, u8 off, u8 min, u8 max); /* drivers/video/fbmon.c */ -- cgit v1.2.3 From c6dbaef22a2f78700e242915a13218dd780c89ff Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Sat, 11 Nov 2006 17:18:39 +1100 Subject: Driver core: add dev_archdata to struct device Add arch specific dev_archdata to struct device Adds an arch specific struct dev_arch to struct device. This enables architecture to add specific fields to every device in the system, like DMA operation pointers, NUMA node ID, firmware specific data, etc... Signed-off-by: Benjamin Herrenschmidt Acked-by: Andi Kleen Acked-By: David Howells Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 00b29e0c5ce0..5b54d756cd54 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -21,6 +21,7 @@ #include #include #include +#include #define DEVICE_NAME_SIZE 50 #define DEVICE_NAME_HALF __stringify(20) /* Less than half to accommodate slop */ @@ -383,6 +384,8 @@ struct device { struct dma_coherent_mem *dma_mem; /* internal for coherent mem override */ + /* arch specific additions */ + struct dev_archdata archdata; /* class_device migration path */ struct list_head node; -- cgit v1.2.3 From 465ae641e4a3e5028aa9c85d3843259aa28a22ce Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Sat, 11 Nov 2006 17:18:42 +1100 Subject: ACPI: Change ACPI to use dev_archdata instead of firmware_data Change ACPI to use dev_archdata instead of firmware_data This patch changes ACPI to use the new dev_archdata on i386, x86_64 and ia64 (is there any other arch using ACPI ?) to store it's acpi_handle. It also removes the firmware_data field from struct device as this was the only user. Only build-tested on x86 Signed-off-by: Benjamin Herrenschmidt Cc: Len Brown Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 5b54d756cd54..2d9dc358c027 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -369,8 +369,6 @@ struct device { void *driver_data; /* data private to the driver */ void *platform_data; /* Platform specific data, device core doesn't touch it */ - void *firmware_data; /* Firmware specific data (e.g. ACPI, - BIOS data),reserved for device core*/ struct dev_pm_info power; u64 *dma_mask; /* dma mask (if dma'able device) */ -- cgit v1.2.3 From 5ab699810d46011ad2195c5916f3cbc684bfe3ee Mon Sep 17 00:00:00 2001 From: Cornelia Huck Date: Thu, 16 Nov 2006 15:42:07 +0100 Subject: driver core: Introduce device_find_child(). Introduce device_find_child() to match device_for_each_child(). Signed-off-by: Cornelia Huck 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 2d9dc358c027..0a0370c74181 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -421,6 +421,8 @@ extern int __must_check device_add(struct device * dev); extern void device_del(struct device * dev); extern int device_for_each_child(struct device *, void *, int (*fn)(struct device *, void *)); +extern struct device *device_find_child(struct device *, void *data, + int (*match)(struct device *, void *)); extern int device_rename(struct device *dev, char *new_name); /* -- cgit v1.2.3 From 8a82472f86bf693b8e91ed56c9ca4f62fbbdcfa3 Mon Sep 17 00:00:00 2001 From: Cornelia Huck Date: Mon, 20 Nov 2006 17:07:51 +0100 Subject: driver core: Introduce device_move(): move a device to a new parent. Provide a function device_move() to move a device to a new parent device. Add auxilliary functions kobject_move() and sysfs_move_dir(). kobject_move() generates a new uevent of type KOBJ_MOVE, containing the previous path (DEVPATH_OLD) in addition to the usual values. For this, a new interface kobject_uevent_env() is created that allows to add further environmental data to the uevent at the kobject layer. Signed-off-by: Cornelia Huck Acked-by: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 1 + include/linux/kobject.h | 8 ++++++++ include/linux/sysfs.h | 8 ++++++++ 3 files changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 0a0370c74181..583a341e016c 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -424,6 +424,7 @@ extern int device_for_each_child(struct device *, void *, extern struct device *device_find_child(struct device *, void *data, int (*match)(struct device *, void *)); extern int device_rename(struct device *dev, char *new_name); +extern int device_move(struct device *dev, struct device *new_parent); /* * Manual binding of a device to driver. See drivers/base/bus.c diff --git a/include/linux/kobject.h b/include/linux/kobject.h index bcd9cd173c2c..d1c8d28fa92e 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -47,6 +47,7 @@ enum kobject_action { KOBJ_UMOUNT = (__force kobject_action_t) 0x05, /* umount event for block devices (broken) */ KOBJ_OFFLINE = (__force kobject_action_t) 0x06, /* device offline */ KOBJ_ONLINE = (__force kobject_action_t) 0x07, /* device online */ + KOBJ_MOVE = (__force kobject_action_t) 0x08, /* device move */ }; struct kobject { @@ -76,6 +77,7 @@ extern int __must_check kobject_add(struct kobject *); extern void kobject_del(struct kobject *); extern int __must_check kobject_rename(struct kobject *, const char *new_name); +extern int __must_check kobject_move(struct kobject *, struct kobject *); extern int __must_check kobject_register(struct kobject *); extern void kobject_unregister(struct kobject *); @@ -264,6 +266,8 @@ extern int __must_check subsys_create_file(struct subsystem * , #if defined(CONFIG_HOTPLUG) void kobject_uevent(struct kobject *kobj, enum kobject_action action); +void kobject_uevent_env(struct kobject *kobj, enum kobject_action action, + char *envp[]); int add_uevent_var(char **envp, int num_envp, int *cur_index, char *buffer, int buffer_size, int *cur_len, @@ -271,6 +275,10 @@ int add_uevent_var(char **envp, int num_envp, int *cur_index, __attribute__((format (printf, 7, 8))); #else static inline void kobject_uevent(struct kobject *kobj, enum kobject_action action) { } +static inline void kobject_uevent_env(struct kobject *kobj, + enum kobject_action action, + char *envp[]) +{ } static inline int add_uevent_var(char **envp, int num_envp, int *cur_index, char *buffer, int buffer_size, int *cur_len, diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index 6d5c43d31dec..2129d1b6c874 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -96,6 +96,9 @@ sysfs_remove_dir(struct kobject *); extern int __must_check sysfs_rename_dir(struct kobject *, const char *new_name); +extern int __must_check +sysfs_move_dir(struct kobject *, struct kobject *); + extern int __must_check sysfs_create_file(struct kobject *, const struct attribute *); @@ -142,6 +145,11 @@ static inline int sysfs_rename_dir(struct kobject * k, const char *new_name) return 0; } +static inline int sysfs_move_dir(struct kobject * k, struct kobject * new_parent) +{ + return 0; +} + static inline int sysfs_create_file(struct kobject * k, const struct attribute * a) { return 0; -- cgit v1.2.3 From c67334fbdfbba533af767610cf3fde8a49710e62 Mon Sep 17 00:00:00 2001 From: David Brownell Date: Thu, 16 Nov 2006 23:28:47 -0800 Subject: Driver core: platform_driver_probe(), can save codespace This defines a new platform_driver_probe() method allowing the driver's probe() method, and its support code+data, to safely live in __init sections for typical system configurations. Many system-on-chip processors could benefit from this API, to the tune of recovering hundreds to thousands of bytes per driver. That's memory which is currently wasted holding code which can never be called after system startup, yet can not be removed. It can't be removed because of the linkage requirement that pointers to init section code (like, ideally, probe support) must not live in other sections (like driver method tables) after those pointers would be invalid. Signed-off-by: David Brownell Signed-off-by: Greg Kroah-Hartman --- include/linux/platform_device.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index 29cd6dee13db..20f47b81d3fa 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -58,6 +58,12 @@ struct platform_driver { extern int platform_driver_register(struct platform_driver *); extern void platform_driver_unregister(struct platform_driver *); +/* non-hotpluggable platform devices may use this so that probe() and + * its support may live in __init sections, conserving runtime memory. + */ +extern int platform_driver_probe(struct platform_driver *driver, + int (*probe)(struct platform_device *)); + #define platform_get_drvdata(_dev) dev_get_drvdata(&(_dev)->dev) #define platform_set_drvdata(_dev,data) dev_set_drvdata(&(_dev)->dev, (data)) -- cgit v1.2.3 From e17e0f51aeea4e59c7e450a1c0f26605b91c1260 Mon Sep 17 00:00:00 2001 From: Kay Sievers Date: Fri, 24 Nov 2006 12:15:25 +0100 Subject: Driver core: show drivers in /sys/module/ Show the drivers, which belong to the module: $ ls -l /sys/module/usbcore/drivers/ hub -> ../../../bus/usb/drivers/hub usb -> ../../../bus/usb/drivers/usb usbfs -> ../../../bus/usb/drivers/usbfs Signed-off-by: Kay Sievers 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 d1d00ce8f4ed..9258ffd8a7f0 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -264,6 +264,7 @@ struct module struct module_attribute *modinfo_attrs; const char *version; const char *srcversion; + struct kobject *drivers_dir; /* Exported symbols */ const struct kernel_symbol *syms; -- cgit v1.2.3 From fc085150b491bfc186efbca90a14cf907a3060a9 Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Tue, 10 Oct 2006 14:28:11 -0700 Subject: [PATCH] libata: add 40pin "short" cable support, honour drive side speed detection [deweerdt@free.fr: build fix] Signed-off-by: Alan Cox Signed-off-by: Frederik Deweerdt Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Jeff Garzik --- include/linux/ata.h | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ata.h b/include/linux/ata.h index d89441907024..1df941648a57 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -200,8 +200,9 @@ enum { ATA_CBL_NONE = 0, ATA_CBL_PATA40 = 1, ATA_CBL_PATA80 = 2, - ATA_CBL_PATA_UNK = 3, - ATA_CBL_SATA = 4, + ATA_CBL_PATA40_SHORT = 3, /* 40 wire cable to high UDMA spec */ + ATA_CBL_PATA_UNK = 4, + ATA_CBL_SATA = 5, /* SATA Status and Control Registers */ SCR_STATUS = 0, @@ -342,6 +343,15 @@ static inline int ata_id_is_cfa(const u16 *id) return 0; } +static inline int ata_drive_40wire(const u16 *dev_id) +{ + if (ata_id_major_version(dev_id) >= 5 && ata_id_is_sata(dev_id)) + return 0; /* SATA */ + if (dev_id[93] & 0x4000) + return 0; /* 80 wire */ + return 1; +} + static inline int atapi_cdb_len(const u16 *dev_id) { u16 tmp = dev_id[0] & 0x3; -- cgit v1.2.3 From 6919a0a6cfdad9e83d02cef5973826acd416560c Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Fri, 27 Oct 2006 19:08:46 -0700 Subject: [PATCH] libata: Revamp blacklist support to allow multiple kinds of blacklisting flaws Signed-off-by: Alan Cox Cc: Jeff Garzik Cc: Tejun Heo Signed-off-by: Andrew Morton 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 abd2debebca2..2300fcc37f80 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -307,6 +307,8 @@ enum { (some horkage may be drive/controller pair dependant */ ATA_HORKAGE_DIAGNOSTIC = (1 << 0), /* Failed boot diag */ + ATA_HORKAGE_NODMA = (1 << 1), /* DMA problems */ + ATA_HORKAGE_NONCQ = (1 << 2), /* Don't use NCQ */ }; enum hsm_task_states { @@ -787,6 +789,7 @@ 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 unsigned long ata_device_blacklisted(const struct ata_device *dev); 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 a20c9e820864e18b59d2a4f2f04e8b6053986c95 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Fri, 27 Oct 2006 19:08:48 -0700 Subject: [PATCH] ata: Generic platform_device libata driver needs a changelog Signed-off-by: Paul Mundt Acked-by: Russell King Cc: Jeff Garzik Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Jeff Garzik --- include/linux/pata_platform.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) create mode 100644 include/linux/pata_platform.h (limited to 'include/linux') diff --git a/include/linux/pata_platform.h b/include/linux/pata_platform.h new file mode 100644 index 000000000000..2d5fd647e0e9 --- /dev/null +++ b/include/linux/pata_platform.h @@ -0,0 +1,13 @@ +#ifndef __LINUX_PATA_PLATFORM_H +#define __LINUX_PATA_PLATFORM_H + +struct pata_platform_info { + /* + * I/O port shift, for platforms with ports that are + * constantly spaced and need larger than the 1-byte + * spacing used by ata_std_ports(). + */ + unsigned int ioport_shift; +}; + +#endif /* __LINUX_PATA_PLATFORM_H */ -- cgit v1.2.3 From d1adc1bbd6dde3e05a91e2d3e6ab42d202ea61d5 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 9 Oct 2006 18:32:15 +0900 Subject: [PATCH] libata: handle 0xff status properly libata waits for !BSY even when the status register reports 0xff. This causes long boot delays when D8 isn't pulled down properly. This patch does the followings. * don't wait if status register is 0xff in all wait functions * make ata_busy_sleep() return 0 on success and -errno on failure. -ENODEV is returned on 0xff status and -EBUSY on other failures. * make ata_bus_softreset() succeed on 0xff status. 0xff status is not reset failure. It indicates no device. This removes unnecessary retries on such ports. Note that the code change assumes unoccupied port reporting 0xff status does not produce valid device signature. Signed-off-by: Tejun Heo Cc: Joe Jin Signed-off-by: Jeff Garzik --- include/linux/libata.h | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 2300fcc37f80..6c003d852a88 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -746,9 +746,8 @@ extern int ata_scsi_device_suspend(struct scsi_device *, pm_message_t mesg); extern int ata_host_suspend(struct ata_host *host, pm_message_t mesg); extern void ata_host_resume(struct ata_host *host); extern int ata_ratelimit(void); -extern unsigned int ata_busy_sleep(struct ata_port *ap, - unsigned long timeout_pat, - unsigned long timeout); +extern 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); extern u32 ata_wait_register(void __iomem *reg, u32 mask, u32 val, @@ -1064,7 +1063,7 @@ static inline u8 ata_busy_wait(struct ata_port *ap, unsigned int bits, udelay(10); status = ata_chk_status(ap); max--; - } while ((status & bits) && (max > 0)); + } while (status != 0xff && (status & bits) && (max > 0)); return status; } @@ -1085,7 +1084,7 @@ static inline u8 ata_wait_idle(struct ata_port *ap) { u8 status = ata_busy_wait(ap, ATA_BUSY | ATA_DRQ, 1000); - if (status & (ATA_BUSY | ATA_DRQ)) { + if (status != 0xff && (status & (ATA_BUSY | ATA_DRQ))) { unsigned long l = ap->ioaddr.status_addr; if (ata_msg_warn(ap)) printk(KERN_WARNING "ATA: abnormal status 0x%X on port 0x%lX\n", -- cgit v1.2.3 From 90088bb41200b4da962282dfd45db82544adac3b Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 9 Oct 2006 11:10:26 +0900 Subject: [PATCH] libata: move ata_irq_on() into libata-sff.c ata_irq_on() isn't used outside of libata core layer. The function is TF/SFF interface specific but currently used by core path with some hack too. Move it from include/linux/libata.h to drivers/ata/libata-sff.c. Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- include/linux/libata.h | 31 ------------------------------- 1 file changed, 31 deletions(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 6c003d852a88..d3bf7b936c3f 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1149,37 +1149,6 @@ static inline void ata_qc_reinit(struct ata_queued_cmd *qc) qc->result_tf.feature = 0; } -/** - * ata_irq_on - Enable interrupts on a port. - * @ap: Port on which interrupts are enabled. - * - * Enable interrupts on a legacy IDE device using MMIO or PIO, - * wait for idle, clear any pending interrupts. - * - * LOCKING: - * Inherited from caller. - */ - -static inline u8 ata_irq_on(struct ata_port *ap) -{ - struct ata_ioports *ioaddr = &ap->ioaddr; - u8 tmp; - - ap->ctl &= ~ATA_NIEN; - ap->last_ctl = ap->ctl; - - if (ap->flags & ATA_FLAG_MMIO) - writeb(ap->ctl, (void __iomem *) ioaddr->ctl_addr); - else - outb(ap->ctl, ioaddr->ctl_addr); - tmp = ata_wait_idle(ap); - - ap->ops->irq_clear(ap); - - return tmp; -} - - /** * ata_irq_ack - Acknowledge a device interrupt. * @ap: Port on which interrupts are enabled. -- cgit v1.2.3 From b6103f6d1659e2024776bc759d28613fb36344a8 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 1 Nov 2006 17:59:53 +0900 Subject: [PATCH] libata: separate out and export sata_port_hardreset() Separate out sata_port_hardreset() from sata_std_hardreset(). This will be used by LLD hardreset implementation and later by PMP. 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 d3bf7b936c3f..41fa0890dbfb 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -702,6 +702,8 @@ extern int sata_phy_debounce(struct ata_port *ap, const unsigned long *param); extern int sata_phy_resume(struct ata_port *ap, const unsigned long *param); extern int ata_std_prereset(struct ata_port *ap); extern int ata_std_softreset(struct ata_port *ap, unsigned int *classes); +extern int sata_port_hardreset(struct ata_port *ap, + const unsigned long *timing); extern int sata_std_hardreset(struct ata_port *ap, unsigned int *class); extern void ata_std_postreset(struct ata_port *ap, unsigned int *classes); extern void ata_port_disable(struct ata_port *); -- cgit v1.2.3 From efdaedc443e935eda82e9e78a6e65d1f993d242f Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 1 Nov 2006 18:38:52 +0900 Subject: [PATCH] libata: implement ATA_EHI_PRINTINFO Implement ehi flag ATA_EHI_PRINTINFO. This flag is set when device configuration needs to print out device info. This used to be handled by @print_info argument to ata_dev_configure() but LLDs also need to know about it in ->dev_config() callback. This patch replaces @print_info w/ ATA_EHI_PRINTINFO and make sata_sil print workaround messages only on the initial configuration. 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 41fa0890dbfb..949484627e67 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -283,6 +283,7 @@ enum { ATA_EHI_QUIET = (1 << 3), /* be quiet */ ATA_EHI_DID_RESET = (1 << 16), /* already reset this port */ + ATA_EHI_PRINTINFO = (1 << 17), /* print configuration info */ ATA_EHI_RESET_MODIFIER_MASK = ATA_EHI_RESUME_LINK, -- cgit v1.2.3 From baa1e78a834c917984a4659fd282f712c17ee3bf Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 1 Nov 2006 18:39:27 +0900 Subject: [PATCH] libata: implement ATA_EHI_SETMODE and ATA_EHI_POST_SETMODE libata EH used to perform ata_set_mode() iff the EH session performed reset as indicated by ATA_EHI_DID_RESET. This is incorrect because ->dev_config() called by revalidation is allowed to modify transfer mode which ata_set_mode() should take care of. This patch implements the following two flags. * ATA_EHI_SETMODE: set during EH to schedule ata_set_mode(). Both new device attachment and revalidation set this flag. * ATA_EHI_POST_SETMODE: set while the device is revalidated after ata_set_mode(). Post-setmode revalidation is different from initial configuaration and EH revalidation in that ->dev_config() is not allowed tune transfer mode. LLD can use this flag to determine whether it's allowed to tune transfer mode. Note that POST_SETMODE ->dev_config() is guaranteed to be preceded by non-POST_SETMODE ->dev_config(). 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 949484627e67..0d0ddeaee73f 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -284,6 +284,8 @@ enum { ATA_EHI_DID_RESET = (1 << 16), /* already reset this port */ ATA_EHI_PRINTINFO = (1 << 17), /* print configuration info */ + ATA_EHI_SETMODE = (1 << 18), /* configure transfer mode */ + ATA_EHI_POST_SETMODE = (1 << 19), /* revaildating after setmode */ ATA_EHI_RESET_MODIFIER_MASK = ATA_EHI_RESUME_LINK, -- cgit v1.2.3 From 6fc49adb9417b9c793e8f88d485387bb89ceb733 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Sat, 11 Nov 2006 20:10:45 +0900 Subject: [PATCH] libata: use FLUSH_EXT only when driver is larger than LBA28 limit Many drives support LBA48 even when its capacity is smaller than 1<<28, as LBA48 is required for many functionalities. FLUSH_EXT is mandatory for drives w/ LBA48 support. Interestingly, at least one of such drives (ST960812A) has problems dealing with FLUSH_EXT. It eventually completes the command but takes around 7 seconds to finish in many cases thus drastically slowing down IO transactions. This seems to be a firmware bug which sneaked into production probably because no other ATA driver including linux IDE issues FLUSH_EXT to drives which report support for LBA48 & FLUSH_EXT but is smaller than 1<<28 blocks. This patch adds ATA_DFLAG_FLUSH_EXT which is set iff the drive supports LBA48 & FLUSH_EXT and is larger than LBA28 limit. Both cache flush paths are updated to issue FLUSH_EXT only when the flag is set. Note that the changed behavior is more inline with the rest of libata. libata prefers shorter commands whenever possible. Signed-off-by: Tejun Heo Cc: Danny Kukawka Cc: Stefan Seyfried 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 0d0ddeaee73f..36e233cc3886 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -140,6 +140,7 @@ enum { ATA_DFLAG_LBA48 = (1 << 1), /* device supports LBA48 */ ATA_DFLAG_CDB_INTR = (1 << 2), /* device asserts INTRQ when ready for CDB */ ATA_DFLAG_NCQ = (1 << 3), /* device supports NCQ */ + ATA_DFLAG_FLUSH_EXT = (1 << 4), /* do FLUSH_EXT instead of FLUSH */ ATA_DFLAG_CFG_MASK = (1 << 8) - 1, ATA_DFLAG_PIO = (1 << 8), /* device limited to PIO mode */ -- cgit v1.2.3 From 55a8e2c83ce50548dfef74bb19dfe2b809cb3099 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 10 Nov 2006 18:08:10 +0900 Subject: [PATCH] libata: implement presence detection via polling IDENTIFY On some controllers (ICHs in piix mode), there is *NO* reliable way to determine device presence other than issuing IDENTIFY and see how the transaction proceeds by watching the TF status register. libata acted this way before irq-pio and phantom devices caused very little problem but now that IDENTIFY is performed using IRQ drive PIO, such phantom devices now result in multiple 30sec timeouts during boot. This patch implements ATA_FLAG_DETECT_POLLING. If a LLD sets this flag, libata core issues the initial IDENTIFY in polling mode and if the initial data transfer fails w/ HSM violation, the port is considered to be empty thus replicating the old libata and IDE behavior. 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 36e233cc3886..9080789913f7 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -176,6 +176,8 @@ enum { ATA_FLAG_SKIP_D2H_BSY = (1 << 12), /* can't wait for the first D2H * Register FIS clearing BSY */ ATA_FLAG_DEBUGMSG = (1 << 13), + ATA_FLAG_DETECT_POLLING = (1 << 14), /* detect device presence by + * polling IDENTIFY */ /* The following flag belongs to ap->pflags but is kept in * ap->flags because it's referenced in many LLDs and will be @@ -335,6 +337,7 @@ enum ata_completion_errors { AC_ERR_SYSTEM = (1 << 6), /* system error */ AC_ERR_INVALID = (1 << 7), /* invalid argument */ AC_ERR_OTHER = (1 << 8), /* unknown */ + AC_ERR_NODEV_HINT = (1 << 9), /* polling device detection hint */ }; /* forward declarations */ -- cgit v1.2.3 From 13df29f69749a61b5209d52b71fcbf7300e5d6fb Mon Sep 17 00:00:00 2001 From: "Maciej W. Rozycki" Date: Tue, 3 Oct 2006 16:18:28 +0100 Subject: [PATCH] 2.6.18: sb1250-mac: Missing inclusions from The uses some types and macros defined in , , and , but fails to include these headers. Signed-off-by: Maciej W. Rozycki patch-mips-2.6.18-20060920-include-phy-16 Signed-off-by: Jeff Garzik --- include/linux/phy.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 9447a57ee8a9..ce8bc80b3c86 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -20,6 +20,10 @@ #include #include +#include +#include +#include +#include #define PHY_BASIC_FEATURES (SUPPORTED_10baseT_Half | \ SUPPORTED_10baseT_Full | \ -- cgit v1.2.3 From fe75f7471ba5604fe65435f717e3612a482c28cb Mon Sep 17 00:00:00 2001 From: Christian Lamparter Date: Mon, 2 Oct 2006 19:55:22 +0200 Subject: [PATCH] wext: extend MLME support This patch adds two new defines for the SIOCSIWMLME to cover all kinds MLMEs (well, except REASSOC) through a ioctl. Signed-off-by: Christian Lamparter Signed-off-by: John W. Linville --- include/linux/wireless.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/wireless.h b/include/linux/wireless.h index a50a0130fd9e..7c269f4992eb 100644 --- a/include/linux/wireless.h +++ b/include/linux/wireless.h @@ -546,6 +546,8 @@ /* MLME requests (SIOCSIWMLME / struct iw_mlme) */ #define IW_MLME_DEAUTH 0 #define IW_MLME_DISASSOC 1 +#define IW_MLME_AUTH 2 +#define IW_MLME_ASSOC 3 /* SIOCSIWAUTH/SIOCGIWAUTH struct iw_param flags */ #define IW_AUTH_INDEX 0x0FFF -- cgit v1.2.3 From 52d78d63310d9818458fd9800d24a4d5425aeac7 Mon Sep 17 00:00:00 2001 From: Ayaz Abdulla Date: Mon, 6 Nov 2006 00:43:39 -0800 Subject: [PATCH] forcedeth: add new NVIDIA pci ids Add pci device ids for the NVIDIA MCP67 chip. Signed-off-by: Ayaz Abdulla Signed-off-by: Andrew Morton Signed-off-by: Jeff Garzik --- 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 e060a7637947..fd5033b8a927 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1213,6 +1213,10 @@ #define PCI_DEVICE_ID_NVIDIA_NVENET_21 0x0451 #define PCI_DEVICE_ID_NVIDIA_NVENET_22 0x0452 #define PCI_DEVICE_ID_NVIDIA_NVENET_23 0x0453 +#define PCI_DEVICE_ID_NVIDIA_NVENET_24 0x054C +#define PCI_DEVICE_ID_NVIDIA_NVENET_25 0x054D +#define PCI_DEVICE_ID_NVIDIA_NVENET_26 0x054E +#define PCI_DEVICE_ID_NVIDIA_NVENET_27 0x054F #define PCI_DEVICE_ID_NVIDIA_NFORCE_MCP67_IDE 0x0560 #define PCI_VENDOR_ID_IMS 0x10e0 -- cgit v1.2.3 From f789dfdc44d5bbc04fb7f06e1e4eb682169acaaf Mon Sep 17 00:00:00 2001 From: Mariusz Kozlowski Date: Thu, 30 Nov 2006 04:27:00 -0700 Subject: [PATCH] mv643xx_eth: fix unbalanced parentheses in macros Signed-off-by: Mariusz Kozlowski Signed-off-by: Dale Farnsworth Signed-off-by: Jeff Garzik --- include/linux/mv643xx.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mv643xx.h b/include/linux/mv643xx.h index edfa012fad3a..aff25c000abf 100644 --- a/include/linux/mv643xx.h +++ b/include/linux/mv643xx.h @@ -724,7 +724,7 @@ #define MV643XX_ETH_RX_FIFO_URGENT_THRESHOLD_REG(port) (0x2470 + (port<<10)) #define MV643XX_ETH_TX_FIFO_URGENT_THRESHOLD_REG(port) (0x2474 + (port<<10)) #define MV643XX_ETH_RX_MINIMAL_FRAME_SIZE_REG(port) (0x247c + (port<<10)) -#define MV643XX_ETH_RX_DISCARDED_FRAMES_COUNTER(port) (0x2484 + (port<<10) +#define MV643XX_ETH_RX_DISCARDED_FRAMES_COUNTER(port) (0x2484 + (port<<10)) #define MV643XX_ETH_PORT_DEBUG_0_REG(port) (0x248c + (port<<10)) #define MV643XX_ETH_PORT_DEBUG_1_REG(port) (0x2490 + (port<<10)) #define MV643XX_ETH_PORT_INTERNAL_ADDR_ERROR_REG(port) (0x2494 + (port<<10)) @@ -1135,7 +1135,7 @@ struct mv64xxx_i2c_pdata { #define MV643XX_ETH_DEFAULT_RX_UDP_QUEUE_1 (1<<19) #define MV643XX_ETH_DEFAULT_RX_UDP_QUEUE_2 (1<<20) #define MV643XX_ETH_DEFAULT_RX_UDP_QUEUE_3 ((1<<20) | (1<<19)) -#define MV643XX_ETH_DEFAULT_RX_UDP_QUEUE_4 ((1<<21) +#define MV643XX_ETH_DEFAULT_RX_UDP_QUEUE_4 (1<<21) #define MV643XX_ETH_DEFAULT_RX_UDP_QUEUE_5 ((1<<21) | (1<<19)) #define MV643XX_ETH_DEFAULT_RX_UDP_QUEUE_6 ((1<<21) | (1<<20)) #define MV643XX_ETH_DEFAULT_RX_UDP_QUEUE_7 ((1<<21) | (1<<20) | (1<<19)) -- cgit v1.2.3 From e8a2b6a4207332a2d59628a12cece9e8c1d769e4 Mon Sep 17 00:00:00 2001 From: Andy Fleming Date: Fri, 1 Dec 2006 12:01:06 -0600 Subject: [PATCH] PHY: Add support for configuring the PHY connection interface Most PHYs connect to an ethernet controller over a GMII or MII interface. However, a growing number are connected over different interfaces, such as RGMII or SGMII. The ethernet driver will tell the PHY what type of connection it is by setting it manually, or passing it in through phy_connect (or phy_attach). Changes include: * Updates to documentation * Updates to PHY Lib consumers * Changes to PHY Lib to add interface support * Some minor changes to whitespace in phy.h * gianfar driver now detects interface and passes appropriate value to PHY Lib Signed-off-by: Andrew Fleming Signed-off-by: Jeff Garzik --- include/linux/phy.h | 26 ++++++++++++++++++++------ 1 file changed, 20 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index ce8bc80b3c86..edd4c88ca7d8 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -47,15 +47,26 @@ #define PHY_HAS_INTERRUPT 0x00000001 #define PHY_HAS_MAGICANEG 0x00000002 +/* Interface Mode definitions */ +typedef enum { + PHY_INTERFACE_MODE_MII, + PHY_INTERFACE_MODE_GMII, + PHY_INTERFACE_MODE_SGMII, + PHY_INTERFACE_MODE_TBI, + PHY_INTERFACE_MODE_RMII, + PHY_INTERFACE_MODE_RGMII, + PHY_INTERFACE_MODE_RTBI +} phy_interface_t; + #define MII_BUS_MAX 4 -#define PHY_INIT_TIMEOUT 100000 +#define PHY_INIT_TIMEOUT 100000 #define PHY_STATE_TIME 1 #define PHY_FORCE_TIMEOUT 10 #define PHY_AN_TIMEOUT 10 -#define PHY_MAX_ADDR 32 +#define PHY_MAX_ADDR 32 /* Used when trying to connect to a specific phy (mii bus id:phy device id) */ #define PHY_ID_FMT "%x:%02x" @@ -87,8 +98,8 @@ struct mii_bus { int *irq; }; -#define PHY_INTERRUPT_DISABLED 0x0 -#define PHY_INTERRUPT_ENABLED 0x80000000 +#define PHY_INTERRUPT_DISABLED 0x0 +#define PHY_INTERRUPT_ENABLED 0x80000000 /* PHY state machine states: * @@ -230,6 +241,8 @@ struct phy_device { u32 dev_flags; + phy_interface_t interface; + /* Bus address of the PHY (0-32) */ int addr; @@ -345,9 +358,10 @@ struct phy_device* get_phy_device(struct mii_bus *bus, int addr); int phy_clear_interrupt(struct phy_device *phydev); int phy_config_interrupt(struct phy_device *phydev, u32 interrupts); struct phy_device * phy_attach(struct net_device *dev, - const char *phy_id, u32 flags); + const char *phy_id, u32 flags, phy_interface_t interface); struct phy_device * phy_connect(struct net_device *dev, const char *phy_id, - void (*handler)(struct net_device *), u32 flags); + void (*handler)(struct net_device *), u32 flags, + phy_interface_t interface); void phy_disconnect(struct phy_device *phydev); void phy_detach(struct phy_device *phydev); void phy_start(struct phy_device *phydev); -- cgit v1.2.3 From 3e6c8cd5669c1202fe806ce3e13d701f20a71c7e Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 8 Nov 2006 00:19:09 -0800 Subject: [TIPC]: endianness annotations Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/tipc_config.h | 32 ++++++++++++++++---------------- 1 file changed, 16 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tipc_config.h b/include/linux/tipc_config.h index 33a653913d94..b0c916d1f375 100644 --- a/include/linux/tipc_config.h +++ b/include/linux/tipc_config.h @@ -194,34 +194,34 @@ struct tipc_node_info { - __u32 addr; /* network address of node */ - __u32 up; /* 0=down, 1= up */ + __be32 addr; /* network address of node */ + __be32 up; /* 0=down, 1= up */ }; struct tipc_link_info { - __u32 dest; /* network address of peer node */ - __u32 up; /* 0=down, 1=up */ + __be32 dest; /* network address of peer node */ + __be32 up; /* 0=down, 1=up */ char str[TIPC_MAX_LINK_NAME]; /* link name */ }; struct tipc_bearer_config { - __u32 priority; /* Range [1,31]. Override per link */ - __u32 detect_scope; + __be32 priority; /* Range [1,31]. Override per link */ + __be32 detect_scope; char name[TIPC_MAX_BEARER_NAME]; }; struct tipc_link_config { - __u32 value; + __be32 value; char name[TIPC_MAX_LINK_NAME]; }; #define TIPC_NTQ_ALLTYPES 0x80000000 struct tipc_name_table_query { - __u32 depth; /* 1:type, 2:+name info, 3:+port info, 4+:+debug info */ - __u32 type; /* {t,l,u} info ignored if high bit of "depth" is set */ - __u32 lowbound; /* (i.e. displays all entries of name table) */ - __u32 upbound; + __be32 depth; /* 1:type, 2:+name info, 3:+port info, 4+:+debug info */ + __be32 type; /* {t,l,u} info ignored if high bit of "depth" is set */ + __be32 lowbound; /* (i.e. displays all entries of name table) */ + __be32 upbound; }; /* @@ -262,8 +262,8 @@ struct tipc_route_info { */ struct tlv_desc { - __u16 tlv_len; /* TLV length (descriptor + value) */ - __u16 tlv_type; /* TLV identifier */ + __be16 tlv_len; /* TLV length (descriptor + value) */ + __be16 tlv_type; /* TLV identifier */ }; #define TLV_ALIGNTO 4 @@ -377,9 +377,9 @@ struct tipc_genlmsghdr { struct tipc_cfg_msg_hdr { - __u32 tcm_len; /* Message length (including header) */ - __u16 tcm_type; /* Command type */ - __u16 tcm_flags; /* Additional flags */ + __be32 tcm_len; /* Message length (including header) */ + __be16 tcm_type; /* Command type */ + __be16 tcm_flags; /* Additional flags */ char tcm_reserved[8]; /* Unused */ }; -- cgit v1.2.3 From 5a874db4d9bfd8a4c6324d844a4d1c7cfa5cf2c4 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 8 Nov 2006 00:19:38 -0800 Subject: [NET]: ipconfig and nfsroot annotations Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/nfs_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 45228c1a1195..625ffea98561 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -318,7 +318,7 @@ extern void put_nfs_open_context(struct nfs_open_context *ctx); extern struct nfs_open_context *nfs_find_open_context(struct inode *inode, struct rpc_cred *cred, int mode); /* linux/net/ipv4/ipconfig.c: trims ip addr off front of name, too. */ -extern u32 root_nfs_parse_addr(char *name); /*__init*/ +extern __be32 root_nfs_parse_addr(char *name); /*__init*/ static inline void nfs_fattr_init(struct nfs_fattr *fattr) { -- cgit v1.2.3 From a27ee7a4dd30feda1954950b5840455a51ae1507 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 8 Nov 2006 00:21:21 -0800 Subject: [IPV6]: annotate icmpv6 headers Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/icmpv6.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/icmpv6.h b/include/linux/icmpv6.h index c771a7db9871..dc79396aac25 100644 --- a/include/linux/icmpv6.h +++ b/include/linux/icmpv6.h @@ -7,17 +7,17 @@ struct icmp6hdr { __u8 icmp6_type; __u8 icmp6_code; - __u16 icmp6_cksum; + __be16 icmp6_cksum; union { - __u32 un_data32[1]; - __u16 un_data16[2]; + __be32 un_data32[1]; + __be16 un_data16[2]; __u8 un_data8[4]; struct icmpv6_echo { - __u16 identifier; - __u16 sequence; + __be16 identifier; + __be16 sequence; } u_echo; struct icmpv6_nd_advt { @@ -53,7 +53,7 @@ struct icmp6hdr { #else #error "Please fix " #endif - __u16 rt_lifetime; + __be16 rt_lifetime; } u_nd_ra; } icmp6_dataun; -- cgit v1.2.3 From d5a0a1e3109339090769e40fdaa62482fcf2a717 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 8 Nov 2006 00:23:14 -0800 Subject: [IPV4]: encapsulation annotations Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/if_tunnel.h | 8 ++++---- include/linux/xfrm.h | 4 ++-- 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_tunnel.h b/include/linux/if_tunnel.h index bef9f8fd93b3..8de079ba1107 100644 --- a/include/linux/if_tunnel.h +++ b/include/linux/if_tunnel.h @@ -19,10 +19,10 @@ struct ip_tunnel_parm { char name[IFNAMSIZ]; int link; - __u16 i_flags; - __u16 o_flags; - __u32 i_key; - __u32 o_key; + __be16 i_flags; + __be16 o_flags; + __be32 i_key; + __be32 o_key; struct iphdr iph; }; diff --git a/include/linux/xfrm.h b/include/linux/xfrm.h index 8ae7f744917b..7907c42bd4e4 100644 --- a/include/linux/xfrm.h +++ b/include/linux/xfrm.h @@ -211,8 +211,8 @@ struct xfrm_user_tmpl { struct xfrm_encap_tmpl { __u16 encap_type; - __u16 encap_sport; - __u16 encap_dport; + __be16 encap_sport; + __be16 encap_dport; xfrm_address_t encap_oa; }; -- cgit v1.2.3 From d29ef86b0a497dd2c4f9601644a15392f7e21f73 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 8 Nov 2006 00:23:42 -0800 Subject: [AF_KEY]: annotate Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/pfkeyv2.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pfkeyv2.h b/include/linux/pfkeyv2.h index d5dd471da225..0f0b880c4280 100644 --- a/include/linux/pfkeyv2.h +++ b/include/linux/pfkeyv2.h @@ -32,7 +32,7 @@ struct sadb_ext { struct sadb_sa { uint16_t sadb_sa_len; uint16_t sadb_sa_exttype; - uint32_t sadb_sa_spi; + __be32 sadb_sa_spi; uint8_t sadb_sa_replay; uint8_t sadb_sa_state; uint8_t sadb_sa_auth; @@ -211,7 +211,7 @@ struct sadb_x_nat_t_type { struct sadb_x_nat_t_port { uint16_t sadb_x_nat_t_port_len; uint16_t sadb_x_nat_t_port_exttype; - uint16_t sadb_x_nat_t_port_port; + __be16 sadb_x_nat_t_port_port; uint16_t sadb_x_nat_t_port_reserved; } __attribute__((packed)); /* sizeof(struct sadb_x_nat_t_port) == 8 */ -- cgit v1.2.3 From 90bcaf7b4a33bb9b100cc06869f0c033a870d4a0 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 8 Nov 2006 00:25:17 -0800 Subject: [IPV6]: flowlabels are net-endian Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/in6.h | 4 ++-- include/linux/ip6_tunnel.h | 2 +- include/linux/ipv6.h | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/in6.h b/include/linux/in6.h index f28621f638e0..4e8350ae8869 100644 --- a/include/linux/in6.h +++ b/include/linux/in6.h @@ -54,7 +54,7 @@ extern const struct in6_addr in6addr_loopback; struct sockaddr_in6 { unsigned short int sin6_family; /* AF_INET6 */ __be16 sin6_port; /* Transport layer port # */ - __u32 sin6_flowinfo; /* IPv6 flow information */ + __be32 sin6_flowinfo; /* IPv6 flow information */ struct in6_addr sin6_addr; /* IPv6 address */ __u32 sin6_scope_id; /* scope id (new in RFC2553) */ }; @@ -72,7 +72,7 @@ struct ipv6_mreq { struct in6_flowlabel_req { struct in6_addr flr_dst; - __u32 flr_label; + __be32 flr_label; __u8 flr_action; __u8 flr_share; __u16 flr_flags; diff --git a/include/linux/ip6_tunnel.h b/include/linux/ip6_tunnel.h index 5c23aeb104ca..af3f4a70f3df 100644 --- a/include/linux/ip6_tunnel.h +++ b/include/linux/ip6_tunnel.h @@ -25,7 +25,7 @@ struct ip6_tnl_parm { __u8 proto; /* tunnel protocol */ __u8 encap_limit; /* encapsulation limit for tunnel */ __u8 hop_limit; /* hop limit for tunnel */ - __u32 flowinfo; /* traffic class and flowlabel for tunnel */ + __be32 flowinfo; /* traffic class and flowlabel for tunnel */ __u32 flags; /* tunnel flags */ struct in6_addr laddr; /* local tunnel end-point address */ struct in6_addr raddr; /* remote tunnel end-point address */ diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 4f435c59de06..f8241130f5ea 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -274,7 +274,7 @@ struct ipv6_pinfo { struct in6_addr *saddr_cache; #endif - __u32 flow_label; + __be32 flow_label; __u32 frag_size; __s16 hop_limit; __s16 mcast_hops; -- cgit v1.2.3 From 0e11c91e1e912bc4db5b71607d149e7e9a77e756 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 8 Nov 2006 00:26:29 -0800 Subject: [AF_PACKET]: annotate Weirdness: the third argument of socket() is net-endian here. Oh, well - it's documented in packet(7). Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/if_packet.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_packet.h b/include/linux/if_packet.h index b92558549d27..99393ef3af39 100644 --- a/include/linux/if_packet.h +++ b/include/linux/if_packet.h @@ -1,17 +1,19 @@ #ifndef __LINUX_IF_PACKET_H #define __LINUX_IF_PACKET_H +#include + struct sockaddr_pkt { unsigned short spkt_family; unsigned char spkt_device[14]; - unsigned short spkt_protocol; + __be16 spkt_protocol; }; struct sockaddr_ll { unsigned short sll_family; - unsigned short sll_protocol; + __be16 sll_protocol; int sll_ifindex; unsigned short sll_hatype; unsigned char sll_pkttype; -- cgit v1.2.3 From 98a4a86128d7179b22365e16bf880e849e20bc7d Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 8 Nov 2006 00:26:51 -0800 Subject: [NETFILTER]: trivial annotations Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/netfilter/nfnetlink.h | 2 +- include/linux/netfilter/nfnetlink_log.h | 10 +++++----- include/linux/netfilter/nfnetlink_queue.h | 18 +++++++++--------- include/linux/netfilter/xt_conntrack.h | 4 ++-- include/linux/netfilter/xt_policy.h | 2 +- include/linux/types.h | 2 ++ 6 files changed, 20 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index 6d8e3e5a80e9..1e9c821f152d 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -78,7 +78,7 @@ struct nfattr struct nfgenmsg { u_int8_t nfgen_family; /* AF_xxx */ u_int8_t version; /* nfnetlink version */ - u_int16_t res_id; /* resource id */ + __be16 res_id; /* resource id */ }; #define NFNETLINK_V0 0 diff --git a/include/linux/netfilter/nfnetlink_log.h b/include/linux/netfilter/nfnetlink_log.h index 87b92f8b988f..55a2a2b814ed 100644 --- a/include/linux/netfilter/nfnetlink_log.h +++ b/include/linux/netfilter/nfnetlink_log.h @@ -16,20 +16,20 @@ enum nfulnl_msg_types { }; struct nfulnl_msg_packet_hdr { - u_int16_t hw_protocol; /* hw protocol (network order) */ + __be16 hw_protocol; /* hw protocol (network order) */ u_int8_t hook; /* netfilter hook */ u_int8_t _pad; }; struct nfulnl_msg_packet_hw { - u_int16_t hw_addrlen; + __be16 hw_addrlen; u_int16_t _pad; u_int8_t hw_addr[8]; }; struct nfulnl_msg_packet_timestamp { - aligned_u64 sec; - aligned_u64 usec; + aligned_be64 sec; + aligned_be64 usec; }; #define NFULNL_PREFIXLEN 30 /* just like old log target */ @@ -67,7 +67,7 @@ struct nfulnl_msg_config_cmd { } __attribute__ ((packed)); struct nfulnl_msg_config_mode { - u_int32_t copy_range; + __be32 copy_range; u_int8_t copy_mode; u_int8_t _pad; } __attribute__ ((packed)); diff --git a/include/linux/netfilter/nfnetlink_queue.h b/include/linux/netfilter/nfnetlink_queue.h index 36af0360b56d..4beea3d6fda8 100644 --- a/include/linux/netfilter/nfnetlink_queue.h +++ b/include/linux/netfilter/nfnetlink_queue.h @@ -13,20 +13,20 @@ enum nfqnl_msg_types { }; struct nfqnl_msg_packet_hdr { - u_int32_t packet_id; /* unique ID of packet in queue */ - u_int16_t hw_protocol; /* hw protocol (network order) */ + __be32 packet_id; /* unique ID of packet in queue */ + __be16 hw_protocol; /* hw protocol (network order) */ u_int8_t hook; /* netfilter hook */ } __attribute__ ((packed)); struct nfqnl_msg_packet_hw { - u_int16_t hw_addrlen; + __be16 hw_addrlen; u_int16_t _pad; u_int8_t hw_addr[8]; }; struct nfqnl_msg_packet_timestamp { - aligned_u64 sec; - aligned_u64 usec; + aligned_be64 sec; + aligned_be64 usec; }; enum nfqnl_attr_type { @@ -47,8 +47,8 @@ enum nfqnl_attr_type { #define NFQA_MAX (__NFQA_MAX - 1) struct nfqnl_msg_verdict_hdr { - u_int32_t verdict; - u_int32_t id; + __be32 verdict; + __be32 id; }; @@ -63,7 +63,7 @@ enum nfqnl_msg_config_cmds { struct nfqnl_msg_config_cmd { u_int8_t command; /* nfqnl_msg_config_cmds */ u_int8_t _pad; - u_int16_t pf; /* AF_xxx for PF_[UN]BIND */ + __be16 pf; /* AF_xxx for PF_[UN]BIND */ }; enum nfqnl_config_mode { @@ -73,7 +73,7 @@ enum nfqnl_config_mode { }; struct nfqnl_msg_config_params { - u_int32_t copy_range; + __be32 copy_range; u_int8_t copy_mode; /* enum nfqnl_config_mode */ } __attribute__ ((packed)); diff --git a/include/linux/netfilter/xt_conntrack.h b/include/linux/netfilter/xt_conntrack.h index 4c2d9945ca54..70b6f718cf4c 100644 --- a/include/linux/netfilter/xt_conntrack.h +++ b/include/linux/netfilter/xt_conntrack.h @@ -29,14 +29,14 @@ struct ip_conntrack_old_tuple { struct { - __u32 ip; + __be32 ip; union { __u16 all; } u; } src; struct { - __u32 ip; + __be32 ip; union { __u16 all; } u; diff --git a/include/linux/netfilter/xt_policy.h b/include/linux/netfilter/xt_policy.h index a8132ec076fb..45654d359a68 100644 --- a/include/linux/netfilter/xt_policy.h +++ b/include/linux/netfilter/xt_policy.h @@ -39,7 +39,7 @@ struct xt_policy_elem union xt_policy_addr smask; union xt_policy_addr daddr; union xt_policy_addr dmask; - u_int32_t spi; + __be32 spi; u_int32_t reqid; u_int8_t proto; u_int8_t mode; diff --git a/include/linux/types.h b/include/linux/types.h index 750f085fa564..9f11fdd2bd72 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -128,6 +128,8 @@ typedef __s64 int64_t; /* this is a special 64bit data type that is 8-byte aligned */ #define aligned_u64 unsigned long long __attribute__((aligned(8))) +#define aligned_be64 __be64 __attribute__((aligned(8))) +#define aligned_le64 __le64 __attribute__((aligned(8))) /** * The type used for indexing onto a disc or disc partition. -- cgit v1.2.3 From ae08e1f092210619fe49551aa3ed0dc0003d5880 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 8 Nov 2006 00:27:11 -0800 Subject: [IPV6]: ip6_output annotations Signed-off-by: Al Viro 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 85577a4ffa61..7fc9a3aaa1c9 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -139,7 +139,7 @@ struct skb_shared_info { /* Warning: this field is not always filled in (UFO)! */ unsigned short gso_segs; unsigned short gso_type; - unsigned int ip6_frag_id; + __be32 ip6_frag_id; struct sk_buff *frag_list; skb_frag_t frags[MAX_SKB_FRAGS]; }; -- cgit v1.2.3 From c1a856c9640c9ff3d70bbd8214b6a0974609eef8 Mon Sep 17 00:00:00 2001 From: Venkat Yekkirala Date: Wed, 8 Nov 2006 17:03:44 -0600 Subject: SELinux: Various xfrm labeling fixes Since the upstreaming of the mlsxfrm modification a few months back, testing has resulted in the identification of the following issues/bugs that are resolved in this patch set. 1. Fix the security context used in the IKE negotiation to be the context of the socket as opposed to the context of the SPD rule. 2. Fix SO_PEERSEC for tcp sockets to return the security context of the peer as opposed to the source. 3. Fix the selection of an SA for an outgoing packet to be at the same context as the originating socket/flow. The following would be the result of applying this patchset: - SO_PEERSEC will now correctly return the peer's context. - IKE deamons will receive the context of the source socket/flow as opposed to the SPD rule's context so that the negotiated SA will be at the same context as the source socket/flow. - The SELinux policy will require one or more of the following for a socket to be able to communicate with/without SAs: 1. To enable a socket to communicate without using labeled-IPSec SAs: allow socket_t unlabeled_t:association { sendto recvfrom } 2. To enable a socket to communicate with labeled-IPSec SAs: allow socket_t self:association { sendto }; allow socket_t peer_sa_t:association { recvfrom }; This Patch: Pass correct security context to IKE for use in negotiation Fix the security context passed to IKE for use in negotiation to be the context of the socket as opposed to the context of the SPD rule so that the SA carries the label of the originating socket/flow. Signed-off-by: Venkat Yekkirala Signed-off-by: James Morris --- include/linux/security.h | 21 ++++++++++----------- 1 file changed, 10 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index b200b9856f32..a509329a669b 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -836,10 +836,8 @@ struct request_sock; * used by the XFRM system. * @sec_ctx contains the security context information being provided by * the user-level policy update program (e.g., setkey). - * @sk refers to the sock from which to derive the security context. * Allocate a security structure to the xp->security field; the security - * field is initialized to NULL when the xfrm_policy is allocated. Only - * one of sec_ctx or sock can be specified. + * field is initialized to NULL when the xfrm_policy is allocated. * Return 0 if operation was successful (memory to allocate, legal context) * @xfrm_policy_clone_security: * @old contains an existing xfrm_policy in the SPD. @@ -858,9 +856,6 @@ struct request_sock; * Database by the XFRM system. * @sec_ctx contains the security context information being provided by * the user-level SA generation program (e.g., setkey or racoon). - * @polsec contains the security context information associated with a xfrm - * policy rule from which to take the base context. polsec must be NULL - * when sec_ctx is specified. * @secid contains the secid from which to take the mls portion of the context. * Allocate a security structure to the x->security field; the security * field is initialized to NULL when the xfrm_state is allocated. Set the @@ -1378,12 +1373,12 @@ struct security_operations { #ifdef CONFIG_SECURITY_NETWORK_XFRM int (*xfrm_policy_alloc_security) (struct xfrm_policy *xp, - struct xfrm_user_sec_ctx *sec_ctx, struct sock *sk); + struct xfrm_user_sec_ctx *sec_ctx); int (*xfrm_policy_clone_security) (struct xfrm_policy *old, struct xfrm_policy *new); void (*xfrm_policy_free_security) (struct xfrm_policy *xp); int (*xfrm_policy_delete_security) (struct xfrm_policy *xp); int (*xfrm_state_alloc_security) (struct xfrm_state *x, - struct xfrm_user_sec_ctx *sec_ctx, struct xfrm_sec_ctx *polsec, + struct xfrm_user_sec_ctx *sec_ctx, u32 secid); void (*xfrm_state_free_security) (struct xfrm_state *x); int (*xfrm_state_delete_security) (struct xfrm_state *x); @@ -3120,7 +3115,7 @@ static inline void security_inet_csk_clone(struct sock *newsk, #ifdef CONFIG_SECURITY_NETWORK_XFRM static inline int security_xfrm_policy_alloc(struct xfrm_policy *xp, struct xfrm_user_sec_ctx *sec_ctx) { - return security_ops->xfrm_policy_alloc_security(xp, sec_ctx, NULL); + return security_ops->xfrm_policy_alloc_security(xp, sec_ctx); } static inline int security_xfrm_policy_clone(struct xfrm_policy *old, struct xfrm_policy *new) @@ -3141,7 +3136,7 @@ static inline int security_xfrm_policy_delete(struct xfrm_policy *xp) static inline int security_xfrm_state_alloc(struct xfrm_state *x, struct xfrm_user_sec_ctx *sec_ctx) { - return security_ops->xfrm_state_alloc_security(x, sec_ctx, NULL, 0); + return security_ops->xfrm_state_alloc_security(x, sec_ctx, 0); } static inline int security_xfrm_state_alloc_acquire(struct xfrm_state *x, @@ -3149,7 +3144,11 @@ static inline int security_xfrm_state_alloc_acquire(struct xfrm_state *x, { if (!polsec) return 0; - return security_ops->xfrm_state_alloc_security(x, NULL, polsec, secid); + /* + * We want the context to be taken from secid which is usually + * from the sock. + */ + return security_ops->xfrm_state_alloc_security(x, NULL, secid); } static inline int security_xfrm_state_delete(struct xfrm_state *x) -- cgit v1.2.3 From 6b877699c6f1efede4545bcecc367786a472eedb Mon Sep 17 00:00:00 2001 From: Venkat Yekkirala Date: Wed, 8 Nov 2006 17:04:09 -0600 Subject: SELinux: Return correct context for SO_PEERSEC Fix SO_PEERSEC for tcp sockets to return the security context of the peer (as represented by the SA from the peer) as opposed to the SA used by the local/source socket. Signed-off-by: Venkat Yekkirala Signed-off-by: James Morris --- include/linux/security.h | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index a509329a669b..84cebcdb3f83 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -826,6 +826,8 @@ struct request_sock; * Sets the openreq's sid to socket's sid with MLS portion taken from peer sid. * @inet_csk_clone: * Sets the new child socket's sid to the openreq sid. + * @inet_conn_established: + * Sets the connection's peersid to the secmark on skb. * @req_classify_flow: * Sets the flow's sid to the openreq sid. * @@ -1368,6 +1370,7 @@ struct security_operations { int (*inet_conn_request)(struct sock *sk, struct sk_buff *skb, struct request_sock *req); void (*inet_csk_clone)(struct sock *newsk, const struct request_sock *req); + void (*inet_conn_established)(struct sock *sk, struct sk_buff *skb); void (*req_classify_flow)(const struct request_sock *req, struct flowi *fl); #endif /* CONFIG_SECURITY_NETWORK */ @@ -2961,9 +2964,15 @@ static inline void security_inet_csk_clone(struct sock *newsk, { security_ops->inet_csk_clone(newsk, req); } + +static inline void security_inet_conn_established(struct sock *sk, + struct sk_buff *skb) +{ + security_ops->inet_conn_established(sk, skb); +} #else /* CONFIG_SECURITY_NETWORK */ static inline int security_unix_stream_connect(struct socket * sock, - struct socket * other, + struct socket * other, struct sock * newsk) { return 0; @@ -3110,6 +3119,11 @@ static inline void security_inet_csk_clone(struct sock *newsk, const struct request_sock *req) { } + +static inline void security_inet_conn_established(struct sock *sk, + struct sk_buff *skb) +{ +} #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_NETWORK_XFRM -- cgit v1.2.3 From 67f83cbf081a70426ff667e8d14f94e13ed3bdca Mon Sep 17 00:00:00 2001 From: Venkat Yekkirala Date: Wed, 8 Nov 2006 17:04:26 -0600 Subject: SELinux: Fix SA selection semantics Fix the selection of an SA for an outgoing packet to be at the same context as the originating socket/flow. This eliminates the SELinux policy's ability to use/sendto SAs with contexts other than the socket's. With this patch applied, the SELinux policy will require one or more of the following for a socket to be able to communicate with/without SAs: 1. To enable a socket to communicate without using labeled-IPSec SAs: allow socket_t unlabeled_t:association { sendto recvfrom } 2. To enable a socket to communicate with labeled-IPSec SAs: allow socket_t self:association { sendto }; allow socket_t peer_sa_t:association { recvfrom }; Signed-off-by: Venkat Yekkirala Signed-off-by: James Morris --- include/linux/security.h | 19 ------------------- 1 file changed, 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index 84cebcdb3f83..83cdefae9931 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -886,11 +886,6 @@ struct request_sock; * @xp contains the policy to check for a match. * @fl contains the flow to check for a match. * Return 1 if there is a match. - * @xfrm_flow_state_match: - * @fl contains the flow key to match. - * @xfrm points to the xfrm_state to match. - * @xp points to the xfrm_policy to match. - * Return 1 if there is a match. * @xfrm_decode_session: * @skb points to skb to decode. * @secid points to the flow key secid to set. @@ -1388,8 +1383,6 @@ struct security_operations { int (*xfrm_policy_lookup)(struct xfrm_policy *xp, u32 fl_secid, u8 dir); int (*xfrm_state_pol_flow_match)(struct xfrm_state *x, struct xfrm_policy *xp, struct flowi *fl); - int (*xfrm_flow_state_match)(struct flowi *fl, struct xfrm_state *xfrm, - struct xfrm_policy *xp); int (*xfrm_decode_session)(struct sk_buff *skb, u32 *secid, int ckall); #endif /* CONFIG_SECURITY_NETWORK_XFRM */ @@ -3186,12 +3179,6 @@ static inline int security_xfrm_state_pol_flow_match(struct xfrm_state *x, return security_ops->xfrm_state_pol_flow_match(x, xp, fl); } -static inline int security_xfrm_flow_state_match(struct flowi *fl, - struct xfrm_state *xfrm, struct xfrm_policy *xp) -{ - return security_ops->xfrm_flow_state_match(fl, xfrm, xp); -} - static inline int security_xfrm_decode_session(struct sk_buff *skb, u32 *secid) { return security_ops->xfrm_decode_session(skb, secid, 1); @@ -3255,12 +3242,6 @@ static inline int security_xfrm_state_pol_flow_match(struct xfrm_state *x, return 1; } -static inline int security_xfrm_flow_state_match(struct flowi *fl, - struct xfrm_state *xfrm, struct xfrm_policy *xp) -{ - return 1; -} - static inline int security_xfrm_decode_session(struct sk_buff *skb, u32 *secid) { return 0; -- cgit v1.2.3 From 82e91ffef60e6eba9848fe149ce1eecd2b5aef12 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Thu, 9 Nov 2006 15:19:14 -0800 Subject: [NET]: Turn nfmark into generic mark nfmark is being used in various subsystems and has become the defacto mark field for all kinds of packets. Therefore it makes sense to rename it to `mark' and remove the dependency on CONFIG_NETFILTER. Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/skbuff.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 7fc9a3aaa1c9..e3ae544b3956 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -216,7 +216,7 @@ enum { * @tail: Tail pointer * @end: End pointer * @destructor: Destruct function - * @nfmark: Can be used for communication between hooks + * @mark: Generic packet mark * @nfct: Associated connection, if any * @ipvs_property: skbuff is owned by ipvs * @nfctinfo: Relationship of this skb to the connection @@ -295,7 +295,6 @@ 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 */ @@ -310,6 +309,7 @@ struct sk_buff { __u32 secmark; #endif + __u32 mark; /* These elements must be at the end, see alloc_skb() for details. */ unsigned int truesize; -- cgit v1.2.3 From b8964ed9fa727109c9084abc807652ebfb681c18 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Thu, 9 Nov 2006 15:22:18 -0800 Subject: [NET] rules: Protocol independant mark selector Move mark selector currently implemented per protocol into the protocol independant part. Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/fib_rules.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fib_rules.h b/include/linux/fib_rules.h index 4418c8d9d479..adcdfbdd14d5 100644 --- a/include/linux/fib_rules.h +++ b/include/linux/fib_rules.h @@ -34,7 +34,7 @@ enum FRA_UNUSED3, FRA_UNUSED4, FRA_UNUSED5, - FRA_FWMARK, /* netfilter mark */ + FRA_FWMARK, /* mark */ FRA_FLOW, /* flow/class id */ FRA_UNUSED6, FRA_UNUSED7, -- cgit v1.2.3 From 3dfbcc411e461db51a1ac1aa1c6ebe2c5a0275a0 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Thu, 9 Nov 2006 15:23:20 -0800 Subject: [NET] rules: Add support to invert selectors Introduces a new flag FIB_RULE_INVERT causing rules to apply if the specified selector doesn't match. Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/fib_rules.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fib_rules.h b/include/linux/fib_rules.h index adcdfbdd14d5..8270aac2aa5d 100644 --- a/include/linux/fib_rules.h +++ b/include/linux/fib_rules.h @@ -6,6 +6,7 @@ /* rule is permanent, and cannot be deleted */ #define FIB_RULE_PERMANENT 1 +#define FIB_RULE_INVERT 2 struct fib_rule_hdr { -- cgit v1.2.3 From 3ff825b28d3345ef381eceae22bf9d92231f23dc Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Thu, 9 Nov 2006 16:32:06 -0800 Subject: [TCP]: Add tcp_available_congestion_control sysctl. Create /proc/sys/net/ipv4/tcp_available_congestion_control that reflects currently available TCP choices. Signed-off-by: Stephen Hemminger 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 d98562f1df76..28a48279654d 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -426,6 +426,7 @@ enum NET_CIPSOV4_CACHE_BUCKET_SIZE=119, NET_CIPSOV4_RBM_OPTFMT=120, NET_CIPSOV4_RBM_STRICTVALID=121, + NET_TCP_AVAIL_CONG_CONTROL=122, }; enum { -- cgit v1.2.3 From ce7bc3bf15cbf5dc5a5587ccb6b04c5b4dde4336 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Thu, 9 Nov 2006 16:35:15 -0800 Subject: [TCP]: Restrict congestion control choices. Allow normal users to only choose among a restricted set of congestion control choices. The default is reno and what ever has been configured as default. But the policy can be changed by administrator at any time. For example, to allow any choice: cp /proc/sys/net/ipv4/tcp_available_congestion_control \ /proc/sys/net/ipv4/tcp_allowed_congestion_control Signed-off-by: Stephen Hemminger 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 28a48279654d..0725441621d0 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -427,6 +427,7 @@ enum NET_CIPSOV4_RBM_OPTFMT=120, NET_CIPSOV4_RBM_STRICTVALID=121, NET_TCP_AVAIL_CONG_CONTROL=122, + NET_TCP_ALLOWED_CONG_CONTROL=123, }; enum { -- cgit v1.2.3 From 9b42078ed6edfe04e9dc9a59b946ad912aeef717 Mon Sep 17 00:00:00 2001 From: Gerrit Renker Date: Fri, 10 Nov 2006 11:22:32 -0200 Subject: [DCCP]: Combine allocating & zeroing header space on skb This is a code simplification: it combines three often recurring operations into one inline function, * allocate `len' bytes header space in skb * fill these `len' bytes with zeroes * cast the start of this header space as dccp_hdr Signed-off-by: Gerrit Renker Signed-off-by: Arnaldo Carvalho de Melo --- include/linux/dccp.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dccp.h b/include/linux/dccp.h index 53553c99cad6..90d04ffddae8 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -256,6 +256,13 @@ static inline struct dccp_hdr *dccp_hdr(const struct sk_buff *skb) return (struct dccp_hdr *)skb->h.raw; } +static inline struct dccp_hdr *dccp_zeroed_hdr(struct sk_buff *skb, int headlen) +{ + skb->h.raw = skb_push(skb, headlen); + memset(skb->h.raw, 0, headlen); + return dccp_hdr(skb); +} + static inline struct dccp_hdr_ext *dccp_hdrx(const struct sk_buff *skb) { return (struct dccp_hdr_ext *)(skb->h.raw + sizeof(struct dccp_hdr)); -- cgit v1.2.3 From 6f4e5fff1e4d46714ea554fd83e44eab534e8b11 Mon Sep 17 00:00:00 2001 From: Gerrit Renker Date: Fri, 10 Nov 2006 17:43:06 -0200 Subject: [DCCP]: Support for partial checksums (RFC 4340, sec. 9.2) This patch does the following: a) introduces variable-length checksums as specified in [RFC 4340, sec. 9.2] b) provides necessary socket options and documentation as to how to use them c) basic support and infrastructure for the Minimum Checksum Coverage feature [RFC 4340, sec. 9.2.1]: acceptability tests, user notification and user interface In addition, it (1) fixes two bugs in the DCCPv4 checksum computation: * pseudo-header used checksum_len instead of skb->len * incorrect checksum coverage calculation based on dccph_x (2) removes dccp_v4_verify_checksum() since it reduplicates code of the checksum computation; code calling this function is updated accordingly. (3) now uses skb_checksum(), which is safer than checksum_partial() if the sk_buff has is a non-linear buffer (has pages attached to it). (4) fixes an outstanding TODO item: * If P.CsCov is too large for the packet size, drop packet and return. The code has been tested with applications, the latest version of tcpdump now comes with support for partial DCCP checksums. Signed-off-by: Gerrit Renker Signed-off-by: Arnaldo Carvalho de Melo --- include/linux/dccp.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dccp.h b/include/linux/dccp.h index 90d04ffddae8..0502dfa7f32c 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -183,6 +183,7 @@ enum { DCCPF_ACK_RATIO = 5, DCCPF_SEND_ACK_VECTOR = 6, DCCPF_SEND_NDP_COUNT = 7, + DCCPF_MIN_CSUM_COVER = 8, /* 10-127 reserved */ DCCPF_MIN_CCID_SPECIFIC = 128, DCCPF_MAX_CCID_SPECIFIC = 255, @@ -200,6 +201,8 @@ struct dccp_so_feat { #define DCCP_SOCKOPT_SERVICE 2 #define DCCP_SOCKOPT_CHANGE_L 3 #define DCCP_SOCKOPT_CHANGE_R 4 +#define DCCP_SOCKOPT_SEND_CSCOV 10 +#define DCCP_SOCKOPT_RECV_CSCOV 11 #define DCCP_SOCKOPT_CCID_RX_INFO 128 #define DCCP_SOCKOPT_CCID_TX_INFO 192 @@ -450,6 +453,8 @@ struct dccp_ackvec; * @dccps_timestamp_echo - latest timestamp received on a TIMESTAMP option * @dccps_packet_size - Set thru setsockopt * @dccps_role - Role of this sock, one of %dccp_role + * @dccps_pcslen - sender partial checksum coverage (via sockopt) + * @dccps_pcrlen - receiver partial checksum coverage (via sockopt) * @dccps_ndp_count - number of Non Data Packets since last data packet * @dccps_hc_rx_ackvec - rx half connection ack vector * @dccps_xmit_timer - timer for when CCID is not ready to send @@ -474,6 +479,8 @@ struct dccp_sock { __u32 dccps_packet_size; __u16 dccps_l_ack_ratio; __u16 dccps_r_ack_ratio; + __u16 dccps_pcslen; + __u16 dccps_pcrlen; unsigned long dccps_ndp_count; __u32 dccps_mss_cache; struct dccp_minisock dccps_minisock; -- cgit v1.2.3 From 339bf98ffc6a8d8eb16fc532ac57ffbced2f8a68 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Fri, 10 Nov 2006 14:10:15 -0800 Subject: [NETLINK]: Do precise netlink message allocations where possible Account for the netlink message header size directly in nlmsg_new() instead of relying on the caller calculate it correctly. Replaces error handling of message construction functions when constructing notifications with bug traps since a failure implies a bug in calculating the size of the skb. Signed-off-by: Thomas Graf Acked-by: Paul Moore 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 66411622e06e..e61e1e138421 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -174,6 +174,7 @@ int netlink_sendskb(struct sock *sk, struct sk_buff *skb, int protocol); */ #define NLMSG_GOODORDER 0 #define NLMSG_GOODSIZE (SKB_MAX_ORDER(0, NLMSG_GOODORDER)) +#define NLMSG_DEFAULT_SIZE (NLMSG_GOODSIZE - NLMSG_HDRLEN) struct netlink_callback -- cgit v1.2.3 From 2e2e9e92bd723244ea20fa488b1780111f2b05e1 Mon Sep 17 00:00:00 2001 From: Gerrit Renker Date: Mon, 13 Nov 2006 13:23:52 -0200 Subject: [DCCP]: Add sysctls to control retransmission behaviour This adds 3 sysctls which govern the retransmission behaviour of DCCP control packets (3way handshake, feature negotiation). It removes 4 FIXMEs from the code. The close resemblance of sysctl variables to their TCP analogues is emphasised not only by their name, but also by giving them the same initial values. This is useful since there is not much practical experience with DCCP yet. Furthermore, with regard to the previous patch, it is now possible to limit the number of keepalive-Responses by setting net.dccp.default.request_retries (also a bit like in TCP). Lastly, added documentation of all existing DCCP sysctls. Signed-off-by: Gerrit Renker Signed-off-by: Arnaldo Carvalho de Melo --- include/linux/sysctl.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 0725441621d0..2e8c5ad82793 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -614,6 +614,9 @@ enum { NET_DCCP_DEFAULT_ACK_RATIO = 4, NET_DCCP_DEFAULT_SEND_ACKVEC = 5, NET_DCCP_DEFAULT_SEND_NDP = 6, + NET_DCCP_DEFAULT_REQ_RETRIES = 7, + NET_DCCP_DEFAULT_RETRIES1 = 8, + NET_DCCP_DEFAULT_RETRIES2 = 9, }; /* /proc/sys/net/ipx */ -- cgit v1.2.3 From 90833aa4f496d69ca374af6acef7d1614c8693ff Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Mon, 13 Nov 2006 16:02:22 -0800 Subject: [NET]: The scheduled removal of the frame diverter. This patch contains the scheduled removal of the frame diverter. Signed-off-by: Adrian Bunk Signed-off-by: David S. Miller --- include/linux/Kbuild | 1 - include/linux/divert.h | 132 ---------------------------------------------- include/linux/netdevice.h | 6 --- include/linux/sockios.h | 4 +- 4 files changed, 2 insertions(+), 141 deletions(-) delete mode 100644 include/linux/divert.h (limited to 'include/linux') diff --git a/include/linux/Kbuild b/include/linux/Kbuild index a1155a2beb32..d7e04689304c 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -193,7 +193,6 @@ unifdef-y += cuda.h unifdef-y += cyclades.h unifdef-y += dccp.h unifdef-y += dirent.h -unifdef-y += divert.h unifdef-y += dlm.h unifdef-y += elfcore.h unifdef-y += errno.h diff --git a/include/linux/divert.h b/include/linux/divert.h deleted file mode 100644 index 8fb4e9de6843..000000000000 --- a/include/linux/divert.h +++ /dev/null @@ -1,132 +0,0 @@ -/* - * Frame Diversion, Benoit Locher - * - * Changes: - * 06/09/2000 BL: initial version - * - */ - -#ifndef _LINUX_DIVERT_H -#define _LINUX_DIVERT_H - -#include - -#define MAX_DIVERT_PORTS 8 /* Max number of ports to divert (tcp, udp) */ - -/* Divertable protocols */ -#define DIVERT_PROTO_NONE 0x0000 -#define DIVERT_PROTO_IP 0x0001 -#define DIVERT_PROTO_ICMP 0x0002 -#define DIVERT_PROTO_TCP 0x0004 -#define DIVERT_PROTO_UDP 0x0008 - -/* - * This is an Ethernet Frame Diverter option block - */ -struct divert_blk -{ - int divert; /* are we active */ - unsigned int protos; /* protocols */ - __u16 tcp_dst[MAX_DIVERT_PORTS]; /* specific tcp dst ports to divert */ - __u16 tcp_src[MAX_DIVERT_PORTS]; /* specific tcp src ports to divert */ - __u16 udp_dst[MAX_DIVERT_PORTS]; /* specific udp dst ports to divert */ - __u16 udp_src[MAX_DIVERT_PORTS]; /* specific udp src ports to divert */ -}; - -/* - * Diversion control block, for configuration with the userspace tool - * divert - */ - -typedef union _divert_cf_arg -{ - __s16 int16; - __u16 uint16; - __s32 int32; - __u32 uint32; - __s64 int64; - __u64 uint64; - void __user *ptr; -} divert_cf_arg; - - -struct divert_cf -{ - int cmd; /* Command */ - divert_cf_arg arg1, - arg2, - arg3; - int dev_index; /* device index (eth0=0, etc...) */ -}; - - -/* Diversion commands */ -#define DIVCMD_DIVERT 1 /* ENABLE/DISABLE diversion */ -#define DIVCMD_IP 2 /* ENABLE/DISABLE whold IP diversion */ -#define DIVCMD_TCP 3 /* ENABLE/DISABLE whold TCP diversion */ -#define DIVCMD_TCPDST 4 /* ADD/REMOVE TCP DST port for diversion */ -#define DIVCMD_TCPSRC 5 /* ADD/REMOVE TCP SRC port for diversion */ -#define DIVCMD_UDP 6 /* ENABLE/DISABLE whole UDP diversion */ -#define DIVCMD_UDPDST 7 /* ADD/REMOVE UDP DST port for diversion */ -#define DIVCMD_UDPSRC 8 /* ADD/REMOVE UDP SRC port for diversion */ -#define DIVCMD_ICMP 9 /* ENABLE/DISABLE whole ICMP diversion */ -#define DIVCMD_GETSTATUS 10 /* GET the status of the diverter */ -#define DIVCMD_RESET 11 /* Reset the diverter on the specified dev */ -#define DIVCMD_GETVERSION 12 /* Retrieve the diverter code version (char[32]) */ - -/* General syntax of the commands: - * - * DIVCMD_xxxxxx(arg1, arg2, arg3, dev_index) - * - * SIOCSIFDIVERT: - * DIVCMD_DIVERT(DIVARG1_ENABLE|DIVARG1_DISABLE, , ,ifindex) - * DIVCMD_IP(DIVARG1_ENABLE|DIVARG1_DISABLE, , , ifindex) - * DIVCMD_TCP(DIVARG1_ENABLE|DIVARG1_DISABLE, , , ifindex) - * DIVCMD_TCPDST(DIVARG1_ADD|DIVARG1_REMOVE, port, , ifindex) - * DIVCMD_TCPSRC(DIVARG1_ADD|DIVARG1_REMOVE, port, , ifindex) - * DIVCMD_UDP(DIVARG1_ENABLE|DIVARG1_DISABLE, , , ifindex) - * DIVCMD_UDPDST(DIVARG1_ADD|DIVARG1_REMOVE, port, , ifindex) - * DIVCMD_UDPSRC(DIVARG1_ADD|DIVARG1_REMOVE, port, , ifindex) - * DIVCMD_ICMP(DIVARG1_ENABLE|DIVARG1_DISABLE, , , ifindex) - * DIVCMD_RESET(, , , ifindex) - * - * SIOGIFDIVERT: - * DIVCMD_GETSTATUS(divert_blk, , , ifindex) - * DIVCMD_GETVERSION(string[3]) - */ - - -/* Possible values for arg1 */ -#define DIVARG1_ENABLE 0 /* ENABLE something */ -#define DIVARG1_DISABLE 1 /* DISABLE something */ -#define DIVARG1_ADD 2 /* ADD something */ -#define DIVARG1_REMOVE 3 /* REMOVE something */ - - -#ifdef __KERNEL__ - -/* diverter functions */ -#include - -#ifdef CONFIG_NET_DIVERT -#include - -int alloc_divert_blk(struct net_device *); -void free_divert_blk(struct net_device *); -int divert_ioctl(unsigned int cmd, struct divert_cf __user *arg); -void divert_frame(struct sk_buff *skb); -static inline void handle_diverter(struct sk_buff *skb) -{ - /* if diversion is supported on device, then divert */ - if (skb->dev->divert && skb->dev->divert->divert) - divert_frame(skb); -} - -#else -# define alloc_divert_blk(dev) (0) -# define free_divert_blk(dev) do {} while (0) -# define divert_ioctl(cmd, arg) (-ENOPKG) -# define handle_diverter(skb) do {} while (0) -#endif -#endif -#endif /* _LINUX_DIVERT_H */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 83b8c4f1d69d..4e967b2e22cc 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -38,7 +38,6 @@ #include #include -struct divert_blk; struct vlan_group; struct ethtool_ops; struct netpoll_info; @@ -517,11 +516,6 @@ struct net_device /* bridge stuff */ struct net_bridge_port *br_port; -#ifdef CONFIG_NET_DIVERT - /* this will get initialized at each interface type init routine */ - struct divert_blk *divert; -#endif /* CONFIG_NET_DIVERT */ - /* class/net/name entry */ struct class_device class_dev; /* space for optional statistics and wireless sysfs groups */ diff --git a/include/linux/sockios.h b/include/linux/sockios.h index e6b9d1d36ea2..abef7596655a 100644 --- a/include/linux/sockios.h +++ b/include/linux/sockios.h @@ -72,8 +72,8 @@ #define SIOCGIFTXQLEN 0x8942 /* Get the tx queue length */ #define SIOCSIFTXQLEN 0x8943 /* Set the tx queue length */ -#define SIOCGIFDIVERT 0x8944 /* Frame diversion support */ -#define SIOCSIFDIVERT 0x8945 /* Set frame diversion options */ +/* SIOCGIFDIVERT was: 0x8944 Frame diversion support */ +/* SIOCSIFDIVERT was: 0x8945 Set frame diversion options */ #define SIOCETHTOOL 0x8946 /* Ethtool interface */ -- cgit v1.2.3 From b9df3cb8cf9a96e63dfdcd3056a9cbc71f2459e7 Mon Sep 17 00:00:00 2001 From: Gerrit Renker Date: Tue, 14 Nov 2006 11:21:36 -0200 Subject: [TCP/DCCP]: Introduce net_xmit_eval Throughout the TCP/DCCP (and tunnelling) code, it often happens that the return code of a transmit function needs to be tested against NET_XMIT_CN which is a value that does not indicate a strict error condition. This patch uses a macro for these recurring situations which is consistent with the already existing macro net_xmit_errno, saving on duplicated code. Signed-off-by: Gerrit Renker Signed-off-by: Arnaldo Carvalho de Melo --- include/linux/netdevice.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 4e967b2e22cc..caa3c2593719 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -66,6 +66,10 @@ struct netpoll_info; #define NET_RX_CN_HIGH 4 /* The storm is here */ #define NET_RX_BAD 5 /* packet dropped due to kernel error */ +/* NET_XMIT_CN is special. It does not guarantee that this packet is lost. It + * indicates that the device will soon be dropping packets, or already drops + * some packets of the same priority; prompting us to send less aggressively. */ +#define net_xmit_eval(e) ((e) == NET_XMIT_CN? 0 : (e)) #define net_xmit_errno(e) ((e) != NET_XMIT_CN ? -ENOBUFS : 0) #endif -- cgit v1.2.3 From c02fdc0e81e9c735d8d895af1e201b235df326d8 Mon Sep 17 00:00:00 2001 From: Gerrit Renker Date: Tue, 14 Nov 2006 12:48:10 -0200 Subject: [DCCP]: Make feature negotiation more readable This patch replaces cryptic feature negotiation messages of type Oct 31 15:42:20 kernel: dccp_feat_change: feat change type=32 feat=1 Oct 31 15:42:21 kernel: dccp_feat_change: feat change type=34 feat=1 Oct 31 15:42:21 kernel: dccp_feat_change: feat change type=32 feat=5 into ones of type: Nov 2 13:54:45 kernel: dccp_feat_change: ChangeL(CCID (1), 3) Nov 2 13:54:45 kernel: dccp_feat_change: ChangeR(CCID (1), 3) Nov 2 13:54:45 kernel: dccp_feat_change: ChangeL(Ack Ratio (5), 2) Also, * completed the feature number list wrt RFC 4340 sec. 6.4 * annotating which ones have been implemented so far * implemented rudimentary sanity checking in feat.c (FIXMEs) * some minor fixes Commiter note: uninlined dccp_feat_name and dccp_feat_typename, for consistency with dccp_{state,packet}_name, that, BTW, should be compiled only if CONFIG_IP_DCCP_DEBUG is selected, leaving this to another cset tho. Also shortened dccp_feat_negotiation_debug to dccp_feat_debug. Signed-off-by: Gerrit Renker Signed-off-by: Arnaldo Carvalho de Melo --- include/linux/dccp.h | 25 ++++++++++++++----------- 1 file changed, 14 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dccp.h b/include/linux/dccp.h index 0502dfa7f32c..696319ee2d5b 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -175,18 +175,21 @@ enum { DCCPC_CCID3 = 3, }; -/* 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, +/* DCCP features (RFC 4340 section 6.4) */ + enum { + DCCPF_RESERVED = 0, + DCCPF_CCID = 1, + DCCPF_SHORT_SEQNOS = 2, /* XXX: not yet implemented */ + DCCPF_SEQUENCE_WINDOW = 3, + DCCPF_ECN_INCAPABLE = 4, /* XXX: not yet implemented */ + DCCPF_ACK_RATIO = 5, + DCCPF_SEND_ACK_VECTOR = 6, + DCCPF_SEND_NDP_COUNT = 7, DCCPF_MIN_CSUM_COVER = 8, - /* 10-127 reserved */ - DCCPF_MIN_CCID_SPECIFIC = 128, - DCCPF_MAX_CCID_SPECIFIC = 255, + DCCPF_DATA_CHECKSUM = 9, /* XXX: not yet implemented */ + /* 10-127 reserved */ + DCCPF_MIN_CCID_SPECIFIC = 128, + DCCPF_MAX_CCID_SPECIFIC = 255, }; /* this structure is argument to DCCP_SOCKOPT_CHANGE_X */ -- cgit v1.2.3 From 09dbc3895e3242346bd434dae743c456fd28fc6a Mon Sep 17 00:00:00 2001 From: Gerrit Renker Date: Tue, 14 Nov 2006 12:57:34 -0200 Subject: [DCCP]: Miscellaneous code tidy-ups This patch does not change code; it performs some trivial clean/tidy-ups: * removal of a `debug_prefix' string in favour of the already existing dccp_role(sk) * add documentation of structures and constants * separated out the cases for invalid packets (step 1 of the packet validation) * removing duplicate statements * combining declaration & initialisation Signed-off-by: Gerrit Renker Signed-off-by: Arnaldo Carvalho de Melo --- include/linux/dccp.h | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dccp.h b/include/linux/dccp.h index 696319ee2d5b..d308f1228b61 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -209,6 +209,7 @@ struct dccp_so_feat { #define DCCP_SOCKOPT_CCID_RX_INFO 128 #define DCCP_SOCKOPT_CCID_TX_INFO 192 +/* maximum number of services provided on the same listening port */ #define DCCP_SERVICE_LIST_MAX_LEN 32 #ifdef __KERNEL__ @@ -355,6 +356,9 @@ static inline unsigned int dccp_hdr_len(const struct sk_buff *skb) * @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) + * @dccpms_ack_ratio - Ack Ratio Feature (section 11.3) + * @dccpms_pending - List of features being negotiated + * @dccpms_conf - */ struct dccp_minisock { __u64 dccpms_sequence_window; @@ -452,14 +456,26 @@ struct dccp_ackvec; * @dccps_gss - greatest sequence number sent * @dccps_gsr - greatest valid sequence number received * @dccps_gar - greatest valid ack number received on a non-Sync; initialized to %dccps_iss + * @dccps_service - first (passive sock) or unique (active sock) service code + * @dccps_service_list - second .. last service code on passive socket * @dccps_timestamp_time - time of latest TIMESTAMP option * @dccps_timestamp_echo - latest timestamp received on a TIMESTAMP option * @dccps_packet_size - Set thru setsockopt - * @dccps_role - Role of this sock, one of %dccp_role + * @dccps_l_ack_ratio - + * @dccps_r_ack_ratio - * @dccps_pcslen - sender partial checksum coverage (via sockopt) * @dccps_pcrlen - receiver partial checksum coverage (via sockopt) * @dccps_ndp_count - number of Non Data Packets since last data packet + * @dccps_mss_cache - + * @dccps_minisock - * @dccps_hc_rx_ackvec - rx half connection ack vector + * @dccps_hc_rx_ccid - + * @dccps_hc_tx_ccid - + * @dccps_options_received - + * @dccps_epoch - + * @dccps_role - Role of this sock, one of %dccp_role + * @dccps_hc_rx_insert_options - + * @dccps_hc_tx_insert_options - * @dccps_xmit_timer - timer for when CCID is not ready to send */ struct dccp_sock { -- cgit v1.2.3 From 93ec2c723e3f8a216dde2899aeb85c648672bc6b Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Thu, 26 Oct 2006 15:46:50 -0700 Subject: netpoll info leak After looking harder, Steve noticed that the netpoll beast leaked a little every time it shutdown for a nap. Not a big leak, but a nuisance kind of thing. He took out his refcount duct tape and patched the leak. It was overkill since there was already other locking in that area, but it looked clean and wouldn't attract fleas. Signed-off-by: Stephen Hemminger --- include/linux/netpoll.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index 1efe60c5c00c..39845fc975f9 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -25,6 +25,7 @@ struct netpoll { }; struct netpoll_info { + atomic_t refcnt; spinlock_t poll_lock; int poll_owner; int tries; -- cgit v1.2.3 From b6cd27ed33886a5ffaf0925a6d98e13e18e8a1af Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Thu, 26 Oct 2006 15:46:51 -0700 Subject: netpoll per device txq When the netpoll beast got really busy, it tended to clog things, so it stored them for later. But the beast was putting all it's skb's in one basket. This was bad because maybe some pipes were clogged and others were not. Signed-off-by: Stephen Hemminger --- include/linux/netpoll.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index 39845fc975f9..93a8b7664423 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -33,6 +33,8 @@ struct netpoll_info { spinlock_t rx_lock; struct netpoll *rx_np; /* netpoll that registered an rx_hook */ struct sk_buff_head arp_tx; /* list of arp requests to reply to */ + struct sk_buff_head txq; + struct work_struct tx_work; }; void netpoll_poll(struct netpoll *np); -- cgit v1.2.3 From 2bdfe0baeca0e2750037b8fba71905c00ac3c515 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Thu, 26 Oct 2006 15:46:54 -0700 Subject: netpoll retry cleanup The netpoll beast was still not happy. If the beast got clogged pipes, it tended to stare blankly off in space for a long time. The problem couldn't be completely fixed because the beast talked with irq's disabled. But it could be made less painful and shorter. Signed-off-by: Stephen Hemminger --- include/linux/netpoll.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index 93a8b7664423..c65d12ec7bb0 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -28,7 +28,6 @@ struct netpoll_info { atomic_t refcnt; spinlock_t poll_lock; int poll_owner; - int tries; int rx_flags; spinlock_t rx_lock; struct netpoll *rx_np; /* netpoll that registered an rx_hook */ -- cgit v1.2.3 From 5de4a473bda49554e4e9bd93b78f43c49a7ea69c Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Thu, 26 Oct 2006 15:46:55 -0700 Subject: netpoll queue cleanup The beast had a long and not very happy history. At one point, a friend (netdump) had asked that he open up a little. Well, the friend was long gone now, and the beast had this dangling piece hanging (netpoll_queue). It wasn't hard to stitch the netpoll_queue back in where it belonged and make everything tidy. Signed-off-by: Stephen Hemminger --- include/linux/netpoll.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index c65d12ec7bb0..b7eb008c43de 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -18,7 +18,7 @@ struct netpoll { struct net_device *dev; char dev_name[16], *name; void (*rx_hook)(struct netpoll *, int, char *, int); - void (*drop)(struct sk_buff *skb); + u32 local_ip, remote_ip; u16 local_port, remote_port; unsigned char local_mac[6], remote_mac[6]; @@ -44,7 +44,7 @@ int netpoll_trap(void); void netpoll_set_trap(int trap); void netpoll_cleanup(struct netpoll *np); int __netpoll_rx(struct sk_buff *skb); -void netpoll_queue(struct sk_buff *skb); + #ifdef CONFIG_NETPOLL static inline int netpoll_rx(struct sk_buff *skb) -- cgit v1.2.3 From bf6bce71eae386dbc37f93af7e5ad173450d9945 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Thu, 26 Oct 2006 15:46:56 -0700 Subject: netpoll header cleanup As Steve left netpoll beast, hopefully not to return soon. He noticed that the header was messy. He straightened it up and polished it a little, then waved goodbye. Signed-off-by: Stephen Hemminger --- include/linux/netpoll.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index b7eb008c43de..2cc9867b1626 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -12,16 +12,15 @@ #include #include -struct netpoll; - struct netpoll { struct net_device *dev; - char dev_name[16], *name; + char dev_name[IFNAMSIZ]; + const char *name; void (*rx_hook)(struct netpoll *, int, char *, int); u32 local_ip, remote_ip; u16 local_port, remote_port; - unsigned char local_mac[6], remote_mac[6]; + u8 local_mac[ETH_ALEN], remote_mac[ETH_ALEN]; }; struct netpoll_info { -- cgit v1.2.3 From cfb6eeb4c860592edd123fdea908d23c6ad1c7dc Mon Sep 17 00:00:00 2001 From: YOSHIFUJI Hideaki Date: Tue, 14 Nov 2006 19:07:45 -0800 Subject: [TCP]: MD5 Signature Option (RFC2385) support. Based on implementation by Rick Payne. Signed-off-by: YOSHIFUJI Hideaki Signed-off-by: David S. Miller --- include/linux/tcp.h | 35 ++++++++++++++++++++++++++++++++--- 1 file changed, 32 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 2d36f6db3706..0aecfc955591 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -19,6 +19,7 @@ #include #include +#include struct tcphdr { __be16 source; @@ -94,6 +95,7 @@ enum { #define TCP_INFO 11 /* Information about this connection. */ #define TCP_QUICKACK 12 /* Block/reenable quick acks */ #define TCP_CONGESTION 13 /* Congestion control algorithm */ +#define TCP_MD5SIG 14 /* TCP MD5 Signature (RFC2385) */ #define TCPI_OPT_TIMESTAMPS 1 #define TCPI_OPT_SACK 2 @@ -157,6 +159,17 @@ struct tcp_info __u32 tcpi_total_retrans; }; +/* for TCP_MD5SIG socket option */ +#define TCP_MD5SIG_MAXKEYLEN 80 + +struct tcp_md5sig { + struct __kernel_sockaddr_storage tcpm_addr; /* address associated */ + __u16 __tcpm_pad1; /* zero */ + __u16 tcpm_keylen; /* key length */ + __u32 __tcpm_pad2; /* zero */ + __u8 tcpm_key[TCP_MD5SIG_MAXKEYLEN]; /* key (binary) */ +}; + #ifdef __KERNEL__ #include @@ -197,9 +210,13 @@ struct tcp_options_received { }; struct tcp_request_sock { - struct inet_request_sock req; - __u32 rcv_isn; - __u32 snt_isn; + struct inet_request_sock req; +#ifdef CONFIG_TCP_MD5SIG + /* Only used by TCP MD5 Signature so far. */ + struct tcp_request_sock_ops *af_specific; +#endif + __u32 rcv_isn; + __u32 snt_isn; }; static inline struct tcp_request_sock *tcp_rsk(const struct request_sock *req) @@ -363,6 +380,14 @@ struct tcp_sock { __u32 probe_seq_start; __u32 probe_seq_end; } mtu_probe; + +#ifdef CONFIG_TCP_MD5SIG +/* TCP AF-Specific parts; only used by MD5 Signature support so far */ + struct tcp_sock_af_ops *af_specific; + +/* TCP MD5 Signagure Option information */ + struct tcp_md5sig_info *md5sig_info; +#endif }; static inline struct tcp_sock *tcp_sk(const struct sock *sk) @@ -377,6 +402,10 @@ struct tcp_timewait_sock { __u32 tw_rcv_wnd; __u32 tw_ts_recent; long tw_ts_recent_stamp; +#ifdef CONFIG_TCP_MD5SIG + __u16 tw_md5_keylen; + __u8 tw_md5_key[TCP_MD5SIG_MAXKEYLEN]; +#endif }; static inline struct tcp_timewait_sock *tcp_twsk(const struct sock *sk) -- cgit v1.2.3 From 6051e2f4fb68fc8e5343db58fa680ece376f405c Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Tue, 14 Nov 2006 19:54:19 -0800 Subject: [IPv6] prefix: Convert RTM_NEWPREFIX notifications to use the new netlink api RTM_GETPREFIX is completely unused and is thus removed. Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/rtnetlink.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 3a18addaed4c..33b3d0ab3a91 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -81,8 +81,6 @@ enum { RTM_NEWPREFIX = 52, #define RTM_NEWPREFIX RTM_NEWPREFIX - RTM_GETPREFIX = 54, -#define RTM_GETPREFIX RTM_GETPREFIX RTM_GETMULTICAST = 58, #define RTM_GETMULTICAST RTM_GETMULTICAST -- cgit v1.2.3 From ba4e58eca8aa9473b44fdfd312f26c4a2e7798b3 Mon Sep 17 00:00:00 2001 From: Gerrit Renker Date: Mon, 27 Nov 2006 11:10:57 -0800 Subject: [NET]: Supporting UDP-Lite (RFC 3828) in Linux This is a revision of the previously submitted patch, which alters the way files are organized and compiled in the following manner: * UDP and UDP-Lite now use separate object files * source file dependencies resolved via header files net/ipv{4,6}/udp_impl.h * order of inclusion files in udp.c/udplite.c adapted accordingly [NET/IPv4]: Support for the UDP-Lite protocol (RFC 3828) This patch adds support for UDP-Lite to the IPv4 stack, provided as an extension to the existing UDPv4 code: * generic routines are all located in net/ipv4/udp.c * UDP-Lite specific routines are in net/ipv4/udplite.c * MIB/statistics support in /proc/net/snmp and /proc/net/udplite * shared API with extensions for partial checksum coverage [NET/IPv6]: Extension for UDP-Lite over IPv6 It extends the existing UDPv6 code base with support for UDP-Lite in the same manner as per UDPv4. In particular, * UDPv6 generic and shared code is in net/ipv6/udp.c * UDP-Litev6 specific extensions are in net/ipv6/udplite.c * MIB/statistics support in /proc/net/snmp6 and /proc/net/udplite6 * support for IPV6_ADDRFORM * aligned the coding style of protocol initialisation with af_inet6.c * made the error handling in udpv6_queue_rcv_skb consistent; to return `-1' on error on all error cases * consolidation of shared code [NET]: UDP-Lite Documentation and basic XFRM/Netfilter support The UDP-Lite patch further provides * API documentation for UDP-Lite * basic xfrm support * basic netfilter support for IPv4 and IPv6 (LOG target) Signed-off-by: Gerrit Renker Signed-off-by: David S. Miller --- include/linux/in.h | 1 + include/linux/socket.h | 1 + include/linux/udp.h | 12 ++++++++++++ 3 files changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/in.h b/include/linux/in.h index 2619859f6e1b..1912e7c0bc26 100644 --- a/include/linux/in.h +++ b/include/linux/in.h @@ -45,6 +45,7 @@ enum { IPPROTO_COMP = 108, /* Compression Header protocol */ IPPROTO_SCTP = 132, /* Stream Control Transport Protocol */ + IPPROTO_UDPLITE = 136, /* UDP-Lite (RFC 3828) */ IPPROTO_RAW = 255, /* Raw IP packets */ IPPROTO_MAX diff --git a/include/linux/socket.h b/include/linux/socket.h index 361409094649..592b66679823 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -264,6 +264,7 @@ struct ucred { #define SOL_IPV6 41 #define SOL_ICMPV6 58 #define SOL_SCTP 132 +#define SOL_UDPLITE 136 /* UDP-Lite (RFC 3828) */ #define SOL_RAW 255 #define SOL_IPX 256 #define SOL_AX25 257 diff --git a/include/linux/udp.h b/include/linux/udp.h index 014b41d1e308..564f3b050105 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -38,6 +38,7 @@ struct udphdr { #include #include +#define UDP_HTABLE_SIZE 128 struct udp_sock { /* inet_sock has to be the first member */ @@ -50,12 +51,23 @@ struct udp_sock { * when the socket is uncorked. */ __u16 len; /* total length of pending frames */ + /* + * Fields specific to UDP-Lite. + */ + __u16 pcslen; + __u16 pcrlen; +/* indicator bits used by pcflag: */ +#define UDPLITE_BIT 0x1 /* set by udplite proto init function */ +#define UDPLITE_SEND_CC 0x2 /* set via udplite setsockopt */ +#define UDPLITE_RECV_CC 0x4 /* set via udplite setsocktopt */ + __u8 pcflag; /* marks socket as UDP-Lite if > 0 */ }; static inline struct udp_sock *udp_sk(const struct sock *sk) { return (struct udp_sock *)sk; } +#define IS_UDPLITE(__sk) (udp_sk(__sk)->pcflag) #endif -- cgit v1.2.3 From 714e85be3557222bc25f69c252326207c900a7db Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 14 Nov 2006 20:51:49 -0800 Subject: [IPV6]: Assorted trivial endianness annotations. Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/inetdevice.h | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index 5a0ab04627bc..c0f7aec331c2 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -124,12 +124,13 @@ static __inline__ int inet_ifa_match(__be32 addr, struct in_ifaddr *ifa) * Check if a mask is acceptable. */ -static __inline__ int bad_mask(u32 mask, u32 addr) +static __inline__ int bad_mask(__be32 mask, __be32 addr) { + __u32 hmask; if (addr & (mask = ~mask)) return 1; - mask = ntohl(mask); - if (mask & (mask+1)) + hmask = ntohl(mask); + if (hmask & (hmask+1)) return 1; return 0; } @@ -190,11 +191,12 @@ static __inline__ __be32 inet_make_mask(int logmask) return 0; } -static __inline__ int inet_mask_len(__u32 mask) +static __inline__ int inet_mask_len(__be32 mask) { - if (!(mask = ntohl(mask))) + __u32 hmask = ntohl(mask); + if (!hmask) return 0; - return 32 - ffz(~mask); + return 32 - ffz(~hmask); } -- cgit v1.2.3 From b09b845ca6724c3bbdc00c0cb2313258c7189ca9 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 14 Nov 2006 20:52:19 -0800 Subject: [RANDOM]: Annotate random.h IP helpers. Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/random.h | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/random.h b/include/linux/random.h index 0248b30e306d..01ad71033d65 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -51,16 +51,16 @@ extern void add_interrupt_randomness(int irq); extern void get_random_bytes(void *buf, int nbytes); void generate_random_uuid(unsigned char uuid_out[16]); -extern __u32 secure_ip_id(__u32 daddr); -extern u32 secure_ipv4_port_ephemeral(__u32 saddr, __u32 daddr, __u16 dport); -extern u32 secure_ipv6_port_ephemeral(const __u32 *saddr, const __u32 *daddr, - __u16 dport); -extern __u32 secure_tcp_sequence_number(__u32 saddr, __u32 daddr, - __u16 sport, __u16 dport); -extern __u32 secure_tcpv6_sequence_number(__u32 *saddr, __u32 *daddr, - __u16 sport, __u16 dport); -extern u64 secure_dccp_sequence_number(__u32 saddr, __u32 daddr, - __u16 sport, __u16 dport); +extern __u32 secure_ip_id(__be32 daddr); +extern u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport); +extern u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, + __be16 dport); +extern __u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr, + __be16 sport, __be16 dport); +extern __u32 secure_tcpv6_sequence_number(__be32 *saddr, __be32 *daddr, + __be16 sport, __be16 dport); +extern u64 secure_dccp_sequence_number(__be32 saddr, __be32 daddr, + __be16 sport, __be16 dport); #ifndef MODULE extern struct file_operations random_fops, urandom_fops; -- cgit v1.2.3 From 42d224aa170a4f7446cea6c972d9302d524545e5 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 14 Nov 2006 21:11:08 -0800 Subject: [NETFILTER]: More trivial annotations. Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/netfilter_ipv4/ip_conntrack_tftp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv4/ip_conntrack_tftp.h b/include/linux/netfilter_ipv4/ip_conntrack_tftp.h index cde9729aa173..a404fc0abf0e 100644 --- a/include/linux/netfilter_ipv4/ip_conntrack_tftp.h +++ b/include/linux/netfilter_ipv4/ip_conntrack_tftp.h @@ -4,7 +4,7 @@ #define TFTP_PORT 69 struct tftphdr { - u_int16_t opcode; + __be16 opcode; }; #define TFTP_OPCODE_READ 1 -- cgit v1.2.3 From 30d492da738a8d5f4ec884b3e1a13eef97714994 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 14 Nov 2006 21:11:29 -0800 Subject: [ATM]: Annotations. Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/atmarp.h | 2 +- include/linux/atmbr2684.h | 4 ++-- include/linux/atmmpc.h | 16 ++++++++-------- 3 files changed, 11 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/atmarp.h b/include/linux/atmarp.h index 24f82338f59a..ee108f9e9cb7 100644 --- a/include/linux/atmarp.h +++ b/include/linux/atmarp.h @@ -37,7 +37,7 @@ enum atmarp_ctrl_type { struct atmarp_ctrl { enum atmarp_ctrl_type type; /* message type */ int itf_num;/* interface number (if present) */ - uint32_t ip; /* IP address (act_need only) */ + __be32 ip; /* IP address (act_need only) */ }; #endif diff --git a/include/linux/atmbr2684.h b/include/linux/atmbr2684.h index 7981b733f1ef..969fb6c9e1cc 100644 --- a/include/linux/atmbr2684.h +++ b/include/linux/atmbr2684.h @@ -86,8 +86,8 @@ struct atm_backend_br2684 { * efficient per-if in/out filters, this support will be removed */ struct br2684_filter { - __u32 prefix; /* network byte order */ - __u32 netmask; /* 0 = disable filter */ + __be32 prefix; /* network byte order */ + __be32 netmask; /* 0 = disable filter */ }; struct br2684_filter_set { diff --git a/include/linux/atmmpc.h b/include/linux/atmmpc.h index 5fbfa68136d3..ea1650425a12 100644 --- a/include/linux/atmmpc.h +++ b/include/linux/atmmpc.h @@ -13,7 +13,7 @@ struct atmmpc_ioc { int dev_num; - uint32_t ipaddr; /* the IP address of the shortcut */ + __be32 ipaddr; /* the IP address of the shortcut */ int type; /* ingress or egress */ }; @@ -21,8 +21,8 @@ typedef struct in_ctrl_info { uint8_t Last_NHRP_CIE_code; uint8_t Last_Q2931_cause_value; uint8_t eg_MPC_ATM_addr[ATM_ESA_LEN]; - uint32_t tag; - uint32_t in_dst_ip; /* IP address this ingress MPC sends packets to */ + __be32 tag; + __be32 in_dst_ip; /* IP address this ingress MPC sends packets to */ uint16_t holding_time; uint32_t request_id; } in_ctrl_info; @@ -30,10 +30,10 @@ typedef struct in_ctrl_info { typedef struct eg_ctrl_info { uint8_t DLL_header[256]; uint8_t DH_length; - uint32_t cache_id; - uint32_t tag; - uint32_t mps_ip; - uint32_t eg_dst_ip; /* IP address to which ingress MPC sends packets */ + __be32 cache_id; + __be32 tag; + __be32 mps_ip; + __be32 eg_dst_ip; /* IP address to which ingress MPC sends packets */ uint8_t in_MPC_data_ATM_addr[ATM_ESA_LEN]; uint16_t holding_time; } eg_ctrl_info; @@ -49,7 +49,7 @@ struct mpc_parameters { struct k_message { uint16_t type; - uint32_t ip_mask; + __be32 ip_mask; uint8_t MPS_ctrl[ATM_ESA_LEN]; union { in_ctrl_info in_info; -- cgit v1.2.3 From 47c183fa5ea7feebc356da8ccbd9105a41f8e534 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 14 Nov 2006 21:11:51 -0800 Subject: [BRIDGE]: Annotations. Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/netfilter_bridge.h | 2 +- include/linux/netfilter_bridge/ebt_802_3.h | 10 +++++----- include/linux/netfilter_bridge/ebt_among.h | 2 +- include/linux/netfilter_bridge/ebt_arp.h | 14 +++++++------- include/linux/netfilter_bridge/ebt_ip.h | 8 ++++---- include/linux/netfilter_bridge/ebt_vlan.h | 2 +- include/linux/netfilter_bridge/ebtables.h | 2 +- 7 files changed, 20 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_bridge.h b/include/linux/netfilter_bridge.h index 9a4dd11af86e..6c4613f8ad75 100644 --- a/include/linux/netfilter_bridge.h +++ b/include/linux/netfilter_bridge.h @@ -64,7 +64,7 @@ static inline int nf_bridge_pad(const struct sk_buff *skb) struct bridge_skb_cb { union { - __u32 ipv4; + __be32 ipv4; } daddr; }; diff --git a/include/linux/netfilter_bridge/ebt_802_3.h b/include/linux/netfilter_bridge/ebt_802_3.h index b9f712c14a0a..07f044ff1a6b 100644 --- a/include/linux/netfilter_bridge/ebt_802_3.h +++ b/include/linux/netfilter_bridge/ebt_802_3.h @@ -28,21 +28,21 @@ struct hdr_ui { uint8_t ssap; uint8_t ctrl; uint8_t orig[3]; - uint16_t type; + __be16 type; }; struct hdr_ni { uint8_t dsap; uint8_t ssap; - uint16_t ctrl; + __be16 ctrl; uint8_t orig[3]; - uint16_t type; + __be16 type; }; struct ebt_802_3_hdr { uint8_t daddr[6]; uint8_t saddr[6]; - uint16_t len; + __be16 len; union { struct hdr_ui ui; struct hdr_ni ni; @@ -61,7 +61,7 @@ static inline struct ebt_802_3_hdr *ebt_802_3_hdr(const struct sk_buff *skb) struct ebt_802_3_info { uint8_t sap; - uint16_t type; + __be16 type; uint8_t bitmask; uint8_t invflags; }; diff --git a/include/linux/netfilter_bridge/ebt_among.h b/include/linux/netfilter_bridge/ebt_among.h index 307c1fed8511..7654069233ca 100644 --- a/include/linux/netfilter_bridge/ebt_among.h +++ b/include/linux/netfilter_bridge/ebt_among.h @@ -32,7 +32,7 @@ struct ebt_mac_wormhash_tuple { uint32_t cmp[2]; - uint32_t ip; + __be32 ip; }; struct ebt_mac_wormhash diff --git a/include/linux/netfilter_bridge/ebt_arp.h b/include/linux/netfilter_bridge/ebt_arp.h index 537ec6b487a2..97e4dbde1f89 100644 --- a/include/linux/netfilter_bridge/ebt_arp.h +++ b/include/linux/netfilter_bridge/ebt_arp.h @@ -14,13 +14,13 @@ struct ebt_arp_info { - uint16_t htype; - uint16_t ptype; - uint16_t opcode; - uint32_t saddr; - uint32_t smsk; - uint32_t daddr; - uint32_t dmsk; + __be16 htype; + __be16 ptype; + __be16 opcode; + __be32 saddr; + __be32 smsk; + __be32 daddr; + __be32 dmsk; unsigned char smaddr[ETH_ALEN]; unsigned char smmsk[ETH_ALEN]; unsigned char dmaddr[ETH_ALEN]; diff --git a/include/linux/netfilter_bridge/ebt_ip.h b/include/linux/netfilter_bridge/ebt_ip.h index 7247385cdcb1..d6847475bf2e 100644 --- a/include/linux/netfilter_bridge/ebt_ip.h +++ b/include/linux/netfilter_bridge/ebt_ip.h @@ -28,10 +28,10 @@ /* the same values are used for the invflags */ struct ebt_ip_info { - uint32_t saddr; - uint32_t daddr; - uint32_t smsk; - uint32_t dmsk; + __be32 saddr; + __be32 daddr; + __be32 smsk; + __be32 dmsk; uint8_t tos; uint8_t protocol; uint8_t bitmask; diff --git a/include/linux/netfilter_bridge/ebt_vlan.h b/include/linux/netfilter_bridge/ebt_vlan.h index cb1fcc41565f..1d98be4031e7 100644 --- a/include/linux/netfilter_bridge/ebt_vlan.h +++ b/include/linux/netfilter_bridge/ebt_vlan.h @@ -10,7 +10,7 @@ struct ebt_vlan_info { uint16_t id; /* VLAN ID {1-4095} */ uint8_t prio; /* VLAN User Priority {0-7} */ - uint16_t encap; /* VLAN Encapsulated frame code {0-65535} */ + __be16 encap; /* VLAN Encapsulated frame code {0-65535} */ uint8_t bitmask; /* Args bitmask bit 1=1 - ID arg, bit 2=1 User-Priority arg, bit 3=1 encap*/ uint8_t invflags; /* Inverse bitmask bit 1=1 - inversed ID arg, diff --git a/include/linux/netfilter_bridge/ebtables.h b/include/linux/netfilter_bridge/ebtables.h index b1a7cc90877b..e6ea70de24d5 100644 --- a/include/linux/netfilter_bridge/ebtables.h +++ b/include/linux/netfilter_bridge/ebtables.h @@ -141,7 +141,7 @@ struct ebt_entry { /* this needs to be the first field */ unsigned int bitmask; unsigned int invflags; - uint16_t ethproto; + __be16 ethproto; /* the physical in-dev */ char in[IFNAMSIZ]; /* the logical in-dev */ -- cgit v1.2.3 From a64b78a077a71c9b9c0c1b0be699083379783c3d Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 14 Nov 2006 21:12:29 -0800 Subject: [NET]: Annotate net_srandom(). Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/net.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/net.h b/include/linux/net.h index 15c733b816f0..6f0dfeba509a 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -196,7 +196,7 @@ extern struct socket *sockfd_lookup(int fd, int *err); extern int net_ratelimit(void); #define net_random() random32() -#define net_srandom(seed) srandom32(seed) +#define net_srandom(seed) srandom32((__force u32)seed) extern int kernel_sendmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t len); -- cgit v1.2.3 From 2bc357987a6510e61d33f3b20fa989fb2b6a10b8 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 14 Nov 2006 21:14:18 -0800 Subject: [NET]: Introduce types for checksums. New types - for 16bit checksums and "unfolded" 32bit variant. Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/types.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/types.h b/include/linux/types.h index 9f11fdd2bd72..745c409ebbb5 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -182,6 +182,8 @@ typedef __u32 __bitwise __be32; typedef __u64 __bitwise __le64; typedef __u64 __bitwise __be64; #endif +typedef __u16 __bitwise __sum16; +typedef __u32 __bitwise __wsum; #ifdef __KERNEL__ typedef unsigned __bitwise__ gfp_t; -- cgit v1.2.3 From 9981a0e36a572e9fcf84bfab915fdc93bed0e3c9 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 14 Nov 2006 21:24:30 -0800 Subject: [NET]: Annotate checksums in on-the-wire packets. Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/dccp.h | 2 +- include/linux/icmp.h | 2 +- include/linux/icmpv6.h | 2 +- include/linux/igmp.h | 2 +- include/linux/ip.h | 2 +- include/linux/tcp.h | 2 +- include/linux/udp.h | 2 +- 7 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dccp.h b/include/linux/dccp.h index d308f1228b61..72cc355d7a03 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -30,7 +30,7 @@ struct dccp_hdr { #else #error "Adjust your defines" #endif - __u16 dccph_checksum; + __sum16 dccph_checksum; #if defined(__LITTLE_ENDIAN_BITFIELD) __u8 dccph_x:1, dccph_type:4, diff --git a/include/linux/icmp.h b/include/linux/icmp.h index 878cfe4e587f..24da4fbc1a2f 100644 --- a/include/linux/icmp.h +++ b/include/linux/icmp.h @@ -68,7 +68,7 @@ struct icmphdr { __u8 type; __u8 code; - __be16 checksum; + __sum16 checksum; union { struct { __be16 id; diff --git a/include/linux/icmpv6.h b/include/linux/icmpv6.h index dc79396aac25..68d3526c3a05 100644 --- a/include/linux/icmpv6.h +++ b/include/linux/icmpv6.h @@ -7,7 +7,7 @@ struct icmp6hdr { __u8 icmp6_type; __u8 icmp6_code; - __be16 icmp6_cksum; + __sum16 icmp6_cksum; union { diff --git a/include/linux/igmp.h b/include/linux/igmp.h index 21dd56905271..6e7ea2f0a57c 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -30,7 +30,7 @@ struct igmphdr { __u8 type; __u8 code; /* For newer IGMP */ - __be16 csum; + __sum16 csum; __be32 group; }; diff --git a/include/linux/ip.h b/include/linux/ip.h index ecee9bb27d0e..1d36b971a8b5 100644 --- a/include/linux/ip.h +++ b/include/linux/ip.h @@ -98,7 +98,7 @@ struct iphdr { __be16 frag_off; __u8 ttl; __u8 protocol; - __be16 check; + __sum16 check; __be32 saddr; __be32 daddr; /*The options start here. */ diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 0aecfc955591..dd61b172ac68 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -52,7 +52,7 @@ struct tcphdr { #error "Adjust your defines" #endif __be16 window; - __be16 check; + __sum16 check; __be16 urg_ptr; }; diff --git a/include/linux/udp.h b/include/linux/udp.h index 564f3b050105..7e08c07efe0f 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -23,7 +23,7 @@ struct udphdr { __be16 source; __be16 dest; __be16 len; - __be16 check; + __sum16 check; }; /* UDP socket options */ -- cgit v1.2.3 From 44bb93633f57a55979f3c2589b10fd6a2bfc7c08 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 14 Nov 2006 21:36:14 -0800 Subject: [NET]: Annotate csum_partial() callers in net/* Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/socket.h | 2 +- include/linux/sunrpc/xdr.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index 592b66679823..92cd38efad7f 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -293,7 +293,7 @@ extern int memcpy_fromiovecend(unsigned char *kdata, struct iovec *iov, extern int csum_partial_copy_fromiovecend(unsigned char *kdata, struct iovec *iov, int offset, - unsigned int len, int *csump); + unsigned int len, __wsum *csump); extern int verify_iovec(struct msghdr *m, struct iovec *iov, char *address, int mode); extern int memcpy_toiovec(struct iovec *v, unsigned char *kdata, int len); diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index ac69e5511606..9a527c364394 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -151,7 +151,7 @@ typedef struct { struct sk_buff *skb; unsigned int offset; size_t count; - unsigned int csum; + __wsum csum; } skb_reader_t; typedef size_t (*skb_read_actor_t)(skb_reader_t *desc, void *to, size_t len); -- cgit v1.2.3 From 5084205faf45384fff25c4cf77dd5c96279283ad Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 14 Nov 2006 21:36:34 -0800 Subject: [NET]: Annotate callers of csum_partial_copy_...() and csum_and_copy...() in net/* Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/skbuff.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index e3ae544b3956..64fa7f4c702d 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1199,8 +1199,7 @@ static inline int skb_add_data(struct sk_buff *skb, if (skb->ip_summed == CHECKSUM_NONE) { int err = 0; - unsigned int csum = csum_and_copy_from_user(from, - skb_put(skb, copy), + __wsum csum = csum_and_copy_from_user(from, skb_put(skb, copy), copy, 0, &err); if (!err) { skb->csum = csum_block_add(skb->csum, csum, off); -- cgit v1.2.3 From 2bbbc86890ac4c911c5057f69af93853e52a42a8 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 14 Nov 2006 21:37:14 -0800 Subject: [NET]: Annotate skb_checksum() and callers. Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/skbuff.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 64fa7f4c702d..784129fb61d4 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1334,8 +1334,8 @@ extern int skb_copy_and_csum_datagram_iovec(struct sk_buff *skb, extern void skb_free_datagram(struct sock *sk, struct sk_buff *skb); extern void skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags); -extern unsigned int skb_checksum(const struct sk_buff *skb, int offset, - int len, unsigned int csum); +extern __wsum skb_checksum(const struct sk_buff *skb, int offset, + int len, __wsum csum); extern int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len); extern int skb_store_bits(const struct sk_buff *skb, int offset, -- cgit v1.2.3 From 81d77662763ae527ba3a9b9275467901aaab7dfd Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 14 Nov 2006 21:37:33 -0800 Subject: [NET]: Annotate skb_copy_and_csum_bits() and callers. Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/skbuff.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 784129fb61d4..874ca029fbb9 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1340,9 +1340,9 @@ extern int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len); extern int skb_store_bits(const struct sk_buff *skb, int offset, void *from, int len); -extern unsigned int skb_copy_and_csum_bits(const struct sk_buff *skb, +extern __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, u8 *to, int len, - unsigned int csum); + __wsum csum); extern void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to); extern void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len); -- cgit v1.2.3 From b51655b958dfb1176bfcf99466231fdbef8751ff Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 14 Nov 2006 21:40:42 -0800 Subject: [NET]: Annotate __skb_checksum_complete() and friends. Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/netfilter.h | 6 +++--- include/linux/netfilter_ipv4.h | 2 +- include/linux/netfilter_ipv6.h | 2 +- include/linux/skbuff.h | 2 +- 4 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index b7e67d1d4382..707bb2e53c4e 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -290,7 +290,7 @@ extern u_int16_t nf_proto_csum_update(struct sk_buff *skb, struct nf_afinfo { unsigned short family; - unsigned int (*checksum)(struct sk_buff *skb, unsigned int hook, + __sum16 (*checksum)(struct sk_buff *skb, unsigned int hook, unsigned int dataoff, u_int8_t protocol); void (*saveroute)(const struct sk_buff *skb, struct nf_info *info); @@ -305,12 +305,12 @@ static inline struct nf_afinfo *nf_get_afinfo(unsigned short family) return rcu_dereference(nf_afinfo[family]); } -static inline unsigned int +static inline __sum16 nf_checksum(struct sk_buff *skb, unsigned int hook, unsigned int dataoff, u_int8_t protocol, unsigned short family) { struct nf_afinfo *afinfo; - unsigned int csum = 0; + __sum16 csum = 0; rcu_read_lock(); afinfo = nf_get_afinfo(family); diff --git a/include/linux/netfilter_ipv4.h b/include/linux/netfilter_ipv4.h index 5b63a231a76b..5821eb5a0a3e 100644 --- a/include/linux/netfilter_ipv4.h +++ b/include/linux/netfilter_ipv4.h @@ -79,7 +79,7 @@ enum nf_ip_hook_priorities { #ifdef __KERNEL__ extern int ip_route_me_harder(struct sk_buff **pskb, unsigned addr_type); extern int ip_xfrm_me_harder(struct sk_buff **pskb); -extern unsigned int nf_ip_checksum(struct sk_buff *skb, unsigned int hook, +extern __sum16 nf_ip_checksum(struct sk_buff *skb, unsigned int hook, unsigned int dataoff, u_int8_t protocol); #endif /*__KERNEL__*/ diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h index d97e268cdfe5..ab81a6dc94ea 100644 --- a/include/linux/netfilter_ipv6.h +++ b/include/linux/netfilter_ipv6.h @@ -74,7 +74,7 @@ enum nf_ip6_hook_priorities { #ifdef CONFIG_NETFILTER extern int ip6_route_me_harder(struct sk_buff *skb); -extern unsigned int nf_ip6_checksum(struct sk_buff *skb, unsigned int hook, +extern __sum16 nf_ip6_checksum(struct sk_buff *skb, unsigned int hook, unsigned int dataoff, u_int8_t protocol); extern int ipv6_netfilter_init(void); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 874ca029fbb9..41753667541d 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1398,7 +1398,7 @@ static inline void skb_set_timestamp(struct sk_buff *skb, const struct timeval * extern void __net_timestamp(struct sk_buff *skb); -extern unsigned int __skb_checksum_complete(struct sk_buff *skb); +extern __sum16 __skb_checksum_complete(struct sk_buff *skb); /** * skb_checksum_complete - Calculate checksum of an entire packet -- cgit v1.2.3 From 43bc0ca7eadc024e9e5b935fa5e0892df4fec9eb Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 14 Nov 2006 21:43:23 -0800 Subject: [NET]: netfilter checksum annotations Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/netfilter.h | 26 +++++++++++++++++----- .../linux/netfilter_ipv4/ip_conntrack_proto_gre.h | 4 ++-- 2 files changed, 23 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 707bb2e53c4e..6ab5e2d6133e 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -282,11 +282,27 @@ extern void nf_invalidate_cache(int pf); Returns true or false. */ extern int skb_make_writable(struct sk_buff **pskb, unsigned int writable_len); -extern u_int16_t nf_csum_update(u_int32_t oldval, u_int32_t newval, - u_int32_t csum); -extern u_int16_t nf_proto_csum_update(struct sk_buff *skb, - u_int32_t oldval, u_int32_t newval, - u_int16_t csum, int pseudohdr); +static inline void nf_csum_replace4(__sum16 *sum, __be32 from, __be32 to) +{ + __be32 diff[] = { ~from, to }; + + *sum = csum_fold(csum_partial((char *)diff, sizeof(diff), ~csum_unfold(*sum))); +} + +static inline void nf_csum_replace2(__sum16 *sum, __be16 from, __be16 to) +{ + nf_csum_replace4(sum, (__force __be32)from, (__force __be32)to); +} + +extern void nf_proto_csum_replace4(__sum16 *sum, struct sk_buff *skb, + __be32 from, __be32 to, int pseudohdr); + +static inline void nf_proto_csum_replace2(__sum16 *sum, struct sk_buff *skb, + __be16 from, __be16 to, int pseudohdr) +{ + nf_proto_csum_replace4(sum, skb, (__force __be32)from, + (__force __be32)to, pseudohdr); +} struct nf_afinfo { unsigned short family; diff --git a/include/linux/netfilter_ipv4/ip_conntrack_proto_gre.h b/include/linux/netfilter_ipv4/ip_conntrack_proto_gre.h index 1d853aa873eb..e371e0fc1672 100644 --- a/include/linux/netfilter_ipv4/ip_conntrack_proto_gre.h +++ b/include/linux/netfilter_ipv4/ip_conntrack_proto_gre.h @@ -102,11 +102,11 @@ static inline __be32 *gre_key(struct gre_hdr *greh) } /* get pointer ot gre csum, if present */ -static inline u_int16_t *gre_csum(struct gre_hdr *greh) +static inline __sum16 *gre_csum(struct gre_hdr *greh) { if (!greh->csum) return NULL; - return (u_int16_t *) (greh+sizeof(*greh)); + return (__sum16 *) (greh+sizeof(*greh)); } #endif /* __KERNEL__ */ -- cgit v1.2.3 From 1f61ab5ca5cca939a6509892d84b34849e155036 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 14 Nov 2006 21:44:08 -0800 Subject: [NET]: Preliminaty annotation of skb->csum. It's still not completely right; we need to split it into anon unions of __wsum and unsigned - for cases when we use it for partial checksum and for offset of checksum in skb Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/skbuff.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 41753667541d..fcab543d79ac 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -273,8 +273,8 @@ struct sk_buff { unsigned int len, data_len, - mac_len, - csum; + mac_len; + __wsum csum; __u32 priority; __u8 local_df:1, cloned:1, -- cgit v1.2.3 From bac0dff6cd194f7a28f7e840c9b6a7aa71c6ef97 Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Sun, 19 Nov 2006 14:15:05 -0800 Subject: [BNX2]: Add 5709 PCI ID. Add PCI ID and detection for 5709 copper and SerDes chips. 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 fd5033b8a927..c09da1e30c54 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1897,6 +1897,7 @@ #define PCI_VENDOR_ID_BROADCOM 0x14e4 #define PCI_DEVICE_ID_TIGON3_5752 0x1600 #define PCI_DEVICE_ID_TIGON3_5752M 0x1601 +#define PCI_DEVICE_ID_NX2_5709 0x1639 #define PCI_DEVICE_ID_TIGON3_5700 0x1644 #define PCI_DEVICE_ID_TIGON3_5701 0x1645 #define PCI_DEVICE_ID_TIGON3_5702 0x1646 -- cgit v1.2.3 From 82e3ab9dbeebd5c8d5402ad1607d22086271a56d Mon Sep 17 00:00:00 2001 From: Ian McDonald Date: Mon, 20 Nov 2006 19:19:32 -0200 Subject: [DCCP]: Adds the tx buffer sysctls This one got lost on the way from Ian to Gerrit to me, fix it. Signed-off-by: Ian McDonald Signed-off-by: Arnaldo Carvalho de Melo --- 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 2e8c5ad82793..61dd99c6c2a5 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -617,6 +617,7 @@ enum { NET_DCCP_DEFAULT_REQ_RETRIES = 7, NET_DCCP_DEFAULT_RETRIES1 = 8, NET_DCCP_DEFAULT_RETRIES2 = 9, + NET_DCCP_DEFAULT_TX_QLEN = 10, }; /* /proc/sys/net/ipx */ -- cgit v1.2.3 From f3ffaf14681e3cad61006873be8656ab41b793e0 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 20 Nov 2006 16:59:12 -0800 Subject: [SCTP]: Annotate SCTP headers. Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/sctp.h | 72 ++++++++++++++++++++++++++-------------------------- 1 file changed, 36 insertions(+), 36 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index 6ec66dec29f7..35108fe7a686 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -57,17 +57,17 @@ /* Section 3.1. SCTP Common Header Format */ typedef struct sctphdr { - __u16 source; - __u16 dest; - __u32 vtag; - __u32 checksum; + __be16 source; + __be16 dest; + __be32 vtag; + __be32 checksum; } __attribute__((packed)) sctp_sctphdr_t; /* Section 3.2. Chunk Field Descriptions. */ typedef struct sctp_chunkhdr { __u8 type; __u8 flags; - __u16 length; + __be16 length; } __attribute__((packed)) sctp_chunkhdr_t; @@ -153,8 +153,8 @@ enum { SCTP_CHUNK_FLAG_T = 0x01 }; */ typedef struct sctp_paramhdr { - __u16 type; - __u16 length; + __be16 type; + __be16 length; } __attribute__((packed)) sctp_paramhdr_t; typedef enum { @@ -203,10 +203,10 @@ enum { SCTP_PARAM_ACTION_MASK = __constant_htons(0xc000), }; /* RFC 2960 Section 3.3.1 Payload Data (DATA) (0) */ typedef struct sctp_datahdr { - __u32 tsn; - __u16 stream; - __u16 ssn; - __u32 ppid; + __be32 tsn; + __be16 stream; + __be16 ssn; + __be32 ppid; __u8 payload[0]; } __attribute__((packed)) sctp_datahdr_t; @@ -232,11 +232,11 @@ enum { SCTP_DATA_FRAG_MASK = 0x03, }; * endpoints. */ typedef struct sctp_inithdr { - __u32 init_tag; - __u32 a_rwnd; - __u16 num_outbound_streams; - __u16 num_inbound_streams; - __u32 initial_tsn; + __be32 init_tag; + __be32 a_rwnd; + __be16 num_outbound_streams; + __be16 num_inbound_streams; + __be32 initial_tsn; __u8 params[0]; } __attribute__((packed)) sctp_inithdr_t; @@ -261,7 +261,7 @@ typedef struct sctp_ipv6addr_param { /* Section 3.3.2.1 Cookie Preservative (9) */ typedef struct sctp_cookie_preserve_param { sctp_paramhdr_t param_hdr; - uint32_t lifespan_increment; + __be32 lifespan_increment; } __attribute__((packed)) sctp_cookie_preserve_param_t; /* Section 3.3.2.1 Host Name Address (11) */ @@ -273,7 +273,7 @@ typedef struct sctp_hostname_param { /* Section 3.3.2.1 Supported Address Types (12) */ typedef struct sctp_supported_addrs_param { sctp_paramhdr_t param_hdr; - uint16_t types[0]; + __be16 types[0]; } __attribute__((packed)) sctp_supported_addrs_param_t; /* Appendix A. ECN Capable (32768) */ @@ -284,7 +284,7 @@ typedef struct sctp_ecn_capable_param { /* ADDIP Section 3.2.6 Adaption Layer Indication */ typedef struct sctp_adaption_ind_param { struct sctp_paramhdr param_hdr; - __u32 adaption_ind; + __be32 adaption_ind; } __attribute__((packed)) sctp_adaption_ind_param_t; /* RFC 2960. Section 3.3.3 Initiation Acknowledgement (INIT ACK) (2): @@ -316,11 +316,11 @@ typedef struct sctp_unrecognized_param { */ typedef struct sctp_gap_ack_block { - __u16 start; - __u16 end; + __be16 start; + __be16 end; } __attribute__((packed)) sctp_gap_ack_block_t; -typedef uint32_t sctp_dup_tsn_t; +typedef __be32 sctp_dup_tsn_t; typedef union { sctp_gap_ack_block_t gab; @@ -328,10 +328,10 @@ typedef union { } sctp_sack_variable_t; typedef struct sctp_sackhdr { - __u32 cum_tsn_ack; - __u32 a_rwnd; - __u16 num_gap_ack_blocks; - __u16 num_dup_tsns; + __be32 cum_tsn_ack; + __be32 a_rwnd; + __be16 num_gap_ack_blocks; + __be16 num_dup_tsns; sctp_sack_variable_t variable[0]; } __attribute__((packed)) sctp_sackhdr_t; @@ -371,7 +371,7 @@ typedef struct sctp_abort_chunk { * and the highest consecutive acking value. */ typedef struct sctp_shutdownhdr { - __u32 cum_tsn_ack; + __be32 cum_tsn_ack; } __attribute__((packed)) sctp_shutdownhdr_t; struct sctp_shutdown_chunk_t { @@ -382,8 +382,8 @@ struct sctp_shutdown_chunk_t { /* RFC 2960. Section 3.3.10 Operation Error (ERROR) (9) */ typedef struct sctp_errhdr { - __u16 cause; - __u16 length; + __be16 cause; + __be16 length; __u8 variable[0]; } __attribute__((packed)) sctp_errhdr_t; @@ -462,7 +462,7 @@ typedef enum { * Explicit Congestion Notification Echo (ECNE) (12) */ typedef struct sctp_ecnehdr { - __u32 lowest_tsn; + __be32 lowest_tsn; } sctp_ecnehdr_t; typedef struct sctp_ecne_chunk { @@ -474,7 +474,7 @@ typedef struct sctp_ecne_chunk { * Congestion Window Reduced (CWR) (13) */ typedef struct sctp_cwrhdr { - __u32 lowest_tsn; + __be32 lowest_tsn; } sctp_cwrhdr_t; typedef struct sctp_cwr_chunk { @@ -529,12 +529,12 @@ typedef struct sctp_cwr_chunk { * chunks this field MUST be filled in. */ struct sctp_fwdtsn_skip { - __u16 stream; - __u16 ssn; + __be16 stream; + __be16 ssn; } __attribute__((packed)); struct sctp_fwdtsn_hdr { - __u32 new_cum_tsn; + __be32 new_cum_tsn; struct sctp_fwdtsn_skip skip[0]; } __attribute((packed)); @@ -578,11 +578,11 @@ struct sctp_fwdtsn_chunk { */ typedef struct sctp_addip_param { sctp_paramhdr_t param_hdr; - __u32 crr_id; + __be32 crr_id; } __attribute__((packed)) sctp_addip_param_t; typedef struct sctp_addiphdr { - __u32 serial; + __be32 serial; __u8 params[0]; } __attribute__((packed)) sctp_addiphdr_t; -- cgit v1.2.3 From 962c837275e8a8c1df41f1882e971636093cdee4 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 20 Nov 2006 17:26:08 -0800 Subject: [SCTP]: Netfilter sctp annotations. Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/netfilter/nf_conntrack_sctp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nf_conntrack_sctp.h b/include/linux/netfilter/nf_conntrack_sctp.h index b8994d9fd1a9..5cf2c115cce4 100644 --- a/include/linux/netfilter/nf_conntrack_sctp.h +++ b/include/linux/netfilter/nf_conntrack_sctp.h @@ -20,7 +20,7 @@ struct ip_ct_sctp { enum sctp_conntrack state; - u_int32_t vtag[IP_CT_DIR_MAX]; + __be32 vtag[IP_CT_DIR_MAX]; u_int32_t ttag[IP_CT_DIR_MAX]; }; -- cgit v1.2.3 From ff1dcadb1b55dbf471c5ed109dbbdf06bd19ef3b Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 20 Nov 2006 18:07:29 -0800 Subject: [NET]: Split skb->csum ... into anonymous union of __wsum and __u32 (csum and csum_offset resp.) Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/skbuff.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index fcab543d79ac..14ec16d2d9ba 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -274,7 +274,10 @@ struct sk_buff { unsigned int len, data_len, mac_len; - __wsum csum; + union { + __wsum csum; + __u32 csum_offset; + }; __u32 priority; __u8 local_df:1, cloned:1, -- cgit v1.2.3 From d61c167dd0797a16584f7a922dd5d50efad1d28a Mon Sep 17 00:00:00 2001 From: Gerrit Renker Date: Mon, 27 Nov 2006 12:31:45 -0200 Subject: [NET]: Add documentation for TFRC structures This adds documentation for the TFRC structure fields. Signed-off-by: Gerrit Renker Signed-off-by: Ian McDonald Signed-off-by: Arnaldo Carvalho de Melo --- include/linux/tfrc.h | 20 ++++++++++++++++++-- 1 file changed, 18 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tfrc.h b/include/linux/tfrc.h index 7dab7831c3cb..31a9b25276fe 100644 --- a/include/linux/tfrc.h +++ b/include/linux/tfrc.h @@ -1,7 +1,8 @@ #ifndef _LINUX_TFRC_H_ #define _LINUX_TFRC_H_ /* - * include/linux/tfrc.h + * TFRC - Data Structures for the TCP-Friendly Rate Control congestion + * control mechanism as specified in RFC 3448. * * Copyright (c) 2005 The University of Waikato, Hamilton, New Zealand. * Copyright (c) 2005 Ian McDonald @@ -13,15 +14,30 @@ * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. */ - #include +/** tfrc_rx_info - TFRC Receiver Data Structure + * + * @tfrcrx_x_recv: receiver estimate of sending rate (3.2.2) + * @tfrcrx_rtt: round-trip-time (communicated by sender) + * @tfrcrx_p: current estimate of loss event rate (3.2.2) + */ struct tfrc_rx_info { __u32 tfrcrx_x_recv; __u32 tfrcrx_rtt; __u32 tfrcrx_p; }; +/** tfrc_tx_info - TFRC Sender Data Structure + * + * @tfrctx_x: computed transmit rate (4.3 (4)) + * @tfrctx_x_recv: receiver estimate of send rate (4.3) + * @tfrctx_x_calc: return value of throughput equation (3.1) + * @tfrctx_rtt: (moving average) estimate of RTT (4.3) + * @tfrctx_p: current loss event rate (5.4) + * @tfrctx_rto: estimate of RTO, equals 4*RTT (4.3) + * @tfrctx_ipi: inter-packet interval (4.6) + */ struct tfrc_tx_info { __u32 tfrctx_x; __u32 tfrctx_x_recv; -- cgit v1.2.3 From 4e9b82693542003b028c8494e9e3c49615b91ce7 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Mon, 27 Nov 2006 09:25:58 -0800 Subject: [NETLINK]: Remove unused dst_pid field in netlink_skb_parms The destination PID is passed directly to netlink_unicast() respectively netlink_multicast(). Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/netlink.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index e61e1e138421..b3b9b609ee89 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -141,7 +141,6 @@ struct netlink_skb_parms { struct ucred creds; /* Skb credentials */ __u32 pid; - __u32 dst_pid; __u32 dst_group; kernel_cap_t eff_cap; __u32 loginuid; /* Login (audit) uid */ -- cgit v1.2.3 From e3703b3de1f049b38733ba520e5038f23063068e Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Mon, 27 Nov 2006 09:27:07 -0800 Subject: [RTNETLINK]: Add rtnl_put_cacheinfo() to unify some code IPv4, IPv6, and DECNet all use struct rta_cacheinfo in a similiar way, therefore rtnl_put_cacheinfo() is added to reuse code. Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/rtnetlink.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 33b3d0ab3a91..493297acdae8 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -585,6 +585,9 @@ extern int rtnl_notify(struct sk_buff *skb, u32 pid, u32 group, struct nlmsghdr *nlh, gfp_t flags); extern void rtnl_set_sk_err(u32 group, int error); extern int rtnetlink_put_metrics(struct sk_buff *skb, u32 *metrics); +extern int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, + u32 id, u32 ts, u32 tsage, long expires, + u32 error); extern void __rta_fill(struct sk_buff *skb, int attrtype, int attrlen, const void *data); -- cgit v1.2.3 From d5c42c0ec4f7fd5a4e19e33a2d561758b67c55c8 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 27 Nov 2006 17:58:02 -0200 Subject: [NET]: Pack struct hh_cache [acme@newtoy net-2.6.20]$ pahole net/ipv4/tcp.o hh_cache /* /pub/scm/linux/kernel/git/acme/net-2.6.20/include/linux/netdevice.h:190 */ struct hh_cache { struct hh_cache * hh_next; /* 0 4 */ atomic_t hh_refcnt; /* 4 4 */ __be16 hh_type; /* 8 2 */ /* XXX 2 bytes hole, try to pack */ int hh_len; /* 12 4 */ int (*hh_output)(); /* 16 4 */ rwlock_t hh_lock; /* 20 36 */ long unsigned int hh_data[24]; /* 56 96 */ }; /* size: 152, sum members: 150, holes: 1, sum holes: 2 */ [acme@newtoy net-2.6.20]$ find net -name "*.[ch]" | xargs grep 'hh_len.\+=' | sort -u net/atm/br2684.c: hh->hh_len = PADLEN + ETH_HLEN; net/ethernet/eth.c: hh->hh_len = ETH_HLEN; net/ipv4/ipconfig.c: int hh_len = LL_RESERVED_SPACE(dev); net/ipv4/ip_output.c: hh_len = LL_RESERVED_SPACE(rt->u.dst.dev); net/ipv4/ip_output.c: int hh_len = LL_RESERVED_SPACE(dev); net/ipv4/netfilter.c: hh_len = (*pskb)->dst->dev->hard_header_len; net/ipv4/raw.c: hh_len = LL_RESERVED_SPACE(rt->u.dst.dev); net/ipv6/ip6_output.c: hh_len = LL_RESERVED_SPACE(rt->u.dst.dev); net/ipv6/netfilter/ip6t_REJECT.c: hh_len = (dst->dev->hard_header_len + 15)&~15; net/ipv6/raw.c: hh_len = LL_RESERVED_SPACE(rt->u.dst.dev); [acme@newtoy net-2.6.20]$ [acme@newtoy net-2.6.20]$ find include -name "*.h" | xargs grep 'define ETH_HLEN' include/linux/if_ether.h:#define ETH_HLEN 14 /* Total octets in header. */ (((dev)->hard_header_len&~(HH_DATA_MOD - 1)) + HH_DATA_MOD) [acme@newtoy net-2.6.20]$ pahole net/ipv4/tcp.o net_device | grep hard_header_len short unsigned int hard_header_len; /* 106 2 */ [acme@newtoy net-2.6.20]$ So I think we're safe in turning hh_len an u16, end result: [acme@newtoy net-2.6.20]$ codiff -sV /tmp/tcp.o.before net/ipv4/tcp.o /pub/scm/linux/kernel/git/acme/net-2.6.20/net/ipv4/tcp.c: struct hh_cache | -4 hh_len; from: int /* 12(0) 4(0) */ to: u16 /* 10(0) 2(0) */ 1 struct changed [acme@newtoy net-2.6.20]$ Signed-off-by: Arnaldo Carvalho de Melo --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index caa3c2593719..949eada46ce1 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -196,7 +196,7 @@ struct hh_cache * NOTE: For VLANs, this will be the * encapuslated type. --BLG */ - int hh_len; /* length of header */ + u16 hh_len; /* length of header */ int (*hh_output)(struct sk_buff *skb); rwlock_t hh_lock; -- cgit v1.2.3 From 2ff52f282cf287d60e9eda1f3b5ec83e00a86130 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 28 Nov 2006 00:48:32 -0200 Subject: [TCP]: Change tcp_header_len member in tcp_sock to u16 With this we eliminate the last hole in struct tcp_sock. End result: [acme@newtoy net-2.6.20]$ codiff -sV /tmp/tcp.o.before net/ipv4/tcp.o /pub/scm/linux/kernel/git/acme/net-2.6.20/net/ipv4/tcp.c: struct tcp_sock | -4 tcp_header_len; from: int /* 1000(0) 4(0) */ to: u16 /* 1000(0) 2(0) */ 1 struct changed [acme@newtoy net-2.6.20]$ Now sizeof(tcp_sock) is just... [acme@newtoy net-2.6.20]$ pahole --sizes ../OUTPUT/qemu/net-2.6.20/net/ipv4/tcp.o | grep -w tcp_sock struct tcp_sock: 1500 0 1500 bytes ;-) Signed-off-by: Arnaldo Carvalho de Melo --- include/linux/tcp.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index dd61b172ac68..b42ff0efc2df 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -227,7 +227,8 @@ static inline struct tcp_request_sock *tcp_rsk(const struct request_sock *req) struct tcp_sock { /* inet_connection_sock has to be the first member of tcp_sock */ struct inet_connection_sock inet_conn; - int tcp_header_len; /* Bytes of tcp header to send */ + u16 tcp_header_len; /* Bytes of tcp header to send */ + u16 xmit_size_goal; /* Goal for segmenting output packets */ /* * Header prediction flags @@ -268,8 +269,6 @@ struct tcp_sock { __u32 snd_wnd; /* The window we expect to receive */ __u32 max_window; /* Maximal window ever seen from peer */ __u32 mss_cache; /* Cached effective mss, not including SACKS */ - __u16 xmit_size_goal; /* Goal for segmenting output packets */ - /* XXX Two bytes hole, try to pack */ __u32 window_clamp; /* Maximal window to advertise */ __u32 rcv_ssthresh; /* Current window clamp */ -- cgit v1.2.3 From 3a137d2065571864be0301b9ebd72ddb01060997 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 28 Nov 2006 01:12:38 -0200 Subject: [TCP]: Renove the __ prefix on the struct tcp_sock members As this struct is not userland visible at all. Signed-off-by: Arnaldo Carvalho de Melo --- include/linux/tcp.h | 156 ++++++++++++++++++++++++++-------------------------- 1 file changed, 78 insertions(+), 78 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index b42ff0efc2df..3cc70d1a3504 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -185,17 +185,17 @@ struct tcp_sack_block_wire { }; struct tcp_sack_block { - __u32 start_seq; - __u32 end_seq; + u32 start_seq; + u32 end_seq; }; struct tcp_options_received { /* PAWS/RTTM data */ long ts_recent_stamp;/* Time we stored ts_recent (for aging) */ - __u32 ts_recent; /* Time stamp to echo next */ - __u32 rcv_tsval; /* Time stamp value */ - __u32 rcv_tsecr; /* Time stamp echo reply */ - __u16 saw_tstamp : 1, /* Saw TIMESTAMP on last packet */ + u32 ts_recent; /* Time stamp to echo next */ + u32 rcv_tsval; /* Time stamp value */ + u32 rcv_tsecr; /* Time stamp echo reply */ + u16 saw_tstamp : 1, /* Saw TIMESTAMP on last packet */ tstamp_ok : 1, /* TIMESTAMP seen on SYN packet */ dsack : 1, /* D-SACK is scheduled */ wscale_ok : 1, /* Wscale seen on SYN packet */ @@ -203,10 +203,10 @@ struct tcp_options_received { snd_wscale : 4, /* Window scaling received from sender */ rcv_wscale : 4; /* Window scaling to send to receiver */ /* SACKs data */ - __u8 eff_sacks; /* Size of SACK array to send with next packet */ - __u8 num_sacks; /* Number of SACK blocks */ - __u16 user_mss; /* mss requested by user in ioctl */ - __u16 mss_clamp; /* Maximal mss, negotiated at connection setup */ + u8 eff_sacks; /* Size of SACK array to send with next packet */ + u8 num_sacks; /* Number of SACK blocks */ + u16 user_mss; /* mss requested by user in ioctl */ + u16 mss_clamp; /* Maximal mss, negotiated at connection setup */ }; struct tcp_request_sock { @@ -215,8 +215,8 @@ struct tcp_request_sock { /* Only used by TCP MD5 Signature so far. */ struct tcp_request_sock_ops *af_specific; #endif - __u32 rcv_isn; - __u32 snt_isn; + u32 rcv_isn; + u32 snt_isn; }; static inline struct tcp_request_sock *tcp_rsk(const struct request_sock *req) @@ -241,13 +241,13 @@ struct tcp_sock { * read the code and the spec side by side (and laugh ...) * See RFC793 and RFC1122. The RFC writes these in capitals. */ - __u32 rcv_nxt; /* What we want to receive next */ - __u32 snd_nxt; /* Next sequence we send */ + u32 rcv_nxt; /* What we want to receive next */ + u32 snd_nxt; /* Next sequence we send */ - __u32 snd_una; /* First byte we want an ack for */ - __u32 snd_sml; /* Last byte of the most recently transmitted small packet */ - __u32 rcv_tstamp; /* timestamp of last received ACK (for keepalives) */ - __u32 lsndtime; /* timestamp of last sent data packet (for restart window) */ + u32 snd_una; /* First byte we want an ack for */ + u32 snd_sml; /* Last byte of the most recently transmitted small packet */ + u32 rcv_tstamp; /* timestamp of last received ACK (for keepalives) */ + u32 lsndtime; /* timestamp of last sent data packet (for restart window) */ /* Data for direct copy to user */ struct { @@ -265,30 +265,30 @@ struct tcp_sock { #endif } ucopy; - __u32 snd_wl1; /* Sequence for window update */ - __u32 snd_wnd; /* The window we expect to receive */ - __u32 max_window; /* Maximal window ever seen from peer */ - __u32 mss_cache; /* Cached effective mss, not including SACKS */ + u32 snd_wl1; /* Sequence for window update */ + u32 snd_wnd; /* The window we expect to receive */ + u32 max_window; /* Maximal window ever seen from peer */ + u32 mss_cache; /* Cached effective mss, not including SACKS */ - __u32 window_clamp; /* Maximal window to advertise */ - __u32 rcv_ssthresh; /* Current window clamp */ + u32 window_clamp; /* Maximal window to advertise */ + u32 rcv_ssthresh; /* Current window clamp */ - __u32 frto_highmark; /* snd_nxt when RTO occurred */ - __u8 reordering; /* Packet reordering metric. */ - __u8 frto_counter; /* Number of new acks after RTO */ - __u8 nonagle; /* Disable Nagle algorithm? */ - __u8 keepalive_probes; /* num of allowed keep alive probes */ + u32 frto_highmark; /* snd_nxt when RTO occurred */ + u8 reordering; /* Packet reordering metric. */ + u8 frto_counter; /* Number of new acks after RTO */ + u8 nonagle; /* Disable Nagle algorithm? */ + u8 keepalive_probes; /* num of allowed keep alive probes */ /* RTT measurement */ - __u32 srtt; /* smoothed round trip time << 3 */ - __u32 mdev; /* medium deviation */ - __u32 mdev_max; /* maximal mdev for the last rtt period */ - __u32 rttvar; /* smoothed mdev_max */ - __u32 rtt_seq; /* sequence number to update rttvar */ - - __u32 packets_out; /* Packets which are "in flight" */ - __u32 left_out; /* Packets which leaved network */ - __u32 retrans_out; /* Retransmitted packets out */ + u32 srtt; /* smoothed round trip time << 3 */ + u32 mdev; /* medium deviation */ + u32 mdev_max; /* maximal mdev for the last rtt period */ + u32 rttvar; /* smoothed mdev_max */ + u32 rtt_seq; /* sequence number to update rttvar */ + + u32 packets_out; /* Packets which are "in flight" */ + u32 left_out; /* Packets which leaved network */ + u32 retrans_out; /* Retransmitted packets out */ /* * Options received (usually on last packet, some only on SYN packets). */ @@ -297,20 +297,20 @@ struct tcp_sock { /* * Slow start and congestion control (see also Nagle, and Karn & Partridge) */ - __u32 snd_ssthresh; /* Slow start size threshold */ - __u32 snd_cwnd; /* Sending congestion window */ - __u16 snd_cwnd_cnt; /* Linear increase counter */ - __u16 snd_cwnd_clamp; /* Do not allow snd_cwnd to grow above this */ - __u32 snd_cwnd_used; - __u32 snd_cwnd_stamp; + u32 snd_ssthresh; /* Slow start size threshold */ + u32 snd_cwnd; /* Sending congestion window */ + u16 snd_cwnd_cnt; /* Linear increase counter */ + u16 snd_cwnd_clamp; /* Do not allow snd_cwnd to grow above this */ + u32 snd_cwnd_used; + u32 snd_cwnd_stamp; struct sk_buff_head out_of_order_queue; /* Out of order segments go here */ - __u32 rcv_wnd; /* Current receiver window */ - __u32 rcv_wup; /* rcv_nxt on last window update sent */ - __u32 write_seq; /* Tail(+1) of data held in tcp send buffer */ - __u32 pushed_seq; /* Last pushed seq, required to talk to windows */ - __u32 copied_seq; /* Head of yet unread data */ + u32 rcv_wnd; /* Current receiver window */ + u32 rcv_wup; /* rcv_nxt on last window update sent */ + u32 write_seq; /* Tail(+1) of data held in tcp send buffer */ + u32 pushed_seq; /* Last pushed seq, required to talk to windows */ + u32 copied_seq; /* Head of yet unread data */ /* SACKs data */ struct tcp_sack_block duplicate_sack[1]; /* D-SACK block */ @@ -331,26 +331,26 @@ struct tcp_sock { int retransmit_cnt_hint; int forward_cnt_hint; - __u16 advmss; /* Advertised MSS */ - __u16 prior_ssthresh; /* ssthresh saved at recovery start */ - __u32 lost_out; /* Lost packets */ - __u32 sacked_out; /* SACK'd packets */ - __u32 fackets_out; /* FACK'd packets */ - __u32 high_seq; /* snd_nxt at onset of congestion */ + u16 advmss; /* Advertised MSS */ + u16 prior_ssthresh; /* ssthresh saved at recovery start */ + u32 lost_out; /* Lost packets */ + u32 sacked_out; /* SACK'd packets */ + u32 fackets_out; /* FACK'd packets */ + u32 high_seq; /* snd_nxt at onset of congestion */ - __u32 retrans_stamp; /* Timestamp of the last retransmit, + u32 retrans_stamp; /* Timestamp of the last retransmit, * also used in SYN-SENT to remember stamp of * the first SYN. */ - __u32 undo_marker; /* tracking retrans started here. */ + u32 undo_marker; /* tracking retrans started here. */ int undo_retrans; /* number of undoable retransmissions. */ - __u32 urg_seq; /* Seq of received urgent pointer */ - __u16 urg_data; /* Saved octet of OOB data and control flags */ - __u8 urg_mode; /* In urgent mode */ - __u8 ecn_flags; /* ECN status bits. */ - __u32 snd_up; /* Urgent pointer */ + u32 urg_seq; /* Seq of received urgent pointer */ + u16 urg_data; /* Saved octet of OOB data and control flags */ + u8 urg_mode; /* In urgent mode */ + u8 ecn_flags; /* ECN status bits. */ + u32 snd_up; /* Urgent pointer */ - __u32 total_retrans; /* Total retransmits for entire connection */ - __u32 bytes_acked; /* Appropriate Byte Counting - RFC3465 */ + u32 total_retrans; /* Total retransmits for entire connection */ + u32 bytes_acked; /* Appropriate Byte Counting - RFC3465 */ unsigned int keepalive_time; /* time before keep alive takes place */ unsigned int keepalive_intvl; /* time interval between keep alive probes */ @@ -358,26 +358,26 @@ struct tcp_sock { unsigned long last_synq_overflow; - __u32 tso_deferred; + u32 tso_deferred; /* Receiver side RTT estimation */ struct { - __u32 rtt; - __u32 seq; - __u32 time; + u32 rtt; + u32 seq; + u32 time; } rcv_rtt_est; /* Receiver queue space */ struct { int space; - __u32 seq; - __u32 time; + u32 seq; + u32 time; } rcvq_space; /* TCP-specific MTU probe information. */ struct { - __u32 probe_seq_start; - __u32 probe_seq_end; + u32 probe_seq_start; + u32 probe_seq_end; } mtu_probe; #ifdef CONFIG_TCP_MD5SIG @@ -396,14 +396,14 @@ static inline struct tcp_sock *tcp_sk(const struct sock *sk) struct tcp_timewait_sock { struct inet_timewait_sock tw_sk; - __u32 tw_rcv_nxt; - __u32 tw_snd_nxt; - __u32 tw_rcv_wnd; - __u32 tw_ts_recent; + u32 tw_rcv_nxt; + u32 tw_snd_nxt; + u32 tw_rcv_wnd; + u32 tw_ts_recent; long tw_ts_recent_stamp; #ifdef CONFIG_TCP_MD5SIG - __u16 tw_md5_keylen; - __u8 tw_md5_key[TCP_MD5SIG_MAXKEYLEN]; + u16 tw_md5_keylen; + u8 tw_md5_key[TCP_MD5SIG_MAXKEYLEN]; #endif }; -- cgit v1.2.3 From 4384260443efe90a2ec0d907568dbc58ae792cd0 Mon Sep 17 00:00:00 2001 From: Gerrit Renker Date: Tue, 28 Nov 2006 18:14:10 -0200 Subject: [DCCP]: Remove allocation of sysctl numbers This is in response to a request sent earlier by Eric W. Biederman and replaces all sysctl numbers for net.dccp.default with CTL_UNNUMBERED. It has been tested to compile and to work. Commiter note: I've removed the use of CTL_UNNUMBERED, not setting .ctl_name sets it to 0, that is the what CTL_UNNUMBERED is, reason is to avoid unneeded source code cluttering. Signed-off-by: Gerrit Renker Signed-off-by: Ian McDonald Signed-off-by: Arnaldo Carvalho de Melo --- include/linux/sysctl.h | 14 -------------- 1 file changed, 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 61dd99c6c2a5..94316a98e0d0 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -606,20 +606,6 @@ 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, - NET_DCCP_DEFAULT_REQ_RETRIES = 7, - NET_DCCP_DEFAULT_RETRIES1 = 8, - NET_DCCP_DEFAULT_RETRIES2 = 9, - NET_DCCP_DEFAULT_TX_QLEN = 10, -}; - /* /proc/sys/net/ipx */ enum { NET_IPX_PPROP_BROADCASTING=1, -- cgit v1.2.3 From 5aed324369c94a2c38469c8288e42eb1a9fac400 Mon Sep 17 00:00:00 2001 From: Gerrit Renker Date: Tue, 28 Nov 2006 19:33:36 -0200 Subject: [DCCP]: Tidy up unused structures This removes and cleans up unused variables and structures which have become unnecessary following the introduction of the EWMA patch to automatically track the CCID 3 receiver/sender packet sizes `s'. It deprecates the PACKET_SIZE socket option by returning an error code and printing a deprecation warning if an application tries to read or write this socket option. Signed-off-by: Gerrit Renker Signed-off-by: Arnaldo Carvalho de Melo --- include/linux/dccp.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dccp.h b/include/linux/dccp.h index 72cc355d7a03..ed6cc8962d87 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -200,7 +200,7 @@ struct dccp_so_feat { }; /* DCCP socket options */ -#define DCCP_SOCKOPT_PACKET_SIZE 1 +#define DCCP_SOCKOPT_PACKET_SIZE 1 /* XXX deprecated, without effect */ #define DCCP_SOCKOPT_SERVICE 2 #define DCCP_SOCKOPT_CHANGE_L 3 #define DCCP_SOCKOPT_CHANGE_R 4 @@ -460,7 +460,6 @@ struct dccp_ackvec; * @dccps_service_list - second .. last service code on passive socket * @dccps_timestamp_time - time of latest TIMESTAMP option * @dccps_timestamp_echo - latest timestamp received on a TIMESTAMP option - * @dccps_packet_size - Set thru setsockopt * @dccps_l_ack_ratio - * @dccps_r_ack_ratio - * @dccps_pcslen - sender partial checksum coverage (via sockopt) @@ -495,7 +494,6 @@ struct dccp_sock { struct dccp_service_list *dccps_service_list; struct timeval dccps_timestamp_time; __u32 dccps_timestamp_echo; - __u32 dccps_packet_size; __u16 dccps_l_ack_ratio; __u16 dccps_r_ack_ratio; __u16 dccps_pcslen; -- cgit v1.2.3 From d62f9ed4a490309bd9e5df0b42ba5d096e7b5902 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 29 Nov 2006 02:35:17 +0100 Subject: [NETFILTER]: nf_conntrack: automatic sysctl registation for conntrack protocols Add helper functions for sysctl registration with optional instantiating of common path elements (like net/netfilter) and use it for support for automatic registation of conntrack protocol sysctls. Signed-off-by: Patrick McHardy --- include/linux/netfilter.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 6ab5e2d6133e..f6f3fcbd70ed 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -117,6 +117,16 @@ void nf_unregister_hooks(struct nf_hook_ops *reg, unsigned int n); int nf_register_sockopt(struct nf_sockopt_ops *reg); void nf_unregister_sockopt(struct nf_sockopt_ops *reg); +#ifdef CONFIG_SYSCTL +/* Sysctl registration */ +struct ctl_table_header *nf_register_sysctl_table(struct ctl_table *path, + struct ctl_table *table); +void nf_unregister_sysctl_table(struct ctl_table_header *header, + struct ctl_table *table); +extern struct ctl_table nf_net_netfilter_sysctl_path[]; +extern struct ctl_table nf_net_ipv4_netfilter_sysctl_path[]; +#endif /* CONFIG_SYSCTL */ + extern struct list_head nf_hooks[NPROTO][NF_MAX_HOOKS]; /* those NF_LOG_* defines and struct nf_loginfo are legacy definitios that will -- cgit v1.2.3 From 468ec44bd5a863736d955f78b8c38896f26864a1 Mon Sep 17 00:00:00 2001 From: Yasuyuki Kozakai Date: Wed, 29 Nov 2006 02:35:23 +0100 Subject: [NETFILTER]: conntrack: add '_get' to {ip, nf}_conntrack_expect_find We usually uses 'xxx_find_get' for function which increments reference count. Signed-off-by: Yasuyuki Kozakai Signed-off-by: Patrick McHardy --- include/linux/netfilter_ipv4/ip_conntrack.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv4/ip_conntrack.h b/include/linux/netfilter_ipv4/ip_conntrack.h index 64e868034c4a..61da56941dce 100644 --- a/include/linux/netfilter_ipv4/ip_conntrack.h +++ b/include/linux/netfilter_ipv4/ip_conntrack.h @@ -277,7 +277,7 @@ extern struct ip_conntrack_expect * __ip_conntrack_expect_find(const struct ip_conntrack_tuple *tuple); extern struct ip_conntrack_expect * -ip_conntrack_expect_find(const struct ip_conntrack_tuple *tuple); +ip_conntrack_expect_find_get(const struct ip_conntrack_tuple *tuple); extern struct ip_conntrack_tuple_hash * __ip_conntrack_find(const struct ip_conntrack_tuple *tuple, -- cgit v1.2.3 From 9d5b8baa4e9ace9be113c6151aaeeb3c07a26fc8 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 29 Nov 2006 02:35:26 +0100 Subject: [NETFILTER]: sip conntrack: minor cleanup - Use enum for header field enumeration - Use numerical value instead of pointer to header info structure to identify headers, unexport ct_sip_hdrs - group SIP and SDP entries in header info structure - remove double forward declaration of ct_sip_get_info Signed-off-by: Patrick McHardy --- include/linux/netfilter_ipv4/ip_conntrack_sip.h | 28 +++++++++---------------- 1 file changed, 10 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv4/ip_conntrack_sip.h b/include/linux/netfilter_ipv4/ip_conntrack_sip.h index 913dad66c0fb..2a15eb51fd6b 100644 --- a/include/linux/netfilter_ipv4/ip_conntrack_sip.h +++ b/include/linux/netfilter_ipv4/ip_conntrack_sip.h @@ -5,23 +5,15 @@ #define SIP_PORT 5060 #define SIP_TIMEOUT 3600 -#define POS_VIA 0 -#define POS_CONTACT 1 -#define POS_CONTENT 2 -#define POS_MEDIA 3 -#define POS_OWNER 4 -#define POS_CONNECTION 5 -#define POS_REQ_HEADER 6 -#define POS_SDP_HEADER 7 - -struct sip_header_nfo { - const char *lname; - const char *sname; - const char *ln_str; - size_t lnlen; - size_t snlen; - size_t ln_strlen; - int (*match_len)(const char *, const char *, int *); +enum sip_header_pos { + POS_REQ_HEADER, + POS_VIA, + POS_CONTACT, + POS_CONTENT, + POS_MEDIA, + POS_OWNER, + POS_CONNECTION, + POS_SDP_HEADER, }; extern unsigned int (*ip_nat_sip_hook)(struct sk_buff **pskb, @@ -36,7 +28,7 @@ extern unsigned int (*ip_nat_sdp_hook)(struct sk_buff **pskb, extern int ct_sip_get_info(const char *dptr, size_t dlen, unsigned int *matchoff, unsigned int *matchlen, - struct sip_header_nfo *hnfo); + enum sip_header_pos pos); extern int ct_sip_lnlen(const char *line, const char *limit); extern const char *ct_sip_search(const char *needle, const char *haystack, size_t needle_len, size_t haystack_len); -- cgit v1.2.3 From 40883e8184947879f135605a05c0764c60656cc5 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 29 Nov 2006 02:35:27 +0100 Subject: [NETFILTER]: sip conntrack: do case insensitive SIP header search SIP headers are generally case-insensitive, only SDP headers are case sensitive. Signed-off-by: Patrick McHardy --- include/linux/netfilter_ipv4/ip_conntrack_sip.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv4/ip_conntrack_sip.h b/include/linux/netfilter_ipv4/ip_conntrack_sip.h index 2a15eb51fd6b..51c65ac18c57 100644 --- a/include/linux/netfilter_ipv4/ip_conntrack_sip.h +++ b/include/linux/netfilter_ipv4/ip_conntrack_sip.h @@ -31,6 +31,7 @@ extern int ct_sip_get_info(const char *dptr, size_t dlen, enum sip_header_pos pos); extern int ct_sip_lnlen(const char *line, const char *limit); extern const char *ct_sip_search(const char *needle, const char *haystack, - size_t needle_len, size_t haystack_len); + size_t needle_len, size_t haystack_len, + int case_sensitive); #endif /* __KERNEL__ */ #endif /* __IP_CONNTRACK_SIP_H__ */ -- cgit v1.2.3 From 1b683b551209ca46ae59b29572018001db5af078 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 29 Nov 2006 02:35:30 +0100 Subject: [NETFILTER]: sip conntrack: better NAT handling The NAT handling of the SIP helper has a few problems: - Request headers are only mangled in the reply direction, From/To headers not at all, which can lead to authentication failures with DNAT in case the authentication domain is the IP address - Contact headers in responses are only mangled for REGISTER responses - Headers may be mangled even though they contain addresses not participating in the connection, like alternative addresses - Packets are droppen when domain names are used where the helper expects IP addresses This patch takes a different approach, instead of fixed rules what field to mangle to what content, it adds symetric mapping of From/To/Via/Contact headers, which allows to deal properly with echoed addresses in responses and foreign addresses not belonging to the connection. Signed-off-by: Patrick McHardy --- include/linux/netfilter_ipv4/ip_conntrack_sip.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv4/ip_conntrack_sip.h b/include/linux/netfilter_ipv4/ip_conntrack_sip.h index 51c65ac18c57..bef6c646defa 100644 --- a/include/linux/netfilter_ipv4/ip_conntrack_sip.h +++ b/include/linux/netfilter_ipv4/ip_conntrack_sip.h @@ -6,7 +6,10 @@ #define SIP_TIMEOUT 3600 enum sip_header_pos { - POS_REQ_HEADER, + POS_REG_REQ_URI, + POS_REQ_URI, + POS_FROM, + POS_TO, POS_VIA, POS_CONTACT, POS_CONTENT, -- cgit v1.2.3 From 829e17a1a602572ffa3beefe582dc103ee9fb9c7 Mon Sep 17 00:00:00 2001 From: Eric Leblond Date: Wed, 29 Nov 2006 02:35:33 +0100 Subject: [NETFILTER]: nfnetlink_queue: allow changing queue length through netlink Signed-off-by: Eric Leblond Signed-off-by: Patrick McHardy --- include/linux/netfilter/nfnetlink_queue.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink_queue.h b/include/linux/netfilter/nfnetlink_queue.h index 4beea3d6fda8..83e789633e35 100644 --- a/include/linux/netfilter/nfnetlink_queue.h +++ b/include/linux/netfilter/nfnetlink_queue.h @@ -82,6 +82,7 @@ enum nfqnl_attr_config { NFQA_CFG_UNSPEC, NFQA_CFG_CMD, /* nfqnl_msg_config_cmd */ NFQA_CFG_PARAMS, /* nfqnl_msg_config_params */ + NFQA_CFG_QUEUE_MAXLEN, /* u_int32_t */ __NFQA_CFG_MAX }; #define NFQA_CFG_MAX (__NFQA_CFG_MAX-1) -- cgit v1.2.3 From d7a5c32442ed3d528b9ddfd3d5b837bad0ffa9da Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 29 Nov 2006 02:35:34 +0100 Subject: [NETFILTER]: nfnetlink_log: remove useless prefix length limitation There is no reason for limiting netlink attributes in size. Signed-off-by: Patrick McHardy --- include/linux/netfilter/nfnetlink_log.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink_log.h b/include/linux/netfilter/nfnetlink_log.h index 55a2a2b814ed..5966afa026e9 100644 --- a/include/linux/netfilter/nfnetlink_log.h +++ b/include/linux/netfilter/nfnetlink_log.h @@ -32,8 +32,6 @@ struct nfulnl_msg_packet_timestamp { aligned_be64 usec; }; -#define NFULNL_PREFIXLEN 30 /* just like old log target */ - enum nfulnl_attr_type { NFULA_UNSPEC, NFULA_PACKET_HDR, -- cgit v1.2.3 From 39b46fc6f0d1161a5585cd8af7b3a05e8118ab7e Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 29 Nov 2006 02:35:36 +0100 Subject: [NETFILTER]: x_tables: add port of hashlimit match for IPv4 and IPv6 Signed-off-by: Patrick McHardy --- include/linux/netfilter/Kbuild | 1 + include/linux/netfilter/xt_hashlimit.h | 40 ++++++++++++++++++++++++++ include/linux/netfilter_ipv4/ipt_hashlimit.h | 42 ++++++---------------------- 3 files changed, 49 insertions(+), 34 deletions(-) create mode 100644 include/linux/netfilter/xt_hashlimit.h (limited to 'include/linux') diff --git a/include/linux/netfilter/Kbuild b/include/linux/netfilter/Kbuild index 312bd2ffee33..e379a2d89ea0 100644 --- a/include/linux/netfilter/Kbuild +++ b/include/linux/netfilter/Kbuild @@ -14,6 +14,7 @@ header-y += xt_dscp.h header-y += xt_DSCP.h header-y += xt_esp.h header-y += xt_helper.h +header-y += xt_hashlimit.h header-y += xt_length.h header-y += xt_limit.h header-y += xt_mac.h diff --git a/include/linux/netfilter/xt_hashlimit.h b/include/linux/netfilter/xt_hashlimit.h new file mode 100644 index 000000000000..b4556b8edbfd --- /dev/null +++ b/include/linux/netfilter/xt_hashlimit.h @@ -0,0 +1,40 @@ +#ifndef _XT_HASHLIMIT_H +#define _XT_HASHLIMIT_H + +/* timings are in milliseconds. */ +#define XT_HASHLIMIT_SCALE 10000 +/* 1/10,000 sec period => max of 10,000/sec. Min rate is then 429490 + seconds, or one every 59 hours. */ + +/* details of this structure hidden by the implementation */ +struct xt_hashlimit_htable; + +#define XT_HASHLIMIT_HASH_DIP 0x0001 +#define XT_HASHLIMIT_HASH_DPT 0x0002 +#define XT_HASHLIMIT_HASH_SIP 0x0004 +#define XT_HASHLIMIT_HASH_SPT 0x0008 + +struct hashlimit_cfg { + u_int32_t mode; /* bitmask of IPT_HASHLIMIT_HASH_* */ + u_int32_t avg; /* Average secs between packets * scale */ + u_int32_t burst; /* Period multiplier for upper limit. */ + + /* user specified */ + u_int32_t size; /* how many buckets */ + u_int32_t max; /* max number of entries */ + u_int32_t gc_interval; /* gc interval */ + u_int32_t expire; /* when do entries expire? */ +}; + +struct xt_hashlimit_info { + char name [IFNAMSIZ]; /* name */ + struct hashlimit_cfg cfg; + struct xt_hashlimit_htable *hinfo; + + /* Used internally by the kernel */ + union { + void *ptr; + struct xt_hashlimit_info *master; + } u; +}; +#endif /*_XT_HASHLIMIT_H*/ diff --git a/include/linux/netfilter_ipv4/ipt_hashlimit.h b/include/linux/netfilter_ipv4/ipt_hashlimit.h index ac2cb64ecd76..5662120a3d7b 100644 --- a/include/linux/netfilter_ipv4/ipt_hashlimit.h +++ b/include/linux/netfilter_ipv4/ipt_hashlimit.h @@ -1,40 +1,14 @@ #ifndef _IPT_HASHLIMIT_H #define _IPT_HASHLIMIT_H -/* timings are in milliseconds. */ -#define IPT_HASHLIMIT_SCALE 10000 -/* 1/10,000 sec period => max of 10,000/sec. Min rate is then 429490 - seconds, or one every 59 hours. */ +#include -/* details of this structure hidden by the implementation */ -struct ipt_hashlimit_htable; +#define IPT_HASHLIMIT_SCALE XT_HASHLIMIT_SCALE +#define IPT_HASHLIMIT_HASH_DIP XT_HASHLIMIT_HASH_DIP +#define IPT_HASHLIMIT_HASH_DPT XT_HASHLIMIT_HASH_DPT +#define IPT_HASHLIMIT_HASH_SIP XT_HASHLIMIT_HASH_SIP +#define IPT_HASHLIMIT_HASH_SPT XT_HASHLIMIT_HASH_SPT -#define IPT_HASHLIMIT_HASH_DIP 0x0001 -#define IPT_HASHLIMIT_HASH_DPT 0x0002 -#define IPT_HASHLIMIT_HASH_SIP 0x0004 -#define IPT_HASHLIMIT_HASH_SPT 0x0008 +#define ipt_hashlimit_info xt_hashlimit_info -struct hashlimit_cfg { - u_int32_t mode; /* bitmask of IPT_HASHLIMIT_HASH_* */ - u_int32_t avg; /* Average secs between packets * scale */ - u_int32_t burst; /* Period multiplier for upper limit. */ - - /* user specified */ - u_int32_t size; /* how many buckets */ - u_int32_t max; /* max number of entries */ - u_int32_t gc_interval; /* gc interval */ - u_int32_t expire; /* when do entries expire? */ -}; - -struct ipt_hashlimit_info { - char name [IFNAMSIZ]; /* name */ - struct hashlimit_cfg cfg; - struct ipt_hashlimit_htable *hinfo; - - /* Used internally by the kernel */ - union { - void *ptr; - struct ipt_hashlimit_info *master; - } u; -}; -#endif /*_IPT_HASHLIMIT_H*/ +#endif /* _IPT_HASHLIMIT_H */ -- cgit v1.2.3 From baf7b1e11282127e068d149825cccec002091d61 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 29 Nov 2006 02:35:38 +0100 Subject: [NETFILTER]: x_tables: add NFLOG target Add new NFLOG target to allow use of nfnetlink_log for both IPv4 and IPv6. Currently we have two (unsupported by userspace) hacks in the LOG and ULOG targets to optionally call to the nflog API. They lack a few features, namely the IPv4 and IPv6 LOG targets can not specify a number of arguments related to nfnetlink_log, while the ULOG target is only available for IPv4. Remove those hacks and add a clean way to use nfnetlink_log. Signed-off-by: Patrick McHardy --- include/linux/netfilter/Kbuild | 1 + include/linux/netfilter/xt_NFLOG.h | 18 ++++++++++++++++++ include/linux/netfilter_ipv4/ipt_LOG.h | 2 +- include/linux/netfilter_ipv6/ip6t_LOG.h | 2 +- 4 files changed, 21 insertions(+), 2 deletions(-) create mode 100644 include/linux/netfilter/xt_NFLOG.h (limited to 'include/linux') diff --git a/include/linux/netfilter/Kbuild b/include/linux/netfilter/Kbuild index e379a2d89ea0..6328175a1c3a 100644 --- a/include/linux/netfilter/Kbuild +++ b/include/linux/netfilter/Kbuild @@ -22,6 +22,7 @@ header-y += xt_mark.h header-y += xt_MARK.h header-y += xt_multiport.h header-y += xt_NFQUEUE.h +header-y += xt_NFLOG.h header-y += xt_pkttype.h header-y += xt_policy.h header-y += xt_realm.h diff --git a/include/linux/netfilter/xt_NFLOG.h b/include/linux/netfilter/xt_NFLOG.h new file mode 100644 index 000000000000..cdcd0ed58f7a --- /dev/null +++ b/include/linux/netfilter/xt_NFLOG.h @@ -0,0 +1,18 @@ +#ifndef _XT_NFLOG_TARGET +#define _XT_NFLOG_TARGET + +#define XT_NFLOG_DEFAULT_GROUP 0x1 +#define XT_NFLOG_DEFAULT_THRESHOLD 1 + +#define XT_NFLOG_MASK 0x0 + +struct xt_nflog_info { + u_int32_t len; + u_int16_t group; + u_int16_t threshold; + u_int16_t flags; + u_int16_t pad; + char prefix[64]; +}; + +#endif /* _XT_NFLOG_TARGET */ diff --git a/include/linux/netfilter_ipv4/ipt_LOG.h b/include/linux/netfilter_ipv4/ipt_LOG.h index 892f9a33fea8..90fa6525ef9c 100644 --- a/include/linux/netfilter_ipv4/ipt_LOG.h +++ b/include/linux/netfilter_ipv4/ipt_LOG.h @@ -6,7 +6,7 @@ #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_NFLOG 0x10 /* Log using nf_log backend */ +#define IPT_LOG_NFLOG 0x10 /* Unsupported, don't reuse */ #define IPT_LOG_MASK 0x1f struct ipt_log_info { diff --git a/include/linux/netfilter_ipv6/ip6t_LOG.h b/include/linux/netfilter_ipv6/ip6t_LOG.h index 060c1a1c6c60..0d0119b0458c 100644 --- a/include/linux/netfilter_ipv6/ip6t_LOG.h +++ b/include/linux/netfilter_ipv6/ip6t_LOG.h @@ -6,7 +6,7 @@ #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_NFLOG 0x10 /* Log using nf_log backend */ +#define IP6T_LOG_NFLOG 0x10 /* Unsupported, don't use */ #define IP6T_LOG_MASK 0x1f struct ip6t_log_info { -- cgit v1.2.3 From d12cdc3ccf140bd2febef1c1be92284571da983f Mon Sep 17 00:00:00 2001 From: Bart De Schuymer Date: Wed, 29 Nov 2006 02:35:40 +0100 Subject: [NETFILTER]: ebtables: add --snap-arp option The attached patch adds --snat-arp support, which makes it possible to change the source mac address in both the mac header and the arp header with one rule. Signed-off-by: Bart De Schuymer Signed-off-by: Patrick McHardy --- include/linux/netfilter_bridge/ebt_nat.h | 1 + include/linux/netfilter_bridge/ebtables.h | 4 ++++ 2 files changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter_bridge/ebt_nat.h b/include/linux/netfilter_bridge/ebt_nat.h index 26fd90da4cd6..435b886a51aa 100644 --- a/include/linux/netfilter_bridge/ebt_nat.h +++ b/include/linux/netfilter_bridge/ebt_nat.h @@ -1,6 +1,7 @@ #ifndef __LINUX_BRIDGE_EBT_NAT_H #define __LINUX_BRIDGE_EBT_NAT_H +#define NAT_ARP_BIT (0x00000010) struct ebt_nat_info { unsigned char mac[ETH_ALEN]; diff --git a/include/linux/netfilter_bridge/ebtables.h b/include/linux/netfilter_bridge/ebtables.h index e6ea70de24d5..87775264ff0b 100644 --- a/include/linux/netfilter_bridge/ebtables.h +++ b/include/linux/netfilter_bridge/ebtables.h @@ -26,6 +26,10 @@ #define EBT_CONTINUE -3 #define EBT_RETURN -4 #define NUM_STANDARD_TARGETS 4 +/* ebtables target modules store the verdict inside an int. We can + * reclaim a part of this int for backwards compatible extensions. + * The 4 lsb are more than enough to store the verdict. */ +#define EBT_VERDICT_BITS 0x0000000F struct ebt_counter { -- cgit v1.2.3 From 1e419cd9953f59d06d7b88d0e2911a68a0044f33 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 30 Nov 2006 19:28:48 -0800 Subject: [EBTABLES]: Split ebt_replace into user and kernel variants, annotate. Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/netfilter_bridge/ebtables.h | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_bridge/ebtables.h b/include/linux/netfilter_bridge/ebtables.h index 87775264ff0b..94e0a7dc0cb2 100644 --- a/include/linux/netfilter_bridge/ebtables.h +++ b/include/linux/netfilter_bridge/ebtables.h @@ -38,6 +38,23 @@ struct ebt_counter }; struct ebt_replace +{ + char name[EBT_TABLE_MAXNAMELEN]; + unsigned int valid_hooks; + /* nr of rules in the table */ + unsigned int nentries; + /* total size of the entries */ + unsigned int entries_size; + /* start of the chains */ + struct ebt_entries __user *hook_entry[NF_BR_NUMHOOKS]; + /* nr of counters userspace expects back */ + unsigned int num_counters; + /* where the kernel will put the old counters */ + struct ebt_counter __user *counters; + char __user *entries; +}; + +struct ebt_replace_kernel { char name[EBT_TABLE_MAXNAMELEN]; unsigned int valid_hooks; @@ -255,7 +272,7 @@ struct ebt_table { struct list_head list; char name[EBT_TABLE_MAXNAMELEN]; - struct ebt_replace *table; + struct ebt_replace_kernel *table; unsigned int valid_hooks; rwlock_t lock; /* e.g. could be the table explicitly only allows certain -- cgit v1.2.3 From 9a7c9337a09b1ef07e55f95a4309957a2328a01f Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Sat, 2 Dec 2006 22:04:04 -0800 Subject: [NET]: Accept wildcard delimiters in in[46]_pton Accept -1 as delimiter to abort parsing without an error at the first unknown character. This is needed by the upcoming nf_conntrack SIP helper, where addresses are delimited by either '\r' or '\n' characters. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/inet.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/inet.h b/include/linux/inet.h index b7c6da7d6d32..675a7dbe86f8 100644 --- a/include/linux/inet.h +++ b/include/linux/inet.h @@ -46,7 +46,7 @@ #include extern __be32 in_aton(const char *str); -extern int in4_pton(const char *src, int srclen, u8 *dst, char delim, const char **end); -extern int in6_pton(const char *src, int srclen, u8 *dst, char delim, const char **end); +extern int in4_pton(const char *src, int srclen, u8 *dst, int delim, const char **end); +extern int in6_pton(const char *src, int srclen, u8 *dst, int delim, const char **end); #endif #endif /* _LINUX_INET_H */ -- cgit v1.2.3 From 5b1158e909ecbe1a052203e0d8df15633f829930 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Sat, 2 Dec 2006 22:07:13 -0800 Subject: [NETFILTER]: Add NAT support for nf_conntrack Add NAT support for nf_conntrack. Joint work of Jozsef Kadlecsik, Yasuyuki Kozakai, Martin Josefsson and myself. Signed-off-by: Jozsef Kadlecsik Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index f6f3fcbd70ed..d4c4c5120bc0 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -357,7 +357,7 @@ extern void (*ip_nat_decode_session)(struct sk_buff *, struct flowi *); static inline void nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, int family) { -#ifdef CONFIG_IP_NF_NAT_NEEDED +#if defined(CONFIG_IP_NF_NAT_NEEDED) || defined(CONFIG_NF_NAT_NEEDED) void (*decodefn)(struct sk_buff *, struct flowi *); if (family == AF_INET && (decodefn = ip_nat_decode_session) != NULL) -- cgit v1.2.3 From 55a733247d6d2883d9bb77825fafac3dfca13fc2 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Sat, 2 Dec 2006 22:07:44 -0800 Subject: [NETFILTER]: nf_nat: add FTP NAT helper port Add FTP NAT helper. Split out from Jozsef's big nf_nat patch with a few small fixes by myself. Signed-off-by: Jozsef Kadlecsik Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter/nf_conntrack_ftp.h | 20 ++++++------- include/linux/netfilter_ipv4/ip_conntrack_ftp.h | 40 ++++++++++++++++++++++++- 2 files changed, 49 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nf_conntrack_ftp.h b/include/linux/netfilter/nf_conntrack_ftp.h index ad4a41c9ce93..81453ea7e4c2 100644 --- a/include/linux/netfilter/nf_conntrack_ftp.h +++ b/include/linux/netfilter/nf_conntrack_ftp.h @@ -3,16 +3,16 @@ /* FTP tracking. */ /* This enum is exposed to userspace */ -enum ip_ct_ftp_type +enum nf_ct_ftp_type { /* PORT command from client */ - IP_CT_FTP_PORT, + NF_CT_FTP_PORT, /* PASV response from server */ - IP_CT_FTP_PASV, + NF_CT_FTP_PASV, /* EPRT command from client */ - IP_CT_FTP_EPRT, + NF_CT_FTP_EPRT, /* EPSV response from server */ - IP_CT_FTP_EPSV, + NF_CT_FTP_EPSV, }; #ifdef __KERNEL__ @@ -21,23 +21,23 @@ enum ip_ct_ftp_type #define NUM_SEQ_TO_REMEMBER 2 /* This structure exists only once per master */ -struct ip_ct_ftp_master { +struct nf_ct_ftp_master { /* Valid seq positions for cmd matching after newline */ u_int32_t seq_aft_nl[IP_CT_DIR_MAX][NUM_SEQ_TO_REMEMBER]; /* 0 means seq_match_aft_nl not set */ int seq_aft_nl_num[IP_CT_DIR_MAX]; }; -struct ip_conntrack_expect; +struct nf_conntrack_expect; /* For NAT to hook in when we find a packet which describes what other * connection we should expect. */ -extern unsigned int (*ip_nat_ftp_hook)(struct sk_buff **pskb, +extern unsigned int (*nf_nat_ftp_hook)(struct sk_buff **pskb, enum ip_conntrack_info ctinfo, - enum ip_ct_ftp_type type, + enum nf_ct_ftp_type type, unsigned int matchoff, unsigned int matchlen, - struct ip_conntrack_expect *exp, + struct nf_conntrack_expect *exp, u32 *seq); #endif /* __KERNEL__ */ diff --git a/include/linux/netfilter_ipv4/ip_conntrack_ftp.h b/include/linux/netfilter_ipv4/ip_conntrack_ftp.h index 63811934de4d..2129fc3972ac 100644 --- a/include/linux/netfilter_ipv4/ip_conntrack_ftp.h +++ b/include/linux/netfilter_ipv4/ip_conntrack_ftp.h @@ -1,6 +1,44 @@ #ifndef _IP_CONNTRACK_FTP_H #define _IP_CONNTRACK_FTP_H +/* FTP tracking. */ -#include +/* This enum is exposed to userspace */ +enum ip_ct_ftp_type +{ + /* PORT command from client */ + IP_CT_FTP_PORT, + /* PASV response from server */ + IP_CT_FTP_PASV, + /* EPRT command from client */ + IP_CT_FTP_EPRT, + /* EPSV response from server */ + IP_CT_FTP_EPSV, +}; + +#ifdef __KERNEL__ + +#define FTP_PORT 21 + +#define NUM_SEQ_TO_REMEMBER 2 +/* This structure exists only once per master */ +struct ip_ct_ftp_master { + /* Valid seq positions for cmd matching after newline */ + u_int32_t seq_aft_nl[IP_CT_DIR_MAX][NUM_SEQ_TO_REMEMBER]; + /* 0 means seq_match_aft_nl not set */ + int seq_aft_nl_num[IP_CT_DIR_MAX]; +}; + +struct ip_conntrack_expect; + +/* For NAT to hook in when we find a packet which describes what other + * connection we should expect. */ +extern unsigned int (*ip_nat_ftp_hook)(struct sk_buff **pskb, + enum ip_conntrack_info ctinfo, + enum ip_ct_ftp_type type, + unsigned int matchoff, + unsigned int matchlen, + struct ip_conntrack_expect *exp, + u32 *seq); +#endif /* __KERNEL__ */ #endif /* _IP_CONNTRACK_FTP_H */ -- cgit v1.2.3 From 16958900578b94585c2ab9a2d20d837b4d5e3ba6 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Sat, 2 Dec 2006 22:08:26 -0800 Subject: [NETFILTER]: nf_conntrack/nf_nat: add amanda helper port Add IPv4 and IPv6 capable nf_conntrack port of the Amanda conntrack/NAT helper. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter/nf_conntrack_amanda.h | 10 ++++++++++ 1 file changed, 10 insertions(+) create mode 100644 include/linux/netfilter/nf_conntrack_amanda.h (limited to 'include/linux') diff --git a/include/linux/netfilter/nf_conntrack_amanda.h b/include/linux/netfilter/nf_conntrack_amanda.h new file mode 100644 index 000000000000..26c223544ae8 --- /dev/null +++ b/include/linux/netfilter/nf_conntrack_amanda.h @@ -0,0 +1,10 @@ +#ifndef _NF_CONNTRACK_AMANDA_H +#define _NF_CONNTRACK_AMANDA_H +/* AMANDA tracking. */ + +extern unsigned int (*nf_nat_amanda_hook)(struct sk_buff **pskb, + enum ip_conntrack_info ctinfo, + unsigned int matchoff, + unsigned int matchlen, + struct nf_conntrack_expect *exp); +#endif /* _NF_CONNTRACK_AMANDA_H */ -- cgit v1.2.3 From f587de0e2feb9eb9b94f98d0a7b7437e4d6617b4 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Sat, 2 Dec 2006 22:08:46 -0800 Subject: [NETFILTER]: nf_conntrack/nf_nat: add H.323 helper port Add IPv4 and IPv6 capable nf_conntrack port of the H.323 conntrack/NAT helper. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter/nf_conntrack_h323.h | 92 ++ include/linux/netfilter/nf_conntrack_h323_asn1.h | 98 +++ include/linux/netfilter/nf_conntrack_h323_types.h | 951 +++++++++++++++++++++ include/linux/netfilter_ipv4/Kbuild | 2 - include/linux/netfilter_ipv4/ip_conntrack_h323.h | 2 +- .../netfilter_ipv4/ip_conntrack_helper_h323_asn1.h | 98 --- .../ip_conntrack_helper_h323_types.h | 939 -------------------- 7 files changed, 1142 insertions(+), 1040 deletions(-) create mode 100644 include/linux/netfilter/nf_conntrack_h323.h create mode 100644 include/linux/netfilter/nf_conntrack_h323_asn1.h create mode 100644 include/linux/netfilter/nf_conntrack_h323_types.h delete mode 100644 include/linux/netfilter_ipv4/ip_conntrack_helper_h323_asn1.h delete mode 100644 include/linux/netfilter_ipv4/ip_conntrack_helper_h323_types.h (limited to 'include/linux') diff --git a/include/linux/netfilter/nf_conntrack_h323.h b/include/linux/netfilter/nf_conntrack_h323.h new file mode 100644 index 000000000000..08e2f4977c2e --- /dev/null +++ b/include/linux/netfilter/nf_conntrack_h323.h @@ -0,0 +1,92 @@ +#ifndef _NF_CONNTRACK_H323_H +#define _NF_CONNTRACK_H323_H + +#ifdef __KERNEL__ + +#include + +#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 nf_ct_h323_master { + + /* Original and NATed Q.931 or H.245 signal ports */ + __be16 sig_port[IP_CT_DIR_MAX]; + + /* Original and NATed RTP ports */ + __be16 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]; + }; +}; + +struct nf_conn; + +extern int get_h225_addr(struct nf_conn *ct, unsigned char *data, + TransportAddress *taddr, + union nf_conntrack_address *addr, __be16 *port); +extern void nf_conntrack_h245_expect(struct nf_conn *new, + struct nf_conntrack_expect *this); +extern void nf_conntrack_q931_expect(struct nf_conn *new, + struct nf_conntrack_expect *this); +extern int (*set_h245_addr_hook) (struct sk_buff **pskb, + unsigned char **data, int dataoff, + H245_TransportAddress *taddr, + union nf_conntrack_address *addr, + __be16 port); +extern int (*set_h225_addr_hook) (struct sk_buff **pskb, + unsigned char **data, int dataoff, + TransportAddress *taddr, + union nf_conntrack_address *addr, + __be16 port); +extern int (*set_sig_addr_hook) (struct sk_buff **pskb, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, + TransportAddress *taddr, int count); +extern int (*set_ras_addr_hook) (struct sk_buff **pskb, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, + TransportAddress *taddr, int count); +extern int (*nat_rtp_rtcp_hook) (struct sk_buff **pskb, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, int dataoff, + H245_TransportAddress *taddr, + __be16 port, __be16 rtp_port, + struct nf_conntrack_expect *rtp_exp, + struct nf_conntrack_expect *rtcp_exp); +extern int (*nat_t120_hook) (struct sk_buff **pskb, struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, int dataoff, + H245_TransportAddress *taddr, __be16 port, + struct nf_conntrack_expect *exp); +extern int (*nat_h245_hook) (struct sk_buff **pskb, struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, int dataoff, + TransportAddress *taddr, __be16 port, + struct nf_conntrack_expect *exp); +extern int (*nat_callforwarding_hook) (struct sk_buff **pskb, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, int dataoff, + TransportAddress *taddr, + __be16 port, + struct nf_conntrack_expect *exp); +extern int (*nat_q931_hook) (struct sk_buff **pskb, struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, TransportAddress *taddr, + int idx, __be16 port, + struct nf_conntrack_expect *exp); + +#endif + +#endif diff --git a/include/linux/netfilter/nf_conntrack_h323_asn1.h b/include/linux/netfilter/nf_conntrack_h323_asn1.h new file mode 100644 index 000000000000..8dab5968fc7e --- /dev/null +++ b/include/linux/netfilter/nf_conntrack_h323_asn1.h @@ -0,0 +1,98 @@ +/**************************************************************************** + * ip_conntrack_h323_asn1.h - BER and PER decoding library for H.323 + * conntrack/NAT module. + * + * Copyright (c) 2006 by Jing Min Zhao + * + * This source code is licensed under General Public License version 2. + * + * + * This library is based on H.225 version 4, H.235 version 2 and H.245 + * version 7. It is extremely optimized to decode only the absolutely + * necessary objects in a signal for Linux kernel NAT module use, so don't + * expect it to be a full ASN.1 library. + * + * Features: + * + * 1. Small. The total size of code plus data is less than 20 KB (IA32). + * 2. Fast. Decoding Netmeeting's Setup signal 1 million times on a PIII 866 + * takes only 3.9 seconds. + * 3. No memory allocation. It uses a static object. No need to initialize or + * cleanup. + * 4. Thread safe. + * 5. Support embedded architectures that has no misaligned memory access + * support. + * + * Limitations: + * + * 1. At most 30 faststart entries. Actually this is limited by ethernet's MTU. + * If a Setup signal contains more than 30 faststart, the packet size will + * very likely exceed the MTU size, then the TPKT will be fragmented. I + * don't know how to handle this in a Netfilter module. Anybody can help? + * Although I think 30 is enough for most of the cases. + * 2. IPv4 addresses only. + * + ****************************************************************************/ + +#ifndef _NF_CONNTRACK_HELPER_H323_ASN1_H_ +#define _NF_CONNTRACK_HELPER_H323_ASN1_H_ + +/***************************************************************************** + * H.323 Types + ****************************************************************************/ +#include "nf_conntrack_h323_types.h" + +typedef struct { + enum { + Q931_NationalEscape = 0x00, + Q931_Alerting = 0x01, + Q931_CallProceeding = 0x02, + Q931_Connect = 0x07, + Q931_ConnectAck = 0x0F, + Q931_Progress = 0x03, + Q931_Setup = 0x05, + Q931_SetupAck = 0x0D, + Q931_Resume = 0x26, + Q931_ResumeAck = 0x2E, + Q931_ResumeReject = 0x22, + Q931_Suspend = 0x25, + Q931_SuspendAck = 0x2D, + Q931_SuspendReject = 0x21, + Q931_UserInformation = 0x20, + Q931_Disconnect = 0x45, + Q931_Release = 0x4D, + Q931_ReleaseComplete = 0x5A, + Q931_Restart = 0x46, + Q931_RestartAck = 0x4E, + Q931_Segment = 0x60, + Q931_CongestionCtrl = 0x79, + Q931_Information = 0x7B, + Q931_Notify = 0x6E, + Q931_Status = 0x7D, + Q931_StatusEnquiry = 0x75, + Q931_Facility = 0x62 + } MessageType; + H323_UserInformation UUIE; +} Q931; + +/***************************************************************************** + * Decode Functions Return Codes + ****************************************************************************/ + +#define H323_ERROR_NONE 0 /* Decoded successfully */ +#define H323_ERROR_STOP 1 /* Decoding stopped, not really an error */ +#define H323_ERROR_BOUND -1 +#define H323_ERROR_RANGE -2 + + +/***************************************************************************** + * Decode Functions + ****************************************************************************/ + +int DecodeRasMessage(unsigned char *buf, size_t sz, RasMessage * ras); +int DecodeQ931(unsigned char *buf, size_t sz, Q931 * q931); +int DecodeMultimediaSystemControlMessage(unsigned char *buf, size_t sz, + MultimediaSystemControlMessage * + mscm); + +#endif diff --git a/include/linux/netfilter/nf_conntrack_h323_types.h b/include/linux/netfilter/nf_conntrack_h323_types.h new file mode 100644 index 000000000000..38d74d5c9700 --- /dev/null +++ b/include/linux/netfilter/nf_conntrack_h323_types.h @@ -0,0 +1,951 @@ +/* Generated by Jing Min Zhao's ASN.1 parser, Apr 20 2006 + * + * Copyright (c) 2006 Jing Min Zhao + * + * This source code is licensed under General Public License version 2. + */ + +typedef struct TransportAddress_ipAddress { /* SEQUENCE */ + int options; /* No use */ + unsigned ip; +} TransportAddress_ipAddress; + +typedef struct TransportAddress_ip6Address { /* SEQUENCE */ + int options; /* No use */ + unsigned ip6; +} TransportAddress_ip6Address; + +typedef struct TransportAddress { /* CHOICE */ + enum { + eTransportAddress_ipAddress, + eTransportAddress_ipSourceRoute, + eTransportAddress_ipxAddress, + eTransportAddress_ip6Address, + eTransportAddress_netBios, + eTransportAddress_nsap, + eTransportAddress_nonStandardAddress, + } choice; + union { + TransportAddress_ipAddress ipAddress; + TransportAddress_ip6Address ip6Address; + }; +} TransportAddress; + +typedef struct DataProtocolCapability { /* CHOICE */ + enum { + eDataProtocolCapability_nonStandard, + eDataProtocolCapability_v14buffered, + eDataProtocolCapability_v42lapm, + eDataProtocolCapability_hdlcFrameTunnelling, + eDataProtocolCapability_h310SeparateVCStack, + eDataProtocolCapability_h310SingleVCStack, + eDataProtocolCapability_transparent, + eDataProtocolCapability_segmentationAndReassembly, + eDataProtocolCapability_hdlcFrameTunnelingwSAR, + eDataProtocolCapability_v120, + eDataProtocolCapability_separateLANStack, + eDataProtocolCapability_v76wCompression, + eDataProtocolCapability_tcp, + eDataProtocolCapability_udp, + } choice; +} DataProtocolCapability; + +typedef struct DataApplicationCapability_application { /* CHOICE */ + enum { + eDataApplicationCapability_application_nonStandard, + eDataApplicationCapability_application_t120, + eDataApplicationCapability_application_dsm_cc, + eDataApplicationCapability_application_userData, + eDataApplicationCapability_application_t84, + eDataApplicationCapability_application_t434, + eDataApplicationCapability_application_h224, + eDataApplicationCapability_application_nlpid, + eDataApplicationCapability_application_dsvdControl, + eDataApplicationCapability_application_h222DataPartitioning, + eDataApplicationCapability_application_t30fax, + eDataApplicationCapability_application_t140, + eDataApplicationCapability_application_t38fax, + eDataApplicationCapability_application_genericDataCapability, + } choice; + union { + DataProtocolCapability t120; + }; +} DataApplicationCapability_application; + +typedef struct DataApplicationCapability { /* SEQUENCE */ + int options; /* No use */ + DataApplicationCapability_application application; +} DataApplicationCapability; + +typedef struct DataType { /* CHOICE */ + enum { + eDataType_nonStandard, + eDataType_nullData, + eDataType_videoData, + eDataType_audioData, + eDataType_data, + eDataType_encryptionData, + eDataType_h235Control, + eDataType_h235Media, + eDataType_multiplexedStream, + } choice; + union { + DataApplicationCapability data; + }; +} DataType; + +typedef struct UnicastAddress_iPAddress { /* SEQUENCE */ + int options; /* No use */ + unsigned network; +} UnicastAddress_iPAddress; + +typedef struct UnicastAddress_iP6Address { /* SEQUENCE */ + int options; /* No use */ + unsigned network; +} UnicastAddress_iP6Address; + +typedef struct UnicastAddress { /* CHOICE */ + enum { + eUnicastAddress_iPAddress, + eUnicastAddress_iPXAddress, + eUnicastAddress_iP6Address, + eUnicastAddress_netBios, + eUnicastAddress_iPSourceRouteAddress, + eUnicastAddress_nsap, + eUnicastAddress_nonStandardAddress, + } choice; + union { + UnicastAddress_iPAddress iPAddress; + UnicastAddress_iP6Address iP6Address; + }; +} UnicastAddress; + +typedef struct H245_TransportAddress { /* CHOICE */ + enum { + eH245_TransportAddress_unicastAddress, + eH245_TransportAddress_multicastAddress, + } choice; + union { + UnicastAddress unicastAddress; + }; +} H245_TransportAddress; + +typedef struct H2250LogicalChannelParameters { /* SEQUENCE */ + enum { + eH2250LogicalChannelParameters_nonStandard = (1 << 31), + eH2250LogicalChannelParameters_associatedSessionID = + (1 << 30), + eH2250LogicalChannelParameters_mediaChannel = (1 << 29), + eH2250LogicalChannelParameters_mediaGuaranteedDelivery = + (1 << 28), + eH2250LogicalChannelParameters_mediaControlChannel = + (1 << 27), + eH2250LogicalChannelParameters_mediaControlGuaranteedDelivery + = (1 << 26), + eH2250LogicalChannelParameters_silenceSuppression = (1 << 25), + eH2250LogicalChannelParameters_destination = (1 << 24), + eH2250LogicalChannelParameters_dynamicRTPPayloadType = + (1 << 23), + eH2250LogicalChannelParameters_mediaPacketization = (1 << 22), + eH2250LogicalChannelParameters_transportCapability = + (1 << 21), + eH2250LogicalChannelParameters_redundancyEncoding = (1 << 20), + eH2250LogicalChannelParameters_source = (1 << 19), + } options; + H245_TransportAddress mediaChannel; + H245_TransportAddress mediaControlChannel; +} H2250LogicalChannelParameters; + +typedef struct OpenLogicalChannel_forwardLogicalChannelParameters_multiplexParameters { /* CHOICE */ + enum { + eOpenLogicalChannel_forwardLogicalChannelParameters_multiplexParameters_h222LogicalChannelParameters, + eOpenLogicalChannel_forwardLogicalChannelParameters_multiplexParameters_h223LogicalChannelParameters, + eOpenLogicalChannel_forwardLogicalChannelParameters_multiplexParameters_v76LogicalChannelParameters, + eOpenLogicalChannel_forwardLogicalChannelParameters_multiplexParameters_h2250LogicalChannelParameters, + eOpenLogicalChannel_forwardLogicalChannelParameters_multiplexParameters_none, + } choice; + union { + H2250LogicalChannelParameters h2250LogicalChannelParameters; + }; +} OpenLogicalChannel_forwardLogicalChannelParameters_multiplexParameters; + +typedef struct OpenLogicalChannel_forwardLogicalChannelParameters { /* SEQUENCE */ + enum { + eOpenLogicalChannel_forwardLogicalChannelParameters_portNumber + = (1 << 31), + eOpenLogicalChannel_forwardLogicalChannelParameters_forwardLogicalChannelDependency + = (1 << 30), + eOpenLogicalChannel_forwardLogicalChannelParameters_replacementFor + = (1 << 29), + } options; + DataType dataType; + OpenLogicalChannel_forwardLogicalChannelParameters_multiplexParameters + multiplexParameters; +} OpenLogicalChannel_forwardLogicalChannelParameters; + +typedef struct OpenLogicalChannel_reverseLogicalChannelParameters_multiplexParameters { /* CHOICE */ + enum { + eOpenLogicalChannel_reverseLogicalChannelParameters_multiplexParameters_h223LogicalChannelParameters, + eOpenLogicalChannel_reverseLogicalChannelParameters_multiplexParameters_v76LogicalChannelParameters, + eOpenLogicalChannel_reverseLogicalChannelParameters_multiplexParameters_h2250LogicalChannelParameters, + } choice; + union { + H2250LogicalChannelParameters h2250LogicalChannelParameters; + }; +} OpenLogicalChannel_reverseLogicalChannelParameters_multiplexParameters; + +typedef struct OpenLogicalChannel_reverseLogicalChannelParameters { /* SEQUENCE */ + enum { + eOpenLogicalChannel_reverseLogicalChannelParameters_multiplexParameters + = (1 << 31), + eOpenLogicalChannel_reverseLogicalChannelParameters_reverseLogicalChannelDependency + = (1 << 30), + eOpenLogicalChannel_reverseLogicalChannelParameters_replacementFor + = (1 << 29), + } options; + OpenLogicalChannel_reverseLogicalChannelParameters_multiplexParameters + multiplexParameters; +} OpenLogicalChannel_reverseLogicalChannelParameters; + +typedef struct NetworkAccessParameters_networkAddress { /* CHOICE */ + enum { + eNetworkAccessParameters_networkAddress_q2931Address, + eNetworkAccessParameters_networkAddress_e164Address, + eNetworkAccessParameters_networkAddress_localAreaAddress, + } choice; + union { + H245_TransportAddress localAreaAddress; + }; +} NetworkAccessParameters_networkAddress; + +typedef struct NetworkAccessParameters { /* SEQUENCE */ + enum { + eNetworkAccessParameters_distribution = (1 << 31), + eNetworkAccessParameters_externalReference = (1 << 30), + eNetworkAccessParameters_t120SetupProcedure = (1 << 29), + } options; + NetworkAccessParameters_networkAddress networkAddress; +} NetworkAccessParameters; + +typedef struct OpenLogicalChannel { /* SEQUENCE */ + enum { + eOpenLogicalChannel_reverseLogicalChannelParameters = + (1 << 31), + eOpenLogicalChannel_separateStack = (1 << 30), + eOpenLogicalChannel_encryptionSync = (1 << 29), + } options; + OpenLogicalChannel_forwardLogicalChannelParameters + forwardLogicalChannelParameters; + OpenLogicalChannel_reverseLogicalChannelParameters + reverseLogicalChannelParameters; + NetworkAccessParameters separateStack; +} OpenLogicalChannel; + +typedef struct Setup_UUIE_fastStart { /* SEQUENCE OF */ + int count; + OpenLogicalChannel item[30]; +} Setup_UUIE_fastStart; + +typedef struct Setup_UUIE { /* SEQUENCE */ + enum { + eSetup_UUIE_h245Address = (1 << 31), + eSetup_UUIE_sourceAddress = (1 << 30), + eSetup_UUIE_destinationAddress = (1 << 29), + eSetup_UUIE_destCallSignalAddress = (1 << 28), + eSetup_UUIE_destExtraCallInfo = (1 << 27), + eSetup_UUIE_destExtraCRV = (1 << 26), + eSetup_UUIE_callServices = (1 << 25), + eSetup_UUIE_sourceCallSignalAddress = (1 << 24), + eSetup_UUIE_remoteExtensionAddress = (1 << 23), + eSetup_UUIE_callIdentifier = (1 << 22), + eSetup_UUIE_h245SecurityCapability = (1 << 21), + eSetup_UUIE_tokens = (1 << 20), + eSetup_UUIE_cryptoTokens = (1 << 19), + eSetup_UUIE_fastStart = (1 << 18), + eSetup_UUIE_mediaWaitForConnect = (1 << 17), + eSetup_UUIE_canOverlapSend = (1 << 16), + eSetup_UUIE_endpointIdentifier = (1 << 15), + eSetup_UUIE_multipleCalls = (1 << 14), + eSetup_UUIE_maintainConnection = (1 << 13), + eSetup_UUIE_connectionParameters = (1 << 12), + eSetup_UUIE_language = (1 << 11), + eSetup_UUIE_presentationIndicator = (1 << 10), + eSetup_UUIE_screeningIndicator = (1 << 9), + eSetup_UUIE_serviceControl = (1 << 8), + eSetup_UUIE_symmetricOperationRequired = (1 << 7), + eSetup_UUIE_capacity = (1 << 6), + eSetup_UUIE_circuitInfo = (1 << 5), + eSetup_UUIE_desiredProtocols = (1 << 4), + eSetup_UUIE_neededFeatures = (1 << 3), + eSetup_UUIE_desiredFeatures = (1 << 2), + eSetup_UUIE_supportedFeatures = (1 << 1), + eSetup_UUIE_parallelH245Control = (1 << 0), + } options; + TransportAddress h245Address; + TransportAddress destCallSignalAddress; + TransportAddress sourceCallSignalAddress; + Setup_UUIE_fastStart fastStart; +} Setup_UUIE; + +typedef struct CallProceeding_UUIE_fastStart { /* SEQUENCE OF */ + int count; + OpenLogicalChannel item[30]; +} CallProceeding_UUIE_fastStart; + +typedef struct CallProceeding_UUIE { /* SEQUENCE */ + enum { + eCallProceeding_UUIE_h245Address = (1 << 31), + eCallProceeding_UUIE_callIdentifier = (1 << 30), + eCallProceeding_UUIE_h245SecurityMode = (1 << 29), + eCallProceeding_UUIE_tokens = (1 << 28), + eCallProceeding_UUIE_cryptoTokens = (1 << 27), + eCallProceeding_UUIE_fastStart = (1 << 26), + eCallProceeding_UUIE_multipleCalls = (1 << 25), + eCallProceeding_UUIE_maintainConnection = (1 << 24), + eCallProceeding_UUIE_fastConnectRefused = (1 << 23), + eCallProceeding_UUIE_featureSet = (1 << 22), + } options; + TransportAddress h245Address; + CallProceeding_UUIE_fastStart fastStart; +} CallProceeding_UUIE; + +typedef struct Connect_UUIE_fastStart { /* SEQUENCE OF */ + int count; + OpenLogicalChannel item[30]; +} Connect_UUIE_fastStart; + +typedef struct Connect_UUIE { /* SEQUENCE */ + enum { + eConnect_UUIE_h245Address = (1 << 31), + eConnect_UUIE_callIdentifier = (1 << 30), + eConnect_UUIE_h245SecurityMode = (1 << 29), + eConnect_UUIE_tokens = (1 << 28), + eConnect_UUIE_cryptoTokens = (1 << 27), + eConnect_UUIE_fastStart = (1 << 26), + eConnect_UUIE_multipleCalls = (1 << 25), + eConnect_UUIE_maintainConnection = (1 << 24), + eConnect_UUIE_language = (1 << 23), + eConnect_UUIE_connectedAddress = (1 << 22), + eConnect_UUIE_presentationIndicator = (1 << 21), + eConnect_UUIE_screeningIndicator = (1 << 20), + eConnect_UUIE_fastConnectRefused = (1 << 19), + eConnect_UUIE_serviceControl = (1 << 18), + eConnect_UUIE_capacity = (1 << 17), + eConnect_UUIE_featureSet = (1 << 16), + } options; + TransportAddress h245Address; + Connect_UUIE_fastStart fastStart; +} Connect_UUIE; + +typedef struct Alerting_UUIE_fastStart { /* SEQUENCE OF */ + int count; + OpenLogicalChannel item[30]; +} Alerting_UUIE_fastStart; + +typedef struct Alerting_UUIE { /* SEQUENCE */ + enum { + eAlerting_UUIE_h245Address = (1 << 31), + eAlerting_UUIE_callIdentifier = (1 << 30), + eAlerting_UUIE_h245SecurityMode = (1 << 29), + eAlerting_UUIE_tokens = (1 << 28), + eAlerting_UUIE_cryptoTokens = (1 << 27), + eAlerting_UUIE_fastStart = (1 << 26), + eAlerting_UUIE_multipleCalls = (1 << 25), + eAlerting_UUIE_maintainConnection = (1 << 24), + eAlerting_UUIE_alertingAddress = (1 << 23), + eAlerting_UUIE_presentationIndicator = (1 << 22), + eAlerting_UUIE_screeningIndicator = (1 << 21), + eAlerting_UUIE_fastConnectRefused = (1 << 20), + eAlerting_UUIE_serviceControl = (1 << 19), + eAlerting_UUIE_capacity = (1 << 18), + eAlerting_UUIE_featureSet = (1 << 17), + } options; + TransportAddress h245Address; + Alerting_UUIE_fastStart fastStart; +} Alerting_UUIE; + +typedef struct Information_UUIE_fastStart { /* SEQUENCE OF */ + int count; + OpenLogicalChannel item[30]; +} Information_UUIE_fastStart; + +typedef struct Information_UUIE { /* SEQUENCE */ + enum { + eInformation_UUIE_callIdentifier = (1 << 31), + eInformation_UUIE_tokens = (1 << 30), + eInformation_UUIE_cryptoTokens = (1 << 29), + eInformation_UUIE_fastStart = (1 << 28), + eInformation_UUIE_fastConnectRefused = (1 << 27), + eInformation_UUIE_circuitInfo = (1 << 26), + } options; + Information_UUIE_fastStart fastStart; +} Information_UUIE; + +typedef struct FacilityReason { /* CHOICE */ + enum { + eFacilityReason_routeCallToGatekeeper, + eFacilityReason_callForwarded, + eFacilityReason_routeCallToMC, + eFacilityReason_undefinedReason, + eFacilityReason_conferenceListChoice, + eFacilityReason_startH245, + eFacilityReason_noH245, + eFacilityReason_newTokens, + eFacilityReason_featureSetUpdate, + eFacilityReason_forwardedElements, + eFacilityReason_transportedInformation, + } choice; +} FacilityReason; + +typedef struct Facility_UUIE_fastStart { /* SEQUENCE OF */ + int count; + OpenLogicalChannel item[30]; +} Facility_UUIE_fastStart; + +typedef struct Facility_UUIE { /* SEQUENCE */ + enum { + eFacility_UUIE_alternativeAddress = (1 << 31), + eFacility_UUIE_alternativeAliasAddress = (1 << 30), + eFacility_UUIE_conferenceID = (1 << 29), + eFacility_UUIE_callIdentifier = (1 << 28), + eFacility_UUIE_destExtraCallInfo = (1 << 27), + eFacility_UUIE_remoteExtensionAddress = (1 << 26), + eFacility_UUIE_tokens = (1 << 25), + eFacility_UUIE_cryptoTokens = (1 << 24), + eFacility_UUIE_conferences = (1 << 23), + eFacility_UUIE_h245Address = (1 << 22), + eFacility_UUIE_fastStart = (1 << 21), + eFacility_UUIE_multipleCalls = (1 << 20), + eFacility_UUIE_maintainConnection = (1 << 19), + eFacility_UUIE_fastConnectRefused = (1 << 18), + eFacility_UUIE_serviceControl = (1 << 17), + eFacility_UUIE_circuitInfo = (1 << 16), + eFacility_UUIE_featureSet = (1 << 15), + eFacility_UUIE_destinationInfo = (1 << 14), + eFacility_UUIE_h245SecurityMode = (1 << 13), + } options; + TransportAddress alternativeAddress; + FacilityReason reason; + TransportAddress h245Address; + Facility_UUIE_fastStart fastStart; +} Facility_UUIE; + +typedef struct Progress_UUIE_fastStart { /* SEQUENCE OF */ + int count; + OpenLogicalChannel item[30]; +} Progress_UUIE_fastStart; + +typedef struct Progress_UUIE { /* SEQUENCE */ + enum { + eProgress_UUIE_h245Address = (1 << 31), + eProgress_UUIE_h245SecurityMode = (1 << 30), + eProgress_UUIE_tokens = (1 << 29), + eProgress_UUIE_cryptoTokens = (1 << 28), + eProgress_UUIE_fastStart = (1 << 27), + eProgress_UUIE_multipleCalls = (1 << 26), + eProgress_UUIE_maintainConnection = (1 << 25), + eProgress_UUIE_fastConnectRefused = (1 << 24), + } options; + TransportAddress h245Address; + Progress_UUIE_fastStart fastStart; +} Progress_UUIE; + +typedef struct H323_UU_PDU_h323_message_body { /* CHOICE */ + enum { + eH323_UU_PDU_h323_message_body_setup, + eH323_UU_PDU_h323_message_body_callProceeding, + eH323_UU_PDU_h323_message_body_connect, + eH323_UU_PDU_h323_message_body_alerting, + eH323_UU_PDU_h323_message_body_information, + eH323_UU_PDU_h323_message_body_releaseComplete, + eH323_UU_PDU_h323_message_body_facility, + eH323_UU_PDU_h323_message_body_progress, + eH323_UU_PDU_h323_message_body_empty, + eH323_UU_PDU_h323_message_body_status, + eH323_UU_PDU_h323_message_body_statusInquiry, + eH323_UU_PDU_h323_message_body_setupAcknowledge, + eH323_UU_PDU_h323_message_body_notify, + } choice; + union { + Setup_UUIE setup; + CallProceeding_UUIE callProceeding; + Connect_UUIE connect; + Alerting_UUIE alerting; + Information_UUIE information; + Facility_UUIE facility; + Progress_UUIE progress; + }; +} H323_UU_PDU_h323_message_body; + +typedef struct RequestMessage { /* CHOICE */ + enum { + eRequestMessage_nonStandard, + eRequestMessage_masterSlaveDetermination, + eRequestMessage_terminalCapabilitySet, + eRequestMessage_openLogicalChannel, + eRequestMessage_closeLogicalChannel, + eRequestMessage_requestChannelClose, + eRequestMessage_multiplexEntrySend, + eRequestMessage_requestMultiplexEntry, + eRequestMessage_requestMode, + eRequestMessage_roundTripDelayRequest, + eRequestMessage_maintenanceLoopRequest, + eRequestMessage_communicationModeRequest, + eRequestMessage_conferenceRequest, + eRequestMessage_multilinkRequest, + eRequestMessage_logicalChannelRateRequest, + } choice; + union { + OpenLogicalChannel openLogicalChannel; + }; +} RequestMessage; + +typedef struct OpenLogicalChannelAck_reverseLogicalChannelParameters_multiplexParameters { /* CHOICE */ + enum { + eOpenLogicalChannelAck_reverseLogicalChannelParameters_multiplexParameters_h222LogicalChannelParameters, + eOpenLogicalChannelAck_reverseLogicalChannelParameters_multiplexParameters_h2250LogicalChannelParameters, + } choice; + union { + H2250LogicalChannelParameters h2250LogicalChannelParameters; + }; +} OpenLogicalChannelAck_reverseLogicalChannelParameters_multiplexParameters; + +typedef struct OpenLogicalChannelAck_reverseLogicalChannelParameters { /* SEQUENCE */ + enum { + eOpenLogicalChannelAck_reverseLogicalChannelParameters_portNumber + = (1 << 31), + eOpenLogicalChannelAck_reverseLogicalChannelParameters_multiplexParameters + = (1 << 30), + eOpenLogicalChannelAck_reverseLogicalChannelParameters_replacementFor + = (1 << 29), + } options; + OpenLogicalChannelAck_reverseLogicalChannelParameters_multiplexParameters + multiplexParameters; +} OpenLogicalChannelAck_reverseLogicalChannelParameters; + +typedef struct H2250LogicalChannelAckParameters { /* SEQUENCE */ + enum { + eH2250LogicalChannelAckParameters_nonStandard = (1 << 31), + eH2250LogicalChannelAckParameters_sessionID = (1 << 30), + eH2250LogicalChannelAckParameters_mediaChannel = (1 << 29), + eH2250LogicalChannelAckParameters_mediaControlChannel = + (1 << 28), + eH2250LogicalChannelAckParameters_dynamicRTPPayloadType = + (1 << 27), + eH2250LogicalChannelAckParameters_flowControlToZero = + (1 << 26), + eH2250LogicalChannelAckParameters_portNumber = (1 << 25), + } options; + H245_TransportAddress mediaChannel; + H245_TransportAddress mediaControlChannel; +} H2250LogicalChannelAckParameters; + +typedef struct OpenLogicalChannelAck_forwardMultiplexAckParameters { /* CHOICE */ + enum { + eOpenLogicalChannelAck_forwardMultiplexAckParameters_h2250LogicalChannelAckParameters, + } choice; + union { + H2250LogicalChannelAckParameters + h2250LogicalChannelAckParameters; + }; +} OpenLogicalChannelAck_forwardMultiplexAckParameters; + +typedef struct OpenLogicalChannelAck { /* SEQUENCE */ + enum { + eOpenLogicalChannelAck_reverseLogicalChannelParameters = + (1 << 31), + eOpenLogicalChannelAck_separateStack = (1 << 30), + eOpenLogicalChannelAck_forwardMultiplexAckParameters = + (1 << 29), + eOpenLogicalChannelAck_encryptionSync = (1 << 28), + } options; + OpenLogicalChannelAck_reverseLogicalChannelParameters + reverseLogicalChannelParameters; + OpenLogicalChannelAck_forwardMultiplexAckParameters + forwardMultiplexAckParameters; +} OpenLogicalChannelAck; + +typedef struct ResponseMessage { /* CHOICE */ + enum { + eResponseMessage_nonStandard, + eResponseMessage_masterSlaveDeterminationAck, + eResponseMessage_masterSlaveDeterminationReject, + eResponseMessage_terminalCapabilitySetAck, + eResponseMessage_terminalCapabilitySetReject, + eResponseMessage_openLogicalChannelAck, + eResponseMessage_openLogicalChannelReject, + eResponseMessage_closeLogicalChannelAck, + eResponseMessage_requestChannelCloseAck, + eResponseMessage_requestChannelCloseReject, + eResponseMessage_multiplexEntrySendAck, + eResponseMessage_multiplexEntrySendReject, + eResponseMessage_requestMultiplexEntryAck, + eResponseMessage_requestMultiplexEntryReject, + eResponseMessage_requestModeAck, + eResponseMessage_requestModeReject, + eResponseMessage_roundTripDelayResponse, + eResponseMessage_maintenanceLoopAck, + eResponseMessage_maintenanceLoopReject, + eResponseMessage_communicationModeResponse, + eResponseMessage_conferenceResponse, + eResponseMessage_multilinkResponse, + eResponseMessage_logicalChannelRateAcknowledge, + eResponseMessage_logicalChannelRateReject, + } choice; + union { + OpenLogicalChannelAck openLogicalChannelAck; + }; +} ResponseMessage; + +typedef struct MultimediaSystemControlMessage { /* CHOICE */ + enum { + eMultimediaSystemControlMessage_request, + eMultimediaSystemControlMessage_response, + eMultimediaSystemControlMessage_command, + eMultimediaSystemControlMessage_indication, + } choice; + union { + RequestMessage request; + ResponseMessage response; + }; +} MultimediaSystemControlMessage; + +typedef struct H323_UU_PDU_h245Control { /* SEQUENCE OF */ + int count; + MultimediaSystemControlMessage item[4]; +} H323_UU_PDU_h245Control; + +typedef struct H323_UU_PDU { /* SEQUENCE */ + enum { + eH323_UU_PDU_nonStandardData = (1 << 31), + eH323_UU_PDU_h4501SupplementaryService = (1 << 30), + eH323_UU_PDU_h245Tunneling = (1 << 29), + eH323_UU_PDU_h245Control = (1 << 28), + eH323_UU_PDU_nonStandardControl = (1 << 27), + eH323_UU_PDU_callLinkage = (1 << 26), + eH323_UU_PDU_tunnelledSignallingMessage = (1 << 25), + eH323_UU_PDU_provisionalRespToH245Tunneling = (1 << 24), + eH323_UU_PDU_stimulusControl = (1 << 23), + eH323_UU_PDU_genericData = (1 << 22), + } options; + H323_UU_PDU_h323_message_body h323_message_body; + H323_UU_PDU_h245Control h245Control; +} H323_UU_PDU; + +typedef struct H323_UserInformation { /* SEQUENCE */ + enum { + eH323_UserInformation_user_data = (1 << 31), + } options; + H323_UU_PDU h323_uu_pdu; +} H323_UserInformation; + +typedef struct GatekeeperRequest { /* SEQUENCE */ + enum { + eGatekeeperRequest_nonStandardData = (1 << 31), + eGatekeeperRequest_gatekeeperIdentifier = (1 << 30), + eGatekeeperRequest_callServices = (1 << 29), + eGatekeeperRequest_endpointAlias = (1 << 28), + eGatekeeperRequest_alternateEndpoints = (1 << 27), + eGatekeeperRequest_tokens = (1 << 26), + eGatekeeperRequest_cryptoTokens = (1 << 25), + eGatekeeperRequest_authenticationCapability = (1 << 24), + eGatekeeperRequest_algorithmOIDs = (1 << 23), + eGatekeeperRequest_integrity = (1 << 22), + eGatekeeperRequest_integrityCheckValue = (1 << 21), + eGatekeeperRequest_supportsAltGK = (1 << 20), + eGatekeeperRequest_featureSet = (1 << 19), + eGatekeeperRequest_genericData = (1 << 18), + } options; + TransportAddress rasAddress; +} GatekeeperRequest; + +typedef struct GatekeeperConfirm { /* SEQUENCE */ + enum { + eGatekeeperConfirm_nonStandardData = (1 << 31), + eGatekeeperConfirm_gatekeeperIdentifier = (1 << 30), + eGatekeeperConfirm_alternateGatekeeper = (1 << 29), + eGatekeeperConfirm_authenticationMode = (1 << 28), + eGatekeeperConfirm_tokens = (1 << 27), + eGatekeeperConfirm_cryptoTokens = (1 << 26), + eGatekeeperConfirm_algorithmOID = (1 << 25), + eGatekeeperConfirm_integrity = (1 << 24), + eGatekeeperConfirm_integrityCheckValue = (1 << 23), + eGatekeeperConfirm_featureSet = (1 << 22), + eGatekeeperConfirm_genericData = (1 << 21), + } options; + TransportAddress rasAddress; +} GatekeeperConfirm; + +typedef struct RegistrationRequest_callSignalAddress { /* SEQUENCE OF */ + int count; + TransportAddress item[10]; +} RegistrationRequest_callSignalAddress; + +typedef struct RegistrationRequest_rasAddress { /* SEQUENCE OF */ + int count; + TransportAddress item[10]; +} RegistrationRequest_rasAddress; + +typedef struct RegistrationRequest { /* SEQUENCE */ + enum { + eRegistrationRequest_nonStandardData = (1 << 31), + eRegistrationRequest_terminalAlias = (1 << 30), + eRegistrationRequest_gatekeeperIdentifier = (1 << 29), + eRegistrationRequest_alternateEndpoints = (1 << 28), + eRegistrationRequest_timeToLive = (1 << 27), + eRegistrationRequest_tokens = (1 << 26), + eRegistrationRequest_cryptoTokens = (1 << 25), + eRegistrationRequest_integrityCheckValue = (1 << 24), + eRegistrationRequest_keepAlive = (1 << 23), + eRegistrationRequest_endpointIdentifier = (1 << 22), + eRegistrationRequest_willSupplyUUIEs = (1 << 21), + eRegistrationRequest_maintainConnection = (1 << 20), + eRegistrationRequest_alternateTransportAddresses = (1 << 19), + eRegistrationRequest_additiveRegistration = (1 << 18), + eRegistrationRequest_terminalAliasPattern = (1 << 17), + eRegistrationRequest_supportsAltGK = (1 << 16), + eRegistrationRequest_usageReportingCapability = (1 << 15), + eRegistrationRequest_multipleCalls = (1 << 14), + eRegistrationRequest_supportedH248Packages = (1 << 13), + eRegistrationRequest_callCreditCapability = (1 << 12), + eRegistrationRequest_capacityReportingCapability = (1 << 11), + eRegistrationRequest_capacity = (1 << 10), + eRegistrationRequest_featureSet = (1 << 9), + eRegistrationRequest_genericData = (1 << 8), + } options; + RegistrationRequest_callSignalAddress callSignalAddress; + RegistrationRequest_rasAddress rasAddress; + unsigned timeToLive; +} RegistrationRequest; + +typedef struct RegistrationConfirm_callSignalAddress { /* SEQUENCE OF */ + int count; + TransportAddress item[10]; +} RegistrationConfirm_callSignalAddress; + +typedef struct RegistrationConfirm { /* SEQUENCE */ + enum { + eRegistrationConfirm_nonStandardData = (1 << 31), + eRegistrationConfirm_terminalAlias = (1 << 30), + eRegistrationConfirm_gatekeeperIdentifier = (1 << 29), + eRegistrationConfirm_alternateGatekeeper = (1 << 28), + eRegistrationConfirm_timeToLive = (1 << 27), + eRegistrationConfirm_tokens = (1 << 26), + eRegistrationConfirm_cryptoTokens = (1 << 25), + eRegistrationConfirm_integrityCheckValue = (1 << 24), + eRegistrationConfirm_willRespondToIRR = (1 << 23), + eRegistrationConfirm_preGrantedARQ = (1 << 22), + eRegistrationConfirm_maintainConnection = (1 << 21), + eRegistrationConfirm_serviceControl = (1 << 20), + eRegistrationConfirm_supportsAdditiveRegistration = (1 << 19), + eRegistrationConfirm_terminalAliasPattern = (1 << 18), + eRegistrationConfirm_supportedPrefixes = (1 << 17), + eRegistrationConfirm_usageSpec = (1 << 16), + eRegistrationConfirm_featureServerAlias = (1 << 15), + eRegistrationConfirm_capacityReportingSpec = (1 << 14), + eRegistrationConfirm_featureSet = (1 << 13), + eRegistrationConfirm_genericData = (1 << 12), + } options; + RegistrationConfirm_callSignalAddress callSignalAddress; + unsigned timeToLive; +} RegistrationConfirm; + +typedef struct UnregistrationRequest_callSignalAddress { /* SEQUENCE OF */ + int count; + TransportAddress item[10]; +} UnregistrationRequest_callSignalAddress; + +typedef struct UnregistrationRequest { /* SEQUENCE */ + enum { + eUnregistrationRequest_endpointAlias = (1 << 31), + eUnregistrationRequest_nonStandardData = (1 << 30), + eUnregistrationRequest_endpointIdentifier = (1 << 29), + eUnregistrationRequest_alternateEndpoints = (1 << 28), + eUnregistrationRequest_gatekeeperIdentifier = (1 << 27), + eUnregistrationRequest_tokens = (1 << 26), + eUnregistrationRequest_cryptoTokens = (1 << 25), + eUnregistrationRequest_integrityCheckValue = (1 << 24), + eUnregistrationRequest_reason = (1 << 23), + eUnregistrationRequest_endpointAliasPattern = (1 << 22), + eUnregistrationRequest_supportedPrefixes = (1 << 21), + eUnregistrationRequest_alternateGatekeeper = (1 << 20), + eUnregistrationRequest_genericData = (1 << 19), + } options; + UnregistrationRequest_callSignalAddress callSignalAddress; +} UnregistrationRequest; + +typedef struct AdmissionRequest { /* SEQUENCE */ + enum { + eAdmissionRequest_callModel = (1 << 31), + eAdmissionRequest_destinationInfo = (1 << 30), + eAdmissionRequest_destCallSignalAddress = (1 << 29), + eAdmissionRequest_destExtraCallInfo = (1 << 28), + eAdmissionRequest_srcCallSignalAddress = (1 << 27), + eAdmissionRequest_nonStandardData = (1 << 26), + eAdmissionRequest_callServices = (1 << 25), + eAdmissionRequest_canMapAlias = (1 << 24), + eAdmissionRequest_callIdentifier = (1 << 23), + eAdmissionRequest_srcAlternatives = (1 << 22), + eAdmissionRequest_destAlternatives = (1 << 21), + eAdmissionRequest_gatekeeperIdentifier = (1 << 20), + eAdmissionRequest_tokens = (1 << 19), + eAdmissionRequest_cryptoTokens = (1 << 18), + eAdmissionRequest_integrityCheckValue = (1 << 17), + eAdmissionRequest_transportQOS = (1 << 16), + eAdmissionRequest_willSupplyUUIEs = (1 << 15), + eAdmissionRequest_callLinkage = (1 << 14), + eAdmissionRequest_gatewayDataRate = (1 << 13), + eAdmissionRequest_capacity = (1 << 12), + eAdmissionRequest_circuitInfo = (1 << 11), + eAdmissionRequest_desiredProtocols = (1 << 10), + eAdmissionRequest_desiredTunnelledProtocol = (1 << 9), + eAdmissionRequest_featureSet = (1 << 8), + eAdmissionRequest_genericData = (1 << 7), + } options; + TransportAddress destCallSignalAddress; + TransportAddress srcCallSignalAddress; +} AdmissionRequest; + +typedef struct AdmissionConfirm { /* SEQUENCE */ + enum { + eAdmissionConfirm_irrFrequency = (1 << 31), + eAdmissionConfirm_nonStandardData = (1 << 30), + eAdmissionConfirm_destinationInfo = (1 << 29), + eAdmissionConfirm_destExtraCallInfo = (1 << 28), + eAdmissionConfirm_destinationType = (1 << 27), + eAdmissionConfirm_remoteExtensionAddress = (1 << 26), + eAdmissionConfirm_alternateEndpoints = (1 << 25), + eAdmissionConfirm_tokens = (1 << 24), + eAdmissionConfirm_cryptoTokens = (1 << 23), + eAdmissionConfirm_integrityCheckValue = (1 << 22), + eAdmissionConfirm_transportQOS = (1 << 21), + eAdmissionConfirm_willRespondToIRR = (1 << 20), + eAdmissionConfirm_uuiesRequested = (1 << 19), + eAdmissionConfirm_language = (1 << 18), + eAdmissionConfirm_alternateTransportAddresses = (1 << 17), + eAdmissionConfirm_useSpecifiedTransport = (1 << 16), + eAdmissionConfirm_circuitInfo = (1 << 15), + eAdmissionConfirm_usageSpec = (1 << 14), + eAdmissionConfirm_supportedProtocols = (1 << 13), + eAdmissionConfirm_serviceControl = (1 << 12), + eAdmissionConfirm_multipleCalls = (1 << 11), + eAdmissionConfirm_featureSet = (1 << 10), + eAdmissionConfirm_genericData = (1 << 9), + } options; + TransportAddress destCallSignalAddress; +} AdmissionConfirm; + +typedef struct LocationRequest { /* SEQUENCE */ + enum { + eLocationRequest_endpointIdentifier = (1 << 31), + eLocationRequest_nonStandardData = (1 << 30), + eLocationRequest_sourceInfo = (1 << 29), + eLocationRequest_canMapAlias = (1 << 28), + eLocationRequest_gatekeeperIdentifier = (1 << 27), + eLocationRequest_tokens = (1 << 26), + eLocationRequest_cryptoTokens = (1 << 25), + eLocationRequest_integrityCheckValue = (1 << 24), + eLocationRequest_desiredProtocols = (1 << 23), + eLocationRequest_desiredTunnelledProtocol = (1 << 22), + eLocationRequest_featureSet = (1 << 21), + eLocationRequest_genericData = (1 << 20), + eLocationRequest_hopCount = (1 << 19), + eLocationRequest_circuitInfo = (1 << 18), + } options; + TransportAddress replyAddress; +} LocationRequest; + +typedef struct LocationConfirm { /* SEQUENCE */ + enum { + eLocationConfirm_nonStandardData = (1 << 31), + eLocationConfirm_destinationInfo = (1 << 30), + eLocationConfirm_destExtraCallInfo = (1 << 29), + eLocationConfirm_destinationType = (1 << 28), + eLocationConfirm_remoteExtensionAddress = (1 << 27), + eLocationConfirm_alternateEndpoints = (1 << 26), + eLocationConfirm_tokens = (1 << 25), + eLocationConfirm_cryptoTokens = (1 << 24), + eLocationConfirm_integrityCheckValue = (1 << 23), + eLocationConfirm_alternateTransportAddresses = (1 << 22), + eLocationConfirm_supportedProtocols = (1 << 21), + eLocationConfirm_multipleCalls = (1 << 20), + eLocationConfirm_featureSet = (1 << 19), + eLocationConfirm_genericData = (1 << 18), + eLocationConfirm_circuitInfo = (1 << 17), + eLocationConfirm_serviceControl = (1 << 16), + } options; + TransportAddress callSignalAddress; + TransportAddress rasAddress; +} LocationConfirm; + +typedef struct InfoRequestResponse_callSignalAddress { /* SEQUENCE OF */ + int count; + TransportAddress item[10]; +} InfoRequestResponse_callSignalAddress; + +typedef struct InfoRequestResponse { /* SEQUENCE */ + enum { + eInfoRequestResponse_nonStandardData = (1 << 31), + eInfoRequestResponse_endpointAlias = (1 << 30), + eInfoRequestResponse_perCallInfo = (1 << 29), + eInfoRequestResponse_tokens = (1 << 28), + eInfoRequestResponse_cryptoTokens = (1 << 27), + eInfoRequestResponse_integrityCheckValue = (1 << 26), + eInfoRequestResponse_needResponse = (1 << 25), + eInfoRequestResponse_capacity = (1 << 24), + eInfoRequestResponse_irrStatus = (1 << 23), + eInfoRequestResponse_unsolicited = (1 << 22), + eInfoRequestResponse_genericData = (1 << 21), + } options; + TransportAddress rasAddress; + InfoRequestResponse_callSignalAddress callSignalAddress; +} InfoRequestResponse; + +typedef struct RasMessage { /* CHOICE */ + enum { + eRasMessage_gatekeeperRequest, + eRasMessage_gatekeeperConfirm, + eRasMessage_gatekeeperReject, + eRasMessage_registrationRequest, + eRasMessage_registrationConfirm, + eRasMessage_registrationReject, + eRasMessage_unregistrationRequest, + eRasMessage_unregistrationConfirm, + eRasMessage_unregistrationReject, + eRasMessage_admissionRequest, + eRasMessage_admissionConfirm, + eRasMessage_admissionReject, + eRasMessage_bandwidthRequest, + eRasMessage_bandwidthConfirm, + eRasMessage_bandwidthReject, + eRasMessage_disengageRequest, + eRasMessage_disengageConfirm, + eRasMessage_disengageReject, + eRasMessage_locationRequest, + eRasMessage_locationConfirm, + eRasMessage_locationReject, + eRasMessage_infoRequest, + eRasMessage_infoRequestResponse, + eRasMessage_nonStandardMessage, + eRasMessage_unknownMessageResponse, + eRasMessage_requestInProgress, + eRasMessage_resourcesAvailableIndicate, + eRasMessage_resourcesAvailableConfirm, + eRasMessage_infoRequestAck, + eRasMessage_infoRequestNak, + eRasMessage_serviceControlIndication, + eRasMessage_serviceControlResponse, + } choice; + union { + GatekeeperRequest gatekeeperRequest; + GatekeeperConfirm gatekeeperConfirm; + RegistrationRequest registrationRequest; + RegistrationConfirm registrationConfirm; + UnregistrationRequest unregistrationRequest; + AdmissionRequest admissionRequest; + AdmissionConfirm admissionConfirm; + LocationRequest locationRequest; + LocationConfirm locationConfirm; + InfoRequestResponse infoRequestResponse; + }; +} RasMessage; diff --git a/include/linux/netfilter_ipv4/Kbuild b/include/linux/netfilter_ipv4/Kbuild index 591c1a809c00..180337801a86 100644 --- a/include/linux/netfilter_ipv4/Kbuild +++ b/include/linux/netfilter_ipv4/Kbuild @@ -1,6 +1,4 @@ header-y += ip_conntrack_helper.h -header-y += ip_conntrack_helper_h323_asn1.h -header-y += ip_conntrack_helper_h323_types.h header-y += ip_conntrack_protocol.h header-y += ip_conntrack_sctp.h header-y += ip_conntrack_tcp.h diff --git a/include/linux/netfilter_ipv4/ip_conntrack_h323.h b/include/linux/netfilter_ipv4/ip_conntrack_h323.h index 943cc6a4871d..18f769818f4e 100644 --- a/include/linux/netfilter_ipv4/ip_conntrack_h323.h +++ b/include/linux/netfilter_ipv4/ip_conntrack_h323.h @@ -3,7 +3,7 @@ #ifdef __KERNEL__ -#include +#include #define RAS_PORT 1719 #define Q931_PORT 1720 diff --git a/include/linux/netfilter_ipv4/ip_conntrack_helper_h323_asn1.h b/include/linux/netfilter_ipv4/ip_conntrack_helper_h323_asn1.h deleted file mode 100644 index c6e9a0b6d30b..000000000000 --- a/include/linux/netfilter_ipv4/ip_conntrack_helper_h323_asn1.h +++ /dev/null @@ -1,98 +0,0 @@ -/**************************************************************************** - * ip_conntrack_helper_h323_asn1.h - BER and PER decoding library for H.323 - * conntrack/NAT module. - * - * Copyright (c) 2006 by Jing Min Zhao - * - * This source code is licensed under General Public License version 2. - * - * - * This library is based on H.225 version 4, H.235 version 2 and H.245 - * version 7. It is extremely optimized to decode only the absolutely - * necessary objects in a signal for Linux kernel NAT module use, so don't - * expect it to be a full ASN.1 library. - * - * Features: - * - * 1. Small. The total size of code plus data is less than 20 KB (IA32). - * 2. Fast. Decoding Netmeeting's Setup signal 1 million times on a PIII 866 - * takes only 3.9 seconds. - * 3. No memory allocation. It uses a static object. No need to initialize or - * cleanup. - * 4. Thread safe. - * 5. Support embedded architectures that has no misaligned memory access - * support. - * - * Limitations: - * - * 1. At most 30 faststart entries. Actually this is limited by ethernet's MTU. - * If a Setup signal contains more than 30 faststart, the packet size will - * very likely exceed the MTU size, then the TPKT will be fragmented. I - * don't know how to handle this in a Netfilter module. Anybody can help? - * Although I think 30 is enough for most of the cases. - * 2. IPv4 addresses only. - * - ****************************************************************************/ - -#ifndef _IP_CONNTRACK_HELPER_H323_ASN1_H_ -#define _IP_CONNTRACK_HELPER_H323_ASN1_H_ - -/***************************************************************************** - * H.323 Types - ****************************************************************************/ -#include "ip_conntrack_helper_h323_types.h" - -typedef struct { - enum { - Q931_NationalEscape = 0x00, - Q931_Alerting = 0x01, - Q931_CallProceeding = 0x02, - Q931_Connect = 0x07, - Q931_ConnectAck = 0x0F, - Q931_Progress = 0x03, - Q931_Setup = 0x05, - Q931_SetupAck = 0x0D, - Q931_Resume = 0x26, - Q931_ResumeAck = 0x2E, - Q931_ResumeReject = 0x22, - Q931_Suspend = 0x25, - Q931_SuspendAck = 0x2D, - Q931_SuspendReject = 0x21, - Q931_UserInformation = 0x20, - Q931_Disconnect = 0x45, - Q931_Release = 0x4D, - Q931_ReleaseComplete = 0x5A, - Q931_Restart = 0x46, - Q931_RestartAck = 0x4E, - Q931_Segment = 0x60, - Q931_CongestionCtrl = 0x79, - Q931_Information = 0x7B, - Q931_Notify = 0x6E, - Q931_Status = 0x7D, - Q931_StatusEnquiry = 0x75, - Q931_Facility = 0x62 - } MessageType; - H323_UserInformation UUIE; -} Q931; - -/***************************************************************************** - * Decode Functions Return Codes - ****************************************************************************/ - -#define H323_ERROR_NONE 0 /* Decoded successfully */ -#define H323_ERROR_STOP 1 /* Decoding stopped, not really an error */ -#define H323_ERROR_BOUND -1 -#define H323_ERROR_RANGE -2 - - -/***************************************************************************** - * Decode Functions - ****************************************************************************/ - -int DecodeRasMessage(unsigned char *buf, size_t sz, RasMessage * ras); -int DecodeQ931(unsigned char *buf, size_t sz, Q931 * q931); -int DecodeMultimediaSystemControlMessage(unsigned char *buf, size_t sz, - MultimediaSystemControlMessage * - mscm); - -#endif diff --git a/include/linux/netfilter_ipv4/ip_conntrack_helper_h323_types.h b/include/linux/netfilter_ipv4/ip_conntrack_helper_h323_types.h deleted file mode 100644 index 3d4a773799fc..000000000000 --- a/include/linux/netfilter_ipv4/ip_conntrack_helper_h323_types.h +++ /dev/null @@ -1,939 +0,0 @@ -/* Generated by Jing Min Zhao's ASN.1 parser, Apr 20 2006 - * - * Copyright (c) 2006 Jing Min Zhao - * - * This source code is licensed under General Public License version 2. - */ - -typedef struct TransportAddress_ipAddress { /* SEQUENCE */ - int options; /* No use */ - unsigned ip; -} TransportAddress_ipAddress; - -typedef struct TransportAddress { /* CHOICE */ - enum { - eTransportAddress_ipAddress, - eTransportAddress_ipSourceRoute, - eTransportAddress_ipxAddress, - eTransportAddress_ip6Address, - eTransportAddress_netBios, - eTransportAddress_nsap, - eTransportAddress_nonStandardAddress, - } choice; - union { - TransportAddress_ipAddress ipAddress; - }; -} TransportAddress; - -typedef struct DataProtocolCapability { /* CHOICE */ - enum { - eDataProtocolCapability_nonStandard, - eDataProtocolCapability_v14buffered, - eDataProtocolCapability_v42lapm, - eDataProtocolCapability_hdlcFrameTunnelling, - eDataProtocolCapability_h310SeparateVCStack, - eDataProtocolCapability_h310SingleVCStack, - eDataProtocolCapability_transparent, - eDataProtocolCapability_segmentationAndReassembly, - eDataProtocolCapability_hdlcFrameTunnelingwSAR, - eDataProtocolCapability_v120, - eDataProtocolCapability_separateLANStack, - eDataProtocolCapability_v76wCompression, - eDataProtocolCapability_tcp, - eDataProtocolCapability_udp, - } choice; -} DataProtocolCapability; - -typedef struct DataApplicationCapability_application { /* CHOICE */ - enum { - eDataApplicationCapability_application_nonStandard, - eDataApplicationCapability_application_t120, - eDataApplicationCapability_application_dsm_cc, - eDataApplicationCapability_application_userData, - eDataApplicationCapability_application_t84, - eDataApplicationCapability_application_t434, - eDataApplicationCapability_application_h224, - eDataApplicationCapability_application_nlpid, - eDataApplicationCapability_application_dsvdControl, - eDataApplicationCapability_application_h222DataPartitioning, - eDataApplicationCapability_application_t30fax, - eDataApplicationCapability_application_t140, - eDataApplicationCapability_application_t38fax, - eDataApplicationCapability_application_genericDataCapability, - } choice; - union { - DataProtocolCapability t120; - }; -} DataApplicationCapability_application; - -typedef struct DataApplicationCapability { /* SEQUENCE */ - int options; /* No use */ - DataApplicationCapability_application application; -} DataApplicationCapability; - -typedef struct DataType { /* CHOICE */ - enum { - eDataType_nonStandard, - eDataType_nullData, - eDataType_videoData, - eDataType_audioData, - eDataType_data, - eDataType_encryptionData, - eDataType_h235Control, - eDataType_h235Media, - eDataType_multiplexedStream, - } choice; - union { - DataApplicationCapability data; - }; -} DataType; - -typedef struct UnicastAddress_iPAddress { /* SEQUENCE */ - int options; /* No use */ - unsigned network; -} UnicastAddress_iPAddress; - -typedef struct UnicastAddress { /* CHOICE */ - enum { - eUnicastAddress_iPAddress, - eUnicastAddress_iPXAddress, - eUnicastAddress_iP6Address, - eUnicastAddress_netBios, - eUnicastAddress_iPSourceRouteAddress, - eUnicastAddress_nsap, - eUnicastAddress_nonStandardAddress, - } choice; - union { - UnicastAddress_iPAddress iPAddress; - }; -} UnicastAddress; - -typedef struct H245_TransportAddress { /* CHOICE */ - enum { - eH245_TransportAddress_unicastAddress, - eH245_TransportAddress_multicastAddress, - } choice; - union { - UnicastAddress unicastAddress; - }; -} H245_TransportAddress; - -typedef struct H2250LogicalChannelParameters { /* SEQUENCE */ - enum { - eH2250LogicalChannelParameters_nonStandard = (1 << 31), - eH2250LogicalChannelParameters_associatedSessionID = - (1 << 30), - eH2250LogicalChannelParameters_mediaChannel = (1 << 29), - eH2250LogicalChannelParameters_mediaGuaranteedDelivery = - (1 << 28), - eH2250LogicalChannelParameters_mediaControlChannel = - (1 << 27), - eH2250LogicalChannelParameters_mediaControlGuaranteedDelivery - = (1 << 26), - eH2250LogicalChannelParameters_silenceSuppression = (1 << 25), - eH2250LogicalChannelParameters_destination = (1 << 24), - eH2250LogicalChannelParameters_dynamicRTPPayloadType = - (1 << 23), - eH2250LogicalChannelParameters_mediaPacketization = (1 << 22), - eH2250LogicalChannelParameters_transportCapability = - (1 << 21), - eH2250LogicalChannelParameters_redundancyEncoding = (1 << 20), - eH2250LogicalChannelParameters_source = (1 << 19), - } options; - H245_TransportAddress mediaChannel; - H245_TransportAddress mediaControlChannel; -} H2250LogicalChannelParameters; - -typedef struct OpenLogicalChannel_forwardLogicalChannelParameters_multiplexParameters { /* CHOICE */ - enum { - eOpenLogicalChannel_forwardLogicalChannelParameters_multiplexParameters_h222LogicalChannelParameters, - eOpenLogicalChannel_forwardLogicalChannelParameters_multiplexParameters_h223LogicalChannelParameters, - eOpenLogicalChannel_forwardLogicalChannelParameters_multiplexParameters_v76LogicalChannelParameters, - eOpenLogicalChannel_forwardLogicalChannelParameters_multiplexParameters_h2250LogicalChannelParameters, - eOpenLogicalChannel_forwardLogicalChannelParameters_multiplexParameters_none, - } choice; - union { - H2250LogicalChannelParameters h2250LogicalChannelParameters; - }; -} OpenLogicalChannel_forwardLogicalChannelParameters_multiplexParameters; - -typedef struct OpenLogicalChannel_forwardLogicalChannelParameters { /* SEQUENCE */ - enum { - eOpenLogicalChannel_forwardLogicalChannelParameters_portNumber - = (1 << 31), - eOpenLogicalChannel_forwardLogicalChannelParameters_forwardLogicalChannelDependency - = (1 << 30), - eOpenLogicalChannel_forwardLogicalChannelParameters_replacementFor - = (1 << 29), - } options; - DataType dataType; - OpenLogicalChannel_forwardLogicalChannelParameters_multiplexParameters - multiplexParameters; -} OpenLogicalChannel_forwardLogicalChannelParameters; - -typedef struct OpenLogicalChannel_reverseLogicalChannelParameters_multiplexParameters { /* CHOICE */ - enum { - eOpenLogicalChannel_reverseLogicalChannelParameters_multiplexParameters_h223LogicalChannelParameters, - eOpenLogicalChannel_reverseLogicalChannelParameters_multiplexParameters_v76LogicalChannelParameters, - eOpenLogicalChannel_reverseLogicalChannelParameters_multiplexParameters_h2250LogicalChannelParameters, - } choice; - union { - H2250LogicalChannelParameters h2250LogicalChannelParameters; - }; -} OpenLogicalChannel_reverseLogicalChannelParameters_multiplexParameters; - -typedef struct OpenLogicalChannel_reverseLogicalChannelParameters { /* SEQUENCE */ - enum { - eOpenLogicalChannel_reverseLogicalChannelParameters_multiplexParameters - = (1 << 31), - eOpenLogicalChannel_reverseLogicalChannelParameters_reverseLogicalChannelDependency - = (1 << 30), - eOpenLogicalChannel_reverseLogicalChannelParameters_replacementFor - = (1 << 29), - } options; - OpenLogicalChannel_reverseLogicalChannelParameters_multiplexParameters - multiplexParameters; -} OpenLogicalChannel_reverseLogicalChannelParameters; - -typedef struct NetworkAccessParameters_networkAddress { /* CHOICE */ - enum { - eNetworkAccessParameters_networkAddress_q2931Address, - eNetworkAccessParameters_networkAddress_e164Address, - eNetworkAccessParameters_networkAddress_localAreaAddress, - } choice; - union { - H245_TransportAddress localAreaAddress; - }; -} NetworkAccessParameters_networkAddress; - -typedef struct NetworkAccessParameters { /* SEQUENCE */ - enum { - eNetworkAccessParameters_distribution = (1 << 31), - eNetworkAccessParameters_externalReference = (1 << 30), - eNetworkAccessParameters_t120SetupProcedure = (1 << 29), - } options; - NetworkAccessParameters_networkAddress networkAddress; -} NetworkAccessParameters; - -typedef struct OpenLogicalChannel { /* SEQUENCE */ - enum { - eOpenLogicalChannel_reverseLogicalChannelParameters = - (1 << 31), - eOpenLogicalChannel_separateStack = (1 << 30), - eOpenLogicalChannel_encryptionSync = (1 << 29), - } options; - OpenLogicalChannel_forwardLogicalChannelParameters - forwardLogicalChannelParameters; - OpenLogicalChannel_reverseLogicalChannelParameters - reverseLogicalChannelParameters; - NetworkAccessParameters separateStack; -} OpenLogicalChannel; - -typedef struct Setup_UUIE_fastStart { /* SEQUENCE OF */ - int count; - OpenLogicalChannel item[30]; -} Setup_UUIE_fastStart; - -typedef struct Setup_UUIE { /* SEQUENCE */ - enum { - eSetup_UUIE_h245Address = (1 << 31), - eSetup_UUIE_sourceAddress = (1 << 30), - eSetup_UUIE_destinationAddress = (1 << 29), - eSetup_UUIE_destCallSignalAddress = (1 << 28), - eSetup_UUIE_destExtraCallInfo = (1 << 27), - eSetup_UUIE_destExtraCRV = (1 << 26), - eSetup_UUIE_callServices = (1 << 25), - eSetup_UUIE_sourceCallSignalAddress = (1 << 24), - eSetup_UUIE_remoteExtensionAddress = (1 << 23), - eSetup_UUIE_callIdentifier = (1 << 22), - eSetup_UUIE_h245SecurityCapability = (1 << 21), - eSetup_UUIE_tokens = (1 << 20), - eSetup_UUIE_cryptoTokens = (1 << 19), - eSetup_UUIE_fastStart = (1 << 18), - eSetup_UUIE_mediaWaitForConnect = (1 << 17), - eSetup_UUIE_canOverlapSend = (1 << 16), - eSetup_UUIE_endpointIdentifier = (1 << 15), - eSetup_UUIE_multipleCalls = (1 << 14), - eSetup_UUIE_maintainConnection = (1 << 13), - eSetup_UUIE_connectionParameters = (1 << 12), - eSetup_UUIE_language = (1 << 11), - eSetup_UUIE_presentationIndicator = (1 << 10), - eSetup_UUIE_screeningIndicator = (1 << 9), - eSetup_UUIE_serviceControl = (1 << 8), - eSetup_UUIE_symmetricOperationRequired = (1 << 7), - eSetup_UUIE_capacity = (1 << 6), - eSetup_UUIE_circuitInfo = (1 << 5), - eSetup_UUIE_desiredProtocols = (1 << 4), - eSetup_UUIE_neededFeatures = (1 << 3), - eSetup_UUIE_desiredFeatures = (1 << 2), - eSetup_UUIE_supportedFeatures = (1 << 1), - eSetup_UUIE_parallelH245Control = (1 << 0), - } options; - TransportAddress h245Address; - TransportAddress destCallSignalAddress; - TransportAddress sourceCallSignalAddress; - Setup_UUIE_fastStart fastStart; -} Setup_UUIE; - -typedef struct CallProceeding_UUIE_fastStart { /* SEQUENCE OF */ - int count; - OpenLogicalChannel item[30]; -} CallProceeding_UUIE_fastStart; - -typedef struct CallProceeding_UUIE { /* SEQUENCE */ - enum { - eCallProceeding_UUIE_h245Address = (1 << 31), - eCallProceeding_UUIE_callIdentifier = (1 << 30), - eCallProceeding_UUIE_h245SecurityMode = (1 << 29), - eCallProceeding_UUIE_tokens = (1 << 28), - eCallProceeding_UUIE_cryptoTokens = (1 << 27), - eCallProceeding_UUIE_fastStart = (1 << 26), - eCallProceeding_UUIE_multipleCalls = (1 << 25), - eCallProceeding_UUIE_maintainConnection = (1 << 24), - eCallProceeding_UUIE_fastConnectRefused = (1 << 23), - eCallProceeding_UUIE_featureSet = (1 << 22), - } options; - TransportAddress h245Address; - CallProceeding_UUIE_fastStart fastStart; -} CallProceeding_UUIE; - -typedef struct Connect_UUIE_fastStart { /* SEQUENCE OF */ - int count; - OpenLogicalChannel item[30]; -} Connect_UUIE_fastStart; - -typedef struct Connect_UUIE { /* SEQUENCE */ - enum { - eConnect_UUIE_h245Address = (1 << 31), - eConnect_UUIE_callIdentifier = (1 << 30), - eConnect_UUIE_h245SecurityMode = (1 << 29), - eConnect_UUIE_tokens = (1 << 28), - eConnect_UUIE_cryptoTokens = (1 << 27), - eConnect_UUIE_fastStart = (1 << 26), - eConnect_UUIE_multipleCalls = (1 << 25), - eConnect_UUIE_maintainConnection = (1 << 24), - eConnect_UUIE_language = (1 << 23), - eConnect_UUIE_connectedAddress = (1 << 22), - eConnect_UUIE_presentationIndicator = (1 << 21), - eConnect_UUIE_screeningIndicator = (1 << 20), - eConnect_UUIE_fastConnectRefused = (1 << 19), - eConnect_UUIE_serviceControl = (1 << 18), - eConnect_UUIE_capacity = (1 << 17), - eConnect_UUIE_featureSet = (1 << 16), - } options; - TransportAddress h245Address; - Connect_UUIE_fastStart fastStart; -} Connect_UUIE; - -typedef struct Alerting_UUIE_fastStart { /* SEQUENCE OF */ - int count; - OpenLogicalChannel item[30]; -} Alerting_UUIE_fastStart; - -typedef struct Alerting_UUIE { /* SEQUENCE */ - enum { - eAlerting_UUIE_h245Address = (1 << 31), - eAlerting_UUIE_callIdentifier = (1 << 30), - eAlerting_UUIE_h245SecurityMode = (1 << 29), - eAlerting_UUIE_tokens = (1 << 28), - eAlerting_UUIE_cryptoTokens = (1 << 27), - eAlerting_UUIE_fastStart = (1 << 26), - eAlerting_UUIE_multipleCalls = (1 << 25), - eAlerting_UUIE_maintainConnection = (1 << 24), - eAlerting_UUIE_alertingAddress = (1 << 23), - eAlerting_UUIE_presentationIndicator = (1 << 22), - eAlerting_UUIE_screeningIndicator = (1 << 21), - eAlerting_UUIE_fastConnectRefused = (1 << 20), - eAlerting_UUIE_serviceControl = (1 << 19), - eAlerting_UUIE_capacity = (1 << 18), - eAlerting_UUIE_featureSet = (1 << 17), - } options; - TransportAddress h245Address; - Alerting_UUIE_fastStart fastStart; -} Alerting_UUIE; - -typedef struct Information_UUIE_fastStart { /* SEQUENCE OF */ - int count; - OpenLogicalChannel item[30]; -} Information_UUIE_fastStart; - -typedef struct Information_UUIE { /* SEQUENCE */ - enum { - eInformation_UUIE_callIdentifier = (1 << 31), - eInformation_UUIE_tokens = (1 << 30), - eInformation_UUIE_cryptoTokens = (1 << 29), - eInformation_UUIE_fastStart = (1 << 28), - eInformation_UUIE_fastConnectRefused = (1 << 27), - eInformation_UUIE_circuitInfo = (1 << 26), - } options; - Information_UUIE_fastStart fastStart; -} Information_UUIE; - -typedef struct FacilityReason { /* CHOICE */ - enum { - eFacilityReason_routeCallToGatekeeper, - eFacilityReason_callForwarded, - eFacilityReason_routeCallToMC, - eFacilityReason_undefinedReason, - eFacilityReason_conferenceListChoice, - eFacilityReason_startH245, - eFacilityReason_noH245, - eFacilityReason_newTokens, - eFacilityReason_featureSetUpdate, - eFacilityReason_forwardedElements, - eFacilityReason_transportedInformation, - } choice; -} FacilityReason; - -typedef struct Facility_UUIE_fastStart { /* SEQUENCE OF */ - int count; - OpenLogicalChannel item[30]; -} Facility_UUIE_fastStart; - -typedef struct Facility_UUIE { /* SEQUENCE */ - enum { - eFacility_UUIE_alternativeAddress = (1 << 31), - eFacility_UUIE_alternativeAliasAddress = (1 << 30), - eFacility_UUIE_conferenceID = (1 << 29), - eFacility_UUIE_callIdentifier = (1 << 28), - eFacility_UUIE_destExtraCallInfo = (1 << 27), - eFacility_UUIE_remoteExtensionAddress = (1 << 26), - eFacility_UUIE_tokens = (1 << 25), - eFacility_UUIE_cryptoTokens = (1 << 24), - eFacility_UUIE_conferences = (1 << 23), - eFacility_UUIE_h245Address = (1 << 22), - eFacility_UUIE_fastStart = (1 << 21), - eFacility_UUIE_multipleCalls = (1 << 20), - eFacility_UUIE_maintainConnection = (1 << 19), - eFacility_UUIE_fastConnectRefused = (1 << 18), - eFacility_UUIE_serviceControl = (1 << 17), - eFacility_UUIE_circuitInfo = (1 << 16), - eFacility_UUIE_featureSet = (1 << 15), - eFacility_UUIE_destinationInfo = (1 << 14), - eFacility_UUIE_h245SecurityMode = (1 << 13), - } options; - TransportAddress alternativeAddress; - FacilityReason reason; - TransportAddress h245Address; - Facility_UUIE_fastStart fastStart; -} Facility_UUIE; - -typedef struct Progress_UUIE_fastStart { /* SEQUENCE OF */ - int count; - OpenLogicalChannel item[30]; -} Progress_UUIE_fastStart; - -typedef struct Progress_UUIE { /* SEQUENCE */ - enum { - eProgress_UUIE_h245Address = (1 << 31), - eProgress_UUIE_h245SecurityMode = (1 << 30), - eProgress_UUIE_tokens = (1 << 29), - eProgress_UUIE_cryptoTokens = (1 << 28), - eProgress_UUIE_fastStart = (1 << 27), - eProgress_UUIE_multipleCalls = (1 << 26), - eProgress_UUIE_maintainConnection = (1 << 25), - eProgress_UUIE_fastConnectRefused = (1 << 24), - } options; - TransportAddress h245Address; - Progress_UUIE_fastStart fastStart; -} Progress_UUIE; - -typedef struct H323_UU_PDU_h323_message_body { /* CHOICE */ - enum { - eH323_UU_PDU_h323_message_body_setup, - eH323_UU_PDU_h323_message_body_callProceeding, - eH323_UU_PDU_h323_message_body_connect, - eH323_UU_PDU_h323_message_body_alerting, - eH323_UU_PDU_h323_message_body_information, - eH323_UU_PDU_h323_message_body_releaseComplete, - eH323_UU_PDU_h323_message_body_facility, - eH323_UU_PDU_h323_message_body_progress, - eH323_UU_PDU_h323_message_body_empty, - eH323_UU_PDU_h323_message_body_status, - eH323_UU_PDU_h323_message_body_statusInquiry, - eH323_UU_PDU_h323_message_body_setupAcknowledge, - eH323_UU_PDU_h323_message_body_notify, - } choice; - union { - Setup_UUIE setup; - CallProceeding_UUIE callProceeding; - Connect_UUIE connect; - Alerting_UUIE alerting; - Information_UUIE information; - Facility_UUIE facility; - Progress_UUIE progress; - }; -} H323_UU_PDU_h323_message_body; - -typedef struct RequestMessage { /* CHOICE */ - enum { - eRequestMessage_nonStandard, - eRequestMessage_masterSlaveDetermination, - eRequestMessage_terminalCapabilitySet, - eRequestMessage_openLogicalChannel, - eRequestMessage_closeLogicalChannel, - eRequestMessage_requestChannelClose, - eRequestMessage_multiplexEntrySend, - eRequestMessage_requestMultiplexEntry, - eRequestMessage_requestMode, - eRequestMessage_roundTripDelayRequest, - eRequestMessage_maintenanceLoopRequest, - eRequestMessage_communicationModeRequest, - eRequestMessage_conferenceRequest, - eRequestMessage_multilinkRequest, - eRequestMessage_logicalChannelRateRequest, - } choice; - union { - OpenLogicalChannel openLogicalChannel; - }; -} RequestMessage; - -typedef struct OpenLogicalChannelAck_reverseLogicalChannelParameters_multiplexParameters { /* CHOICE */ - enum { - eOpenLogicalChannelAck_reverseLogicalChannelParameters_multiplexParameters_h222LogicalChannelParameters, - eOpenLogicalChannelAck_reverseLogicalChannelParameters_multiplexParameters_h2250LogicalChannelParameters, - } choice; - union { - H2250LogicalChannelParameters h2250LogicalChannelParameters; - }; -} OpenLogicalChannelAck_reverseLogicalChannelParameters_multiplexParameters; - -typedef struct OpenLogicalChannelAck_reverseLogicalChannelParameters { /* SEQUENCE */ - enum { - eOpenLogicalChannelAck_reverseLogicalChannelParameters_portNumber - = (1 << 31), - eOpenLogicalChannelAck_reverseLogicalChannelParameters_multiplexParameters - = (1 << 30), - eOpenLogicalChannelAck_reverseLogicalChannelParameters_replacementFor - = (1 << 29), - } options; - OpenLogicalChannelAck_reverseLogicalChannelParameters_multiplexParameters - multiplexParameters; -} OpenLogicalChannelAck_reverseLogicalChannelParameters; - -typedef struct H2250LogicalChannelAckParameters { /* SEQUENCE */ - enum { - eH2250LogicalChannelAckParameters_nonStandard = (1 << 31), - eH2250LogicalChannelAckParameters_sessionID = (1 << 30), - eH2250LogicalChannelAckParameters_mediaChannel = (1 << 29), - eH2250LogicalChannelAckParameters_mediaControlChannel = - (1 << 28), - eH2250LogicalChannelAckParameters_dynamicRTPPayloadType = - (1 << 27), - eH2250LogicalChannelAckParameters_flowControlToZero = - (1 << 26), - eH2250LogicalChannelAckParameters_portNumber = (1 << 25), - } options; - H245_TransportAddress mediaChannel; - H245_TransportAddress mediaControlChannel; -} H2250LogicalChannelAckParameters; - -typedef struct OpenLogicalChannelAck_forwardMultiplexAckParameters { /* CHOICE */ - enum { - eOpenLogicalChannelAck_forwardMultiplexAckParameters_h2250LogicalChannelAckParameters, - } choice; - union { - H2250LogicalChannelAckParameters - h2250LogicalChannelAckParameters; - }; -} OpenLogicalChannelAck_forwardMultiplexAckParameters; - -typedef struct OpenLogicalChannelAck { /* SEQUENCE */ - enum { - eOpenLogicalChannelAck_reverseLogicalChannelParameters = - (1 << 31), - eOpenLogicalChannelAck_separateStack = (1 << 30), - eOpenLogicalChannelAck_forwardMultiplexAckParameters = - (1 << 29), - eOpenLogicalChannelAck_encryptionSync = (1 << 28), - } options; - OpenLogicalChannelAck_reverseLogicalChannelParameters - reverseLogicalChannelParameters; - OpenLogicalChannelAck_forwardMultiplexAckParameters - forwardMultiplexAckParameters; -} OpenLogicalChannelAck; - -typedef struct ResponseMessage { /* CHOICE */ - enum { - eResponseMessage_nonStandard, - eResponseMessage_masterSlaveDeterminationAck, - eResponseMessage_masterSlaveDeterminationReject, - eResponseMessage_terminalCapabilitySetAck, - eResponseMessage_terminalCapabilitySetReject, - eResponseMessage_openLogicalChannelAck, - eResponseMessage_openLogicalChannelReject, - eResponseMessage_closeLogicalChannelAck, - eResponseMessage_requestChannelCloseAck, - eResponseMessage_requestChannelCloseReject, - eResponseMessage_multiplexEntrySendAck, - eResponseMessage_multiplexEntrySendReject, - eResponseMessage_requestMultiplexEntryAck, - eResponseMessage_requestMultiplexEntryReject, - eResponseMessage_requestModeAck, - eResponseMessage_requestModeReject, - eResponseMessage_roundTripDelayResponse, - eResponseMessage_maintenanceLoopAck, - eResponseMessage_maintenanceLoopReject, - eResponseMessage_communicationModeResponse, - eResponseMessage_conferenceResponse, - eResponseMessage_multilinkResponse, - eResponseMessage_logicalChannelRateAcknowledge, - eResponseMessage_logicalChannelRateReject, - } choice; - union { - OpenLogicalChannelAck openLogicalChannelAck; - }; -} ResponseMessage; - -typedef struct MultimediaSystemControlMessage { /* CHOICE */ - enum { - eMultimediaSystemControlMessage_request, - eMultimediaSystemControlMessage_response, - eMultimediaSystemControlMessage_command, - eMultimediaSystemControlMessage_indication, - } choice; - union { - RequestMessage request; - ResponseMessage response; - }; -} MultimediaSystemControlMessage; - -typedef struct H323_UU_PDU_h245Control { /* SEQUENCE OF */ - int count; - MultimediaSystemControlMessage item[4]; -} H323_UU_PDU_h245Control; - -typedef struct H323_UU_PDU { /* SEQUENCE */ - enum { - eH323_UU_PDU_nonStandardData = (1 << 31), - eH323_UU_PDU_h4501SupplementaryService = (1 << 30), - eH323_UU_PDU_h245Tunneling = (1 << 29), - eH323_UU_PDU_h245Control = (1 << 28), - eH323_UU_PDU_nonStandardControl = (1 << 27), - eH323_UU_PDU_callLinkage = (1 << 26), - eH323_UU_PDU_tunnelledSignallingMessage = (1 << 25), - eH323_UU_PDU_provisionalRespToH245Tunneling = (1 << 24), - eH323_UU_PDU_stimulusControl = (1 << 23), - eH323_UU_PDU_genericData = (1 << 22), - } options; - H323_UU_PDU_h323_message_body h323_message_body; - H323_UU_PDU_h245Control h245Control; -} H323_UU_PDU; - -typedef struct H323_UserInformation { /* SEQUENCE */ - enum { - eH323_UserInformation_user_data = (1 << 31), - } options; - H323_UU_PDU h323_uu_pdu; -} H323_UserInformation; - -typedef struct GatekeeperRequest { /* SEQUENCE */ - enum { - eGatekeeperRequest_nonStandardData = (1 << 31), - eGatekeeperRequest_gatekeeperIdentifier = (1 << 30), - eGatekeeperRequest_callServices = (1 << 29), - eGatekeeperRequest_endpointAlias = (1 << 28), - eGatekeeperRequest_alternateEndpoints = (1 << 27), - eGatekeeperRequest_tokens = (1 << 26), - eGatekeeperRequest_cryptoTokens = (1 << 25), - eGatekeeperRequest_authenticationCapability = (1 << 24), - eGatekeeperRequest_algorithmOIDs = (1 << 23), - eGatekeeperRequest_integrity = (1 << 22), - eGatekeeperRequest_integrityCheckValue = (1 << 21), - eGatekeeperRequest_supportsAltGK = (1 << 20), - eGatekeeperRequest_featureSet = (1 << 19), - eGatekeeperRequest_genericData = (1 << 18), - } options; - TransportAddress rasAddress; -} GatekeeperRequest; - -typedef struct GatekeeperConfirm { /* SEQUENCE */ - enum { - eGatekeeperConfirm_nonStandardData = (1 << 31), - eGatekeeperConfirm_gatekeeperIdentifier = (1 << 30), - eGatekeeperConfirm_alternateGatekeeper = (1 << 29), - eGatekeeperConfirm_authenticationMode = (1 << 28), - eGatekeeperConfirm_tokens = (1 << 27), - eGatekeeperConfirm_cryptoTokens = (1 << 26), - eGatekeeperConfirm_algorithmOID = (1 << 25), - eGatekeeperConfirm_integrity = (1 << 24), - eGatekeeperConfirm_integrityCheckValue = (1 << 23), - eGatekeeperConfirm_featureSet = (1 << 22), - eGatekeeperConfirm_genericData = (1 << 21), - } options; - TransportAddress rasAddress; -} GatekeeperConfirm; - -typedef struct RegistrationRequest_callSignalAddress { /* SEQUENCE OF */ - int count; - TransportAddress item[10]; -} RegistrationRequest_callSignalAddress; - -typedef struct RegistrationRequest_rasAddress { /* SEQUENCE OF */ - int count; - TransportAddress item[10]; -} RegistrationRequest_rasAddress; - -typedef struct RegistrationRequest { /* SEQUENCE */ - enum { - eRegistrationRequest_nonStandardData = (1 << 31), - eRegistrationRequest_terminalAlias = (1 << 30), - eRegistrationRequest_gatekeeperIdentifier = (1 << 29), - eRegistrationRequest_alternateEndpoints = (1 << 28), - eRegistrationRequest_timeToLive = (1 << 27), - eRegistrationRequest_tokens = (1 << 26), - eRegistrationRequest_cryptoTokens = (1 << 25), - eRegistrationRequest_integrityCheckValue = (1 << 24), - eRegistrationRequest_keepAlive = (1 << 23), - eRegistrationRequest_endpointIdentifier = (1 << 22), - eRegistrationRequest_willSupplyUUIEs = (1 << 21), - eRegistrationRequest_maintainConnection = (1 << 20), - eRegistrationRequest_alternateTransportAddresses = (1 << 19), - eRegistrationRequest_additiveRegistration = (1 << 18), - eRegistrationRequest_terminalAliasPattern = (1 << 17), - eRegistrationRequest_supportsAltGK = (1 << 16), - eRegistrationRequest_usageReportingCapability = (1 << 15), - eRegistrationRequest_multipleCalls = (1 << 14), - eRegistrationRequest_supportedH248Packages = (1 << 13), - eRegistrationRequest_callCreditCapability = (1 << 12), - eRegistrationRequest_capacityReportingCapability = (1 << 11), - eRegistrationRequest_capacity = (1 << 10), - eRegistrationRequest_featureSet = (1 << 9), - eRegistrationRequest_genericData = (1 << 8), - } options; - RegistrationRequest_callSignalAddress callSignalAddress; - RegistrationRequest_rasAddress rasAddress; - unsigned timeToLive; -} RegistrationRequest; - -typedef struct RegistrationConfirm_callSignalAddress { /* SEQUENCE OF */ - int count; - TransportAddress item[10]; -} RegistrationConfirm_callSignalAddress; - -typedef struct RegistrationConfirm { /* SEQUENCE */ - enum { - eRegistrationConfirm_nonStandardData = (1 << 31), - eRegistrationConfirm_terminalAlias = (1 << 30), - eRegistrationConfirm_gatekeeperIdentifier = (1 << 29), - eRegistrationConfirm_alternateGatekeeper = (1 << 28), - eRegistrationConfirm_timeToLive = (1 << 27), - eRegistrationConfirm_tokens = (1 << 26), - eRegistrationConfirm_cryptoTokens = (1 << 25), - eRegistrationConfirm_integrityCheckValue = (1 << 24), - eRegistrationConfirm_willRespondToIRR = (1 << 23), - eRegistrationConfirm_preGrantedARQ = (1 << 22), - eRegistrationConfirm_maintainConnection = (1 << 21), - eRegistrationConfirm_serviceControl = (1 << 20), - eRegistrationConfirm_supportsAdditiveRegistration = (1 << 19), - eRegistrationConfirm_terminalAliasPattern = (1 << 18), - eRegistrationConfirm_supportedPrefixes = (1 << 17), - eRegistrationConfirm_usageSpec = (1 << 16), - eRegistrationConfirm_featureServerAlias = (1 << 15), - eRegistrationConfirm_capacityReportingSpec = (1 << 14), - eRegistrationConfirm_featureSet = (1 << 13), - eRegistrationConfirm_genericData = (1 << 12), - } options; - RegistrationConfirm_callSignalAddress callSignalAddress; - unsigned timeToLive; -} RegistrationConfirm; - -typedef struct UnregistrationRequest_callSignalAddress { /* SEQUENCE OF */ - int count; - TransportAddress item[10]; -} UnregistrationRequest_callSignalAddress; - -typedef struct UnregistrationRequest { /* SEQUENCE */ - enum { - eUnregistrationRequest_endpointAlias = (1 << 31), - eUnregistrationRequest_nonStandardData = (1 << 30), - eUnregistrationRequest_endpointIdentifier = (1 << 29), - eUnregistrationRequest_alternateEndpoints = (1 << 28), - eUnregistrationRequest_gatekeeperIdentifier = (1 << 27), - eUnregistrationRequest_tokens = (1 << 26), - eUnregistrationRequest_cryptoTokens = (1 << 25), - eUnregistrationRequest_integrityCheckValue = (1 << 24), - eUnregistrationRequest_reason = (1 << 23), - eUnregistrationRequest_endpointAliasPattern = (1 << 22), - eUnregistrationRequest_supportedPrefixes = (1 << 21), - eUnregistrationRequest_alternateGatekeeper = (1 << 20), - eUnregistrationRequest_genericData = (1 << 19), - } options; - UnregistrationRequest_callSignalAddress callSignalAddress; -} UnregistrationRequest; - -typedef struct AdmissionRequest { /* SEQUENCE */ - enum { - eAdmissionRequest_callModel = (1 << 31), - eAdmissionRequest_destinationInfo = (1 << 30), - eAdmissionRequest_destCallSignalAddress = (1 << 29), - eAdmissionRequest_destExtraCallInfo = (1 << 28), - eAdmissionRequest_srcCallSignalAddress = (1 << 27), - eAdmissionRequest_nonStandardData = (1 << 26), - eAdmissionRequest_callServices = (1 << 25), - eAdmissionRequest_canMapAlias = (1 << 24), - eAdmissionRequest_callIdentifier = (1 << 23), - eAdmissionRequest_srcAlternatives = (1 << 22), - eAdmissionRequest_destAlternatives = (1 << 21), - eAdmissionRequest_gatekeeperIdentifier = (1 << 20), - eAdmissionRequest_tokens = (1 << 19), - eAdmissionRequest_cryptoTokens = (1 << 18), - eAdmissionRequest_integrityCheckValue = (1 << 17), - eAdmissionRequest_transportQOS = (1 << 16), - eAdmissionRequest_willSupplyUUIEs = (1 << 15), - eAdmissionRequest_callLinkage = (1 << 14), - eAdmissionRequest_gatewayDataRate = (1 << 13), - eAdmissionRequest_capacity = (1 << 12), - eAdmissionRequest_circuitInfo = (1 << 11), - eAdmissionRequest_desiredProtocols = (1 << 10), - eAdmissionRequest_desiredTunnelledProtocol = (1 << 9), - eAdmissionRequest_featureSet = (1 << 8), - eAdmissionRequest_genericData = (1 << 7), - } options; - TransportAddress destCallSignalAddress; - TransportAddress srcCallSignalAddress; -} AdmissionRequest; - -typedef struct AdmissionConfirm { /* SEQUENCE */ - enum { - eAdmissionConfirm_irrFrequency = (1 << 31), - eAdmissionConfirm_nonStandardData = (1 << 30), - eAdmissionConfirm_destinationInfo = (1 << 29), - eAdmissionConfirm_destExtraCallInfo = (1 << 28), - eAdmissionConfirm_destinationType = (1 << 27), - eAdmissionConfirm_remoteExtensionAddress = (1 << 26), - eAdmissionConfirm_alternateEndpoints = (1 << 25), - eAdmissionConfirm_tokens = (1 << 24), - eAdmissionConfirm_cryptoTokens = (1 << 23), - eAdmissionConfirm_integrityCheckValue = (1 << 22), - eAdmissionConfirm_transportQOS = (1 << 21), - eAdmissionConfirm_willRespondToIRR = (1 << 20), - eAdmissionConfirm_uuiesRequested = (1 << 19), - eAdmissionConfirm_language = (1 << 18), - eAdmissionConfirm_alternateTransportAddresses = (1 << 17), - eAdmissionConfirm_useSpecifiedTransport = (1 << 16), - eAdmissionConfirm_circuitInfo = (1 << 15), - eAdmissionConfirm_usageSpec = (1 << 14), - eAdmissionConfirm_supportedProtocols = (1 << 13), - eAdmissionConfirm_serviceControl = (1 << 12), - eAdmissionConfirm_multipleCalls = (1 << 11), - eAdmissionConfirm_featureSet = (1 << 10), - eAdmissionConfirm_genericData = (1 << 9), - } options; - TransportAddress destCallSignalAddress; -} AdmissionConfirm; - -typedef struct LocationRequest { /* SEQUENCE */ - enum { - eLocationRequest_endpointIdentifier = (1 << 31), - eLocationRequest_nonStandardData = (1 << 30), - eLocationRequest_sourceInfo = (1 << 29), - eLocationRequest_canMapAlias = (1 << 28), - eLocationRequest_gatekeeperIdentifier = (1 << 27), - eLocationRequest_tokens = (1 << 26), - eLocationRequest_cryptoTokens = (1 << 25), - eLocationRequest_integrityCheckValue = (1 << 24), - eLocationRequest_desiredProtocols = (1 << 23), - eLocationRequest_desiredTunnelledProtocol = (1 << 22), - eLocationRequest_featureSet = (1 << 21), - eLocationRequest_genericData = (1 << 20), - eLocationRequest_hopCount = (1 << 19), - eLocationRequest_circuitInfo = (1 << 18), - } options; - TransportAddress replyAddress; -} LocationRequest; - -typedef struct LocationConfirm { /* SEQUENCE */ - enum { - eLocationConfirm_nonStandardData = (1 << 31), - eLocationConfirm_destinationInfo = (1 << 30), - eLocationConfirm_destExtraCallInfo = (1 << 29), - eLocationConfirm_destinationType = (1 << 28), - eLocationConfirm_remoteExtensionAddress = (1 << 27), - eLocationConfirm_alternateEndpoints = (1 << 26), - eLocationConfirm_tokens = (1 << 25), - eLocationConfirm_cryptoTokens = (1 << 24), - eLocationConfirm_integrityCheckValue = (1 << 23), - eLocationConfirm_alternateTransportAddresses = (1 << 22), - eLocationConfirm_supportedProtocols = (1 << 21), - eLocationConfirm_multipleCalls = (1 << 20), - eLocationConfirm_featureSet = (1 << 19), - eLocationConfirm_genericData = (1 << 18), - eLocationConfirm_circuitInfo = (1 << 17), - eLocationConfirm_serviceControl = (1 << 16), - } options; - TransportAddress callSignalAddress; - TransportAddress rasAddress; -} LocationConfirm; - -typedef struct InfoRequestResponse_callSignalAddress { /* SEQUENCE OF */ - int count; - TransportAddress item[10]; -} InfoRequestResponse_callSignalAddress; - -typedef struct InfoRequestResponse { /* SEQUENCE */ - enum { - eInfoRequestResponse_nonStandardData = (1 << 31), - eInfoRequestResponse_endpointAlias = (1 << 30), - eInfoRequestResponse_perCallInfo = (1 << 29), - eInfoRequestResponse_tokens = (1 << 28), - eInfoRequestResponse_cryptoTokens = (1 << 27), - eInfoRequestResponse_integrityCheckValue = (1 << 26), - eInfoRequestResponse_needResponse = (1 << 25), - eInfoRequestResponse_capacity = (1 << 24), - eInfoRequestResponse_irrStatus = (1 << 23), - eInfoRequestResponse_unsolicited = (1 << 22), - eInfoRequestResponse_genericData = (1 << 21), - } options; - TransportAddress rasAddress; - InfoRequestResponse_callSignalAddress callSignalAddress; -} InfoRequestResponse; - -typedef struct RasMessage { /* CHOICE */ - enum { - eRasMessage_gatekeeperRequest, - eRasMessage_gatekeeperConfirm, - eRasMessage_gatekeeperReject, - eRasMessage_registrationRequest, - eRasMessage_registrationConfirm, - eRasMessage_registrationReject, - eRasMessage_unregistrationRequest, - eRasMessage_unregistrationConfirm, - eRasMessage_unregistrationReject, - eRasMessage_admissionRequest, - eRasMessage_admissionConfirm, - eRasMessage_admissionReject, - eRasMessage_bandwidthRequest, - eRasMessage_bandwidthConfirm, - eRasMessage_bandwidthReject, - eRasMessage_disengageRequest, - eRasMessage_disengageConfirm, - eRasMessage_disengageReject, - eRasMessage_locationRequest, - eRasMessage_locationConfirm, - eRasMessage_locationReject, - eRasMessage_infoRequest, - eRasMessage_infoRequestResponse, - eRasMessage_nonStandardMessage, - eRasMessage_unknownMessageResponse, - eRasMessage_requestInProgress, - eRasMessage_resourcesAvailableIndicate, - eRasMessage_resourcesAvailableConfirm, - eRasMessage_infoRequestAck, - eRasMessage_infoRequestNak, - eRasMessage_serviceControlIndication, - eRasMessage_serviceControlResponse, - } choice; - union { - GatekeeperRequest gatekeeperRequest; - GatekeeperConfirm gatekeeperConfirm; - RegistrationRequest registrationRequest; - RegistrationConfirm registrationConfirm; - UnregistrationRequest unregistrationRequest; - AdmissionRequest admissionRequest; - AdmissionConfirm admissionConfirm; - LocationRequest locationRequest; - LocationConfirm locationConfirm; - InfoRequestResponse infoRequestResponse; - }; -} RasMessage; -- cgit v1.2.3 From 869f37d8e48f3911eb70f38a994feaa8f8380008 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Sat, 2 Dec 2006 22:09:06 -0800 Subject: [NETFILTER]: nf_conntrack/nf_nat: add IRC helper port Add nf_conntrack port of the IRC conntrack/NAT helper. Since DCC doesn't support IPv6 yet, the helper is still IPv4 only. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter/nf_conntrack_irc.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) create mode 100644 include/linux/netfilter/nf_conntrack_irc.h (limited to 'include/linux') diff --git a/include/linux/netfilter/nf_conntrack_irc.h b/include/linux/netfilter/nf_conntrack_irc.h new file mode 100644 index 000000000000..2ab6b8255911 --- /dev/null +++ b/include/linux/netfilter/nf_conntrack_irc.h @@ -0,0 +1,15 @@ +#ifndef _NF_CONNTRACK_IRC_H +#define _NF_CONNTRACK_IRC_H + +#ifdef __KERNEL__ + +#define IRC_PORT 6667 + +extern unsigned int (*nf_nat_irc_hook)(struct sk_buff **pskb, + enum ip_conntrack_info ctinfo, + unsigned int matchoff, + unsigned int matchlen, + struct nf_conntrack_expect *exp); + +#endif /* __KERNEL__ */ +#endif /* _NF_CONNTRACK_IRC_H */ -- cgit v1.2.3 From f09943fefe6b702e40893d35b4f10fd1064037fe Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Sat, 2 Dec 2006 22:09:41 -0800 Subject: [NETFILTER]: nf_conntrack/nf_nat: add PPTP helper port Add nf_conntrack port of the PPtP conntrack/NAT helper. Since there seems to be no IPv6-capable PPtP implementation the helper only support IPv4. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter/nf_conntrack_pptp.h | 321 +++++++++++++++++++++++ include/linux/netfilter/nf_conntrack_proto_gre.h | 112 ++++++++ 2 files changed, 433 insertions(+) create mode 100644 include/linux/netfilter/nf_conntrack_pptp.h create mode 100644 include/linux/netfilter/nf_conntrack_proto_gre.h (limited to 'include/linux') diff --git a/include/linux/netfilter/nf_conntrack_pptp.h b/include/linux/netfilter/nf_conntrack_pptp.h new file mode 100644 index 000000000000..fb049ec11ff2 --- /dev/null +++ b/include/linux/netfilter/nf_conntrack_pptp.h @@ -0,0 +1,321 @@ +/* PPTP constants and structs */ +#ifndef _NF_CONNTRACK_PPTP_H +#define _NF_CONNTRACK_PPTP_H + +/* state of the control session */ +enum pptp_ctrlsess_state { + PPTP_SESSION_NONE, /* no session present */ + PPTP_SESSION_ERROR, /* some session error */ + PPTP_SESSION_STOPREQ, /* stop_sess request seen */ + PPTP_SESSION_REQUESTED, /* start_sess request seen */ + PPTP_SESSION_CONFIRMED, /* session established */ +}; + +/* state of the call inside the control session */ +enum pptp_ctrlcall_state { + PPTP_CALL_NONE, + PPTP_CALL_ERROR, + PPTP_CALL_OUT_REQ, + PPTP_CALL_OUT_CONF, + PPTP_CALL_IN_REQ, + PPTP_CALL_IN_REP, + PPTP_CALL_IN_CONF, + PPTP_CALL_CLEAR_REQ, +}; + +/* conntrack private data */ +struct nf_ct_pptp_master { + enum pptp_ctrlsess_state sstate; /* session state */ + enum pptp_ctrlcall_state cstate; /* call state */ + __be16 pac_call_id; /* call id of PAC */ + __be16 pns_call_id; /* call id of PNS */ + + /* in pre-2.6.11 this used to be per-expect. Now it is per-conntrack + * and therefore imposes a fixed limit on the number of maps */ + struct nf_ct_gre_keymap *keymap[IP_CT_DIR_MAX]; +}; + +struct nf_nat_pptp { + __be16 pns_call_id; /* NAT'ed PNS call id */ + __be16 pac_call_id; /* NAT'ed PAC call id */ +}; + +#ifdef __KERNEL__ + +#define PPTP_CONTROL_PORT 1723 + +#define PPTP_PACKET_CONTROL 1 +#define PPTP_PACKET_MGMT 2 + +#define PPTP_MAGIC_COOKIE 0x1a2b3c4d + +struct pptp_pkt_hdr { + __u16 packetLength; + __be16 packetType; + __be32 magicCookie; +}; + +/* PptpControlMessageType values */ +#define PPTP_START_SESSION_REQUEST 1 +#define PPTP_START_SESSION_REPLY 2 +#define PPTP_STOP_SESSION_REQUEST 3 +#define PPTP_STOP_SESSION_REPLY 4 +#define PPTP_ECHO_REQUEST 5 +#define PPTP_ECHO_REPLY 6 +#define PPTP_OUT_CALL_REQUEST 7 +#define PPTP_OUT_CALL_REPLY 8 +#define PPTP_IN_CALL_REQUEST 9 +#define PPTP_IN_CALL_REPLY 10 +#define PPTP_IN_CALL_CONNECT 11 +#define PPTP_CALL_CLEAR_REQUEST 12 +#define PPTP_CALL_DISCONNECT_NOTIFY 13 +#define PPTP_WAN_ERROR_NOTIFY 14 +#define PPTP_SET_LINK_INFO 15 + +#define PPTP_MSG_MAX 15 + +/* PptpGeneralError values */ +#define PPTP_ERROR_CODE_NONE 0 +#define PPTP_NOT_CONNECTED 1 +#define PPTP_BAD_FORMAT 2 +#define PPTP_BAD_VALUE 3 +#define PPTP_NO_RESOURCE 4 +#define PPTP_BAD_CALLID 5 +#define PPTP_REMOVE_DEVICE_ERROR 6 + +struct PptpControlHeader { + __be16 messageType; + __u16 reserved; +}; + +/* FramingCapability Bitmap Values */ +#define PPTP_FRAME_CAP_ASYNC 0x1 +#define PPTP_FRAME_CAP_SYNC 0x2 + +/* BearerCapability Bitmap Values */ +#define PPTP_BEARER_CAP_ANALOG 0x1 +#define PPTP_BEARER_CAP_DIGITAL 0x2 + +struct PptpStartSessionRequest { + __be16 protocolVersion; + __u16 reserved1; + __be32 framingCapability; + __be32 bearerCapability; + __be16 maxChannels; + __be16 firmwareRevision; + __u8 hostName[64]; + __u8 vendorString[64]; +}; + +/* PptpStartSessionResultCode Values */ +#define PPTP_START_OK 1 +#define PPTP_START_GENERAL_ERROR 2 +#define PPTP_START_ALREADY_CONNECTED 3 +#define PPTP_START_NOT_AUTHORIZED 4 +#define PPTP_START_UNKNOWN_PROTOCOL 5 + +struct PptpStartSessionReply { + __be16 protocolVersion; + __u8 resultCode; + __u8 generalErrorCode; + __be32 framingCapability; + __be32 bearerCapability; + __be16 maxChannels; + __be16 firmwareRevision; + __u8 hostName[64]; + __u8 vendorString[64]; +}; + +/* PptpStopReasons */ +#define PPTP_STOP_NONE 1 +#define PPTP_STOP_PROTOCOL 2 +#define PPTP_STOP_LOCAL_SHUTDOWN 3 + +struct PptpStopSessionRequest { + __u8 reason; + __u8 reserved1; + __u16 reserved2; +}; + +/* PptpStopSessionResultCode */ +#define PPTP_STOP_OK 1 +#define PPTP_STOP_GENERAL_ERROR 2 + +struct PptpStopSessionReply { + __u8 resultCode; + __u8 generalErrorCode; + __u16 reserved1; +}; + +struct PptpEchoRequest { + __be32 identNumber; +}; + +/* PptpEchoReplyResultCode */ +#define PPTP_ECHO_OK 1 +#define PPTP_ECHO_GENERAL_ERROR 2 + +struct PptpEchoReply { + __be32 identNumber; + __u8 resultCode; + __u8 generalErrorCode; + __u16 reserved; +}; + +/* PptpFramingType */ +#define PPTP_ASYNC_FRAMING 1 +#define PPTP_SYNC_FRAMING 2 +#define PPTP_DONT_CARE_FRAMING 3 + +/* PptpCallBearerType */ +#define PPTP_ANALOG_TYPE 1 +#define PPTP_DIGITAL_TYPE 2 +#define PPTP_DONT_CARE_BEARER_TYPE 3 + +struct PptpOutCallRequest { + __be16 callID; + __be16 callSerialNumber; + __be32 minBPS; + __be32 maxBPS; + __be32 bearerType; + __be32 framingType; + __be16 packetWindow; + __be16 packetProcDelay; + __be16 phoneNumberLength; + __u16 reserved1; + __u8 phoneNumber[64]; + __u8 subAddress[64]; +}; + +/* PptpCallResultCode */ +#define PPTP_OUTCALL_CONNECT 1 +#define PPTP_OUTCALL_GENERAL_ERROR 2 +#define PPTP_OUTCALL_NO_CARRIER 3 +#define PPTP_OUTCALL_BUSY 4 +#define PPTP_OUTCALL_NO_DIAL_TONE 5 +#define PPTP_OUTCALL_TIMEOUT 6 +#define PPTP_OUTCALL_DONT_ACCEPT 7 + +struct PptpOutCallReply { + __be16 callID; + __be16 peersCallID; + __u8 resultCode; + __u8 generalErrorCode; + __be16 causeCode; + __be32 connectSpeed; + __be16 packetWindow; + __be16 packetProcDelay; + __be32 physChannelID; +}; + +struct PptpInCallRequest { + __be16 callID; + __be16 callSerialNumber; + __be32 callBearerType; + __be32 physChannelID; + __be16 dialedNumberLength; + __be16 dialingNumberLength; + __u8 dialedNumber[64]; + __u8 dialingNumber[64]; + __u8 subAddress[64]; +}; + +/* PptpInCallResultCode */ +#define PPTP_INCALL_ACCEPT 1 +#define PPTP_INCALL_GENERAL_ERROR 2 +#define PPTP_INCALL_DONT_ACCEPT 3 + +struct PptpInCallReply { + __be16 callID; + __be16 peersCallID; + __u8 resultCode; + __u8 generalErrorCode; + __be16 packetWindow; + __be16 packetProcDelay; + __u16 reserved; +}; + +struct PptpInCallConnected { + __be16 peersCallID; + __u16 reserved; + __be32 connectSpeed; + __be16 packetWindow; + __be16 packetProcDelay; + __be32 callFramingType; +}; + +struct PptpClearCallRequest { + __be16 callID; + __u16 reserved; +}; + +struct PptpCallDisconnectNotify { + __be16 callID; + __u8 resultCode; + __u8 generalErrorCode; + __be16 causeCode; + __u16 reserved; + __u8 callStatistics[128]; +}; + +struct PptpWanErrorNotify { + __be16 peersCallID; + __u16 reserved; + __be32 crcErrors; + __be32 framingErrors; + __be32 hardwareOverRuns; + __be32 bufferOverRuns; + __be32 timeoutErrors; + __be32 alignmentErrors; +}; + +struct PptpSetLinkInfo { + __be16 peersCallID; + __u16 reserved; + __be32 sendAccm; + __be32 recvAccm; +}; + +union pptp_ctrl_union { + struct PptpStartSessionRequest sreq; + struct PptpStartSessionReply srep; + struct PptpStopSessionRequest streq; + struct PptpStopSessionReply strep; + struct PptpOutCallRequest ocreq; + struct PptpOutCallReply ocack; + struct PptpInCallRequest icreq; + struct PptpInCallReply icack; + struct PptpInCallConnected iccon; + struct PptpClearCallRequest clrreq; + struct PptpCallDisconnectNotify disc; + struct PptpWanErrorNotify wanerr; + struct PptpSetLinkInfo setlink; +}; + +/* crap needed for nf_conntrack_compat.h */ +struct nf_conn; +struct nf_conntrack_expect; +enum ip_conntrack_info; + +extern int +(*nf_nat_pptp_hook_outbound)(struct sk_buff **pskb, + struct nf_conn *ct, enum ip_conntrack_info ctinfo, + struct PptpControlHeader *ctlh, + union pptp_ctrl_union *pptpReq); + +extern int +(*nf_nat_pptp_hook_inbound)(struct sk_buff **pskb, + struct nf_conn *ct, enum ip_conntrack_info ctinfo, + struct PptpControlHeader *ctlh, + union pptp_ctrl_union *pptpReq); + +extern void +(*nf_nat_pptp_hook_exp_gre)(struct nf_conntrack_expect *exp_orig, + struct nf_conntrack_expect *exp_reply); + +extern void +(*nf_nat_pptp_hook_expectfn)(struct nf_conn *ct, + struct nf_conntrack_expect *exp); + +#endif /* __KERNEL__ */ +#endif /* _NF_CONNTRACK_PPTP_H */ diff --git a/include/linux/netfilter/nf_conntrack_proto_gre.h b/include/linux/netfilter/nf_conntrack_proto_gre.h new file mode 100644 index 000000000000..4e6bbce04ff8 --- /dev/null +++ b/include/linux/netfilter/nf_conntrack_proto_gre.h @@ -0,0 +1,112 @@ +#ifndef _CONNTRACK_PROTO_GRE_H +#define _CONNTRACK_PROTO_GRE_H +#include + +/* GRE PROTOCOL HEADER */ + +/* GRE Version field */ +#define GRE_VERSION_1701 0x0 +#define GRE_VERSION_PPTP 0x1 + +/* GRE Protocol field */ +#define GRE_PROTOCOL_PPTP 0x880B + +/* GRE Flags */ +#define GRE_FLAG_C 0x80 +#define GRE_FLAG_R 0x40 +#define GRE_FLAG_K 0x20 +#define GRE_FLAG_S 0x10 +#define GRE_FLAG_A 0x80 + +#define GRE_IS_C(f) ((f)&GRE_FLAG_C) +#define GRE_IS_R(f) ((f)&GRE_FLAG_R) +#define GRE_IS_K(f) ((f)&GRE_FLAG_K) +#define GRE_IS_S(f) ((f)&GRE_FLAG_S) +#define GRE_IS_A(f) ((f)&GRE_FLAG_A) + +/* GRE is a mess: Four different standards */ +struct gre_hdr { +#if defined(__LITTLE_ENDIAN_BITFIELD) + __u16 rec:3, + srr:1, + seq:1, + key:1, + routing:1, + csum:1, + version:3, + reserved:4, + ack:1; +#elif defined(__BIG_ENDIAN_BITFIELD) + __u16 csum:1, + routing:1, + key:1, + seq:1, + srr:1, + rec:3, + ack:1, + reserved:4, + version:3; +#else +#error "Adjust your defines" +#endif + __be16 protocol; +}; + +/* modified GRE header for PPTP */ +struct gre_hdr_pptp { + __u8 flags; /* bitfield */ + __u8 version; /* should be GRE_VERSION_PPTP */ + __be16 protocol; /* should be GRE_PROTOCOL_PPTP */ + __be16 payload_len; /* size of ppp payload, not inc. gre header */ + __be16 call_id; /* peer's call_id for this session */ + __be32 seq; /* sequence number. Present if S==1 */ + __be32 ack; /* seq number of highest packet recieved by */ + /* sender in this session */ +}; + +struct nf_ct_gre { + unsigned int stream_timeout; + unsigned int timeout; +}; + +#ifdef __KERNEL__ +#include + +struct nf_conn; + +/* structure for original <-> reply keymap */ +struct nf_ct_gre_keymap { + struct list_head list; + struct nf_conntrack_tuple tuple; +}; + +/* add new tuple->key_reply pair to keymap */ +int nf_ct_gre_keymap_add(struct nf_conn *ct, enum ip_conntrack_dir dir, + struct nf_conntrack_tuple *t); + +/* delete keymap entries */ +void nf_ct_gre_keymap_destroy(struct nf_conn *ct); + +/* get pointer to gre key, if present */ +static inline __be32 *gre_key(struct gre_hdr *greh) +{ + if (!greh->key) + return NULL; + if (greh->csum || greh->routing) + return (__be32 *)(greh+sizeof(*greh)+4); + return (__be32 *)(greh+sizeof(*greh)); +} + +/* get pointer ot gre csum, if present */ +static inline __sum16 *gre_csum(struct gre_hdr *greh) +{ + if (!greh->csum) + return NULL; + return (__sum16 *)(greh+sizeof(*greh)); +} + +extern void nf_ct_gre_keymap_flush(void); +extern void nf_nat_need_gre(void); + +#endif /* __KERNEL__ */ +#endif /* _CONNTRACK_PROTO_GRE_H */ -- cgit v1.2.3 From 9fafcd7b203229c3f3893a475741afc27e276306 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Sat, 2 Dec 2006 22:09:57 -0800 Subject: [NETFILTER]: nf_conntrack/nf_nat: add SIP helper port Add IPv4 and IPv6 capable nf_conntrack port of the SIP conntrack/NAT helper. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter/nf_conntrack_sip.h | 41 ++++++++++++++++++++++++++++++ 1 file changed, 41 insertions(+) create mode 100644 include/linux/netfilter/nf_conntrack_sip.h (limited to 'include/linux') diff --git a/include/linux/netfilter/nf_conntrack_sip.h b/include/linux/netfilter/nf_conntrack_sip.h new file mode 100644 index 000000000000..bb7f2041db74 --- /dev/null +++ b/include/linux/netfilter/nf_conntrack_sip.h @@ -0,0 +1,41 @@ +#ifndef __NF_CONNTRACK_SIP_H__ +#define __NF_CONNTRACK_SIP_H__ +#ifdef __KERNEL__ + +#define SIP_PORT 5060 +#define SIP_TIMEOUT 3600 + +enum sip_header_pos { + POS_REG_REQ_URI, + POS_REQ_URI, + POS_FROM, + POS_TO, + POS_VIA, + POS_CONTACT, + POS_CONTENT, + POS_MEDIA, + POS_OWNER_IP4, + POS_CONNECTION_IP4, + POS_OWNER_IP6, + POS_CONNECTION_IP6, + POS_SDP_HEADER, +}; + +extern unsigned int (*nf_nat_sip_hook)(struct sk_buff **pskb, + enum ip_conntrack_info ctinfo, + struct nf_conn *ct, + const char **dptr); +extern unsigned int (*nf_nat_sdp_hook)(struct sk_buff **pskb, + enum ip_conntrack_info ctinfo, + struct nf_conntrack_expect *exp, + const char *dptr); + +extern int ct_sip_get_info(struct nf_conn *ct, const char *dptr, size_t dlen, + unsigned int *matchoff, unsigned int *matchlen, + enum sip_header_pos pos); +extern int ct_sip_lnlen(const char *line, const char *limit); +extern const char *ct_sip_search(const char *needle, const char *haystack, + size_t needle_len, size_t haystack_len, + int case_sensitive); +#endif /* __KERNEL__ */ +#endif /* __NF_CONNTRACK_SIP_H__ */ -- cgit v1.2.3 From a536df35b3a58caa9015bf7887a374b20f658368 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Sat, 2 Dec 2006 22:10:18 -0800 Subject: [NETFILTER]: nf_conntrack/nf_nat: add TFTP helper port Add IPv4 and IPv6 capable nf_conntrack port of the TFTP conntrack/NAT helper. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter/nf_conntrack_tftp.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) create mode 100644 include/linux/netfilter/nf_conntrack_tftp.h (limited to 'include/linux') diff --git a/include/linux/netfilter/nf_conntrack_tftp.h b/include/linux/netfilter/nf_conntrack_tftp.h new file mode 100644 index 000000000000..0d79b7ae051f --- /dev/null +++ b/include/linux/netfilter/nf_conntrack_tftp.h @@ -0,0 +1,20 @@ +#ifndef _NF_CONNTRACK_TFTP_H +#define _NF_CONNTRACK_TFTP_H + +#define TFTP_PORT 69 + +struct tftphdr { + __be16 opcode; +}; + +#define TFTP_OPCODE_READ 1 +#define TFTP_OPCODE_WRITE 2 +#define TFTP_OPCODE_DATA 3 +#define TFTP_OPCODE_ACK 4 +#define TFTP_OPCODE_ERROR 5 + +extern unsigned int (*nf_nat_tftp_hook)(struct sk_buff **pskb, + enum ip_conntrack_info ctinfo, + struct nf_conntrack_expect *exp); + +#endif /* _NF_CONNTRACK_TFTP_H */ -- cgit v1.2.3 From 2b5f6dcce5bf94b9b119e9ed8d537098ec61c3d2 Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Sat, 2 Dec 2006 22:22:25 -0800 Subject: [XFRM]: Fix aevent structuring to be more complete. aevents can not uniquely identify an SA. We break the ABI with this patch, but consensus is that since it is not yet utilized by any (known) application then it is fine (better do it now than later). Signed-off-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/linux/xfrm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/xfrm.h b/include/linux/xfrm.h index 7907c42bd4e4..088ba8113f7e 100644 --- a/include/linux/xfrm.h +++ b/include/linux/xfrm.h @@ -289,7 +289,9 @@ struct xfrm_usersa_id { struct xfrm_aevent_id { struct xfrm_usersa_id sa_id; + xfrm_address_t saddr; __u32 flags; + __u32 reqid; }; struct xfrm_userspi_info { -- cgit v1.2.3 From 582982e6991d6718ddadf8751072b50a850dde48 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 17 Nov 2006 12:05:11 +0900 Subject: [PATCH] libata: remove unused HSM_ST_UNKNOWN HSM_ST_UNKNOWN is not used anywhere. Its value is zero and supposed to serve sanity check purpose but HSM_ST_IDLE is used for that purpose. This unused state causes confusion. After a port is initialized but before the first command is executed, the idle hsm state is UNKNOWN. However, once a command has completed, the idle hsm state is IDLE. This defeats sanity check in ata_pio_task() for the first command. This patch removes HSM_ST_UNKNOWN and consequently make HSM_ST_IDLE the default state. Signed-off-by: Tejun Heo --- 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 9080789913f7..6013211ac7de 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -318,7 +318,6 @@ enum { }; enum hsm_task_states { - HSM_ST_UNKNOWN, /* state unknown */ HSM_ST_IDLE, /* no command on going */ HSM_ST, /* (waiting the device to) transfer data */ HSM_ST_LAST, /* (waiting the device to) complete command */ -- cgit v1.2.3 From 3d3cca37559e3ab2b574eda11ed5207ccdb8980a Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 16 Nov 2006 10:50:50 +0900 Subject: [PATCH] libata: implement ATA_FLAG_SETXFER_POLLING and use it in pata_via, take #2 This patch implements ATA_FLAG_SETXFER_POLLING and use in pata_via. If this flag is set, transfer mode setting performed by polling not by interrupt. This should help those controllers which raise interrupt before the command is actually complete on SETXFER. Rationale for this approach. * uses existing facility and relatively simple * no busy sleep in the interrupt handler * updating drivers is easy While at it, kill now unused flag ATA_FLAG_SRST in pata_via. Signed-off-by: Tejun Heo --- 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 6013211ac7de..8b57b6a806cc 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -178,6 +178,7 @@ enum { ATA_FLAG_DEBUGMSG = (1 << 13), ATA_FLAG_DETECT_POLLING = (1 << 14), /* detect device presence by * polling IDENTIFY */ + ATA_FLAG_SETXFER_POLLING= (1 << 15), /* use polling for SETXFER */ /* The following flag belongs to ap->pflags but is kept in * ap->flags because it's referenced in many LLDs and will be -- cgit v1.2.3 From 800b399669ad495ad4361d134df87401ae36f44f Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Sun, 3 Dec 2006 21:34:13 +0900 Subject: [PATCH] libata: always use polling IDENTIFY libata switched to IRQ-driven IDENTIFY when IRQ-driven PIO was introduced. This has caused a lot of problems including device misdetection and phantom device. ATA_FLAG_DETECT_POLLING was added recently to selectively use polling IDENTIFY on problemetic drivers but many controllers and devices are affected by this problem and trying to adding ATA_FLAG_DETECT_POLLING for each such case is diffcult and not very rewarding. This patch makes libata always use polling IDENTIFY. This is consistent with libata's original behavior and drivers/ide's behavior. Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- include/linux/libata.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 8b57b6a806cc..202283b5df96 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -176,9 +176,7 @@ enum { ATA_FLAG_SKIP_D2H_BSY = (1 << 12), /* can't wait for the first D2H * Register FIS clearing BSY */ ATA_FLAG_DEBUGMSG = (1 << 13), - ATA_FLAG_DETECT_POLLING = (1 << 14), /* detect device presence by - * polling IDENTIFY */ - ATA_FLAG_SETXFER_POLLING= (1 << 15), /* use polling for SETXFER */ + ATA_FLAG_SETXFER_POLLING= (1 << 14), /* use polling for SETXFER */ /* The following flag belongs to ap->pflags but is kept in * ap->flags because it's referenced in many LLDs and will be -- cgit v1.2.3 From d916faace3efc0bf19fe9a615a1ab8fa1a24cd93 Mon Sep 17 00:00:00 2001 From: Jeff Garzik Date: Sun, 3 Dec 2006 22:22:41 -0500 Subject: Remove long-unmaintained ftape driver subsystem. It's bitrotten, long unmaintained, long hidden under BROKEN_ON_SMP, etc. As scheduled in feature-removal-schedule.txt, and ack'd several times on lkml. Signed-off-by: Jeff Garzik --- include/linux/Kbuild | 4 - include/linux/ftape-header-segment.h | 122 --------------------- include/linux/ftape-vendors.h | 137 ------------------------ include/linux/ftape.h | 201 ----------------------------------- include/linux/zftape.h | 87 --------------- 5 files changed, 551 deletions(-) delete mode 100644 include/linux/ftape-header-segment.h delete mode 100644 include/linux/ftape-vendors.h delete mode 100644 include/linux/ftape.h delete mode 100644 include/linux/zftape.h (limited to 'include/linux') diff --git a/include/linux/Kbuild b/include/linux/Kbuild index d7e04689304c..ff433126361f 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -60,8 +60,6 @@ header-y += fadvise.h header-y += fd.h header-y += fdreg.h header-y += fib_rules.h -header-y += ftape-header-segment.h -header-y += ftape-vendors.h header-y += fuse.h header-y += futex.h header-y += genetlink.h @@ -206,7 +204,6 @@ unifdef-y += fcntl.h unifdef-y += filter.h unifdef-y += flat.h unifdef-y += fs.h -unifdef-y += ftape.h unifdef-y += gameport.h unifdef-y += generic_serial.h unifdef-y += genhd.h @@ -341,6 +338,5 @@ unifdef-y += wait.h unifdef-y += wanrouter.h unifdef-y += watchdog.h unifdef-y += xfrm.h -unifdef-y += zftape.h objhdr-y += version.h diff --git a/include/linux/ftape-header-segment.h b/include/linux/ftape-header-segment.h deleted file mode 100644 index 4732218f0708..000000000000 --- a/include/linux/ftape-header-segment.h +++ /dev/null @@ -1,122 +0,0 @@ -#ifndef _FTAPE_HEADER_SEGMENT_H -#define _FTAPE_HEADER_SEGMENT_H - -/* - * Copyright (C) 1996-1997 Claus-Justus Heine. - - This program is free software; you can redistribute it and/or modify - it under the terms of the GNU General Public License as published by - the Free Software Foundation; either version 2, or (at your option) - any later version. - - This program is distributed in the hope that it will be useful, - but WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - GNU General Public License for more details. - - You should have received a copy of the GNU General Public License - along with this program; see the file COPYING. If not, write to - the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA. - - * - * $Source: /homes/cvs/ftape-stacked/include/linux/ftape-header-segment.h,v $ - * $Revision: 1.2 $ - * $Date: 1997/10/05 19:19:28 $ - * - * This file defines some offsets into the header segment of a - * floppy tape cartridge. For use with the QIC-40/80/3010/3020 - * floppy-tape driver "ftape" for Linux. - */ - -#define FT_SIGNATURE 0 /* must be 0xaa55aa55 */ -#define FT_FMT_CODE 4 -#define FT_REV_LEVEL 5 /* only for QIC-80 since. Rev. L (== 0x0c) */ -#define FT_HSEG_1 6 /* first header segment, except for format code 6 */ -#define FT_HSEG_2 8 /* second header segment, except for format code 6 */ -#define FT_FRST_SEG 10 /* first data segment, except for format code 6 */ -#define FT_LAST_SEG 12 /* last data segment, except for format code 6 */ -#define FT_FMT_DATE 14 /* date and time of most recent format, see below */ -#define FT_WR_DATE 18 /* date and time of most recent write or format */ -#define FT_SPT 24 /* segments per track */ -#define FT_TPC 26 /* tracks per cartridge */ -#define FT_FHM 27 /* floppy drive head (maximum of it) */ -#define FT_FTM 28 /* floppy track max. */ -#define FT_FSM 29 /* floppy sector max. (128) */ -#define FT_LABEL 30 /* floppy tape label */ -#define FT_LABEL_DATE 74 /* date and time the tape label was written */ -#define FT_LABEL_SZ (FT_LABEL_DATE - FT_LABEL) -#define FT_CMAP_START 78 /* starting segment of compression map */ -#define FT_FMT_ERROR 128 /* must be set to 0xff if remainder gets lost during - * tape format - */ -#define FT_SEG_CNT 130 /* number of seg. written, formatted or verified - * through lifetime of tape (why not read?) - */ -#define FT_INIT_DATE 138 /* date and time of initial tape format */ -#define FT_FMT_CNT 142 /* number of times tape has been formatted */ -#define FT_FSL_CNT 144 /* number of segments in failed sector log */ -#define FT_MK_CODE 146 /* id string of tape manufacturer */ -#define FT_LOT_CODE 190 /* tape manufacturer lot code */ -#define FT_6_HSEG_1 234 /* first header segment for format code 6 */ -#define FT_6_HSEG_2 238 /* second header segment for format code 6 */ -#define FT_6_FRST_SEG 242 /* first data segment for format code 6 */ -#define FT_6_LAST_SEG 246 /* last data segment for format code 6 */ - -#define FT_FSL 256 -#define FT_HEADER_END 256 /* space beyond this point: - * format codes 2, 3 and 5: - * - failed sector log until byte 2047 - * - bad sector map in the reamining part of segment - * format codes 4 and 6: - * - bad sector map starts hear - */ - - -/* value to be stored at the FT_SIGNATURE offset - */ -#define FT_HSEG_MAGIC 0xaa55aa55 -#define FT_D2G_MAGIC 0x82288228 /* Ditto 2GB */ - -/* data and time encoding: */ -#define FT_YEAR_SHIFT 25 -#define FT_YEAR_MASK 0xfe000000 -#define FT_YEAR_0 1970 -#define FT_YEAR_MAX 127 -#define FT_YEAR(year) ((((year)-FT_YEAR_0)< -#include -#endif -#include -#include - -#define FT_SECTOR(x) (x+1) /* sector offset into real sector */ -#define FT_SECTOR_SIZE 1024 -#define FT_SECTORS_PER_SEGMENT 32 -#define FT_ECC_SECTORS 3 -#define FT_SEGMENT_SIZE ((FT_SECTORS_PER_SEGMENT - FT_ECC_SECTORS) * FT_SECTOR_SIZE) -#define FT_BUFF_SIZE (FT_SECTORS_PER_SEGMENT * FT_SECTOR_SIZE) - -/* - * bits of the minor device number that define drive selection - * methods. Could be used one day to access multiple tape - * drives on the same controller. - */ -#define FTAPE_SEL_A 0 -#define FTAPE_SEL_B 1 -#define FTAPE_SEL_C 2 -#define FTAPE_SEL_D 3 -#define FTAPE_SEL_MASK 3 -#define FTAPE_SEL(unit) ((unit) & FTAPE_SEL_MASK) -#define FTAPE_NO_REWIND 4 /* mask for minor nr */ - -/* the following two may be reported when MTIOCGET is requested ... */ -typedef union { - struct { - __u8 error; - __u8 command; - } error; - long space; -} ft_drive_error; -typedef union { - struct { - __u8 drive_status; - __u8 drive_config; - __u8 tape_status; - } status; - long space; -} ft_drive_status; - -#ifdef __KERNEL__ - -#define FT_RQM_DELAY 12 -#define FT_MILLISECOND 1 -#define FT_SECOND 1000 -#define FT_FOREVER -1 -#ifndef HZ -#error "HZ undefined." -#endif -#define FT_USPT (1000000/HZ) /* microseconds per tick */ - -/* This defines the number of retries that the driver will allow - * before giving up (and letting a higher level handle the error). - */ -#ifdef TESTING -#define FT_SOFT_RETRIES 1 /* number of low level retries */ -#define FT_RETRIES_ON_ECC_ERROR 3 /* ecc error when correcting segment */ -#else -#define FT_SOFT_RETRIES 6 /* number of low level retries (triple) */ -#define FT_RETRIES_ON_ECC_ERROR 3 /* ecc error when correcting segment */ -#endif - -#ifndef THE_FTAPE_MAINTAINER -#define THE_FTAPE_MAINTAINER "the ftape maintainer" -#endif - -/* Initialize missing configuration parameters. - */ -#ifndef CONFIG_FT_NR_BUFFERS -# define CONFIG_FT_NR_BUFFERS 3 -#endif -#ifndef CONFIG_FT_FDC_THR -# define CONFIG_FT_FDC_THR 8 -#endif -#ifndef CONFIG_FT_FDC_MAX_RATE -# define CONFIG_FT_FDC_MAX_RATE 2000 -#endif -#ifndef CONFIG_FT_FDC_BASE -# define CONFIG_FT_FDC_BASE 0 -#endif -#ifndef CONFIG_FT_FDC_IRQ -# define CONFIG_FT_FDC_IRQ 0 -#endif -#ifndef CONFIG_FT_FDC_DMA -# define CONFIG_FT_FDC_DMA 0 -#endif - -/* Turn some booleans into numbers. - */ -#ifdef CONFIG_FT_PROBE_FC10 -# undef CONFIG_FT_PROBE_FC10 -# define CONFIG_FT_PROBE_FC10 1 -#else -# define CONFIG_FT_PROBE_FC10 0 -#endif -#ifdef CONFIG_FT_MACH2 -# undef CONFIG_FT_MACH2 -# define CONFIG_FT_MACH2 1 -#else -# define CONFIG_FT_MACH2 0 -#endif - -/* Insert default settings - */ -#if CONFIG_FT_PROBE_FC10 == 1 -# if CONFIG_FT_FDC_BASE == 0 -# undef CONFIG_FT_FDC_BASE -# define CONFIG_FT_FDC_BASE 0x180 -# endif -# if CONFIG_FT_FDC_IRQ == 0 -# undef CONFIG_FT_FDC_IRQ -# define CONFIG_FT_FDC_IRQ 9 -# endif -# if CONFIG_FT_FDC_DMA == 0 -# undef CONFIG_FT_FDC_DMA -# define CONFIG_FT_FDC_DMA 3 -# endif -#elif CONFIG_FT_MACH2 == 1 /* CONFIG_FT_PROBE_FC10 == 1 */ -# if CONFIG_FT_FDC_BASE == 0 -# undef CONFIG_FT_FDC_BASE -# define CONFIG_FT_FDC_BASE 0x1E0 -# endif -# if CONFIG_FT_FDC_IRQ == 0 -# undef CONFIG_FT_FDC_IRQ -# define CONFIG_FT_FDC_IRQ 6 -# endif -# if CONFIG_FT_FDC_DMA == 0 -# undef CONFIG_FT_FDC_DMA -# define CONFIG_FT_FDC_DMA 2 -# endif -#elif defined(CONFIG_FT_ALT_FDC) /* CONFIG_FT_MACH2 */ -# if CONFIG_FT_FDC_BASE == 0 -# undef CONFIG_FT_FDC_BASE -# define CONFIG_FT_FDC_BASE 0x370 -# endif -# if CONFIG_FT_FDC_IRQ == 0 -# undef CONFIG_FT_FDC_IRQ -# define CONFIG_FT_FDC_IRQ 6 -# endif -# if CONFIG_FT_FDC_DMA == 0 -# undef CONFIG_FT_FDC_DMA -# define CONFIG_FT_FDC_DMA 2 -# endif -#else /* CONFIG_FT_ALT_FDC */ -# if CONFIG_FT_FDC_BASE == 0 -# undef CONFIG_FT_FDC_BASE -# define CONFIG_FT_FDC_BASE 0x3f0 -# endif -# if CONFIG_FT_FDC_IRQ == 0 -# undef CONFIG_FT_FDC_IRQ -# define CONFIG_FT_FDC_IRQ 6 -# endif -# if CONFIG_FT_FDC_DMA == 0 -# undef CONFIG_FT_FDC_DMA -# define CONFIG_FT_FDC_DMA 2 -# endif -#endif /* standard FDC */ - -/* some useful macro's - */ -#define NR_ITEMS(x) (int)(sizeof(x)/ sizeof(*x)) - -#endif /* __KERNEL__ */ - -#endif diff --git a/include/linux/zftape.h b/include/linux/zftape.h deleted file mode 100644 index b057c65366c6..000000000000 --- a/include/linux/zftape.h +++ /dev/null @@ -1,87 +0,0 @@ -#ifndef _ZFTAPE_H -#define _ZFTAPE_H - -/* - * Copyright (C) 1996, 1997 Claus-Justus Heine. - - This program is free software; you can redistribute it and/or modify - it under the terms of the GNU General Public License as published by - the Free Software Foundation; either version 2, or (at your option) - any later version. - - This program is distributed in the hope that it will be useful, - but WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - GNU General Public License for more details. - - You should have received a copy of the GNU General Public License - along with this program; see the file COPYING. If not, write to - the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA. - - * - * $Source: /homes/cvs/ftape-stacked/include/linux/zftape.h,v $ - * $Revision: 1.12 $ - * $Date: 1997/10/21 11:02:37 $ - * - * Special ioctl and other global info for the zftape VFS - * interface for the QIC-40/80/3010/3020 floppy-tape driver for - * Linux. - */ - -#define ZFTAPE_VERSION "zftape for " FTAPE_VERSION - -#include - -#define ZFTAPE_LABEL "Ftape - The Linux Floppy Tape Project!" - -/* Bits of the minor device number that control the operation mode */ -#define ZFT_Q80_MODE (1 << 3) -#define ZFT_ZIP_MODE (1 << 4) -#define ZFT_RAW_MODE (1 << 5) -#define ZFT_MINOR_OP_MASK (ZFT_Q80_MODE | \ - ZFT_ZIP_MODE | \ - ZFT_RAW_MODE) -#define ZFT_MINOR_MASK (FTAPE_SEL_MASK | \ - ZFT_MINOR_OP_MASK | \ - FTAPE_NO_REWIND) - -#ifdef ZFT_OBSOLETE -struct mtblksz { - unsigned int mt_blksz; -}; -#define MTIOC_ZFTAPE_GETBLKSZ _IOR('m', 104, struct mtblksz) -#endif - -#ifdef __KERNEL__ - -extern int zft_init(void); - -static inline __s64 zft_div_blksz(__s64 value, __u32 blk_sz) -{ - if (blk_sz == 1) { - return value; - } else { - return (__s64)(((__u32)(value >> 10) + (blk_sz >> 10) - 1) - / (blk_sz >> 10)); - } -} - -static inline __s64 zft_mul_blksz(__s64 value, __u32 blk_sz) -{ - if (blk_sz == 1) { - return value; - } else { - /* if blk_sz != 1, then it is a multiple of 1024. In - * this case, `value' will also fit into 32 bits. - * - * Actually, this limits the capacity to 42 - * bits. This is (2^32)*1024, roughly a thousand - * times 2GB, or 3 Terabytes. Hopefully this is enough - */ - return(__s64)(((__u32)(value)*(blk_sz>>10))<<10); - } -} - -#endif - -#endif -- cgit v1.2.3 From f6a570333e554b48ad589e7137c77c57809eee81 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 18 Oct 2006 01:47:25 -0400 Subject: [PATCH] severing module.h->sched.h Signed-off-by: Al Viro --- include/linux/acct.h | 1 + include/linux/module.h | 13 +------------ 2 files changed, 2 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/acct.h b/include/linux/acct.h index 0496d1f09952..302eb727ecb8 100644 --- a/include/linux/acct.h +++ b/include/linux/acct.h @@ -119,6 +119,7 @@ struct acct_v3 #ifdef CONFIG_BSD_PROCESS_ACCT struct vfsmount; struct super_block; +struct pacct_struct; extern void acct_auto_close_mnt(struct vfsmount *m); extern void acct_auto_close(struct super_block *sb); extern void acct_init_pacct(struct pacct_struct *pacct); diff --git a/include/linux/module.h b/include/linux/module.h index 9258ffd8a7f0..d33df2408e05 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -6,7 +6,6 @@ * Rewritten by Richard Henderson Dec 1996 * Rewritten again by Rusty Russell, 2002 */ -#include #include #include #include @@ -411,17 +410,7 @@ static inline int try_module_get(struct module *module) return ret; } -static inline void module_put(struct module *module) -{ - if (module) { - unsigned int cpu = get_cpu(); - local_dec(&module->ref[cpu].count); - /* Maybe they're waiting for us to drop reference? */ - if (unlikely(!module_is_live(module))) - wake_up_process(module->waiter); - put_cpu(); - } -} +extern void module_put(struct module *module); #else /*!CONFIG_MODULE_UNLOAD*/ static inline int try_module_get(struct module *module) -- cgit v1.2.3 From 914e26379decf1fd984b22e51fd2e4209b7a7f1b Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 18 Oct 2006 13:55:46 -0400 Subject: [PATCH] severing fs.h, radix-tree.h -> sched.h Signed-off-by: Al Viro --- include/linux/fs.h | 37 +++++++------------------------------ include/linux/radix-tree.h | 1 - 2 files changed, 7 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 2fe6e3f900ba..cac7b1ef9543 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -276,7 +276,7 @@ extern int dir_notify_enable; #include #include #include -#include +#include #include #include @@ -977,36 +977,13 @@ enum { #define vfs_check_frozen(sb, level) \ wait_event((sb)->s_wait_unfrozen, ((sb)->s_frozen < (level))) -static inline void get_fs_excl(void) -{ - atomic_inc(¤t->fs_excl); -} - -static inline void put_fs_excl(void) -{ - atomic_dec(¤t->fs_excl); -} - -static inline int has_fs_excl(void) -{ - return atomic_read(¤t->fs_excl); -} +#define get_fs_excl() atomic_inc(¤t->fs_excl) +#define put_fs_excl() atomic_dec(¤t->fs_excl) +#define has_fs_excl() atomic_read(¤t->fs_excl) - -/* - * Superblock locking. - */ -static inline void lock_super(struct super_block * sb) -{ - get_fs_excl(); - mutex_lock(&sb->s_lock); -} - -static inline void unlock_super(struct super_block * sb) -{ - put_fs_excl(); - mutex_unlock(&sb->s_lock); -} +/* not quite ready to be deprecated, but... */ +extern void lock_super(struct super_block *); +extern void unlock_super(struct super_block *); /* * VFS helper functions.. diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 9158a68140c9..cbfa11537421 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -19,7 +19,6 @@ #ifndef _LINUX_RADIX_TREE_H #define _LINUX_RADIX_TREE_H -#include #include #include -- cgit v1.2.3 From a1f8e7f7fb9d7e2cbcb53170edca7c0ac4680697 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 19 Oct 2006 16:08:53 -0400 Subject: [PATCH] severing skbuff.h -> highmem.h Signed-off-by: Al Viro --- include/linux/skbuff.h | 19 ------------------- 1 file changed, 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 14ec16d2d9ba..24ce0add6c54 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -23,7 +23,6 @@ #include #include #include -#include #include #include #include @@ -1295,24 +1294,6 @@ static inline int pskb_trim_rcsum(struct sk_buff *skb, unsigned int len) return __pskb_trim(skb, len); } -static inline void *kmap_skb_frag(const skb_frag_t *frag) -{ -#ifdef CONFIG_HIGHMEM - BUG_ON(in_irq()); - - local_bh_disable(); -#endif - return kmap_atomic(frag->page, KM_SKB_DATA_SOFTIRQ); -} - -static inline void kunmap_skb_frag(void *vaddr) -{ - kunmap_atomic(vaddr, KM_SKB_DATA_SOFTIRQ); -#ifdef CONFIG_HIGHMEM - local_bh_enable(); -#endif -} - #define skb_queue_walk(queue, skb) \ for (skb = (queue)->next; \ prefetch(skb->next), (skb != (struct sk_buff *)(queue)); \ -- cgit v1.2.3 From bd01f843c3368dcee735c19603251669f23f4477 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 19 Oct 2006 17:23:57 -0400 Subject: [PATCH] severing skbuff.h -> poll.h Signed-off-by: Al Viro --- include/linux/skbuff.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 24ce0add6c54..5c5a08576dcc 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -23,7 +23,6 @@ #include #include #include -#include #include #include #include -- cgit v1.2.3 From d7fe0f241dceade9c8d4af75498765c5ff7f27e6 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 3 Dec 2006 23:15:30 -0500 Subject: [PATCH] severing skbuff.h -> mm.h Signed-off-by: Al Viro --- include/linux/igmp.h | 1 + include/linux/kernelcapi.h | 1 + include/linux/netdevice.h | 1 + include/linux/netfilter_ipv4/ip_conntrack.h | 1 + include/linux/skbuff.h | 1 - 5 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/igmp.h b/include/linux/igmp.h index 6e7ea2f0a57c..9dbb525c5178 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -127,6 +127,7 @@ struct igmpv3_query { #ifdef __KERNEL__ #include +#include #include extern int sysctl_igmp_max_memberships; diff --git a/include/linux/kernelcapi.h b/include/linux/kernelcapi.h index 891bb2cf0aa8..f8a0ff86dacc 100644 --- a/include/linux/kernelcapi.h +++ b/include/linux/kernelcapi.h @@ -47,6 +47,7 @@ typedef struct kcapi_carddef { #include #include +#include #define KCI_CONTRUP 0 /* arg: struct capi_profile */ #define KCI_CONTRDOWN 1 /* arg: NULL */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 949eada46ce1..c57088f575a3 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -30,6 +30,7 @@ #include #ifdef __KERNEL__ +#include #include #include #include diff --git a/include/linux/netfilter_ipv4/ip_conntrack.h b/include/linux/netfilter_ipv4/ip_conntrack.h index 61da56941dce..33581c13d947 100644 --- a/include/linux/netfilter_ipv4/ip_conntrack.h +++ b/include/linux/netfilter_ipv4/ip_conntrack.h @@ -9,6 +9,7 @@ #include #include +#include #include #include #include diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 5c5a08576dcc..6bdff9b148d0 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -22,7 +22,6 @@ #include #include #include -#include #include #include #include -- cgit v1.2.3 From f23f6e08c47acbdd20e9c49a79da8c404ea168e1 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 20 Oct 2006 15:17:02 -0400 Subject: [PATCH] severing poll.h -> mm.h Signed-off-by: Al Viro --- include/linux/poll.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/poll.h b/include/linux/poll.h index 51e1b56741fb..27690798623f 100644 --- a/include/linux/poll.h +++ b/include/linux/poll.h @@ -8,7 +8,8 @@ #include #include #include -#include +#include +#include #include /* ~832 bytes of stack space used max in sys_select/sys_poll before allocating -- cgit v1.2.3 From bf1ab978be2318c5a564de9aa0f1a217b44170d4 Mon Sep 17 00:00:00 2001 From: Dwayne Grant McConnell Date: Thu, 23 Nov 2006 00:46:37 +0100 Subject: [POWERPC] coredump: Add SPU elf notes to coredump. This patch adds SPU elf notes to the coredump. It creates a separate note for each of /regs, /fpcr, /lslr, /decr, /decr_status, /mem, /signal1, /signal1_type, /signal2, /signal2_type, /event_mask, /event_status, /mbox_info, /ibox_info, /wbox_info, /dma_info, /proxydma_info, /object-id. A new macro, ARCH_HAVE_EXTRA_NOTES, was created for architectures to specify they have extra elf core notes. A new macro, ELF_CORE_EXTRA_NOTES_SIZE, was created so the size of the additional notes could be calculated and added to the notes phdr entry. A new macro, ELF_CORE_WRITE_EXTRA_NOTES, was created so the new notes would be written after the existing notes. The SPU coredump code resides in spufs. Stub functions are provided in the kernel which are hooked into the spufs code which does the actual work via register_arch_coredump_calls(). A new set of __spufs__read/get() functions was provided to allow the coredump code to read from the spufs files without having to lock the SPU context for each file read from. Cc: Signed-off-by: Dwayne Grant McConnell Signed-off-by: Arnd Bergmann --- include/linux/elf.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/elf.h b/include/linux/elf.h index b70d1d2c8d28..743d5c8e6d36 100644 --- a/include/linux/elf.h +++ b/include/linux/elf.h @@ -368,5 +368,12 @@ extern Elf64_Dyn _DYNAMIC []; #endif +#ifndef ARCH_HAVE_EXTRA_ELF_NOTES +static inline int arch_notes_size(void) { return 0; } +static inline void arch_write_notes(struct file *file) { } + +#define ELF_CORE_EXTRA_NOTES_SIZE arch_notes_size() +#define ELF_CORE_WRITE_EXTRA_NOTES arch_write_notes(file) +#endif /* ARCH_HAVE_EXTRA_ELF_NOTES */ #endif /* _LINUX_ELF_H */ -- cgit v1.2.3 From 0c789ff64e874bbece03b607f200566ab24ea9ab Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 4 Dec 2006 10:52:29 -0800 Subject: netfilter.h needs rcuupdate.h for RCU locking functions This was exposed by Al's recent header file dependency reduction patches.. Cc: Al Viro Cc: David S. Miller Signed-off-by: Linus Torvalds --- include/linux/netfilter.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index d4c4c5120bc0..9389cf7d4062 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -11,6 +11,7 @@ #include #endif #include +#include /* Responses from hook functions. */ #define NF_DROP 0 -- cgit v1.2.3 From a80958f4849316a18c06f75b9e850ccecbf20df8 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 4 Dec 2006 20:41:19 +0000 Subject: [PATCH] fix fallout from header dependency trimming OK, that seems to be enough to deal with the mess. Signed-off-by: Al Viro Signed-off-by: Linus Torvalds --- include/linux/kernelcapi.h | 1 + include/linux/netfilter.h | 1 - include/linux/skbuff.h | 1 + 3 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kernelcapi.h b/include/linux/kernelcapi.h index f8a0ff86dacc..aea34e74c496 100644 --- a/include/linux/kernelcapi.h +++ b/include/linux/kernelcapi.h @@ -48,6 +48,7 @@ typedef struct kcapi_carddef { #include #include #include +#include #define KCI_CONTRUP 0 /* arg: struct capi_profile */ #define KCI_CONTRDOWN 1 /* arg: NULL */ diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 9389cf7d4062..d4c4c5120bc0 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -11,7 +11,6 @@ #include #endif #include -#include /* Responses from hook functions. */ #define NF_DROP 0 diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 6bdff9b148d0..a05a5f7c0b73 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -25,6 +25,7 @@ #include #include #include +#include #include #define HAVE_ALLOC_SKB /* For the drivers to know */ -- cgit v1.2.3 From e62438630ca37539c8cc1553710bbfaa3cf960a7 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 4 Dec 2006 03:38:31 -0700 Subject: [PATCH] Centralise definitions of sector_t and blkcnt_t CONFIG_LBD and CONFIG_LSF are spread into asm/types.h for no particularly good reason. Centralising the definition in linux/types.h means that arch maintainers don't need to bother adding it, as well as fixing the problem with x86-64 users being asked to make a decision that has absolutely no effect. The H8/300 porters seem particularly confused since I'm not aware of any microcontrollers that need to support 2TB filesystems. Signed-off-by: Matthew Wilcox Signed-off-by: Linus Torvalds --- include/linux/types.h | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/types.h b/include/linux/types.h index 745c409ebbb5..0351bf2fac85 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -136,15 +136,19 @@ typedef __s64 int64_t; * * Linux always considers sectors to be 512 bytes long independently * of the devices real block size. - * - * If required, asm/types.h can override it and define - * HAVE_SECTOR_T */ -#ifndef HAVE_SECTOR_T +#ifdef CONFIG_LBD +typedef u64 sector_t; +#else typedef unsigned long sector_t; #endif -#ifndef HAVE_BLKCNT_T +/* + * The type of the inode's block count. + */ +#ifdef CONFIG_LSF +typedef u64 blkcnt_t; +#else typedef unsigned long blkcnt_t; #endif -- cgit v1.2.3 From 6d5aefb8eaa38e44b5b8cf60c812aceafc02d924 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 5 Dec 2006 19:36:26 +0000 Subject: WorkQueue: Fix up arch-specific work items where possible Fix up arch-specific work items where possible to use the new work_struct and delayed_work structs. Three places that enqueue bits of their stack and then return have been marked with #error as this is not permitted. Signed-Off-By: David Howells --- include/linux/netpoll.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index 2cc9867b1626..29930b71a9aa 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -32,7 +32,7 @@ struct netpoll_info { struct netpoll *rx_np; /* netpoll that registered an rx_hook */ struct sk_buff_head arp_tx; /* list of arp requests to reply to */ struct sk_buff_head txq; - struct work_struct tx_work; + struct delayed_work tx_work; }; void netpoll_poll(struct netpoll *np); -- cgit v1.2.3 From e6b3c4db6fbcd0d33720696f37790d6b8be12313 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 11 Nov 2006 22:18:03 -0500 Subject: Fix a second potential rpc_wakeup race... Signed-off-by: Trond Myklebust --- include/linux/sunrpc/sched.h | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index f399c138f79d..9fdb8c9d09f2 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -178,13 +178,6 @@ struct rpc_call_ops { } while (0) #define RPC_IS_ACTIVATED(t) (test_bit(RPC_TASK_ACTIVE, &(t)->tk_runstate)) -#define rpc_set_active(t) (set_bit(RPC_TASK_ACTIVE, &(t)->tk_runstate)) -#define rpc_clear_active(t) \ - do { \ - smp_mb__before_clear_bit(); \ - clear_bit(RPC_TASK_ACTIVE, &(t)->tk_runstate); \ - smp_mb__after_clear_bit(); \ - } while(0) /* * Task priorities. @@ -254,6 +247,7 @@ struct rpc_task *rpc_run_task(struct rpc_clnt *clnt, int flags, void rpc_init_task(struct rpc_task *task, struct rpc_clnt *clnt, int flags, const struct rpc_call_ops *ops, void *data); +void rpc_put_task(struct rpc_task *); void rpc_release_task(struct rpc_task *); void rpc_exit_task(struct rpc_task *); void rpc_killall_tasks(struct rpc_clnt *); -- cgit v1.2.3 From 8aca67f0ae2d8811165c22326825a645cc8e1b48 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 13 Nov 2006 16:23:44 -0500 Subject: SUNRPC: Fix a potential race in rpc_wake_up_task() Use RCU to ensure that we can safely call rpc_finish_wakeup after we've called __rpc_do_wake_up_task. If not, there is a theoretical race, in which the rpc_task finishes executing, and gets freed first. Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 7 ++----- include/linux/sunrpc/sched.h | 2 ++ 2 files changed, 4 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 625ffea98561..02f38189d180 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -428,11 +428,6 @@ extern int nfs_updatepage(struct file *, struct page *, unsigned int, unsigned extern int nfs_writeback_done(struct rpc_task *, struct nfs_write_data *); extern void nfs_writedata_release(void *); -#if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4) -struct nfs_write_data *nfs_commit_alloc(void); -void nfs_commit_free(struct nfs_write_data *p); -#endif - /* * Try to write back everything synchronously (but check the * return value!) @@ -440,6 +435,8 @@ void nfs_commit_free(struct nfs_write_data *p); extern int nfs_sync_inode_wait(struct inode *, unsigned long, unsigned int, int); #if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4) extern int nfs_commit_inode(struct inode *, int); +extern struct nfs_write_data *nfs_commit_alloc(void); +extern void nfs_commit_free(struct nfs_write_data *wdata); extern void nfs_commit_release(void *wdata); #else static inline int diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index 9fdb8c9d09f2..14fc813ddd0c 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -11,6 +11,7 @@ #include #include +#include #include #include #include @@ -85,6 +86,7 @@ struct rpc_task { union { struct work_struct tk_work; /* Async task work queue */ struct rpc_wait tk_wait; /* RPC wait */ + struct rcu_head tk_rcu; /* for task deletion */ } u; unsigned short tk_timeouts; /* maj timeouts */ -- cgit v1.2.3 From 3e32a5d99a467b9d4d416323c8c292479b4915e5 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 16 Nov 2006 11:37:27 -0500 Subject: SUNRPC: Give cloned RPC clients their own rpc_pipefs directory Signed-off-by: Trond Myklebust --- include/linux/sunrpc/clnt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index f6d1d646ce05..a1be89deb3af 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -53,6 +53,7 @@ struct rpc_clnt { struct dentry * cl_dentry; /* inode */ struct rpc_clnt * cl_parent; /* Points to parent of clones */ struct rpc_rtt cl_rtt_default; + struct rpc_program * cl_program; char cl_inline_name[32]; }; -- cgit v1.2.3 From bbd5a1f9fc9fad0f8725812d91c51b052e847de8 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 18 Oct 2006 16:01:05 -0400 Subject: SUNRPC: Fix up missing BKL in asynchronous RPC callback functions Signed-off-by: Trond Myklebust --- include/linux/sunrpc/sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index 14fc813ddd0c..b6b6ad6253b4 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -252,6 +252,7 @@ void rpc_init_task(struct rpc_task *task, struct rpc_clnt *clnt, void rpc_put_task(struct rpc_task *); void rpc_release_task(struct rpc_task *); void rpc_exit_task(struct rpc_task *); +void rpc_release_calldata(const struct rpc_call_ops *, void *); void rpc_killall_tasks(struct rpc_clnt *); int rpc_execute(struct rpc_task *); void rpc_init_priority_wait_queue(struct rpc_wait_queue *, const char *); -- cgit v1.2.3 From 1e78957e0a8f882df6a3660b62f9aae441f54891 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 31 Aug 2006 15:09:19 -0400 Subject: SUNRPC: Clean up argument types in xdr.c Converts various integer buffer offsets and sizes to unsigned integer. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xdr.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 9a527c364394..441b91dbafe5 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -139,10 +139,10 @@ xdr_adjust_iovec(struct kvec *iov, __be32 *p) */ extern void xdr_shift_buf(struct xdr_buf *, size_t); extern void xdr_buf_from_iov(struct kvec *, struct xdr_buf *); -extern int xdr_buf_subsegment(struct xdr_buf *, struct xdr_buf *, int, int); -extern int xdr_buf_read_netobj(struct xdr_buf *, struct xdr_netobj *, int); -extern int read_bytes_from_xdr_buf(struct xdr_buf *, int, void *, int); -extern int write_bytes_to_xdr_buf(struct xdr_buf *, int, void *, int); +extern int xdr_buf_subsegment(struct xdr_buf *, struct xdr_buf *, unsigned int, unsigned int); +extern int xdr_buf_read_netobj(struct xdr_buf *, struct xdr_netobj *, unsigned int); +extern int read_bytes_from_xdr_buf(struct xdr_buf *, unsigned int, void *, unsigned int); +extern int write_bytes_to_xdr_buf(struct xdr_buf *, unsigned int, void *, unsigned int); /* * Helper structure for copying from an sk_buff. @@ -160,8 +160,8 @@ extern int csum_partial_copy_to_xdr(struct xdr_buf *, struct sk_buff *); extern ssize_t xdr_partial_copy_from_skb(struct xdr_buf *, unsigned int, skb_reader_t *, skb_read_actor_t); -extern int xdr_encode_word(struct xdr_buf *, int, u32); -extern int xdr_decode_word(struct xdr_buf *, int, u32 *); +extern int xdr_encode_word(struct xdr_buf *, unsigned int, u32); +extern int xdr_decode_word(struct xdr_buf *, unsigned int, u32 *); struct xdr_array2_desc; typedef int (*xdr_xcode_elem_t)(struct xdr_array2_desc *desc, void *elem); -- cgit v1.2.3 From e744cf2e3ab8535a8494a4cf0177de26f94586da Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 17 Oct 2006 14:44:24 -0400 Subject: SUNRPC: minor optimization of "xid" field in rpc_xprt Move the xid field in the rpc_xprt structure to be in the same cache line as the reserve_lock, since these are used at the same time. Test plan: None. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 60394fbc4c70..0321fb53bd02 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -157,11 +157,6 @@ struct rpc_xprt { unsigned char shutdown : 1, /* being shut down */ resvport : 1; /* use a reserved port */ - /* - * XID - */ - __u32 xid; /* Next XID value to use */ - /* * State of TCP reply receive stuff */ @@ -193,8 +188,8 @@ struct rpc_xprt { */ spinlock_t transport_lock; /* lock transport info */ spinlock_t reserve_lock; /* lock slot table */ + u32 xid; /* Next XID value to use */ struct rpc_task * snd_task; /* Task blocked in send */ - struct list_head recv; struct { -- cgit v1.2.3 From c8541ecdd5692bcfbcb5305cab9a873288d29175 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 17 Oct 2006 14:44:27 -0400 Subject: SUNRPC: Make the transport-specific setup routine allocate rpc_xprt Change the location where the rpc_xprt structure is allocated so each transport implementation can allocate a private area from the same chunk of memory. Note also that xprt->ops->destroy, rather than xprt_destroy, is now responsible for freeing rpc_xprt when the transport is destroyed. Test plan: Connectathon. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 0321fb53bd02..d7919010863d 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -265,8 +265,8 @@ void xprt_disconnect(struct rpc_xprt *xprt); /* * Socket transport setup operations */ -int xs_setup_udp(struct rpc_xprt *xprt, struct rpc_timeout *to); -int xs_setup_tcp(struct rpc_xprt *xprt, struct rpc_timeout *to); +struct rpc_xprt * xs_setup_udp(struct sockaddr *addr, size_t addrlen, struct rpc_timeout *to); +struct rpc_xprt * xs_setup_tcp(struct sockaddr *addr, size_t addrlen, struct rpc_timeout *to); /* * Reserved bit positions in xprt->state -- cgit v1.2.3 From 3f442547b76bf9fb70d7aecc41cf1980459253c9 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 17 Sep 2006 14:46:44 -0400 Subject: NFS: Clean up nfs_scan_dirty() Pass down struct writeback control. Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 2 +- include/linux/nfs_page.h | 5 +++-- 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 02f38189d180..f8190ae9e3fb 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -432,7 +432,7 @@ extern void nfs_writedata_release(void *); * Try to write back everything synchronously (but check the * return value!) */ -extern int nfs_sync_inode_wait(struct inode *, unsigned long, unsigned int, int); +extern long nfs_sync_inode_wait(struct inode *, unsigned long, unsigned int, int); #if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4) extern int nfs_commit_inode(struct inode *, int); extern struct nfs_write_data *nfs_commit_alloc(void); diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index 1f7bd287c230..38aa15fea638 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -60,8 +60,9 @@ extern void nfs_clear_request(struct nfs_page *req); extern void nfs_release_request(struct nfs_page *req); -extern int nfs_scan_lock_dirty(struct nfs_inode *nfsi, struct list_head *dst, - unsigned long idx_start, unsigned int npages); +extern long nfs_scan_dirty(struct address_space *mapping, + struct writeback_control *wbc, + struct list_head *dst); extern int nfs_scan_list(struct nfs_inode *nfsi, struct list_head *head, struct list_head *dst, unsigned long idx_start, unsigned int npages); extern int nfs_coalesce_requests(struct list_head *, struct list_head *, -- cgit v1.2.3 From 1c75950b9a2254ef08f986e00ad20266ae9ba7f1 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 9 Oct 2006 16:18:38 -0400 Subject: NFS: cleanup of nfs_sync_inode_wait() Allow callers to directly pass it a struct writeback_control. Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 27 ++++----------------------- 1 file changed, 4 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index f8190ae9e3fb..f2ec9be1e22f 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -432,7 +432,10 @@ extern void nfs_writedata_release(void *); * Try to write back everything synchronously (but check the * return value!) */ -extern long nfs_sync_inode_wait(struct inode *, unsigned long, unsigned int, int); +extern long nfs_sync_mapping_wait(struct address_space *, struct writeback_control *, int); +extern int nfs_sync_mapping_range(struct address_space *, loff_t, loff_t, int); +extern int nfs_wb_all(struct inode *inode); +extern int nfs_wb_page(struct inode *inode, struct page* page); #if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4) extern int nfs_commit_inode(struct inode *, int); extern struct nfs_write_data *nfs_commit_alloc(void); @@ -452,28 +455,6 @@ nfs_have_writebacks(struct inode *inode) return NFS_I(inode)->npages != 0; } -static inline int -nfs_wb_all(struct inode *inode) -{ - int error = nfs_sync_inode_wait(inode, 0, 0, 0); - return (error < 0) ? error : 0; -} - -/* - * Write back all requests on one page - we do this before reading it. - */ -static inline int nfs_wb_page_priority(struct inode *inode, struct page* page, int how) -{ - int error = nfs_sync_inode_wait(inode, page->index, 1, - how | FLUSH_STABLE); - return (error < 0) ? error : 0; -} - -static inline int nfs_wb_page(struct inode *inode, struct page* page) -{ - return nfs_wb_page_priority(inode, page, 0); -} - /* * Allocate nfs_write_data structures */ -- cgit v1.2.3 From 200baa2112012dd8a13db9da3ee6885403f9c013 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 5 Dec 2006 00:35:40 -0500 Subject: NFS: Remove nfs_writepage_sync() Maintaining two parallel ways of doing synchronous writes is rather pointless. This patch gets rid of the legacy nfs_writepage_sync(), and replaces it with the faster asynchronous writes. Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 768c1ad5ff6f..9ee9da5e1cc9 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -785,8 +785,6 @@ struct nfs_rpc_ops { int (*readlink)(struct inode *, struct page *, unsigned int, unsigned int); int (*read) (struct nfs_read_data *); - int (*write) (struct nfs_write_data *); - int (*commit) (struct nfs_write_data *); int (*create) (struct inode *, struct dentry *, struct iattr *, int, struct nameidata *); int (*remove) (struct inode *, struct qstr *); -- cgit v1.2.3 From 1a54533ec8d92a5edae97ec6ae10023ee71c4b46 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 5 Dec 2006 00:35:40 -0500 Subject: NFS: Add nfs_set_page_dirty() We will want to allow nfs_writepage() to distinguish between pages that have been marked as dirty by the VM, and those that have been marked as dirty by nfs_updatepage(). In the former case, the entire page will want to be written out, and so any requests that were pending need to be flushed out first. Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 1 + include/linux/nfs_page.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index f2ec9be1e22f..1b38c2085a53 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -427,6 +427,7 @@ extern int nfs_flush_incompatible(struct file *file, struct page *page); extern int nfs_updatepage(struct file *, struct page *, unsigned int, unsigned int); extern int nfs_writeback_done(struct rpc_task *, struct nfs_write_data *); extern void nfs_writedata_release(void *); +extern int nfs_set_page_dirty(struct page *); /* * Try to write back everything synchronously (but check the diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index 38aa15fea638..d111be639140 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -30,6 +30,7 @@ #define PG_BUSY 0 #define PG_NEED_COMMIT 1 #define PG_NEED_RESCHED 2 +#define PG_NEED_FLUSH 3 struct nfs_inode; struct nfs_page { -- cgit v1.2.3 From 4d770ccf4257b23a7ca2a85de1b1c22657b581d8 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 5 Dec 2006 00:35:41 -0500 Subject: NFS: Ensure that nfs_wb_page() calls writepage when necessary. Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 1b38c2085a53..3de334c72b1f 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -33,6 +33,7 @@ #define FLUSH_HIGHPRI 16 /* high priority memory reclaim flush */ #define FLUSH_NOCOMMIT 32 /* Don't send the NFSv3/v4 COMMIT */ #define FLUSH_INVALIDATE 64 /* Invalidate the page cache */ +#define FLUSH_NOWRITEPAGE 128 /* Don't call writepage() */ #ifdef __KERNEL__ -- cgit v1.2.3 From e261f51f25b98c213e0b3d7f2109b117d714f69d Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 5 Dec 2006 00:35:41 -0500 Subject: NFS: Make nfs_updatepage() mark the page as dirty. This will ensure that we can call set_page_writeback() from within nfs_writepage(), which is always called with the page lock set. Signed-off-by: Trond Myklebust --- include/linux/nfs_page.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index d111be639140..2e555d49c9b7 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -31,6 +31,7 @@ #define PG_NEED_COMMIT 1 #define PG_NEED_RESCHED 2 #define PG_NEED_FLUSH 3 +#define PG_FLUSHING 4 struct nfs_inode; struct nfs_page { -- cgit v1.2.3 From 61822ab5e3ed09fcfc49e37227b655202adf6130 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 5 Dec 2006 00:35:42 -0500 Subject: NFS: Ensure we only call set_page_writeback() under the page lock Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 3de334c72b1f..04963063e620 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -438,6 +438,7 @@ extern long nfs_sync_mapping_wait(struct address_space *, struct writeback_contr extern int nfs_sync_mapping_range(struct address_space *, loff_t, loff_t, int); extern int nfs_wb_all(struct inode *inode); extern int nfs_wb_page(struct inode *inode, struct page* page); +extern int nfs_wb_page_priority(struct inode *inode, struct page* page, int how); #if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4) extern int nfs_commit_inode(struct inode *, int); extern struct nfs_write_data *nfs_commit_alloc(void); -- cgit v1.2.3 From 8fc7500bb8ea3b5c909869d00628635e964ae882 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Mon, 4 Dec 2006 20:22:31 -0500 Subject: rpc: gss: eliminate print_hexl()'s Dumping all this data to the logs is wasteful (even when debugging is turned off), and creates too much output to be useful when it's turned on. Fix a minor style bug or two while we're at it. Signed-off-by: J. Bruce Fields Signed-off-by: Trond Myklebust --- include/linux/sunrpc/auth_gss.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/auth_gss.h b/include/linux/sunrpc/auth_gss.h index 97b62e97dd8d..2db2fbf34947 100644 --- a/include/linux/sunrpc/auth_gss.h +++ b/include/linux/sunrpc/auth_gss.h @@ -90,8 +90,6 @@ struct gss_cred { #define gc_flags gc_base.cr_flags #define gc_expire gc_base.cr_expire -void print_hexl(u32 *p, u_int length, u_int offset); - #endif /* __KERNEL__ */ #endif /* _LINUX_SUNRPC_AUTH_GSS_H */ -- cgit v1.2.3 From 37a4e6cb0391f2293ba3d59e3a63ec0e56ed720d Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Mon, 4 Dec 2006 20:22:33 -0500 Subject: rpc: move process_xdr_buf Since process_xdr_buf() is useful outside of the kerberos-specific code, we move it to net/sunrpc/xdr.c, export it, and rename it in keeping with xdr_* naming convention of xdr.c. Signed-off-by: J. Bruce Fields Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xdr.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 441b91dbafe5..4d17846cd78a 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -11,6 +11,7 @@ #include #include +#include /* * Buffer adjustment @@ -196,6 +197,7 @@ extern void xdr_init_decode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 extern __be32 *xdr_inline_decode(struct xdr_stream *xdr, size_t nbytes); extern void xdr_read_pages(struct xdr_stream *xdr, unsigned int len); extern void xdr_enter_page(struct xdr_stream *xdr, unsigned int len); +extern int xdr_process_buf(struct xdr_buf *buf, unsigned int offset, unsigned int len, int (*actor)(struct scatterlist *, void *), void *data); #endif /* __KERNEL__ */ -- cgit v1.2.3 From adeb8133dd57f380e70a389a89a2ea3ae227f9e2 Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Mon, 4 Dec 2006 20:22:34 -0500 Subject: rpc: spkm3 update This updates the spkm3 code to bring it up to date with our current understanding of the spkm3 spec. In doing so, we're changing the downcall format used by gssd in the spkm3 case, which will cause an incompatilibity with old userland spkm3 support. Since the old code a) didn't implement the protocol correctly, and b) was never distributed except in the form of some experimental patches from the citi web site, we're assuming this is OK. We do detect the old downcall format and print warning (and fail). We also include a version number in the new downcall format, to be used in the future in case any further change is required. In some more detail: - fix integrity support - removed dependency on NIDs. instead OIDs are used - known OID values for algorithms added. - fixed some context fields and types Signed-off-by: J. Bruce Fields Signed-off-by: Trond Myklebust --- include/linux/sunrpc/gss_spkm3.h | 34 ++++++++++++++-------------------- 1 file changed, 14 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/gss_spkm3.h b/include/linux/sunrpc/gss_spkm3.h index 2cf3fbb40b4f..e3e6a3437f8b 100644 --- a/include/linux/sunrpc/gss_spkm3.h +++ b/include/linux/sunrpc/gss_spkm3.h @@ -12,27 +12,19 @@ #include struct spkm3_ctx { - struct xdr_netobj ctx_id; /* per message context id */ - int qop; /* negotiated qop */ + struct xdr_netobj ctx_id; /* per message context id */ + int endtime; /* endtime of the context */ struct xdr_netobj mech_used; unsigned int ret_flags ; - unsigned int req_flags ; - struct xdr_netobj share_key; - int conf_alg; - struct crypto_blkcipher *derived_conf_key; - int intg_alg; - struct crypto_blkcipher *derived_integ_key; - int keyestb_alg; /* alg used to get share_key */ - int owf_alg; /* one way function */ + struct xdr_netobj conf_alg; + struct xdr_netobj derived_conf_key; + struct xdr_netobj intg_alg; + struct xdr_netobj derived_integ_key; }; -/* from openssl/objects.h */ -/* XXX need SEAL_ALG_NONE */ -#define NID_md5 4 -#define NID_dhKeyAgreement 28 -#define NID_des_cbc 31 -#define NID_sha1 64 -#define NID_cast5_cbc 108 +/* OIDs declarations for K-ALG, I-ALG, C-ALG, and OWF-ALG */ +extern const struct xdr_netobj hmac_md5_oid; +extern const struct xdr_netobj cast5_cbc_oid; /* SPKM InnerContext Token types */ @@ -46,11 +38,13 @@ u32 spkm3_make_token(struct spkm3_ctx *ctx, struct xdr_buf * text, struct xdr_ne u32 spkm3_read_token(struct spkm3_ctx *ctx, struct xdr_netobj *read_token, struct xdr_buf *message_buffer, int toktype); #define CKSUMTYPE_RSA_MD5 0x0007 +#define CKSUMTYPE_HMAC_MD5 0x0008 -s32 make_checksum(s32 cksumtype, char *header, int hdrlen, struct xdr_buf *body, - int body_offset, struct xdr_netobj *cksum); +s32 make_spkm3_checksum(s32 cksumtype, struct xdr_netobj *key, char *header, + unsigned int hdrlen, struct xdr_buf *body, + unsigned int body_offset, struct xdr_netobj *cksum); void asn1_bitstring_len(struct xdr_netobj *in, int *enclen, int *zerobits); -int decode_asn1_bitstring(struct xdr_netobj *out, char *in, int enclen, +int decode_asn1_bitstring(struct xdr_netobj *out, char *in, int enclen, int explen); void spkm3_mic_header(unsigned char **hdrbuf, unsigned int *hdrlen, unsigned char *ctxhdr, int elen, int zbit); -- cgit v1.2.3 From e678e06bf8fa25981a6fa1f08b979fd086d713f8 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Mon, 4 Dec 2006 20:22:35 -0500 Subject: gss: krb5: remove signalg and sealalg We designed the krb5 context import without completely understanding the context. Now it's clear that there are a number of fields that we ignore, or that we depend on having one single value. In particular, we only support one value of signalg currently; so let's check the signalg field in the downcall (in case we decide there's something else we could support here eventually), but ignore it otherwise. Signed-off-by: J. Bruce Fields Signed-off-by: Trond Myklebust --- include/linux/sunrpc/gss_krb5.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/gss_krb5.h b/include/linux/sunrpc/gss_krb5.h index e30ba201910a..f680ed3b1b5e 100644 --- a/include/linux/sunrpc/gss_krb5.h +++ b/include/linux/sunrpc/gss_krb5.h @@ -44,7 +44,6 @@ struct krb5_ctx { int initiate; /* 1 = initiating, 0 = accepting */ int seed_init; unsigned char seed[16]; - int signalg; int sealalg; struct crypto_blkcipher *enc; struct crypto_blkcipher *seq; -- cgit v1.2.3 From ca54f896454852f0bc8d50e6e4c55d9defedbd0a Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Mon, 4 Dec 2006 20:22:38 -0500 Subject: rpcgss: simplify make_checksum We're doing some pointless translation between krb5 constants and kernel crypto string names. Also clean up some related spkm3 code as necessary. Signed-off-by: J. Bruce Fields Signed-off-by: Trond Myklebust --- include/linux/sunrpc/gss_krb5.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/gss_krb5.h b/include/linux/sunrpc/gss_krb5.h index f680ed3b1b5e..abfa1f32d914 100644 --- a/include/linux/sunrpc/gss_krb5.h +++ b/include/linux/sunrpc/gss_krb5.h @@ -116,7 +116,7 @@ enum seal_alg { #define ENCTYPE_UNKNOWN 0x01ff s32 -make_checksum(s32 cksumtype, char *header, int hdrlen, struct xdr_buf *body, +make_checksum(char *, char *header, int hdrlen, struct xdr_buf *body, int body_offset, struct xdr_netobj *cksum); u32 gss_get_mic_kerberos(struct gss_ctx *, struct xdr_buf *, -- cgit v1.2.3 From d922a84a8bf1d627810906d033223d4fa629fdbf Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Mon, 4 Dec 2006 20:22:40 -0500 Subject: rpcgss: krb5: sanity check sealalg value in the downcall The sealalg is checked in several places, giving the impression it could be either SEAL_ALG_NONE or SEAL_ALG_DES. But in fact SEAL_ALG_NONE seems to be sufficient only for making mic's, and all the contexts we get must be capable of wrapping as well. So the sealalg must be SEAL_ALG_DES. As with signalg, just check for the right value on the downcall and ignore it otherwise. Similarly, tighten expectations for the sealalg on incoming tokens, in case we do support other values eventually. Signed-off-by: J. Bruce Fields Signed-off-by: Trond Myklebust --- include/linux/sunrpc/gss_krb5.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/gss_krb5.h b/include/linux/sunrpc/gss_krb5.h index abfa1f32d914..01c5e4314632 100644 --- a/include/linux/sunrpc/gss_krb5.h +++ b/include/linux/sunrpc/gss_krb5.h @@ -44,7 +44,6 @@ struct krb5_ctx { int initiate; /* 1 = initiating, 0 = accepting */ int seed_init; unsigned char seed[16]; - int sealalg; struct crypto_blkcipher *enc; struct crypto_blkcipher *seq; s32 endtime; -- cgit v1.2.3 From 717757ad1038ab6aacb89bad579c89b006efd913 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Mon, 4 Dec 2006 20:22:41 -0500 Subject: rpcgss: krb5: ignore seed We're currently not actually using seed or seed_init. Signed-off-by: J. Bruce Fields Signed-off-by: Trond Myklebust --- include/linux/sunrpc/gss_krb5.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/gss_krb5.h b/include/linux/sunrpc/gss_krb5.h index 01c5e4314632..5a4b1e0206e3 100644 --- a/include/linux/sunrpc/gss_krb5.h +++ b/include/linux/sunrpc/gss_krb5.h @@ -42,8 +42,6 @@ struct krb5_ctx { int initiate; /* 1 = initiating, 0 = accepting */ - int seed_init; - unsigned char seed[16]; struct crypto_blkcipher *enc; struct crypto_blkcipher *seq; s32 endtime; -- cgit v1.2.3 From ee0ac0c227c2a2b6dd1b33c23831100ee895dacf Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 5 Dec 2006 16:35:15 -0500 Subject: SUNRPC: Remove sock and inet fields from rpc_xprt The "sock" and "inet" fields are socket-specific. Move them to a private data structure maintained entirely within net/sunrpc/xprtsock.c Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index d7919010863d..4c074a73670c 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -17,6 +17,8 @@ #include #include +#include + extern unsigned int xprt_udp_slot_table_entries; extern unsigned int xprt_tcp_slot_table_entries; @@ -126,8 +128,6 @@ struct rpc_xprt_ops { struct rpc_xprt { struct kref kref; /* Reference count */ struct rpc_xprt_ops * ops; /* transport methods */ - struct socket * sock; /* BSD socket layer */ - struct sock * inet; /* INET layer */ struct rpc_timeout timeout; /* timeout parms */ struct sockaddr_storage addr; /* server address */ -- cgit v1.2.3 From 51971139b2342fa1005e87bbfcb52305da3fe891 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 5 Dec 2006 16:35:19 -0500 Subject: SUNRPC: Move TCP receive state variables into private data structure Move the TCP receive state variables from the generic rpc_xprt structure to a private structure maintained inside net/sunrpc/xprtsock.c. Also rename a function/variable pair to refer to RPC fragment headers instead of record markers, to be consistent with types defined in sunrpc/*.h. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 4c074a73670c..0a0ad1ce70e4 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -157,15 +157,6 @@ struct rpc_xprt { unsigned char shutdown : 1, /* being shut down */ resvport : 1; /* use a reserved port */ - /* - * State of TCP reply receive stuff - */ - __be32 tcp_recm, /* Fragment header */ - tcp_xid; /* Current XID */ - u32 tcp_reclen, /* fragment length */ - tcp_offset; /* fragment offset */ - unsigned long tcp_copied, /* copied to request */ - tcp_flags; /* * Connection of transports */ -- cgit v1.2.3 From e136d0926ef6a048f6e65b35263c0a9faae3abbe Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 5 Dec 2006 16:35:23 -0500 Subject: SUNRPC: Move TCP state flags into xprtsock.c Move "XPRT_LAST_FRAG" and friends from xprt.h into xprtsock.c, and rename them to use the naming scheme in use in xprtsock.c. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 0a0ad1ce70e4..3ff8230c7dd9 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -203,11 +203,6 @@ struct rpc_xprt { char * address_strings[RPC_DISPLAY_MAX]; }; -#define XPRT_LAST_FRAG (1 << 0) -#define XPRT_COPY_RECM (1 << 1) -#define XPRT_COPY_XID (1 << 2) -#define XPRT_COPY_DATA (1 << 3) - #ifdef __KERNEL__ /* -- cgit v1.2.3 From c8475461829fd94f30208fbfa4eab7e5584c6495 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 5 Dec 2006 16:35:26 -0500 Subject: SUNRPC: Move rpc_xprt socket connect fields into private data structure Move the socket-specific connection management fields out of the generic rpc_xprt structure into a private data structure maintained in net/sunrpc/xprtsock.c. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 3ff8230c7dd9..18bf72c06488 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -163,8 +163,6 @@ struct rpc_xprt { unsigned long connect_timeout, bind_timeout, reestablish_timeout; - struct work_struct connect_worker; - unsigned short port; /* * Disconnection of idle transports -- cgit v1.2.3 From 7c6e066ec29290bf062f5bff2984bad9be5809c7 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 5 Dec 2006 16:35:30 -0500 Subject: SUNRPC: Move the UDP socket bufsize parameters to a private data structure Move the socket-specific buffer size parameters for UDP sockets to a private data structure maintained in net/sunrpc/xprtsock.c. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 18bf72c06488..21beb56fb84c 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -137,9 +137,6 @@ struct rpc_xprt { unsigned long cong; /* current congestion */ unsigned long cwnd; /* congestion window */ - size_t rcvsize, /* transport rcv buffer size */ - sndsize; /* transport send buffer size */ - size_t max_payload; /* largest RPC payload size, in bytes */ unsigned int tsh_size; /* size of transport specific -- cgit v1.2.3 From 314dfd7987c71d7ba0c43ac3bf3d243c102ce025 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 5 Dec 2006 16:35:34 -0500 Subject: SUNRPC: move saved socket callback functions to a private data structure Move the three fields for saving socket callback functions out of the rpc_xprt structure and into a private data structure maintained in net/sunrpc/xprtsock.c. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 21beb56fb84c..17f322794e91 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -17,8 +17,6 @@ #include #include -#include - extern unsigned int xprt_udp_slot_table_entries; extern unsigned int xprt_tcp_slot_table_entries; @@ -191,10 +189,6 @@ struct rpc_xprt { bklog_u; /* backlog queue utilization */ } stat; - void (*old_data_ready)(struct sock *, int); - void (*old_state_change)(struct sock *); - void (*old_write_space)(struct sock *); - char * address_strings[RPC_DISPLAY_MAX]; }; -- cgit v1.2.3 From 7559c7a28fbcaa0bca028eeebd5f251b09befe6b Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 5 Dec 2006 16:35:37 -0500 Subject: SUNRPC: Make address format buffers more generic For now we will assume that all transports will use the address format buffers in the rpc_xprt struct to store their addresses. Change rpc_peer2str() to be a generic routine to handle this, and get rid of the print_address() op in the rpc_xprt_ops vector. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 17f322794e91..f780e72fc417 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -106,7 +106,6 @@ struct rpc_rqst { struct rpc_xprt_ops { void (*set_buffer_size)(struct rpc_xprt *xprt, size_t sndsize, size_t rcvsize); - char * (*print_addr)(struct rpc_xprt *xprt, enum rpc_display_format_t format); int (*reserve_xprt)(struct rpc_task *task); void (*release_xprt)(struct rpc_xprt *xprt, struct rpc_task *task); void (*rpcbind)(struct rpc_task *task); -- cgit v1.2.3 From 9d29231690925915015c21c1fff73c7118099843 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 5 Dec 2006 16:35:41 -0500 Subject: SUNRPC: skb_read_bits is the same as xs_tcp_copy_data Clean-up: eliminate xs_tcp_copy_data -- it's exactly the same logic as the common routine skb_read_bits. The UDP and TCP socket read code now share the same routine for copying data into an xdr_buf. Now that skb_read_bits() is exported, rename it to avoid confusing it with a generic skb_* function. As these functions are XDR-specific, they should not have names that suggest they are of generic use. Also rename skb_read_and_csum_bits() to be consistent. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xdr.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 4d17846cd78a..a06aab278fe0 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -157,6 +157,7 @@ typedef struct { typedef size_t (*skb_read_actor_t)(skb_reader_t *desc, void *to, size_t len); +size_t xdr_skb_read_bits(skb_reader_t *desc, void *to, size_t len); extern int csum_partial_copy_to_xdr(struct xdr_buf *, struct sk_buff *); extern ssize_t xdr_partial_copy_from_skb(struct xdr_buf *, unsigned int, skb_reader_t *, skb_read_actor_t); -- cgit v1.2.3 From dd4564715eae2c4136f278da9ae1c3bb5af3e509 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 5 Dec 2006 16:35:44 -0500 Subject: SUNRPC: Rename skb_reader_t and friends Clean-up: hch suggested that the RPC client shouldn't pollute the name space used by the generic skb manipulation routines in net/core/skbuff.c. Rename a couple of types in xdr.h to adhere to this convention. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xdr.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index a06aab278fe0..9e340fa23c06 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -148,19 +148,19 @@ extern int write_bytes_to_xdr_buf(struct xdr_buf *, unsigned int, void *, unsign /* * Helper structure for copying from an sk_buff. */ -typedef struct { +struct xdr_skb_reader { struct sk_buff *skb; unsigned int offset; size_t count; __wsum csum; -} skb_reader_t; +}; -typedef size_t (*skb_read_actor_t)(skb_reader_t *desc, void *to, size_t len); +typedef size_t (*xdr_skb_read_actor)(struct xdr_skb_reader *desc, void *to, size_t len); -size_t xdr_skb_read_bits(skb_reader_t *desc, void *to, size_t len); +size_t xdr_skb_read_bits(struct xdr_skb_reader *desc, void *to, size_t len); extern int csum_partial_copy_to_xdr(struct xdr_buf *, struct sk_buff *); extern ssize_t xdr_partial_copy_from_skb(struct xdr_buf *, unsigned int, - skb_reader_t *, skb_read_actor_t); + struct xdr_skb_reader *, xdr_skb_read_actor); extern int xdr_encode_word(struct xdr_buf *, unsigned int, u32); extern int xdr_decode_word(struct xdr_buf *, unsigned int, u32 *); -- cgit v1.2.3 From 5847e1f4d058677c5e46dc6c3e3c70e8855ea3ba Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 5 Dec 2006 16:36:14 -0500 Subject: SUNRPC: Remove pprintk() from net/sunrpc/xprt.c These appear to be deprecated. Removing them also gets rid of some sparse noise. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/sunrpc/debug.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/debug.h b/include/linux/sunrpc/debug.h index e4729aa67654..60fce3c92857 100644 --- a/include/linux/sunrpc/debug.h +++ b/include/linux/sunrpc/debug.h @@ -62,12 +62,6 @@ extern unsigned int nlm_debug; # define RPC_IFDEBUG(x) #endif -#ifdef RPC_PROFILE -# define pprintk(args...) printk(## args) -#else -# define pprintk(args...) do ; while (0) -#endif - /* * Sysctl interface for RPC debugging */ -- cgit v1.2.3 From bb81a09e55eaf7e5f798468ab971469b6f66a259 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Thu, 7 Dec 2006 02:14:01 +0100 Subject: [PATCH] x86: all cpu backtrace When a spinlock lockup occurs, arrange for the NMI code to emit an all-cpu backtrace, so we get to see which CPU is holding the lock, and where. Cc: Andi Kleen Cc: Ingo Molnar Cc: Badari Pulavarty Signed-off-by: Andrew Morton Signed-off-by: Andi Kleen --- include/linux/nmi.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nmi.h b/include/linux/nmi.h index e16904e28c3a..acb4ed130247 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -15,9 +15,14 @@ * disables interrupts for a long time. This call is stateless. */ #ifdef ARCH_HAS_NMI_WATCHDOG +#include extern void touch_nmi_watchdog(void); #else # define touch_nmi_watchdog() touch_softlockup_watchdog() #endif +#ifndef trigger_all_cpu_backtrace +#define trigger_all_cpu_backtrace() do { } while (0) +#endif + #endif -- cgit v1.2.3 From 968de4f02621db35b8ae5239c8cfc6664fb872d8 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 7 Dec 2006 02:14:04 +0100 Subject: [PATCH] i386: Relocatable kernel support This patch modifies the i386 kernel so that if CONFIG_RELOCATABLE is selected it will be able to be loaded at any 4K aligned address below 1G. The technique used is to compile the decompressor with -fPIC and modify it so the decompressor is fully relocatable. For the main kernel relocations are generated. Resulting in a kernel that is relocatable with no runtime overhead and no need to modify the source code. A reserved 32bit word in the parameters has been assigned to serve as a stack so we figure out where are running. Signed-off-by: Eric W. Biederman Signed-off-by: Vivek Goyal Signed-off-by: Andi Kleen --- include/linux/screen_info.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/screen_info.h b/include/linux/screen_info.h index 2925e66a6732..b02308ee7667 100644 --- a/include/linux/screen_info.h +++ b/include/linux/screen_info.h @@ -42,7 +42,8 @@ struct screen_info { u16 pages; /* 0x32 */ u16 vesa_attributes; /* 0x34 */ u32 capabilities; /* 0x36 */ - /* 0x3a -- 0x3f reserved for future expansion */ + /* 0x3a -- 0x3b reserved for future expansion */ + /* 0x3c -- 0x3f micro stack for relocatable kernels */ }; extern struct screen_info screen_info; -- cgit v1.2.3 From 2fff0a48416af891dce38fd425246e337831e0bb Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Thu, 7 Dec 2006 02:14:05 +0100 Subject: [PATCH] Generic: Move __user cast into probe_kernel_address Caller of probe_kernel_address shouldn't need to know that pka is internally implemented with __get_user. So move the __user cast into pka. Signed-off-by: Andi Kleen --- include/linux/uaccess.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index a48d7f11c7be..65a68da8bd5d 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -36,7 +36,7 @@ static inline unsigned long __copy_from_user_nocache(void *to, long ret; \ \ inc_preempt_count(); \ - ret = __get_user(retval, addr); \ + ret = __get_user(retval, (__force typeof(*addr) __user *)addr);\ dec_preempt_count(); \ ret; \ }) -- cgit v1.2.3 From d7cd56111f30259e1b532a12e06f59f8e0a20355 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Thu, 7 Dec 2006 02:14:08 +0100 Subject: [PATCH] i386: cpu_detect extraction Both lhype and Xen want to call the core of the x86 cpu detect code before calling start_kernel. (extracted from larger patch) AK: folded in start_kernel header patch Signed-off-by: Jeremy Fitzhardinge Signed-off-by: Rusty Russell Signed-off-by: Andi Kleen Cc: Jeremy Fitzhardinge Cc: Andi Kleen Signed-off-by: Andrew Morton --- include/linux/start_kernel.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) create mode 100644 include/linux/start_kernel.h (limited to 'include/linux') diff --git a/include/linux/start_kernel.h b/include/linux/start_kernel.h new file mode 100644 index 000000000000..d3e5f2756545 --- /dev/null +++ b/include/linux/start_kernel.h @@ -0,0 +1,12 @@ +#ifndef _LINUX_START_KERNEL_H +#define _LINUX_START_KERNEL_H + +#include +#include + +/* Define the prototype for start_kernel here, rather than cluttering + up something else. */ + +extern asmlinkage void __init start_kernel(void); + +#endif /* _LINUX_START_KERNEL_H */ -- cgit v1.2.3 From 72486f1f8f0a2bc828b9d30cf4690cf2dd6807fc Mon Sep 17 00:00:00 2001 From: "Siddha, Suresh B" Date: Thu, 7 Dec 2006 02:14:10 +0100 Subject: [PATCH] i386: change the 'no_control' field to 'hotpluggable' in the struct cpu Change the 'no_control' field in the cpu struct to a more positive and better term 'hotpluggable'. And change(/cleanup) the logic accordingly. Signed-off-by: Suresh Siddha Signed-off-by: Andi Kleen Cc: Andi Kleen Cc: "Li, Shaohua" Signed-off-by: Andrew Morton --- 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 f02d71bf6894..ad90340e7dba 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -27,7 +27,7 @@ struct cpu { int node_id; /* The node which contains the CPU */ - int no_control; /* Should the sysfs control file be created? */ + int hotpluggable; /* creates sysfs control file if hotpluggable */ struct sys_device sysdev; }; -- cgit v1.2.3 From e1cccf48b182dd743c3c83a4fdf8dc570a43b393 Mon Sep 17 00:00:00 2001 From: Artiom Myaskouvskey Date: Thu, 7 Dec 2006 02:14:11 +0100 Subject: [PATCH] i386: call efi_get_time during suspend Function efi_get_time called not only during init kernel phase but also during suspend (from get_cmos_time). When it is called from get_cmos_time the corresponding runtime service should be called in virtual and not in physical mode. Signed-off-by: Artiom Myaskouvskey Signed-off-by: Andi Kleen Cc: "Narayanan, Chandramouli" Cc: "Jiossy, Rami" Cc: "Satt, Shai" Cc: Andi Kleen Cc: Matt Domsch Signed-off-by: Andrew Morton --- include/linux/efi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 66d621dbcb6c..91ecf49fbf21 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -300,7 +300,7 @@ extern int efi_mem_attribute_range (unsigned long phys_addr, unsigned long size, extern int __init efi_uart_console_only (void); extern void efi_initialize_iomem_resources(struct resource *code_resource, struct resource *data_resource); -extern unsigned long __init efi_get_time(void); +extern unsigned long efi_get_time(void); extern int __init efi_set_rtc_mmss(unsigned long nowtime); extern struct efi_memory_map memmap; -- cgit v1.2.3 From bf7e6a196318316e921f357557fca9d11d15f486 Mon Sep 17 00:00:00 2001 From: Artiom Myaskouvskey Date: Thu, 7 Dec 2006 02:14:11 +0100 Subject: [PATCH] i386: Preserve EFI run time regions with memmap parameter When using memmap kernel parameter in EFI boot we should also add to memory map memory regions of runtime services to enable their mapping later. AK: merged and cleaned up the patch Signed-off-by: Artiom Myaskouvskey Signed-off-by: Andi Kleen --- include/linux/efi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 91ecf49fbf21..df1c91855f0e 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -302,6 +302,7 @@ extern void efi_initialize_iomem_resources(struct resource *code_resource, struct resource *data_resource); extern unsigned long efi_get_time(void); extern int __init efi_set_rtc_mmss(unsigned long nowtime); +extern int is_available_memory(efi_memory_desc_t * md); extern struct efi_memory_map memmap; /** -- cgit v1.2.3 From 334c29a64507dda187565dd0db0403de3d70ec8b Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Mon, 4 Dec 2006 19:31:51 -0800 Subject: [GENETLINK]: Move command capabilities to flags. This patch moves command capabilities to command flags. Other than being cleaner, saves several bytes. We increment the nlctrl version so as to signal to user space that to not expect the attributes. We will try to be careful not to do this too often ;-> Signed-off-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/linux/genetlink.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/genetlink.h b/include/linux/genetlink.h index 9049dc65ae51..f7a93770e1be 100644 --- a/include/linux/genetlink.h +++ b/include/linux/genetlink.h @@ -17,6 +17,9 @@ struct genlmsghdr { #define GENL_HDRLEN NLMSG_ALIGN(sizeof(struct genlmsghdr)) #define GENL_ADMIN_PERM 0x01 +#define GENL_CMD_CAP_DO 0x02 +#define GENL_CMD_CAP_DUMP 0x04 +#define GENL_CMD_CAP_HASPOL 0x08 /* * List of reserved static generic netlink identifiers: @@ -58,9 +61,6 @@ enum { CTRL_ATTR_OP_UNSPEC, CTRL_ATTR_OP_ID, CTRL_ATTR_OP_FLAGS, - CTRL_ATTR_OP_POLICY, - CTRL_ATTR_OP_DOIT, - CTRL_ATTR_OP_DUMPIT, __CTRL_ATTR_OP_MAX, }; -- cgit v1.2.3 From 7cf4c1a5fd13820d7591179c0b925d739b2be9a7 Mon Sep 17 00:00:00 2001 From: Kazunori MIYAZAWA Date: Sat, 28 Oct 2006 13:21:22 +1000 Subject: [IPSEC]: Add support for AES-XCBC-MAC The glue of xfrm. Signed-off-by: Kazunori MIYAZAWA Signed-off-by: Herbert Xu --- include/linux/pfkeyv2.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pfkeyv2.h b/include/linux/pfkeyv2.h index 0f0b880c4280..265bafab6494 100644 --- a/include/linux/pfkeyv2.h +++ b/include/linux/pfkeyv2.h @@ -285,6 +285,7 @@ struct sadb_x_sec_ctx { #define SADB_X_AALG_SHA2_384HMAC 6 #define SADB_X_AALG_SHA2_512HMAC 7 #define SADB_X_AALG_RIPEMD160HMAC 8 +#define SADB_X_AALG_AES_XCBC_MAC 9 #define SADB_X_AALG_NULL 251 /* kame */ #define SADB_AALG_MAX 251 -- cgit v1.2.3 From cc44215eaaa5e4032946b962353526ae6c370c0e Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Wed, 22 Nov 2006 17:55:00 +1100 Subject: [CRYPTO] api: Remove unused functions This patch removes the following no longer used functions: - api.c: crypto_alg_available() - digest.c: crypto_digest_init() - digest.c: crypto_digest_update() - digest.c: crypto_digest_final() - digest.c: crypto_digest_digest() Signed-off-by: Adrian Bunk Signed-off-by: Herbert Xu --- include/linux/crypto.h | 22 ---------------------- 1 file changed, 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index 6485e9716b36..4aa9046601da 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -241,12 +241,8 @@ int crypto_unregister_alg(struct crypto_alg *alg); * Algorithm query interface. */ #ifdef CONFIG_CRYPTO -int crypto_alg_available(const char *name, u32 flags) - __deprecated_for_modules; int crypto_has_alg(const char *name, u32 type, u32 mask); #else -static int crypto_alg_available(const char *name, u32 flags) - __deprecated_for_modules; static inline int crypto_alg_available(const char *name, u32 flags) { return 0; @@ -707,16 +703,6 @@ static inline void crypto_cipher_decrypt_one(struct crypto_cipher *tfm, dst, src); } -void crypto_digest_init(struct crypto_tfm *tfm) __deprecated_for_modules; -void crypto_digest_update(struct crypto_tfm *tfm, - struct scatterlist *sg, unsigned int nsg) - __deprecated_for_modules; -void crypto_digest_final(struct crypto_tfm *tfm, u8 *out) - __deprecated_for_modules; -void crypto_digest_digest(struct crypto_tfm *tfm, - struct scatterlist *sg, unsigned int nsg, u8 *out) - __deprecated_for_modules; - static inline struct crypto_hash *__crypto_hash_cast(struct crypto_tfm *tfm) { return (struct crypto_hash *)tfm; @@ -729,14 +715,6 @@ static inline struct crypto_hash *crypto_hash_cast(struct crypto_tfm *tfm) return __crypto_hash_cast(tfm); } -static int crypto_digest_setkey(struct crypto_tfm *tfm, const u8 *key, - unsigned int keylen) __deprecated; -static inline int crypto_digest_setkey(struct crypto_tfm *tfm, - const u8 *key, unsigned int keylen) -{ - return tfm->crt_hash.setkey(crypto_hash_cast(tfm), key, keylen); -} - static inline struct crypto_hash *crypto_alloc_hash(const char *alg_name, u32 type, u32 mask) { -- cgit v1.2.3 From 9ee0779e994c6916863045297b831212e285da3b Mon Sep 17 00:00:00 2001 From: Yasuyuki Kozakai Date: Tue, 5 Dec 2006 13:44:31 -0800 Subject: [NETFILTER]: nf_conntrack: fix warning in PPTP helper Signed-off-by: Yasuyuki Kozakai Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter/nf_conntrack_pptp.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nf_conntrack_pptp.h b/include/linux/netfilter/nf_conntrack_pptp.h index fb049ec11ff2..9d8144a488cd 100644 --- a/include/linux/netfilter/nf_conntrack_pptp.h +++ b/include/linux/netfilter/nf_conntrack_pptp.h @@ -2,6 +2,8 @@ #ifndef _NF_CONNTRACK_PPTP_H #define _NF_CONNTRACK_PPTP_H +#include + /* state of the control session */ enum pptp_ctrlsess_state { PPTP_SESSION_NONE, /* no session present */ @@ -295,7 +297,6 @@ union pptp_ctrl_union { /* crap needed for nf_conntrack_compat.h */ struct nf_conn; struct nf_conntrack_expect; -enum ip_conntrack_info; extern int (*nf_nat_pptp_hook_outbound)(struct sk_buff **pskb, -- cgit v1.2.3 From 161a09e737f0761ca064ee6a907313402f7a54b6 Mon Sep 17 00:00:00 2001 From: Joy Latten Date: Mon, 27 Nov 2006 13:11:54 -0600 Subject: audit: Add auditing to ipsec An audit message occurs when an ipsec SA or ipsec policy is created/deleted. Signed-off-by: Joy Latten Signed-off-by: James Morris Signed-off-by: David S. Miller --- include/linux/audit.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index b2ca666d9997..0e07db6cc0d0 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -101,6 +101,10 @@ #define AUDIT_MAC_CIPSOV4_DEL 1408 /* NetLabel: del CIPSOv4 DOI entry */ #define AUDIT_MAC_MAP_ADD 1409 /* NetLabel: add LSM domain mapping */ #define AUDIT_MAC_MAP_DEL 1410 /* NetLabel: del LSM domain mapping */ +#define AUDIT_MAC_IPSEC_ADDSA 1411 /* Add a XFRM state */ +#define AUDIT_MAC_IPSEC_DELSA 1412 /* Delete a XFRM state */ +#define AUDIT_MAC_IPSEC_ADDSPD 1413 /* Add a XFRM policy */ +#define AUDIT_MAC_IPSEC_DELSPD 1414 /* Delete a XFRM policy */ #define AUDIT_FIRST_KERN_ANOM_MSG 1700 #define AUDIT_LAST_KERN_ANOM_MSG 1799 @@ -377,6 +381,7 @@ extern void auditsc_get_stamp(struct audit_context *ctx, struct timespec *t, unsigned int *serial); extern int audit_set_loginuid(struct task_struct *task, uid_t loginuid); extern uid_t audit_get_loginuid(struct audit_context *ctx); +extern void audit_log_task_context(struct audit_buffer *ab); extern int __audit_ipc_obj(struct kern_ipc_perm *ipcp); extern int __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, mode_t mode); extern int audit_bprm(struct linux_binprm *bprm); @@ -449,6 +454,7 @@ extern int audit_n_rules; #define audit_inode_update(i) do { ; } while (0) #define auditsc_get_stamp(c,t,s) do { BUG(); } while (0) #define audit_get_loginuid(c) ({ -1; }) +#define audit_log_task_context(b) do { ; } while (0) #define audit_ipc_obj(i) ({ 0; }) #define audit_ipc_set_perm(q,u,g,m) ({ 0; }) #define audit_bprm(p) ({ 0; }) -- cgit v1.2.3 From 676917d488212303ce4a7d033815ce8799201010 Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Thu, 7 Dec 2006 00:20:22 -0800 Subject: [TG3]: Add 5787F device ID. 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 c09da1e30c54..edddcce68b94 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1931,6 +1931,7 @@ #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_5787F 0x167f #define PCI_DEVICE_ID_TIGON3_5787M 0x1693 #define PCI_DEVICE_ID_TIGON3_5782 0x1696 #define PCI_DEVICE_ID_TIGON3_5786 0x169a -- cgit v1.2.3 From 9d26e213423923c9e033ccd373705118131827c9 Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Thu, 7 Dec 2006 00:21:14 -0800 Subject: [TG3]: Add TG3_FLG2_IS_NIC flag. Add Tg3_FLG2_IS_NIC flag to unambiguously determine whether the device is NIC or onboard. Previously, the EEPROM_WRITE_PROT flag was overloaded to also mean onboard. With the separation, we can support some devices that are onboard but do not use eeprom write protect. 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 edddcce68b94..ebc597d57242 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2003,6 +2003,8 @@ #define PCI_DEVICE_ID_FARSITE_TE1 0x1610 #define PCI_DEVICE_ID_FARSITE_TE1C 0x1612 +#define PCI_VENDOR_ID_ARIMA 0x161f + #define PCI_VENDOR_ID_SIBYTE 0x166d #define PCI_DEVICE_ID_BCM1250_PCI 0x0001 #define PCI_DEVICE_ID_BCM1250_HT 0x0002 -- cgit v1.2.3 From 676dcb8bc2ec78d80091037773598d6ec8c673d6 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Wed, 6 Dec 2006 20:31:30 -0800 Subject: [PATCH] add bottom_half.h With CONFIG_SMP=n: drivers/input/ff-memless.c:384: warning: implicit declaration of function 'local_bh_disable' drivers/input/ff-memless.c:393: warning: implicit declaration of function 'local_bh_enable' Really linux/spinlock.h should include linux/interrupt.h. But interrupt.h includes sched.h which will need spinlock.h. So the patch breaks the _bh declarations out into a separate header and includes it in both interrupt.h and spinlock.h. Cc: "Randy.Dunlap" Cc: Andi Kleen Cc: Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bottom_half.h | 10 ++++++++++ include/linux/interrupt.h | 7 +------ include/linux/spinlock.h | 1 + 3 files changed, 12 insertions(+), 6 deletions(-) create mode 100644 include/linux/bottom_half.h (limited to 'include/linux') diff --git a/include/linux/bottom_half.h b/include/linux/bottom_half.h new file mode 100644 index 000000000000..777dbf695d44 --- /dev/null +++ b/include/linux/bottom_half.h @@ -0,0 +1,10 @@ +#ifndef _LINUX_BH_H +#define _LINUX_BH_H + +extern void local_bh_disable(void); +extern void __local_bh_enable(void); +extern void _local_bh_enable(void); +extern void local_bh_enable(void); +extern void local_bh_enable_ip(unsigned long ip); + +#endif /* _LINUX_BH_H */ diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 5b83e7b59621..de7593f4e895 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include @@ -217,12 +218,6 @@ static inline void __deprecated save_and_cli(unsigned long *x) #define save_and_cli(x) save_and_cli(&x) #endif /* CONFIG_SMP */ -extern void local_bh_disable(void); -extern void __local_bh_enable(void); -extern void _local_bh_enable(void); -extern void local_bh_enable(void); -extern void local_bh_enable_ip(unsigned long ip); - /* PLEASE, avoid to allocate new softirqs, if you need not _really_ high frequency threaded job scheduling. For almost all the purposes tasklets are more than enough. F.e. all serial device BHs et diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index 8451052ca66f..94b767d64275 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -52,6 +52,7 @@ #include #include #include +#include #include -- cgit v1.2.3 From 89689ae7f95995723fbcd5c116c47933a3bb8b13 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Wed, 6 Dec 2006 20:31:45 -0800 Subject: [PATCH] Get rid of zone_table[] The zone table is mostly not needed. If we have a node in the page flags then we can get to the zone via NODE_DATA() which is much more likely to be already in the cpu cache. In case of SMP and UP NODE_DATA() is a constant pointer which allows us to access an exact replica of zonetable in the node_zones field. In all of the above cases there will be no need at all for the zone table. The only remaining case is if in a NUMA system the node numbers do not fit into the page flags. In that case we make sparse generate a table that maps sections to nodes and use that table to to figure out the node number. This table is sized to fit in a single cache line for the known 32 bit NUMA platform which makes it very likely that the information can be obtained without a cache miss. For sparsemem the zone table seems to be have been fairly large based on the maximum possible number of sections and the number of zones per node. There is some memory saving by removing zone_table. The main benefit is to reduce the cache foootprint of the VM from the frequent lookups of zones. Plus it simplifies the page allocator. [akpm@osdl.org: build fix] Signed-off-by: Christoph Lameter Cc: Dave Hansen Cc: Andy Whitcroft Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 57 ++++++++++++++++++++++++++++++++++-------------------- 1 file changed, 36 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index d538de901965..ab6e4974f379 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -396,7 +396,9 @@ void split_page(struct page *page, unsigned int order); * We are going to use the flags for the page to node mapping if its in * there. This includes the case where there is no node, so it is implicit. */ -#define FLAGS_HAS_NODE (NODES_WIDTH > 0 || NODES_SHIFT == 0) +#if !(NODES_WIDTH > 0 || NODES_SHIFT == 0) +#define NODE_NOT_IN_PAGE_FLAGS +#endif #ifndef PFN_SECTION_SHIFT #define PFN_SECTION_SHIFT 0 @@ -411,13 +413,18 @@ void split_page(struct page *page, unsigned int order); #define NODES_PGSHIFT (NODES_PGOFF * (NODES_WIDTH != 0)) #define ZONES_PGSHIFT (ZONES_PGOFF * (ZONES_WIDTH != 0)) -/* NODE:ZONE or SECTION:ZONE is used to lookup the zone from a page. */ -#if FLAGS_HAS_NODE -#define ZONETABLE_SHIFT (NODES_SHIFT + ZONES_SHIFT) +/* NODE:ZONE or SECTION:ZONE is used to ID a zone for the buddy allcator */ +#ifdef NODE_NOT_IN_PAGEFLAGS +#define ZONEID_SHIFT (SECTIONS_SHIFT + ZONES_SHIFT) #else -#define ZONETABLE_SHIFT (SECTIONS_SHIFT + ZONES_SHIFT) +#define ZONEID_SHIFT (NODES_SHIFT + ZONES_SHIFT) +#endif + +#if ZONES_WIDTH > 0 +#define ZONEID_PGSHIFT ZONES_PGSHIFT +#else +#define ZONEID_PGSHIFT NODES_PGOFF #endif -#define ZONETABLE_PGSHIFT ZONES_PGSHIFT #if SECTIONS_WIDTH+NODES_WIDTH+ZONES_WIDTH > FLAGS_RESERVED #error SECTIONS_WIDTH+NODES_WIDTH+ZONES_WIDTH > FLAGS_RESERVED @@ -426,23 +433,25 @@ void split_page(struct page *page, unsigned int order); #define ZONES_MASK ((1UL << ZONES_WIDTH) - 1) #define NODES_MASK ((1UL << NODES_WIDTH) - 1) #define SECTIONS_MASK ((1UL << SECTIONS_WIDTH) - 1) -#define ZONETABLE_MASK ((1UL << ZONETABLE_SHIFT) - 1) +#define ZONEID_MASK ((1UL << ZONEID_SHIFT) - 1) static inline enum zone_type page_zonenum(struct page *page) { return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK; } -struct zone; -extern struct zone *zone_table[]; - +/* + * The identification function is only used by the buddy allocator for + * determining if two pages could be buddies. We are not really + * identifying a zone since we could be using a the section number + * id if we have not node id available in page flags. + * We guarantee only that it will return the same value for two + * combinable pages in a zone. + */ static inline int page_zone_id(struct page *page) { - return (page->flags >> ZONETABLE_PGSHIFT) & ZONETABLE_MASK; -} -static inline struct zone *page_zone(struct page *page) -{ - return zone_table[page_zone_id(page)]; + BUILD_BUG_ON(ZONEID_PGSHIFT == 0 && ZONEID_MASK); + return (page->flags >> ZONEID_PGSHIFT) & ZONEID_MASK; } static inline unsigned long zone_to_nid(struct zone *zone) @@ -454,13 +463,20 @@ static inline unsigned long zone_to_nid(struct zone *zone) #endif } +#ifdef NODE_NOT_IN_PAGE_FLAGS +extern unsigned long page_to_nid(struct page *page); +#else static inline unsigned long page_to_nid(struct page *page) { - if (FLAGS_HAS_NODE) - return (page->flags >> NODES_PGSHIFT) & NODES_MASK; - else - return zone_to_nid(page_zone(page)); + return (page->flags >> NODES_PGSHIFT) & NODES_MASK; } +#endif + +static inline struct zone *page_zone(struct page *page) +{ + return &NODE_DATA(page_to_nid(page))->node_zones[page_zonenum(page)]; +} + static inline unsigned long page_to_section(struct page *page) { return (page->flags >> SECTIONS_PGSHIFT) & SECTIONS_MASK; @@ -477,6 +493,7 @@ static inline void set_page_node(struct page *page, unsigned long node) page->flags &= ~(NODES_MASK << NODES_PGSHIFT); page->flags |= (node & NODES_MASK) << NODES_PGSHIFT; } + static inline void set_page_section(struct page *page, unsigned long section) { page->flags &= ~(SECTIONS_MASK << SECTIONS_PGSHIFT); @@ -947,8 +964,6 @@ extern void mem_init(void); extern void show_mem(void); extern void si_meminfo(struct sysinfo * val); extern void si_meminfo_node(struct sysinfo *val, int nid); -extern void zonetable_add(struct zone *zone, int nid, enum zone_type zid, - unsigned long pfn, unsigned long size); #ifdef CONFIG_NUMA extern void setup_per_cpu_pageset(void); -- cgit v1.2.3 From 9276b1bc96a132f4068fdee00983c532f43d3a26 Mon Sep 17 00:00:00 2001 From: Paul Jackson Date: Wed, 6 Dec 2006 20:31:48 -0800 Subject: [PATCH] memory page_alloc zonelist caching speedup Optimize the critical zonelist scanning for free pages in the kernel memory allocator by caching the zones that were found to be full recently, and skipping them. Remembers the zones in a zonelist that were short of free memory in the last second. And it stashes a zone-to-node table in the zonelist struct, to optimize that conversion (minimize its cache footprint.) Recent changes: This differs in a significant way from a similar patch that I posted a week ago. Now, instead of having a nodemask_t of recently full nodes, I have a bitmask of recently full zones. This solves a problem that last weeks patch had, which on systems with multiple zones per node (such as DMA zone) would take seeing any of these zones full as meaning that all zones on that node were full. Also I changed names - from "zonelist faster" to "zonelist cache", as that seemed to better convey what we're doing here - caching some of the key zonelist state (for faster access.) See below for some performance benchmark results. After all that discussion with David on why I didn't need them, I went and got some ;). I wanted to verify that I had not hurt the normal case of memory allocation noticeably. At least for my one little microbenchmark, I found (1) the normal case wasn't affected, and (2) workloads that forced scanning across multiple nodes for memory improved up to 10% fewer System CPU cycles and lower elapsed clock time ('sys' and 'real'). Good. See details, below. I didn't have the logic in get_page_from_freelist() for various full nodes and zone reclaim failures correct. That should be fixed up now - notice the new goto labels zonelist_scan, this_zone_full, and try_next_zone, in get_page_from_freelist(). There are two reasons I persued this alternative, over some earlier proposals that would have focused on optimizing the fake numa emulation case by caching the last useful zone: 1) Contrary to what I said before, we (SGI, on large ia64 sn2 systems) have seen real customer loads where the cost to scan the zonelist was a problem, due to many nodes being full of memory before we got to a node we could use. Or at least, I think we have. This was related to me by another engineer, based on experiences from some time past. So this is not guaranteed. Most likely, though. The following approach should help such real numa systems just as much as it helps fake numa systems, or any combination thereof. 2) The effort to distinguish fake from real numa, using node_distance, so that we could cache a fake numa node and optimize choosing it over equivalent distance fake nodes, while continuing to properly scan all real nodes in distance order, was going to require a nasty blob of zonelist and node distance munging. The following approach has no new dependency on node distances or zone sorting. See comment in the patch below for a description of what it actually does. Technical details of note (or controversy): - See the use of "zlc_active" and "did_zlc_setup" below, to delay adding any work for this new mechanism until we've looked at the first zone in zonelist. I figured the odds of the first zone having the memory we needed were high enough that we should just look there, first, then get fancy only if we need to keep looking. - Some odd hackery was needed to add items to struct zonelist, while not tripping up the custom zonelists built by the mm/mempolicy.c code for MPOL_BIND. My usual wordy comments below explain this. Search for "MPOL_BIND". - Some per-node data in the struct zonelist is now modified frequently, with no locking. Multiple CPU cores on a node could hit and mangle this data. The theory is that this is just performance hint data, and the memory allocator will work just fine despite any such mangling. The fields at risk are the struct 'zonelist_cache' fields 'fullzones' (a bitmask) and 'last_full_zap' (unsigned long jiffies). It should all be self correcting after at most a one second delay. - This still does a linear scan of the same lengths as before. All I've optimized is making the scan faster, not algorithmically shorter. It is now able to scan a compact array of 'unsigned short' in the case of many full nodes, so one cache line should cover quite a few nodes, rather than each node hitting another one or two new and distinct cache lines. - If both Andi and Nick don't find this too complicated, I will be (pleasantly) flabbergasted. - I removed the comment claiming we only use one cachline's worth of zonelist. We seem, at least in the fake numa case, to have put the lie to that claim. - I pay no attention to the various watermarks and such in this performance hint. A node could be marked full for one watermark, and then skipped over when searching for a page using a different watermark. I think that's actually quite ok, as it will tend to slightly increase the spreading of memory over other nodes, away from a memory stressed node. =============== Performance - some benchmark results and analysis: This benchmark runs a memory hog program that uses multiple threads to touch alot of memory as quickly as it can. Multiple runs were made, touching 12, 38, 64 or 90 GBytes out of the total 96 GBytes on the system, and using 1, 19, 37, or 55 threads (on a 56 CPU system.) System, user and real (elapsed) timings were recorded for each run, shown in units of seconds, in the table below. Two kernels were tested - 2.6.18-mm3 and the same kernel with this zonelist caching patch added. The table also shows the percentage improvement the zonelist caching sys time is over (lower than) the stock *-mm kernel. number 2.6.18-mm3 zonelist-cache delta (< 0 good) percent GBs N ------------ -------------- ---------------- systime mem threads sys user real sys user real sys user real better 12 1 153 24 177 151 24 176 -2 0 -1 1% 12 19 99 22 8 99 22 8 0 0 0 0% 12 37 111 25 6 112 25 6 1 0 0 -0% 12 55 115 25 5 110 23 5 -5 -2 0 4% 38 1 502 74 576 497 73 570 -5 -1 -6 0% 38 19 426 78 48 373 76 39 -53 -2 -9 12% 38 37 544 83 36 547 82 36 3 -1 0 -0% 38 55 501 77 23 511 80 24 10 3 1 -1% 64 1 917 125 1042 890 124 1014 -27 -1 -28 2% 64 19 1118 138 119 965 141 103 -153 3 -16 13% 64 37 1202 151 94 1136 150 81 -66 -1 -13 5% 64 55 1118 141 61 1072 140 58 -46 -1 -3 4% 90 1 1342 177 1519 1275 174 1450 -67 -3 -69 4% 90 19 2392 199 192 2116 189 176 -276 -10 -16 11% 90 37 3313 238 175 2972 225 145 -341 -13 -30 10% 90 55 1948 210 104 1843 213 100 -105 3 -4 5% Notes: 1) This test ran a memory hog program that started a specified number N of threads, and had each thread allocate and touch 1/N'th of the total memory to be used in the test run in a single loop, writing a constant word to memory, one store every 4096 bytes. Watching this test during some earlier trial runs, I would see each of these threads sit down on one CPU and stay there, for the remainder of the pass, a different CPU for each thread. 2) The 'real' column is not comparable to the 'sys' or 'user' columns. The 'real' column is seconds wall clock time elapsed, from beginning to end of that test pass. The 'sys' and 'user' columns are total CPU seconds spent on that test pass. For a 19 thread test run, for example, the sum of 'sys' and 'user' could be up to 19 times the number of 'real' elapsed wall clock seconds. 3) Tests were run on a fresh, single-user boot, to minimize the amount of memory already in use at the start of the test, and to minimize the amount of background activity that might interfere. 4) Tests were done on a 56 CPU, 28 Node system with 96 GBytes of RAM. 5) Notice that the 'real' time gets large for the single thread runs, even though the measured 'sys' and 'user' times are modest. I'm not sure what that means - probably something to do with it being slow for one thread to be accessing memory along ways away. Perhaps the fake numa system, running ostensibly the same workload, would not show this substantial degradation of 'real' time for one thread on many nodes -- lets hope not. 6) The high thread count passes (one thread per CPU - on 55 of 56 CPUs) ran quite efficiently, as one might expect. Each pair of threads needed to allocate and touch the memory on the node the two threads shared, a pleasantly parallizable workload. 7) The intermediate thread count passes, when asking for alot of memory forcing them to go to a few neighboring nodes, improved the most with this zonelist caching patch. Conclusions: * This zonelist cache patch probably makes little difference one way or the other for most workloads on real numa hardware, if those workloads avoid heavy off node allocations. * For memory intensive workloads requiring substantial off-node allocations on real numa hardware, this patch improves both kernel and elapsed timings up to ten per-cent. * For fake numa systems, I'm optimistic, but will have to leave that up to Rohit Seth to actually test (once I get him a 2.6.18 backport.) Signed-off-by: Paul Jackson Cc: Rohit Seth Cc: Christoph Lameter Cc: David Rientjes Cc: Paul Menage Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cpuset.h | 2 ++ include/linux/mmzone.h | 85 +++++++++++++++++++++++++++++++++++++++++++++++--- 2 files changed, 82 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index 4d8adf663681..748d2c996631 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -23,6 +23,7 @@ extern void cpuset_fork(struct task_struct *p); extern void cpuset_exit(struct task_struct *p); extern cpumask_t cpuset_cpus_allowed(struct task_struct *p); extern nodemask_t cpuset_mems_allowed(struct task_struct *p); +#define cpuset_current_mems_allowed (current->mems_allowed) void cpuset_init_current_mems_allowed(void); void cpuset_update_task_memory_state(void); #define cpuset_nodes_subset_current_mems_allowed(nodes) \ @@ -83,6 +84,7 @@ static inline nodemask_t cpuset_mems_allowed(struct task_struct *p) return node_possible_map; } +#define cpuset_current_mems_allowed (node_online_map) static inline void cpuset_init_current_mems_allowed(void) {} static inline void cpuset_update_task_memory_state(void) {} #define cpuset_nodes_subset_current_mems_allowed(nodes) (1) diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index e06683e2bea3..09bf9d8d7b72 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -288,19 +288,94 @@ struct zone { */ #define DEF_PRIORITY 12 +/* Maximum number of zones on a zonelist */ +#define MAX_ZONES_PER_ZONELIST (MAX_NUMNODES * MAX_NR_ZONES) + +#ifdef CONFIG_NUMA +/* + * We cache key information from each zonelist for smaller cache + * footprint when scanning for free pages in get_page_from_freelist(). + * + * 1) The BITMAP fullzones tracks which zones in a zonelist have come + * up short of free memory since the last time (last_fullzone_zap) + * we zero'd fullzones. + * 2) The array z_to_n[] maps each zone in the zonelist to its node + * id, so that we can efficiently evaluate whether that node is + * set in the current tasks mems_allowed. + * + * Both fullzones and z_to_n[] are one-to-one with the zonelist, + * indexed by a zones offset in the zonelist zones[] array. + * + * The get_page_from_freelist() routine does two scans. During the + * first scan, we skip zones whose corresponding bit in 'fullzones' + * is set or whose corresponding node in current->mems_allowed (which + * comes from cpusets) is not set. During the second scan, we bypass + * this zonelist_cache, to ensure we look methodically at each zone. + * + * Once per second, we zero out (zap) fullzones, forcing us to + * reconsider nodes that might have regained more free memory. + * The field last_full_zap is the time we last zapped fullzones. + * + * This mechanism reduces the amount of time we waste repeatedly + * reexaming zones for free memory when they just came up low on + * memory momentarilly ago. + * + * The zonelist_cache struct members logically belong in struct + * zonelist. However, the mempolicy zonelists constructed for + * MPOL_BIND are intentionally variable length (and usually much + * shorter). A general purpose mechanism for handling structs with + * multiple variable length members is more mechanism than we want + * here. We resort to some special case hackery instead. + * + * The MPOL_BIND zonelists don't need this zonelist_cache (in good + * part because they are shorter), so we put the fixed length stuff + * at the front of the zonelist struct, ending in a variable length + * zones[], as is needed by MPOL_BIND. + * + * Then we put the optional zonelist cache on the end of the zonelist + * struct. This optional stuff is found by a 'zlcache_ptr' pointer in + * the fixed length portion at the front of the struct. This pointer + * both enables us to find the zonelist cache, and in the case of + * MPOL_BIND zonelists, (which will just set the zlcache_ptr to NULL) + * to know that the zonelist cache is not there. + * + * The end result is that struct zonelists come in two flavors: + * 1) The full, fixed length version, shown below, and + * 2) The custom zonelists for MPOL_BIND. + * The custom MPOL_BIND zonelists have a NULL zlcache_ptr and no zlcache. + * + * Even though there may be multiple CPU cores on a node modifying + * fullzones or last_full_zap in the same zonelist_cache at the same + * time, we don't lock it. This is just hint data - if it is wrong now + * and then, the allocator will still function, perhaps a bit slower. + */ + + +struct zonelist_cache { + DECLARE_BITMAP(fullzones, MAX_ZONES_PER_ZONELIST); /* zone full? */ + unsigned short z_to_n[MAX_ZONES_PER_ZONELIST]; /* zone->nid */ + unsigned long last_full_zap; /* when last zap'd (jiffies) */ +}; +#else +struct zonelist_cache; +#endif + /* * One allocation request operates on a zonelist. A zonelist * is a list of zones, the first one is the 'goal' of the * allocation, the other zones are fallback zones, in decreasing * priority. * - * Right now a zonelist takes up less than a cacheline. We never - * modify it apart from boot-up, and only a few indices are used, - * so despite the zonelist table being relatively big, the cache - * footprint of this construct is very small. + * If zlcache_ptr is not NULL, then it is just the address of zlcache, + * as explained above. If zlcache_ptr is NULL, there is no zlcache. */ + struct zonelist { - struct zone *zones[MAX_NUMNODES * MAX_NR_ZONES + 1]; // NULL delimited + struct zonelist_cache *zlcache_ptr; // NULL or &zlcache + struct zone *zones[MAX_ZONES_PER_ZONELIST + 1]; // NULL delimited +#ifdef CONFIG_NUMA + struct zonelist_cache zlcache; // optional ... +#endif }; #ifdef CONFIG_ARCH_POPULATES_NODE_MAP -- cgit v1.2.3 From 7253f4ef04b1cd138baf2b29a95473743ac0a307 Mon Sep 17 00:00:00 2001 From: Paul Jackson Date: Wed, 6 Dec 2006 20:31:49 -0800 Subject: [PATCH] memory page_alloc zonelist caching reorder structure Rearrange the struct members in the 'struct zonelist_cache' structure, so as to put the readonly (once initialized) z_to_n[] array first, where it will come right after the zones[] array in struct zonelist. This pretty much eliminates the chance that the two frequently written elements of 'struct zonelist_cache', the fullzones bitmap and last_full_zap times, will end up on the same cache line as the performance sensitive, frequently read, never (after init) written zones[] array. Keeping frequently written data off frequently read cache lines is good for performance. Thanks to Rohit Seth for the suggestion. Signed-off-by: Paul Jackson Cc: Rohit Seth Cc: Paul Menage Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 09bf9d8d7b72..da6002dec205 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -352,8 +352,8 @@ struct zone { struct zonelist_cache { - DECLARE_BITMAP(fullzones, MAX_ZONES_PER_ZONELIST); /* zone full? */ unsigned short z_to_n[MAX_ZONES_PER_ZONELIST]; /* zone->nid */ + DECLARE_BITMAP(fullzones, MAX_ZONES_PER_ZONELIST); /* zone full? */ unsigned long last_full_zap; /* when last zap'd (jiffies) */ }; #else -- cgit v1.2.3 From 7602bdf2fd14a40dd9b104e516fdc05e1bd17952 Mon Sep 17 00:00:00 2001 From: Ashwin Chaugule Date: Wed, 6 Dec 2006 20:31:57 -0800 Subject: [PATCH] new scheme to preempt swap token The new swap token patches replace the current token traversal algo. The old algo had a crude timeout parameter that was used to handover the token from one task to another. This algo, transfers the token to the tasks that are in need of the token. The urgency for the token is based on the number of times a task is required to swap-in pages. Accordingly, the priority of a task is incremented if it has been badly affected due to swap-outs. To ensure that the token doesnt bounce around rapidly, the token holders are given a priority boost. The priority of tasks is also decremented, if their rate of swap-in's keeps reducing. This way, the condition to check whether to pre-empt the swap token, is a matter of comparing two task's priority fields. [akpm@osdl.org: cleanups] Signed-off-by: Ashwin Chaugule Cc: Rik van Riel Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 13 ++++++++++--- include/linux/swap.h | 1 - 2 files changed, 10 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index eafe4a7b8237..cad6a16260f7 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -344,9 +344,16 @@ struct mm_struct { /* Architecture-specific MM context */ mm_context_t context; - /* Token based thrashing protection. */ - unsigned long swap_token_time; - char recent_pagein; + /* Swap token stuff */ + /* + * Last value of global fault stamp as seen by this process. + * In other words, this value gives an indication of how long + * it has been since this task got the token. + * Look at mm/thrash.c + */ + unsigned int faultstamp; + unsigned int token_priority; + unsigned int last_interval; /* coredumping support */ int core_waiters; diff --git a/include/linux/swap.h b/include/linux/swap.h index e7c36ba2a2db..89f8a39773bf 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -259,7 +259,6 @@ extern spinlock_t swap_lock; /* linux/mm/thrash.c */ extern struct mm_struct * swap_token_mm; -extern unsigned long swap_token_default_timeout; extern void grab_swap_token(void); extern void __put_swap_token(struct mm_struct *); -- cgit v1.2.3 From cc102509074bba0316f2b5deebd7ef4447da295e Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Wed, 6 Dec 2006 20:32:00 -0800 Subject: [PATCH] mm: add arch_alloc_page Add an arch_alloc_page to match arch_free_page. Signed-off-by: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index bf2b6bc3f6fd..00c314aedab7 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -116,6 +116,9 @@ static inline enum zone_type gfp_zone(gfp_t flags) #ifndef HAVE_ARCH_FREE_PAGE static inline void arch_free_page(struct page *page, int order) { } #endif +#ifndef HAVE_ARCH_ALLOC_PAGE +static inline void arch_alloc_page(struct page *page, int order) { } +#endif extern struct page * FASTCALL(__alloc_pages(gfp_t, unsigned int, struct zonelist *)); -- cgit v1.2.3 From 39dde65c9940c97fcd178a3d2b1c57ed8b7b68aa Mon Sep 17 00:00:00 2001 From: "Chen, Kenneth W" Date: Wed, 6 Dec 2006 20:32:03 -0800 Subject: [PATCH] shared page table for hugetlb page Following up with the work on shared page table done by Dave McCracken. This set of patch target shared page table for hugetlb memory only. The shared page table is particular useful in the situation of large number of independent processes sharing large shared memory segments. In the normal page case, the amount of memory saved from process' page table is quite significant. For hugetlb, the saving on page table memory is not the primary objective (as hugetlb itself already cuts down page table overhead significantly), instead, the purpose of using shared page table on hugetlb is to allow faster TLB refill and smaller cache pollution upon TLB miss. With PT sharing, pte entries are shared among hundreds of processes, the cache consumption used by all the page table is smaller and in return, application gets much higher cache hit ratio. One other effect is that cache hit ratio with hardware page walker hitting on pte in cache will be higher and this helps to reduce tlb miss latency. These two effects contribute to higher application performance. Signed-off-by: Ken Chen Acked-by: Hugh Dickins Cc: Dave McCracken Cc: William Lee Irwin III Cc: "Luck, Tony" Cc: Paul Mackerras Cc: Benjamin Herrenschmidt Cc: David Gibson Cc: Adam Litke Cc: Paul Mundt Cc: "David S. Miller" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index ace64e57e17f..a60995afe334 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -35,6 +35,7 @@ extern int sysctl_hugetlb_shm_group; pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr); pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr); +int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep); 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, -- cgit v1.2.3 From a866374aecc90c7d90619727ccd851ac096b2fc7 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 6 Dec 2006 20:32:20 -0800 Subject: [PATCH] mm: pagefault_{disable,enable}() Introduce pagefault_{disable,enable}() and use these where previously we did manual preempt increments/decrements to make the pagefault handler do the atomic thing. Currently they still rely on the increased preempt count, but do not rely on the disabled preemption, this might go away in the future. (NOTE: the extra barrier() in pagefault_disable might fix some holes on machines which have too many registers for their own good) [heiko.carstens@de.ibm.com: s390 fix] Signed-off-by: Peter Zijlstra Acked-by: Nick Piggin Cc: Martin Schwidefsky Signed-off-by: Heiko Carstens Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/uaccess.h | 39 +++++++++++++++++++++++++++++++++++++-- 1 file changed, 37 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index a48d7f11c7be..67918c22339c 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -1,8 +1,43 @@ #ifndef __LINUX_UACCESS_H__ #define __LINUX_UACCESS_H__ +#include #include +/* + * These routines enable/disable the pagefault handler in that + * it will not take any locks and go straight to the fixup table. + * + * They have great resemblance to the preempt_disable/enable calls + * and in fact they are identical; this is because currently there is + * no other way to make the pagefault handlers do this. So we do + * disable preemption but we don't necessarily care about that. + */ +static inline void pagefault_disable(void) +{ + inc_preempt_count(); + /* + * make sure to have issued the store before a pagefault + * can hit. + */ + barrier(); +} + +static inline void pagefault_enable(void) +{ + /* + * make sure to issue those last loads/stores before enabling + * the pagefault handler again. + */ + barrier(); + dec_preempt_count(); + /* + * make sure we do.. + */ + barrier(); + preempt_check_resched(); +} + #ifndef ARCH_HAS_NOCACHE_UACCESS static inline unsigned long __copy_from_user_inatomic_nocache(void *to, @@ -35,9 +70,9 @@ static inline unsigned long __copy_from_user_nocache(void *to, ({ \ long ret; \ \ - inc_preempt_count(); \ + pagefault_disable(); \ ret = __get_user(retval, addr); \ - dec_preempt_count(); \ + pagefault_enable(); \ ret; \ }) -- cgit v1.2.3 From ad76fb6b5a5183255279e0ab5260715481770678 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 6 Dec 2006 20:32:21 -0800 Subject: [PATCH] mm: k{,um}map_atomic() vs in_atomic() Make kmap_atomic/kunmap_atomic denote a pagefault disabled scope. All non trivial implementations already do this anyway. Signed-off-by: Peter Zijlstra Acked-by: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/highmem.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/highmem.h b/include/linux/highmem.h index fd7d12daa94f..3d8768b619e9 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -3,6 +3,7 @@ #include #include +#include #include @@ -41,9 +42,10 @@ static inline void *kmap(struct page *page) #define kunmap(page) do { (void) (page); } while (0) -#define kmap_atomic(page, idx) page_address(page) -#define kunmap_atomic(addr, idx) do { } while (0) -#define kmap_atomic_pfn(pfn, idx) page_address(pfn_to_page(pfn)) +#define kmap_atomic(page, idx) \ + ({ pagefault_disable(); page_address(page); }) +#define kunmap_atomic(addr, idx) do { pagefault_enable(); } while (0) +#define kmap_atomic_pfn(pfn, idx) kmap_atomic(pfn_to_page(pfn), (idx)) #define kmap_atomic_to_page(ptr) virt_to_page(ptr) #endif -- cgit v1.2.3 From 8b98c1699eba23cfd2e8b366625c50ff5fd1415b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 6 Dec 2006 20:32:30 -0800 Subject: [PATCH] leak tracking for kmalloc_node We have variants of kmalloc and kmem_cache_alloc that leave leak tracking to the caller. This is used for subsystem-specific allocators like skb_alloc. To make skb_alloc node-aware we need similar routines for the node-aware slab allocator, which this patch adds. Note that the code is rather ugly, but it mirrors the non-node-aware code 1:1: [akpm@osdl.org: add module export] Signed-off-by: Christoph Hellwig Cc: Al Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index c4947b8a2c03..66c4640d3656 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -236,7 +236,25 @@ found: } return __kmalloc_node(size, flags, node); } + +/* + * kmalloc_node_track_caller is a special version of kmalloc_node that + * records the calling function of the routine calling it for slab leak + * tracking instead of just the calling function (confusing, eh?). + * It's useful when the call to kmalloc_node comes from a widely-used + * standard allocator where we care about the real place the memory + * allocation request comes from. + */ +#ifndef CONFIG_DEBUG_SLAB +#define kmalloc_node_track_caller(size, flags, node) \ + __kmalloc_node(size, flags, node) #else +extern void *__kmalloc_node_track_caller(size_t, gfp_t, int, void *); +#define kmalloc_node_track_caller(size, flags, node) \ + __kmalloc_node_track_caller(size, flags, node, \ + __builtin_return_address(0)) +#endif +#else /* CONFIG_NUMA */ static inline void *kmem_cache_alloc_node(kmem_cache_t *cachep, gfp_t flags, int node) { return kmem_cache_alloc(cachep, flags); @@ -245,6 +263,9 @@ static inline void *kmalloc_node(size_t size, gfp_t flags, int node) { return kmalloc(size, flags); } + +#define kmalloc_node_track_caller(size, flags, node) \ + kmalloc_track_caller(size, flags) #endif extern int FASTCALL(kmem_cache_reap(int)); @@ -283,6 +304,8 @@ static inline void *kcalloc(size_t n, size_t size, gfp_t flags) #define kzalloc(s, f) __kzalloc(s, f) #define kmalloc_track_caller kmalloc +#define kmalloc_node_track_caller kmalloc_node + #endif /* CONFIG_SLOB */ /* System wide caches */ -- cgit v1.2.3 From 873481367edb18a7d0d7e5a285e6728c16bb44a9 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 6 Dec 2006 20:32:33 -0800 Subject: [PATCH] add numa node information to struct device For node-aware skb allocations we need information about the node in struct net_device or struct device. Davem suggested to put it into struct device which this patch does. In particular: - struct device gets a new int numa_node member if CONFIG_NUMA is set - there are two new helpers, dev_to_node and set_dev_node to transparently deal with the non-numa case - for pci devices the node-info is set to the value we get from pcibus_to_node. Note that for some architectures pcibus_to_node doesn't work yet at the time we call it currently. This is harmless and will just mean skb allocations aren't node-local on this architectures until the implementation of pcibus_to_node on these architectures have been updated (There are patches for x86 and x86_64 floating around) [akpm@osdl.org: cleanup] Signed-off-by: Christoph Hellwig Cc: Christoph Lameter Cc: Greg KH Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/device.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 583a341e016c..49ab53ce92dc 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -371,6 +371,9 @@ struct device { core doesn't touch it */ struct dev_pm_info power; +#ifdef CONFIG_NUMA + int numa_node; /* NUMA node this device is close to */ +#endif u64 *dma_mask; /* dma mask (if dma'able device) */ u64 coherent_dma_mask;/* Like dma_mask, but for alloc_coherent mappings as @@ -394,6 +397,25 @@ struct device { void (*release)(struct device * dev); }; +#ifdef CONFIG_NUMA +static inline int dev_to_node(struct device *dev) +{ + return dev->numa_node; +} +static inline void set_dev_node(struct device *dev, int node) +{ + dev->numa_node = node; +} +#else +static inline int dev_to_node(struct device *dev) +{ + return -1; +} +static inline void set_dev_node(struct device *dev, int node) +{ +} +#endif + static inline void * dev_get_drvdata (struct device *dev) { -- cgit v1.2.3 From b30973f877fea1a3fb84e05599890fcc082a88e5 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 6 Dec 2006 20:32:36 -0800 Subject: [PATCH] node-aware skb allocation Node-aware allocation of skbs for the receive path. Details: - __alloc_skb gets a new node argument and cals the node-aware slab functions with it. - netdev_alloc_skb passed the node number it gets from dev_to_node to it, everyone else passes -1 (any node) Signed-off-by: Christoph Hellwig Cc: Christoph Lameter Cc: "David S. Miller" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/skbuff.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index a05a5f7c0b73..1d649f3eb006 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -332,17 +332,17 @@ struct sk_buff { 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); + gfp_t priority, int fclone, int node); static inline struct sk_buff *alloc_skb(unsigned int size, gfp_t priority) { - return __alloc_skb(size, priority, 0); + return __alloc_skb(size, priority, 0, -1); } static inline struct sk_buff *alloc_skb_fclone(unsigned int size, gfp_t priority) { - return __alloc_skb(size, priority, 1); + return __alloc_skb(size, priority, 1, -1); } extern struct sk_buff *alloc_skb_from_cache(kmem_cache_t *cp, -- cgit v1.2.3 From 54cc211ce3fc73a9d21c6316886db0676beaca95 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Wed, 6 Dec 2006 20:32:45 -0800 Subject: [PATCH] Remove bio_cachep from slab.h Remove bio_cachep from slab.h - it no longer exists. Signed-off-by: Christoph Lameter 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 66c4640d3656..6b7d096f056b 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -315,7 +315,6 @@ extern kmem_cache_t *files_cachep; extern kmem_cache_t *filp_cachep; extern kmem_cache_t *fs_cachep; extern kmem_cache_t *sighand_cachep; -extern kmem_cache_t *bio_cachep; #endif /* __KERNEL__ */ -- cgit v1.2.3 From 298ec1e2ac85cecce3eddd167286359358c44d5d Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Wed, 6 Dec 2006 20:32:47 -0800 Subject: [PATCH] Move sighand_cachep to include/signal.h Move sighand_cachep definitioni to linux/signal.h The sighand cache is only used in fs/exec.c and kernel/fork.c. It is defined in kernel/fork.c but only used in fs/exec.c. The sighand_cachep is related to signal processing. So add the definition to signal.h. Signed-off-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/signal.h | 2 ++ include/linux/slab.h | 1 - 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/signal.h b/include/linux/signal.h index 117135e33d67..14749056dd63 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -241,6 +241,8 @@ extern int sigprocmask(int, sigset_t *, sigset_t *); struct pt_regs; extern int get_signal_to_deliver(siginfo_t *info, struct k_sigaction *return_ka, struct pt_regs *regs, void *cookie); +extern struct kmem_cache *sighand_cachep; + #endif /* __KERNEL__ */ #endif /* _LINUX_SIGNAL_H */ diff --git a/include/linux/slab.h b/include/linux/slab.h index 6b7d096f056b..467b297d2c6f 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -314,7 +314,6 @@ extern kmem_cache_t *names_cachep; extern kmem_cache_t *files_cachep; extern kmem_cache_t *filp_cachep; extern kmem_cache_t *fs_cachep; -extern kmem_cache_t *sighand_cachep; #endif /* __KERNEL__ */ -- cgit v1.2.3 From c43692e85f306667545b91194c748a6e46c1f8b4 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Wed, 6 Dec 2006 20:32:48 -0800 Subject: [PATCH] Move vm_area_cachep to include/mm.h vm_area_cachep is used to store vm_area_structs. So move to mm.h. Signed-off-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 ++ include/linux/slab.h | 1 - 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index ab6e4974f379..840303769c11 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -114,6 +114,8 @@ struct vm_area_struct { #endif }; +extern struct kmem_cache *vm_area_cachep; + /* * This struct defines the per-mm list of VMAs for uClinux. If CONFIG_MMU is * disabled, then there's a single shared list of VMAs maintained by the diff --git a/include/linux/slab.h b/include/linux/slab.h index 467b297d2c6f..a30a4028a92e 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -309,7 +309,6 @@ static inline void *kcalloc(size_t n, size_t size, gfp_t flags) #endif /* CONFIG_SLOB */ /* System wide caches */ -extern kmem_cache_t *vm_area_cachep; extern kmem_cache_t *names_cachep; extern kmem_cache_t *files_cachep; extern kmem_cache_t *filp_cachep; -- cgit v1.2.3 From 5d6538fcf231faccb2ac42f92851d259d00e62f9 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Wed, 6 Dec 2006 20:32:50 -0800 Subject: [PATCH] Move files_cachep to include/file.h Proper place is in file.h since files_cachep uses are rated to file I/O. Signed-off-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/file.h | 2 ++ include/linux/slab.h | 1 - 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/file.h b/include/linux/file.h index 74183e6f7f45..be37423e9920 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -114,4 +114,6 @@ struct files_struct *get_files_struct(struct task_struct *); void FASTCALL(put_files_struct(struct files_struct *fs)); void reset_files_struct(struct task_struct *, struct files_struct *); +extern struct kmem_cache *files_cachep; + #endif /* __LINUX_FILE_H */ diff --git a/include/linux/slab.h b/include/linux/slab.h index a30a4028a92e..dd9efecff410 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -310,7 +310,6 @@ static inline void *kcalloc(size_t n, size_t size, gfp_t flags) /* System wide caches */ extern kmem_cache_t *names_cachep; -extern kmem_cache_t *files_cachep; extern kmem_cache_t *filp_cachep; extern kmem_cache_t *fs_cachep; -- cgit v1.2.3 From 8b7d91eb7f6a3e8f0caaa613937bda5ab7dc7dc2 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Wed, 6 Dec 2006 20:32:52 -0800 Subject: [PATCH] Move filep_cachep to include/file.h filp_cachep is only used in fs/file_table.c and in fs/dcache.c where it is defined. Move it to related definitions in linux/file.h. Signed-off-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/file.h | 2 ++ include/linux/slab.h | 1 - 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/file.h b/include/linux/file.h index be37423e9920..6e77b9177f9e 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -64,6 +64,8 @@ struct files_struct { #define files_fdtable(files) (rcu_dereference((files)->fdt)) +extern struct kmem_cache *filp_cachep; + extern void FASTCALL(__fput(struct file *)); extern void FASTCALL(fput(struct file *)); diff --git a/include/linux/slab.h b/include/linux/slab.h index dd9efecff410..f9202d60d769 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -310,7 +310,6 @@ static inline void *kcalloc(size_t n, size_t size, gfp_t flags) /* System wide caches */ extern kmem_cache_t *names_cachep; -extern kmem_cache_t *filp_cachep; extern kmem_cache_t *fs_cachep; #endif /* __KERNEL__ */ -- cgit v1.2.3 From aa362a83e78d2e9320da588805cf2a0b53356bc3 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Wed, 6 Dec 2006 20:32:54 -0800 Subject: [PATCH] Move fs_cachep to linux/fs_struct.h fs_cachep is only used in kernel/exit.c and in kernel/fork.c. It is used to store fs_struct items so it should be placed in linux/fs_struct.h Signed-off-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs_struct.h | 2 ++ include/linux/slab.h | 1 - 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs_struct.h b/include/linux/fs_struct.h index c623d12a486e..11a36ceddf73 100644 --- a/include/linux/fs_struct.h +++ b/include/linux/fs_struct.h @@ -18,6 +18,8 @@ struct fs_struct { .umask = 0022, \ } +extern struct kmem_cache *fs_cachep; + extern void exit_fs(struct task_struct *); extern void set_fs_altroot(void); extern void set_fs_root(struct fs_struct *, struct vfsmount *, struct dentry *); diff --git a/include/linux/slab.h b/include/linux/slab.h index f9202d60d769..bfc063ee94e8 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -310,7 +310,6 @@ static inline void *kcalloc(size_t n, size_t size, gfp_t flags) /* System wide caches */ extern kmem_cache_t *names_cachep; -extern kmem_cache_t *fs_cachep; #endif /* __KERNEL__ */ -- cgit v1.2.3 From b86c089b83b8ae2bc814db865057768a9ba787b5 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Wed, 6 Dec 2006 20:32:57 -0800 Subject: [PATCH] Move names_cachep to linux/fs.h The names_cachep is used for getname() and putname(). So lets put it into fs.h near those two definitions. Signed-off-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 2 ++ include/linux/slab.h | 3 --- 2 files changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index cac7b1ef9543..a8039c8d8cbb 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1481,6 +1481,8 @@ extern char * getname(const char __user *); extern void __init vfs_caches_init_early(void); extern void __init vfs_caches_init(unsigned long); +extern struct kmem_cache *names_cachep; + #define __getname() kmem_cache_alloc(names_cachep, SLAB_KERNEL) #define __putname(name) kmem_cache_free(names_cachep, (void *)(name)) #ifndef CONFIG_AUDITSYSCALL diff --git a/include/linux/slab.h b/include/linux/slab.h index bfc063ee94e8..e67314e4a0a0 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -308,9 +308,6 @@ static inline void *kcalloc(size_t n, size_t size, gfp_t flags) #endif /* CONFIG_SLOB */ -/* System wide caches */ -extern kmem_cache_t *names_cachep; - #endif /* __KERNEL__ */ #endif /* _LINUX_SLAB_H */ -- cgit v1.2.3 From ebe29738f3934ad6a93c8bd76e30aa5d797a269d Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Wed, 6 Dec 2006 20:32:59 -0800 Subject: [PATCH] Remove uses of kmem_cache_t from mm/* and include/linux/slab.h Remove all uses of kmem_cache_t (the most were left in slab.h). The typedef for kmem_cache_t is then only necessary for other kernel subsystems. Add a comment to that effect. Signed-off-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab.h | 33 ++++++++++++++++++--------------- 1 file changed, 18 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index e67314e4a0a0..b831776b2fc7 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -9,6 +9,7 @@ #if defined(__KERNEL__) +/* kmem_cache_t exists for legacy reasons and is not used by code in mm */ typedef struct kmem_cache kmem_cache_t; #include @@ -57,22 +58,23 @@ typedef struct kmem_cache kmem_cache_t; /* prototypes */ extern void __init kmem_cache_init(void); -extern kmem_cache_t *kmem_cache_create(const char *, size_t, size_t, unsigned long, - void (*)(void *, kmem_cache_t *, unsigned long), - void (*)(void *, kmem_cache_t *, unsigned long)); -extern void kmem_cache_destroy(kmem_cache_t *); -extern int kmem_cache_shrink(kmem_cache_t *); -extern void *kmem_cache_alloc(kmem_cache_t *, gfp_t); +extern struct kmem_cache *kmem_cache_create(const char *, size_t, size_t, + unsigned long, + void (*)(void *, struct kmem_cache *, unsigned long), + void (*)(void *, struct kmem_cache *, unsigned long)); +extern void kmem_cache_destroy(struct kmem_cache *); +extern int kmem_cache_shrink(struct kmem_cache *); +extern void *kmem_cache_alloc(struct kmem_cache *, gfp_t); extern void *kmem_cache_zalloc(struct kmem_cache *, gfp_t); -extern void kmem_cache_free(kmem_cache_t *, void *); -extern unsigned int kmem_cache_size(kmem_cache_t *); -extern const char *kmem_cache_name(kmem_cache_t *); +extern void kmem_cache_free(struct kmem_cache *, void *); +extern unsigned int kmem_cache_size(struct kmem_cache *); +extern const char *kmem_cache_name(struct kmem_cache *); /* Size description struct for general caches. */ struct cache_sizes { - size_t cs_size; - kmem_cache_t *cs_cachep; - kmem_cache_t *cs_dmacachep; + size_t cs_size; + struct kmem_cache *cs_cachep; + struct kmem_cache *cs_dmacachep; }; extern struct cache_sizes malloc_sizes[]; @@ -211,7 +213,7 @@ extern unsigned int ksize(const void *); extern int slab_is_available(void); #ifdef CONFIG_NUMA -extern void *kmem_cache_alloc_node(kmem_cache_t *, gfp_t flags, int node); +extern void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node); extern void *__kmalloc_node(size_t size, gfp_t flags, int node); static inline void *kmalloc_node(size_t size, gfp_t flags, int node) @@ -255,7 +257,8 @@ extern void *__kmalloc_node_track_caller(size_t, gfp_t, int, void *); __builtin_return_address(0)) #endif #else /* CONFIG_NUMA */ -static inline void *kmem_cache_alloc_node(kmem_cache_t *cachep, gfp_t flags, int node) +static inline void *kmem_cache_alloc_node(struct kmem_cache *cachep, + gfp_t flags, int node) { return kmem_cache_alloc(cachep, flags); } @@ -269,7 +272,7 @@ static inline void *kmalloc_node(size_t size, gfp_t flags, int node) #endif extern int FASTCALL(kmem_cache_reap(int)); -extern int FASTCALL(kmem_ptr_validate(kmem_cache_t *cachep, void *ptr)); +extern int FASTCALL(kmem_ptr_validate(struct kmem_cache *cachep, void *ptr)); #else /* CONFIG_SLOB */ -- cgit v1.2.3 From 25ba77c141dbcd2602dd0171824d0d72aa023a01 Mon Sep 17 00:00:00 2001 From: Andy Whitcroft Date: Wed, 6 Dec 2006 20:33:03 -0800 Subject: [PATCH] numa node ids are int, page_to_nid and zone_to_nid should return int NUMA node ids are passed as either int or unsigned int almost exclusivly page_to_nid and zone_to_nid both return unsigned long. This is a throw back to when page_to_nid was a #define and was thus exposing the real type of the page flags field. In addition to fixing up the definitions of page_to_nid and zone_to_nid I audited the users of these functions identifying the following incorrect uses: 1) mm/page_alloc.c show_node() -- printk dumping the node id, 2) include/asm-ia64/pgalloc.h pgtable_quicklist_free() -- comparison against numa_node_id() which returns an int from cpu_to_node(), and 3) mm/mpolicy.c check_pte_range -- used as an index in node_isset which uses bit_set which in generic code takes an int. Signed-off-by: Andy Whitcroft Cc: Christoph Lameter Cc: "Luck, Tony" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 840303769c11..0e266fe1b4c4 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -456,7 +456,7 @@ static inline int page_zone_id(struct page *page) return (page->flags >> ZONEID_PGSHIFT) & ZONEID_MASK; } -static inline unsigned long zone_to_nid(struct zone *zone) +static inline int zone_to_nid(struct zone *zone) { #ifdef CONFIG_NUMA return zone->node; @@ -466,9 +466,9 @@ static inline unsigned long zone_to_nid(struct zone *zone) } #ifdef NODE_NOT_IN_PAGE_FLAGS -extern unsigned long page_to_nid(struct page *page); +extern int page_to_nid(struct page *page); #else -static inline unsigned long page_to_nid(struct page *page) +static inline int page_to_nid(struct page *page) { return (page->flags >> NODES_PGSHIFT) & NODES_MASK; } -- cgit v1.2.3 From 6e0eaa4b05cf53ca5caa702fd2760a5b3376be69 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Wed, 6 Dec 2006 20:33:10 -0800 Subject: [PATCH] slab: remove SLAB_NO_GROW It is only used internally in the slab. Signed-off-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index b831776b2fc7..9ffd1c1616bd 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -28,8 +28,6 @@ typedef struct kmem_cache kmem_cache_t; #define SLAB_LEVEL_MASK GFP_LEVEL_MASK -#define SLAB_NO_GROW __GFP_NO_GROW /* don't grow a cache */ - /* flags to pass to kmem_cache_create(). * The first 3 are only valid when the allocator as been build * SLAB_DEBUG_SUPPORT. -- cgit v1.2.3 From a06d72c1dcbff015250df6ad9f0b1d18c02113bf Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Wed, 6 Dec 2006 20:33:12 -0800 Subject: [PATCH] slab: remove SLAB_LEVEL_MASK SLAB_LEVEL_MASK is only used internally to the slab and is and alias of GFP_LEVEL_MASK. Signed-off-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 9ffd1c1616bd..6f7b9bb43065 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -26,8 +26,6 @@ typedef struct kmem_cache kmem_cache_t; #define SLAB_KERNEL GFP_KERNEL #define SLAB_DMA GFP_DMA -#define SLAB_LEVEL_MASK GFP_LEVEL_MASK - /* flags to pass to kmem_cache_create(). * The first 3 are only valid when the allocator as been build * SLAB_DEBUG_SUPPORT. -- cgit v1.2.3 From 55acbda0965ca0a29b0ca276e7d17a55edc11d1b Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Wed, 6 Dec 2006 20:33:13 -0800 Subject: [PATCH] slab: remove SLAB_NOIO SLAB_NOIO is an alias of GFP_NOIO with a single instance of use. Signed-off-by: Christoph Lameter 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 6f7b9bb43065..43ced80c327b 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -20,7 +20,6 @@ typedef struct kmem_cache kmem_cache_t; /* flags for kmem_cache_alloc() */ #define SLAB_NOFS GFP_NOFS -#define SLAB_NOIO GFP_NOIO #define SLAB_ATOMIC GFP_ATOMIC #define SLAB_USER GFP_USER #define SLAB_KERNEL GFP_KERNEL -- cgit v1.2.3 From e6b4f8da3a88457148038bc952043e99a7fdba64 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Wed, 6 Dec 2006 20:33:14 -0800 Subject: [PATCH] slab: remove SLAB_NOFS SLAB_NOFS is an alias of GFP_NOFS. Signed-off-by: Christoph Lameter 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 43ced80c327b..5b70d52b4f86 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -19,7 +19,6 @@ typedef struct kmem_cache kmem_cache_t; #include /* kmalloc_sizes.h needs L1_CACHE_BYTES */ /* flags for kmem_cache_alloc() */ -#define SLAB_NOFS GFP_NOFS #define SLAB_ATOMIC GFP_ATOMIC #define SLAB_USER GFP_USER #define SLAB_KERNEL GFP_KERNEL -- cgit v1.2.3 From f7267c0c0721fd02ad3dc37c3d6dd24ccd81d4d6 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Wed, 6 Dec 2006 20:33:15 -0800 Subject: [PATCH] slab: remove SLAB_USER SLAB_USER is an alias of GFP_USER Signed-off-by: Christoph Lameter 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 5b70d52b4f86..d7ee28e51330 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -20,7 +20,6 @@ typedef struct kmem_cache kmem_cache_t; /* flags for kmem_cache_alloc() */ #define SLAB_ATOMIC GFP_ATOMIC -#define SLAB_USER GFP_USER #define SLAB_KERNEL GFP_KERNEL #define SLAB_DMA GFP_DMA -- cgit v1.2.3 From 54e6ecb23951b195d02433a741c7f7cb0b796c78 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Wed, 6 Dec 2006 20:33:16 -0800 Subject: [PATCH] slab: remove SLAB_ATOMIC SLAB_ATOMIC is an alias of GFP_ATOMIC Signed-off-by: Christoph Lameter 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 d7ee28e51330..34b046ea88f1 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -19,7 +19,6 @@ typedef struct kmem_cache kmem_cache_t; #include /* kmalloc_sizes.h needs L1_CACHE_BYTES */ /* flags for kmem_cache_alloc() */ -#define SLAB_ATOMIC GFP_ATOMIC #define SLAB_KERNEL GFP_KERNEL #define SLAB_DMA GFP_DMA -- cgit v1.2.3 From e94b1766097d53e6f3ccfb36c8baa562ffeda3fc Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Wed, 6 Dec 2006 20:33:17 -0800 Subject: [PATCH] slab: remove SLAB_KERNEL SLAB_KERNEL is an alias of GFP_KERNEL. Signed-off-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 2 +- include/linux/rmap.h | 2 +- include/linux/slab.h | 1 - include/linux/taskstats_kern.h | 2 +- 4 files changed, 3 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index a8039c8d8cbb..94b831b8157c 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1483,7 +1483,7 @@ extern void __init vfs_caches_init(unsigned long); extern struct kmem_cache *names_cachep; -#define __getname() kmem_cache_alloc(names_cachep, SLAB_KERNEL) +#define __getname() kmem_cache_alloc(names_cachep, GFP_KERNEL) #define __putname(name) kmem_cache_free(names_cachep, (void *)(name)) #ifndef CONFIG_AUDITSYSCALL #define putname(name) __putname(name) diff --git a/include/linux/rmap.h b/include/linux/rmap.h index db2c1df4fef9..61c2ab634b00 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -34,7 +34,7 @@ extern kmem_cache_t *anon_vma_cachep; static inline struct anon_vma *anon_vma_alloc(void) { - return kmem_cache_alloc(anon_vma_cachep, SLAB_KERNEL); + return kmem_cache_alloc(anon_vma_cachep, GFP_KERNEL); } static inline void anon_vma_free(struct anon_vma *anon_vma) diff --git a/include/linux/slab.h b/include/linux/slab.h index 34b046ea88f1..639f65efa46e 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -19,7 +19,6 @@ typedef struct kmem_cache kmem_cache_t; #include /* kmalloc_sizes.h needs L1_CACHE_BYTES */ /* flags for kmem_cache_alloc() */ -#define SLAB_KERNEL GFP_KERNEL #define SLAB_DMA GFP_DMA /* flags to pass to kmem_cache_create(). diff --git a/include/linux/taskstats_kern.h b/include/linux/taskstats_kern.h index 6562a2050a25..f81a5af8a4f8 100644 --- a/include/linux/taskstats_kern.h +++ b/include/linux/taskstats_kern.h @@ -35,7 +35,7 @@ static inline void taskstats_tgid_alloc(struct task_struct *tsk) return; /* No problem if kmem_cache_zalloc() fails */ - stats = kmem_cache_zalloc(taskstats_cache, SLAB_KERNEL); + stats = kmem_cache_zalloc(taskstats_cache, GFP_KERNEL); spin_lock_irq(&tsk->sighand->siglock); if (!sig->stats) { -- cgit v1.2.3 From 441e143e95f5aa1e04026cb0aa71c801ba53982f Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Wed, 6 Dec 2006 20:33:19 -0800 Subject: [PATCH] slab: remove SLAB_DMA SLAB_DMA is an alias of GFP_DMA. This is the last one so we remove the leftover comment too. Signed-off-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 639f65efa46e..fbcfc208f52b 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -18,9 +18,6 @@ typedef struct kmem_cache kmem_cache_t; #include /* kmalloc_sizes.h needs PAGE_SIZE */ #include /* kmalloc_sizes.h needs L1_CACHE_BYTES */ -/* flags for kmem_cache_alloc() */ -#define SLAB_DMA GFP_DMA - /* flags to pass to kmem_cache_create(). * The first 3 are only valid when the allocator as been build * SLAB_DEBUG_SUPPORT. -- cgit v1.2.3 From e18b890bb0881bbab6f4f1a6cd20d9c60d66b003 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Wed, 6 Dec 2006 20:33:20 -0800 Subject: [PATCH] slab: remove kmem_cache_t Replace all uses of kmem_cache_t with struct kmem_cache. The patch was generated using the following script: #!/bin/sh # # Replace one string by another in all the kernel sources. # set -e for file in `find * -name "*.c" -o -name "*.h"|xargs grep -l $1`; do quilt add $file sed -e "1,\$s/$1/$2/g" $file >/tmp/$$ mv /tmp/$$ $file quilt refresh done The script was run like this sh replace kmem_cache_t "struct kmem_cache" Signed-off-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/delayacct.h | 2 +- include/linux/i2o.h | 2 +- include/linux/jbd.h | 2 +- include/linux/jbd2.h | 2 +- include/linux/raid/raid5.h | 2 +- include/linux/rmap.h | 2 +- include/linux/skbuff.h | 2 +- include/linux/taskstats_kern.h | 2 +- 8 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h index 561e2a77805c..55d1ca5e60f5 100644 --- a/include/linux/delayacct.h +++ b/include/linux/delayacct.h @@ -30,7 +30,7 @@ #ifdef CONFIG_TASK_DELAY_ACCT extern int delayacct_on; /* Delay accounting turned on/off */ -extern kmem_cache_t *delayacct_cache; +extern struct kmem_cache *delayacct_cache; extern void delayacct_init(void); extern void __delayacct_tsk_init(struct task_struct *); extern void __delayacct_tsk_exit(struct task_struct *); diff --git a/include/linux/i2o.h b/include/linux/i2o.h index 1fb02e17f6f6..2514f4e286b7 100644 --- a/include/linux/i2o.h +++ b/include/linux/i2o.h @@ -490,7 +490,7 @@ struct i2o_dma { */ struct i2o_pool { char *name; - kmem_cache_t *slab; + struct kmem_cache *slab; mempool_t *mempool; }; diff --git a/include/linux/jbd.h b/include/linux/jbd.h index fe89444b1c6f..dacd566c9f6c 100644 --- a/include/linux/jbd.h +++ b/include/linux/jbd.h @@ -949,7 +949,7 @@ void journal_put_journal_head(struct journal_head *jh); /* * handle management */ -extern kmem_cache_t *jbd_handle_cache; +extern struct kmem_cache *jbd_handle_cache; static inline handle_t *jbd_alloc_handle(gfp_t gfp_flags) { diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index ddb128795781..98a0ae52660f 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -958,7 +958,7 @@ void jbd2_journal_put_journal_head(struct journal_head *jh); /* * handle management */ -extern kmem_cache_t *jbd2_handle_cache; +extern struct kmem_cache *jbd2_handle_cache; static inline handle_t *jbd_alloc_handle(gfp_t gfp_flags) { diff --git a/include/linux/raid/raid5.h b/include/linux/raid/raid5.h index f13299a15591..03636d7918fe 100644 --- a/include/linux/raid/raid5.h +++ b/include/linux/raid/raid5.h @@ -235,7 +235,7 @@ struct raid5_private_data { */ int active_name; char cache_name[2][20]; - kmem_cache_t *slab_cache; /* for allocating stripes */ + struct kmem_cache *slab_cache; /* for allocating stripes */ int seq_flush, seq_write; int quiesce; diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 61c2ab634b00..36f850373d2c 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -30,7 +30,7 @@ struct anon_vma { #ifdef CONFIG_MMU -extern kmem_cache_t *anon_vma_cachep; +extern struct kmem_cache *anon_vma_cachep; static inline struct anon_vma *anon_vma_alloc(void) { diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 1d649f3eb006..4ff3940210d8 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -345,7 +345,7 @@ static inline struct sk_buff *alloc_skb_fclone(unsigned int size, return __alloc_skb(size, priority, 1, -1); } -extern struct sk_buff *alloc_skb_from_cache(kmem_cache_t *cp, +extern struct sk_buff *alloc_skb_from_cache(struct kmem_cache *cp, unsigned int size, gfp_t priority); extern void kfree_skbmem(struct sk_buff *skb); diff --git a/include/linux/taskstats_kern.h b/include/linux/taskstats_kern.h index f81a5af8a4f8..ce8a912e5426 100644 --- a/include/linux/taskstats_kern.h +++ b/include/linux/taskstats_kern.h @@ -12,7 +12,7 @@ #include #ifdef CONFIG_TASKSTATS -extern kmem_cache_t *taskstats_cache; +extern struct kmem_cache *taskstats_cache; extern struct mutex taskstats_exit_mutex; static inline void taskstats_exit_free(struct taskstats *tidstats) -- cgit v1.2.3 From 1b1cec4bbc59feac89670d5d6d222a02545bac94 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Wed, 6 Dec 2006 20:33:22 -0800 Subject: [PATCH] slab: deprecate kmem_cache_t Cc: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab.h | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index fbcfc208f52b..2271886744f8 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -7,16 +7,17 @@ #ifndef _LINUX_SLAB_H #define _LINUX_SLAB_H -#if defined(__KERNEL__) +#ifdef __KERNEL__ -/* kmem_cache_t exists for legacy reasons and is not used by code in mm */ -typedef struct kmem_cache kmem_cache_t; +#include +#include +#include +#include /* kmalloc_sizes.h needs PAGE_SIZE */ +#include /* kmalloc_sizes.h needs L1_CACHE_BYTES */ +#include -#include -#include -#include -#include /* kmalloc_sizes.h needs PAGE_SIZE */ -#include /* kmalloc_sizes.h needs L1_CACHE_BYTES */ +/* kmem_cache_t exists for legacy reasons and is not used by code in mm */ +typedef struct kmem_cache kmem_cache_t __deprecated; /* flags to pass to kmem_cache_create(). * The first 3 are only valid when the allocator as been build -- cgit v1.2.3 From 33f2ef89f8e181486b63fdbdc97c6afa6ca9f34b Mon Sep 17 00:00:00 2001 From: Andy Whitcroft Date: Wed, 6 Dec 2006 20:33:32 -0800 Subject: [PATCH] mm: make compound page destructor handling explicit Currently we we use the lru head link of the second page of a compound page to hold its destructor. This was ok when it was purely an internal implmentation detail. However, hugetlbfs overrides this destructor violating the layering. Abstract this out as explicit calls, also introduce a type for the callback function allowing them to be type checked. For each callback we pre-declare the function, causing a type error on definition rather than on use elsewhere. [akpm@osdl.org: cleanups] Signed-off-by: Andy Whitcroft Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 0e266fe1b4c4..a17b147c61e7 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -295,6 +295,24 @@ void put_pages_list(struct list_head *pages); void split_page(struct page *page, unsigned int order); +/* + * Compound pages have a destructor function. Provide a + * prototype for that function and accessor functions. + * These are _only_ valid on the head of a PG_compound page. + */ +typedef void compound_page_dtor(struct page *); + +static inline void set_compound_page_dtor(struct page *page, + compound_page_dtor *dtor) +{ + page[1].lru.next = (void *)dtor; +} + +static inline compound_page_dtor *get_compound_page_dtor(struct page *page) +{ + return (compound_page_dtor *)page[1].lru.next; +} + /* * 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 36de6437866bbb1d37e2312ff4f95ee4ed6d2b61 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 6 Dec 2006 20:33:42 -0800 Subject: [PATCH] Save some bytes in struct mm_struct Before: [acme@newtoy net-2.6.20]$ pahole --cacheline 32 kernel/sched.o mm_struct /* include2/asm/processor.h:542 */ struct mm_struct { struct vm_area_struct * mmap; /* 0 4 */ struct rb_root mm_rb; /* 4 4 */ struct vm_area_struct * mmap_cache; /* 8 4 */ long unsigned int (*get_unmapped_area)(); /* 12 4 */ void (*unmap_area)(); /* 16 4 */ long unsigned int mmap_base; /* 20 4 */ long unsigned int task_size; /* 24 4 */ long unsigned int cached_hole_size; /* 28 4 */ /* ---------- cacheline 1 boundary ---------- */ long unsigned int free_area_cache; /* 32 4 */ pgd_t * pgd; /* 36 4 */ atomic_t mm_users; /* 40 4 */ atomic_t mm_count; /* 44 4 */ int map_count; /* 48 4 */ struct rw_semaphore mmap_sem; /* 52 64 */ spinlock_t page_table_lock; /* 116 40 */ struct list_head mmlist; /* 156 8 */ mm_counter_t _file_rss; /* 164 4 */ mm_counter_t _anon_rss; /* 168 4 */ long unsigned int hiwater_rss; /* 172 4 */ long unsigned int hiwater_vm; /* 176 4 */ long unsigned int total_vm; /* 180 4 */ long unsigned int locked_vm; /* 184 4 */ long unsigned int shared_vm; /* 188 4 */ /* ---------- cacheline 6 boundary ---------- */ long unsigned int exec_vm; /* 192 4 */ long unsigned int stack_vm; /* 196 4 */ long unsigned int reserved_vm; /* 200 4 */ long unsigned int def_flags; /* 204 4 */ long unsigned int nr_ptes; /* 208 4 */ long unsigned int start_code; /* 212 4 */ long unsigned int end_code; /* 216 4 */ long unsigned int start_data; /* 220 4 */ /* ---------- cacheline 7 boundary ---------- */ long unsigned int end_data; /* 224 4 */ long unsigned int start_brk; /* 228 4 */ long unsigned int brk; /* 232 4 */ long unsigned int start_stack; /* 236 4 */ long unsigned int arg_start; /* 240 4 */ long unsigned int arg_end; /* 244 4 */ long unsigned int env_start; /* 248 4 */ long unsigned int env_end; /* 252 4 */ /* ---------- cacheline 8 boundary ---------- */ long unsigned int saved_auxv[44]; /* 256 176 */ unsigned int dumpable:2; /* 432 4 */ cpumask_t cpu_vm_mask; /* 436 4 */ mm_context_t context; /* 440 68 */ long unsigned int swap_token_time; /* 508 4 */ /* ---------- cacheline 16 boundary ---------- */ char recent_pagein; /* 512 1 */ /* XXX 3 bytes hole, try to pack */ int core_waiters; /* 516 4 */ struct completion * core_startup_done; /* 520 4 */ struct completion core_done; /* 524 52 */ rwlock_t ioctx_list_lock; /* 576 36 */ struct kioctx * ioctx_list; /* 612 4 */ }; /* size: 616, sum members: 613, holes: 1, sum holes: 3, cachelines: 20, last cacheline: 8 bytes */ After: [acme@newtoy net-2.6.20]$ pahole --cacheline 32 kernel/sched.o mm_struct /* include2/asm/processor.h:542 */ struct mm_struct { struct vm_area_struct * mmap; /* 0 4 */ struct rb_root mm_rb; /* 4 4 */ struct vm_area_struct * mmap_cache; /* 8 4 */ long unsigned int (*get_unmapped_area)(); /* 12 4 */ void (*unmap_area)(); /* 16 4 */ long unsigned int mmap_base; /* 20 4 */ long unsigned int task_size; /* 24 4 */ long unsigned int cached_hole_size; /* 28 4 */ /* ---------- cacheline 1 boundary ---------- */ long unsigned int free_area_cache; /* 32 4 */ pgd_t * pgd; /* 36 4 */ atomic_t mm_users; /* 40 4 */ atomic_t mm_count; /* 44 4 */ int map_count; /* 48 4 */ struct rw_semaphore mmap_sem; /* 52 64 */ spinlock_t page_table_lock; /* 116 40 */ struct list_head mmlist; /* 156 8 */ mm_counter_t _file_rss; /* 164 4 */ mm_counter_t _anon_rss; /* 168 4 */ long unsigned int hiwater_rss; /* 172 4 */ long unsigned int hiwater_vm; /* 176 4 */ long unsigned int total_vm; /* 180 4 */ long unsigned int locked_vm; /* 184 4 */ long unsigned int shared_vm; /* 188 4 */ /* ---------- cacheline 6 boundary ---------- */ long unsigned int exec_vm; /* 192 4 */ long unsigned int stack_vm; /* 196 4 */ long unsigned int reserved_vm; /* 200 4 */ long unsigned int def_flags; /* 204 4 */ long unsigned int nr_ptes; /* 208 4 */ long unsigned int start_code; /* 212 4 */ long unsigned int end_code; /* 216 4 */ long unsigned int start_data; /* 220 4 */ /* ---------- cacheline 7 boundary ---------- */ long unsigned int end_data; /* 224 4 */ long unsigned int start_brk; /* 228 4 */ long unsigned int brk; /* 232 4 */ long unsigned int start_stack; /* 236 4 */ long unsigned int arg_start; /* 240 4 */ long unsigned int arg_end; /* 244 4 */ long unsigned int env_start; /* 248 4 */ long unsigned int env_end; /* 252 4 */ /* ---------- cacheline 8 boundary ---------- */ long unsigned int saved_auxv[44]; /* 256 176 */ cpumask_t cpu_vm_mask; /* 432 4 */ mm_context_t context; /* 436 68 */ long unsigned int swap_token_time; /* 504 4 */ char recent_pagein; /* 508 1 */ unsigned char dumpable:2; /* 509 1 */ /* XXX 2 bytes hole, try to pack */ int core_waiters; /* 512 4 */ struct completion * core_startup_done; /* 516 4 */ struct completion core_done; /* 520 52 */ rwlock_t ioctx_list_lock; /* 572 36 */ struct kioctx * ioctx_list; /* 608 4 */ }; /* size: 612, sum members: 610, holes: 1, sum holes: 2, cachelines: 20, last cacheline: 4 bytes */ [acme@newtoy net-2.6.20]$ codiff -V /tmp/sched.o.before kernel/sched.o /pub/scm/linux/kernel/git/acme/net-2.6.20/kernel/sched.c: struct mm_struct | -4 dumpable:2; from: unsigned int /* 432(30) 4(2) */ to: unsigned char /* 509(6) 1(2) */ < SNIP other offset changes > 1 struct changed [acme@newtoy net-2.6.20]$ I'm not aware of any problem about using 2 byte wide bitfields where previously a 4 byte wide one was, holler if there is any, I wouldn't be surprised, bitfields are things from hell. For the curious, 432(30) means: at offset 432 from the struct start, at offset 30 in the bitfield (yeah, it comes backwards, hellish, huh?) ditto for 509(6), while 4(2) and 1(2) means "struct field size(bitfield size)". Now we have a 2 bytes hole and are using only 4 bytes of the last 32 bytes cacheline, any takers? :-) Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index cad6a16260f7..acfd2e15c5f2 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -338,7 +338,6 @@ struct mm_struct { unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */ - unsigned dumpable:2; cpumask_t cpu_vm_mask; /* Architecture-specific MM context */ @@ -355,6 +354,8 @@ struct mm_struct { unsigned int token_priority; unsigned int last_interval; + unsigned char dumpable:2; + /* coredumping support */ int core_waiters; struct completion *core_startup_done, core_done; -- cgit v1.2.3 From 7cf9c2c76c1a17b32f2da85b50cd4fe468ed44b5 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Wed, 6 Dec 2006 20:33:44 -0800 Subject: [PATCH] radix-tree: RCU lockless readside Make radix tree lookups safe to be performed without locks. Readers are protected against nodes being deleted by using RCU based freeing. Readers are protected against new node insertion by using memory barriers to ensure the node itself will be properly written before it is visible in the radix tree. Each radix tree node keeps a record of their height (above leaf nodes). This height does not change after insertion -- when the radix tree is extended, higher nodes are only inserted in the top. So a lookup can take the pointer to what is *now* the root node, and traverse down it even if the tree is concurrently extended and this node becomes a subtree of a new root. "Direct" pointers (tree height of 0, where root->rnode points directly to the data item) are handled by using the low bit of the pointer to signal whether rnode is a direct pointer or a pointer to a radix tree node. When a reader wants to traverse the next branch, they will take a copy of the pointer. This pointer will be either NULL (and the branch is empty) or non-NULL (and will point to a valid node). [akpm@osdl.org: cleanups] [Lee.Schermerhorn@hp.com: bugfixes, comments, simplifications] [clameter@sgi.com: build fix] Signed-off-by: Nick Piggin Cc: "Paul E. McKenney" Signed-off-by: Lee Schermerhorn Cc: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/radix-tree.h | 101 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 101 insertions(+) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index cbfa11537421..0deb842541ac 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -1,6 +1,7 @@ /* * Copyright (C) 2001 Momchil Velikov * Portions Copyright (C) 2001 Christoph Hellwig + * Copyright (C) 2006 Nick Piggin * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License as @@ -21,6 +22,35 @@ #include #include +#include +#include + +/* + * A direct pointer (root->rnode pointing directly to a data item, + * rather than another radix_tree_node) is signalled by the low bit + * set in the root->rnode pointer. + * + * In this case root->height is also NULL, but the direct pointer tests are + * needed for RCU lookups when root->height is unreliable. + */ +#define RADIX_TREE_DIRECT_PTR 1 + +static inline void *radix_tree_ptr_to_direct(void *ptr) +{ + return (void *)((unsigned long)ptr | RADIX_TREE_DIRECT_PTR); +} + +static inline void *radix_tree_direct_to_ptr(void *ptr) +{ + return (void *)((unsigned long)ptr & ~RADIX_TREE_DIRECT_PTR); +} + +static inline int radix_tree_is_direct_ptr(void *ptr) +{ + return (int)((unsigned long)ptr & RADIX_TREE_DIRECT_PTR); +} + +/*** radix-tree API starts here ***/ #define RADIX_TREE_MAX_TAGS 2 @@ -47,6 +77,77 @@ do { \ (root)->rnode = NULL; \ } while (0) +/** + * Radix-tree synchronization + * + * The radix-tree API requires that users provide all synchronisation (with + * specific exceptions, noted below). + * + * Synchronization of access to the data items being stored in the tree, and + * management of their lifetimes must be completely managed by API users. + * + * For API usage, in general, + * - any function _modifying_ the the tree or tags (inserting or deleting + * items, setting or clearing tags must exclude other modifications, and + * exclude any functions reading the tree. + * - any function _reading_ the the tree or tags (looking up items or tags, + * gang lookups) must exclude modifications to the tree, but may occur + * concurrently with other readers. + * + * The notable exceptions to this rule are the following functions: + * radix_tree_lookup + * radix_tree_tag_get + * radix_tree_gang_lookup + * radix_tree_gang_lookup_tag + * radix_tree_tagged + * + * The first 4 functions are able to be called locklessly, using RCU. The + * caller must ensure calls to these functions are made within rcu_read_lock() + * regions. Other readers (lock-free or otherwise) and modifications may be + * running concurrently. + * + * It is still required that the caller manage the synchronization and lifetimes + * of the items. So if RCU lock-free lookups are used, typically this would mean + * that the items have their own locks, or are amenable to lock-free access; and + * that the items are freed by RCU (or only freed after having been deleted from + * the radix tree *and* a synchronize_rcu() grace period). + * + * (Note, rcu_assign_pointer and rcu_dereference are not needed to control + * access to data items when inserting into or looking up from the radix tree) + * + * radix_tree_tagged is able to be called without locking or RCU. + */ + +/** + * radix_tree_deref_slot - dereference a slot + * @pslot: pointer to slot, returned by radix_tree_lookup_slot + * Returns: item that was stored in that slot with any direct pointer flag + * removed. + * + * For use with radix_tree_lookup_slot(). Caller must hold tree at least read + * locked across slot lookup and dereference. More likely, will be used with + * radix_tree_replace_slot(), as well, so caller will hold tree write locked. + */ +static inline void *radix_tree_deref_slot(void **pslot) +{ + return radix_tree_direct_to_ptr(*pslot); +} +/** + * radix_tree_replace_slot - replace item in a slot + * @pslot: pointer to slot, returned by radix_tree_lookup_slot + * @item: new item to store in the slot. + * + * For use with radix_tree_lookup_slot(). Caller must hold tree write locked + * across slot lookup and replacement. + */ +static inline void radix_tree_replace_slot(void **pslot, void *item) +{ + BUG_ON(radix_tree_is_direct_ptr(item)); + rcu_assign_pointer(*pslot, + (void *)((unsigned long)item | + ((unsigned long)*pslot & RADIX_TREE_DIRECT_PTR))); +} + int radix_tree_insert(struct radix_tree_root *, unsigned long, void *); void *radix_tree_lookup(struct radix_tree_root *, unsigned long); void **radix_tree_lookup_slot(struct radix_tree_root *, unsigned long); -- cgit v1.2.3 From 915bae9ebe41e52d71ad8b06d50e4ab26189f964 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 6 Dec 2006 20:34:07 -0800 Subject: [PATCH] swsusp: use partition device and offset to identify swap areas The Linux kernel handles swap files almost in the same way as it handles swap partitions and there are only two differences between these two types of swap areas: (1) swap files need not be contiguous, (2) the header of a swap file is not in the first block of the partition that holds it. From the swsusp's point of view (1) is not a problem, because it is already taken care of by the swap-handling code, but (2) has to be taken into consideration. In principle the location of a swap file's header may be determined with the help of appropriate filesystem driver. Unfortunately, however, it requires the filesystem holding the swap file to be mounted, and if this filesystem is journaled, it cannot be mounted during a resume from disk. For this reason we need some other means by which swap areas can be identified. For example, to identify a swap area we can use the partition that holds the area and the offset from the beginning of this partition at which the swap header is located. The following patch allows swsusp to identify swap areas this way. It changes swap_type_of() so that it takes an additional argument representing an offset of the swap header within the partition represented by its first argument. Signed-off-by: Rafael J. Wysocki Acked-by: Pavel Machek Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 89f8a39773bf..d51e35e4e168 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -247,7 +247,7 @@ extern int swap_duplicate(swp_entry_t); extern int valid_swaphandles(swp_entry_t, unsigned long *); extern void swap_free(swp_entry_t); extern void free_swap_and_cache(swp_entry_t); -extern int swap_type_of(dev_t); +extern int swap_type_of(dev_t, sector_t); extern unsigned int count_swap_pages(int, int); extern sector_t map_swap_page(struct swap_info_struct *, pgoff_t); extern struct swap_info_struct *get_swap_info_struct(unsigned); -- cgit v1.2.3 From 3aef83e0ef1ffb8ea3bea97be46821a45c952173 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 6 Dec 2006 20:34:10 -0800 Subject: [PATCH] swsusp: use block device offsets to identify swap locations Make swsusp use block device offsets instead of swap offsets to identify swap locations and make it use the same code paths for writing as well as for reading data. This allows us to use the same code for handling swap files and swap partitions and to simplify the code, eg. by dropping rw_swap_page_sync(). Signed-off-by: Rafael J. Wysocki Cc: Pavel Machek Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index d51e35e4e168..add51cebc8d9 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -218,8 +218,6 @@ extern void swap_unplug_io_fn(struct backing_dev_info *, struct page *); /* linux/mm/page_io.c */ extern int swap_readpage(struct file *, struct page *); extern int swap_writepage(struct page *page, struct writeback_control *wbc); -extern int rw_swap_page_sync(int rw, swp_entry_t entry, struct page *page, - struct bio **bio_chain); extern int end_swap_bio_read(struct bio *bio, unsigned int bytes_done, int err); /* linux/mm/swap_state.c */ @@ -250,6 +248,7 @@ extern void free_swap_and_cache(swp_entry_t); extern int swap_type_of(dev_t, sector_t); extern unsigned int count_swap_pages(int, int); extern sector_t map_swap_page(struct swap_info_struct *, pgoff_t); +extern sector_t swapdev_block(int, pgoff_t); extern struct swap_info_struct *get_swap_info_struct(unsigned); extern int can_share_swap_page(struct page *); extern int remove_exclusive_swap_page(struct page *); -- cgit v1.2.3 From 8357376d3df21b7d6f857931a57ac50da9c66e26 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 6 Dec 2006 20:34:18 -0800 Subject: [PATCH] swsusp: Improve handling of highmem Currently swsusp saves the contents of highmem pages by copying them to the normal zone which is quite inefficient (eg. it requires two normal pages to be used for saving one highmem page). This may be improved by using highmem for saving the contents of saveable highmem pages. Namely, during the suspend phase of the suspend-resume cycle we try to allocate as many free highmem pages as there are saveable highmem pages. If there are not enough highmem image pages to store the contents of all of the saveable highmem pages, some of them will be stored in the "normal" memory. Next, we allocate as many free "normal" pages as needed to store the (remaining) image data. We use a memory bitmap to mark the allocated free pages (ie. highmem as well as "normal" image pages). Now, we use another memory bitmap to mark all of the saveable pages (highmem as well as "normal") and the contents of the saveable pages are copied into the image pages. Then, the second bitmap is used to save the pfns corresponding to the saveable pages and the first one is used to save their data. During the resume phase the pfns of the pages that were saveable during the suspend are loaded from the image and used to mark the "unsafe" page frames. Next, we try to allocate as many free highmem page frames as to load all of the image data that had been in the highmem before the suspend and we allocate so many free "normal" page frames that the total number of allocated free pages (highmem and "normal") is equal to the size of the image. While doing this we have to make sure that there will be some extra free "normal" and "safe" page frames for two lists of PBEs constructed later. Now, the image data are loaded, if possible, into their "original" page frames. The image data that cannot be written into their "original" page frames are loaded into "safe" page frames and their "original" kernel virtual addresses, as well as the addresses of the "safe" pages containing their copies, are stored in one of two lists of PBEs. One list of PBEs is for the copies of "normal" suspend pages (ie. "normal" pages that were saveable during the suspend) and it is used in the same way as previously (ie. by the architecture-dependent parts of swsusp). The other list of PBEs is for the copies of highmem suspend pages. The pages in this list are restored (in a reversible way) right before the arch-dependent code is called. Signed-off-by: Rafael J. Wysocki Cc: Pavel Machek Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/suspend.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/suspend.h b/include/linux/suspend.h index b1237f16ecde..bf99bd49f8ef 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -9,10 +9,13 @@ #include #include -/* page backup entry */ +/* struct pbe is used for creating lists of pages that should be restored + * atomically during the resume from disk, because the page frames they have + * occupied before the suspend are in use. + */ struct pbe { - unsigned long address; /* address of the copy */ - unsigned long orig_address; /* original address of page */ + void *address; /* address of the copy */ + void *orig_address; /* original address of a page */ struct pbe *next; }; -- cgit v1.2.3 From 7dfb71030f7636a0d65200158113c37764552f93 Mon Sep 17 00:00:00 2001 From: Nigel Cunningham Date: Wed, 6 Dec 2006 20:34:23 -0800 Subject: [PATCH] Add include/linux/freezer.h and move definitions from sched.h Move process freezing functions from include/linux/sched.h to freezer.h, so that modifications to the freezer or the kernel configuration don't require recompiling just about everything. [akpm@osdl.org: fix ueagle driver] Signed-off-by: Nigel Cunningham Cc: "Rafael J. Wysocki" Cc: Pavel Machek Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/freezer.h | 84 +++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/sched.h | 81 ----------------------------------------------- 2 files changed, 84 insertions(+), 81 deletions(-) create mode 100644 include/linux/freezer.h (limited to 'include/linux') diff --git a/include/linux/freezer.h b/include/linux/freezer.h new file mode 100644 index 000000000000..266373f74445 --- /dev/null +++ b/include/linux/freezer.h @@ -0,0 +1,84 @@ +/* Freezer declarations */ + +#ifdef CONFIG_PM +/* + * Check if a process has been frozen + */ +static inline int frozen(struct task_struct *p) +{ + return p->flags & PF_FROZEN; +} + +/* + * Check if there is a request to freeze a process + */ +static inline int freezing(struct task_struct *p) +{ + return p->flags & PF_FREEZE; +} + +/* + * Request that a process be frozen + * FIXME: SMP problem. We may not modify other process' flags! + */ +static inline void freeze(struct task_struct *p) +{ + p->flags |= PF_FREEZE; +} + +/* + * Sometimes we may need to cancel the previous 'freeze' request + */ +static inline void do_not_freeze(struct task_struct *p) +{ + p->flags &= ~PF_FREEZE; +} + +/* + * Wake up a frozen process + */ +static inline int thaw_process(struct task_struct *p) +{ + if (frozen(p)) { + p->flags &= ~PF_FROZEN; + wake_up_process(p); + return 1; + } + return 0; +} + +/* + * freezing is complete, mark process as frozen + */ +static inline void frozen_process(struct task_struct *p) +{ + p->flags = (p->flags & ~PF_FREEZE) | PF_FROZEN; +} + +extern void refrigerator(void); +extern int freeze_processes(void); +extern void thaw_processes(void); + +static inline int try_to_freeze(void) +{ + if (freezing(current)) { + refrigerator(); + return 1; + } else + return 0; +} +#else +static inline int frozen(struct task_struct *p) { return 0; } +static inline int freezing(struct task_struct *p) { return 0; } +static inline void freeze(struct task_struct *p) { BUG(); } +static inline int thaw_process(struct task_struct *p) { return 1; } +static inline void frozen_process(struct task_struct *p) { BUG(); } + +static inline void refrigerator(void) {} +static inline int freeze_processes(void) { BUG(); return 0; } +static inline void thaw_processes(void) {} + +static inline int try_to_freeze(void) { return 0; } + + +#endif diff --git a/include/linux/sched.h b/include/linux/sched.h index acfd2e15c5f2..837a012f573c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1618,87 +1618,6 @@ extern int sched_create_sysfs_power_savings_entries(struct sysdev_class *cls); extern void normalize_rt_tasks(void); -#ifdef CONFIG_PM -/* - * Check if a process has been frozen - */ -static inline int frozen(struct task_struct *p) -{ - return p->flags & PF_FROZEN; -} - -/* - * Check if there is a request to freeze a process - */ -static inline int freezing(struct task_struct *p) -{ - return p->flags & PF_FREEZE; -} - -/* - * Request that a process be frozen - * FIXME: SMP problem. We may not modify other process' flags! - */ -static inline void freeze(struct task_struct *p) -{ - p->flags |= PF_FREEZE; -} - -/* - * Sometimes we may need to cancel the previous 'freeze' request - */ -static inline void do_not_freeze(struct task_struct *p) -{ - p->flags &= ~PF_FREEZE; -} - -/* - * Wake up a frozen process - */ -static inline int thaw_process(struct task_struct *p) -{ - if (frozen(p)) { - p->flags &= ~PF_FROZEN; - wake_up_process(p); - return 1; - } - return 0; -} - -/* - * freezing is complete, mark process as frozen - */ -static inline void frozen_process(struct task_struct *p) -{ - p->flags = (p->flags & ~PF_FREEZE) | PF_FROZEN; -} - -extern void refrigerator(void); -extern int freeze_processes(void); -extern void thaw_processes(void); - -static inline int try_to_freeze(void) -{ - if (freezing(current)) { - refrigerator(); - return 1; - } else - return 0; -} -#else -static inline int frozen(struct task_struct *p) { return 0; } -static inline int freezing(struct task_struct *p) { return 0; } -static inline void freeze(struct task_struct *p) { BUG(); } -static inline int thaw_process(struct task_struct *p) { return 1; } -static inline void frozen_process(struct task_struct *p) { BUG(); } - -static inline void refrigerator(void) {} -static inline int freeze_processes(void) { BUG(); return 0; } -static inline void thaw_processes(void) {} - -static inline int try_to_freeze(void) { return 0; } - -#endif /* CONFIG_PM */ #endif /* __KERNEL__ */ #endif -- cgit v1.2.3 From ff39593ad0ff7a79a3717edac6634407aa8200c2 Mon Sep 17 00:00:00 2001 From: Nigel Cunningham Date: Wed, 6 Dec 2006 20:34:28 -0800 Subject: [PATCH] swsusp: thaw userspace and kernel space separately Modify process thawing so that we can thaw kernel space without thawing userspace, and thaw kernelspace first. This will be useful in later patches, where I intend to get swsusp thawing kernel threads only before seeking to free memory. Signed-off-by: Nigel Cunningham Cc: Pavel Machek Cc: "Rafael J. Wysocki" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/freezer.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/freezer.h b/include/linux/freezer.h index 266373f74445..294ebea859c9 100644 --- a/include/linux/freezer.h +++ b/include/linux/freezer.h @@ -1,5 +1,8 @@ /* Freezer declarations */ +#define FREEZER_KERNEL_THREADS 0 +#define FREEZER_ALL_THREADS 1 + #ifdef CONFIG_PM /* * Check if a process has been frozen @@ -57,7 +60,8 @@ static inline void frozen_process(struct task_struct *p) extern void refrigerator(void); extern int freeze_processes(void); -extern void thaw_processes(void); +#define thaw_processes() do { thaw_some_processes(FREEZER_ALL_THREADS); } while(0) +#define thaw_kernel_threads() do { thaw_some_processes(FREEZER_KERNEL_THREADS); } while(0) static inline int try_to_freeze(void) { @@ -67,6 +71,9 @@ static inline int try_to_freeze(void) } else return 0; } + +extern void thaw_some_processes(int all); + #else static inline int frozen(struct task_struct *p) { return 0; } static inline int freezing(struct task_struct *p) { return 0; } -- cgit v1.2.3 From a9b6f562f14dc28fb4b2415f0f275cede0abe9b5 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 6 Dec 2006 20:34:37 -0800 Subject: [PATCH] swsusp: Untangle thaw_processes Move the loop from thaw_processes() to a separate function and call it independently for kernel threads and user space processes so that the order of thawing tasks is clearly visible. Drop thaw_kernel_threads() which is never used. Signed-off-by: Rafael J. Wysocki Cc: Pavel Machek Cc: Nigel Cunningham Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/freezer.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/freezer.h b/include/linux/freezer.h index 294ebea859c9..6e05e3e7ce39 100644 --- a/include/linux/freezer.h +++ b/include/linux/freezer.h @@ -1,8 +1,5 @@ /* Freezer declarations */ -#define FREEZER_KERNEL_THREADS 0 -#define FREEZER_ALL_THREADS 1 - #ifdef CONFIG_PM /* * Check if a process has been frozen @@ -60,8 +57,7 @@ static inline void frozen_process(struct task_struct *p) extern void refrigerator(void); extern int freeze_processes(void); -#define thaw_processes() do { thaw_some_processes(FREEZER_ALL_THREADS); } while(0) -#define thaw_kernel_threads() do { thaw_some_processes(FREEZER_KERNEL_THREADS); } while(0) +extern void thaw_processes(void); static inline int try_to_freeze(void) { -- cgit v1.2.3 From 341a595850dac1b0503df34260257d71b4fdf72c Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 6 Dec 2006 20:34:49 -0800 Subject: [PATCH] Support for freezeable workqueues Make it possible to create a workqueue the worker thread of which will be frozen during suspend, along with other kernel threads. Signed-off-by: Rafael J. Wysocki Acked-by: Pavel Machek Cc: Nigel Cunningham Cc: David Chinner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/workqueue.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 4a3ea83c6d16..f0cb1df7b475 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -147,9 +147,11 @@ struct execute_work { extern struct workqueue_struct *__create_workqueue(const char *name, - int singlethread); -#define create_workqueue(name) __create_workqueue((name), 0) -#define create_singlethread_workqueue(name) __create_workqueue((name), 1) + int singlethread, + int freezeable); +#define create_workqueue(name) __create_workqueue((name), 0, 0) +#define create_freezeable_workqueue(name) __create_workqueue((name), 0, 1) +#define create_singlethread_workqueue(name) __create_workqueue((name), 1, 0) extern void destroy_workqueue(struct workqueue_struct *wq); -- cgit v1.2.3 From 799202cbd0ef6a201446d99fcbd78b9f0bda6ae5 Mon Sep 17 00:00:00 2001 From: Mike Miller Date: Wed, 6 Dec 2006 20:35:12 -0800 Subject: [PATCH] cciss: add support for 1024 logical volumes Add the support for a large number of logical volumes. We will soon have hardware that support up to 1024 logical volumes. Signed-off-by: Mike Miller Cc: Jens Axboe Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cciss_ioctl.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cciss_ioctl.h b/include/linux/cciss_ioctl.h index 6e27f42e3a57..cb57c30081a8 100644 --- a/include/linux/cciss_ioctl.h +++ b/include/linux/cciss_ioctl.h @@ -80,7 +80,7 @@ typedef __u32 DriverVer_type; #define HWORD __u16 #define DWORD __u32 -#define CISS_MAX_LUN 16 +#define CISS_MAX_LUN 1024 #define LEVEL2LUN 1 // index into Target(x) structure, due to byte swapping #define LEVEL3LUN 0 -- cgit v1.2.3 From 238b8721a554a33a451a3f13bdb5be8fe5cfc927 Mon Sep 17 00:00:00 2001 From: Peter Korsgaard Date: Wed, 6 Dec 2006 20:35:17 -0800 Subject: [PATCH] serial uartlite driver Add a driver for the Xilinx uartlite serial controller used in boards with the PPC405 core in the Xilinx V2P/V4 fpgas. The hardware is very simple (baudrate/start/stopbits fixed and no break support). See the datasheet for details: http://www.xilinx.com/bvdocs/ipcenter/data_sheet/opb_uartlite.pdf See http://thread.gmane.org/gmane.linux.serial/1237/ for the email thread. Signed-off-by: Peter Korsgaard Acked-by: Olof Johansson Cc: Russell King Cc: Alan Cox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/serial_core.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 463ab953b092..827672136646 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -132,6 +132,8 @@ #define PORT_S3C2412 73 +/* Xilinx uartlite */ +#define PORT_UARTLITE 74 #ifdef __KERNEL__ -- cgit v1.2.3 From 48ed214d10ae3c3999af938970f7b5b58df77be3 Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Wed, 6 Dec 2006 20:35:37 -0800 Subject: [PATCH] constify inode accessors Change the signature of i_size_read(), IMINOR() and IMAJOR() because they, or the functions they call, will never modify the argument. Signed-off-by: Jan Engelhardt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 94b831b8157c..d791bae9de9c 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -636,7 +636,7 @@ extern void inode_double_unlock(struct inode *inode1, struct inode *inode2); * cmpxchg8b without the need of the lock prefix). For SMP compiles * and 64bit archs it makes no difference if preempt is enabled or not. */ -static inline loff_t i_size_read(struct inode *inode) +static inline loff_t i_size_read(const struct inode *inode) { #if BITS_PER_LONG==32 && defined(CONFIG_SMP) loff_t i_size; @@ -679,12 +679,12 @@ static inline void i_size_write(struct inode *inode, loff_t i_size) #endif } -static inline unsigned iminor(struct inode *inode) +static inline unsigned iminor(const struct inode *inode) { return MINOR(inode->i_rdev); } -static inline unsigned imajor(struct inode *inode) +static inline unsigned imajor(const struct inode *inode) { return MAJOR(inode->i_rdev); } -- cgit v1.2.3 From e9168c189fd54171124b5d25644024d99869e6a8 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Wed, 6 Dec 2006 20:35:38 -0800 Subject: [PATCH] fuse: update userspace interface to version 7.8 Add a flag to the RELEASE message which specifies that a FLUSH operation should be performed as well. This interface update is needed for the FreeBSD port, and doesn't actually touch the Linux implementation at all. Also rename the unused 'flush_flags' in the FLUSH message to 'unused'. Signed-off-by: Miklos Szeredi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fuse.h | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fuse.h b/include/linux/fuse.h index 9fc48a674b82..76336327a941 100644 --- a/include/linux/fuse.h +++ b/include/linux/fuse.h @@ -15,7 +15,7 @@ #define FUSE_KERNEL_VERSION 7 /** Minor version number of this interface */ -#define FUSE_KERNEL_MINOR_VERSION 7 +#define FUSE_KERNEL_MINOR_VERSION 8 /** The node ID of the root inode */ #define FUSE_ROOT_ID 1 @@ -92,6 +92,11 @@ struct fuse_file_lock { #define FUSE_ASYNC_READ (1 << 0) #define FUSE_POSIX_LOCKS (1 << 1) +/** + * Release flags + */ +#define FUSE_RELEASE_FLUSH (1 << 0) + enum fuse_opcode { FUSE_LOOKUP = 1, FUSE_FORGET = 2, /* no reply */ @@ -205,12 +210,13 @@ struct fuse_open_out { struct fuse_release_in { __u64 fh; __u32 flags; - __u32 padding; + __u32 release_flags; + __u64 lock_owner; }; struct fuse_flush_in { __u64 fh; - __u32 flush_flags; + __u32 unused; __u32 padding; __u64 lock_owner; }; -- cgit v1.2.3 From b2d2272fae1e1df26ec8f93a6d5baea891dcce37 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Wed, 6 Dec 2006 20:35:51 -0800 Subject: [PATCH] fuse: add bmap support Add support for the BMAP operation for block device based filesystems. This is needed to support swap-files and lilo. Signed-off-by: Miklos Szeredi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fuse.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fuse.h b/include/linux/fuse.h index 76336327a941..162a754f4db7 100644 --- a/include/linux/fuse.h +++ b/include/linux/fuse.h @@ -132,6 +132,7 @@ enum fuse_opcode { FUSE_ACCESS = 34, FUSE_CREATE = 35, FUSE_INTERRUPT = 36, + FUSE_BMAP = 37, }; /* The read buffer is required to be at least 8k, but may be much larger */ @@ -302,6 +303,16 @@ struct fuse_interrupt_in { __u64 unique; }; +struct fuse_bmap_in { + __u64 block; + __u32 blocksize; + __u32 padding; +}; + +struct fuse_bmap_out { + __u64 block; +}; + struct fuse_in_header { __u32 len; __u32 opcode; -- cgit v1.2.3 From 0ec7ca41f6f0f74a394a7d686bc0ee8afef84887 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Wed, 6 Dec 2006 20:35:52 -0800 Subject: [PATCH] fuse: add DESTROY operation Add a DESTROY operation for block device based filesystems. With the help of this operation, such a filesystem can flush dirty data to the device synchronously before the umount returns. This is needed in situations where the filesystem is assumed to be clean immediately after unmount (e.g. ejecting removable media). Signed-off-by: Miklos Szeredi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fuse.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fuse.h b/include/linux/fuse.h index 162a754f4db7..534744efe30d 100644 --- a/include/linux/fuse.h +++ b/include/linux/fuse.h @@ -133,6 +133,7 @@ enum fuse_opcode { FUSE_CREATE = 35, FUSE_INTERRUPT = 36, FUSE_BMAP = 37, + FUSE_DESTROY = 38, }; /* The read buffer is required to be at least 8k, but may be much larger */ -- cgit v1.2.3 From e59e2ae2c29700117a54e85c106017c24837119f Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 6 Dec 2006 20:35:59 -0800 Subject: [PATCH] SysRq-X: show blocked tasks Add SysRq-X support: show blocked (TASK_UNINTERRUPTIBLE) tasks only. Useful for debugging IO stalls. Signed-off-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 837a012f573c..0a90cefb0b0d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -194,7 +194,16 @@ extern void init_idle(struct task_struct *idle, int cpu); extern cpumask_t nohz_cpu_mask; -extern void show_state(void); +/* + * Only dump TASK_* tasks. (-1 for all tasks) + */ +extern void show_state_filter(unsigned long state_filter); + +static inline void show_state(void) +{ + show_state_filter(-1); +} + extern void show_regs(struct pt_regs *); /* -- cgit v1.2.3 From 5ec68b2e310437e99c297ba04e1afc5297aa6de1 Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Wed, 6 Dec 2006 20:36:14 -0800 Subject: [PATCH] pull in necessary header files for cdev.h linux/cdev.h uses struct kobject and other structs and should therefore include them. Currently, a module either needs to add the missing includes itself, or, in case a module includes other headers already, needs to put last, which goes against a alphabetically-sorted include list. Signed-off-by: Jan Engelhardt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cdev.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cdev.h b/include/linux/cdev.h index ee5f53f2ca15..f309b00e986e 100644 --- a/include/linux/cdev.h +++ b/include/linux/cdev.h @@ -2,6 +2,10 @@ #define _LINUX_CDEV_H #ifdef __KERNEL__ +#include +#include +#include + struct cdev { struct kobject kobj; struct module *owner; -- cgit v1.2.3 From c140e110019f25ffa1c6f3f365b0c9103d0b8475 Mon Sep 17 00:00:00 2001 From: Ryan Underwood Date: Wed, 6 Dec 2006 20:36:38 -0800 Subject: [PATCH] parport_pc: Add support for OX16PCI952 parallel port Add support for the parallel port (implemented as separate PCI function) on the Oxford Semiconductor OX16PCI952. Signed-off-by: Ryan Underwood Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- 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 c09da1e30c54..dcdb90f06d73 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1864,6 +1864,7 @@ #define PCI_DEVICE_ID_OXSEMI_16PCI95N 0x9511 #define PCI_DEVICE_ID_OXSEMI_16PCI954PP 0x9513 #define PCI_DEVICE_ID_OXSEMI_16PCI952 0x9521 +#define PCI_DEVICE_ID_OXSEMI_16PCI952PP 0x9523 #define PCI_VENDOR_ID_SAMSUNG 0x144d -- cgit v1.2.3 From 20aa7b21b1cbd1aa3fbf5fc14da5f7484a61a824 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Wed, 6 Dec 2006 20:36:40 -0800 Subject: [PATCH] probe_kernel_address() needs to do set_fs() probe_kernel_address() purports to be generic, only it forgot to select KERNEL_DS, so it presently won't work right on all architectures. Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/uaccess.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 67918c22339c..76c3fe325101 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -65,14 +65,22 @@ static inline unsigned long __copy_from_user_nocache(void *to, * do_page_fault() doesn't attempt to take mmap_sem. This makes * probe_kernel_address() suitable for use within regions where the caller * already holds mmap_sem, or other locks which nest inside mmap_sem. + * This must be a macro because __get_user() needs to know the types of the + * args. + * + * We don't include enough header files to be able to do the set_fs(). We + * require that the probe_kernel_address() caller will do that. */ #define probe_kernel_address(addr, retval) \ ({ \ long ret; \ + mm_segment_t old_fs = get_fs(); \ \ + set_fs(KERNEL_DS); \ pagefault_disable(); \ ret = __get_user(retval, addr); \ pagefault_enable(); \ + set_fs(old_fs); \ ret; \ }) -- cgit v1.2.3 From 115085ea0794c0f339be8f9d25505c7f9861d824 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 6 Dec 2006 20:36:51 -0800 Subject: [PATCH] taskstats: cleanup do_exit() path do_exit: taskstats_exit_alloc() ... taskstats_exit_send() taskstats_exit_free() I think this is not good, let it be a single function exported to the core kernel, taskstats_exit(), which does alloc + send + free itself. Signed-off-by: Oleg Nesterov Cc: Balbir Singh Cc: Shailabh Nagar Cc: Jay Lan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/taskstats_kern.h | 17 ++--------------- 1 file changed, 2 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/taskstats_kern.h b/include/linux/taskstats_kern.h index ce8a912e5426..f1261a532496 100644 --- a/include/linux/taskstats_kern.h +++ b/include/linux/taskstats_kern.h @@ -15,12 +15,6 @@ extern struct kmem_cache *taskstats_cache; extern struct mutex taskstats_exit_mutex; -static inline void taskstats_exit_free(struct taskstats *tidstats) -{ - if (tidstats) - kmem_cache_free(taskstats_cache, tidstats); -} - static inline void taskstats_tgid_init(struct signal_struct *sig) { sig->stats = NULL; @@ -54,17 +48,10 @@ static inline void taskstats_tgid_free(struct signal_struct *sig) kmem_cache_free(taskstats_cache, sig->stats); } -extern void taskstats_exit_alloc(struct taskstats **, unsigned int *); -extern void taskstats_exit_send(struct task_struct *, struct taskstats *, int, unsigned int); +extern void taskstats_exit(struct task_struct *, int group_dead); extern void taskstats_init_early(void); #else -static inline void taskstats_exit_alloc(struct taskstats **ptidstats, unsigned int *mycpu) -{} -static inline void taskstats_exit_free(struct taskstats *ptidstats) -{} -static inline void taskstats_exit_send(struct task_struct *tsk, - struct taskstats *tidstats, - int group_dead, unsigned int cpu) +static inline void taskstats_exit(struct task_struct *tsk, int group_dead) {} static inline void taskstats_tgid_init(struct signal_struct *sig) {} -- cgit v1.2.3 From 34ec12349c8a9505adc59d72f92b4595bc2483ff Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 6 Dec 2006 20:36:52 -0800 Subject: [PATCH] taskstats: cleanup ->signal->stats allocation Allocate ->signal->stats on demand in taskstats_exit(), this allows us to remove taskstats_tgid_alloc() (the last non-trivial inline) from taskstat's public interface. Signed-off-by: Oleg Nesterov Cc: Balbir Singh Cc: Shailabh Nagar Cc: Jay Lan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/taskstats_kern.h | 24 ------------------------ 1 file changed, 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/taskstats_kern.h b/include/linux/taskstats_kern.h index f1261a532496..7e9680f4afdd 100644 --- a/include/linux/taskstats_kern.h +++ b/include/linux/taskstats_kern.h @@ -20,28 +20,6 @@ static inline void taskstats_tgid_init(struct signal_struct *sig) sig->stats = NULL; } -static inline void taskstats_tgid_alloc(struct task_struct *tsk) -{ - struct signal_struct *sig = tsk->signal; - struct taskstats *stats; - - if (sig->stats != NULL) - return; - - /* No problem if kmem_cache_zalloc() fails */ - stats = kmem_cache_zalloc(taskstats_cache, GFP_KERNEL); - - spin_lock_irq(&tsk->sighand->siglock); - if (!sig->stats) { - sig->stats = stats; - stats = NULL; - } - spin_unlock_irq(&tsk->sighand->siglock); - - if (stats) - kmem_cache_free(taskstats_cache, stats); -} - static inline void taskstats_tgid_free(struct signal_struct *sig) { if (sig->stats) @@ -55,8 +33,6 @@ static inline void taskstats_exit(struct task_struct *tsk, int group_dead) {} static inline void taskstats_tgid_init(struct signal_struct *sig) {} -static inline void taskstats_tgid_alloc(struct task_struct *tsk) -{} static inline void taskstats_tgid_free(struct signal_struct *sig) {} static inline void taskstats_init_early(void) -- cgit v1.2.3 From 9774a1f54f173ad18e816496c8979f1bf8ef666a Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Wed, 6 Dec 2006 20:36:56 -0800 Subject: [PATCH] Compile-time check re world-writeable module params One of the mistakes a module_param() user can make is to supply default value of module parameter as the last argument. module_param() accepts permissions instead. If default value is, say, 3 (-------wx), parameter becomes world-writeable. So far, the only remedy was to apply grep(1) and read drivers submitted to -mm. BTDT. With this patch applied, compiler will finally do some job. *) bounds checking on permissions *) world-writeable bit checking on permissions *) compile breakage if checks trigger First version of this check (only "& 2" part) directly caught 4 out of 7 places during my last grep. Subject: Neverending module_param() bugs [X] drivers/acpi/sbs.c:101:module_param(capacity_mode, int, CAPACITY_UNIT); [X] drivers/acpi/sbs.c:102:module_param(update_mode, int, UPDATE_MODE); [ ] drivers/acpi/sbs.c:103:module_param(update_info_mode, int, UPDATE_INFO_MODE); [ ] drivers/acpi/sbs.c:104:module_param(update_time, int, UPDATE_TIME); [ ] drivers/acpi/sbs.c:105:module_param(update_time2, int, UPDATE_TIME2); [X] drivers/char/watchdog/sbc8360.c:203:module_param(timeout, int, 27); [X] drivers/media/video/tuner-simple.c:13:module_param(offset, int, 0666); Signed-off-by: Alexey Dobriyan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/moduleparam.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h index 7c0c2c198f1f..4a189dadb160 100644 --- a/include/linux/moduleparam.h +++ b/include/linux/moduleparam.h @@ -63,6 +63,9 @@ struct kparam_array not there, read bits mean it's readable, write bits mean it's writable. */ #define __module_param_call(prefix, name, set, get, arg, perm) \ + /* Default value instead of permissions? */ \ + static int __param_perm_check_##name __attribute__((unused)) = \ + BUILD_BUG_ON_ZERO((perm) < 0 || (perm) > 0777 || ((perm) & 2)); \ static char __param_str_##name[] = prefix #name; \ static struct kernel_param const __param_##name \ __attribute_used__ \ -- cgit v1.2.3 From e0980dafa329d33bb88edc8a3ef9fab4e070590c Mon Sep 17 00:00:00 2001 From: Paul B Schroeder Date: Wed, 6 Dec 2006 20:37:03 -0800 Subject: [PATCH] Exar quad port serial This is on our "Envoy" boxes which we have, according to the documentation, an "Exar ST16C554/554D Quad UART with 16-byte Fifo's". The box also has two other "on-board" serial ports and a modem chip. The two on-board serial UARTs were being detected along with the first two Exar UARTs. The last two Exar UARTs were not showing up and neither was the modem. This patch was the only way I could the kernel to see beyond the standard four serial ports and get all four of the Exar UARTs to show up. [akpm@osdl.org: build fix] Signed-off-by: Paul B Schroeder Cc: Lennart Sorensen Acked-by: Alan Cox Cc: Russell King Cc: Greg KH Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/serial_8250.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h index 8e9681413726..71310d80c09a 100644 --- a/include/linux/serial_8250.h +++ b/include/linux/serial_8250.h @@ -41,6 +41,7 @@ enum { PLAT8250_DEV_FOURPORT, PLAT8250_DEV_ACCENT, PLAT8250_DEV_BOCA, + PLAT8250_DEV_EXAR_ST16C554, PLAT8250_DEV_HUB6, PLAT8250_DEV_MCA, PLAT8250_DEV_AU1X00, -- cgit v1.2.3 From 3a229b39eb8497ae5f8077f81f7c8c3e1aacd624 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Wed, 6 Dec 2006 20:37:14 -0800 Subject: [PATCH] ext3: uninline large functions Saves nearly 4kbytes on x86. Cc: Arnaldo Carvalho de Melo Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ext3_jbd.h | 76 +++++++++++------------------------------------- 1 file changed, 17 insertions(+), 59 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ext3_jbd.h b/include/linux/ext3_jbd.h index ce0e6109aff0..8c43b13a02fe 100644 --- a/include/linux/ext3_jbd.h +++ b/include/linux/ext3_jbd.h @@ -109,74 +109,32 @@ int ext3_mark_inode_dirty(handle_t *handle, struct inode *inode); * been done yet. */ -void ext3_journal_abort_handle(const char *caller, const char *err_fn, - struct buffer_head *bh, handle_t *handle, int err); - -static inline int -__ext3_journal_get_undo_access(const char *where, handle_t *handle, - struct buffer_head *bh) +static inline void ext3_journal_release_buffer(handle_t *handle, + struct buffer_head *bh) { - int err = journal_get_undo_access(handle, bh); - if (err) - ext3_journal_abort_handle(where, __FUNCTION__, bh, handle,err); - return err; + journal_release_buffer(handle, bh); } -static inline int -__ext3_journal_get_write_access(const char *where, handle_t *handle, - struct buffer_head *bh) -{ - int err = journal_get_write_access(handle, bh); - if (err) - ext3_journal_abort_handle(where, __FUNCTION__, bh, handle,err); - return err; -} +void ext3_journal_abort_handle(const char *caller, const char *err_fn, + struct buffer_head *bh, handle_t *handle, int err); -static inline void -ext3_journal_release_buffer(handle_t *handle, struct buffer_head *bh) -{ - journal_release_buffer(handle, bh); -} +int __ext3_journal_get_undo_access(const char *where, handle_t *handle, + struct buffer_head *bh); -static inline int -__ext3_journal_forget(const char *where, handle_t *handle, struct buffer_head *bh) -{ - int err = journal_forget(handle, bh); - if (err) - ext3_journal_abort_handle(where, __FUNCTION__, bh, handle,err); - return err; -} +int __ext3_journal_get_write_access(const char *where, handle_t *handle, + struct buffer_head *bh); -static inline int -__ext3_journal_revoke(const char *where, handle_t *handle, - unsigned long blocknr, struct buffer_head *bh) -{ - int err = journal_revoke(handle, blocknr, bh); - if (err) - ext3_journal_abort_handle(where, __FUNCTION__, bh, handle,err); - return err; -} +int __ext3_journal_forget(const char *where, handle_t *handle, + struct buffer_head *bh); -static inline int -__ext3_journal_get_create_access(const char *where, - handle_t *handle, struct buffer_head *bh) -{ - int err = journal_get_create_access(handle, bh); - if (err) - ext3_journal_abort_handle(where, __FUNCTION__, bh, handle,err); - return err; -} +int __ext3_journal_revoke(const char *where, handle_t *handle, + unsigned long blocknr, struct buffer_head *bh); -static inline int -__ext3_journal_dirty_metadata(const char *where, - handle_t *handle, struct buffer_head *bh) -{ - int err = journal_dirty_metadata(handle, bh); - if (err) - ext3_journal_abort_handle(where, __FUNCTION__, bh, handle,err); - return err; -} +int __ext3_journal_get_create_access(const char *where, + handle_t *handle, struct buffer_head *bh); +int __ext3_journal_dirty_metadata(const char *where, + handle_t *handle, struct buffer_head *bh); #define ext3_journal_get_undo_access(handle, bh) \ __ext3_journal_get_undo_access(__FUNCTION__, (handle), (bh)) -- cgit v1.2.3 From 8984d137df669a6e94dbce7b87095e4ce80b9e67 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Wed, 6 Dec 2006 20:37:15 -0800 Subject: [PATCH] ext4: uninline large functions Saves nearly 4kbytes on x86. Cc: Arnaldo Carvalho de Melo Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ext4_jbd2.h | 76 +++++++++++------------------------------------ 1 file changed, 17 insertions(+), 59 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ext4_jbd2.h b/include/linux/ext4_jbd2.h index 72dd631912e4..d716e6392cf6 100644 --- a/include/linux/ext4_jbd2.h +++ b/include/linux/ext4_jbd2.h @@ -114,74 +114,32 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode); * been done yet. */ -void ext4_journal_abort_handle(const char *caller, const char *err_fn, - struct buffer_head *bh, handle_t *handle, int err); - -static inline int -__ext4_journal_get_undo_access(const char *where, handle_t *handle, - struct buffer_head *bh) +static inline void ext4_journal_release_buffer(handle_t *handle, + struct buffer_head *bh) { - int err = jbd2_journal_get_undo_access(handle, bh); - if (err) - ext4_journal_abort_handle(where, __FUNCTION__, bh, handle,err); - return err; + jbd2_journal_release_buffer(handle, bh); } -static inline int -__ext4_journal_get_write_access(const char *where, handle_t *handle, - struct buffer_head *bh) -{ - int err = jbd2_journal_get_write_access(handle, bh); - if (err) - ext4_journal_abort_handle(where, __FUNCTION__, bh, handle,err); - return err; -} +void ext4_journal_abort_handle(const char *caller, const char *err_fn, + struct buffer_head *bh, handle_t *handle, int err); -static inline void -ext4_journal_release_buffer(handle_t *handle, struct buffer_head *bh) -{ - jbd2_journal_release_buffer(handle, bh); -} +int __ext4_journal_get_undo_access(const char *where, handle_t *handle, + struct buffer_head *bh); -static inline int -__ext4_journal_forget(const char *where, handle_t *handle, struct buffer_head *bh) -{ - int err = jbd2_journal_forget(handle, bh); - if (err) - ext4_journal_abort_handle(where, __FUNCTION__, bh, handle,err); - return err; -} +int __ext4_journal_get_write_access(const char *where, handle_t *handle, + struct buffer_head *bh); -static inline int -__ext4_journal_revoke(const char *where, handle_t *handle, - ext4_fsblk_t blocknr, struct buffer_head *bh) -{ - int err = jbd2_journal_revoke(handle, blocknr, bh); - if (err) - ext4_journal_abort_handle(where, __FUNCTION__, bh, handle,err); - return err; -} +int __ext4_journal_forget(const char *where, handle_t *handle, + struct buffer_head *bh); -static inline int -__ext4_journal_get_create_access(const char *where, - handle_t *handle, struct buffer_head *bh) -{ - int err = jbd2_journal_get_create_access(handle, bh); - if (err) - ext4_journal_abort_handle(where, __FUNCTION__, bh, handle,err); - return err; -} +int __ext4_journal_revoke(const char *where, handle_t *handle, + ext4_fsblk_t blocknr, struct buffer_head *bh); -static inline int -__ext4_journal_dirty_metadata(const char *where, - handle_t *handle, struct buffer_head *bh) -{ - int err = jbd2_journal_dirty_metadata(handle, bh); - if (err) - ext4_journal_abort_handle(where, __FUNCTION__, bh, handle,err); - return err; -} +int __ext4_journal_get_create_access(const char *where, + handle_t *handle, struct buffer_head *bh); +int __ext4_journal_dirty_metadata(const char *where, + handle_t *handle, struct buffer_head *bh); #define ext4_journal_get_undo_access(handle, bh) \ __ext4_journal_get_undo_access(__FUNCTION__, (handle), (bh)) -- cgit v1.2.3 From 6cfd76a26d9fe2ba54b9d496a48c1d9285e5c5ed Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 6 Dec 2006 20:37:22 -0800 Subject: [PATCH] lockdep: name some old style locks Name some of the remaning 'old_style_spin_init' locks Signed-off-by: Peter Zijlstra Acked-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/init_task.h | 2 +- include/linux/mutex.h | 2 +- include/linux/rtmutex.h | 2 +- include/linux/rwsem-spinlock.h | 3 ++- include/linux/sunrpc/sched.h | 4 ++-- 5 files changed, 7 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 33c5daacc743..733790d4f7db 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -73,7 +73,7 @@ extern struct nsproxy init_nsproxy; #define INIT_NSPROXY(nsproxy) { \ .count = ATOMIC_INIT(1), \ - .nslock = SPIN_LOCK_UNLOCKED, \ + .nslock = __SPIN_LOCK_UNLOCKED(nsproxy.nslock), \ .uts_ns = &init_uts_ns, \ .namespace = NULL, \ INIT_IPC_NS(ipc_ns) \ diff --git a/include/linux/mutex.h b/include/linux/mutex.h index 27c48daa3183..b2b91c477563 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -94,7 +94,7 @@ do { \ #define __MUTEX_INITIALIZER(lockname) \ { .count = ATOMIC_INIT(1) \ - , .wait_lock = SPIN_LOCK_UNLOCKED \ + , .wait_lock = __SPIN_LOCK_UNLOCKED(lockname.wait_lock) \ , .wait_list = LIST_HEAD_INIT(lockname.wait_list) \ __DEBUG_MUTEX_INITIALIZER(lockname) \ __DEP_MAP_MUTEX_INITIALIZER(lockname) } diff --git a/include/linux/rtmutex.h b/include/linux/rtmutex.h index 5d41dee82f80..b0090e9f7884 100644 --- a/include/linux/rtmutex.h +++ b/include/linux/rtmutex.h @@ -63,7 +63,7 @@ struct hrtimer_sleeper; #endif #define __RT_MUTEX_INITIALIZER(mutexname) \ - { .wait_lock = SPIN_LOCK_UNLOCKED \ + { .wait_lock = __SPIN_LOCK_UNLOCKED(mutexname.wait_lock) \ , .wait_list = PLIST_HEAD_INIT(mutexname.wait_list, mutexname.wait_lock) \ , .owner = NULL \ __DEBUG_RT_MUTEX_INITIALIZER(mutexname)} diff --git a/include/linux/rwsem-spinlock.h b/include/linux/rwsem-spinlock.h index ae1fcadd598e..813cee13da0d 100644 --- a/include/linux/rwsem-spinlock.h +++ b/include/linux/rwsem-spinlock.h @@ -44,7 +44,8 @@ struct rw_semaphore { #endif #define __RWSEM_INITIALIZER(name) \ -{ 0, SPIN_LOCK_UNLOCKED, LIST_HEAD_INIT((name).wait_list) __RWSEM_DEP_MAP_INIT(name) } +{ 0, __SPIN_LOCK_UNLOCKED(name.wait_lock), LIST_HEAD_INIT((name).wait_list) \ + __RWSEM_DEP_MAP_INIT(name) } #define DECLARE_RWSEM(name) \ struct rw_semaphore name = __RWSEM_INITIALIZER(name) diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index f399c138f79d..0746c3b16f3a 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -222,7 +222,7 @@ struct rpc_wait_queue { #ifndef RPC_DEBUG # define RPC_WAITQ_INIT(var,qname) { \ - .lock = SPIN_LOCK_UNLOCKED, \ + .lock = __SPIN_LOCK_UNLOCKED(var.lock), \ .tasks = { \ [0] = LIST_HEAD_INIT(var.tasks[0]), \ [1] = LIST_HEAD_INIT(var.tasks[1]), \ @@ -231,7 +231,7 @@ struct rpc_wait_queue { } #else # define RPC_WAITQ_INIT(var,qname) { \ - .lock = SPIN_LOCK_UNLOCKED, \ + .lock = __SPIN_LOCK_UNLOCKED(var.lock), \ .tasks = { \ [0] = LIST_HEAD_INIT(var.tasks[0]), \ [1] = LIST_HEAD_INIT(var.tasks[1]), \ -- cgit v1.2.3 From ece8a684c75df215320b4155944979e3f78c5c93 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 6 Dec 2006 20:37:24 -0800 Subject: [PATCH] sleep profiling Implement prof=sleep profiling. TASK_UNINTERRUPTIBLE sleeps will be taken as a profile hit, and every millisecond spent sleeping causes a profile-hit for the call site that initiated the sleep. Sample readprofile output on i386: 306 ps2_sendbyte 1.3973 432 call_usermodehelper_keys 1.9548 484 ps2_command 0.6453 790 __driver_attach 4.7879 1593 msleep 44.2500 3976 sync_buffer 64.1290 4076 do_lookup 12.4648 8587 sync_page 122.6714 20820 total 0.0067 (NOTE: architectures need to check whether get_wchan() can be called from deep within the wakeup path.) akpm: we need to mark more functions __sched. lock_sock(), msleep(), others.. akpm: the contention in do_lookup() is a surprise. Presumably doing disk reads for directory contents while holding i_mutex. [akpm@osdl.org: various fixes] Signed-off-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/profile.h | 24 +++++++++++++++++++++++- 1 file changed, 23 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/profile.h b/include/linux/profile.h index acce53fd38b6..5670b340c4ef 100644 --- a/include/linux/profile.h +++ b/include/linux/profile.h @@ -6,10 +6,15 @@ #include #include #include +#include + #include +extern int prof_on __read_mostly; + #define CPU_PROFILING 1 #define SCHED_PROFILING 2 +#define SLEEP_PROFILING 3 struct proc_dir_entry; struct pt_regs; @@ -18,7 +23,24 @@ struct notifier_block; /* init basic kernel profiler */ void __init profile_init(void); void profile_tick(int); -void profile_hit(int, void *); + +/* + * Add multiple profiler hits to a given address: + */ +void profile_hits(int, void *ip, unsigned int nr_hits); + +/* + * Single profiler hit: + */ +static inline void profile_hit(int type, void *ip) +{ + /* + * Speedup for the common (no profiling enabled) case: + */ + if (unlikely(prof_on == type)) + profile_hits(type, ip, 1); +} + #ifdef CONFIG_PROC_FS void create_prof_cpu_mask(struct proc_dir_entry *); #else -- cgit v1.2.3 From d5abe669172f20a4129a711de0f250a4e07db298 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 6 Dec 2006 20:37:26 -0800 Subject: [PATCH] debug: workqueue locking sanity Workqueue functions should not leak locks, assert so, printing the last function ran. Use macros in lockdep.h to avoid include dependency pains. [akpm@osdl.org: build fix] Signed-off-by: Peter Zijlstra Acked-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/lockdep.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 819f08f1310d..da19aeb0dbe8 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -243,6 +243,8 @@ extern void lock_release(struct lockdep_map *lock, int nested, # define INIT_LOCKDEP .lockdep_recursion = 0, +#define lockdep_depth(tsk) ((tsk)->lockdep_depth) + #else /* !LOCKDEP */ static inline void lockdep_off(void) @@ -277,6 +279,9 @@ static inline int lockdep_internal(void) * The class key takes no space if lockdep is disabled: */ struct lock_class_key { }; + +#define lockdep_depth(tsk) (0) + #endif /* !LOCKDEP */ #if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_GENERIC_HARDIRQS) -- cgit v1.2.3 From 04903664325acb3f199dd8a4b8f1aa437e9fd6b2 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Wed, 6 Dec 2006 20:37:33 -0800 Subject: [PATCH] remove HASH_HIGHMEM It has no users and it's doubtful that we'll need it again. Cc: "David S. Miller" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootmem.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 31e9abb6d977..2275f2748708 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -119,8 +119,7 @@ extern void *alloc_large_system_hash(const char *tablename, unsigned int *_hash_mask, unsigned long limit); -#define HASH_HIGHMEM 0x00000001 /* Consider highmem? */ -#define HASH_EARLY 0x00000002 /* Allocating during early boot? */ +#define HASH_EARLY 0x00000001 /* Allocating during early boot? */ /* Only NUMA needs hash distribution. * IA64 is known to have sufficient vmalloc space. -- cgit v1.2.3 From cfd1893477fa94bb0915e39afa2f044ac978b5c6 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 6 Dec 2006 20:37:38 -0800 Subject: [PATCH] ktime: Fix signed / unsigned mismatch in ktime_to_ns The 32 bit implementation of ktime_to_ns returns unsigned value, while the 64 bit version correctly returns an signed value. There is no current user affected by this, but it has to be fixed, as ktime values can be negative. Pointed-out-by: Helmut Duregger Signed-off-by: Thomas Gleixner Acked-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ktime.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ktime.h b/include/linux/ktime.h index 84eeecd60a02..611f17f79eef 100644 --- a/include/linux/ktime.h +++ b/include/linux/ktime.h @@ -248,9 +248,9 @@ static inline struct timeval ktime_to_timeval(const ktime_t kt) * * Returns the scalar nanoseconds representation of kt */ -static inline u64 ktime_to_ns(const ktime_t kt) +static inline s64 ktime_to_ns(const ktime_t kt) { - return (u64) kt.tv.sec * NSEC_PER_SEC + kt.tv.nsec; + return (s64) kt.tv.sec * NSEC_PER_SEC + kt.tv.nsec; } #endif -- cgit v1.2.3 From 651971cb7242e8f6d7ebd153e69bd271cb731223 Mon Sep 17 00:00:00 2001 From: suzuki Date: Wed, 6 Dec 2006 20:37:48 -0800 Subject: [PATCH] Fix the size limit of compat space msgsize Currently we allocate 64k space on the user stack and use it the msgbuf for sys_{msgrcv,msgsnd} for compat and the results are later copied in user [ by copy_in_user]. This patch introduces helper routines for sys_{msgrcv,msgsnd} as below: do_msgsnd() : Accepts the mtype and user space ptr to the buffer along with the msqid and msgflg. do_msgrcv() : Accepts a kernel space ptr to mtype and a userspace ptr to the buffer. The mtype has to be copied back the user space msgbuf by the caller. These changes avoid the need to allocate the msgsize on the userspace ( thus removing the size limt ) and the overhead of an extra copy_in_user(). Signed-off-by: Suzuki K P Cc: Arnd Bergmann Cc: "David S. Miller" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/msg.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/msg.h b/include/linux/msg.h index acc7c174ff00..f1b60740d641 100644 --- a/include/linux/msg.h +++ b/include/linux/msg.h @@ -92,6 +92,12 @@ struct msg_queue { struct list_head q_senders; }; +/* Helper routines for sys_msgsnd and sys_msgrcv */ +extern long do_msgsnd(int msqid, long mtype, void __user *mtext, + size_t msgsz, int msgflg); +extern long do_msgrcv(int msqid, long *pmtype, void __user *mtext, + size_t msgsz, long msgtyp, int msgflg); + #endif /* __KERNEL__ */ #endif /* _LINUX_MSG_H */ -- cgit v1.2.3 From 386d9a7edd9f3492c99124b0a659e9ed7abb30f9 Mon Sep 17 00:00:00 2001 From: Magnus Damm Date: Wed, 6 Dec 2006 20:37:53 -0800 Subject: [PATCH] elf: Always define elf_addr_t in linux/elf.h Define elf_addr_t in linux/elf.h. The size of the type is determined using ELF_CLASS. This allows us to remove the defines that today are spread all over .c and .h files. Signed-off-by: Magnus Damm Cc: Daniel Jacobowitz Cc: Roland McGrath Cc: Jakub Jelinek Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/elf.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/elf.h b/include/linux/elf.h index 743d5c8e6d36..b403516d5c3d 100644 --- a/include/linux/elf.h +++ b/include/linux/elf.h @@ -358,6 +358,7 @@ extern Elf32_Dyn _DYNAMIC []; #define elfhdr elf32_hdr #define elf_phdr elf32_phdr #define elf_note elf32_note +#define elf_addr_t Elf32_Off #else @@ -365,6 +366,7 @@ extern Elf64_Dyn _DYNAMIC []; #define elfhdr elf64_hdr #define elf_phdr elf64_phdr #define elf_note elf64_note +#define elf_addr_t Elf64_Off #endif -- cgit v1.2.3 From b4c6c34a530b4d1c626f4ac0a884e0a9b849378c Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Wed, 6 Dec 2006 20:38:11 -0800 Subject: [PATCH] kprobes: enable booster on the preemptible kernel When we are unregistering a kprobe-booster, we can't release its instruction buffer immediately on the preemptive kernel, because some processes might be preempted on the buffer. The freeze_processes() and thaw_processes() functions can clean most of processes up from the buffer. There are still some non-frozen threads who have the PF_NOFREEZE flag. If those threads are sleeping (not preempted) at the known place outside the buffer, we can ensure safety of freeing. However, the processing of this check routine takes a long time. So, this patch introduces the garbage collection mechanism of insn_slot. It also introduces the "dirty" flag to free_insn_slot because of efficiency. The "clean" instruction slots (dirty flag is cleared) are released immediately. But the "dirty" slots which are used by boosted kprobes, are marked as garbages. collect_garbage_slots() will be invoked to release "dirty" slots if there are more than INSNS_PER_PAGE garbage slots or if there are no unused slots. Cc: "Keshavamurthy, Anil S" Cc: Ananth N Mavinakayanahalli Cc: "bibo,mao" Cc: Prasanna S Panchamukhi Cc: Yumiko Sugita Cc: Satoshi Oshima Cc: Hideo Aoki Signed-off-by: Masami Hiramatsu Acked-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kprobes.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index ac4c0559f751..769be39b9681 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -165,7 +165,7 @@ extern void arch_disarm_kprobe(struct kprobe *p); extern int arch_init_kprobes(void); extern void show_registers(struct pt_regs *regs); extern kprobe_opcode_t *get_insn_slot(void); -extern void free_insn_slot(kprobe_opcode_t *slot); +extern void free_insn_slot(kprobe_opcode_t *slot, int dirty); extern void kprobes_inc_nmissed_count(struct kprobe *p); /* Get the kprobe at this addr (if any) - called with preemption disabled */ -- cgit v1.2.3 From 83df8db9e62129975fab6d800fb381faf0dfee74 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 6 Dec 2006 20:38:14 -0800 Subject: [PATCH] declare smp_call_function_single in generic code smp_call_function_single() needs to be visible in non-SMP builds, to fix: arch/x86_64/kernel/vsyscall.c:283: warning: implicit declaration of function 'smp_call_function_single' Signed-off-by: Randy Dunlap Cc: Ingo Molnar Cc: Andi Kleen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/smp.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/smp.h b/include/linux/smp.h index 51649987f691..7ba23ec8211b 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -99,6 +99,13 @@ static inline int up_smp_call_function(void) static inline void smp_send_reschedule(int cpu) { } #define num_booting_cpus() 1 #define smp_prepare_boot_cpu() do {} while (0) +static inline int smp_call_function_single(int cpuid, void (*func) (void *info), + void *info, int retry, int wait) +{ + /* Disable interrupts here? */ + func(info); + return 0; +} #endif /* !SMP */ -- cgit v1.2.3 From 02316067852187b8bec781bec07410e91af79627 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 6 Dec 2006 20:38:17 -0800 Subject: [PATCH] hotplug CPU: clean up hotcpu_notifier() use There was lots of #ifdef noise in the kernel due to hotcpu_notifier(fn, prio) not correctly marking 'fn' as used in the !HOTPLUG_CPU case, and thus generating compiler warnings of unused symbols, hence forcing people to add #ifdefs. the compiler can skip truly unused functions just fine: text data bss dec hex filename 1624412 728710 3674856 6027978 5bfaca vmlinux.before 1624412 728710 3674856 6027978 5bfaca vmlinux.after [akpm@osdl.org: topology.c fix] Signed-off-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cpu.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index f02d71bf6894..71dc6ba4f73f 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -89,9 +89,9 @@ int cpu_down(unsigned int cpu); #define lock_cpu_hotplug() do { } while (0) #define unlock_cpu_hotplug() do { } while (0) #define lock_cpu_hotplug_interruptible() 0 -#define hotcpu_notifier(fn, pri) do { } while (0) -#define register_hotcpu_notifier(nb) do { } while (0) -#define unregister_hotcpu_notifier(nb) do { } while (0) +#define hotcpu_notifier(fn, pri) do { (void)(fn); } while (0) +#define register_hotcpu_notifier(nb) do { (void)(nb); } while (0) +#define unregister_hotcpu_notifier(nb) do { (void)(nb); } while (0) /* CPUs don't go offline once they're online w/o CONFIG_HOTPLUG_CPU */ static inline int cpu_is_offline(int cpu) { return 0; } -- cgit v1.2.3 From ebe7e5fe4b41deeb2731c5b52d8c8e6ac08b1f74 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Wed, 6 Dec 2006 20:38:21 -0800 Subject: [PATCH] remove kernel/lockdep.c:lockdep_internal Remove the no longer used lockdep_internal(). Signed-off-by: Adrian Bunk Acked-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/lockdep.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index da19aeb0dbe8..498bfbd3b4e1 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -193,7 +193,6 @@ extern void lockdep_free_key_range(void *start, unsigned long size); extern void lockdep_off(void); extern void lockdep_on(void); -extern int lockdep_internal(void); /* * These methods are used by specific locking variants (spinlocks, @@ -255,11 +254,6 @@ static inline void lockdep_on(void) { } -static inline int lockdep_internal(void) -{ - return 0; -} - # define lock_acquire(l, s, t, r, c, i) do { } while (0) # define lock_release(l, n, i) do { } while (0) # define lockdep_init() do { } while (0) -- cgit v1.2.3 From d3228a887cae75ef2b8b1211c31c539bef5a5698 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Wed, 6 Dec 2006 20:38:22 -0800 Subject: [PATCH] make kernel/signal.c:kill_proc_info() static Signed-off-by: Adrian Bunk 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 0a90cefb0b0d..3a767242e72f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1305,7 +1305,6 @@ extern int kill_pgrp(struct pid *pid, int sig, int priv); extern int kill_pid(struct pid *pid, int sig, int priv); extern int __kill_pg_info(int sig, struct siginfo *info, pid_t pgrp); extern int kill_pg_info(int, struct siginfo *, pid_t); -extern int kill_proc_info(int, struct siginfo *, pid_t); extern void do_notify_parent(struct task_struct *, int); extern void force_sig(int, struct task_struct *); extern void force_sig_specific(int, struct task_struct *); -- cgit v1.2.3 From d394e122bc1adba0f3eb1ebec1cedb8a8c524741 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Wed, 6 Dec 2006 20:38:26 -0800 Subject: [PATCH] make fs/jbd/transaction.c:__journal_temp_unlink_buffer() static Signed-off-by: Adrian Bunk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/jbd.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/jbd.h b/include/linux/jbd.h index dacd566c9f6c..452737551260 100644 --- a/include/linux/jbd.h +++ b/include/linux/jbd.h @@ -839,7 +839,6 @@ struct journal_s */ /* Filing buffers */ -extern void __journal_temp_unlink_buffer(struct journal_head *jh); extern void journal_unfile_buffer(journal_t *, struct journal_head *); extern void __journal_unfile_buffer(struct journal_head *); extern void __journal_refile_buffer(struct journal_head *); -- cgit v1.2.3 From 7ddae86095794cce4364740edd8463c77654a265 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Wed, 6 Dec 2006 20:38:27 -0800 Subject: [PATCH] make fs/jbd2/transaction.c:__kbd2_journal_temp_unlink_buffer() static Signed-off-by: Adrian Bunk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/jbd2.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 98a0ae52660f..0e0fedd2039a 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -848,7 +848,6 @@ struct journal_s */ /* Filing buffers */ -extern void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh); extern void jbd2_journal_unfile_buffer(journal_t *, struct journal_head *); extern void __jbd2_journal_unfile_buffer(struct journal_head *); extern void __jbd2_journal_refile_buffer(struct journal_head *); -- cgit v1.2.3 From c585646dd1d98caf0a5f2e85c794c1441df6fac1 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Wed, 6 Dec 2006 20:38:29 -0800 Subject: [PATCH] fs/lockd/host.c: make 2 functions static Make the following needlessly global functions static: - nlm_lookup_host() - nsm_find() Signed-off-by: Adrian Bunk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/lockd/lockd.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index 862d9730a60d..8c39654549d8 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -164,14 +164,12 @@ void nlmclnt_next_cookie(struct nlm_cookie *); */ struct nlm_host * nlmclnt_lookup_host(const struct sockaddr_in *, int, int, const char *, int); struct nlm_host * nlmsvc_lookup_host(struct svc_rqst *, const char *, int); -struct nlm_host * nlm_lookup_host(int server, const struct sockaddr_in *, int, int, const char *, int); struct rpc_clnt * nlm_bind_host(struct nlm_host *); void nlm_rebind_host(struct nlm_host *); struct nlm_host * nlm_get_host(struct nlm_host *); void nlm_release_host(struct nlm_host *); void nlm_shutdown_hosts(void); extern void nlm_host_rebooted(const struct sockaddr_in *, const char *, int, u32); -struct nsm_handle *nsm_find(const struct sockaddr_in *, const char *, int); void nsm_release(struct nsm_handle *); -- cgit v1.2.3 From d9489fb60614794cbca4b6b173c60ed9388974c6 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 6 Dec 2006 20:38:43 -0800 Subject: [PATCH] kernel-doc: fix fusion and i2o docs Correct lots of typos, kernel-doc warnings, & kernel-doc usage in fusion and i2o drivers. Signed-off-by: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/i2o.h | 18 +++++++++++------- 1 file changed, 11 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2o.h b/include/linux/i2o.h index 2514f4e286b7..52f53e2e70c3 100644 --- a/include/linux/i2o.h +++ b/include/linux/i2o.h @@ -986,7 +986,8 @@ extern void i2o_driver_unregister(struct i2o_driver *); /** * i2o_driver_notify_controller_add - Send notification of added controller - * to a single I2O driver + * @drv: I2O driver + * @c: I2O controller * * Send notification of added controller to a single registered driver. */ @@ -998,8 +999,9 @@ static inline void i2o_driver_notify_controller_add(struct i2o_driver *drv, }; /** - * i2o_driver_notify_controller_remove - Send notification of removed - * controller to a single I2O driver + * i2o_driver_notify_controller_remove - Send notification of removed controller + * @drv: I2O driver + * @c: I2O controller * * Send notification of removed controller to a single registered driver. */ @@ -1011,8 +1013,9 @@ static inline void i2o_driver_notify_controller_remove(struct i2o_driver *drv, }; /** - * i2o_driver_notify_device_add - Send notification of added device to a - * single I2O driver + * i2o_driver_notify_device_add - Send notification of added device + * @drv: I2O driver + * @i2o_dev: the added i2o_device * * Send notification of added device to a single registered driver. */ @@ -1025,7 +1028,8 @@ static inline void i2o_driver_notify_device_add(struct i2o_driver *drv, /** * i2o_driver_notify_device_remove - Send notification of removed device - * to a single I2O driver + * @drv: I2O driver + * @i2o_dev: the added i2o_device * * Send notification of removed device to a single registered driver. */ @@ -1148,7 +1152,7 @@ static inline void i2o_msg_post(struct i2o_controller *c, /** * i2o_msg_post_wait - Post and wait a message and wait until return * @c: controller - * @m: message to post + * @msg: message to post * @timeout: time in seconds to wait * * This API allows an OSM to post a message and then be told whether or -- cgit v1.2.3 From 83b7b44e1c1e9e493ccd4146558481ab5af0116a Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 6 Dec 2006 20:38:53 -0800 Subject: [PATCH] fs: reorder some 'struct inode' fields to speedup i_size manipulations On 32bits SMP platforms, 64bits i_size is protected by a seqcount (i_size_seqcount). When i_size is read or written, i_size_seqcount is read/written as well, so it make sense to group these two fields together in the same cache line. This patch moves i_size_seqcount next to i_size, and also moves i_version to let offsetof(struct inode, i_size) being 0x40 instead of 0x3c (for 32bits platforms). For 64 bits platforms, i_size_seqcount doesnt exist, and the move of a 'long i_version' should not introduce a new hole because of padding. Signed-off-by: Eric Dumazet Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index d791bae9de9c..3a1927e516d0 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -548,12 +548,15 @@ struct inode { uid_t i_uid; gid_t i_gid; dev_t i_rdev; + unsigned long i_version; loff_t i_size; +#ifdef __NEED_I_SIZE_ORDERED + seqcount_t i_size_seqcount; +#endif struct timespec i_atime; struct timespec i_mtime; struct timespec i_ctime; unsigned int i_blkbits; - unsigned long i_version; blkcnt_t i_blocks; unsigned short i_bytes; spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */ @@ -598,9 +601,6 @@ struct inode { void *i_security; #endif void *i_private; /* fs or device private pointer */ -#ifdef __NEED_I_SIZE_ORDERED - seqcount_t i_size_seqcount; -#endif }; /* -- cgit v1.2.3 From f7dff2b12654149c9cac8d8c79b6588759edd5a9 Mon Sep 17 00:00:00 2001 From: Gautham R Shenoy Date: Wed, 6 Dec 2006 20:38:58 -0800 Subject: [PATCH] Handle per-subsystem mutexes for CONFIG_HOTPLUG_CPU not set Provide a common interface for all the subsystems to lock and unlock their per-subsystem hotcpu mutexes. When CONFIG_HOTPLUG_CPU is not set, these operations would be no-ops. [akpm@osdl.org: macros -> inlines] Signed-off-by: Gautham R Shenoy Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cpu.h | 23 +++++++++++++++++++++-- 1 file changed, 21 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 71dc6ba4f73f..bf00ce6ecadf 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -24,6 +24,7 @@ #include #include #include +#include struct cpu { int node_id; /* The node which contains the CPU */ @@ -74,6 +75,17 @@ extern struct sysdev_class cpu_sysdev_class; #ifdef CONFIG_HOTPLUG_CPU /* Stop CPUs going up and down. */ + +static inline void cpuhotplug_mutex_lock(struct mutex *cpu_hp_mutex) +{ + mutex_lock(cpu_hp_mutex); +} + +static inline void cpuhotplug_mutex_unlock(struct mutex *cpu_hp_mutex) +{ + mutex_unlock(cpu_hp_mutex); +} + extern void lock_cpu_hotplug(void); extern void unlock_cpu_hotplug(void); #define hotcpu_notifier(fn, pri) { \ @@ -85,7 +97,14 @@ extern void unlock_cpu_hotplug(void); #define unregister_hotcpu_notifier(nb) unregister_cpu_notifier(nb) int cpu_down(unsigned int cpu); #define cpu_is_offline(cpu) unlikely(!cpu_online(cpu)) -#else + +#else /* CONFIG_HOTPLUG_CPU */ + +static inline void cpuhotplug_mutex_lock(struct mutex *cpu_hp_mutex) +{ } +static inline void cpuhotplug_mutex_unlock(struct mutex *cpu_hp_mutex) +{ } + #define lock_cpu_hotplug() do { } while (0) #define unlock_cpu_hotplug() do { } while (0) #define lock_cpu_hotplug_interruptible() 0 @@ -95,7 +114,7 @@ int cpu_down(unsigned int cpu); /* CPUs don't go offline once they're online w/o CONFIG_HOTPLUG_CPU */ static inline int cpu_is_offline(int cpu) { return 0; } -#endif +#endif /* CONFIG_HOTPLUG_CPU */ #ifdef CONFIG_SUSPEND_SMP extern int disable_nonboot_cpus(void); -- cgit v1.2.3 From 0b71c8e76d20d0329bf7e54f172389f3c343dc41 Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Wed, 6 Dec 2006 20:39:15 -0800 Subject: [PATCH] remove useless carta_random32.h Remove the carta_random32.h header file. The carta_random32() function was was put in and removed in favor of random32(). In the removal process, the header file was forgotten. Signed-off-by: Stephane Eranian Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/carta_random32.h | 29 ----------------------------- 1 file changed, 29 deletions(-) delete mode 100644 include/linux/carta_random32.h (limited to 'include/linux') diff --git a/include/linux/carta_random32.h b/include/linux/carta_random32.h deleted file mode 100644 index f6f3bd9f20b5..000000000000 --- a/include/linux/carta_random32.h +++ /dev/null @@ -1,29 +0,0 @@ -/* - * Fast, simple, yet decent quality random number generator based on - * a paper by David G. Carta ("Two Fast Implementations of the - * `Minimal Standard' Random Number Generator," Communications of the - * ACM, January, 1990). - * - * Copyright (c) 2002-2006 Hewlett-Packard Development Company, L.P. - * Contributed by Stephane Eranian - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of version 2 of the GNU General Public - * License as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA - * 02111-1307 USA - */ -#ifndef _LINUX_CARTA_RANDOM32_H_ -#define _LINUX_CARTA_RANDOM32_H_ - -u64 carta_random32(u64 seed); - -#endif /* _LINUX_CARTA_RANDOM32_H_ */ -- cgit v1.2.3 From 2ee91f197c0bc654b24eed5831fd12aa0d566a7d Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 6 Dec 2006 20:39:32 -0800 Subject: [PATCH] lockdep: show more details about self-test failures Make the locking self-test failures (of 'FAILURE' type) easier to debug by printing more information. Signed-off-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/debug_locks.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/debug_locks.h b/include/linux/debug_locks.h index 952bee79a8f3..a1c10b0c4cf0 100644 --- a/include/linux/debug_locks.h +++ b/include/linux/debug_locks.h @@ -24,7 +24,7 @@ extern int debug_locks_off(void); int __ret = 0; \ \ if (unlikely(c)) { \ - if (debug_locks_off()) \ + if (debug_locks_silent || debug_locks_off()) \ WARN_ON(1); \ __ret = 1; \ } \ -- cgit v1.2.3 From 12d40e43d251de4fa1f982567fc8b4ee5e858367 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 6 Dec 2006 20:39:53 -0800 Subject: [PATCH] Save some bytes in struct inode [acme@newtoy net-2.6.20]$ pahole --cacheline 64 fs/inode.o inode /* /pub/scm/linux/kernel/git/acme/net-2.6.20/include/linux/dcache.h:86 */ struct inode { struct hlist_node i_hash; /* 0 8 */ struct list_head i_list; /* 8 8 */ struct list_head i_sb_list; /* 16 8 */ struct list_head i_dentry; /* 24 8 */ long unsigned int i_ino; /* 32 4 */ atomic_t i_count; /* 36 4 */ umode_t i_mode; /* 40 2 */ /* XXX 2 bytes hole, try to pack */ unsigned int i_nlink; /* 44 4 */ uid_t i_uid; /* 48 4 */ gid_t i_gid; /* 52 4 */ dev_t i_rdev; /* 56 4 */ loff_t i_size; /* 60 8 */ struct timespec i_atime; /* 68 8 */ struct timespec i_mtime; /* 76 8 */ struct timespec i_ctime; /* 84 8 */ unsigned int i_blkbits; /* 92 4 */ long unsigned int i_version; /* 96 4 */ blkcnt_t i_blocks; /* 100 4 */ short unsigned int i_bytes; /* 104 2 */ /* XXX 2 bytes hole, try to pack */ spinlock_t i_lock; /* 108 40 */ struct mutex i_mutex; /* 148 76 */ struct rw_semaphore i_alloc_sem; /* 224 64 */ struct inode_operations * i_op; /* 288 4 */ const struct file_operations * i_fop; /* 292 4 */ struct super_block * i_sb; /* 296 4 */ struct file_lock * i_flock; /* 300 4 */ struct address_space * i_mapping; /* 304 4 */ struct address_space i_data; /* 308 188 */ struct list_head i_devices; /* 496 8 */ union ; /* 504 4 */ int i_cindex; /* 508 4 */ __u32 i_generation; /* 512 4 */ /* ---------- cacheline 8 boundary ---------- */ long unsigned int i_dnotify_mask; /* 516 4 */ struct dnotify_struct * i_dnotify; /* 520 4 */ struct list_head inotify_watches; /* 524 8 */ struct mutex inotify_mutex; /* 532 76 */ long unsigned int i_state; /* 608 4 */ long unsigned int dirtied_when; /* 612 4 */ unsigned int i_flags; /* 616 4 */ atomic_t i_writecount; /* 620 4 */ void * i_security; /* 624 4 */ void * i_private; /* 628 4 */ }; /* size: 632, sum members: 628, holes: 2, sum holes: 4 */ [acme@newtoy net-2.6.20]$ So just moving i_mode to after i_bytes we save 4 bytes by nuking both holes: [acme@newtoy net-2.6.20]$ codiff -V /tmp/inode.o.before fs/inode.o /pub/scm/linux/kernel/git/acme/net-2.6.20/fs/inode.c: struct inode | -4 i_mode; from: umode_t /* 40(0) 2(0) */ to: umode_t /* 102(0) 2(0) */ 1 struct changed [acme@newtoy net-2.6.20]$ I've prunned all the other offset changes, only this one is of interest here. So now we have: [acme@newtoy net-2.6.20]$ pahole --cacheline 64 ../OUTPUT/qemu/net-2.6.20/fs/inode.o inode /* /pub/scm/linux/kernel/git/acme/net-2.6.20/include/linux/dcache.h:86 */ struct inode { struct hlist_node i_hash; /* 0 8 */ struct list_head i_list; /* 8 8 */ struct list_head i_sb_list; /* 16 8 */ struct list_head i_dentry; /* 24 8 */ long unsigned int i_ino; /* 32 4 */ atomic_t i_count; /* 36 4 */ unsigned int i_nlink; /* 40 4 */ uid_t i_uid; /* 44 4 */ gid_t i_gid; /* 48 4 */ dev_t i_rdev; /* 52 4 */ loff_t i_size; /* 56 8 */ /* ---------- cacheline 1 boundary ---------- */ struct timespec i_atime; /* 64 8 */ struct timespec i_mtime; /* 72 8 */ struct timespec i_ctime; /* 80 8 */ unsigned int i_blkbits; /* 88 4 */ long unsigned int i_version; /* 92 4 */ blkcnt_t i_blocks; /* 96 4 */ short unsigned int i_bytes; /* 100 2 */ umode_t i_mode; /* 102 2 */ spinlock_t i_lock; /* 104 40 */ struct mutex i_mutex; /* 144 76 */ struct rw_semaphore i_alloc_sem; /* 220 64 */ struct inode_operations * i_op; /* 284 4 */ const struct file_operations * i_fop; /* 288 4 */ struct super_block * i_sb; /* 292 4 */ struct file_lock * i_flock; /* 296 4 */ struct address_space * i_mapping; /* 300 4 */ struct address_space i_data; /* 304 188 */ struct list_head i_devices; /* 492 8 */ union ; /* 500 4 */ int i_cindex; /* 504 4 */ __u32 i_generation; /* 508 4 */ /* ---------- cacheline 8 boundary ---------- */ long unsigned int i_dnotify_mask; /* 512 4 */ struct dnotify_struct * i_dnotify; /* 516 4 */ struct list_head inotify_watches; /* 520 8 */ struct mutex inotify_mutex; /* 528 76 */ long unsigned int i_state; /* 604 4 */ long unsigned int dirtied_when; /* 608 4 */ unsigned int i_flags; /* 612 4 */ atomic_t i_writecount; /* 616 4 */ void * i_security; /* 620 4 */ void * i_private; /* 624 4 */ }; /* size: 628 */ [acme@newtoy net-2.6.20]$ Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 3a1927e516d0..70b99fbb560b 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -543,7 +543,6 @@ struct inode { struct list_head i_dentry; unsigned long i_ino; atomic_t i_count; - umode_t i_mode; unsigned int i_nlink; uid_t i_uid; gid_t i_gid; @@ -559,6 +558,7 @@ struct inode { unsigned int i_blkbits; blkcnt_t i_blocks; unsigned short i_bytes; + umode_t i_mode; spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */ struct mutex i_mutex; struct rw_semaphore i_alloc_sem; -- cgit v1.2.3 From 0da1480ec33d4bac8c32051c1d33202be6dc439f Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Wed, 6 Dec 2006 20:40:03 -0800 Subject: [PATCH] proper prototype for remove_inode_dquot_ref() Add a proper prototype for remove_inode_dquot_ref() in include/linux/quotaops.h Signed-off-by: Adrian Bunk Acked-by: Jan Kara Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/quotaops.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index 5110201a4159..90c23f690c0d 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -37,6 +37,9 @@ extern int dquot_release(struct dquot *dquot); extern int dquot_commit_info(struct super_block *sb, int type); extern int dquot_mark_dquot_dirty(struct dquot *dquot); +int remove_inode_dquot_ref(struct inode *inode, int type, + struct list_head *tofree_head); + extern int vfs_quota_on(struct super_block *sb, int type, int format_id, char *path); extern int vfs_quota_on_mount(struct super_block *sb, char *qf_name, int format_id, int type); -- cgit v1.2.3 From 65867beb0de4d055637476327b533e5ffbec2b97 Mon Sep 17 00:00:00 2001 From: Jordan Crouse Date: Wed, 6 Dec 2006 20:40:07 -0800 Subject: [PATCH] Trivial cleanup in the PCI IDs for the CS5535 Rename a poorly worded PCI ID for the Geode GX and CS5535 companion chips. The graphics processor and host bridge actually live in the northbridge on the integrated processor, not in the companion chip. Signed-off-by: Jordan Crouse Acked-by: Alan Cox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pci_ids.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index dcdb90f06d73..ff2dcb436cd0 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -390,7 +390,7 @@ #define PCI_DEVICE_ID_NS_CS5535_IDE 0x002d #define PCI_DEVICE_ID_NS_CS5535_AUDIO 0x002e #define PCI_DEVICE_ID_NS_CS5535_USB 0x002f -#define PCI_DEVICE_ID_NS_CS5535_VIDEO 0x0030 +#define PCI_DEVICE_ID_NS_GX_VIDEO 0x0030 #define PCI_DEVICE_ID_NS_SATURN 0x0035 #define PCI_DEVICE_ID_NS_SCx200_BRIDGE 0x0500 #define PCI_DEVICE_ID_NS_SCx200_SMI 0x0501 @@ -403,8 +403,7 @@ #define PCI_DEVICE_ID_NS_SC1100_XBUS 0x0515 #define PCI_DEVICE_ID_NS_87410 0xd001 -#define PCI_DEVICE_ID_NS_CS5535_HOST_BRIDGE 0x0028 -#define PCI_DEVICE_ID_NS_CS5535_ISA_BRIDGE 0x002b +#define PCI_DEVICE_ID_NS_GX_HOST_BRIDGE 0x0028 #define PCI_VENDOR_ID_TSENG 0x100c #define PCI_DEVICE_ID_TSENG_W32P_2 0x3202 -- cgit v1.2.3 From 5296c7bec8c85aa0a6964eca9ff4a1a8847fba8a Mon Sep 17 00:00:00 2001 From: Mariusz Kozlowski Date: Wed, 6 Dec 2006 20:40:10 -0800 Subject: [PATCH] fs: reiserfs add missing brackets Signed-off-by: Andrew Morton 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 7bc6bfb86253..d0e4dce33ad5 100644 --- a/include/linux/reiserfs_fs.h +++ b/include/linux/reiserfs_fs.h @@ -739,7 +739,7 @@ struct block_head { #define PUT_B_FREE_SPACE(p_s_bh,val) do { set_blkh_free_space(B_BLK_HEAD(p_s_bh),val); } while (0) /* Get right delimiting key. -- little endian */ -#define B_PRIGHT_DELIM_KEY(p_s_bh) (&(blk_right_delim_key(B_BLK_HEAD(p_s_bh)) +#define B_PRIGHT_DELIM_KEY(p_s_bh) (&(blk_right_delim_key(B_BLK_HEAD(p_s_bh)))) /* Does the buffer contain a disk leaf. */ #define B_IS_ITEMS_LEVEL(p_s_bh) (B_LEVEL(p_s_bh) == DISK_LEAF_NODE_LEVEL) -- cgit v1.2.3 From a0e7688df1484fbf4d6d61c31f7d61a5d8cacf3c Mon Sep 17 00:00:00 2001 From: "Robert P. J. Day" Date: Wed, 6 Dec 2006 20:40:12 -0800 Subject: [PATCH] Kbuild: add 3 more header files to get properly "unifdef"ed Add 3 more files to get "unifdef"ed when creating sanitized headers with "make headers_install". Signed-off-by: Robert P. J. Day Acked-by: David Woodhouse Acked-by: "John W. Linville" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/Kbuild | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/Kbuild b/include/linux/Kbuild index ff433126361f..e618b25b5add 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -221,6 +221,7 @@ unifdef-y += if_bridge.h unifdef-y += if_ec.h unifdef-y += if_eql.h unifdef-y += if_ether.h +unifdef-y += if_fddi.h unifdef-y += if_frad.h unifdef-y += if_ltalk.h unifdef-y += if_pppox.h @@ -282,6 +283,7 @@ unifdef-y += nvram.h unifdef-y += parport.h unifdef-y += patchkey.h unifdef-y += pci.h +unifdef-y += personality.h unifdef-y += pktcdvd.h unifdef-y += pmu.h unifdef-y += poll.h @@ -337,6 +339,7 @@ unifdef-y += videodev.h unifdef-y += wait.h unifdef-y += wanrouter.h unifdef-y += watchdog.h +unifdef-y += wireless.h unifdef-y += xfrm.h objhdr-y += version.h -- cgit v1.2.3 From 15ad7cdcfd76450d4beebc789ec646664238184d Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Wed, 6 Dec 2006 20:40:36 -0800 Subject: [PATCH] struct seq_operations and struct file_operations constification - move some file_operations structs into the .rodata section - move static strings from policy_types[] array into the .rodata section - fix generic seq_operations usages, so that those structs may be defined as "const" as well [akpm@osdl.org: couple of fixes] Signed-off-by: Helge Deller Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cpuset.h | 2 +- include/linux/mmzone.h | 2 +- include/linux/relay.h | 2 +- include/linux/sched.h | 2 +- include/linux/seq_file.h | 4 ++-- 5 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index 748d2c996631..8821e1f75b44 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -46,7 +46,7 @@ extern int cpuset_excl_nodes_overlap(const struct task_struct *p); extern int cpuset_memory_pressure_enabled; extern void __cpuset_memory_pressure_bump(void); -extern struct file_operations proc_cpuset_operations; +extern const struct file_operations proc_cpuset_operations; extern char *cpuset_task_status_allowed(struct task_struct *task, char *buffer); extern void cpuset_lock(void); diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index da6002dec205..e339a7345f25 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -278,7 +278,7 @@ struct zone { /* * rarely used fields: */ - char *name; + const char *name; } ____cacheline_internodealigned_in_smp; /* diff --git a/include/linux/relay.h b/include/linux/relay.h index 0e3d91b76996..c6a48bfc8b14 100644 --- a/include/linux/relay.h +++ b/include/linux/relay.h @@ -274,7 +274,7 @@ static inline void subbuf_start_reserve(struct rchan_buf *buf, /* * exported relay file operations, kernel/relay.c */ -extern struct file_operations relay_file_operations; +extern const struct file_operations relay_file_operations; #endif /* _LINUX_RELAY_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 3a767242e72f..dede82c63445 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -573,7 +573,7 @@ struct sched_info { #endif /* defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) */ #ifdef CONFIG_SCHEDSTATS -extern struct file_operations proc_schedstat_operations; +extern const struct file_operations proc_schedstat_operations; #endif /* CONFIG_SCHEDSTATS */ #ifdef CONFIG_TASK_DELAY_ACCT diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index b95f6eb7254c..3e3cccbb1cac 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -20,7 +20,7 @@ struct seq_file { loff_t index; loff_t version; struct mutex lock; - struct seq_operations *op; + const struct seq_operations *op; void *private; }; @@ -31,7 +31,7 @@ struct seq_operations { int (*show) (struct seq_file *m, void *v); }; -int seq_open(struct file *, struct seq_operations *); +int seq_open(struct file *, const struct seq_operations *); ssize_t seq_read(struct file *, char __user *, size_t, loff_t *); loff_t seq_lseek(struct file *, loff_t, int); int seq_release(struct inode *, struct file *); -- cgit v1.2.3 From 85916f8166b59eeac63d2b4f7f1df8de849334b4 Mon Sep 17 00:00:00 2001 From: Magnus Damm Date: Wed, 6 Dec 2006 20:40:41 -0800 Subject: [PATCH] Kexec / Kdump: Unify elf note code The elf note saving code is currently duplicated over several architectures. This cleanup patch simply adds code to a common file and then replaces the arch-specific code with calls to the newly added code. The only drawback with this approach is that s390 doesn't fully support kexec-on-panic which for that arch leads to introduction of unused code. Signed-off-by: Magnus Damm Cc: Vivek Goyal Cc: Andi Kleen Cc: Paul Mackerras Cc: Benjamin Herrenschmidt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kexec.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index a4ede62b339d..e3abcec6c51c 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -105,6 +105,7 @@ extern struct page *kimage_alloc_control_pages(struct kimage *image, unsigned int order); extern void crash_kexec(struct pt_regs *); int kexec_should_crash(struct task_struct *); +void crash_save_cpu(struct pt_regs *regs, int cpu); extern struct kimage *kexec_image; extern struct kimage *kexec_crash_image; -- cgit v1.2.3 From 97d2a80584b30b5cd32da411deca1986ef61877a Mon Sep 17 00:00:00 2001 From: Benjamin LaHaise Date: Wed, 6 Dec 2006 20:40:45 -0800 Subject: [PATCH] aio: remove ki_retried debugging member Remove the ki_retried member from struct kiocb. I think the idea was bounced around a while back, but Arnaldo pointed out another reason that we should dig it up when he pointed out that the last cacheline of struct kiocb only contains 4 bytes. By removing the debugging member, we save more than the 8 byte on 64 bit machines. Signed-off-by: Benjamin LaHaise Acked-by: Ken Chen Acked-by: Zach Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/aio.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/aio.h b/include/linux/aio.h index 9e350fd44d77..3372ec6bf53a 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -111,7 +111,6 @@ struct kiocb { size_t ki_nbytes; /* copy of iocb->aio_nbytes */ char __user *ki_buf; /* remaining iocb->aio_buf */ size_t ki_left; /* remaining bytes */ - long ki_retried; /* just for testing */ struct iovec ki_inline_vec; /* inline vector */ struct iovec *ki_iovec; unsigned long ki_nr_segs; @@ -238,7 +237,6 @@ do { \ } while (0) #define io_wait_to_kiocb(wait) container_of(wait, struct kiocb, ki_wait) -#define is_retried_kiocb(iocb) ((iocb)->ki_retried > 1) #include -- cgit v1.2.3 From 6b39bb6548d60b9a18826134b5ccd5c3cef85fe2 Mon Sep 17 00:00:00 2001 From: Paul Clements Date: Wed, 6 Dec 2006 20:40:53 -0800 Subject: [PATCH] nbd: show nbd client pid in sysfs Allow nbd to expose the nbd-client daemon's PID in /sys/block/nbd/pid. This is helpful for tracking connection status of a device and for determining which nbd devices are currently in use. Signed-off-by: Paul Clements Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nbd.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nbd.h b/include/linux/nbd.h index d6b6dc09ad97..0f3e69302540 100644 --- a/include/linux/nbd.h +++ b/include/linux/nbd.h @@ -64,6 +64,7 @@ struct nbd_device { struct gendisk *disk; int blksize; u64 bytesize; + pid_t pid; /* pid of nbd-client, if attached */ }; #endif -- cgit v1.2.3 From 759643b874907e76ae81e34df62f41ab6683f5c2 Mon Sep 17 00:00:00 2001 From: Corey Minyard Date: Wed, 6 Dec 2006 20:40:59 -0800 Subject: [PATCH] IPMI: pass sysfs name from lower level driver Pass in the sysfs name from the lower-level IPMI driver, as the coming IPMI serial driver will need that to link properly from the serial device sysfs directory. Signed-off-by: Corey Minyard Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ipmi_smi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ipmi_smi.h b/include/linux/ipmi_smi.h index 6d9c7e4da472..2cc960da4176 100644 --- a/include/linux/ipmi_smi.h +++ b/include/linux/ipmi_smi.h @@ -173,6 +173,7 @@ int ipmi_register_smi(struct ipmi_smi_handlers *handlers, void *send_info, struct ipmi_device_id *device_id, struct device *dev, + const char *sysfs_name, unsigned char slave_addr); /* -- cgit v1.2.3 From b9675136e2ad95156fb93be6155f17590bb26fd7 Mon Sep 17 00:00:00 2001 From: Corey Minyard Date: Wed, 6 Dec 2006 20:41:02 -0800 Subject: [PATCH] IPMI: Add maintenance mode Some commands and operations on a BMC can cause the BMC to "go away" for a while. This can cause the automatic flag processing and other things of that nature to timeout and generate annoying logs, or possibly cause other bad things to happen when in firmware update mode. Add detection of those commands (cold reset, warm reset, and any firmware command) and turns off automatic processing for 30 seconds. It also add a manual override either way. Signed-off-by: Corey Minyard Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ipmi.h | 45 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/ipmi_msgdefs.h | 5 +++++ include/linux/ipmi_smi.h | 7 +++++++ 3 files changed, 57 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ipmi.h b/include/linux/ipmi.h index 796ca009fd46..7a9db390c56a 100644 --- a/include/linux/ipmi.h +++ b/include/linux/ipmi.h @@ -208,6 +208,15 @@ struct kernel_ipmi_msg code as the first byte of the incoming data, unlike a response. */ +/* + * Modes for ipmi_set_maint_mode() and the userland IOCTL. The AUTO + * setting is the default and means it will be set on certain + * commands. Hard setting it on and off will override automatic + * operation. + */ +#define IPMI_MAINTENANCE_MODE_AUTO 0 +#define IPMI_MAINTENANCE_MODE_OFF 1 +#define IPMI_MAINTENANCE_MODE_ON 2 #ifdef __KERNEL__ @@ -373,6 +382,35 @@ int ipmi_unregister_for_cmd(ipmi_user_t user, unsigned char cmd, unsigned int chans); +/* + * Go into a mode where the driver will not autonomously attempt to do + * things with the interface. It will still respond to attentions and + * interrupts, and it will expect that commands will complete. It + * will not automatcially check for flags, events, or things of that + * nature. + * + * This is primarily used for firmware upgrades. The idea is that + * when you go into firmware upgrade mode, you do this operation + * and the driver will not attempt to do anything but what you tell + * it or what the BMC asks for. + * + * Note that if you send a command that resets the BMC, the driver + * will still expect a response from that command. So the BMC should + * reset itself *after* the response is sent. Resetting before the + * response is just silly. + * + * If in auto maintenance mode, the driver will automatically go into + * maintenance mode for 30 seconds if it sees a cold reset, a warm + * reset, or a firmware NetFN. This means that code that uses only + * firmware NetFN commands to do upgrades will work automatically + * without change, assuming it sends a message every 30 seconds or + * less. + * + * See the IPMI_MAINTENANCE_MODE_xxx defines for what the mode means. + */ +int ipmi_get_maintenance_mode(ipmi_user_t user); +int ipmi_set_maintenance_mode(ipmi_user_t user, int mode); + /* * Allow run-to-completion mode to be set for the interface of * a specific user. @@ -656,4 +694,11 @@ struct ipmi_timing_parms #define IPMICTL_GET_TIMING_PARMS_CMD _IOR(IPMI_IOC_MAGIC, 23, \ struct ipmi_timing_parms) +/* + * Set the maintenance mode. See ipmi_set_maintenance_mode() above + * for a description of what this does. + */ +#define IPMICTL_GET_MAINTENANCE_MODE_CMD _IOR(IPMI_IOC_MAGIC, 30, int) +#define IPMICTL_SET_MAINTENANCE_MODE_CMD _IOW(IPMI_IOC_MAGIC, 31, int) + #endif /* __LINUX_IPMI_H */ diff --git a/include/linux/ipmi_msgdefs.h b/include/linux/ipmi_msgdefs.h index 4d04d8b58a0a..8d6759cc1a71 100644 --- a/include/linux/ipmi_msgdefs.h +++ b/include/linux/ipmi_msgdefs.h @@ -46,6 +46,8 @@ #define IPMI_NETFN_APP_REQUEST 0x06 #define IPMI_NETFN_APP_RESPONSE 0x07 #define IPMI_GET_DEVICE_ID_CMD 0x01 +#define IPMI_COLD_RESET_CMD 0x02 +#define IPMI_WARM_RESET_CMD 0x03 #define IPMI_CLEAR_MSG_FLAGS_CMD 0x30 #define IPMI_GET_DEVICE_GUID_CMD 0x08 #define IPMI_GET_MSG_FLAGS_CMD 0x31 @@ -60,6 +62,9 @@ #define IPMI_NETFN_STORAGE_RESPONSE 0x0b #define IPMI_ADD_SEL_ENTRY_CMD 0x44 +#define IPMI_NETFN_FIRMWARE_REQUEST 0x08 +#define IPMI_NETFN_FIRMWARE_RESPONSE 0x09 + /* The default slave address */ #define IPMI_BMC_SLAVE_ADDR 0x20 diff --git a/include/linux/ipmi_smi.h b/include/linux/ipmi_smi.h index 2cc960da4176..c0633108d05d 100644 --- a/include/linux/ipmi_smi.h +++ b/include/linux/ipmi_smi.h @@ -115,6 +115,13 @@ struct ipmi_smi_handlers poll for operations during things like crash dumps. */ void (*poll)(void *send_info); + /* Enable/disable firmware maintenance mode. Note that this + is *not* the modes defined, this is simply an on/off + setting. The message handler does the mode handling. Note + that this is called from interupt context, so it cannot + block. */ + void (*set_maintenance_mode)(void *send_info, int enable); + /* Tell the handler that we are using it/not using it. The message handler get the modules that this handler belongs to; this function lets the SMI claim any modules that it -- cgit v1.2.3 From 4d7cbac7c870ca66d8fb27d68188efbb5de2dffa Mon Sep 17 00:00:00 2001 From: Corey Minyard Date: Wed, 6 Dec 2006 20:41:14 -0800 Subject: [PATCH] IPMI: Fix BT long busy The IPMI BT subdriver has been patched to survive "long busy" timeouts seen during firmware upgrades and resets. The patch never returns the HOSED state, synthesizes response messages with meaningful completion codes, and recovers gracefully when the hardware finishes the long busy. The subdriver now issues a "Get BT Capabilities" command and properly uses those results. More informative completion codes are returned on error from transaction starts; this logic was propogated to the KCS and SMIC subdrivers. Finally, indent and other style quirks were normalized. Signed-off-by: Rocky Craig Signed-off-by: Corey Minyard Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ipmi_msgdefs.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ipmi_msgdefs.h b/include/linux/ipmi_msgdefs.h index 8d6759cc1a71..b56a158d587a 100644 --- a/include/linux/ipmi_msgdefs.h +++ b/include/linux/ipmi_msgdefs.h @@ -71,14 +71,18 @@ /* The BT interface on high-end HP systems supports up to 255 bytes in * one transfer. Its "virtual" BMC supports some commands that are longer * than 128 bytes. Use the full 256, plus NetFn/LUN, Cmd, cCode, plus - * some overhead. It would be nice to base this on the "BT Capabilities" - * but that's too hard to propagate to the rest of the driver. */ + * some overhead; it's not worth the effort to dynamically size this based + * on the results of the "Get BT Capabilities" command. */ #define IPMI_MAX_MSG_LENGTH 272 /* multiple of 16 */ #define IPMI_CC_NO_ERROR 0x00 #define IPMI_NODE_BUSY_ERR 0xc0 #define IPMI_INVALID_COMMAND_ERR 0xc1 +#define IPMI_TIMEOUT_ERR 0xc3 #define IPMI_ERR_MSG_TRUNCATED 0xc6 +#define IPMI_REQ_LEN_INVALID_ERR 0xc7 +#define IPMI_REQ_LEN_EXCEEDED_ERR 0xc8 +#define IPMI_NOT_IN_MY_STATE_ERR 0xd5 /* IPMI 2.0 */ #define IPMI_LOST_ARBITRATION_ERR 0x81 #define IPMI_BUS_ERR 0x82 #define IPMI_NAK_ON_WRITE_ERR 0x83 -- cgit v1.2.3 From 6cf24f031bc97cb5a7c9df3b6e73c45b628b2b28 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Wed, 6 Dec 2006 20:41:39 -0800 Subject: [PATCH] elf.h: forward declare struct file In file included from include/asm/patch.h:14, from arch/ia64/kernel/patch.c:10: include/linux/elf.h:375: warning: "struct file" declared inside parameter list include/linux/elf.h:375: warning: its scope is only this definition or declaration, which is probably not what you want Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/elf.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/elf.h b/include/linux/elf.h index b403516d5c3d..60713e6ea297 100644 --- a/include/linux/elf.h +++ b/include/linux/elf.h @@ -6,6 +6,8 @@ #include #include +struct file; + #ifndef elf_read_implies_exec /* Executables for which elf_read_implies_exec() returns TRUE will have the READ_IMPLIES_EXEC personality flag set automatically. -- cgit v1.2.3 From 68380b581383c028830f79ec2670f4a193854aa6 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 7 Dec 2006 09:28:19 -0800 Subject: Add "run_scheduled_work()" workqueue function This allows workqueue users to run just their own pending work, rather than wait for the whole workqueue to finish running. This solves the deadlock with networking libphy that was due to other workqueue entries possibly needing a lock that was held by the routine that wanted to flush its own work. It's not wonderful: if you absolutely need to synchronize with the work function having been executed, any user strictly speaking should have its own completion tracking logic, since when we run things explicitly by hand, the generic workqueue layer can no longer help us synchronize. Also, this is strictly only usable for work that has been scheduled without any delayed timers. You can not mix the new interface with schedule_delayed_work(). But it's better than what we had currently. Acked-by: Maciej W. Rozycki Signed-off-by: Linus Torvalds --- include/linux/workqueue.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index f0cb1df7b475..edef8d50b26b 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -162,6 +162,7 @@ extern int queue_delayed_work_on(int cpu, struct workqueue_struct *wq, extern void FASTCALL(flush_workqueue(struct workqueue_struct *wq)); extern int FASTCALL(schedule_work(struct work_struct *work)); +extern int FASTCALL(run_scheduled_work(struct work_struct *work)); extern int FASTCALL(schedule_delayed_work(struct delayed_work *work, unsigned long delay)); extern int schedule_delayed_work_on(int cpu, struct delayed_work *work, unsigned long delay); -- cgit v1.2.3 From a79561134f38de12dce14ed72138f38e55ef53fc Mon Sep 17 00:00:00 2001 From: Zou Nan hai Date: Thu, 7 Dec 2006 09:51:35 -0800 Subject: [IA64] IA64 Kexec/kdump Changes and updates. 1. Remove fake rendz path and related code according to discuss with Khalid Aziz. 2. fc.i offset fix in relocate_kernel.S. 3. iospic shutdown code eoi and mask race fix from Fujitsu. 4. Warm boot hook in machine_kexec to SN SAL code from Jack Steiner. 5. Send slave to SAL slave loop patch from Jay Lan. 6. Kdump on non-recoverable MCA event patch from Jay Lan 7. Use CTL_UNNUMBERED in kdump_on_init sysctl. Signed-off-by: Zou Nan hai Signed-off-by: Tony Luck --- include/linux/kexec.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index a4ede62b339d..e14cd388c65b 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -108,6 +108,10 @@ int kexec_should_crash(struct task_struct *); extern struct kimage *kexec_image; extern struct kimage *kexec_crash_image; +#ifndef kexec_flush_icache_page +#define kexec_flush_icache_page(page) +#endif + #define KEXEC_ON_CRASH 0x00000001 #define KEXEC_ARCH_MASK 0xffff0000 @@ -133,6 +137,7 @@ extern struct resource crashk_res; typedef u32 note_buf_t[MAX_NOTE_BYTES/4]; extern note_buf_t *crash_notes; + #else /* !CONFIG_KEXEC */ struct pt_regs; struct task_struct; -- cgit v1.2.3 From 24ec839c431eb79bb8f6abc00c4e1eb3b8c4d517 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 8 Dec 2006 02:36:04 -0800 Subject: [PATCH] tty: ->signal->tty locking Fix the locking of signal->tty. Use ->sighand->siglock to protect ->signal->tty; this lock is already used by most other members of ->signal/->sighand. And unless we are 'current' or the tasklist_lock is held we need ->siglock to access ->signal anyway. (NOTE: sys_unshare() is broken wrt ->sighand locking rules) Note that tty_mutex is held over tty destruction, so while holding tty_mutex any tty pointer remains valid. Otherwise the lifetime of ttys are governed by their open file handles. This leaves some holes for tty access from signal->tty (or any other non file related tty access). It solves the tty SLAB scribbles we were seeing. (NOTE: the change from group_send_sig_info to __group_send_sig_info needs to be examined by someone familiar with the security framework, I think it is safe given the SEND_SIG_PRIV from other __group_send_sig_info invocations) [schwidefsky@de.ibm.com: 3270 fix] [akpm@osdl.org: various post-viro fixes] Signed-off-by: Peter Zijlstra Acked-by: Alan Cox Cc: Oleg Nesterov Cc: Prarit Bhargava Cc: Chris Wright Cc: Roland McGrath Cc: Stephen Smalley Cc: James Morris Cc: "David S. Miller" Cc: Jeff Dike Cc: Martin Schwidefsky Cc: Jan Kara Signed-off-by: Martin Schwidefsky Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/tty.h | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index f717f0898238..1d29999a3439 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -309,6 +309,12 @@ extern void tty_ldisc_flush(struct tty_struct *tty); extern int tty_ioctl(struct inode *inode, struct file *file, unsigned int cmd, unsigned long arg); +extern dev_t tty_devnum(struct tty_struct *tty); +extern void proc_clear_tty(struct task_struct *p); +extern void __proc_set_tty(struct task_struct *tsk, struct tty_struct *tty); +extern void proc_set_tty(struct task_struct *tsk, struct tty_struct *tty); +extern struct tty_struct *get_current_tty(void); + extern struct mutex tty_mutex; /* n_tty.c */ @@ -335,10 +341,5 @@ extern void console_print(const char *); extern int vt_ioctl(struct tty_struct *tty, struct file * file, unsigned int cmd, unsigned long arg); -static inline dev_t tty_devnum(struct tty_struct *tty) -{ - return MKDEV(tty->driver->major, tty->driver->minor_start) + tty->index; -} - #endif /* __KERNEL__ */ #endif -- cgit v1.2.3 From ae424ae4b5bcd820ad6ee6f0b986c4e14ed4d6cf Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 8 Dec 2006 02:36:08 -0800 Subject: [PATCH] make set_special_pids() static Make set_special_pids() static, the only caller is daemonize(). Signed-off-by: Oleg Nesterov 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 dede82c63445..5e8a0ba61749 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1240,7 +1240,6 @@ extern struct mm_struct init_mm; #define find_task_by_pid(nr) find_task_by_pid_type(PIDTYPE_PID, nr) extern struct task_struct *find_task_by_pid_type(int type, int pid); -extern void set_special_pids(pid_t session, pid_t pgrp); extern void __set_special_pids(pid_t session, pid_t pgrp); /* per-UID process charging. */ -- cgit v1.2.3 From 0a0fc9601dd1024ec7171993bf075a789246e1ed Mon Sep 17 00:00:00 2001 From: Thomas Maier Date: Fri, 8 Dec 2006 02:36:11 -0800 Subject: [PATCH] pktcdvd: bio write congestion using congestion_wait() This adds a bio write queue congestion control to the pktcdvd driver with fixed on/off marks. It prevents that the driver consumes a unlimited amount of write requests. [akpm@osdl.org: sync with congestion_wait() renaming] Signed-off-by: Thomas Maier Cc: Peter Osterlund Cc: Jens Axboe Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pktcdvd.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pktcdvd.h b/include/linux/pktcdvd.h index 8a94c717c266..9b1a185fb1e5 100644 --- a/include/linux/pktcdvd.h +++ b/include/linux/pktcdvd.h @@ -112,6 +112,12 @@ struct pkt_ctrl_command { #include #include + +/* default bio write queue congestion marks */ +#define PKT_WRITE_CONGESTION_ON 10000 +#define PKT_WRITE_CONGESTION_OFF 9000 + + struct packet_settings { __u32 size; /* packet size in (512 byte) sectors */ @@ -271,6 +277,9 @@ struct pktcdvd_device struct packet_iosched iosched; struct gendisk *disk; + + int write_congestion_off; + int write_congestion_on; }; #endif /* __KERNEL__ */ -- cgit v1.2.3 From 32694850a91bd4fedcdd4a46292f870588be81d1 Mon Sep 17 00:00:00 2001 From: Thomas Maier Date: Fri, 8 Dec 2006 02:36:12 -0800 Subject: [PATCH] pktcdvd: add sysfs and debugfs interface Add a sysfs and debugfs interface to the pktcdvd driver. Look into the Documentation/ABI/testing/* files in the patch for more info. Signed-off-by: Thomas Maier Signed-off-by: Peter Osterlund Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pktcdvd.h | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pktcdvd.h b/include/linux/pktcdvd.h index 9b1a185fb1e5..5ea4f05683f6 100644 --- a/include/linux/pktcdvd.h +++ b/include/linux/pktcdvd.h @@ -111,7 +111,8 @@ struct pkt_ctrl_command { #include #include #include - +#include +#include /* default bio write queue congestion marks */ #define PKT_WRITE_CONGESTION_ON 10000 @@ -247,6 +248,14 @@ struct packet_stacked_data }; #define PSD_POOL_SIZE 64 +struct pktcdvd_kobj +{ + struct kobject kobj; + struct pktcdvd_device *pd; +}; +#define to_pktcdvdkobj(_k) \ + ((struct pktcdvd_kobj*)container_of(_k,struct pktcdvd_kobj,kobj)) + struct pktcdvd_device { struct block_device *bdev; /* dev attached */ @@ -280,6 +289,13 @@ struct pktcdvd_device int write_congestion_off; int write_congestion_on; + + struct class_device *clsdev; /* sysfs pktcdvd[0-7] class dev */ + struct pktcdvd_kobj *kobj_stat; /* sysfs pktcdvd[0-7]/stat/ */ + struct pktcdvd_kobj *kobj_wqueue; /* sysfs pktcdvd[0-7]/write_queue/ */ + + struct dentry *dfs_d_root; /* debugfs: devname directory */ + struct dentry *dfs_f_info; /* debugfs: info file */ }; #endif /* __KERNEL__ */ -- cgit v1.2.3 From 2e7b651df113c8a463853e4169951c52c39f9d19 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 8 Dec 2006 02:36:13 -0800 Subject: [PATCH] remove the old bd_mutex lockdep annotation Remove the old complex and crufty bd_mutex annotation. Signed-off-by: Peter Zijlstra Cc: Neil Brown Cc: Ingo Molnar Cc: Arjan van de Ven Cc: Jason Baron Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 17 ----------------- 1 file changed, 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 70b99fbb560b..45f2cabb8c75 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -481,21 +481,6 @@ struct block_device { unsigned long bd_private; }; -/* - * bdev->bd_mutex nesting subclasses for the lock validator: - * - * 0: normal - * 1: 'whole' - * 2: 'partition' - */ -enum bdev_bd_mutex_lock_class -{ - BD_MUTEX_NORMAL, - BD_MUTEX_WHOLE, - BD_MUTEX_PARTITION -}; - - /* * Radix-tree tags, for tagging dirty and writeback pages within the pagecache * radix trees @@ -1499,7 +1484,6 @@ extern void bd_set_size(struct block_device *, loff_t size); extern void bd_forget(struct inode *inode); extern void bdput(struct block_device *); extern struct block_device *open_by_devnum(dev_t, unsigned); -extern struct block_device *open_partition_by_devnum(dev_t, unsigned); extern const struct address_space_operations def_blk_aops; #else static inline void bd_forget(struct inode *inode) {} @@ -1517,7 +1501,6 @@ extern int blkdev_driver_ioctl(struct inode *inode, struct file *file, extern long compat_blkdev_ioctl(struct file *, unsigned, unsigned long); extern int blkdev_get(struct block_device *, mode_t, unsigned); extern int blkdev_put(struct block_device *); -extern int blkdev_put_partition(struct block_device *); extern int bd_claim(struct block_device *, void *); extern void bd_release(struct block_device *); #ifdef CONFIG_SYSFS -- cgit v1.2.3 From d63a5a74dee87883fda6b7d170244acaac5b05e8 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Fri, 8 Dec 2006 02:36:17 -0800 Subject: [PATCH] lockdep: avoid lockdep warning in md md_open takes ->reconfig_mutex which causes lockdep to complain. This (normally) doesn't have deadlock potential as the possible conflict is with a reconfig_mutex in a different device. I say "normally" because if a loop were created in the array->member hierarchy a deadlock could happen. However that causes bigger problems than a deadlock and should be fixed independently. So we flag the lock in md_open as a nested lock. This requires defining mutex_lock_interruptible_nested. Cc: Ingo Molnar Acked-by: Peter Zijlstra Acked-by: Ingo Molnar Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mutex.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mutex.h b/include/linux/mutex.h index b2b91c477563..a7544afd7582 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -125,8 +125,10 @@ extern int fastcall mutex_lock_interruptible(struct mutex *lock); #ifdef CONFIG_DEBUG_LOCK_ALLOC extern void mutex_lock_nested(struct mutex *lock, unsigned int subclass); +extern int mutex_lock_interruptible_nested(struct mutex *lock, unsigned int subclass); #else # define mutex_lock_nested(lock, subclass) mutex_lock(lock) +# define mutex_lock_interruptible_nested(lock, subclass) mutex_lock_interruptible(lock) #endif /* -- cgit v1.2.3 From 7664c5a1da4711bb6383117f51b94c8dc8f3f1cd Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Fri, 8 Dec 2006 02:36:19 -0800 Subject: [PATCH] Generic BUG implementation This patch adds common handling for kernel BUGs, for use by architectures as they wish. The code is derived from arch/powerpc. The advantages of having common BUG handling are: - consistent BUG reporting across architectures - shared implementation of out-of-line file/line data - implement CONFIG_DEBUG_BUGVERBOSE consistently This means that in inline impact of BUG is just the illegal instruction itself, which is an improvement for i386 and x86-64. A BUG is represented in the instruction stream as an illegal instruction, which has file/line information associated with it. This extra information is stored in the __bug_table section in the ELF file. When the kernel gets an illegal instruction, it first confirms it might possibly be from a BUG (ie, in kernel mode, the right illegal instruction). It then calls report_bug(). This searches __bug_table for a matching instruction pointer, and if found, prints the corresponding file/line information. If report_bug() determines that it wasn't a BUG which caused the trap, it returns BUG_TRAP_TYPE_NONE. Some architectures (powerpc) implement WARN using the same mechanism; if the illegal instruction was the result of a WARN, then report_bug(Q) returns CONFIG_DEBUG_BUGVERBOSE; otherwise it returns BUG_TRAP_TYPE_BUG. lib/bug.c keeps a list of loaded modules which can be searched for __bug_table entries. The architecture must call module_bug_finalize()/module_bug_cleanup() from its corresponding module_finalize/cleanup functions. Unsetting CONFIG_DEBUG_BUGVERBOSE will reduce the kernel size by some amount. At the very least, filename and line information will not be recorded for each but, but architectures may decide to store no extra information per BUG at all. Unfortunately, gcc doesn't have a general way to mark an asm() as noreturn, so architectures will generally have to include an infinite loop (or similar) in the BUG code, so that gcc knows execution won't continue beyond that point. gcc does have a __builtin_trap() operator which may be useful to achieve the same effect, unfortunately it cannot be used to actually implement the BUG itself, because there's no way to get the instruction's address for use in generating the __bug_table entry. [randy.dunlap@oracle.com: Handle BUG=n, GENERIC_BUG=n to prevent build errors] [bunk@stusta.de: include/linux/bug.h must always #include Cc: Andi Kleen Cc: Hugh Dickens Cc: Michael Ellerman Cc: Paul Mackerras Cc: Benjamin Herrenschmidt Cc: Rusty Russell Signed-off-by: Adrian Bunk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bug.h | 47 +++++++++++++++++++++++++++++++++++++++++++++++ include/linux/module.h | 7 +++++++ 2 files changed, 54 insertions(+) create mode 100644 include/linux/bug.h (limited to 'include/linux') diff --git a/include/linux/bug.h b/include/linux/bug.h new file mode 100644 index 000000000000..42aa0a54b6f4 --- /dev/null +++ b/include/linux/bug.h @@ -0,0 +1,47 @@ +#ifndef _LINUX_BUG_H +#define _LINUX_BUG_H + +#include +#include + +enum bug_trap_type { + BUG_TRAP_TYPE_NONE = 0, + BUG_TRAP_TYPE_WARN = 1, + BUG_TRAP_TYPE_BUG = 2, +}; + +#ifdef CONFIG_GENERIC_BUG +#include + +static inline int is_warning_bug(const struct bug_entry *bug) +{ + return bug->flags & BUGFLAG_WARNING; +} + +const struct bug_entry *find_bug(unsigned long bugaddr); + +enum bug_trap_type report_bug(unsigned long bug_addr); + +int module_bug_finalize(const Elf_Ehdr *, const Elf_Shdr *, + struct module *); +void module_bug_cleanup(struct module *); + +/* These are defined by the architecture */ +int is_valid_bugaddr(unsigned long addr); + +#else /* !CONFIG_GENERIC_BUG */ + +static inline enum bug_trap_type report_bug(unsigned long bug_addr) +{ + return BUG_TRAP_TYPE_BUG; +} +static inline int module_bug_finalize(const Elf_Ehdr *hdr, + const Elf_Shdr *sechdrs, + struct module *mod) +{ + return 0; +} +static inline void module_bug_cleanup(struct module *mod) {} + +#endif /* CONFIG_GENERIC_BUG */ +#endif /* _LINUX_BUG_H */ diff --git a/include/linux/module.h b/include/linux/module.h index d33df2408e05..10f771a49997 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -319,6 +319,13 @@ struct module unsigned int taints; /* same bits as kernel:tainted */ +#ifdef CONFIG_GENERIC_BUG + /* Support for BUG */ + struct list_head bug_list; + struct bug_entry *bug_table; + unsigned num_bugs; +#endif + #ifdef CONFIG_MODULE_UNLOAD /* Reference counts */ struct module_ref ref[NR_CPUS]; -- cgit v1.2.3 From a5cfc1ec58a07074dacb6aa8c79eff864c966d12 Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Fri, 8 Dec 2006 02:36:25 -0800 Subject: [PATCH] bit reverse library This patch provides two bit reverse functions and bit reverse table. - reverse the order of bits in a u32 value u8 bitrev8(u8 x); - reverse the order of bits in a u32 value u32 bitrev32(u32 x); - byte reverse table const u8 byte_rev_table[256]; Signed-off-by: Akinobu Mita Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bitrev.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) create mode 100644 include/linux/bitrev.h (limited to 'include/linux') diff --git a/include/linux/bitrev.h b/include/linux/bitrev.h new file mode 100644 index 000000000000..05e540d6963a --- /dev/null +++ b/include/linux/bitrev.h @@ -0,0 +1,15 @@ +#ifndef _LINUX_BITREV_H +#define _LINUX_BITREV_H + +#include + +extern u8 const byte_rev_table[256]; + +static inline u8 bitrev8(u8 byte) +{ + return byte_rev_table[byte]; +} + +extern u32 bitrev32(u32 in); + +#endif /* _LINUX_BITREV_H */ -- cgit v1.2.3 From 906d66df18faa4aac8d898ae6920d1014694a932 Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Fri, 8 Dec 2006 02:36:25 -0800 Subject: [PATCH] crc32: replace bitreverse by bitrev32 This patch replaces bitreverse() by bitrev32. The only users of bitreverse() are crc32 itself and via-velocity. Cc: Jeff Garzik Cc: Matt Domsch Signed-off-by: Akinobu Mita Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/crc32.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/crc32.h b/include/linux/crc32.h index 56c0645789a9..e20dd1f9b40a 100644 --- a/include/linux/crc32.h +++ b/include/linux/crc32.h @@ -6,10 +6,10 @@ #define _LINUX_CRC32_H #include +#include extern u32 crc32_le(u32 crc, unsigned char const *p, size_t len); extern u32 crc32_be(u32 crc, unsigned char const *p, size_t len); -extern u32 bitreverse(u32 in); #define crc32(seed, data, length) crc32_le(seed, (unsigned char const *)data, length) @@ -21,7 +21,7 @@ extern u32 bitreverse(u32 in); * is in bit nr 0], thus it must be reversed before use. Except for * nics that bit swap the result internally... */ -#define ether_crc(length, data) bitreverse(crc32_le(~0, data, length)) +#define ether_crc(length, data) bitrev32(crc32_le(~0, data, length)) #define ether_crc_le(length, data) crc32_le(~0, data, length) #endif /* _LINUX_CRC32_H */ -- cgit v1.2.3 From 42cf11939becc717bd125d121a1a23415106a099 Mon Sep 17 00:00:00 2001 From: "Josef \"Jeff\" Sipek" Date: Fri, 8 Dec 2006 02:36:31 -0800 Subject: [PATCH] fsstack: Introduce fsstack_copy_{attr,inode}_* Introduce several fsstack_copy_* functions which allow stackable filesystems (such as eCryptfs and Unionfs) to easily copy over (currently only) inode attributes. This prevents code duplication and allows for code reuse. [akpm@osdl.org: Remove unneeded wrapper] [bunk@stusta.de: fs/stack.c should #include ] Signed-off-by: Josef "Jeff" Sipek Cc: Michael Halcrow Signed-off-by: Adrian Bunk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs_stack.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) create mode 100644 include/linux/fs_stack.h (limited to 'include/linux') diff --git a/include/linux/fs_stack.h b/include/linux/fs_stack.h new file mode 100644 index 000000000000..bb516ceeefc9 --- /dev/null +++ b/include/linux/fs_stack.h @@ -0,0 +1,31 @@ +#ifndef _LINUX_FS_STACK_H +#define _LINUX_FS_STACK_H + +/* This file defines generic functions used primarily by stackable + * filesystems; none of these functions require i_mutex to be held. + */ + +#include + +/* externs for fs/stack.c */ +extern void fsstack_copy_attr_all(struct inode *dest, const struct inode *src, + int (*get_nlinks)(struct inode *)); + +extern void fsstack_copy_inode_size(struct inode *dst, const struct inode *src); + +/* inlines */ +static inline void fsstack_copy_attr_atime(struct inode *dest, + const struct inode *src) +{ + dest->i_atime = src->i_atime; +} + +static inline void fsstack_copy_attr_times(struct inode *dest, + const struct inode *src) +{ + dest->i_atime = src->i_atime; + dest->i_mtime = src->i_mtime; + dest->i_ctime = src->i_ctime; +} + +#endif /* _LINUX_FS_STACK_H */ -- cgit v1.2.3 From fec6d055da71fb02a76f9c2c12427fa79974018b Mon Sep 17 00:00:00 2001 From: "Josef \"Jeff\" Sipek" Date: Fri, 8 Dec 2006 02:36:32 -0800 Subject: [PATCH] struct path: rename Reiserfs's struct path Rename Reiserfs's struct path to struct treepath to prevent name collision between it and struct path from fs/namei.c. Signed-off-by: Josef "Jeff" Sipek Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/reiserfs_fs.h | 44 ++++++++++++++++++++++---------------------- 1 file changed, 22 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h index d0e4dce33ad5..c3fc6caaad3f 100644 --- a/include/linux/reiserfs_fs.h +++ b/include/linux/reiserfs_fs.h @@ -1159,7 +1159,7 @@ znodes are the way! */ #define PATH_READA 0x1 /* do read ahead */ #define PATH_READA_BACK 0x2 /* read backwards */ -struct path { +struct treepath { int path_length; /* Length of the array above. */ int reada; struct path_element path_elements[EXTENDED_MAX_HEIGHT]; /* Array of the path elements. */ @@ -1169,7 +1169,7 @@ struct path { #define pos_in_item(path) ((path)->pos_in_item) #define INITIALIZE_PATH(var) \ -struct path var = {.path_length = ILLEGAL_PATH_ELEMENT_OFFSET, .reada = 0,} +struct treepath var = {.path_length = ILLEGAL_PATH_ELEMENT_OFFSET, .reada = 0,} /* Get path element by path and path position. */ #define PATH_OFFSET_PELEMENT(p_s_path,n_offset) ((p_s_path)->path_elements +(n_offset)) @@ -1327,7 +1327,7 @@ struct tree_balance { int need_balance_dirty; struct super_block *tb_sb; struct reiserfs_transaction_handle *transaction_handle; - struct path *tb_path; + struct treepath *tb_path; struct buffer_head *L[MAX_HEIGHT]; /* array of left neighbors of nodes in the path */ struct buffer_head *R[MAX_HEIGHT]; /* array of right neighbors of nodes in the path */ struct buffer_head *FL[MAX_HEIGHT]; /* array of fathers of the left neighbors */ @@ -1793,41 +1793,41 @@ static inline void copy_key(struct reiserfs_key *to, memcpy(to, from, KEY_SIZE); } -int comp_items(const struct item_head *stored_ih, const struct path *p_s_path); -const struct reiserfs_key *get_rkey(const struct path *p_s_chk_path, +int comp_items(const struct item_head *stored_ih, const struct treepath *p_s_path); +const struct reiserfs_key *get_rkey(const struct treepath *p_s_chk_path, const struct super_block *p_s_sb); int search_by_key(struct super_block *, const struct cpu_key *, - struct path *, int); + struct treepath *, int); #define search_item(s,key,path) search_by_key (s, key, path, DISK_LEAF_NODE_LEVEL) int search_for_position_by_key(struct super_block *p_s_sb, const struct cpu_key *p_s_cpu_key, - struct path *p_s_search_path); + struct treepath *p_s_search_path); extern void decrement_bcount(struct buffer_head *p_s_bh); -void decrement_counters_in_path(struct path *p_s_search_path); -void pathrelse(struct path *p_s_search_path); -int reiserfs_check_path(struct path *p); -void pathrelse_and_restore(struct super_block *s, struct path *p_s_search_path); +void decrement_counters_in_path(struct treepath *p_s_search_path); +void pathrelse(struct treepath *p_s_search_path); +int reiserfs_check_path(struct treepath *p); +void pathrelse_and_restore(struct super_block *s, struct treepath *p_s_search_path); int reiserfs_insert_item(struct reiserfs_transaction_handle *th, - struct path *path, + struct treepath *path, const struct cpu_key *key, struct item_head *ih, struct inode *inode, const char *body); int reiserfs_paste_into_item(struct reiserfs_transaction_handle *th, - struct path *path, + struct treepath *path, const struct cpu_key *key, struct inode *inode, const char *body, int paste_size); int reiserfs_cut_from_item(struct reiserfs_transaction_handle *th, - struct path *path, + struct treepath *path, struct cpu_key *key, struct inode *inode, struct page *page, loff_t new_file_size); int reiserfs_delete_item(struct reiserfs_transaction_handle *th, - struct path *path, + struct treepath *path, const struct cpu_key *key, struct inode *inode, struct buffer_head *p_s_un_bh); @@ -1858,7 +1858,7 @@ void padd_item(char *item, int total_length, int length); #define GET_BLOCK_NO_DANGLE 16 /* don't leave any transactions running */ int restart_transaction(struct reiserfs_transaction_handle *th, - struct inode *inode, struct path *path); + struct inode *inode, struct treepath *path); void reiserfs_read_locked_inode(struct inode *inode, struct reiserfs_iget_args *args); int reiserfs_find_actor(struct inode *inode, void *p); @@ -1905,7 +1905,7 @@ int reiserfs_setattr(struct dentry *dentry, struct iattr *attr); /* namei.c */ void set_de_name_and_namelen(struct reiserfs_dir_entry *de); int search_by_entry_key(struct super_block *sb, const struct cpu_key *key, - struct path *path, struct reiserfs_dir_entry *de); + struct treepath *path, struct reiserfs_dir_entry *de); struct dentry *reiserfs_get_parent(struct dentry *); /* procfs.c */ @@ -1956,9 +1956,9 @@ extern const struct file_operations reiserfs_dir_operations; /* tail_conversion.c */ int direct2indirect(struct reiserfs_transaction_handle *, struct inode *, - struct path *, struct buffer_head *, loff_t); + struct treepath *, struct buffer_head *, loff_t); int indirect2direct(struct reiserfs_transaction_handle *, struct inode *, - struct page *, struct path *, const struct cpu_key *, + struct page *, struct treepath *, const struct cpu_key *, loff_t, char *); void reiserfs_unmap_buffer(struct buffer_head *); @@ -2045,7 +2045,7 @@ struct __reiserfs_blocknr_hint { struct inode *inode; /* inode passed to allocator, if we allocate unf. nodes */ long block; /* file offset, in blocks */ struct in_core_key key; - struct path *path; /* search path, used by allocator to deternine search_start by + struct treepath *path; /* search path, used by allocator to deternine search_start by * various ways */ struct reiserfs_transaction_handle *th; /* transaction handle is needed to log super blocks and * bitmap blocks changes */ @@ -2101,7 +2101,7 @@ static inline int reiserfs_new_form_blocknrs(struct tree_balance *tb, static inline int reiserfs_new_unf_blocknrs(struct reiserfs_transaction_handle *th, struct inode *inode, b_blocknr_t * new_blocknrs, - struct path *path, long block) + struct treepath *path, long block) { reiserfs_blocknr_hint_t hint = { .th = th, @@ -2118,7 +2118,7 @@ static inline int reiserfs_new_unf_blocknrs(struct reiserfs_transaction_handle static inline int reiserfs_new_unf_blocknrs2(struct reiserfs_transaction_handle *th, struct inode *inode, b_blocknr_t * new_blocknrs, - struct path *path, long block) + struct treepath *path, long block) { reiserfs_blocknr_hint_t hint = { .th = th, -- cgit v1.2.3 From 346f20ff6020ffa11d40b789069079c56a444ae6 Mon Sep 17 00:00:00 2001 From: "Josef \"Jeff\" Sipek" Date: Fri, 8 Dec 2006 02:36:34 -0800 Subject: [PATCH] struct path: move struct path from fs/namei.c into include/linux Moved struct path from fs/namei.c to include/linux/namei.h. This allows many places in the VFS, as well as any stackable filesystem to easily keep track of dentry-vfsmount pairs. Signed-off-by: Josef "Jeff" Sipek Cc: Al Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/namei.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/namei.h b/include/linux/namei.h index f5f19606effb..d39a5a67e979 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -29,6 +29,11 @@ struct nameidata { } intent; }; +struct path { + struct vfsmount *mnt; + struct dentry *dentry; +}; + /* * Type of the last component on LOOKUP_PARENT */ -- cgit v1.2.3 From 0f7fc9e4d03987fe29f6dd4aa67e4c56eb7ecb05 Mon Sep 17 00:00:00 2001 From: "Josef \"Jeff\" Sipek" Date: Fri, 8 Dec 2006 02:36:35 -0800 Subject: [PATCH] VFS: change struct file to use struct path This patch changes struct file to use struct path instead of having independent pointers to struct dentry and struct vfsmount, and converts all users of f_{dentry,vfsmnt} in fs/ to use f_path.{dentry,mnt}. Additionally, it adds two #define's to make the transition easier for users of the f_dentry and f_vfsmnt. Signed-off-by: Josef "Jeff" Sipek Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 10 ++++++---- include/linux/fsnotify.h | 2 +- 2 files changed, 7 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 45f2cabb8c75..adce6e1d70c2 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -269,6 +269,7 @@ extern int dir_notify_enable; #include #include #include +#include #include #include #include @@ -711,8 +712,9 @@ struct file { struct list_head fu_list; struct rcu_head fu_rcuhead; } f_u; - struct dentry *f_dentry; - struct vfsmount *f_vfsmnt; + struct path f_path; +#define f_dentry f_path.dentry +#define f_vfsmnt f_path.mnt const struct file_operations *f_op; atomic_t f_count; unsigned int f_flags; @@ -1224,7 +1226,7 @@ extern void touch_atime(struct vfsmount *mnt, struct dentry *dentry); static inline void file_accessed(struct file *file) { if (!(file->f_flags & O_NOATIME)) - touch_atime(file->f_vfsmnt, file->f_dentry); + touch_atime(file->f_path.mnt, file->f_path.dentry); } int sync_inode(struct inode *inode, struct writeback_control *wbc); @@ -1615,7 +1617,7 @@ static inline void put_write_access(struct inode * inode) static inline void allow_write_access(struct file *file) { if (file) - atomic_inc(&file->f_dentry->d_inode->i_writecount); + atomic_inc(&file->f_path.dentry->d_inode->i_writecount); } extern int do_pipe(int *); extern struct file *create_read_pipe(struct file *f); diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index d4f219ffaa5d..dfc4e4f68da4 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -164,7 +164,7 @@ static inline void fsnotify_open(struct dentry *dentry) */ static inline void fsnotify_close(struct file *file) { - struct dentry *dentry = file->f_dentry; + struct dentry *dentry = file->f_path.dentry; struct inode *inode = dentry->d_inode; const char *name = dentry->d_name.name; mode_t mode = file->f_mode; -- cgit v1.2.3 From 225a719f79fbc4d0cd9d9ebc5b2e3ac0e95845aa Mon Sep 17 00:00:00 2001 From: Josef Sipek Date: Fri, 8 Dec 2006 02:37:18 -0800 Subject: [PATCH] struct path: convert lockd Signed-off-by: Josef Sipek Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/lockd/lockd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index 8c39654549d8..0c962b82a9de 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -206,7 +206,7 @@ void nlmsvc_invalidate_all(void); static __inline__ struct inode * nlmsvc_file_inode(struct nlm_file *file) { - return file->f_file->f_dentry->d_inode; + return file->f_file->f_path.dentry->d_inode; } /* -- cgit v1.2.3 From f0d1b0b30d250a07627ad8b9fbbb5c7cc08422e8 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 8 Dec 2006 02:37:49 -0800 Subject: [PATCH] LOG2: Implement a general integer log2 facility in the kernel This facility provides three entry points: ilog2() Log base 2 of unsigned long ilog2_u32() Log base 2 of u32 ilog2_u64() Log base 2 of u64 These facilities can either be used inside functions on dynamic data: int do_something(long q) { ...; y = ilog2(x) ...; } Or can be used to statically initialise global variables with constant values: unsigned n = ilog2(27); When performing static initialisation, the compiler will report "error: initializer element is not constant" if asked to take a log of zero or of something not reducible to a constant. They treat negative numbers as unsigned. When not dealing with a constant, they fall back to using fls() which permits them to use arch-specific log calculation instructions - such as BSR on x86/x86_64 or SCAN on FRV - if available. [akpm@osdl.org: MMC fix] Signed-off-by: David Howells Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Herbert Xu Cc: David Howells Cc: Wojtek Kaniewski Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 9 +--- include/linux/log2.h | 131 +++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 132 insertions(+), 8 deletions(-) create mode 100644 include/linux/log2.h (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 6738283ac385..3710cce16642 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -13,6 +13,7 @@ #include #include #include +#include #include #include @@ -157,14 +158,6 @@ static inline int printk(const char *s, ...) { return 0; } unsigned long int_sqrt(unsigned long); -static inline int __attribute_pure__ long_log2(unsigned long x) -{ - int r = 0; - for (x >>= 1; x > 0; x >>= 1) - r++; - return r; -} - static inline unsigned long __attribute_const__ roundup_pow_of_two(unsigned long x) { diff --git a/include/linux/log2.h b/include/linux/log2.h new file mode 100644 index 000000000000..3979c60325ff --- /dev/null +++ b/include/linux/log2.h @@ -0,0 +1,131 @@ +/* Integer base 2 logarithm calculation + * + * Copyright (C) 2006 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#ifndef _LINUX_LOG2_H +#define _LINUX_LOG2_H + +#include +#include + +/* + * deal with unrepresentable constant logarithms + */ +extern __attribute__((const, noreturn)) +int ____ilog2_NaN(void); + +/* + * non-constant log of base 2 calculators + * - the arch may override these in asm/bitops.h if they can be implemented + * more efficiently than using fls() and fls64() + * - the arch is not required to handle n==0 if implementing the fallback + */ +#ifndef CONFIG_ARCH_HAS_ILOG2_U32 +static inline __attribute__((const)) +int __ilog2_u32(u32 n) +{ + return fls(n) - 1; +} +#endif + +#ifndef CONFIG_ARCH_HAS_ILOG2_U64 +static inline __attribute__((const)) +int __ilog2_u64(u64 n) +{ + return fls64(n) - 1; +} +#endif + +/** + * ilog2 - log of base 2 of 32-bit or a 64-bit unsigned value + * @n - parameter + * + * constant-capable log of base 2 calculation + * - this can be used to initialise global variables from constant data, hence + * the massive ternary operator construction + * + * selects the appropriately-sized optimised version depending on sizeof(n) + */ +#define ilog2(n) \ +( \ + __builtin_constant_p(n) ? ( \ + (n) < 1 ? ____ilog2_NaN() : \ + (n) & (1ULL << 63) ? 63 : \ + (n) & (1ULL << 62) ? 62 : \ + (n) & (1ULL << 61) ? 61 : \ + (n) & (1ULL << 60) ? 60 : \ + (n) & (1ULL << 59) ? 59 : \ + (n) & (1ULL << 58) ? 58 : \ + (n) & (1ULL << 57) ? 57 : \ + (n) & (1ULL << 56) ? 56 : \ + (n) & (1ULL << 55) ? 55 : \ + (n) & (1ULL << 54) ? 54 : \ + (n) & (1ULL << 53) ? 53 : \ + (n) & (1ULL << 52) ? 52 : \ + (n) & (1ULL << 51) ? 51 : \ + (n) & (1ULL << 50) ? 50 : \ + (n) & (1ULL << 49) ? 49 : \ + (n) & (1ULL << 48) ? 48 : \ + (n) & (1ULL << 47) ? 47 : \ + (n) & (1ULL << 46) ? 46 : \ + (n) & (1ULL << 45) ? 45 : \ + (n) & (1ULL << 44) ? 44 : \ + (n) & (1ULL << 43) ? 43 : \ + (n) & (1ULL << 42) ? 42 : \ + (n) & (1ULL << 41) ? 41 : \ + (n) & (1ULL << 40) ? 40 : \ + (n) & (1ULL << 39) ? 39 : \ + (n) & (1ULL << 38) ? 38 : \ + (n) & (1ULL << 37) ? 37 : \ + (n) & (1ULL << 36) ? 36 : \ + (n) & (1ULL << 35) ? 35 : \ + (n) & (1ULL << 34) ? 34 : \ + (n) & (1ULL << 33) ? 33 : \ + (n) & (1ULL << 32) ? 32 : \ + (n) & (1ULL << 31) ? 31 : \ + (n) & (1ULL << 30) ? 30 : \ + (n) & (1ULL << 29) ? 29 : \ + (n) & (1ULL << 28) ? 28 : \ + (n) & (1ULL << 27) ? 27 : \ + (n) & (1ULL << 26) ? 26 : \ + (n) & (1ULL << 25) ? 25 : \ + (n) & (1ULL << 24) ? 24 : \ + (n) & (1ULL << 23) ? 23 : \ + (n) & (1ULL << 22) ? 22 : \ + (n) & (1ULL << 21) ? 21 : \ + (n) & (1ULL << 20) ? 20 : \ + (n) & (1ULL << 19) ? 19 : \ + (n) & (1ULL << 18) ? 18 : \ + (n) & (1ULL << 17) ? 17 : \ + (n) & (1ULL << 16) ? 16 : \ + (n) & (1ULL << 15) ? 15 : \ + (n) & (1ULL << 14) ? 14 : \ + (n) & (1ULL << 13) ? 13 : \ + (n) & (1ULL << 12) ? 12 : \ + (n) & (1ULL << 11) ? 11 : \ + (n) & (1ULL << 10) ? 10 : \ + (n) & (1ULL << 9) ? 9 : \ + (n) & (1ULL << 8) ? 8 : \ + (n) & (1ULL << 7) ? 7 : \ + (n) & (1ULL << 6) ? 6 : \ + (n) & (1ULL << 5) ? 5 : \ + (n) & (1ULL << 4) ? 4 : \ + (n) & (1ULL << 3) ? 3 : \ + (n) & (1ULL << 2) ? 2 : \ + (n) & (1ULL << 1) ? 1 : \ + (n) & (1ULL << 0) ? 0 : \ + ____ilog2_NaN() \ + ) : \ + (sizeof(n) <= 4) ? \ + __ilog2_u32(n) : \ + __ilog2_u64(n) \ + ) + +#endif /* _LINUX_LOG2_H */ -- cgit v1.2.3 From 312a0c170945b49f319960afd2e492c05f9dd551 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 8 Dec 2006 02:37:51 -0800 Subject: [PATCH] LOG2: Alter roundup_pow_of_two() so that it can use a ilog2() on a constant Alter roundup_pow_of_two() so that it can make use of ilog2() on a constant to produce a constant value, retaining the ability for an arch to override it in the non-const case. This permits the function to be used to initialise variables. Signed-off-by: David Howells Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 6 ------ include/linux/log2.h | 26 ++++++++++++++++++++++++++ 2 files changed, 26 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 3710cce16642..e8bfac34d2ba 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -158,12 +158,6 @@ static inline int printk(const char *s, ...) { return 0; } unsigned long int_sqrt(unsigned long); -static inline unsigned long -__attribute_const__ roundup_pow_of_two(unsigned long x) -{ - return 1UL << fls_long(x - 1); -} - extern int printk_ratelimit(void); extern int __printk_ratelimit(int ratelimit_jiffies, int ratelimit_burst); extern bool printk_timed_ratelimit(unsigned long *caller_jiffies, diff --git a/include/linux/log2.h b/include/linux/log2.h index 3979c60325ff..d02e1a547a7e 100644 --- a/include/linux/log2.h +++ b/include/linux/log2.h @@ -43,6 +43,15 @@ int __ilog2_u64(u64 n) } #endif +/* + * round up to nearest power of two + */ +static inline __attribute__((const)) +unsigned long __roundup_pow_of_two(unsigned long n) +{ + return 1UL << fls_long(n - 1); +} + /** * ilog2 - log of base 2 of 32-bit or a 64-bit unsigned value * @n - parameter @@ -128,4 +137,21 @@ int __ilog2_u64(u64 n) __ilog2_u64(n) \ ) +/** + * roundup_pow_of_two - round the given value up to nearest power of two + * @n - parameter + * + * round the given balue up to the nearest power of two + * - the result is undefined when n == 0 + * - this can be used to initialise global variables from constant data + */ +#define roundup_pow_of_two(n) \ +( \ + __builtin_constant_p(n) ? ( \ + (n == 1) ? 0 : \ + (1UL << (ilog2((n) - 1) + 1)) \ + ) : \ + __roundup_pow_of_two(n) \ + ) + #endif /* _LINUX_LOG2_H */ -- cgit v1.2.3 From 937949d9edbf4049bd41af6c9f92c26280584564 Mon Sep 17 00:00:00 2001 From: Cedric Le Goater Date: Fri, 8 Dec 2006 02:37:54 -0800 Subject: [PATCH] add process_session() helper routine Replace occurences of task->signal->session by a new process_session() helper routine. It will be useful for pid namespaces to abstract the session pid number. Signed-off-by: Cedric Le Goater Cc: Kirill Korotaev Cc: Eric W. Biederman Cc: Herbert Poetzl Cc: Sukadev Bhattiprolu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 5e8a0ba61749..270d864a8ff1 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1047,6 +1047,11 @@ static inline pid_t process_group(struct task_struct *tsk) return tsk->signal->pgrp; } +static inline pid_t process_session(struct task_struct *tsk) +{ + return tsk->signal->session; +} + static inline struct pid *task_pid(struct task_struct *task) { return task->pids[PIDTYPE_PID].pid; -- cgit v1.2.3 From 1ec320afdc9552c92191d5f89fcd1ebe588334ca Mon Sep 17 00:00:00 2001 From: Cedric Le Goater Date: Fri, 8 Dec 2006 02:37:55 -0800 Subject: [PATCH] add process_session() helper routine: deprecate old field Add an anonymous union and ((deprecated)) to catch direct usage of the session field. [akpm@osdl.org: fix various missed conversions] [jdike@addtoit.com: fix UML bug] Signed-off-by: Jeff Dike Cc: Cedric Le Goater Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/init_task.h | 11 ++++++----- include/linux/sched.h | 19 +++++++++++++++++-- 2 files changed, 23 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 733790d4f7db..848a68af3d42 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -57,17 +57,18 @@ .cpu_vm_mask = CPU_MASK_ALL, \ } -#define INIT_SIGNALS(sig) { \ - .count = ATOMIC_INIT(1), \ +#define INIT_SIGNALS(sig) { \ + .count = ATOMIC_INIT(1), \ .wait_chldexit = __WAIT_QUEUE_HEAD_INITIALIZER(sig.wait_chldexit),\ - .shared_pending = { \ + .shared_pending = { \ .list = LIST_HEAD_INIT(sig.shared_pending.list), \ - .signal = {{0}}}, \ + .signal = {{0}}}, \ .posix_timers = LIST_HEAD_INIT(sig.posix_timers), \ .cpu_timers = INIT_CPU_TIMERS(sig.cpu_timers), \ .rlim = INIT_RLIMITS, \ .pgrp = 1, \ - .session = 1, \ + .tty_old_pgrp = 0, \ + { .__session = 1}, \ } extern struct nsproxy init_nsproxy; diff --git a/include/linux/sched.h b/include/linux/sched.h index 270d864a8ff1..6fec1d419714 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -436,7 +436,12 @@ struct signal_struct { /* job control IDs */ pid_t pgrp; pid_t tty_old_pgrp; - pid_t session; + + union { + pid_t session __deprecated; + pid_t __session; + }; + /* boolean value for session group leader */ int leader; @@ -1047,9 +1052,19 @@ static inline pid_t process_group(struct task_struct *tsk) return tsk->signal->pgrp; } +static inline pid_t signal_session(struct signal_struct *sig) +{ + return sig->__session; +} + static inline pid_t process_session(struct task_struct *tsk) { - return tsk->signal->session; + return signal_session(tsk->signal); +} + +static inline void set_signal_session(struct signal_struct *sig, pid_t session) +{ + sig->__session = session; } static inline struct pid *task_pid(struct task_struct *task) -- cgit v1.2.3 From 6b3286ed1169d74fea401367d6d4d6c6ec758a81 Mon Sep 17 00:00:00 2001 From: Kirill Korotaev Date: Fri, 8 Dec 2006 02:37:56 -0800 Subject: [PATCH] rename struct namespace to struct mnt_namespace Rename 'struct namespace' to 'struct mnt_namespace' to avoid confusion with other namespaces being developped for the containers : pid, uts, ipc, etc. 'namespace' variables and attributes are also renamed to 'mnt_ns' Signed-off-by: Kirill Korotaev Signed-off-by: Cedric Le Goater Cc: Eric W. Biederman Cc: Herbert Poetzl Cc: Sukadev Bhattiprolu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/init_task.h | 2 +- include/linux/mnt_namespace.h | 42 ++++++++++++++++++++++++++++++++++++++++++ include/linux/mount.h | 4 ++-- include/linux/namespace.h | 42 ------------------------------------------ include/linux/nsproxy.h | 4 ++-- 5 files changed, 47 insertions(+), 47 deletions(-) create mode 100644 include/linux/mnt_namespace.h delete mode 100644 include/linux/namespace.h (limited to 'include/linux') diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 848a68af3d42..5c4989172f7e 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -76,7 +76,7 @@ extern struct nsproxy init_nsproxy; .count = ATOMIC_INIT(1), \ .nslock = __SPIN_LOCK_UNLOCKED(nsproxy.nslock), \ .uts_ns = &init_uts_ns, \ - .namespace = NULL, \ + .mnt_ns = NULL, \ INIT_IPC_NS(ipc_ns) \ } diff --git a/include/linux/mnt_namespace.h b/include/linux/mnt_namespace.h new file mode 100644 index 000000000000..4af0b1fc282a --- /dev/null +++ b/include/linux/mnt_namespace.h @@ -0,0 +1,42 @@ +#ifndef _NAMESPACE_H_ +#define _NAMESPACE_H_ +#ifdef __KERNEL__ + +#include +#include +#include + +struct mnt_namespace { + atomic_t count; + struct vfsmount * root; + struct list_head list; + wait_queue_head_t poll; + int event; +}; + +extern int copy_mnt_ns(int, struct task_struct *); +extern void __put_mnt_ns(struct mnt_namespace *ns); +extern struct mnt_namespace *dup_mnt_ns(struct task_struct *, + struct fs_struct *); + +static inline void put_mnt_ns(struct mnt_namespace *ns) +{ + if (atomic_dec_and_lock(&ns->count, &vfsmount_lock)) + /* releases vfsmount_lock */ + __put_mnt_ns(ns); +} + +static inline void exit_mnt_ns(struct task_struct *p) +{ + struct mnt_namespace *ns = p->nsproxy->mnt_ns; + if (ns) + put_mnt_ns(ns); +} + +static inline void get_mnt_ns(struct mnt_namespace *ns) +{ + atomic_inc(&ns->count); +} + +#endif +#endif diff --git a/include/linux/mount.h b/include/linux/mount.h index 403d1a97c512..e357dc86a4de 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -20,7 +20,7 @@ struct super_block; struct vfsmount; struct dentry; -struct namespace; +struct mnt_namespace; #define MNT_NOSUID 0x01 #define MNT_NODEV 0x02 @@ -52,7 +52,7 @@ struct vfsmount { struct list_head mnt_slave_list;/* list of slave mounts */ struct list_head mnt_slave; /* slave list entry */ struct vfsmount *mnt_master; /* slave is on master->mnt_slave_list */ - struct namespace *mnt_namespace; /* containing namespace */ + struct mnt_namespace *mnt_ns; /* containing namespace */ int mnt_pinned; }; diff --git a/include/linux/namespace.h b/include/linux/namespace.h deleted file mode 100644 index d137009f0b2b..000000000000 --- a/include/linux/namespace.h +++ /dev/null @@ -1,42 +0,0 @@ -#ifndef _NAMESPACE_H_ -#define _NAMESPACE_H_ -#ifdef __KERNEL__ - -#include -#include -#include - -struct namespace { - atomic_t count; - struct vfsmount * root; - struct list_head list; - wait_queue_head_t poll; - int event; -}; - -extern int copy_namespace(int, struct task_struct *); -extern void __put_namespace(struct namespace *namespace); -extern struct namespace *dup_namespace(struct task_struct *, struct fs_struct *); - -static inline void put_namespace(struct namespace *namespace) -{ - if (atomic_dec_and_lock(&namespace->count, &vfsmount_lock)) - /* releases vfsmount_lock */ - __put_namespace(namespace); -} - -static inline void exit_namespace(struct task_struct *p) -{ - struct namespace *namespace = p->nsproxy->namespace; - if (namespace) { - put_namespace(namespace); - } -} - -static inline void get_namespace(struct namespace *namespace) -{ - atomic_inc(&namespace->count); -} - -#endif -#endif diff --git a/include/linux/nsproxy.h b/include/linux/nsproxy.h index 971d1c6dfc4b..0aba1b1a39c7 100644 --- a/include/linux/nsproxy.h +++ b/include/linux/nsproxy.h @@ -4,7 +4,7 @@ #include #include -struct namespace; +struct mnt_namespace; struct uts_namespace; struct ipc_namespace; @@ -25,7 +25,7 @@ struct nsproxy { spinlock_t nslock; struct uts_namespace *uts_ns; struct ipc_namespace *ipc_ns; - struct namespace *namespace; + struct mnt_namespace *mnt_ns; }; extern struct nsproxy init_nsproxy; -- cgit v1.2.3 From 373beb35cd6b625e0ba4ad98baace12310a26aa8 Mon Sep 17 00:00:00 2001 From: Cedric Le Goater Date: Fri, 8 Dec 2006 02:37:57 -0800 Subject: [PATCH] identifier to nsproxy Add an identifier to nsproxy. The default init_ns_proxy has identifier 0 and allocated nsproxies are given -1. This identifier will be used by a new syscall sys_bind_ns. Signed-off-by: Cedric Le Goater Cc: Kirill Korotaev Cc: Eric W. Biederman Cc: Herbert Poetzl Cc: Sukadev Bhattiprolu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/init_task.h | 1 + include/linux/nsproxy.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 5c4989172f7e..90c5f9a07730 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -75,6 +75,7 @@ extern struct nsproxy init_nsproxy; #define INIT_NSPROXY(nsproxy) { \ .count = ATOMIC_INIT(1), \ .nslock = __SPIN_LOCK_UNLOCKED(nsproxy.nslock), \ + .id = 0, \ .uts_ns = &init_uts_ns, \ .mnt_ns = NULL, \ INIT_IPC_NS(ipc_ns) \ diff --git a/include/linux/nsproxy.h b/include/linux/nsproxy.h index 0aba1b1a39c7..27f37c1ec1d9 100644 --- a/include/linux/nsproxy.h +++ b/include/linux/nsproxy.h @@ -23,6 +23,7 @@ struct ipc_namespace; struct nsproxy { atomic_t count; spinlock_t nslock; + unsigned long id; struct uts_namespace *uts_ns; struct ipc_namespace *ipc_ns; struct mnt_namespace *mnt_ns; -- cgit v1.2.3 From 61a58c6c238cc81f7742b8cc84212cc55fb57747 Mon Sep 17 00:00:00 2001 From: Sukadev Bhattiprolu Date: Fri, 8 Dec 2006 02:37:58 -0800 Subject: [PATCH] rename struct pspace to struct pid_namespace Rename struct pspace to struct pid_namespace for consistency with other namespaces (uts_namespace and ipc_namespace). Also rename include/linux/pspace.h to include/linux/pid_namespace.h and variables from pspace to pid_ns. Signed-off-by: Sukadev Bhattiprolu Signed-off-by: Cedric Le Goater Cc: Kirill Korotaev Cc: Eric W. Biederman Cc: Herbert Poetzl Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pid_namespace.h | 23 +++++++++++++++++++++++ include/linux/pspace.h | 23 ----------------------- 2 files changed, 23 insertions(+), 23 deletions(-) create mode 100644 include/linux/pid_namespace.h delete mode 100644 include/linux/pspace.h (limited to 'include/linux') diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h new file mode 100644 index 000000000000..54d79095e295 --- /dev/null +++ b/include/linux/pid_namespace.h @@ -0,0 +1,23 @@ +#ifndef _LINUX_PID_NS_H +#define _LINUX_PID_NS_H + +#include +#include +#include +#include + +struct pidmap { + atomic_t nr_free; + void *page; +}; + +#define PIDMAP_ENTRIES ((PID_MAX_LIMIT + 8*PAGE_SIZE - 1)/PAGE_SIZE/8) + +struct pid_namespace { + struct pidmap pidmap[PIDMAP_ENTRIES]; + int last_pid; +}; + +extern struct pid_namespace init_pid_ns; + +#endif /* _LINUX_PID_NS_H */ diff --git a/include/linux/pspace.h b/include/linux/pspace.h deleted file mode 100644 index 91d48b8b2d99..000000000000 --- a/include/linux/pspace.h +++ /dev/null @@ -1,23 +0,0 @@ -#ifndef _LINUX_PSPACE_H -#define _LINUX_PSPACE_H - -#include -#include -#include -#include - -struct pidmap { - atomic_t nr_free; - void *page; -}; - -#define PIDMAP_ENTRIES ((PID_MAX_LIMIT + 8*PAGE_SIZE - 1)/PAGE_SIZE/8) - -struct pspace { - struct pidmap pidmap[PIDMAP_ENTRIES]; - int last_pid; -}; - -extern struct pspace init_pspace; - -#endif /* _LINUX_PSPACE_H */ -- cgit v1.2.3 From 9a575a92db3312a40cdf0b0406d88de88ad9741e Mon Sep 17 00:00:00 2001 From: Cedric Le Goater Date: Fri, 8 Dec 2006 02:37:59 -0800 Subject: [PATCH] to nsproxy Add the pid namespace framework to the nsproxy object. The copy of the pid namespace only increases the refcount on the global pid namespace, init_pid_ns, and unshare is not implemented. There is no configuration option to activate or deactivate this feature because this not relevant for the moment. Signed-off-by: Cedric Le Goater Cc: Kirill Korotaev Cc: Eric W. Biederman Cc: Herbert Poetzl Cc: Sukadev Bhattiprolu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/init_task.h | 2 ++ include/linux/nsproxy.h | 2 ++ include/linux/pid_namespace.h | 20 ++++++++++++++++++-- 3 files changed, 22 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 90c5f9a07730..7272ff9ee77c 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -7,6 +7,7 @@ #include #include #include +#include #define INIT_FDTABLE \ { \ @@ -73,6 +74,7 @@ extern struct nsproxy init_nsproxy; #define INIT_NSPROXY(nsproxy) { \ + .pid_ns = &init_pid_ns, \ .count = ATOMIC_INIT(1), \ .nslock = __SPIN_LOCK_UNLOCKED(nsproxy.nslock), \ .id = 0, \ diff --git a/include/linux/nsproxy.h b/include/linux/nsproxy.h index 27f37c1ec1d9..fdfb0e44912f 100644 --- a/include/linux/nsproxy.h +++ b/include/linux/nsproxy.h @@ -7,6 +7,7 @@ struct mnt_namespace; struct uts_namespace; struct ipc_namespace; +struct pid_namespace; /* * A structure to contain pointers to all per-process @@ -27,6 +28,7 @@ struct nsproxy { struct uts_namespace *uts_ns; struct ipc_namespace *ipc_ns; struct mnt_namespace *mnt_ns; + struct pid_namespace *pid_ns; }; extern struct nsproxy init_nsproxy; diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h index 54d79095e295..76e7c6b2cf33 100644 --- a/include/linux/pid_namespace.h +++ b/include/linux/pid_namespace.h @@ -5,6 +5,8 @@ #include #include #include +#include +#include struct pidmap { atomic_t nr_free; @@ -14,10 +16,24 @@ struct pidmap { #define PIDMAP_ENTRIES ((PID_MAX_LIMIT + 8*PAGE_SIZE - 1)/PAGE_SIZE/8) struct pid_namespace { - struct pidmap pidmap[PIDMAP_ENTRIES]; - int last_pid; + struct kref kref; + struct pidmap pidmap[PIDMAP_ENTRIES]; + int last_pid; }; extern struct pid_namespace init_pid_ns; +static inline void get_pid_ns(struct pid_namespace *ns) +{ + kref_get(&ns->kref); +} + +extern int copy_pid_ns(int flags, struct task_struct *tsk); +extern void free_pid_ns(struct kref *kref); + +static inline void put_pid_ns(struct pid_namespace *ns) +{ + kref_put(&ns->kref, free_pid_ns); +} + #endif /* _LINUX_PID_NS_H */ -- cgit v1.2.3 From 84d737866e2babdeab0c6b18ea155c6a649663b8 Mon Sep 17 00:00:00 2001 From: Sukadev Bhattiprolu Date: Fri, 8 Dec 2006 02:38:01 -0800 Subject: [PATCH] add child reaper to pid_namespace Add a per pid_namespace child-reaper. This is needed so processes are reaped within the same pid space and do not spill over to the parent pid space. Its also needed so containers preserve existing semantic that pid == 1 would reap orphaned children. This is based on Eric Biederman's patch: http://lkml.org/lkml/2006/2/6/285 Signed-off-by: Sukadev Bhattiprolu Signed-off-by: Cedric Le Goater Cc: Kirill Korotaev Cc: Eric W. Biederman Cc: Herbert Poetzl Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pid.h | 5 +++-- include/linux/pid_namespace.h | 6 ++++++ include/linux/sched.h | 1 - 3 files changed, 9 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pid.h b/include/linux/pid.h index 2c0007d17218..4dec047b1837 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -35,8 +35,9 @@ enum pid_type * * Holding a reference to struct pid solves both of these problems. * It is small so holding a reference does not consume a lot of - * resources, and since a new struct pid is allocated when the numeric - * pid value is reused we don't mistakenly refer to new processes. + * resources, and since a new struct pid is allocated when the numeric pid + * value is reused (when pids wrap around) we don't mistakenly refer to new + * processes. */ struct pid diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h index 76e7c6b2cf33..d2a9d419f01f 100644 --- a/include/linux/pid_namespace.h +++ b/include/linux/pid_namespace.h @@ -19,6 +19,7 @@ struct pid_namespace { struct kref kref; struct pidmap pidmap[PIDMAP_ENTRIES]; int last_pid; + struct task_struct *child_reaper; }; extern struct pid_namespace init_pid_ns; @@ -36,4 +37,9 @@ static inline void put_pid_ns(struct pid_namespace *ns) kref_put(&ns->kref, free_pid_ns); } +static inline struct task_struct *child_reaper(struct task_struct *tsk) +{ + return tsk->nsproxy->pid_ns->child_reaper; +} + #endif /* _LINUX_PID_NS_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 6fec1d419714..f0317edea141 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1400,7 +1400,6 @@ extern NORET_TYPE void do_group_exit(int); extern void daemonize(const char *, ...); extern int allow_signal(int); extern int disallow_signal(int); -extern struct task_struct *child_reaper; extern int do_execve(char *, char __user * __user *, char __user * __user *, struct pt_regs *); extern long do_fork(unsigned long, unsigned long, struct pt_regs *, unsigned long, int __user *, int __user *); -- cgit v1.2.3 From 3306ce3d0554e2e59cc429b7133e17e1513307cb Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Fri, 8 Dec 2006 02:38:13 -0800 Subject: [PATCH] Char: mxser_new, upgrade to 1.9.1 Change cloned experimental driver according to original 1.9.1 moxa driver. Some int->ulong conversions, outb ~UART_IER_THRI constant. Remove commented stuff. I also added printk line with info, if somebody wants to test it, he may contact me as I can potentially debug the driver with him or just to confirm it works properly. Signed-off-by: Jiri Slaby Cc: Alan Cox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pci_ids.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 4d972bbef316..51180dba9a98 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1785,14 +1785,17 @@ #define PCI_DEVICE_ID_MOXA_C104 0x1040 #define PCI_DEVICE_ID_MOXA_CP104U 0x1041 #define PCI_DEVICE_ID_MOXA_CP104JU 0x1042 +#define PCI_DEVICE_ID_MOXA_CP104EL 0x1043 #define PCI_DEVICE_ID_MOXA_CT114 0x1140 #define PCI_DEVICE_ID_MOXA_CP114 0x1141 #define PCI_DEVICE_ID_MOXA_CP118U 0x1180 +#define PCI_DEVICE_ID_MOXA_CP118EL 0x1181 #define PCI_DEVICE_ID_MOXA_CP132 0x1320 #define PCI_DEVICE_ID_MOXA_CP132U 0x1321 #define PCI_DEVICE_ID_MOXA_CP134U 0x1340 #define PCI_DEVICE_ID_MOXA_C168 0x1680 #define PCI_DEVICE_ID_MOXA_CP168U 0x1681 +#define PCI_DEVICE_ID_MOXA_CP168EL 0x1682 #define PCI_VENDOR_ID_CCD 0x1397 #define PCI_DEVICE_ID_CCD_2BD0 0x2bd0 -- cgit v1.2.3 From ca7ed0f22f4876986b2eb1fbd80ba78e07fd69d5 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Fri, 8 Dec 2006 02:38:39 -0800 Subject: [PATCH] Char: stallion, kill typedefs Typedefs are considered ugly in the kernel. Eliminate them. Signed-off-by: Jiri Slaby Cc: Alan Cox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/stallion.h | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/stallion.h b/include/linux/stallion.h index 13a37f137ea2..ef5270b83d02 100644 --- a/include/linux/stallion.h +++ b/include/linux/stallion.h @@ -52,11 +52,11 @@ * protection - since "write" code only needs to change the head, and * interrupt code only needs to change the tail. */ -typedef struct { +struct stlrq { char *buf; char *head; char *tail; -} stlrq_t; +}; /* * Port, panel and board structures to hold status info about each. @@ -67,7 +67,7 @@ typedef struct { * is associated with, this makes it (fairly) easy to get back to the * board/panel info for a port. */ -typedef struct stlport { +struct stlport { unsigned long magic; int portnr; int panelnr; @@ -97,10 +97,10 @@ typedef struct stlport { wait_queue_head_t close_wait; struct work_struct tqueue; comstats_t stats; - stlrq_t tx; -} stlport_t; + struct stlrq tx; +}; -typedef struct stlpanel { +struct stlpanel { unsigned long magic; int panelnr; int brdnr; @@ -111,10 +111,10 @@ typedef struct stlpanel { void (*isr)(struct stlpanel *panelp, unsigned int iobase); unsigned int hwid; unsigned int ackmask; - stlport_t *ports[STL_PORTSPERPANEL]; -} stlpanel_t; + struct stlport *ports[STL_PORTSPERPANEL]; +}; -typedef struct stlbrd { +struct stlbrd { unsigned long magic; int brdnr; int brdtype; @@ -136,9 +136,9 @@ typedef struct stlbrd { unsigned long clk; unsigned int bnkpageaddr[STL_MAXBANKS]; unsigned int bnkstataddr[STL_MAXBANKS]; - stlpanel_t *bnk2panel[STL_MAXBANKS]; - stlpanel_t *panels[STL_MAXPANELS]; -} stlbrd_t; + struct stlpanel *bnk2panel[STL_MAXBANKS]; + struct stlpanel *panels[STL_MAXPANELS]; +}; /* -- cgit v1.2.3 From edc6afc5496875a640bef0913604be7550c1795d Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Fri, 8 Dec 2006 02:38:44 -0800 Subject: [PATCH] tty: switch to ktermios and new framework This is the core of the switch to the new framework. I've split it from the driver patches which are mostly search/replace and would encourage people to give this one a good hard stare. The references to BOTHER and ISHIFT are the termios values that must be defined by a platform once it wants to turn on "new style" ioctl support. The code patches here ensure that providing 1. The termios overlays the ktermios in memory 2. The only new kernel only fields are c_ispeed/c_ospeed (or none) the existing behaviour is retained. This is true for the patches at this point in time. Future patches will define BOTHER, ISHIFT and enable newer termios structures for each architecture, and once they are all done some of the ifdefs also vanish. [akpm@osdl.org: warning fix] [akpm@osdl.org: IRDA fix] Signed-off-by: Alan Cox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/tty.h | 9 +++++---- include/linux/tty_driver.h | 12 ++++++------ include/linux/tty_ldisc.h | 4 ++-- 3 files changed, 13 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 1d29999a3439..65cbcf22c31e 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -175,7 +175,7 @@ struct tty_struct { int index; struct tty_ldisc ldisc; struct mutex termios_mutex; - struct termios *termios, *termios_locked; + struct ktermios *termios, *termios_locked; char name[64]; int pgrp; int session; @@ -258,7 +258,7 @@ struct tty_struct { extern void tty_write_flush(struct tty_struct *); -extern struct termios tty_std_termios; +extern struct ktermios tty_std_termios; extern int kmsg_redirect; @@ -293,8 +293,9 @@ extern int tty_hung_up_p(struct file * filp); extern void do_SAK(struct tty_struct *tty); extern void disassociate_ctty(int priv); extern void tty_flip_buffer_push(struct tty_struct *tty); -extern int tty_get_baud_rate(struct tty_struct *tty); -extern int tty_termios_baud_rate(struct termios *termios); +extern speed_t tty_get_baud_rate(struct tty_struct *tty); +extern speed_t tty_termios_baud_rate(struct ktermios *termios); +extern speed_t tty_termios_input_baud_rate(struct ktermios *termios); extern struct tty_ldisc *tty_ldisc_ref(struct tty_struct *); extern void tty_ldisc_deref(struct tty_ldisc *); diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h index 5c8473bb6882..659487e3ebeb 100644 --- a/include/linux/tty_driver.h +++ b/include/linux/tty_driver.h @@ -53,7 +53,7 @@ * device-specific ioctl's. If the ioctl number passed in cmd * is not recognized by the driver, it should return ENOIOCTLCMD. * - * void (*set_termios)(struct tty_struct *tty, struct termios * old); + * void (*set_termios)(struct tty_struct *tty, struct ktermios * old); * * This routine allows the tty driver to be notified when * device's termios settings have changed. Note that a @@ -132,7 +132,7 @@ struct tty_operations { int (*chars_in_buffer)(struct tty_struct *tty); int (*ioctl)(struct tty_struct *tty, struct file * file, unsigned int cmd, unsigned long arg); - void (*set_termios)(struct tty_struct *tty, struct termios * old); + void (*set_termios)(struct tty_struct *tty, struct ktermios * old); void (*throttle)(struct tty_struct * tty); void (*unthrottle)(struct tty_struct * tty); void (*stop)(struct tty_struct *tty); @@ -165,7 +165,7 @@ struct tty_driver { int num; /* number of devices allocated */ short type; /* type of tty driver */ short subtype; /* subtype of tty driver */ - struct termios init_termios; /* Initial termios */ + struct ktermios init_termios; /* Initial termios */ int flags; /* tty driver flags */ int refcount; /* for loadable tty drivers */ struct proc_dir_entry *proc_entry; /* /proc fs entry */ @@ -175,8 +175,8 @@ struct tty_driver { * Pointer to the tty data structures */ struct tty_struct **ttys; - struct termios **termios; - struct termios **termios_locked; + struct ktermios **termios; + struct ktermios **termios_locked; void *driver_state; /* only used for the PTY driver */ /* @@ -193,7 +193,7 @@ struct tty_driver { int (*chars_in_buffer)(struct tty_struct *tty); int (*ioctl)(struct tty_struct *tty, struct file * file, unsigned int cmd, unsigned long arg); - void (*set_termios)(struct tty_struct *tty, struct termios * old); + void (*set_termios)(struct tty_struct *tty, struct ktermios * old); void (*throttle)(struct tty_struct * tty); void (*unthrottle)(struct tty_struct * tty); void (*stop)(struct tty_struct *tty); diff --git a/include/linux/tty_ldisc.h b/include/linux/tty_ldisc.h index 83c6e6c10ebb..d75932e27710 100644 --- a/include/linux/tty_ldisc.h +++ b/include/linux/tty_ldisc.h @@ -59,7 +59,7 @@ * low-level driver can "grab" an ioctl request before the line * discpline has a chance to see it. * - * void (*set_termios)(struct tty_struct *tty, struct termios * old); + * void (*set_termios)(struct tty_struct *tty, struct ktermios * old); * * This function notifies the line discpline that a change has * been made to the termios structure. @@ -118,7 +118,7 @@ struct tty_ldisc { const unsigned char * buf, size_t nr); int (*ioctl)(struct tty_struct * tty, struct file * file, unsigned int cmd, unsigned long arg); - void (*set_termios)(struct tty_struct *tty, struct termios * old); + void (*set_termios)(struct tty_struct *tty, struct ktermios * old); unsigned int (*poll)(struct tty_struct *, struct file *, struct poll_table_struct *); int (*hangup)(struct tty_struct *tty); -- cgit v1.2.3 From 606d099cdd1080bbb50ea50dc52d98252f8f10a1 Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Fri, 8 Dec 2006 02:38:45 -0800 Subject: [PATCH] tty: switch to ktermios This is the grungy swap all the occurrences in the right places patch that goes with the updates. At this point we have the same functionality as before (except that sgttyb() returns speeds not zero) and are ready to begin turning new stuff on providing nobody reports lots of bugs If you are a tty driver author converting an out of tree driver the only impact should be termios->ktermios name changes for the speed/property setting functions from your upper layers. If you are implementing your own TCGETS function before then your driver was broken already and its about to get a whole lot more painful for you so please fix it 8) Also fill in c_ispeed/ospeed on init for most devices, although the current code will do this for you anyway but I'd like eventually to lose that extra paranoia [akpm@osdl.org: bluetooth fix] [mp3@de.ibm.com: sclp fix] [mp3@de.ibm.com: warning fix for tty3270] [hugh@veritas.com: fix tty_ioctl powerpc build] [jdike@addtoit.com: uml: fix ->set_termios declaration] Signed-off-by: Alan Cox Signed-off-by: Martin Peschke Acked-by: Peter Oberparleiter Cc: Cornelia Huck Signed-off-by: Hugh Dickins Signed-off-by: Jeff Dike Cc: Paolo 'Blaisorblade' Giarrusso Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/generic_serial.h | 2 +- include/linux/isdn.h | 8 ++++---- include/linux/serial_core.h | 8 ++++---- include/linux/usb/serial.h | 2 +- 4 files changed, 10 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/generic_serial.h b/include/linux/generic_serial.h index e25384561955..5412da28fa47 100644 --- a/include/linux/generic_serial.h +++ b/include/linux/generic_serial.h @@ -91,7 +91,7 @@ void gs_hangup(struct tty_struct *tty); int gs_block_til_ready(void *port, struct file *filp); void gs_close(struct tty_struct *tty, struct file *filp); void gs_set_termios (struct tty_struct * tty, - struct termios * old_termios); + struct ktermios * old_termios); int gs_init_port(struct gs_port *port); int gs_setserial(struct gs_port *port, struct serial_struct __user *sp); int gs_getserial(struct gs_port *port, struct serial_struct __user *sp); diff --git a/include/linux/isdn.h b/include/linux/isdn.h index 62991148d5a5..3c7875b7ab5b 100644 --- a/include/linux/isdn.h +++ b/include/linux/isdn.h @@ -511,8 +511,8 @@ typedef struct modem_info { #endif struct tty_struct *tty; /* Pointer to corresponding tty */ atemu emu; /* AT-emulator data */ - struct termios normal_termios; /* For saving termios structs */ - struct termios callout_termios; + struct ktermios normal_termios; /* For saving termios structs */ + struct ktermios callout_termios; wait_queue_head_t open_wait, close_wait; struct semaphore write_sem; spinlock_t readlock; @@ -525,8 +525,8 @@ typedef struct _isdn_modem { int refcount; /* Number of opens */ struct tty_driver *tty_modem; /* tty-device */ struct tty_struct *modem_table[ISDN_MAX_CHANNELS]; /* ?? copied from Orig */ - struct termios *modem_termios[ISDN_MAX_CHANNELS]; - struct termios *modem_termios_locked[ISDN_MAX_CHANNELS]; + struct ktermios *modem_termios[ISDN_MAX_CHANNELS]; + struct ktermios *modem_termios_locked[ISDN_MAX_CHANNELS]; modem_info info[ISDN_MAX_CHANNELS]; /* Private data */ } isdn_modem_t; diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 827672136646..cf23813cbec2 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -166,8 +166,8 @@ struct uart_ops { void (*break_ctl)(struct uart_port *, int ctl); int (*startup)(struct uart_port *); void (*shutdown)(struct uart_port *); - void (*set_termios)(struct uart_port *, struct termios *new, - struct termios *old); + void (*set_termios)(struct uart_port *, struct ktermios *new, + struct ktermios *old); void (*pm)(struct uart_port *, unsigned int state, unsigned int oldstate); int (*set_wake)(struct uart_port *, unsigned int state); @@ -361,8 +361,8 @@ void uart_write_wakeup(struct uart_port *port); */ void uart_update_timeout(struct uart_port *port, unsigned int cflag, unsigned int baud); -unsigned int uart_get_baud_rate(struct uart_port *port, struct termios *termios, - struct termios *old, unsigned int min, +unsigned int uart_get_baud_rate(struct uart_port *port, struct ktermios *termios, + struct ktermios *old, unsigned int min, unsigned int max); unsigned int uart_get_divisor(struct uart_port *port, unsigned int baud); diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h index 91b3ea2bbb14..10f99e5f1a97 100644 --- a/include/linux/usb/serial.h +++ b/include/linux/usb/serial.h @@ -218,7 +218,7 @@ struct usb_serial_driver { int (*write) (struct usb_serial_port *port, const unsigned char *buf, int count); int (*write_room) (struct usb_serial_port *port); int (*ioctl) (struct usb_serial_port *port, struct file * file, unsigned int cmd, unsigned long arg); - void (*set_termios) (struct usb_serial_port *port, struct termios * old); + void (*set_termios) (struct usb_serial_port *port, struct ktermios * old); void (*break_ctl) (struct usb_serial_port *port, int break_state); int (*chars_in_buffer) (struct usb_serial_port *port); void (*throttle) (struct usb_serial_port *port); -- cgit v1.2.3 From 6b2c9457bb377bf843f0a3ca2f4eb2ef69c67985 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Fri, 8 Dec 2006 02:39:15 -0800 Subject: [PATCH] Char: stallion, variables cleanup - fix `gcc -W' un/signed warnings by converting some ints -> uints. - move 3 global variables into functions, where are they used. Signed-off-by: Jiri Slaby Cc: Alan Cox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/stallion.h | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/stallion.h b/include/linux/stallion.h index ef5270b83d02..4a0a329beafb 100644 --- a/include/linux/stallion.h +++ b/include/linux/stallion.h @@ -69,12 +69,12 @@ struct stlrq { */ struct stlport { unsigned long magic; - int portnr; - int panelnr; - int brdnr; + unsigned int portnr; + unsigned int panelnr; + unsigned int brdnr; int ioaddr; int uartaddr; - int pagenr; + unsigned int pagenr; long istate; int flags; int baud_base; @@ -102,10 +102,10 @@ struct stlport { struct stlpanel { unsigned long magic; - int panelnr; - int brdnr; - int pagenr; - int nrports; + unsigned int panelnr; + unsigned int brdnr; + unsigned int pagenr; + unsigned int nrports; int iobase; void *uartp; void (*isr)(struct stlpanel *panelp, unsigned int iobase); @@ -116,12 +116,12 @@ struct stlpanel { struct stlbrd { unsigned long magic; - int brdnr; - int brdtype; - int state; - int nrpanels; - int nrports; - int nrbnks; + unsigned int brdnr; + unsigned int brdtype; + unsigned int state; + unsigned int nrpanels; + unsigned int nrports; + unsigned int nrbnks; int irq; int irqtype; int (*isr)(struct stlbrd *brdp); -- cgit v1.2.3 From 1f8ec435e3516eb831bb98110cc2b2b28057154b Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Fri, 8 Dec 2006 02:39:18 -0800 Subject: [PATCH] Char: istallion, eliminate typedefs Use only struct instead of defining a new type . Signed-off-by: Jiri Slaby Cc: Alan Cox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/istallion.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/istallion.h b/include/linux/istallion.h index b55e2a035605..af2c32d16d45 100644 --- a/include/linux/istallion.h +++ b/include/linux/istallion.h @@ -49,7 +49,7 @@ * communication with the slave board will always be on a per port * basis. */ -typedef struct { +struct stliport { unsigned long magic; int portnr; int panelnr; @@ -72,7 +72,7 @@ typedef struct { wait_queue_head_t close_wait; wait_queue_head_t raw_wait; struct work_struct tqhangup; - asysigs_t asig; + struct asysigs asig; unsigned long addr; unsigned long rxoffset; unsigned long txoffset; @@ -83,13 +83,13 @@ typedef struct { unsigned char reqbit; unsigned char portidx; unsigned char portbit; -} stliport_t; +}; /* * Use a structure of function pointers to do board level operations. * These include, enable/disable, paging shared memory, interrupting, etc. */ -typedef struct stlibrd { +struct stlibrd { unsigned long magic; int brdnr; int brdtype; @@ -116,8 +116,8 @@ typedef struct stlibrd { void __iomem *(*getmemptr)(struct stlibrd *brdp, unsigned long offset, int line); void (*intr)(struct stlibrd *brdp); void (*reset)(struct stlibrd *brdp); - stliport_t *ports[STL_MAXPORTS]; -} stlibrd_t; + struct stliport *ports[STL_MAXPORTS]; +}; /* -- cgit v1.2.3 From 1328d737f510e9933a621f66aa8de81c02b647a7 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Fri, 8 Dec 2006 02:39:19 -0800 Subject: [PATCH] Char: istallion, variables cleanup - wipe gcc -W warnings by int -> uint conversion - move 2 global variables into their local place Signed-off-by: Jiri Slaby Cc: Alan Cox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/istallion.h | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/istallion.h b/include/linux/istallion.h index af2c32d16d45..106a5e85e5c4 100644 --- a/include/linux/istallion.h +++ b/include/linux/istallion.h @@ -51,11 +51,11 @@ */ struct stliport { unsigned long magic; - int portnr; - int panelnr; - int brdnr; + unsigned int portnr; + unsigned int panelnr; + unsigned int brdnr; unsigned long state; - int devnr; + unsigned int devnr; int flags; int baud_base; int custom_divisor; @@ -91,23 +91,23 @@ struct stliport { */ struct stlibrd { unsigned long magic; - int brdnr; - int brdtype; - int state; - int nrpanels; - int nrports; - int nrdevs; + unsigned int brdnr; + unsigned int brdtype; + unsigned int state; + unsigned int nrpanels; + unsigned int nrports; + unsigned int nrdevs; unsigned int iobase; int iosize; unsigned long memaddr; void __iomem *membase; - int memsize; + unsigned long memsize; int pagesize; int hostoffset; int slaveoffset; int bitsize; int enabval; - int panels[STL_MAXPANELS]; + unsigned int panels[STL_MAXPANELS]; int panelids[STL_MAXPANELS]; void (*init)(struct stlibrd *brdp); void (*enable)(struct stlibrd *brdp); -- cgit v1.2.3 From 6ff1cb355e628f8fc55fa2d01e269e5e1bbc2fe9 Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Fri, 8 Dec 2006 02:39:43 -0800 Subject: [PATCH] fault-injection capabilities infrastructure This patch provides base functions implement to fault-injection capabilities. - The function should_fail() is taken from failmalloc-1.0 (http://www.nongnu.org/failmalloc/) [akpm@osdl.org: cleanups, comments, add __init] Cc: Signed-off-by: Akinobu Mita Signed-off-by: Don Mullis Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fault-inject.h | 69 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 69 insertions(+) create mode 100644 include/linux/fault-inject.h (limited to 'include/linux') diff --git a/include/linux/fault-inject.h b/include/linux/fault-inject.h new file mode 100644 index 000000000000..4df4902bc8d8 --- /dev/null +++ b/include/linux/fault-inject.h @@ -0,0 +1,69 @@ +#ifndef _LINUX_FAULT_INJECT_H +#define _LINUX_FAULT_INJECT_H + +#ifdef CONFIG_FAULT_INJECTION + +#include +#include +#include + +/* + * For explanation of the elements of this struct, see + * Documentation/fault-injection/fault-injection.txt + */ +struct fault_attr { + unsigned long probability; + unsigned long interval; + atomic_t times; + atomic_t space; + unsigned long verbose; + + unsigned long count; + +#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS + + struct { + struct dentry *dir; + + struct dentry *probability_file; + struct dentry *interval_file; + struct dentry *times_file; + struct dentry *space_file; + struct dentry *verbose_file; + } dentries; + +#endif +}; + +#define FAULT_ATTR_INITIALIZER { \ + .interval = 1, \ + .times = ATOMIC_INIT(1), \ + } + +#define DECLARE_FAULT_ATTR(name) struct fault_attr name = FAULT_ATTR_INITIALIZER +int setup_fault_attr(struct fault_attr *attr, char *str); +void should_fail_srandom(unsigned long entropy); +int should_fail(struct fault_attr *attr, ssize_t size); + +#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS + +int init_fault_attr_dentries(struct fault_attr *attr, const char *name); +void cleanup_fault_attr_dentries(struct fault_attr *attr); + +#else /* CONFIG_FAULT_INJECTION_DEBUG_FS */ + +static inline int init_fault_attr_dentries(struct fault_attr *attr, + const char *name) +{ + return -ENODEV; +} + +static inline void cleanup_fault_attr_dentries(struct fault_attr *attr) +{ +} + +#endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */ + +#endif /* CONFIG_FAULT_INJECTION */ + +#endif /* _LINUX_FAULT_INJECT_H */ -- cgit v1.2.3 From c17bb4951752d3e0f49cd1ea9d2e868422f9e0d6 Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Fri, 8 Dec 2006 02:39:46 -0800 Subject: [PATCH] fault-injection capability for disk IO This patch provides fault-injection capability for disk IO. Boot option: fail_make_request=,,, -- specifies the interval of failures. -- specifies how often it should fail in percent. -- specifies the size of free space where disk IO can be issued safely in bytes. -- specifies how many times failures may happen at most. Debugfs: /debug/fail_make_request/interval /debug/fail_make_request/probability /debug/fail_make_request/specifies /debug/fail_make_request/times Example: fail_make_request=10,100,0,-1 echo 1 > /sys/blocks/hda/hda1/make-it-fail generic_make_request() on /dev/hda1 fails once per 10 times. Cc: Jens Axboe Signed-off-by: Akinobu Mita Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/genhd.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 41f276fdd185..0a022b2f63fc 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -83,6 +83,9 @@ struct hd_struct { struct kobject *holder_dir; unsigned ios[2], sectors[2]; /* READs and WRITEs */ int policy, partno; +#ifdef CONFIG_FAIL_MAKE_REQUEST + int make_it_fail; +#endif }; #define GENHD_FL_REMOVABLE 1 @@ -90,6 +93,7 @@ struct hd_struct { #define GENHD_FL_CD 8 #define GENHD_FL_UP 16 #define GENHD_FL_SUPPRESS_PARTITION_INFO 32 +#define GENHD_FL_FAIL 64 struct disk_stats { unsigned long sectors[2]; /* READs and WRITEs */ -- cgit v1.2.3 From f4f154fd920b2178382a6a24a236348e4429ebc1 Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Fri, 8 Dec 2006 02:39:47 -0800 Subject: [PATCH] fault injection: process filtering for fault-injection capabilities This patch provides process filtering feature. The process filter allows failing only permitted processes by /proc//make-it-fail Please see the example that demostrates how to inject slab allocation failures into module init/cleanup code in Documentation/fault-injection/fault-injection.txt Signed-off-by: Akinobu Mita Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fault-inject.h | 2 ++ include/linux/sched.h | 3 +++ 2 files changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fault-inject.h b/include/linux/fault-inject.h index 4df4902bc8d8..a525f9b9f015 100644 --- a/include/linux/fault-inject.h +++ b/include/linux/fault-inject.h @@ -17,6 +17,7 @@ struct fault_attr { atomic_t times; atomic_t space; unsigned long verbose; + u32 task_filter; unsigned long count; @@ -30,6 +31,7 @@ struct fault_attr { struct dentry *times_file; struct dentry *space_file; struct dentry *verbose_file; + struct dentry *task_filter_file; } dentries; #endif diff --git a/include/linux/sched.h b/include/linux/sched.h index f0317edea141..ad9c46071ff8 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1045,6 +1045,9 @@ struct task_struct { #ifdef CONFIG_TASK_DELAY_ACCT struct task_delay_info *delays; #endif +#ifdef CONFIG_FAULT_INJECTION + int make_it_fail; +#endif }; static inline pid_t process_group(struct task_struct *tsk) -- cgit v1.2.3 From 329409aeda064c4aff00c51f837fcd3bbdaeeba6 Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Fri, 8 Dec 2006 02:39:48 -0800 Subject: [PATCH] fault injection: stacktrace filtering This patch provides stacktrace filtering feature. The stacktrace filter allows failing only for the caller you are interested in. For example someone may want to inject kmalloc() failures into only e100 module. they want to inject not only direct kmalloc() call, but also indirect allocation, too. - e100_poll --> netif_receive_skb --> packet_rcv_spkt --> skb_clone --> kmem_cache_alloc This patch enables to detect function calls like this by stacktrace and inject failures. The script Documentaion/fault-injection/failmodule.sh helps it. The range of text section of loaded e100 is expected to be [/sys/module/e100/sections/.text, /sys/module/e100/sections/.exit.text) So failmodule.sh stores these values into /debug/failslab/address-start and /debug/failslab/address-end. The maximum stacktrace depth is specified by /debug/failslab/stacktrace-depth. Please see the example that demonstrates how to inject slab allocation failures only for a specific module in Documentation/fault-injection/fault-injection.txt [dwm@meer.net: reject failure if any caller lies within specified range] Signed-off-by: Akinobu Mita Signed-off-by: Don Mullis Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fault-inject.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fault-inject.h b/include/linux/fault-inject.h index a525f9b9f015..9bb584e89399 100644 --- a/include/linux/fault-inject.h +++ b/include/linux/fault-inject.h @@ -18,6 +18,11 @@ struct fault_attr { atomic_t space; unsigned long verbose; u32 task_filter; + unsigned long stacktrace_depth; + unsigned long require_start; + unsigned long require_end; + unsigned long reject_start; + unsigned long reject_end; unsigned long count; @@ -32,6 +37,11 @@ struct fault_attr { struct dentry *space_file; struct dentry *verbose_file; struct dentry *task_filter_file; + struct dentry *stacktrace_depth_file; + struct dentry *require_start_file; + struct dentry *require_end_file; + struct dentry *reject_start_file; + struct dentry *reject_end_file; } dentries; #endif @@ -40,6 +50,8 @@ struct fault_attr { #define FAULT_ATTR_INITIALIZER { \ .interval = 1, \ .times = ATOMIC_INIT(1), \ + .require_end = ULONG_MAX, \ + .stacktrace_depth = 32, \ } #define DECLARE_FAULT_ATTR(name) struct fault_attr name = FAULT_ATTR_INITIALIZER -- cgit v1.2.3 From 08b3df2d16cbebf7d72c09dcbc071696c14d07e3 Mon Sep 17 00:00:00 2001 From: Don Mullis Date: Fri, 8 Dec 2006 02:39:51 -0800 Subject: [PATCH] fault-injection: Use bool-true-false throughout Use bool-true-false throughout. Signed-off-by: Don Mullis Cc: Akinobu Mita Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fault-inject.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fault-inject.h b/include/linux/fault-inject.h index 9bb584e89399..c77067916b7e 100644 --- a/include/linux/fault-inject.h +++ b/include/linux/fault-inject.h @@ -57,7 +57,7 @@ struct fault_attr { #define DECLARE_FAULT_ATTR(name) struct fault_attr name = FAULT_ATTR_INITIALIZER int setup_fault_attr(struct fault_attr *attr, char *str); void should_fail_srandom(unsigned long entropy); -int should_fail(struct fault_attr *attr, ssize_t size); +bool should_fail(struct fault_attr *attr, ssize_t size); #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS -- cgit v1.2.3 From 6b1b60f41eef3ba7b188fd72f1d6de478aafd93c Mon Sep 17 00:00:00 2001 From: Don Mullis Date: Fri, 8 Dec 2006 02:39:53 -0800 Subject: [PATCH] fault-injection: defaults likely to please a new user Assign defaults most likely to please a new user: 1) generate some logging output (verbose=2) 2) avoid injecting failures likely to lock up UI (ignore_gfp_wait=1, ignore_gfp_highmem=1) Signed-off-by: Don Mullis Cc: Akinobu Mita Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fault-inject.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fault-inject.h b/include/linux/fault-inject.h index c77067916b7e..32368c4f0326 100644 --- a/include/linux/fault-inject.h +++ b/include/linux/fault-inject.h @@ -52,6 +52,7 @@ struct fault_attr { .times = ATOMIC_INIT(1), \ .require_end = ULONG_MAX, \ .stacktrace_depth = 32, \ + .verbose = 2, \ } #define DECLARE_FAULT_ATTR(name) struct fault_attr name = FAULT_ATTR_INITIALIZER -- cgit v1.2.3 From adf6b206546414fd006098d027e81f2b576ea2aa Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Fri, 8 Dec 2006 02:40:27 -0800 Subject: [PATCH] fbcmap.c: mark structs const or __read_mostly - Mark the default colormaps read-only, as nobody should be allowed to modify them - Additionally mark color values as __read_mostly since they will only be modified (very seldom) by fb_invert_cmaps() - Add named C99-initializers in fb_cmap structs and use the ARRAY_SIZE() macro Signed-off-by: Helge Deller Acked-by: James Simmons Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fb.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fb.h b/include/linux/fb.h index fa23e0671bb3..6fe56aaa6685 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -970,11 +970,11 @@ extern struct fb_videomode *fb_find_best_display(struct fb_monspecs *specs, /* drivers/video/fbcmap.c */ extern int fb_alloc_cmap(struct fb_cmap *cmap, int len, int transp); extern void fb_dealloc_cmap(struct fb_cmap *cmap); -extern int fb_copy_cmap(struct fb_cmap *from, struct fb_cmap *to); -extern int fb_cmap_to_user(struct fb_cmap *from, struct fb_cmap_user *to); +extern int fb_copy_cmap(const struct fb_cmap *from, struct fb_cmap *to); +extern int fb_cmap_to_user(const struct fb_cmap *from, struct fb_cmap_user *to); extern int fb_set_cmap(struct fb_cmap *cmap, struct fb_info *fb_info); extern int fb_set_user_cmap(struct fb_cmap_user *cmap, struct fb_info *fb_info); -extern struct fb_cmap *fb_default_cmap(int len); +extern const struct fb_cmap *fb_default_cmap(int len); extern void fb_invert_cmaps(void); struct fb_videomode { -- cgit v1.2.3 From a3d77d35be6f416a250c528c3ed5c70013a915e8 Mon Sep 17 00:00:00 2001 From: Kiyoshi Ueda Date: Fri, 8 Dec 2006 02:41:04 -0800 Subject: [PATCH] dm: suspend: parameter change Change the interface of dm_suspend() so that we can pass several options without increasing the number of parameters. The existing 'do_lockfs' integer parameter is replaced by a flag DM_SUSPEND_LOCKFS_FLAG. There is no functional change to the code. Test results: I have tested 'dmsetup suspend' command with/without the '--nolockfs' option and confirmed the do_lockfs value is correctly set. Signed-off-by: Kiyoshi Ueda Signed-off-by: Jun'ichi Nomura Signed-off-by: Alasdair G Kergon Cc: dm-devel@redhat.com Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/device-mapper.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 03ef41c1eaac..9194ff2d08c0 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -173,7 +173,7 @@ void *dm_get_mdptr(struct mapped_device *md); /* * A device can still be used while suspended, but I/O is deferred. */ -int dm_suspend(struct mapped_device *md, int with_lockfs); +int dm_suspend(struct mapped_device *md, unsigned suspend_flags); int dm_resume(struct mapped_device *md); /* -- cgit v1.2.3 From 45cbcd798354251b99694086af9d57c99e89bb43 Mon Sep 17 00:00:00 2001 From: Kiyoshi Ueda Date: Fri, 8 Dec 2006 02:41:05 -0800 Subject: [PATCH] dm: map and endio return code clarification Tighten the use of return values from the target map and end_io functions. Values of 2 and above are now explictly reserved for future use. There are no existing targets using such values. The patch has no effect on existing behaviour. o Reserve return values of 2 and above from target map functions. Any positive value currently indicates "mapping complete", but all existing drivers use the value 1. We now make that a requirement so we can assign new meaning to higher values in future. The new definition of return values from target map functions is: < 0 : error = 0 : The target will handle the io (DM_MAPIO_SUBMITTED). = 1 : Mapping completed (DM_MAPIO_REMAPPED). > 1 : Reserved (undefined). Previously this was the same as '= 1'. o Reserve return values of 2 and above from target end_io functions for similar reasons. DM_ENDIO_INCOMPLETE is introduced for a return value of 1. Test results: I have tested by using the multipath target. I/Os succeed when valid paths exist. I/Os are queued in the multipath target when there are no valid paths and queue_if_no_path is set. I/Os fail when there are no valid paths and queue_if_no_path is not set. Signed-off-by: Kiyoshi Ueda Signed-off-by: Jun'ichi Nomura Signed-off-by: Alasdair G Kergon Cc: dm-devel@redhat.com Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/device-mapper.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 9194ff2d08c0..2e5c42346c38 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -39,7 +39,7 @@ typedef void (*dm_dtr_fn) (struct dm_target *ti); * The map function must return: * < 0: error * = 0: The target will handle the io by resubmitting it later - * > 0: simple remap complete + * = 1: simple remap complete */ typedef int (*dm_map_fn) (struct dm_target *ti, struct bio *bio, union map_info *map_context); -- cgit v1.2.3 From 81fdb096dbcedcc3b94c7e47b59362b5214891e2 Mon Sep 17 00:00:00 2001 From: Kiyoshi Ueda Date: Fri, 8 Dec 2006 02:41:07 -0800 Subject: [PATCH] dm: ioctl: add noflush suspend Provide a dm ioctl option to request noflush suspending. (See next patch for what this is for.) As the interface is extended, the version number is incremented. Other than accepting the new option through the interface, There is no change to existing behaviour. Test results: Confirmed the option is given from user-space correctly. Signed-off-by: Kiyoshi Ueda Signed-off-by: Jun'ichi Nomura Signed-off-by: Alasdair G Kergon Cc: dm-devel@redhat.com Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/dm-ioctl.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dm-ioctl.h b/include/linux/dm-ioctl.h index 8853fc4d1c5e..b93486107821 100644 --- a/include/linux/dm-ioctl.h +++ b/include/linux/dm-ioctl.h @@ -285,9 +285,9 @@ typedef char ioctl_struct[308]; #define DM_DEV_SET_GEOMETRY _IOWR(DM_IOCTL, DM_DEV_SET_GEOMETRY_CMD, struct dm_ioctl) #define DM_VERSION_MAJOR 4 -#define DM_VERSION_MINOR 10 +#define DM_VERSION_MINOR 11 #define DM_VERSION_PATCHLEVEL 0 -#define DM_VERSION_EXTRA "-ioctl (2006-09-14)" +#define DM_VERSION_EXTRA "-ioctl (2006-10-12)" /* Status bits */ #define DM_READONLY_FLAG (1 << 0) /* In/Out */ @@ -323,4 +323,9 @@ typedef char ioctl_struct[308]; */ #define DM_SKIP_LOCKFS_FLAG (1 << 10) /* In */ +/* + * Set this to suspend without flushing queued ios. + */ +#define DM_NOFLUSH_FLAG (1 << 11) /* In */ + #endif /* _LINUX_DM_IOCTL_H */ -- cgit v1.2.3 From 2e93ccc1933d08d32d9bde3784c3823e67b9b030 Mon Sep 17 00:00:00 2001 From: Kiyoshi Ueda Date: Fri, 8 Dec 2006 02:41:09 -0800 Subject: [PATCH] dm: suspend: add noflush pushback In device-mapper I/O is sometimes queued within targets for later processing. For example the multipath target can be configured to store I/O when no paths are available instead of returning it -EIO. This patch allows the device-mapper core to instruct a target to transfer the contents of any such in-target queue back into the core. This frees up the resources used by the target so the core can replace that target with an alternative one and then resend the I/O to it. Without this patch the only way to change the target in such circumstances involves returning the I/O with an error back to the filesystem/application. In the multipath case, this patch will let us add new paths for existing I/O to try after all the existing paths have failed. DMF_NOFLUSH_SUSPENDING ---------------------- If the DM_NOFLUSH_FLAG ioctl option is specified at suspend time, the DMF_NOFLUSH_SUSPENDING flag is set in md->flags during dm_suspend(). It is always cleared before dm_suspend() returns. The flag must be visible while the target is flushing pending I/Os so it is set before presuspend where the flush starts and unset after the wait for md->pending where the flush ends. Target drivers can check this flag by calling dm_noflush_suspending(). DM_MAPIO_REQUEUE / DM_ENDIO_REQUEUE ----------------------------------- A target's map() function can now return DM_MAPIO_REQUEUE to request the device mapper core queue the bio. Similarly, a target's end_io() function can return DM_ENDIO_REQUEUE to request the same. This has been labelled 'pushback'. The __map_bio() and clone_endio() functions in the core treat these return values as errors and call dec_pending() to end the I/O. dec_pending ----------- dec_pending() saves the pushback request in struct dm_io->error. Once all the split clones have ended, dec_pending() will put the original bio on the md->pushback list. Note that this supercedes any I/O errors. It is possible for the suspend with DM_NOFLUSH_FLAG to be aborted while in progress (e.g. by user interrupt). dec_pending() checks for this and returns -EIO if it happened. pushdback list and pushback_lock -------------------------------- The bio is queued on md->pushback temporarily in dec_pending(), and after all pending I/Os return, md->pushback is merged into md->deferred in dm_suspend() for re-issuing at resume time. md->pushback_lock protects md->pushback. The lock should be held with irq disabled because dec_pending() can be called from interrupt context. Queueing bios to md->pushback in dec_pending() must be done atomically with the check for DMF_NOFLUSH_SUSPENDING flag. So md->pushback_lock is held when checking the flag. Otherwise dec_pending() may queue a bio to md->pushback after the interrupted dm_suspend() flushes md->pushback. Then the bio would be left in md->pushback. Flag setting in dm_suspend() can be done without md->pushback_lock because the flag is checked only after presuspend and the set value is already made visible via the target's presuspend function. The flag can be checked without md->pushback_lock (e.g. the first part of the dec_pending() or target drivers), because the flag is checked again with md->pushback_lock held when the bio is really queued to md->pushback as described above. So even if the flag is cleared after the lockless checkings, the bio isn't left in md->pushback but returned to applications with -EIO. Other notes on the current patch -------------------------------- - md->pushback is added to the struct mapped_device instead of using md->deferred directly because md->io_lock which protects md->deferred is rw_semaphore and can't be used in interrupt context like dec_pending(), and md->io_lock protects the DMF_BLOCK_IO flag of md->flags too. - Don't issue lock_fs() in dm_suspend() if the DM_NOFLUSH_FLAG ioctl option is specified, because I/Os generated by lock_fs() would be pushed back and never return if there were no valid devices. - If an error occurs in dm_suspend() after the DMF_NOFLUSH_SUSPENDING flag is set, md->pushback must be flushed because I/Os may be queued to the list already. (flush_and_out label in dm_suspend()) Test results ------------ I have tested using multipath target with the next patch. The following tests are for regression/compatibility: - I/Os succeed when valid paths exist; - I/Os fail when there are no valid paths and queue_if_no_path is not set; - I/Os are queued in the multipath target when there are no valid paths and queue_if_no_path is set; - The queued I/Os above fail when suspend is issued without the DM_NOFLUSH_FLAG ioctl option. I/Os spanning 2 multipath targets also fail. The following tests are for the normal code path of new pushback feature: - Queued I/Os in the multipath target are flushed from the target but don't return when suspend is issued with the DM_NOFLUSH_FLAG ioctl option; - The I/Os above are queued in the multipath target again when resume is issued without path recovery; - The I/Os above succeed when resume is issued after path recovery or table load; - Queued I/Os in the multipath target succeed when resume is issued with the DM_NOFLUSH_FLAG ioctl option after table load. I/Os spanning 2 multipath targets also succeed. The following tests are for the error paths of the new pushback feature: - When the bdget_disk() fails in dm_suspend(), the DMF_NOFLUSH_SUSPENDING flag is cleared and I/Os already queued to the pushback list are flushed properly. - When suspend with the DM_NOFLUSH_FLAG ioctl option is interrupted, o I/Os which had already been queued to the pushback list at the time don't return, and are re-issued at resume time; o I/Os which hadn't been returned at the time return with EIO. Signed-off-by: Kiyoshi Ueda Signed-off-by: Jun'ichi Nomura Signed-off-by: Alasdair G Kergon Cc: dm-devel@redhat.com Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/device-mapper.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 2e5c42346c38..499f5373e213 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -40,6 +40,7 @@ typedef void (*dm_dtr_fn) (struct dm_target *ti); * < 0: error * = 0: The target will handle the io by resubmitting it later * = 1: simple remap complete + * = 2: The target wants to push back the io */ typedef int (*dm_map_fn) (struct dm_target *ti, struct bio *bio, union map_info *map_context); @@ -50,6 +51,7 @@ typedef int (*dm_map_fn) (struct dm_target *ti, struct bio *bio, * 0 : ended successfully * 1 : for some reason the io has still not completed (eg, * multipath target might want to requeue a failed io). + * 2 : The target wants to push back the io */ typedef int (*dm_endio_fn) (struct dm_target *ti, struct bio *bio, int error, @@ -188,6 +190,7 @@ int dm_wait_event(struct mapped_device *md, int event_nr); const char *dm_device_name(struct mapped_device *md); struct gendisk *dm_disk(struct mapped_device *md); int dm_suspended(struct mapped_device *md); +int dm_noflush_suspending(struct dm_target *ti); /* * Geometry functions. -- cgit v1.2.3 From dde5845a529ff753364a6d1aea61180946270bfa Mon Sep 17 00:00:00 2001 From: Jiri Kosina Date: Fri, 8 Dec 2006 18:40:44 +0100 Subject: [PATCH] Generic HID layer - code split The "big main" split of USB HID code into generic HID code and USB-transport specific HID handling. Signed-off-by: Jiri Kosina Signed-off-by: Marcel Holtmann Cc: Dmitry Torokhov Signed-off-by: Greg Kroah-Hartman --- include/linux/hid-debug.h | 757 ++++++++++++++++++++++++++++++++++++++++++++++ include/linux/hid.h | 540 +++++++++++++++++++++++++++++++++ 2 files changed, 1297 insertions(+) create mode 100644 include/linux/hid-debug.h create mode 100644 include/linux/hid.h (limited to 'include/linux') diff --git a/include/linux/hid-debug.h b/include/linux/hid-debug.h new file mode 100644 index 000000000000..f04d6d75c098 --- /dev/null +++ b/include/linux/hid-debug.h @@ -0,0 +1,757 @@ +/* + * $Id: hid-debug.h,v 1.8 2001/09/25 09:37:57 vojtech Exp $ + * + * (c) 1999 Andreas Gal + * (c) 2000-2001 Vojtech Pavlik + * + * Some debug stuff for the HID parser. + */ + +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + * Should you need to contact me, the author, you can do so either by + * e-mail - mail your message to , or by paper mail: + * Vojtech Pavlik, Simunkova 1594, Prague 8, 182 00 Czech Republic + */ + +#include + +struct hid_usage_entry { + unsigned page; + unsigned usage; + char *description; +}; + +static const struct hid_usage_entry hid_usage_table[] = { + { 0, 0, "Undefined" }, + { 1, 0, "GenericDesktop" }, + {0, 0x01, "Pointer"}, + {0, 0x02, "Mouse"}, + {0, 0x04, "Joystick"}, + {0, 0x05, "GamePad"}, + {0, 0x06, "Keyboard"}, + {0, 0x07, "Keypad"}, + {0, 0x08, "MultiAxis"}, + {0, 0x30, "X"}, + {0, 0x31, "Y"}, + {0, 0x32, "Z"}, + {0, 0x33, "Rx"}, + {0, 0x34, "Ry"}, + {0, 0x35, "Rz"}, + {0, 0x36, "Slider"}, + {0, 0x37, "Dial"}, + {0, 0x38, "Wheel"}, + {0, 0x39, "HatSwitch"}, + {0, 0x3a, "CountedBuffer"}, + {0, 0x3b, "ByteCount"}, + {0, 0x3c, "MotionWakeup"}, + {0, 0x3d, "Start"}, + {0, 0x3e, "Select"}, + {0, 0x40, "Vx"}, + {0, 0x41, "Vy"}, + {0, 0x42, "Vz"}, + {0, 0x43, "Vbrx"}, + {0, 0x44, "Vbry"}, + {0, 0x45, "Vbrz"}, + {0, 0x46, "Vno"}, + {0, 0x80, "SystemControl"}, + {0, 0x81, "SystemPowerDown"}, + {0, 0x82, "SystemSleep"}, + {0, 0x83, "SystemWakeUp"}, + {0, 0x84, "SystemContextMenu"}, + {0, 0x85, "SystemMainMenu"}, + {0, 0x86, "SystemAppMenu"}, + {0, 0x87, "SystemMenuHelp"}, + {0, 0x88, "SystemMenuExit"}, + {0, 0x89, "SystemMenuSelect"}, + {0, 0x8a, "SystemMenuRight"}, + {0, 0x8b, "SystemMenuLeft"}, + {0, 0x8c, "SystemMenuUp"}, + {0, 0x8d, "SystemMenuDown"}, + {0, 0x90, "D-PadUp"}, + {0, 0x91, "D-PadDown"}, + {0, 0x92, "D-PadRight"}, + {0, 0x93, "D-PadLeft"}, + { 2, 0, "Simulation" }, + {0, 0xb0, "Aileron"}, + {0, 0xb1, "AileronTrim"}, + {0, 0xb2, "Anti-Torque"}, + {0, 0xb3, "Autopilot"}, + {0, 0xb4, "Chaff"}, + {0, 0xb5, "Collective"}, + {0, 0xb6, "DiveBrake"}, + {0, 0xb7, "ElectronicCountermeasures"}, + {0, 0xb8, "Elevator"}, + {0, 0xb9, "ElevatorTrim"}, + {0, 0xba, "Rudder"}, + {0, 0xbb, "Throttle"}, + {0, 0xbc, "FlightCommunications"}, + {0, 0xbd, "FlareRelease"}, + {0, 0xbe, "LandingGear"}, + {0, 0xbf, "ToeBrake"}, + { 7, 0, "Keyboard" }, + { 8, 0, "LED" }, + {0, 0x01, "NumLock"}, + {0, 0x02, "CapsLock"}, + {0, 0x03, "ScrollLock"}, + {0, 0x04, "Compose"}, + {0, 0x05, "Kana"}, + {0, 0x4b, "GenericIndicator"}, + { 9, 0, "Button" }, + { 10, 0, "Ordinal" }, + { 12, 0, "Consumer" }, + {0, 0x238, "HorizontalWheel"}, + { 13, 0, "Digitizers" }, + {0, 0x01, "Digitizer"}, + {0, 0x02, "Pen"}, + {0, 0x03, "LightPen"}, + {0, 0x04, "TouchScreen"}, + {0, 0x05, "TouchPad"}, + {0, 0x20, "Stylus"}, + {0, 0x21, "Puck"}, + {0, 0x22, "Finger"}, + {0, 0x30, "TipPressure"}, + {0, 0x31, "BarrelPressure"}, + {0, 0x32, "InRange"}, + {0, 0x33, "Touch"}, + {0, 0x34, "UnTouch"}, + {0, 0x35, "Tap"}, + {0, 0x39, "TabletFunctionKey"}, + {0, 0x3a, "ProgramChangeKey"}, + {0, 0x3c, "Invert"}, + {0, 0x42, "TipSwitch"}, + {0, 0x43, "SecondaryTipSwitch"}, + {0, 0x44, "BarrelSwitch"}, + {0, 0x45, "Eraser"}, + {0, 0x46, "TabletPick"}, + { 15, 0, "PhysicalInterfaceDevice" }, + {0, 0x00, "Undefined"}, + {0, 0x01, "Physical_Interface_Device"}, + {0, 0x20, "Normal"}, + {0, 0x21, "Set_Effect_Report"}, + {0, 0x22, "Effect_Block_Index"}, + {0, 0x23, "Parameter_Block_Offset"}, + {0, 0x24, "ROM_Flag"}, + {0, 0x25, "Effect_Type"}, + {0, 0x26, "ET_Constant_Force"}, + {0, 0x27, "ET_Ramp"}, + {0, 0x28, "ET_Custom_Force_Data"}, + {0, 0x30, "ET_Square"}, + {0, 0x31, "ET_Sine"}, + {0, 0x32, "ET_Triangle"}, + {0, 0x33, "ET_Sawtooth_Up"}, + {0, 0x34, "ET_Sawtooth_Down"}, + {0, 0x40, "ET_Spring"}, + {0, 0x41, "ET_Damper"}, + {0, 0x42, "ET_Inertia"}, + {0, 0x43, "ET_Friction"}, + {0, 0x50, "Duration"}, + {0, 0x51, "Sample_Period"}, + {0, 0x52, "Gain"}, + {0, 0x53, "Trigger_Button"}, + {0, 0x54, "Trigger_Repeat_Interval"}, + {0, 0x55, "Axes_Enable"}, + {0, 0x56, "Direction_Enable"}, + {0, 0x57, "Direction"}, + {0, 0x58, "Type_Specific_Block_Offset"}, + {0, 0x59, "Block_Type"}, + {0, 0x5A, "Set_Envelope_Report"}, + {0, 0x5B, "Attack_Level"}, + {0, 0x5C, "Attack_Time"}, + {0, 0x5D, "Fade_Level"}, + {0, 0x5E, "Fade_Time"}, + {0, 0x5F, "Set_Condition_Report"}, + {0, 0x60, "CP_Offset"}, + {0, 0x61, "Positive_Coefficient"}, + {0, 0x62, "Negative_Coefficient"}, + {0, 0x63, "Positive_Saturation"}, + {0, 0x64, "Negative_Saturation"}, + {0, 0x65, "Dead_Band"}, + {0, 0x66, "Download_Force_Sample"}, + {0, 0x67, "Isoch_Custom_Force_Enable"}, + {0, 0x68, "Custom_Force_Data_Report"}, + {0, 0x69, "Custom_Force_Data"}, + {0, 0x6A, "Custom_Force_Vendor_Defined_Data"}, + {0, 0x6B, "Set_Custom_Force_Report"}, + {0, 0x6C, "Custom_Force_Data_Offset"}, + {0, 0x6D, "Sample_Count"}, + {0, 0x6E, "Set_Periodic_Report"}, + {0, 0x6F, "Offset"}, + {0, 0x70, "Magnitude"}, + {0, 0x71, "Phase"}, + {0, 0x72, "Period"}, + {0, 0x73, "Set_Constant_Force_Report"}, + {0, 0x74, "Set_Ramp_Force_Report"}, + {0, 0x75, "Ramp_Start"}, + {0, 0x76, "Ramp_End"}, + {0, 0x77, "Effect_Operation_Report"}, + {0, 0x78, "Effect_Operation"}, + {0, 0x79, "Op_Effect_Start"}, + {0, 0x7A, "Op_Effect_Start_Solo"}, + {0, 0x7B, "Op_Effect_Stop"}, + {0, 0x7C, "Loop_Count"}, + {0, 0x7D, "Device_Gain_Report"}, + {0, 0x7E, "Device_Gain"}, + {0, 0x7F, "PID_Pool_Report"}, + {0, 0x80, "RAM_Pool_Size"}, + {0, 0x81, "ROM_Pool_Size"}, + {0, 0x82, "ROM_Effect_Block_Count"}, + {0, 0x83, "Simultaneous_Effects_Max"}, + {0, 0x84, "Pool_Alignment"}, + {0, 0x85, "PID_Pool_Move_Report"}, + {0, 0x86, "Move_Source"}, + {0, 0x87, "Move_Destination"}, + {0, 0x88, "Move_Length"}, + {0, 0x89, "PID_Block_Load_Report"}, + {0, 0x8B, "Block_Load_Status"}, + {0, 0x8C, "Block_Load_Success"}, + {0, 0x8D, "Block_Load_Full"}, + {0, 0x8E, "Block_Load_Error"}, + {0, 0x8F, "Block_Handle"}, + {0, 0x90, "PID_Block_Free_Report"}, + {0, 0x91, "Type_Specific_Block_Handle"}, + {0, 0x92, "PID_State_Report"}, + {0, 0x94, "Effect_Playing"}, + {0, 0x95, "PID_Device_Control_Report"}, + {0, 0x96, "PID_Device_Control"}, + {0, 0x97, "DC_Enable_Actuators"}, + {0, 0x98, "DC_Disable_Actuators"}, + {0, 0x99, "DC_Stop_All_Effects"}, + {0, 0x9A, "DC_Device_Reset"}, + {0, 0x9B, "DC_Device_Pause"}, + {0, 0x9C, "DC_Device_Continue"}, + {0, 0x9F, "Device_Paused"}, + {0, 0xA0, "Actuators_Enabled"}, + {0, 0xA4, "Safety_Switch"}, + {0, 0xA5, "Actuator_Override_Switch"}, + {0, 0xA6, "Actuator_Power"}, + {0, 0xA7, "Start_Delay"}, + {0, 0xA8, "Parameter_Block_Size"}, + {0, 0xA9, "Device_Managed_Pool"}, + {0, 0xAA, "Shared_Parameter_Blocks"}, + {0, 0xAB, "Create_New_Effect_Report"}, + {0, 0xAC, "RAM_Pool_Available"}, + { 0x84, 0, "Power Device" }, + { 0x84, 0x02, "PresentStatus" }, + { 0x84, 0x03, "ChangeStatus" }, + { 0x84, 0x04, "UPS" }, + { 0x84, 0x05, "PowerSupply" }, + { 0x84, 0x10, "BatterySystem" }, + { 0x84, 0x11, "BatterySystemID" }, + { 0x84, 0x12, "Battery" }, + { 0x84, 0x13, "BatteryID" }, + { 0x84, 0x14, "Charger" }, + { 0x84, 0x15, "ChargerID" }, + { 0x84, 0x16, "PowerConverter" }, + { 0x84, 0x17, "PowerConverterID" }, + { 0x84, 0x18, "OutletSystem" }, + { 0x84, 0x19, "OutletSystemID" }, + { 0x84, 0x1a, "Input" }, + { 0x84, 0x1b, "InputID" }, + { 0x84, 0x1c, "Output" }, + { 0x84, 0x1d, "OutputID" }, + { 0x84, 0x1e, "Flow" }, + { 0x84, 0x1f, "FlowID" }, + { 0x84, 0x20, "Outlet" }, + { 0x84, 0x21, "OutletID" }, + { 0x84, 0x22, "Gang" }, + { 0x84, 0x24, "PowerSummary" }, + { 0x84, 0x25, "PowerSummaryID" }, + { 0x84, 0x30, "Voltage" }, + { 0x84, 0x31, "Current" }, + { 0x84, 0x32, "Frequency" }, + { 0x84, 0x33, "ApparentPower" }, + { 0x84, 0x35, "PercentLoad" }, + { 0x84, 0x40, "ConfigVoltage" }, + { 0x84, 0x41, "ConfigCurrent" }, + { 0x84, 0x43, "ConfigApparentPower" }, + { 0x84, 0x53, "LowVoltageTransfer" }, + { 0x84, 0x54, "HighVoltageTransfer" }, + { 0x84, 0x56, "DelayBeforeStartup" }, + { 0x84, 0x57, "DelayBeforeShutdown" }, + { 0x84, 0x58, "Test" }, + { 0x84, 0x5a, "AudibleAlarmControl" }, + { 0x84, 0x60, "Present" }, + { 0x84, 0x61, "Good" }, + { 0x84, 0x62, "InternalFailure" }, + { 0x84, 0x65, "Overload" }, + { 0x84, 0x66, "OverCharged" }, + { 0x84, 0x67, "OverTemperature" }, + { 0x84, 0x68, "ShutdownRequested" }, + { 0x84, 0x69, "ShutdownImminent" }, + { 0x84, 0x6b, "SwitchOn/Off" }, + { 0x84, 0x6c, "Switchable" }, + { 0x84, 0x6d, "Used" }, + { 0x84, 0x6e, "Boost" }, + { 0x84, 0x73, "CommunicationLost" }, + { 0x84, 0xfd, "iManufacturer" }, + { 0x84, 0xfe, "iProduct" }, + { 0x84, 0xff, "iSerialNumber" }, + { 0x85, 0, "Battery System" }, + { 0x85, 0x01, "SMBBatteryMode" }, + { 0x85, 0x02, "SMBBatteryStatus" }, + { 0x85, 0x03, "SMBAlarmWarning" }, + { 0x85, 0x04, "SMBChargerMode" }, + { 0x85, 0x05, "SMBChargerStatus" }, + { 0x85, 0x06, "SMBChargerSpecInfo" }, + { 0x85, 0x07, "SMBSelectorState" }, + { 0x85, 0x08, "SMBSelectorPresets" }, + { 0x85, 0x09, "SMBSelectorInfo" }, + { 0x85, 0x29, "RemainingCapacityLimit" }, + { 0x85, 0x2c, "CapacityMode" }, + { 0x85, 0x42, "BelowRemainingCapacityLimit" }, + { 0x85, 0x44, "Charging" }, + { 0x85, 0x45, "Discharging" }, + { 0x85, 0x4b, "NeedReplacement" }, + { 0x85, 0x66, "RemainingCapacity" }, + { 0x85, 0x68, "RunTimeToEmpty" }, + { 0x85, 0x6a, "AverageTimeToFull" }, + { 0x85, 0x83, "DesignCapacity" }, + { 0x85, 0x85, "ManufacturerDate" }, + { 0x85, 0x89, "iDeviceChemistry" }, + { 0x85, 0x8b, "Rechargable" }, + { 0x85, 0x8f, "iOEMInformation" }, + { 0x85, 0x8d, "CapacityGranularity1" }, + { 0x85, 0xd0, "ACPresent" }, + /* pages 0xff00 to 0xffff are vendor-specific */ + { 0xffff, 0, "Vendor-specific-FF" }, + { 0, 0, NULL } +}; + +static void resolv_usage_page(unsigned page) { + const struct hid_usage_entry *p; + + for (p = hid_usage_table; p->description; p++) + if (p->page == page) { + printk("%s", p->description); + return; + } + printk("%04x", page); +} + +static void resolv_usage(unsigned usage) { + const struct hid_usage_entry *p; + + resolv_usage_page(usage >> 16); + printk("."); + for (p = hid_usage_table; p->description; p++) + if (p->page == (usage >> 16)) { + for(++p; p->description && p->usage != 0; p++) + if (p->usage == (usage & 0xffff)) { + printk("%s", p->description); + return; + } + break; + } + printk("%04x", usage & 0xffff); +} + +__inline__ static void tab(int n) { + while (n--) printk(" "); +} + +static void hid_dump_field(struct hid_field *field, int n) { + int j; + + if (field->physical) { + tab(n); + printk("Physical("); + resolv_usage(field->physical); printk(")\n"); + } + if (field->logical) { + tab(n); + printk("Logical("); + resolv_usage(field->logical); printk(")\n"); + } + tab(n); printk("Usage(%d)\n", field->maxusage); + for (j = 0; j < field->maxusage; j++) { + tab(n+2);resolv_usage(field->usage[j].hid); printk("\n"); + } + if (field->logical_minimum != field->logical_maximum) { + tab(n); printk("Logical Minimum(%d)\n", field->logical_minimum); + tab(n); printk("Logical Maximum(%d)\n", field->logical_maximum); + } + if (field->physical_minimum != field->physical_maximum) { + tab(n); printk("Physical Minimum(%d)\n", field->physical_minimum); + tab(n); printk("Physical Maximum(%d)\n", field->physical_maximum); + } + if (field->unit_exponent) { + tab(n); printk("Unit Exponent(%d)\n", field->unit_exponent); + } + if (field->unit) { + char *systems[5] = { "None", "SI Linear", "SI Rotation", "English Linear", "English Rotation" }; + char *units[5][8] = { + { "None", "None", "None", "None", "None", "None", "None", "None" }, + { "None", "Centimeter", "Gram", "Seconds", "Kelvin", "Ampere", "Candela", "None" }, + { "None", "Radians", "Gram", "Seconds", "Kelvin", "Ampere", "Candela", "None" }, + { "None", "Inch", "Slug", "Seconds", "Fahrenheit", "Ampere", "Candela", "None" }, + { "None", "Degrees", "Slug", "Seconds", "Fahrenheit", "Ampere", "Candela", "None" } + }; + + int i; + int sys; + __u32 data = field->unit; + + /* First nibble tells us which system we're in. */ + sys = data & 0xf; + data >>= 4; + + if(sys > 4) { + tab(n); printk("Unit(Invalid)\n"); + } + else { + int earlier_unit = 0; + + tab(n); printk("Unit(%s : ", systems[sys]); + + for (i=1 ; i>= 4; + if (nibble != 0) { + if(earlier_unit++ > 0) + printk("*"); + printk("%s", units[sys][i]); + if(nibble != 1) { + /* This is a _signed_ nibble(!) */ + + int val = nibble & 0x7; + if(nibble & 0x08) + val = -((0x7 & ~val) +1); + printk("^%d", val); + } + } + } + printk(")\n"); + } + } + tab(n); printk("Report Size(%u)\n", field->report_size); + tab(n); printk("Report Count(%u)\n", field->report_count); + tab(n); printk("Report Offset(%u)\n", field->report_offset); + + tab(n); printk("Flags( "); + j = field->flags; + printk("%s", HID_MAIN_ITEM_CONSTANT & j ? "Constant " : ""); + printk("%s", HID_MAIN_ITEM_VARIABLE & j ? "Variable " : "Array "); + printk("%s", HID_MAIN_ITEM_RELATIVE & j ? "Relative " : "Absolute "); + printk("%s", HID_MAIN_ITEM_WRAP & j ? "Wrap " : ""); + printk("%s", HID_MAIN_ITEM_NONLINEAR & j ? "NonLinear " : ""); + printk("%s", HID_MAIN_ITEM_NO_PREFERRED & j ? "NoPrefferedState " : ""); + printk("%s", HID_MAIN_ITEM_NULL_STATE & j ? "NullState " : ""); + printk("%s", HID_MAIN_ITEM_VOLATILE & j ? "Volatile " : ""); + printk("%s", HID_MAIN_ITEM_BUFFERED_BYTE & j ? "BufferedByte " : ""); + printk(")\n"); +} + +static void __attribute__((unused)) hid_dump_device(struct hid_device *device) { + struct hid_report_enum *report_enum; + struct hid_report *report; + struct list_head *list; + unsigned i,k; + static char *table[] = {"INPUT", "OUTPUT", "FEATURE"}; + + for (i = 0; i < HID_REPORT_TYPES; i++) { + report_enum = device->report_enum + i; + list = report_enum->report_list.next; + while (list != &report_enum->report_list) { + report = (struct hid_report *) list; + tab(2); + printk("%s", table[i]); + if (report->id) + printk("(%d)", report->id); + printk("[%s]", table[report->type]); + printk("\n"); + for (k = 0; k < report->maxfield; k++) { + tab(4); + printk("Field(%d)\n", k); + hid_dump_field(report->field[k], 6); + } + list = list->next; + } + } +} + +static void __attribute__((unused)) hid_dump_input(struct hid_usage *usage, __s32 value) { + printk("hid-debug: input "); + resolv_usage(usage->hid); + printk(" = %d\n", value); +} + + +static char *events[EV_MAX + 1] = { + [EV_SYN] = "Sync", [EV_KEY] = "Key", + [EV_REL] = "Relative", [EV_ABS] = "Absolute", + [EV_MSC] = "Misc", [EV_LED] = "LED", + [EV_SND] = "Sound", [EV_REP] = "Repeat", + [EV_FF] = "ForceFeedback", [EV_PWR] = "Power", + [EV_FF_STATUS] = "ForceFeedbackStatus", +}; + +static char *syncs[2] = { + [SYN_REPORT] = "Report", [SYN_CONFIG] = "Config", +}; +static char *keys[KEY_MAX + 1] = { + [KEY_RESERVED] = "Reserved", [KEY_ESC] = "Esc", + [KEY_1] = "1", [KEY_2] = "2", + [KEY_3] = "3", [KEY_4] = "4", + [KEY_5] = "5", [KEY_6] = "6", + [KEY_7] = "7", [KEY_8] = "8", + [KEY_9] = "9", [KEY_0] = "0", + [KEY_MINUS] = "Minus", [KEY_EQUAL] = "Equal", + [KEY_BACKSPACE] = "Backspace", [KEY_TAB] = "Tab", + [KEY_Q] = "Q", [KEY_W] = "W", + [KEY_E] = "E", [KEY_R] = "R", + [KEY_T] = "T", [KEY_Y] = "Y", + [KEY_U] = "U", [KEY_I] = "I", + [KEY_O] = "O", [KEY_P] = "P", + [KEY_LEFTBRACE] = "LeftBrace", [KEY_RIGHTBRACE] = "RightBrace", + [KEY_ENTER] = "Enter", [KEY_LEFTCTRL] = "LeftControl", + [KEY_A] = "A", [KEY_S] = "S", + [KEY_D] = "D", [KEY_F] = "F", + [KEY_G] = "G", [KEY_H] = "H", + [KEY_J] = "J", [KEY_K] = "K", + [KEY_L] = "L", [KEY_SEMICOLON] = "Semicolon", + [KEY_APOSTROPHE] = "Apostrophe", [KEY_GRAVE] = "Grave", + [KEY_LEFTSHIFT] = "LeftShift", [KEY_BACKSLASH] = "BackSlash", + [KEY_Z] = "Z", [KEY_X] = "X", + [KEY_C] = "C", [KEY_V] = "V", + [KEY_B] = "B", [KEY_N] = "N", + [KEY_M] = "M", [KEY_COMMA] = "Comma", + [KEY_DOT] = "Dot", [KEY_SLASH] = "Slash", + [KEY_RIGHTSHIFT] = "RightShift", [KEY_KPASTERISK] = "KPAsterisk", + [KEY_LEFTALT] = "LeftAlt", [KEY_SPACE] = "Space", + [KEY_CAPSLOCK] = "CapsLock", [KEY_F1] = "F1", + [KEY_F2] = "F2", [KEY_F3] = "F3", + [KEY_F4] = "F4", [KEY_F5] = "F5", + [KEY_F6] = "F6", [KEY_F7] = "F7", + [KEY_F8] = "F8", [KEY_F9] = "F9", + [KEY_F10] = "F10", [KEY_NUMLOCK] = "NumLock", + [KEY_SCROLLLOCK] = "ScrollLock", [KEY_KP7] = "KP7", + [KEY_KP8] = "KP8", [KEY_KP9] = "KP9", + [KEY_KPMINUS] = "KPMinus", [KEY_KP4] = "KP4", + [KEY_KP5] = "KP5", [KEY_KP6] = "KP6", + [KEY_KPPLUS] = "KPPlus", [KEY_KP1] = "KP1", + [KEY_KP2] = "KP2", [KEY_KP3] = "KP3", + [KEY_KP0] = "KP0", [KEY_KPDOT] = "KPDot", + [KEY_ZENKAKUHANKAKU] = "Zenkaku/Hankaku", [KEY_102ND] = "102nd", + [KEY_F11] = "F11", [KEY_F12] = "F12", + [KEY_RO] = "RO", [KEY_KATAKANA] = "Katakana", + [KEY_HIRAGANA] = "HIRAGANA", [KEY_HENKAN] = "Henkan", + [KEY_KATAKANAHIRAGANA] = "Katakana/Hiragana", [KEY_MUHENKAN] = "Muhenkan", + [KEY_KPJPCOMMA] = "KPJpComma", [KEY_KPENTER] = "KPEnter", + [KEY_RIGHTCTRL] = "RightCtrl", [KEY_KPSLASH] = "KPSlash", + [KEY_SYSRQ] = "SysRq", [KEY_RIGHTALT] = "RightAlt", + [KEY_LINEFEED] = "LineFeed", [KEY_HOME] = "Home", + [KEY_UP] = "Up", [KEY_PAGEUP] = "PageUp", + [KEY_LEFT] = "Left", [KEY_RIGHT] = "Right", + [KEY_END] = "End", [KEY_DOWN] = "Down", + [KEY_PAGEDOWN] = "PageDown", [KEY_INSERT] = "Insert", + [KEY_DELETE] = "Delete", [KEY_MACRO] = "Macro", + [KEY_MUTE] = "Mute", [KEY_VOLUMEDOWN] = "VolumeDown", + [KEY_VOLUMEUP] = "VolumeUp", [KEY_POWER] = "Power", + [KEY_KPEQUAL] = "KPEqual", [KEY_KPPLUSMINUS] = "KPPlusMinus", + [KEY_PAUSE] = "Pause", [KEY_KPCOMMA] = "KPComma", + [KEY_HANGUEL] = "Hangeul", [KEY_HANJA] = "Hanja", + [KEY_YEN] = "Yen", [KEY_LEFTMETA] = "LeftMeta", + [KEY_RIGHTMETA] = "RightMeta", [KEY_COMPOSE] = "Compose", + [KEY_STOP] = "Stop", [KEY_AGAIN] = "Again", + [KEY_PROPS] = "Props", [KEY_UNDO] = "Undo", + [KEY_FRONT] = "Front", [KEY_COPY] = "Copy", + [KEY_OPEN] = "Open", [KEY_PASTE] = "Paste", + [KEY_FIND] = "Find", [KEY_CUT] = "Cut", + [KEY_HELP] = "Help", [KEY_MENU] = "Menu", + [KEY_CALC] = "Calc", [KEY_SETUP] = "Setup", + [KEY_SLEEP] = "Sleep", [KEY_WAKEUP] = "WakeUp", + [KEY_FILE] = "File", [KEY_SENDFILE] = "SendFile", + [KEY_DELETEFILE] = "DeleteFile", [KEY_XFER] = "X-fer", + [KEY_PROG1] = "Prog1", [KEY_PROG2] = "Prog2", + [KEY_WWW] = "WWW", [KEY_MSDOS] = "MSDOS", + [KEY_COFFEE] = "Coffee", [KEY_DIRECTION] = "Direction", + [KEY_CYCLEWINDOWS] = "CycleWindows", [KEY_MAIL] = "Mail", + [KEY_BOOKMARKS] = "Bookmarks", [KEY_COMPUTER] = "Computer", + [KEY_BACK] = "Back", [KEY_FORWARD] = "Forward", + [KEY_CLOSECD] = "CloseCD", [KEY_EJECTCD] = "EjectCD", + [KEY_EJECTCLOSECD] = "EjectCloseCD", [KEY_NEXTSONG] = "NextSong", + [KEY_PLAYPAUSE] = "PlayPause", [KEY_PREVIOUSSONG] = "PreviousSong", + [KEY_STOPCD] = "StopCD", [KEY_RECORD] = "Record", + [KEY_REWIND] = "Rewind", [KEY_PHONE] = "Phone", + [KEY_ISO] = "ISOKey", [KEY_CONFIG] = "Config", + [KEY_HOMEPAGE] = "HomePage", [KEY_REFRESH] = "Refresh", + [KEY_EXIT] = "Exit", [KEY_MOVE] = "Move", + [KEY_EDIT] = "Edit", [KEY_SCROLLUP] = "ScrollUp", + [KEY_SCROLLDOWN] = "ScrollDown", [KEY_KPLEFTPAREN] = "KPLeftParenthesis", + [KEY_KPRIGHTPAREN] = "KPRightParenthesis", [KEY_NEW] = "New", + [KEY_REDO] = "Redo", [KEY_F13] = "F13", + [KEY_F14] = "F14", [KEY_F15] = "F15", + [KEY_F16] = "F16", [KEY_F17] = "F17", + [KEY_F18] = "F18", [KEY_F19] = "F19", + [KEY_F20] = "F20", [KEY_F21] = "F21", + [KEY_F22] = "F22", [KEY_F23] = "F23", + [KEY_F24] = "F24", [KEY_PLAYCD] = "PlayCD", + [KEY_PAUSECD] = "PauseCD", [KEY_PROG3] = "Prog3", + [KEY_PROG4] = "Prog4", [KEY_SUSPEND] = "Suspend", + [KEY_CLOSE] = "Close", [KEY_PLAY] = "Play", + [KEY_FASTFORWARD] = "FastForward", [KEY_BASSBOOST] = "BassBoost", + [KEY_PRINT] = "Print", [KEY_HP] = "HP", + [KEY_CAMERA] = "Camera", [KEY_SOUND] = "Sound", + [KEY_QUESTION] = "Question", [KEY_EMAIL] = "Email", + [KEY_CHAT] = "Chat", [KEY_SEARCH] = "Search", + [KEY_CONNECT] = "Connect", [KEY_FINANCE] = "Finance", + [KEY_SPORT] = "Sport", [KEY_SHOP] = "Shop", + [KEY_ALTERASE] = "AlternateErase", [KEY_CANCEL] = "Cancel", + [KEY_BRIGHTNESSDOWN] = "BrightnessDown", [KEY_BRIGHTNESSUP] = "BrightnessUp", + [KEY_MEDIA] = "Media", [KEY_UNKNOWN] = "Unknown", + [BTN_0] = "Btn0", [BTN_1] = "Btn1", + [BTN_2] = "Btn2", [BTN_3] = "Btn3", + [BTN_4] = "Btn4", [BTN_5] = "Btn5", + [BTN_6] = "Btn6", [BTN_7] = "Btn7", + [BTN_8] = "Btn8", [BTN_9] = "Btn9", + [BTN_LEFT] = "LeftBtn", [BTN_RIGHT] = "RightBtn", + [BTN_MIDDLE] = "MiddleBtn", [BTN_SIDE] = "SideBtn", + [BTN_EXTRA] = "ExtraBtn", [BTN_FORWARD] = "ForwardBtn", + [BTN_BACK] = "BackBtn", [BTN_TASK] = "TaskBtn", + [BTN_TRIGGER] = "Trigger", [BTN_THUMB] = "ThumbBtn", + [BTN_THUMB2] = "ThumbBtn2", [BTN_TOP] = "TopBtn", + [BTN_TOP2] = "TopBtn2", [BTN_PINKIE] = "PinkieBtn", + [BTN_BASE] = "BaseBtn", [BTN_BASE2] = "BaseBtn2", + [BTN_BASE3] = "BaseBtn3", [BTN_BASE4] = "BaseBtn4", + [BTN_BASE5] = "BaseBtn5", [BTN_BASE6] = "BaseBtn6", + [BTN_DEAD] = "BtnDead", [BTN_A] = "BtnA", + [BTN_B] = "BtnB", [BTN_C] = "BtnC", + [BTN_X] = "BtnX", [BTN_Y] = "BtnY", + [BTN_Z] = "BtnZ", [BTN_TL] = "BtnTL", + [BTN_TR] = "BtnTR", [BTN_TL2] = "BtnTL2", + [BTN_TR2] = "BtnTR2", [BTN_SELECT] = "BtnSelect", + [BTN_START] = "BtnStart", [BTN_MODE] = "BtnMode", + [BTN_THUMBL] = "BtnThumbL", [BTN_THUMBR] = "BtnThumbR", + [BTN_TOOL_PEN] = "ToolPen", [BTN_TOOL_RUBBER] = "ToolRubber", + [BTN_TOOL_BRUSH] = "ToolBrush", [BTN_TOOL_PENCIL] = "ToolPencil", + [BTN_TOOL_AIRBRUSH] = "ToolAirbrush", [BTN_TOOL_FINGER] = "ToolFinger", + [BTN_TOOL_MOUSE] = "ToolMouse", [BTN_TOOL_LENS] = "ToolLens", + [BTN_TOUCH] = "Touch", [BTN_STYLUS] = "Stylus", + [BTN_STYLUS2] = "Stylus2", [BTN_TOOL_DOUBLETAP] = "ToolDoubleTap", + [BTN_TOOL_TRIPLETAP] = "ToolTripleTap", [BTN_GEAR_DOWN] = "WheelBtn", + [BTN_GEAR_UP] = "Gear up", [KEY_OK] = "Ok", + [KEY_SELECT] = "Select", [KEY_GOTO] = "Goto", + [KEY_CLEAR] = "Clear", [KEY_POWER2] = "Power2", + [KEY_OPTION] = "Option", [KEY_INFO] = "Info", + [KEY_TIME] = "Time", [KEY_VENDOR] = "Vendor", + [KEY_ARCHIVE] = "Archive", [KEY_PROGRAM] = "Program", + [KEY_CHANNEL] = "Channel", [KEY_FAVORITES] = "Favorites", + [KEY_EPG] = "EPG", [KEY_PVR] = "PVR", + [KEY_MHP] = "MHP", [KEY_LANGUAGE] = "Language", + [KEY_TITLE] = "Title", [KEY_SUBTITLE] = "Subtitle", + [KEY_ANGLE] = "Angle", [KEY_ZOOM] = "Zoom", + [KEY_MODE] = "Mode", [KEY_KEYBOARD] = "Keyboard", + [KEY_SCREEN] = "Screen", [KEY_PC] = "PC", + [KEY_TV] = "TV", [KEY_TV2] = "TV2", + [KEY_VCR] = "VCR", [KEY_VCR2] = "VCR2", + [KEY_SAT] = "Sat", [KEY_SAT2] = "Sat2", + [KEY_CD] = "CD", [KEY_TAPE] = "Tape", + [KEY_RADIO] = "Radio", [KEY_TUNER] = "Tuner", + [KEY_PLAYER] = "Player", [KEY_TEXT] = "Text", + [KEY_DVD] = "DVD", [KEY_AUX] = "Aux", + [KEY_MP3] = "MP3", [KEY_AUDIO] = "Audio", + [KEY_VIDEO] = "Video", [KEY_DIRECTORY] = "Directory", + [KEY_LIST] = "List", [KEY_MEMO] = "Memo", + [KEY_CALENDAR] = "Calendar", [KEY_RED] = "Red", + [KEY_GREEN] = "Green", [KEY_YELLOW] = "Yellow", + [KEY_BLUE] = "Blue", [KEY_CHANNELUP] = "ChannelUp", + [KEY_CHANNELDOWN] = "ChannelDown", [KEY_FIRST] = "First", + [KEY_LAST] = "Last", [KEY_AB] = "AB", + [KEY_NEXT] = "Next", [KEY_RESTART] = "Restart", + [KEY_SLOW] = "Slow", [KEY_SHUFFLE] = "Shuffle", + [KEY_BREAK] = "Break", [KEY_PREVIOUS] = "Previous", + [KEY_DIGITS] = "Digits", [KEY_TEEN] = "TEEN", + [KEY_TWEN] = "TWEN", [KEY_DEL_EOL] = "DeleteEOL", + [KEY_DEL_EOS] = "DeleteEOS", [KEY_INS_LINE] = "InsertLine", + [KEY_DEL_LINE] = "DeleteLine", + [KEY_SEND] = "Send", [KEY_REPLY] = "Reply", + [KEY_FORWARDMAIL] = "ForwardMail", [KEY_SAVE] = "Save", + [KEY_DOCUMENTS] = "Documents", + [KEY_FN] = "Fn", [KEY_FN_ESC] = "Fn+ESC", + [KEY_FN_1] = "Fn+1", [KEY_FN_2] = "Fn+2", + [KEY_FN_B] = "Fn+B", [KEY_FN_D] = "Fn+D", + [KEY_FN_E] = "Fn+E", [KEY_FN_F] = "Fn+F", + [KEY_FN_S] = "Fn+S", + [KEY_FN_F1] = "Fn+F1", [KEY_FN_F2] = "Fn+F2", + [KEY_FN_F3] = "Fn+F3", [KEY_FN_F4] = "Fn+F4", + [KEY_FN_F5] = "Fn+F5", [KEY_FN_F6] = "Fn+F6", + [KEY_FN_F7] = "Fn+F7", [KEY_FN_F8] = "Fn+F8", + [KEY_FN_F9] = "Fn+F9", [KEY_FN_F10] = "Fn+F10", + [KEY_FN_F11] = "Fn+F11", [KEY_FN_F12] = "Fn+F12", + [KEY_KBDILLUMTOGGLE] = "KbdIlluminationToggle", + [KEY_KBDILLUMDOWN] = "KbdIlluminationDown", + [KEY_KBDILLUMUP] = "KbdIlluminationUp", + [KEY_SWITCHVIDEOMODE] = "SwitchVideoMode", +}; + +static char *relatives[REL_MAX + 1] = { + [REL_X] = "X", [REL_Y] = "Y", + [REL_Z] = "Z", [REL_HWHEEL] = "HWheel", + [REL_DIAL] = "Dial", [REL_WHEEL] = "Wheel", + [REL_MISC] = "Misc", +}; + +static char *absolutes[ABS_MAX + 1] = { + [ABS_X] = "X", [ABS_Y] = "Y", + [ABS_Z] = "Z", [ABS_RX] = "Rx", + [ABS_RY] = "Ry", [ABS_RZ] = "Rz", + [ABS_THROTTLE] = "Throttle", [ABS_RUDDER] = "Rudder", + [ABS_WHEEL] = "Wheel", [ABS_GAS] = "Gas", + [ABS_BRAKE] = "Brake", [ABS_HAT0X] = "Hat0X", + [ABS_HAT0Y] = "Hat0Y", [ABS_HAT1X] = "Hat1X", + [ABS_HAT1Y] = "Hat1Y", [ABS_HAT2X] = "Hat2X", + [ABS_HAT2Y] = "Hat2Y", [ABS_HAT3X] = "Hat3X", + [ABS_HAT3Y] = "Hat 3Y", [ABS_PRESSURE] = "Pressure", + [ABS_DISTANCE] = "Distance", [ABS_TILT_X] = "XTilt", + [ABS_TILT_Y] = "YTilt", [ABS_TOOL_WIDTH] = "Tool Width", + [ABS_VOLUME] = "Volume", [ABS_MISC] = "Misc", +}; + +static char *misc[MSC_MAX + 1] = { + [MSC_SERIAL] = "Serial", [MSC_PULSELED] = "Pulseled", + [MSC_GESTURE] = "Gesture", [MSC_RAW] = "RawData" +}; + +static char *leds[LED_MAX + 1] = { + [LED_NUML] = "NumLock", [LED_CAPSL] = "CapsLock", + [LED_SCROLLL] = "ScrollLock", [LED_COMPOSE] = "Compose", + [LED_KANA] = "Kana", [LED_SLEEP] = "Sleep", + [LED_SUSPEND] = "Suspend", [LED_MUTE] = "Mute", + [LED_MISC] = "Misc", +}; + +static char *repeats[REP_MAX + 1] = { + [REP_DELAY] = "Delay", [REP_PERIOD] = "Period" +}; + +static char *sounds[SND_MAX + 1] = { + [SND_CLICK] = "Click", [SND_BELL] = "Bell", + [SND_TONE] = "Tone" +}; + +static char **names[EV_MAX + 1] = { + [EV_SYN] = syncs, [EV_KEY] = keys, + [EV_REL] = relatives, [EV_ABS] = absolutes, + [EV_MSC] = misc, [EV_LED] = leds, + [EV_SND] = sounds, [EV_REP] = repeats, +}; + +static void __attribute__((unused)) resolv_event(__u8 type, __u16 code) { + + printk("%s.%s", events[type] ? events[type] : "?", + names[type] ? (names[type][code] ? names[type][code] : "?") : "?"); +} diff --git a/include/linux/hid.h b/include/linux/hid.h new file mode 100644 index 000000000000..ee567ae6fec1 --- /dev/null +++ b/include/linux/hid.h @@ -0,0 +1,540 @@ +#ifndef __HID_H +#define __HID_H + +/* + * $Id: hid.h,v 1.24 2001/12/27 10:37:41 vojtech Exp $ + * + * Copyright (c) 1999 Andreas Gal + * Copyright (c) 2000-2001 Vojtech Pavlik + * Copyright (c) 2006 Jiri Kosina + */ + +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + * Should you need to contact me, the author, you can do so either by + * e-mail - mail your message to , or by paper mail: + * Vojtech Pavlik, Simunkova 1594, Prague 8, 182 00 Czech Republic + */ + +#include +#include +#include +#include +#include +#include + +/* + * USB HID (Human Interface Device) interface class code + */ + +#define USB_INTERFACE_CLASS_HID 3 + +/* + * USB HID interface subclass and protocol codes + */ + +#define USB_INTERFACE_SUBCLASS_BOOT 1 +#define USB_INTERFACE_PROTOCOL_KEYBOARD 1 +#define USB_INTERFACE_PROTOCOL_MOUSE 2 + +/* + * HID class requests + */ + +#define HID_REQ_GET_REPORT 0x01 +#define HID_REQ_GET_IDLE 0x02 +#define HID_REQ_GET_PROTOCOL 0x03 +#define HID_REQ_SET_REPORT 0x09 +#define HID_REQ_SET_IDLE 0x0A +#define HID_REQ_SET_PROTOCOL 0x0B + +/* + * HID class descriptor types + */ + +#define HID_DT_HID (USB_TYPE_CLASS | 0x01) +#define HID_DT_REPORT (USB_TYPE_CLASS | 0x02) +#define HID_DT_PHYSICAL (USB_TYPE_CLASS | 0x03) + +/* + * We parse each description item into this structure. Short items data + * values are expanded to 32-bit signed int, long items contain a pointer + * into the data area. + */ + +struct hid_item { + unsigned format; + __u8 size; + __u8 type; + __u8 tag; + union { + __u8 u8; + __s8 s8; + __u16 u16; + __s16 s16; + __u32 u32; + __s32 s32; + __u8 *longdata; + } data; +}; + +/* + * HID report item format + */ + +#define HID_ITEM_FORMAT_SHORT 0 +#define HID_ITEM_FORMAT_LONG 1 + +/* + * Special tag indicating long items + */ + +#define HID_ITEM_TAG_LONG 15 + +/* + * HID report descriptor item type (prefix bit 2,3) + */ + +#define HID_ITEM_TYPE_MAIN 0 +#define HID_ITEM_TYPE_GLOBAL 1 +#define HID_ITEM_TYPE_LOCAL 2 +#define HID_ITEM_TYPE_RESERVED 3 + +/* + * HID report descriptor main item tags + */ + +#define HID_MAIN_ITEM_TAG_INPUT 8 +#define HID_MAIN_ITEM_TAG_OUTPUT 9 +#define HID_MAIN_ITEM_TAG_FEATURE 11 +#define HID_MAIN_ITEM_TAG_BEGIN_COLLECTION 10 +#define HID_MAIN_ITEM_TAG_END_COLLECTION 12 + +/* + * HID report descriptor main item contents + */ + +#define HID_MAIN_ITEM_CONSTANT 0x001 +#define HID_MAIN_ITEM_VARIABLE 0x002 +#define HID_MAIN_ITEM_RELATIVE 0x004 +#define HID_MAIN_ITEM_WRAP 0x008 +#define HID_MAIN_ITEM_NONLINEAR 0x010 +#define HID_MAIN_ITEM_NO_PREFERRED 0x020 +#define HID_MAIN_ITEM_NULL_STATE 0x040 +#define HID_MAIN_ITEM_VOLATILE 0x080 +#define HID_MAIN_ITEM_BUFFERED_BYTE 0x100 + +/* + * HID report descriptor collection item types + */ + +#define HID_COLLECTION_PHYSICAL 0 +#define HID_COLLECTION_APPLICATION 1 +#define HID_COLLECTION_LOGICAL 2 + +/* + * HID report descriptor global item tags + */ + +#define HID_GLOBAL_ITEM_TAG_USAGE_PAGE 0 +#define HID_GLOBAL_ITEM_TAG_LOGICAL_MINIMUM 1 +#define HID_GLOBAL_ITEM_TAG_LOGICAL_MAXIMUM 2 +#define HID_GLOBAL_ITEM_TAG_PHYSICAL_MINIMUM 3 +#define HID_GLOBAL_ITEM_TAG_PHYSICAL_MAXIMUM 4 +#define HID_GLOBAL_ITEM_TAG_UNIT_EXPONENT 5 +#define HID_GLOBAL_ITEM_TAG_UNIT 6 +#define HID_GLOBAL_ITEM_TAG_REPORT_SIZE 7 +#define HID_GLOBAL_ITEM_TAG_REPORT_ID 8 +#define HID_GLOBAL_ITEM_TAG_REPORT_COUNT 9 +#define HID_GLOBAL_ITEM_TAG_PUSH 10 +#define HID_GLOBAL_ITEM_TAG_POP 11 + +/* + * HID report descriptor local item tags + */ + +#define HID_LOCAL_ITEM_TAG_USAGE 0 +#define HID_LOCAL_ITEM_TAG_USAGE_MINIMUM 1 +#define HID_LOCAL_ITEM_TAG_USAGE_MAXIMUM 2 +#define HID_LOCAL_ITEM_TAG_DESIGNATOR_INDEX 3 +#define HID_LOCAL_ITEM_TAG_DESIGNATOR_MINIMUM 4 +#define HID_LOCAL_ITEM_TAG_DESIGNATOR_MAXIMUM 5 +#define HID_LOCAL_ITEM_TAG_STRING_INDEX 7 +#define HID_LOCAL_ITEM_TAG_STRING_MINIMUM 8 +#define HID_LOCAL_ITEM_TAG_STRING_MAXIMUM 9 +#define HID_LOCAL_ITEM_TAG_DELIMITER 10 + +/* + * HID usage tables + */ + +#define HID_USAGE_PAGE 0xffff0000 + +#define HID_UP_UNDEFINED 0x00000000 +#define HID_UP_GENDESK 0x00010000 +#define HID_UP_SIMULATION 0x00020000 +#define HID_UP_KEYBOARD 0x00070000 +#define HID_UP_LED 0x00080000 +#define HID_UP_BUTTON 0x00090000 +#define HID_UP_ORDINAL 0x000a0000 +#define HID_UP_CONSUMER 0x000c0000 +#define HID_UP_DIGITIZER 0x000d0000 +#define HID_UP_PID 0x000f0000 +#define HID_UP_HPVENDOR 0xff7f0000 +#define HID_UP_MSVENDOR 0xff000000 +#define HID_UP_CUSTOM 0x00ff0000 +#define HID_UP_LOGIVENDOR 0xffbc0000 + +#define HID_USAGE 0x0000ffff + +#define HID_GD_POINTER 0x00010001 +#define HID_GD_MOUSE 0x00010002 +#define HID_GD_JOYSTICK 0x00010004 +#define HID_GD_GAMEPAD 0x00010005 +#define HID_GD_KEYBOARD 0x00010006 +#define HID_GD_KEYPAD 0x00010007 +#define HID_GD_MULTIAXIS 0x00010008 +#define HID_GD_X 0x00010030 +#define HID_GD_Y 0x00010031 +#define HID_GD_Z 0x00010032 +#define HID_GD_RX 0x00010033 +#define HID_GD_RY 0x00010034 +#define HID_GD_RZ 0x00010035 +#define HID_GD_SLIDER 0x00010036 +#define HID_GD_DIAL 0x00010037 +#define HID_GD_WHEEL 0x00010038 +#define HID_GD_HATSWITCH 0x00010039 +#define HID_GD_BUFFER 0x0001003a +#define HID_GD_BYTECOUNT 0x0001003b +#define HID_GD_MOTION 0x0001003c +#define HID_GD_START 0x0001003d +#define HID_GD_SELECT 0x0001003e +#define HID_GD_VX 0x00010040 +#define HID_GD_VY 0x00010041 +#define HID_GD_VZ 0x00010042 +#define HID_GD_VBRX 0x00010043 +#define HID_GD_VBRY 0x00010044 +#define HID_GD_VBRZ 0x00010045 +#define HID_GD_VNO 0x00010046 +#define HID_GD_FEATURE 0x00010047 +#define HID_GD_UP 0x00010090 +#define HID_GD_DOWN 0x00010091 +#define HID_GD_RIGHT 0x00010092 +#define HID_GD_LEFT 0x00010093 + +/* + * HID report types --- Ouch! HID spec says 1 2 3! + */ + +#define HID_INPUT_REPORT 0 +#define HID_OUTPUT_REPORT 1 +#define HID_FEATURE_REPORT 2 + +/* + * HID device quirks. + */ + +#define HID_QUIRK_INVERT 0x00000001 +#define HID_QUIRK_NOTOUCH 0x00000002 +#define HID_QUIRK_IGNORE 0x00000004 +#define HID_QUIRK_NOGET 0x00000008 +#define HID_QUIRK_HIDDEV 0x00000010 +#define HID_QUIRK_BADPAD 0x00000020 +#define HID_QUIRK_MULTI_INPUT 0x00000040 +#define HID_QUIRK_2WHEEL_MOUSE_HACK_7 0x00000080 +#define HID_QUIRK_2WHEEL_MOUSE_HACK_5 0x00000100 +#define HID_QUIRK_2WHEEL_MOUSE_HACK_ON 0x00000200 +#define HID_QUIRK_MIGHTYMOUSE 0x00000400 +#define HID_QUIRK_CYMOTION 0x00000800 +#define HID_QUIRK_POWERBOOK_HAS_FN 0x00001000 +#define HID_QUIRK_POWERBOOK_FN_ON 0x00002000 +#define HID_QUIRK_INVERT_HWHEEL 0x00004000 +#define HID_QUIRK_POWERBOOK_ISO_KEYBOARD 0x00008000 +#define HID_QUIRK_BAD_RELATIVE_KEYS 0x00010000 + +/* + * This is the global environment of the parser. This information is + * persistent for main-items. The global environment can be saved and + * restored with PUSH/POP statements. + */ + +struct hid_global { + unsigned usage_page; + __s32 logical_minimum; + __s32 logical_maximum; + __s32 physical_minimum; + __s32 physical_maximum; + __s32 unit_exponent; + unsigned unit; + unsigned report_id; + unsigned report_size; + unsigned report_count; +}; + +/* + * This is the local environment. It is persistent up the next main-item. + */ + +#define HID_MAX_DESCRIPTOR_SIZE 4096 +#define HID_MAX_USAGES 1024 +#define HID_DEFAULT_NUM_COLLECTIONS 16 + +struct hid_local { + unsigned usage[HID_MAX_USAGES]; /* usage array */ + unsigned collection_index[HID_MAX_USAGES]; /* collection index array */ + unsigned usage_index; + unsigned usage_minimum; + unsigned delimiter_depth; + unsigned delimiter_branch; +}; + +/* + * This is the collection stack. We climb up the stack to determine + * application and function of each field. + */ + +struct hid_collection { + unsigned type; + unsigned usage; + unsigned level; +}; + +struct hid_usage { + unsigned hid; /* hid usage code */ + unsigned collection_index; /* index into collection array */ + /* hidinput data */ + __u16 code; /* input driver code */ + __u8 type; /* input driver type */ + __s8 hat_min; /* hat switch fun */ + __s8 hat_max; /* ditto */ + __s8 hat_dir; /* ditto */ +}; + +struct hid_input; + +struct hid_field { + unsigned physical; /* physical usage for this field */ + unsigned logical; /* logical usage for this field */ + unsigned application; /* application usage for this field */ + struct hid_usage *usage; /* usage table for this function */ + unsigned maxusage; /* maximum usage index */ + unsigned flags; /* main-item flags (i.e. volatile,array,constant) */ + unsigned report_offset; /* bit offset in the report */ + unsigned report_size; /* size of this field in the report */ + unsigned report_count; /* number of this field in the report */ + unsigned report_type; /* (input,output,feature) */ + __s32 *value; /* last known value(s) */ + __s32 logical_minimum; + __s32 logical_maximum; + __s32 physical_minimum; + __s32 physical_maximum; + __s32 unit_exponent; + unsigned unit; + struct hid_report *report; /* associated report */ + unsigned index; /* index into report->field[] */ + /* hidinput data */ + struct hid_input *hidinput; /* associated input structure */ + __u16 dpad; /* dpad input code */ +}; + +#define HID_MAX_FIELDS 64 + +struct hid_report { + struct list_head list; + unsigned id; /* id of this report */ + unsigned type; /* report type */ + struct hid_field *field[HID_MAX_FIELDS]; /* fields of the report */ + unsigned maxfield; /* maximum valid field index */ + unsigned size; /* size of the report (bits) */ + struct hid_device *device; /* associated device */ +}; + +struct hid_report_enum { + unsigned numbered; + struct list_head report_list; + struct hid_report *report_id_hash[256]; +}; + +#define HID_REPORT_TYPES 3 + +#define HID_MIN_BUFFER_SIZE 64 /* make sure there is at least a packet size of space */ +#define HID_MAX_BUFFER_SIZE 4096 /* 4kb */ +#define HID_CONTROL_FIFO_SIZE 256 /* to init devices with >100 reports */ +#define HID_OUTPUT_FIFO_SIZE 64 + +struct hid_control_fifo { + unsigned char dir; + struct hid_report *report; +}; + +#define HID_CLAIMED_INPUT 1 +#define HID_CLAIMED_HIDDEV 2 + +#define HID_CTRL_RUNNING 1 +#define HID_OUT_RUNNING 2 +#define HID_IN_RUNNING 3 +#define HID_RESET_PENDING 4 +#define HID_SUSPENDED 5 +#define HID_CLEAR_HALT 6 + +struct hid_input { + struct list_head list; + struct hid_report *report; + struct input_dev *input; +}; + +struct hid_device { /* device report descriptor */ + __u8 *rdesc; + unsigned rsize; + struct hid_collection *collection; /* List of HID collections */ + unsigned collection_size; /* Number of allocated hid_collections */ + unsigned maxcollection; /* Number of parsed collections */ + unsigned maxapplication; /* Number of applications */ + unsigned version; /* HID version */ + unsigned country; /* HID country */ + struct hid_report_enum report_enum[HID_REPORT_TYPES]; + + struct usb_device *dev; /* USB device */ + struct usb_interface *intf; /* USB interface */ + int ifnum; /* USB interface number */ + + unsigned long iofl; /* I/O flags (CTRL_RUNNING, OUT_RUNNING) */ + struct timer_list io_retry; /* Retry timer */ + unsigned long stop_retry; /* Time to give up, in jiffies */ + unsigned int retry_delay; /* Delay length in ms */ + struct work_struct reset_work; /* Task context for resets */ + + unsigned int bufsize; /* URB buffer size */ + + struct urb *urbin; /* Input URB */ + char *inbuf; /* Input buffer */ + dma_addr_t inbuf_dma; /* Input buffer dma */ + spinlock_t inlock; /* Input fifo spinlock */ + + struct urb *urbctrl; /* Control URB */ + struct usb_ctrlrequest *cr; /* Control request struct */ + dma_addr_t cr_dma; /* Control request struct dma */ + struct hid_control_fifo ctrl[HID_CONTROL_FIFO_SIZE]; /* Control fifo */ + unsigned char ctrlhead, ctrltail; /* Control fifo head & tail */ + char *ctrlbuf; /* Control buffer */ + dma_addr_t ctrlbuf_dma; /* Control buffer dma */ + spinlock_t ctrllock; /* Control fifo spinlock */ + + struct urb *urbout; /* Output URB */ + struct hid_report *out[HID_CONTROL_FIFO_SIZE]; /* Output pipe fifo */ + unsigned char outhead, outtail; /* Output pipe fifo head & tail */ + char *outbuf; /* Output buffer */ + dma_addr_t outbuf_dma; /* Output buffer dma */ + spinlock_t outlock; /* Output fifo spinlock */ + + unsigned claimed; /* Claimed by hidinput, hiddev? */ + unsigned quirks; /* Various quirks the device can pull on us */ + + struct list_head inputs; /* The list of inputs */ + void *hiddev; /* The hiddev structure */ + int minor; /* Hiddev minor number */ + + wait_queue_head_t wait; /* For sleeping */ + + int open; /* is the device open by anyone? */ + char name[128]; /* Device name */ + char phys[64]; /* Device physical location */ + char uniq[64]; /* Device unique identifier (serial #) */ + +#ifdef CONFIG_USB_HIDINPUT_POWERBOOK + unsigned long pb_pressed_fn[NBITS(KEY_MAX)]; + unsigned long pb_pressed_numlock[NBITS(KEY_MAX)]; +#endif +}; + +#define HID_GLOBAL_STACK_SIZE 4 +#define HID_COLLECTION_STACK_SIZE 4 + +struct hid_parser { + struct hid_global global; + struct hid_global global_stack[HID_GLOBAL_STACK_SIZE]; + unsigned global_stack_ptr; + struct hid_local local; + unsigned collection_stack[HID_COLLECTION_STACK_SIZE]; + unsigned collection_stack_ptr; + struct hid_device *device; +}; + +struct hid_class_descriptor { + __u8 bDescriptorType; + __u16 wDescriptorLength; +} __attribute__ ((packed)); + +struct hid_descriptor { + __u8 bLength; + __u8 bDescriptorType; + __u16 bcdHID; + __u8 bCountryCode; + __u8 bNumDescriptors; + + struct hid_class_descriptor desc[1]; +} __attribute__ ((packed)); + +#ifdef DEBUG +#include "hid-debug.h" +#else +#define hid_dump_input(a,b) do { } while (0) +#define hid_dump_device(c) do { } while (0) +#define hid_dump_field(a,b) do { } while (0) +#define resolv_usage(a) do { } while (0) +#define resolv_event(a,b) do { } while (0) +#endif + +#ifdef CONFIG_HID +/* Applications from HID Usage Tables 4/8/99 Version 1.1 */ +/* We ignore a few input applications that are not widely used */ +#define IS_INPUT_APPLICATION(a) (((a >= 0x00010000) && (a <= 0x00010008)) || (a == 0x00010080) || (a == 0x000c0001)) +extern void hidinput_hid_event(struct hid_device *, struct hid_field *, struct hid_usage *, __s32); +extern void hidinput_report_event(struct hid_device *hid, struct hid_report *report); +extern int hidinput_connect(struct hid_device *); +extern void hidinput_disconnect(struct hid_device *); +#else +#define IS_INPUT_APPLICATION(a) (0) +static inline void hidinput_hid_event(struct hid_device *hid, struct hid_field *field, struct hid_usage *usage, __s32 value) { } +static inline void hidinput_report_event(struct hid_device *hid, struct hid_report *report) { } +static inline int hidinput_connect(struct hid_device *hid) { return -ENODEV; } +static inline void hidinput_disconnect(struct hid_device *hid) { } +#endif + +int hid_set_field(struct hid_field *, unsigned, __s32); +int hidinput_find_field(struct hid_device *hid, unsigned int type, unsigned int code, struct hid_field **field); +void hid_input_field(struct hid_device *hid, struct hid_field *field, __u8 *data, int interrupt); +void hid_output_report(struct hid_report *report, __u8 *data); +void hid_free_device(struct hid_device *device); +struct hid_device *hid_parse_report(__u8 *start, unsigned size); + +#ifdef CONFIG_HID_FF +int hid_ff_init(struct hid_device *hid); + +int hid_lgff_init(struct hid_device *hid); +int hid_tmff_init(struct hid_device *hid); +int hid_zpff_init(struct hid_device *hid); +#ifdef CONFIG_HID_PID +int hid_pidff_init(struct hid_device *hid); +#else +static inline int hid_pidff_init(struct hid_device *hid) { return -ENODEV; } +#endif + +#else +static inline int hid_ff_init(struct hid_device *hid) { return -1; } +#endif +#endif + -- cgit v1.2.3 From 229695e51efc4ed5e04ab471c82591d0f432909d Mon Sep 17 00:00:00 2001 From: Jiri Kosina Date: Fri, 8 Dec 2006 18:40:53 +0100 Subject: [PATCH] Generic HID layer - API - fixed generic API (added neccessary EXPORT_SYMBOL, fixed hid.h to provide correct prototypes) - extended hid_device with open/close/event function pointers to driver-specific functions - added driver specific driver_data to hid_device Signed-off-by: Jiri Kosina Signed-off-by: Marcel Holtmann Cc: Dmitry Torokhov Signed-off-by: Greg Kroah-Hartman --- include/linux/hid.h | 36 ++++++++++++++++++++++++++++-------- 1 file changed, 28 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index ee567ae6fec1..0473b45b73b8 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -403,11 +403,17 @@ struct hid_device { /* device report descriptor */ unsigned collection_size; /* Number of allocated hid_collections */ unsigned maxcollection; /* Number of parsed collections */ unsigned maxapplication; /* Number of applications */ + unsigned short bus; /* BUS ID */ + unsigned short vendor; /* Vendor ID */ + unsigned short product; /* Product ID */ unsigned version; /* HID version */ unsigned country; /* HID country */ struct hid_report_enum report_enum[HID_REPORT_TYPES]; - struct usb_device *dev; /* USB device */ + struct usb_device *dev; /* device */ + + /* USB specific fields */ + struct usb_interface *intf; /* USB interface */ int ifnum; /* USB interface number */ @@ -454,6 +460,13 @@ struct hid_device { /* device report descriptor */ char phys[64]; /* Device physical location */ char uniq[64]; /* Device unique identifier (serial #) */ + void *driver_data; + + /* device-specific function pointers */ + int (*hidinput_input_event) (struct input_dev *, unsigned int, unsigned int, int); + int (*hidinput_open) (struct input_dev *); + void (*hidinput_close) (struct input_dev *); + #ifdef CONFIG_USB_HIDINPUT_POWERBOOK unsigned long pb_pressed_fn[NBITS(KEY_MAX)]; unsigned long pb_pressed_numlock[NBITS(KEY_MAX)]; @@ -502,17 +515,15 @@ struct hid_descriptor { /* Applications from HID Usage Tables 4/8/99 Version 1.1 */ /* We ignore a few input applications that are not widely used */ #define IS_INPUT_APPLICATION(a) (((a >= 0x00010000) && (a <= 0x00010008)) || (a == 0x00010080) || (a == 0x000c0001)) +#else +#define IS_INPUT_APPLICATION(a) (0) +#endif + +/* HID core API */ extern void hidinput_hid_event(struct hid_device *, struct hid_field *, struct hid_usage *, __s32); extern void hidinput_report_event(struct hid_device *hid, struct hid_report *report); extern int hidinput_connect(struct hid_device *); extern void hidinput_disconnect(struct hid_device *); -#else -#define IS_INPUT_APPLICATION(a) (0) -static inline void hidinput_hid_event(struct hid_device *hid, struct hid_field *field, struct hid_usage *usage, __s32 value) { } -static inline void hidinput_report_event(struct hid_device *hid, struct hid_report *report) { } -static inline int hidinput_connect(struct hid_device *hid) { return -ENODEV; } -static inline void hidinput_disconnect(struct hid_device *hid) { } -#endif int hid_set_field(struct hid_field *, unsigned, __s32); int hidinput_find_field(struct hid_device *hid, unsigned int type, unsigned int code, struct hid_field **field); @@ -536,5 +547,14 @@ static inline int hid_pidff_init(struct hid_device *hid) { return -ENODEV; } #else static inline int hid_ff_init(struct hid_device *hid) { return -1; } #endif +#ifdef DEBUG +#define dbg(format, arg...) printk(KERN_DEBUG "%s: " format "\n" , \ + __FILE__ , ## arg) +#else +#define dbg(format, arg...) do {} while (0) +#endif + +#define err(format, arg...) printk(KERN_ERR "%s: " format "\n" , \ + __FILE__ , ## arg) #endif -- cgit v1.2.3 From 4916b3a57fc94664677d439b911b8aaf86c7ec23 Mon Sep 17 00:00:00 2001 From: Jiri Kosina Date: Fri, 8 Dec 2006 18:41:03 +0100 Subject: [PATCH] Generic HID layer - USB API - 'dev' in struct hid_device changed from struct usb_device to struct device and fixed all the users - renamed functions which are part of USB HID API from 'hid_*' to 'usbhid_*' - force feedback initialization moved from common part into USB-specific driver - added usbhid.h header for USB HID API users - removed USB-specific fields from struct hid_device and moved them to new usbhid_device, which is pointed to by hid_device->driver_data - fixed all USB users to use this new structure Signed-off-by: Jiri Kosina Signed-off-by: Marcel Holtmann Cc: Dmitry Torokhov Signed-off-by: Greg Kroah-Hartman --- include/linux/hid.h | 36 +----------------------------------- 1 file changed, 1 insertion(+), 35 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index 0473b45b73b8..fc6f74228da3 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -410,41 +410,7 @@ struct hid_device { /* device report descriptor */ unsigned country; /* HID country */ struct hid_report_enum report_enum[HID_REPORT_TYPES]; - struct usb_device *dev; /* device */ - - /* USB specific fields */ - - struct usb_interface *intf; /* USB interface */ - int ifnum; /* USB interface number */ - - unsigned long iofl; /* I/O flags (CTRL_RUNNING, OUT_RUNNING) */ - struct timer_list io_retry; /* Retry timer */ - unsigned long stop_retry; /* Time to give up, in jiffies */ - unsigned int retry_delay; /* Delay length in ms */ - struct work_struct reset_work; /* Task context for resets */ - - unsigned int bufsize; /* URB buffer size */ - - struct urb *urbin; /* Input URB */ - char *inbuf; /* Input buffer */ - dma_addr_t inbuf_dma; /* Input buffer dma */ - spinlock_t inlock; /* Input fifo spinlock */ - - struct urb *urbctrl; /* Control URB */ - struct usb_ctrlrequest *cr; /* Control request struct */ - dma_addr_t cr_dma; /* Control request struct dma */ - struct hid_control_fifo ctrl[HID_CONTROL_FIFO_SIZE]; /* Control fifo */ - unsigned char ctrlhead, ctrltail; /* Control fifo head & tail */ - char *ctrlbuf; /* Control buffer */ - dma_addr_t ctrlbuf_dma; /* Control buffer dma */ - spinlock_t ctrllock; /* Control fifo spinlock */ - - struct urb *urbout; /* Output URB */ - struct hid_report *out[HID_CONTROL_FIFO_SIZE]; /* Output pipe fifo */ - unsigned char outhead, outtail; /* Output pipe fifo head & tail */ - char *outbuf; /* Output buffer */ - dma_addr_t outbuf_dma; /* Output buffer dma */ - spinlock_t outlock; /* Output fifo spinlock */ + struct device *dev; /* device */ unsigned claimed; /* Claimed by hidinput, hiddev? */ unsigned quirks; /* Various quirks the device can pull on us */ -- cgit v1.2.3 From aa938f7974b82cfd9ee955031987344f332b7c77 Mon Sep 17 00:00:00 2001 From: Jiri Kosina Date: Fri, 8 Dec 2006 18:41:10 +0100 Subject: [PATCH] Generic HID layer - hiddev - hiddev is USB-only (agreed with Marcel Holtmann that Bluetooth currently doesn't need it, and future planned interface (rawhid) will be more flexible and usable) - both HID and USB-hid can be now compiled as modules (wasn't possible before hiddev was fully separated from generic HID layer) Signed-off-by: Jiri Kosina Signed-off-by: Marcel Holtmann Cc: Dmitry Torokhov Signed-off-by: Greg Kroah-Hartman --- include/linux/hid.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index fc6f74228da3..5a969a137b85 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -433,6 +433,10 @@ struct hid_device { /* device report descriptor */ int (*hidinput_open) (struct input_dev *); void (*hidinput_close) (struct input_dev *); + /* hiddev event handler */ + void (*hiddev_hid_event) (struct hid_device *, struct hid_field *field, + struct hid_usage *, __s32); + #ifdef CONFIG_USB_HIDINPUT_POWERBOOK unsigned long pb_pressed_fn[NBITS(KEY_MAX)]; unsigned long pb_pressed_numlock[NBITS(KEY_MAX)]; @@ -477,13 +481,9 @@ struct hid_descriptor { #define resolv_event(a,b) do { } while (0) #endif -#ifdef CONFIG_HID /* Applications from HID Usage Tables 4/8/99 Version 1.1 */ /* We ignore a few input applications that are not widely used */ #define IS_INPUT_APPLICATION(a) (((a >= 0x00010000) && (a <= 0x00010008)) || (a == 0x00010080) || (a == 0x000c0001)) -#else -#define IS_INPUT_APPLICATION(a) (0) -#endif /* HID core API */ extern void hidinput_hid_event(struct hid_device *, struct hid_field *, struct hid_usage *, __s32); -- cgit v1.2.3 From aa8de2f038baec993f07ef66fb3e94481d1ec22b Mon Sep 17 00:00:00 2001 From: Jiri Kosina Date: Fri, 8 Dec 2006 18:41:17 +0100 Subject: [PATCH] Generic HID layer - input and event reporting hid_input_report() was needlessly USB-specific in USB HID. This patch makes the function independent of HID implementation and fixes all the current users. Bluetooth patches comply with this prototype. Signed-off-by: Jiri Kosina Signed-off-by: Marcel Holtmann Cc: Dmitry Torokhov Signed-off-by: Greg Kroah-Hartman --- include/linux/hid.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index 5a969a137b85..342b4e639acb 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -436,7 +436,7 @@ struct hid_device { /* device report descriptor */ /* hiddev event handler */ void (*hiddev_hid_event) (struct hid_device *, struct hid_field *field, struct hid_usage *, __s32); - + void (*hiddev_report_event) (struct hid_device *, struct hid_report *); #ifdef CONFIG_USB_HIDINPUT_POWERBOOK unsigned long pb_pressed_fn[NBITS(KEY_MAX)]; unsigned long pb_pressed_numlock[NBITS(KEY_MAX)]; @@ -492,6 +492,7 @@ extern int hidinput_connect(struct hid_device *); extern void hidinput_disconnect(struct hid_device *); int hid_set_field(struct hid_field *, unsigned, __s32); +int hid_input_report(struct hid_device *, int type, u8 *, int, int); int hidinput_find_field(struct hid_device *hid, unsigned int type, unsigned int code, struct hid_field **field); void hid_input_field(struct hid_device *hid, struct hid_field *field, __u8 *data, int interrupt); void hid_output_report(struct hid_report *report, __u8 *data); -- cgit v1.2.3 From 4c2ae844b5ef85fd4b571c9c91ac48afa6ef2dfc Mon Sep 17 00:00:00 2001 From: Jiri Kosina Date: Fri, 8 Dec 2006 18:41:22 +0100 Subject: [PATCH] Generic HID layer - pb_fnmode pb_fnmode parameter has to be passed to usbhid, both for compatibility reasons and also because it logically belongs there. Also removes empty hid-input.c file in drivers/usb/input. Signed-off-by: Jiri Kosina Signed-off-by: Marcel Holtmann Cc: Dmitry Torokhov Signed-off-by: Greg Kroah-Hartman --- include/linux/hid.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index 342b4e639acb..770120add15a 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -438,6 +438,7 @@ struct hid_device { /* device report descriptor */ struct hid_usage *, __s32); void (*hiddev_report_event) (struct hid_device *, struct hid_report *); #ifdef CONFIG_USB_HIDINPUT_POWERBOOK + unsigned int pb_fnmode; unsigned long pb_pressed_fn[NBITS(KEY_MAX)]; unsigned long pb_pressed_numlock[NBITS(KEY_MAX)]; #endif -- cgit v1.2.3 From 3644f0cee77494190452de132e82245107939284 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Thu, 7 Dec 2006 15:08:17 -0800 Subject: [NET]: Convert hh_lock to seqlock. The hard header cache is in the main output path, so using seqlock instead of reader/writer lock should reduce overhead. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index c57088f575a3..631cec4ff5e1 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -199,7 +199,7 @@ struct hh_cache */ u16 hh_len; /* length of header */ int (*hh_output)(struct sk_buff *skb); - rwlock_t hh_lock; + seqlock_t hh_lock; /* cached hardware header; allow for machine alignment needs. */ #define HH_DATA_MOD 16 -- cgit v1.2.3 From e07bca84cd9d31f76ed655d51e68b6a0ca15f162 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Thu, 7 Dec 2006 23:49:45 -0800 Subject: [NETLINK]: Restore API compatibility of address and neighbour bits Restore API compatibility due to bits moved from rtnetlink.h to separate headers. Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/rtnetlink.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 493297acdae8..4a629ea70cc4 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -3,6 +3,8 @@ #include #include +#include +#include /**** * Routing/neighbour discovery messages. -- cgit v1.2.3 From f0490980a152958d25ce9762bfb296d8fd4c5512 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 8 Dec 2006 00:08:43 -0800 Subject: [NET]: Force a cache line split in hh_cache in SMP. hh_lock was converted from rwlock to seqlock by Stephen. To have a 100% benefit of this change, I suggest to place read mostly fields of hh_cache in a separate cache line, because hh_refcnt may be changed quite frequently on some busy machines. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 631cec4ff5e1..6be767c76b37 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -193,7 +193,14 @@ struct hh_cache { struct hh_cache *hh_next; /* Next entry */ atomic_t hh_refcnt; /* number of users */ - __be16 hh_type; /* protocol identifier, f.e ETH_P_IP +/* + * We want hh_output, hh_len, hh_lock and hh_data be a in a separate + * cache line on SMP. + * They are mostly read, but hh_refcnt may be changed quite frequently, + * incurring cache line ping pongs. + */ + __be16 hh_type ____cacheline_aligned_in_smp; + /* protocol identifier, f.e ETH_P_IP * NOTE: For VLANs, this will be the * encapuslated type. --BLG */ -- cgit v1.2.3 From 93366c537b3426261cac4db27acc10a99cd91b06 Mon Sep 17 00:00:00 2001 From: J Hadi Salim Date: Fri, 8 Dec 2006 00:12:15 -0800 Subject: [XFRM]: Fix XFRMGRP_REPORT to use correct multicast group. XFRMGRP_REPORT uses 0x10 which is a group that belongs to events. The correct value is 0x20. We should really be using xfrm_nlgroups going forward; it was tempting to delete the definition of XFRMGRP_REPORT but it would break at least iproute2. Signed-off-by: J 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 088ba8113f7e..9529ea1ae392 100644 --- a/include/linux/xfrm.h +++ b/include/linux/xfrm.h @@ -357,7 +357,7 @@ struct xfrm_user_report { #define XFRMGRP_EXPIRE 2 #define XFRMGRP_SA 4 #define XFRMGRP_POLICY 8 -#define XFRMGRP_REPORT 0x10 +#define XFRMGRP_REPORT 0x20 #endif enum xfrm_nlgroups { -- cgit v1.2.3 From d3dcc077bf88806201093f86325ec656e4dbfbce Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Fri, 8 Dec 2006 17:05:13 -0800 Subject: [NETLINK]: Put {IFA,IFLA}_{RTA,PAYLOAD} macros back for userspace. GLIBC uses them etc. They are guarded by ifndef __KERNEL__ so nobody will start accidently using them in the kernel again, it's just for userspace. Signed-off-by: David S. Miller --- include/linux/if_addr.h | 6 ++++++ include/linux/if_link.h | 6 ++++++ 2 files changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/if_addr.h b/include/linux/if_addr.h index dbe8f6120a40..d557e4ce9b6b 100644 --- a/include/linux/if_addr.h +++ b/include/linux/if_addr.h @@ -52,4 +52,10 @@ struct ifa_cacheinfo __u32 tstamp; /* updated timestamp, hundredths of seconds */ }; +/* backwards compatibility for userspace */ +#ifndef __KERNEL__ +#define IFA_RTA(r) ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct ifaddrmsg)))) +#define IFA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct ifaddrmsg)) +#endif + #endif diff --git a/include/linux/if_link.h b/include/linux/if_link.h index e963a077e6f5..35ed3b5467f3 100644 --- a/include/linux/if_link.h +++ b/include/linux/if_link.h @@ -82,6 +82,12 @@ enum #define IFLA_MAX (__IFLA_MAX - 1) +/* backwards compatibility for userspace */ +#ifndef __KERNEL__ +#define IFLA_RTA(r) ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct ifinfomsg)))) +#define IFLA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct ifinfomsg)) +#endif + /* ifi_flags. IFF_* flags. -- cgit v1.2.3 From 9c4dfadbde3cfa78b92c28597125b8c41d36ffd0 Mon Sep 17 00:00:00 2001 From: Jonathan Corbet Date: Sat, 4 Nov 2006 09:22:27 -0300 Subject: V4L/DVB (4796): A couple of V4L2 defines needed by Cafe Camara driver Two defines for V4L2, needed by the Cafe camera driver: 1) Add the RGB444 image format 2) Add the "init" internal command which is separate from "reset". Signed-off-by: Jonathan Corbet 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 df5c4654360d..5cb380a559fd 100644 --- a/include/linux/videodev2.h +++ b/include/linux/videodev2.h @@ -244,6 +244,7 @@ struct v4l2_pix_format #define V4L2_PIX_FMT_YYUV v4l2_fourcc('Y','Y','U','V') /* 16 YUV 4:2:2 */ #define V4L2_PIX_FMT_HI240 v4l2_fourcc('H','I','2','4') /* 8 8-bit color */ #define V4L2_PIX_FMT_HM12 v4l2_fourcc('H','M','1','2') /* 8 YUV 4:2:0 16x16 macroblocks */ +#define V4L2_PIX_FMT_RGB444 v4l2_fourcc('R','4','4','4') /* 16 xxxxrrrr ggggbbbb */ /* see http://www.siliconimaging.com/RGB%20Bayer.htm */ #define V4L2_PIX_FMT_SBGGR8 v4l2_fourcc('B','A','8','1') /* 8 BGBG.. GRGR.. */ -- cgit v1.2.3 From d905b382d797a213e15868cbf3204f50ed52e30b Mon Sep 17 00:00:00 2001 From: Jonathan Corbet Date: Sat, 4 Nov 2006 09:25:53 -0300 Subject: V4L/DVB (4797): Marvell 88ALP01 "cafe" driver A driver for the Marvell M88ALP01 "CAFE" CMOS integrated camera controller. This driver has been renamed "cafe_ccic" since my previous patch set. Signed-off-by: Jonathan Corbet Signed-off-by: Mauro Carvalho Chehab --- include/linux/i2c-id.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/i2c-id.h b/include/linux/i2c-id.h index 0a8f750cbede..a32db163cbc0 100644 --- a/include/linux/i2c-id.h +++ b/include/linux/i2c-id.h @@ -250,6 +250,7 @@ #define I2C_HW_SMBUS_OV518 0x04000f /* OV518(+) USB 1.1 webcam ICs */ #define I2C_HW_SMBUS_OV519 0x040010 /* OV519 USB 1.1 webcam IC */ #define I2C_HW_SMBUS_OVFX2 0x040011 /* Cypress/OmniVision FX2 webcam */ +#define I2C_HW_SMBUS_CAFE 0x040012 /* Marvell 88ALP01 "CAFE" cam */ /* --- ISA pseudo-adapter */ #define I2C_HW_ISA 0x050000 -- cgit v1.2.3 From 111f33564e19b2b5f70e3df9a8f92c08c1c91fd9 Mon Sep 17 00:00:00 2001 From: Jonathan Corbet Date: Sat, 4 Nov 2006 09:26:00 -0300 Subject: V4L/DVB (4798): OmniVision OV7670 driver This patch adds a V4L2 driver for the OmniVision OV7670 camera. Signed-off-by: Jonathan Corbet Signed-off-by: Mauro Carvalho Chehab --- include/linux/i2c-id.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/i2c-id.h b/include/linux/i2c-id.h index a32db163cbc0..0f4cf34b6fa2 100644 --- a/include/linux/i2c-id.h +++ b/include/linux/i2c-id.h @@ -159,6 +159,7 @@ #define I2C_DRIVERID_ASB100 1043 #define I2C_DRIVERID_FSCHER 1046 #define I2C_DRIVERID_W83L785TS 1047 +#define I2C_DRIVERID_OV7670 1048 /* Omnivision 7670 camera */ /* * ---- Adapter types ---------------------------------------------------- -- cgit v1.2.3 From 5c543eff6cc658f46241f1ccb77436d65abbf445 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 10 Dec 2006 02:18:58 -0800 Subject: [PATCH] freezer.h uses task_struct fields freezer.h uses task_struct fields so it should include sched.h. CC [M] fs/jfs/jfs_txnmgr.o In file included from fs/jfs/jfs_txnmgr.c:49: include/linux/freezer.h: In function 'frozen': include/linux/freezer.h:9: error: dereferencing pointer to incomplete type include/linux/freezer.h:9: error: 'PF_FROZEN' undeclared (first use in this function) include/linux/freezer.h:9: error: (Each undeclared identifier is reported only once include/linux/freezer.h:9: error: for each function it appears in.) include/linux/freezer.h: In function 'freezing': include/linux/freezer.h:17: error: dereferencing pointer to incomplete type include/linux/freezer.h:17: error: 'PF_FREEZE' undeclared (first use in this function) include/linux/freezer.h: In function 'freeze': include/linux/freezer.h:26: error: dereferencing pointer to incomplete type include/linux/freezer.h:26: error: 'PF_FREEZE' undeclared (first use in this function) include/linux/freezer.h: In function 'do_not_freeze': include/linux/freezer.h:34: error: dereferencing pointer to incomplete type include/linux/freezer.h:34: error: 'PF_FREEZE' undeclared (first use in this function) include/linux/freezer.h: In function 'thaw_process': include/linux/freezer.h:43: error: dereferencing pointer to incomplete type include/linux/freezer.h:43: error: 'PF_FROZEN' undeclared (first use in this function) include/linux/freezer.h:44: warning: implicit declaration of function 'wake_up_process' include/linux/freezer.h: In function 'frozen_process': include/linux/freezer.h:55: error: dereferencing pointer to incomplete type include/linux/freezer.h:55: error: dereferencing pointer to incomplete type include/linux/freezer.h:55: error: 'PF_FREEZE' undeclared (first use in this function) include/linux/freezer.h:55: error: 'PF_FROZEN' undeclared (first use in this function) fs/jfs/jfs_txnmgr.c: In function 'freezing': include/linux/freezer.h:18: warning: control reaches end of non-void function make[2]: *** [fs/jfs/jfs_txnmgr.o] Error 1 Signed-off-by: Randy Dunlap Acked-by: Dave Kleikamp Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/freezer.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/freezer.h b/include/linux/freezer.h index 6e05e3e7ce39..393063096134 100644 --- a/include/linux/freezer.h +++ b/include/linux/freezer.h @@ -1,5 +1,7 @@ /* Freezer declarations */ +#include + #ifdef CONFIG_PM /* * Check if a process has been frozen -- cgit v1.2.3 From 884b4aaaa242a2db8c8252796f0118164a680ab5 Mon Sep 17 00:00:00 2001 From: Scott Wood Date: Sun, 10 Dec 2006 02:19:00 -0800 Subject: [PATCH] rtc: Add rtc_merge_alarm() Add rtc_merge_alarm(), which can be used by rtc drivers to turn a partially specified alarm expiry (i.e. most significant fields set to -1, as with the RTC_ALM_SET ioctl()) into a fully specified expiry. If the most significant specified field is earlier than the current time, the least significant unspecified field is incremented. Signed-off-by: Scott Wood Acked-by: Alessandro Zummo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rtc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/rtc.h b/include/linux/rtc.h index 09ff4c3e2713..5e22d4510d11 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -106,6 +106,7 @@ extern int rtc_year_days(unsigned int day, unsigned int month, unsigned int year extern int rtc_valid_tm(struct rtc_time *tm); extern int rtc_tm_to_time(struct rtc_time *tm, unsigned long *time); extern void rtc_time_to_tm(unsigned long time, struct rtc_time *tm); +extern void rtc_merge_alarm(struct rtc_time *now, struct rtc_time *alarm); #include #include -- cgit v1.2.3 From 1f29bcd739972f71f2fd5d5d265daf3e1208fa5e Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Sun, 10 Dec 2006 02:19:10 -0800 Subject: [PATCH] sysctl: remove unused "context" param Signed-off-by: Alexey Dobriyan Cc: Andi Kleen Cc: "David S. Miller" Cc: David Howells Cc: Ralf Baechle Cc: "Eric W. Biederman" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sysctl.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 94316a98e0d0..6d8846e7be6d 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -918,8 +918,7 @@ typedef struct ctl_table ctl_table; typedef int ctl_handler (ctl_table *table, int __user *name, int nlen, void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen, - void **context); + void __user *newval, size_t newlen); typedef int proc_handler (ctl_table *ctl, int write, struct file * filp, void __user *buffer, size_t *lenp, loff_t *ppos); @@ -950,7 +949,7 @@ extern int do_sysctl (int __user *name, int nlen, extern int do_sysctl_strategy (ctl_table *table, int __user *name, int nlen, void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen, void ** context); + void __user *newval, size_t newlen); extern ctl_handler sysctl_string; extern ctl_handler sysctl_intvec; -- cgit v1.2.3 From 58f64d83c37f5073a01573d27043c9c0ccc764f1 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Sun, 10 Dec 2006 02:19:11 -0800 Subject: [PATCH] Fix noise in futex.h There are some kernel-only bits in the middle of which should be removed in what we export to userspace. Signed-off-by: David Woodhouse Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/Kbuild | 2 +- include/linux/futex.h | 2 ++ 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/Kbuild b/include/linux/Kbuild index e618b25b5add..a1b04d8a1d01 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -61,7 +61,6 @@ header-y += fd.h header-y += fdreg.h header-y += fib_rules.h header-y += fuse.h -header-y += futex.h header-y += genetlink.h header-y += gen_stats.h header-y += gigaset_dev.h @@ -203,6 +202,7 @@ unifdef-y += fb.h unifdef-y += fcntl.h unifdef-y += filter.h unifdef-y += flat.h +unifdef-y += futex.h unifdef-y += fs.h unifdef-y += gameport.h unifdef-y += generic_serial.h diff --git a/include/linux/futex.h b/include/linux/futex.h index d097b5b72bc6..3f153b4e156c 100644 --- a/include/linux/futex.h +++ b/include/linux/futex.h @@ -93,6 +93,7 @@ struct robust_list_head { */ #define ROBUST_LIST_LIMIT 2048 +#ifdef __KERNEL__ long do_futex(u32 __user *uaddr, int op, u32 val, unsigned long timeout, u32 __user *uaddr2, u32 val2, u32 val3); @@ -110,6 +111,7 @@ static inline void exit_pi_state_list(struct task_struct *curr) { } #endif +#endif /* __KERNEL__ */ #define FUTEX_OP_SET 0 /* *(int *)UADDR2 = OPARG; */ #define FUTEX_OP_ADD 1 /* *(int *)UADDR2 += OPARG; */ -- cgit v1.2.3 From 7c3ab7381e79dfc7db14a67c6f4f3285664e1ec2 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Sun, 10 Dec 2006 02:19:19 -0800 Subject: [PATCH] io-accounting: core statistics The present per-task IO accounting isn't very useful. It simply counts the number of bytes passed into read() and write(). So if a process reads 1MB from an already-cached file, it is accused of having performed 1MB of I/O, which is wrong. (David Wright had some comments on the applicability of the present logical IO accounting: For billing purposes it is useless but for workload analysis it is very useful read_bytes/read_calls average read request size write_bytes/write_calls average write request size read_bytes/read_blocks ie logical/physical can indicate hit rate or thrashing write_bytes/write_blocks ie logical/physical guess since pdflush writes can be missed I often look for logical larger than physical to see filesystem cache problems. And the bytes/cpusec can help find applications that are dominating the cache and causing slow interactive response from page cache contention. I want to find the IO intensive applications and make sure they are doing efficient IO. Thus the acctcms(sysV) or csacms command would give the high IO commands). This patchset adds new accounting which tries to be more accurate. We account for three things: reads: attempt to count the number of bytes which this process really did cause to be fetched from the storage layer. Done at the submit_bio() level, so it is accurate for block-backed filesystems. I also attempt to wire up NFS and CIFS. writes: attempt to count the number of bytes which this process caused to be sent to the storage layer. This is done at page-dirtying time. The big inaccuracy here is truncate. If a process writes 1MB to a file and then deletes the file, it will in fact perform no writeout. But it will have been accounted as having caused 1MB of write. So... cancelled_writes: account the number of bytes which this process caused to not happen, by truncating pagecache. We _could_ just subtract this from the process's `write' accounting. But that means that some processes would be reported to have done negative amounts of write IO, which is silly. So we just report the raw number and punt this decision up to userspace. Now, we _could_ account for writes at the physical I/O level. But - This would require that we track memory-dirtying tasks at the per-page level (would require a new pointer in struct page). - It would mean that IO statistics for a process are usually only available long after that process has exitted. Which means that we probably cannot communicate this info via taskstats. This patch: Wire up the kernel-private data structures and the accessor functions to manipulate them. Cc: Jay Lan Cc: Shailabh Nagar Cc: Balbir Singh Cc: Chris Sturtivant Cc: Tony Ernst Cc: Guillaume Thouvenin Cc: David Wright Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 2 ++ include/linux/task_io_accounting.h | 37 ++++++++++++++++++++++++++ include/linux/task_io_accounting_ops.h | 47 ++++++++++++++++++++++++++++++++++ 3 files changed, 86 insertions(+) create mode 100644 include/linux/task_io_accounting.h create mode 100644 include/linux/task_io_accounting_ops.h (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index ad9c46071ff8..1208feab46e0 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -82,6 +82,7 @@ struct sched_param { #include #include #include +#include #include @@ -1013,6 +1014,7 @@ struct task_struct { wait_queue_t *io_wait; /* i/o counters(bytes read/written, #syscalls */ u64 rchar, wchar, syscr, syscw; + struct task_io_accounting ioac; #if defined(CONFIG_TASK_XACCT) u64 acct_rss_mem1; /* accumulated rss usage */ u64 acct_vm_mem1; /* accumulated virtual memory usage */ diff --git a/include/linux/task_io_accounting.h b/include/linux/task_io_accounting.h new file mode 100644 index 000000000000..44d00e9cceea --- /dev/null +++ b/include/linux/task_io_accounting.h @@ -0,0 +1,37 @@ +/* + * task_io_accounting: a structure which is used for recording a single task's + * IO statistics. + * + * Don't include this header file directly - it is designed to be dragged in via + * sched.h. + * + * Blame akpm@osdl.org for all this. + */ + +#ifdef CONFIG_TASK_IO_ACCOUNTING +struct task_io_accounting { + /* + * The number of bytes which this task has caused to be read from + * storage. + */ + u64 read_bytes; + + /* + * The number of bytes which this task has caused, or shall cause to be + * written to disk. + */ + u64 write_bytes; + + /* + * A task can cause "negative" IO too. If this task truncates some + * dirty pagecache, some IO which another task has been accounted for + * (in its write_bytes) will not be happening. We _could_ just + * subtract that from the truncating task's write_bytes, but there is + * information loss in doing that. + */ + u64 cancelled_write_bytes; +}; +#else +struct task_io_accounting { +}; +#endif diff --git a/include/linux/task_io_accounting_ops.h b/include/linux/task_io_accounting_ops.h new file mode 100644 index 000000000000..df2a319106b2 --- /dev/null +++ b/include/linux/task_io_accounting_ops.h @@ -0,0 +1,47 @@ +/* + * Task I/O accounting operations + */ +#ifndef __TASK_IO_ACCOUNTING_OPS_INCLUDED +#define __TASK_IO_ACCOUNTING_OPS_INCLUDED + +#ifdef CONFIG_TASK_IO_ACCOUNTING +static inline void task_io_account_read(size_t bytes) +{ + current->ioac.read_bytes += bytes; +} + +static inline void task_io_account_write(size_t bytes) +{ + current->ioac.write_bytes += bytes; +} + +static inline void task_io_account_cancelled_write(size_t bytes) +{ + current->ioac.cancelled_write_bytes += bytes; +} + +static inline void task_io_accounting_init(struct task_struct *tsk) +{ + memset(&tsk->ioac, 0, sizeof(tsk->ioac)); +} + +#else + +static inline void task_io_account_read(size_t bytes) +{ +} + +static inline void task_io_account_write(size_t bytes) +{ +} + +static inline void task_io_account_cancelled_write(size_t bytes) +{ +} + +static inline void task_io_accounting_init(struct task_struct *tsk) +{ +} + +#endif /* CONFIG_TASK_IO_ACCOUNTING */ +#endif /* __TASK_IO_ACCOUNTING_OPS_INCLUDED */ -- cgit v1.2.3 From f2f1f8a3b86ccc5e998dc70a3ba35af199fdbc58 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Sun, 10 Dec 2006 02:19:50 -0800 Subject: [PATCH] cleanup taskstats.h Fix weird whitespace mangling in taskstats.h Cc: Jay Lan Cc: Shailabh Nagar Cc: Balbir Singh Cc: Chris Sturtivant Cc: Tony Ernst Cc: Guillaume Thouvenin Cc: David Wright Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/taskstats.h | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/taskstats.h b/include/linux/taskstats.h index 45248806ae9c..15c64037be1b 100644 --- a/include/linux/taskstats.h +++ b/include/linux/taskstats.h @@ -115,31 +115,31 @@ struct taskstats { __u64 ac_majflt; /* Major Page Fault Count */ /* Basic Accounting Fields end */ - /* Extended accounting fields start */ + /* Extended accounting fields start */ /* Accumulated RSS usage in duration of a task, in MBytes-usecs. * The current rss usage is added to this counter every time * a tick is charged to a task's system time. So, at the end we * will have memory usage multiplied by system time. Thus an * average usage per system time unit can be calculated. */ - __u64 coremem; /* accumulated RSS usage in MB-usec */ + __u64 coremem; /* accumulated RSS usage in MB-usec */ /* Accumulated virtual memory usage in duration of a task. * Same as acct_rss_mem1 above except that we keep track of VM usage. */ - __u64 virtmem; /* accumulated VM usage in MB-usec */ + __u64 virtmem; /* accumulated VM usage in MB-usec */ /* High watermark of RSS and virtual memory usage in duration of * a task, in KBytes. */ - __u64 hiwater_rss; /* High-watermark of RSS usage, in KB */ - __u64 hiwater_vm; /* High-water VM usage, in KB */ + __u64 hiwater_rss; /* High-watermark of RSS usage, in KB */ + __u64 hiwater_vm; /* High-water VM usage, in KB */ /* The following four fields are I/O statistics of a task. */ - __u64 read_char; /* bytes read */ - __u64 write_char; /* bytes written */ - __u64 read_syscalls; /* read syscalls */ - __u64 write_syscalls; /* write syscalls */ - /* Extended accounting fields end */ + __u64 read_char; /* bytes read */ + __u64 write_char; /* bytes written */ + __u64 read_syscalls; /* read syscalls */ + __u64 write_syscalls; /* write syscalls */ + /* Extended accounting fields end */ }; -- cgit v1.2.3 From 4a7864ca638e0a38307962ee8ef122822a351b65 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Sun, 10 Dec 2006 02:19:53 -0800 Subject: [PATCH] io-accounting: via taskstats Deliver IO accounting via taskstats. Cc: Jay Lan Cc: Shailabh Nagar Cc: Balbir Singh Cc: Chris Sturtivant Cc: Tony Ernst Cc: Guillaume Thouvenin Cc: David Wright Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/taskstats.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/taskstats.h b/include/linux/taskstats.h index 15c64037be1b..3fced4798255 100644 --- a/include/linux/taskstats.h +++ b/include/linux/taskstats.h @@ -31,7 +31,7 @@ */ -#define TASKSTATS_VERSION 2 +#define TASKSTATS_VERSION 3 #define TS_COMM_LEN 32 /* should be >= TASK_COMM_LEN * in linux/sched.h */ @@ -140,6 +140,12 @@ struct taskstats { __u64 read_syscalls; /* read syscalls */ __u64 write_syscalls; /* write syscalls */ /* Extended accounting fields end */ + +#define TASKSTATS_HAS_IO_ACCOUNTING + /* Per-task storage I/O accounting starts */ + __u64 read_bytes; /* bytes of read I/O */ + __u64 write_bytes; /* bytes of write I/O */ + __u64 cancelled_write_bytes; /* bytes of cancelled write I/O */ }; -- cgit v1.2.3 From ac7d550499e225efb51a53d0b00667f26b93bdff Mon Sep 17 00:00:00 2001 From: "Siddha, Suresh B" Date: Sun, 10 Dec 2006 02:20:12 -0800 Subject: [PATCH] sched domain: increase the SMT busy rebalance interval With SMT, if the logical processor is busy, load balance happens for every 8msec(min)-16msec(max). There is no need to do this often, as this is just for fairness(to maintain uniform runqueue lengths) and default time slice anyhow is 100msec. Appended patch increases this interval to 64msec(min)-128msec(max) when the logical processor is busy. Signed-off-by: Suresh Siddha Cc: Nick Piggin Acked-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/topology.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/topology.h b/include/linux/topology.h index da508d1998e4..b93bb6cc6cc2 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -93,7 +93,7 @@ .groups = NULL, \ .min_interval = 1, \ .max_interval = 2, \ - .busy_factor = 8, \ + .busy_factor = 64, \ .imbalance_pct = 110, \ .cache_nice_tries = 0, \ .per_cpu_gain = 25, \ -- cgit v1.2.3 From c9819f4593e8d052b41a89f47140f5c5e7e30582 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Sun, 10 Dec 2006 02:20:25 -0800 Subject: [PATCH] sched: use softirq for load balancing Call rebalance_tick (renamed to run_rebalance_domains) from a newly introduced softirq. We calculate the earliest time for each layer of sched domains to be rescanned (this is the rescan time for idle) and use the earliest of those to schedule the softirq via a new field "next_balance" added to struct rq. Signed-off-by: Christoph Lameter Cc: Peter Williams Cc: Nick Piggin Cc: Christoph Lameter Cc: "Siddha, Suresh B" Cc: "Chen, Kenneth W" Acked-by: Ingo Molnar Cc: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/interrupt.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index de7593f4e895..e36e86c869fb 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -231,7 +231,8 @@ enum NET_TX_SOFTIRQ, NET_RX_SOFTIRQ, BLOCK_SOFTIRQ, - TASKLET_SOFTIRQ + TASKLET_SOFTIRQ, + SCHED_SOFTIRQ, }; /* softirq mask and active fields moved to irq_cpustat_t in -- cgit v1.2.3 From 08c183f31bdbb709f177f6d3110d5f288ea33933 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Sun, 10 Dec 2006 02:20:29 -0800 Subject: [PATCH] sched: add option to serialize load balancing Large sched domains can be very expensive to scan. Add an option SD_SERIALIZE to the sched domain flags. If that flag is set then we make sure that no other such domain is being balanced. [akpm@osdl.org: build fix] Signed-off-by: Christoph Lameter Cc: Peter Williams Cc: Nick Piggin Cc: Christoph Lameter Cc: "Siddha, Suresh B" Cc: "Chen, Kenneth W" Acked-by: Ingo Molnar Cc: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 1 + include/linux/topology.h | 3 ++- 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 1208feab46e0..ea92e5c89089 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -648,6 +648,7 @@ enum idle_type #define SD_SHARE_CPUPOWER 128 /* Domain members share cpu power */ #define SD_POWERSAVINGS_BALANCE 256 /* Balance for power savings */ #define SD_SHARE_PKG_RESOURCES 512 /* Domain members share cpu pkg resources */ +#define SD_SERIALIZE 1024 /* Only a single load balancing instance */ #define BALANCE_FOR_MC_POWER \ (sched_smt_power_savings ? SD_POWERSAVINGS_BALANCE : 0) diff --git a/include/linux/topology.h b/include/linux/topology.h index b93bb6cc6cc2..6c5a6e6e813b 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -194,7 +194,8 @@ .wake_idx = 0, /* unused */ \ .forkexec_idx = 0, /* unused */ \ .per_cpu_gain = 100, \ - .flags = SD_LOAD_BALANCE, \ + .flags = SD_LOAD_BALANCE \ + | SD_SERIALIZE, \ .last_balance = jiffies, \ .balance_interval = 64, \ .nr_balance_failed = 0, \ -- cgit v1.2.3 From 783609c6cb4eaa23f2ac5c968a44483584ec133f Mon Sep 17 00:00:00 2001 From: "Siddha, Suresh B" Date: Sun, 10 Dec 2006 02:20:33 -0800 Subject: [PATCH] sched: decrease number of load balances Currently at a particular domain, each cpu in the sched group will do a load balance at the frequency of balance_interval. More the cores and threads, more the cpus will be in each sched group at SMP and NUMA domain. And we endup spending quite a bit of time doing load balancing in those domains. Fix this by making only one cpu(first idle cpu or first cpu in the group if all the cpus are busy) in the sched group do the load balance at that particular sched domain and this load will slowly percolate down to the other cpus with in that group(when they do load balancing at lower domains). Signed-off-by: Suresh Siddha Cc: Christoph Lameter Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index ea92e5c89089..72d6927d29ed 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -707,6 +707,7 @@ struct sched_domain { unsigned long lb_hot_gained[MAX_IDLE_TYPES]; unsigned long lb_nobusyg[MAX_IDLE_TYPES]; unsigned long lb_nobusyq[MAX_IDLE_TYPES]; + unsigned long lb_stopbalance[MAX_IDLE_TYPES]; /* Active load balancing */ unsigned long alb_cnt; -- cgit v1.2.3 From 06066714f6016cffcb249f6ab21b7919de1bc859 Mon Sep 17 00:00:00 2001 From: "Chen, Kenneth W" Date: Sun, 10 Dec 2006 02:20:35 -0800 Subject: [PATCH] sched: remove lb_stopbalance counter Remove scheduler stats lb_stopbalance counter. This counter can be calculated by: lb_balanced - lb_nobusyg - lb_nobusyq. There is no need to create gazillion counters while we can derive the value. Signed-off-by: Ken Chen Signed-off-by: Suresh Siddha Acked-by: Ingo Molnar 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 72d6927d29ed..ea92e5c89089 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -707,7 +707,6 @@ struct sched_domain { unsigned long lb_hot_gained[MAX_IDLE_TYPES]; unsigned long lb_nobusyg[MAX_IDLE_TYPES]; unsigned long lb_nobusyq[MAX_IDLE_TYPES]; - unsigned long lb_stopbalance[MAX_IDLE_TYPES]; /* Active load balancing */ unsigned long alb_cnt; -- cgit v1.2.3 From ee2f344b33b507af23610c8fdfdde38d7c10fb33 Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Sun, 10 Dec 2006 02:20:39 -0800 Subject: [PATCH] ide-cd: Handle strange interrupt on the Intel ESB2 The ESB2 appears to emit spurious DMA interrupts when configured for native mode and handling ATAPI devices. Stratus were able to pin this bug down and produce a patch. This is a rework which applies the fixup only to the ESB2 (for now). We can apply it to other chips later if the same problem is found. This code has been tested and confirmed to fix the problem on the tested systems. Signed-off-by: Alan Cox (Most of the hard work done by Stratus however) Cc: Jens Axboe Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ide.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 9c2050293f17..64e070f62a87 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -796,6 +796,7 @@ typedef struct hwif_s { unsigned sg_mapped : 1; /* sg_table and sg_nents are ready */ unsigned no_io_32bit : 1; /* 1 = can not do 32-bit IO ops */ unsigned err_stops_fifo : 1; /* 1=data FIFO is cleared by an error */ + unsigned atapi_irq_bogon : 1; /* Generates spurious DMA interrupts in PIO mode */ struct device gendev; struct completion gendev_rel_comp; /* To deal with device release() */ -- cgit v1.2.3 From 46031f9a38a9773021f1872abc713d62467ac22e Mon Sep 17 00:00:00 2001 From: "Raz Ben-Jehuda(caro)" Date: Sun, 10 Dec 2006 02:20:47 -0800 Subject: [PATCH] md: allow reads that have bypassed the cache to be retried on failure If a bypass-the-cache read fails, we simply try again through the cache. If it fails again it will trigger normal recovery precedures. update 1: From: NeilBrown 1/ chunk_aligned_read and retry_aligned_read assume that data_disks == raid_disks - 1 which is not true for raid6. So when an aligned read request bypasses the cache, we can get the wrong data. 2/ The cloned bio is being used-after-free in raid5_align_endio (to test BIO_UPTODATE). 3/ We forgot to add rdev->data_offset when submitting a bio for aligned-read 4/ clone_bio calls blk_recount_segments and then we change bi_bdev, so we need to invalidate the segment counts. 5/ We don't de-reference the rdev when the read completes. This means we need to record the rdev to so it is still available in the end_io routine. Fortunately bi_next in the original bio is unused at this point so we can stuff it in there. 6/ We leak a cloned bio if the target rdev is not usable. From: NeilBrown update 2: 1/ When aligned requests fail (read error) they need to be retried via the normal method (stripe cache). As we cannot be sure that we can process a single read in one go (we may not be able to allocate all the stripes needed) we store a bio-being-retried and a list of bioes-that-still-need-to-be-retried. When find a bio that needs to be retried, we should add it to the list, not to single-bio... 2/ We were never incrementing 'scnt' when resubmitting failed aligned requests. [akpm@osdl.org: build fix] Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/raid/raid5.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/raid/raid5.h b/include/linux/raid/raid5.h index 03636d7918fe..d8286db60b96 100644 --- a/include/linux/raid/raid5.h +++ b/include/linux/raid/raid5.h @@ -227,7 +227,10 @@ struct raid5_private_data { struct list_head handle_list; /* stripes needing handling */ struct list_head delayed_list; /* stripes that have plugged requests */ struct list_head bitmap_list; /* stripes delaying awaiting bitmap update */ + struct bio *retry_read_aligned; /* currently retrying aligned bios */ + struct bio *retry_read_aligned_list; /* aligned bios retry list */ atomic_t preread_active_stripes; /* stripes with scheduled io */ + atomic_t active_aligned_reads; atomic_t reshape_stripes; /* stripes with pending writes for reshape */ /* unfortunately we need two cache names as we temporarily have -- cgit v1.2.3 From bbea9f69668a3d0cf9feba15a724cd02896f8675 Mon Sep 17 00:00:00 2001 From: Vadim Lobanov Date: Sun, 10 Dec 2006 02:21:12 -0800 Subject: [PATCH] fdtable: Make fdarray and fdsets equal in size Currently, each fdtable supports three dynamically-sized arrays of data: the fdarray and two fdsets. The code allows the number of fds supported by the fdarray (fdtable->max_fds) to differ from the number of fds supported by each of the fdsets (fdtable->max_fdset). In practice, it is wasteful for these two sizes to differ: whenever we hit a limit on the smaller-capacity structure, we will reallocate the entire fdtable and all the dynamic arrays within it, so any delta in the memory used by the larger-capacity structure will never be touched at all. Rather than hogging this excess, we shouldn't even allocate it in the first place, and keep the capacities of the fdarray and the fdsets equal. This patch removes fdtable->max_fdset. As an added bonus, most of the supporting code becomes simpler. Signed-off-by: Vadim Lobanov Cc: Christoph Hellwig Cc: Al Viro Cc: Dipankar Sarma Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/file.h | 6 ------ include/linux/init_task.h | 1 - 2 files changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/file.h b/include/linux/file.h index 6e77b9177f9e..02be4012225b 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -26,14 +26,8 @@ struct embedded_fd_set { unsigned long fds_bits[1]; }; -/* - * More than this number of fds: we use a separately allocated fd_set - */ -#define EMBEDDED_FD_SET_SIZE (BITS_PER_BYTE * sizeof(struct embedded_fd_set)) - struct fdtable { unsigned int max_fds; - int max_fdset; struct file ** fd; /* current fd array */ fd_set *close_on_exec; fd_set *open_fds; diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 7272ff9ee77c..58c18daab65d 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -12,7 +12,6 @@ #define INIT_FDTABLE \ { \ .max_fds = NR_OPEN_DEFAULT, \ - .max_fdset = EMBEDDED_FD_SET_SIZE, \ .fd = &init_files.fd_array[0], \ .close_on_exec = (fd_set *)&init_files.close_on_exec_init, \ .open_fds = (fd_set *)&init_files.open_fds_init, \ -- cgit v1.2.3 From 4fd45812cbe875a620c86a096a5d46c742694b7e Mon Sep 17 00:00:00 2001 From: Vadim Lobanov Date: Sun, 10 Dec 2006 02:21:17 -0800 Subject: [PATCH] fdtable: Remove the free_files field An fdtable can either be embedded inside a files_struct or standalone (after being expanded). When an fdtable is being discarded after all RCU references to it have expired, we must either free it directly, in the standalone case, or free the files_struct it is contained within, in the embedded case. Currently the free_files field controls this behavior, but we can get rid of it entirely, as all the necessary information is already recorded. We can distinguish embedded and standalone fdtables using max_fds, and if it is embedded we can divine the relevant files_struct using container_of(). Signed-off-by: Vadim Lobanov Cc: Christoph Hellwig Cc: Al Viro Cc: Dipankar Sarma Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/file.h | 3 +-- include/linux/init_task.h | 1 - 2 files changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/file.h b/include/linux/file.h index 02be4012225b..319118f275b0 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -32,7 +32,6 @@ struct fdtable { fd_set *close_on_exec; fd_set *open_fds; struct rcu_head rcu; - struct files_struct *free_files; struct fdtable *next; }; @@ -84,7 +83,7 @@ extern fd_set *alloc_fdset(int); extern void free_fdset(fd_set *, int); extern int expand_files(struct files_struct *, int nr); -extern void free_fdtable(struct fdtable *fdt); +extern void free_fdtable_rcu(struct rcu_head *rcu); extern void __init files_defer_init(void); static inline struct file * fcheck_files(struct files_struct *files, unsigned int fd) diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 58c18daab65d..b5315150199e 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -16,7 +16,6 @@ .close_on_exec = (fd_set *)&init_files.close_on_exec_init, \ .open_fds = (fd_set *)&init_files.open_fds_init, \ .rcu = RCU_HEAD_INIT, \ - .free_files = NULL, \ .next = NULL, \ } -- cgit v1.2.3 From 5466b456ed6748e0bfe02831e570004d4c04c1d7 Mon Sep 17 00:00:00 2001 From: Vadim Lobanov Date: Sun, 10 Dec 2006 02:21:22 -0800 Subject: [PATCH] fdtable: Implement new pagesize-based fdtable allocator This patch provides an improved fdtable allocation scheme, useful for expanding fdtable file descriptor entries. The main focus is on the fdarray, as its memory usage grows 128 times faster than that of an fdset. The allocation algorithm sizes the fdarray in such a way that its memory usage increases in easy page-sized chunks. The overall algorithm expands the allowed size in powers of two, in order to amortize the cost of invoking vmalloc() for larger allocation sizes. Namely, the following sizes for the fdarray are considered, and the smallest that accommodates the requested fd count is chosen: pagesize / 4 pagesize / 2 pagesize <- memory allocator switch point pagesize * 2 pagesize * 4 ...etc... Unlike the current implementation, this allocation scheme does not require a loop to compute the optimal fdarray size, and can be done in efficient straightline code. Furthermore, since the fdarray overflows the pagesize boundary long before any of the fdsets do, it makes sense to optimize run-time by allocating both fdsets in a single swoop. Even together, they will still be, by far, smaller than the fdarray. The fdtable->open_fds is now used as the anchor for the fdset memory allocation. Signed-off-by: Vadim Lobanov Cc: Christoph Hellwig Cc: Al Viro Cc: Dipankar Sarma Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/file.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/file.h b/include/linux/file.h index 319118f275b0..edca361f2ab4 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -76,12 +76,6 @@ extern int get_unused_fd(void); extern void FASTCALL(put_unused_fd(unsigned int fd)); struct kmem_cache; -extern struct file ** alloc_fd_array(int); -extern void free_fd_array(struct file **, int); - -extern fd_set *alloc_fdset(int); -extern void free_fdset(fd_set *, int); - extern int expand_files(struct files_struct *, int nr); extern void free_fdtable_rcu(struct rcu_head *rcu); extern void __init files_defer_init(void); -- cgit v1.2.3 From 4c36a5dec25fb344ad76b11860da3a8b50bd1248 Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Sun, 10 Dec 2006 02:21:24 -0800 Subject: [PATCH] round_jiffies infrastructure Introduce a round_jiffies() function as well as a round_jiffies_relative() function. These functions round a jiffies value to the next whole second. The primary purpose of this rounding is to cause all "we don't care exactly when" timers to happen at the same jiffy. This avoids multiple timers firing within the second for no real reason; with dynamic ticks these extra timers cause wakeups from deep sleep CPU sleep states and thus waste power. The exact wakeup moment is skewed by the cpu number, to avoid all cpus from waking up at the exact same time (and hitting the same lock/cachelines there) [akpm@osdl.org: fix variable type] Signed-off-by: Arjan van de Ven Cc: Thomas Gleixner Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/timer.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/timer.h b/include/linux/timer.h index c982304dbafd..eeef6643d4c6 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -98,4 +98,10 @@ extern void run_local_timers(void); struct hrtimer; extern int it_real_fn(struct hrtimer *); +unsigned long __round_jiffies(unsigned long j, int cpu); +unsigned long __round_jiffies_relative(unsigned long j, int cpu); +unsigned long round_jiffies(unsigned long j); +unsigned long round_jiffies_relative(unsigned long j); + + #endif -- cgit v1.2.3 From f5f1a24a2caa299bb7d294aee92d7dd3410d9ed7 Mon Sep 17 00:00:00 2001 From: Daniel Walker Date: Sun, 10 Dec 2006 02:21:33 -0800 Subject: [PATCH] clocksource: small cleanup Mostly changing alignment. Just some general cleanup. [akpm@osdl.org: build fix] Signed-off-by: Daniel Walker Acked-by: John Stultz Cc: Thomas Gleixner Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/clocksource.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index d852024ed095..1622d23a8dc3 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -159,7 +159,7 @@ static inline s64 cyc2ns(struct clocksource *cs, cycle_t cycles) * Unless you're the timekeeping code, you should not be using this! */ static inline void clocksource_calculate_interval(struct clocksource *c, - unsigned long length_nsec) + unsigned long length_nsec) { u64 tmp; -- cgit v1.2.3 From 6aa8b732ca01c3d7a54e93f4d701b8aabbe60fb7 Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Sun, 10 Dec 2006 02:21:36 -0800 Subject: [PATCH] kvm: userspace interface web site: http://kvm.sourceforge.net mailing list: kvm-devel@lists.sourceforge.net (http://lists.sourceforge.net/lists/listinfo/kvm-devel) The following patchset adds a driver for Intel's hardware virtualization extensions to the x86 architecture. The driver adds a character device (/dev/kvm) that exposes the virtualization capabilities to userspace. Using this driver, a process can run a virtual machine (a "guest") in a fully virtualized PC containing its own virtual hard disks, network adapters, and display. Using this driver, one can start multiple virtual machines on a host. Each virtual machine is a process on the host; a virtual cpu is a thread in that process. kill(1), nice(1), top(1) work as expected. In effect, the driver adds a third execution mode to the existing two: we now have kernel mode, user mode, and guest mode. Guest mode has its own address space mapping guest physical memory (which is accessible to user mode by mmap()ing /dev/kvm). Guest mode has no access to any I/O devices; any such access is intercepted and directed to user mode for emulation. The driver supports i386 and x86_64 hosts and guests. All combinations are allowed except x86_64 guest on i386 host. For i386 guests and hosts, both pae and non-pae paging modes are supported. SMP hosts and UP guests are supported. At the moment only Intel hardware is supported, but AMD virtualization support is being worked on. Performance currently is non-stellar due to the naive implementation of the mmu virtualization, which throws away most of the shadow page table entries every context switch. We plan to address this in two ways: - cache shadow page tables across tlb flushes - wait until AMD and Intel release processors with nested page tables Currently a virtual desktop is responsive but consumes a lot of CPU. Under Windows I tried playing pinball and watching a few flash movies; with a recent CPU one can hardly feel the virtualization. Linux/X is slower, probably due to X being in a separate process. In addition to the driver, you need a slightly modified qemu to provide I/O device emulation and the BIOS. Caveats (akpm: might no longer be true): - The Windows install currently bluescreens due to a problem with the virtual APIC. We are working on a fix. A temporary workaround is to use an existing image or install through qemu - Windows 64-bit does not work. That's also true for qemu, so it's probably a problem with the device model. [bero@arklinux.org: build fix] [simon.kagstrom@bth.se: build fix, other fixes] [uril@qumranet.com: KVM: Expose interrupt bitmap] [akpm@osdl.org: i386 build fix] [mingo@elte.hu: i386 fixes] [rdreier@cisco.com: add log levels to all printks] [randy.dunlap@oracle.com: Fix sparse NULL and C99 struct init warnings] [anthony@codemonkey.ws: KVM: AMD SVM: 32-bit host support] Signed-off-by: Yaniv Kamay Signed-off-by: Avi Kivity Cc: Simon Kagstrom Cc: Bernhard Rosenkraenzer Signed-off-by: Uri Lublin Cc: Ingo Molnar Cc: Roland Dreier Signed-off-by: Randy Dunlap Signed-off-by: Anthony Liguori Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kvm.h | 227 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 227 insertions(+) create mode 100644 include/linux/kvm.h (limited to 'include/linux') diff --git a/include/linux/kvm.h b/include/linux/kvm.h new file mode 100644 index 000000000000..5bb2c3c585c1 --- /dev/null +++ b/include/linux/kvm.h @@ -0,0 +1,227 @@ +#ifndef __LINUX_KVM_H +#define __LINUX_KVM_H + +/* + * Userspace interface for /dev/kvm - kernel based virtual machine + * + * Note: this interface is considered experimental and may change without + * notice. + */ + +#include +#include + +/* + * Architectural interrupt line count, and the size of the bitmap needed + * to hold them. + */ +#define KVM_NR_INTERRUPTS 256 +#define KVM_IRQ_BITMAP_SIZE_BYTES ((KVM_NR_INTERRUPTS + 7) / 8) +#define KVM_IRQ_BITMAP_SIZE(type) (KVM_IRQ_BITMAP_SIZE_BYTES / sizeof(type)) + + +/* for KVM_CREATE_MEMORY_REGION */ +struct kvm_memory_region { + __u32 slot; + __u32 flags; + __u64 guest_phys_addr; + __u64 memory_size; /* bytes */ +}; + +/* for kvm_memory_region::flags */ +#define KVM_MEM_LOG_DIRTY_PAGES 1UL + + +#define KVM_EXIT_TYPE_FAIL_ENTRY 1 +#define KVM_EXIT_TYPE_VM_EXIT 2 + +enum kvm_exit_reason { + KVM_EXIT_UNKNOWN = 0, + KVM_EXIT_EXCEPTION = 1, + KVM_EXIT_IO = 2, + KVM_EXIT_CPUID = 3, + KVM_EXIT_DEBUG = 4, + KVM_EXIT_HLT = 5, + KVM_EXIT_MMIO = 6, +}; + +/* for KVM_RUN */ +struct kvm_run { + /* in */ + __u32 vcpu; + __u32 emulated; /* skip current instruction */ + __u32 mmio_completed; /* mmio request completed */ + + /* out */ + __u32 exit_type; + __u32 exit_reason; + __u32 instruction_length; + union { + /* KVM_EXIT_UNKNOWN */ + struct { + __u32 hardware_exit_reason; + } hw; + /* KVM_EXIT_EXCEPTION */ + struct { + __u32 exception; + __u32 error_code; + } ex; + /* KVM_EXIT_IO */ + struct { +#define KVM_EXIT_IO_IN 0 +#define KVM_EXIT_IO_OUT 1 + __u8 direction; + __u8 size; /* bytes */ + __u8 string; + __u8 string_down; + __u8 rep; + __u8 pad; + __u16 port; + __u64 count; + union { + __u64 address; + __u32 value; + }; + } io; + struct { + } debug; + /* KVM_EXIT_MMIO */ + struct { + __u64 phys_addr; + __u8 data[8]; + __u32 len; + __u8 is_write; + } mmio; + }; +}; + +/* for KVM_GET_REGS and KVM_SET_REGS */ +struct kvm_regs { + /* in */ + __u32 vcpu; + __u32 padding; + + /* out (KVM_GET_REGS) / in (KVM_SET_REGS) */ + __u64 rax, rbx, rcx, rdx; + __u64 rsi, rdi, rsp, rbp; + __u64 r8, r9, r10, r11; + __u64 r12, r13, r14, r15; + __u64 rip, rflags; +}; + +struct kvm_segment { + __u64 base; + __u32 limit; + __u16 selector; + __u8 type; + __u8 present, dpl, db, s, l, g, avl; + __u8 unusable; + __u8 padding; +}; + +struct kvm_dtable { + __u64 base; + __u16 limit; + __u16 padding[3]; +}; + +/* for KVM_GET_SREGS and KVM_SET_SREGS */ +struct kvm_sregs { + /* in */ + __u32 vcpu; + __u32 padding; + + /* out (KVM_GET_SREGS) / in (KVM_SET_SREGS) */ + struct kvm_segment cs, ds, es, fs, gs, ss; + struct kvm_segment tr, ldt; + struct kvm_dtable gdt, idt; + __u64 cr0, cr2, cr3, cr4, cr8; + __u64 efer; + __u64 apic_base; + __u64 interrupt_bitmap[KVM_IRQ_BITMAP_SIZE(__u64)]; +}; + +struct kvm_msr_entry { + __u32 index; + __u32 reserved; + __u64 data; +}; + +/* for KVM_GET_MSRS and KVM_SET_MSRS */ +struct kvm_msrs { + __u32 vcpu; + __u32 nmsrs; /* number of msrs in entries */ + + struct kvm_msr_entry entries[0]; +}; + +/* for KVM_GET_MSR_INDEX_LIST */ +struct kvm_msr_list { + __u32 nmsrs; /* number of msrs in entries */ + __u32 indices[0]; +}; + +/* for KVM_TRANSLATE */ +struct kvm_translation { + /* in */ + __u64 linear_address; + __u32 vcpu; + __u32 padding; + + /* out */ + __u64 physical_address; + __u8 valid; + __u8 writeable; + __u8 usermode; +}; + +/* for KVM_INTERRUPT */ +struct kvm_interrupt { + /* in */ + __u32 vcpu; + __u32 irq; +}; + +struct kvm_breakpoint { + __u32 enabled; + __u32 padding; + __u64 address; +}; + +/* for KVM_DEBUG_GUEST */ +struct kvm_debug_guest { + /* int */ + __u32 vcpu; + __u32 enabled; + struct kvm_breakpoint breakpoints[4]; + __u32 singlestep; +}; + +/* for KVM_GET_DIRTY_LOG */ +struct kvm_dirty_log { + __u32 slot; + __u32 padding; + union { + void __user *dirty_bitmap; /* one bit per page */ + __u64 padding; + }; +}; + +#define KVMIO 0xAE + +#define KVM_RUN _IOWR(KVMIO, 2, struct kvm_run) +#define KVM_GET_REGS _IOWR(KVMIO, 3, struct kvm_regs) +#define KVM_SET_REGS _IOW(KVMIO, 4, struct kvm_regs) +#define KVM_GET_SREGS _IOWR(KVMIO, 5, struct kvm_sregs) +#define KVM_SET_SREGS _IOW(KVMIO, 6, struct kvm_sregs) +#define KVM_TRANSLATE _IOWR(KVMIO, 7, struct kvm_translation) +#define KVM_INTERRUPT _IOW(KVMIO, 8, struct kvm_interrupt) +#define KVM_DEBUG_GUEST _IOW(KVMIO, 9, struct kvm_debug_guest) +#define KVM_SET_MEMORY_REGION _IOW(KVMIO, 10, struct kvm_memory_region) +#define KVM_CREATE_VCPU _IOW(KVMIO, 11, int /* vcpu_slot */) +#define KVM_GET_DIRTY_LOG _IOW(KVMIO, 12, struct kvm_dirty_log) +#define KVM_GET_MSRS _IOWR(KVMIO, 13, struct kvm_msrs) +#define KVM_SET_MSRS _IOWR(KVMIO, 14, struct kvm_msrs) +#define KVM_GET_MSR_INDEX_LIST _IOWR(KVMIO, 15, struct kvm_msr_list) + +#endif -- cgit v1.2.3 From 36cfb5ccfa39ddd030926d08fcf80ba553c88737 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Sun, 10 Dec 2006 21:21:28 +0100 Subject: i2c: Update the list of driver IDs * A chip driver ID was assigned to the Radeon, while it is an adapter so it needs an i2c adapter ID. * The SAA7191 is a video decoder, not encoder. * The icspll driver is dead, and will never be ported to Linux 2.6. Signed-off-by: Jean Delvare --- include/linux/i2c-id.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c-id.h b/include/linux/i2c-id.h index 0a8f750cbede..36f0c5b0cbf7 100644 --- a/include/linux/i2c-id.h +++ b/include/linux/i2c-id.h @@ -82,9 +82,8 @@ #define I2C_DRIVERID_STM41T00 52 /* real time clock */ #define I2C_DRIVERID_UDA1342 53 /* UDA1342 audio codec */ #define I2C_DRIVERID_ADV7170 54 /* video encoder */ -#define I2C_DRIVERID_RADEON 55 /* I2C bus on Radeon boards */ #define I2C_DRIVERID_MAX1617 56 /* temp sensor */ -#define I2C_DRIVERID_SAA7191 57 /* video encoder */ +#define I2C_DRIVERID_SAA7191 57 /* video decoder */ #define I2C_DRIVERID_INDYCAM 58 /* SGI IndyCam */ #define I2C_DRIVERID_BT832 59 /* CMOS camera video processor */ #define I2C_DRIVERID_TDA9887 60 /* TDA988x IF-PLL demodulator */ @@ -132,7 +131,6 @@ #define I2C_DRIVERID_ADM1021 1008 #define I2C_DRIVERID_ADM9240 1009 #define I2C_DRIVERID_LTC1710 1010 -#define I2C_DRIVERID_ICSPLL 1012 #define I2C_DRIVERID_BT869 1013 #define I2C_DRIVERID_MAXILIFE 1014 #define I2C_DRIVERID_MATORB 1015 -- cgit v1.2.3 From 51fd554b6547b74c7e6d1f52885ba8532b531023 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Sun, 10 Dec 2006 21:21:29 +0100 Subject: i2c: Delete the broken i2c-ite bus driver The rest of the ITE8172 support was already removed from MIPS tree. Signed-off-by: Jean Delvare Signed-off-by: Yoichi Yuasa Acked-by: Ralf Baechle --- include/linux/i2c-algo-ite.h | 72 -------------------------------------------- include/linux/i2c-id.h | 3 -- 2 files changed, 75 deletions(-) delete mode 100644 include/linux/i2c-algo-ite.h (limited to 'include/linux') diff --git a/include/linux/i2c-algo-ite.h b/include/linux/i2c-algo-ite.h deleted file mode 100644 index 0073fe96c76e..000000000000 --- a/include/linux/i2c-algo-ite.h +++ /dev/null @@ -1,72 +0,0 @@ -/* ------------------------------------------------------------------------- */ -/* i2c-algo-ite.h i2c driver algorithms for ITE IIC adapters */ -/* ------------------------------------------------------------------------- */ -/* Copyright (C) 1995-97 Simon G. Vogl - 1998-99 Hans Berglund - - This program is free software; you can redistribute it and/or modify - it under the terms of the GNU General Public License as published by - the Free Software Foundation; either version 2 of the License, or - (at your option) any later version. - - This program is distributed in the hope that it will be useful, - but WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - GNU General Public License for more details. - - You should have received a copy of the GNU General Public License - along with this program; if not, write to the Free Software - Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ -/* ------------------------------------------------------------------------- */ - -/* With some changes from Kyösti Mälkki and even - Frodo Looijaard */ - -/* Modifications by MontaVista Software, 2001 - Changes made to support the ITE IIC peripheral */ - - -#ifndef I2C_ALGO_ITE_H -#define I2C_ALGO_ITE_H 1 - -#include - -/* Example of a sequential read request: - struct i2c_iic_msg s_msg; - - s_msg.addr=device_address; - s_msg.len=length; - s_msg.buf=buffer; - s_msg.waddr=word_address; - ioctl(file,I2C_SREAD, &s_msg); - */ -#define I2C_SREAD 0x780 /* SREAD ioctl command */ - -struct i2c_iic_msg { - __u16 addr; /* device address */ - __u16 waddr; /* word address */ - short len; /* msg length */ - char *buf; /* pointer to msg data */ -}; - -#ifdef __KERNEL__ -struct i2c_adapter; - -struct i2c_algo_iic_data { - void *data; /* private data for lolevel routines */ - void (*setiic) (void *data, int ctl, int val); - int (*getiic) (void *data, int ctl); - int (*getown) (void *data); - int (*getclock) (void *data); - void (*waitforpin) (void); - - /* local settings */ - int udelay; - int mdelay; - int timeout; -}; - -int i2c_iic_add_bus(struct i2c_adapter *); -int i2c_iic_del_bus(struct i2c_adapter *); -#endif /* __KERNEL__ */ -#endif /* I2C_ALGO_ITE_H */ diff --git a/include/linux/i2c-id.h b/include/linux/i2c-id.h index 36f0c5b0cbf7..00da370bbcd6 100644 --- a/include/linux/i2c-id.h +++ b/include/linux/i2c-id.h @@ -210,9 +210,6 @@ /* --- MPC8xx PowerPC adapters */ #define I2C_HW_MPC8XX_EPON 0x110000 /* Eponymous MPC8xx I2C adapter */ -/* --- ITE based algorithms */ -#define I2C_HW_I_IIC 0x080000 /* controller on the ITE */ - /* --- PowerPC on-chip adapters */ #define I2C_HW_OCP 0x120000 /* IBM on-chip I2C adapter */ -- cgit v1.2.3 From 41561f28e76a47dc6de0a954da85d0b5c42874eb Mon Sep 17 00:00:00 2001 From: Vitaly Wool Date: Sun, 10 Dec 2006 21:21:29 +0100 Subject: i2c: New Philips PNX bus driver New I2C bus driver for Philips ARM boards (Philips IP3204 I2C IP block). This I2C controller can be found on (at least) PNX010x, PNX52xx and PNX4008 Philips boards. Signed-off-by: Vitaly Wool Signed-off-by: Jean Delvare --- include/linux/i2c-pnx.h | 43 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 43 insertions(+) create mode 100644 include/linux/i2c-pnx.h (limited to 'include/linux') diff --git a/include/linux/i2c-pnx.h b/include/linux/i2c-pnx.h new file mode 100644 index 000000000000..e6e9c814da61 --- /dev/null +++ b/include/linux/i2c-pnx.h @@ -0,0 +1,43 @@ +/* + * Header file for I2C support on PNX010x/4008. + * + * Author: Dennis Kovalev + * + * 2004-2006 (c) MontaVista Software, Inc. This file is licensed under + * the terms of the GNU General Public License version 2. This program + * is licensed "as is" without any warranty of any kind, whether express + * or implied. + */ + +#ifndef __I2C_PNX_H__ +#define __I2C_PNX_H__ + +#include + +struct i2c_pnx_mif { + int ret; /* Return value */ + int mode; /* Interface mode */ + struct completion complete; /* I/O completion */ + struct timer_list timer; /* Timeout */ + char * buf; /* Data buffer */ + int len; /* Length of data buffer */ +}; + +struct i2c_pnx_algo_data { + u32 base; + u32 ioaddr; + int irq; + struct i2c_pnx_mif mif; + int last; +}; + +struct i2c_pnx_data { + int (*suspend) (struct platform_device *pdev, pm_message_t state); + int (*resume) (struct platform_device *pdev); + u32 (*calculate_input_freq) (struct platform_device *pdev); + int (*set_clock_run) (struct platform_device *pdev); + int (*set_clock_stop) (struct platform_device *pdev); + struct i2c_adapter *adapter; +}; + +#endif /* __I2C_PNX_H__ */ -- cgit v1.2.3 From 6ea23039cb1cc7c379eb5fba0ed2c53291e9bea7 Mon Sep 17 00:00:00 2001 From: Jiri Kosina Date: Sun, 10 Dec 2006 21:21:30 +0100 Subject: i2c: Add support for nested i2c bus locking This patch adds the 'level' field into the i2c_adapter structure, which is used to represent the 'logical' level of nesting for the purposes of lockdep. This field is then used in the i2c_transfer() function, to acquire the per-adapter bus_lock with correct nesting level. Signed-off-by: Jiri Kosina Signed-off-by: Jean Delvare --- include/linux/i2c.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 9b5d04768c2c..08df4169b411 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -216,6 +216,7 @@ struct i2c_adapter { int (*client_unregister)(struct i2c_client *); /* data fields that are valid for all devices */ + u8 level; /* nesting level for lockdep */ struct mutex bus_lock; struct mutex clist_lock; -- cgit v1.2.3 From 438d6c2c015cf63bf7e9bdc2033d435433ac8455 Mon Sep 17 00:00:00 2001 From: David Brownell Date: Sun, 10 Dec 2006 21:21:31 +0100 Subject: i2c: Whitespace cleanups Remove extraneous whitespace from various i2c headers and core files, like space-before-tab and whitespace at end of line. Signed-off-by: David Brownell Signed-off-by: Jean Delvare --- include/linux/i2c-algo-bit.h | 4 +-- include/linux/i2c-algo-pcf.h | 2 +- include/linux/i2c-id.h | 10 +++--- include/linux/i2c.h | 74 ++++++++++++++++++++++---------------------- 4 files changed, 45 insertions(+), 45 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c-algo-bit.h b/include/linux/i2c-algo-bit.h index c8f8df25c7e0..a99e28a86c3b 100644 --- a/include/linux/i2c-algo-bit.h +++ b/include/linux/i2c-algo-bit.h @@ -26,9 +26,9 @@ /* --- Defines for bit-adapters --------------------------------------- */ /* - * This struct contains the hw-dependent functions of bit-style adapters to + * This struct contains the hw-dependent functions of bit-style adapters to * manipulate the line states, and to init any hw-specific features. This is - * only used if you have more than one hw-type of adapter running. + * only used if you have more than one hw-type of adapter running. */ struct i2c_algo_bit_data { void *data; /* private data for lowlevel routines */ diff --git a/include/linux/i2c-algo-pcf.h b/include/linux/i2c-algo-pcf.h index 9908f3fc4839..7d7045cbb344 100644 --- a/include/linux/i2c-algo-pcf.h +++ b/include/linux/i2c-algo-pcf.h @@ -31,7 +31,7 @@ struct i2c_algo_pcf_data { int (*getpcf) (void *data, int ctl); int (*getown) (void *data); int (*getclock) (void *data); - void (*waitforpin) (void); + void (*waitforpin) (void); /* local settings */ int udelay; diff --git a/include/linux/i2c-id.h b/include/linux/i2c-id.h index 00da370bbcd6..5b97f1cce7a5 100644 --- a/include/linux/i2c-id.h +++ b/include/linux/i2c-id.h @@ -1,7 +1,7 @@ /* ------------------------------------------------------------------------- */ -/* */ +/* */ /* i2c-id.h - identifier values for i2c drivers and adapters */ -/* */ +/* */ /* ------------------------------------------------------------------------- */ /* Copyright (C) 1995-1999 Simon G. Vogl @@ -40,10 +40,10 @@ #define I2C_DRIVERID_SAA7120 11 /* video encoder */ #define I2C_DRIVERID_SAA7121 12 /* video encoder */ #define I2C_DRIVERID_SAA7185B 13 /* video encoder */ -#define I2C_DRIVERID_CH7003 14 /* digital pc to tv encoder */ +#define I2C_DRIVERID_CH7003 14 /* digital pc to tv encoder */ #define I2C_DRIVERID_PCF8574A 15 /* i2c expander - 8 bit in/out */ #define I2C_DRIVERID_PCF8582C 16 /* eeprom */ -#define I2C_DRIVERID_AT24Cxx 17 /* eeprom 1/2/4/8/16 K */ +#define I2C_DRIVERID_AT24Cxx 17 /* eeprom 1/2/4/8/16 K */ #define I2C_DRIVERID_TEA6300 18 /* audio mixer */ #define I2C_DRIVERID_BT829 19 /* pc to tv encoder */ #define I2C_DRIVERID_TDA9850 20 /* audio mixer */ @@ -162,7 +162,7 @@ * ---- Adapter types ---------------------------------------------------- */ -/* --- Bit algorithm adapters */ +/* --- Bit algorithm adapters */ #define I2C_HW_B_LP 0x010000 /* Parallel port Philips style */ #define I2C_HW_B_SER 0x010002 /* Serial line interface */ #define I2C_HW_B_BT848 0x010005 /* BT848 video boards */ diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 08df4169b411..71e50d3e492f 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -1,7 +1,7 @@ /* ------------------------------------------------------------------------- */ -/* */ +/* */ /* i2c.h - definitions for the i2c-bus interface */ -/* */ +/* */ /* ------------------------------------------------------------------------- */ /* Copyright (C) 1995-2000 Simon G. Vogl @@ -27,7 +27,7 @@ #define _LINUX_I2C_H #include -#ifdef __KERNEL__ +#ifdef __KERNEL__ #include #include #include @@ -53,8 +53,8 @@ union i2c_smbus_data; /* * The master routines are the ones normally used to transmit data to devices - * on a bus (or read from them). Apart from two basic transfer functions to - * transmit one message at a time, a more complex version can be used to + * on a bus (or read from them). Apart from two basic transfer functions to + * transmit one message at a time, a more complex version can be used to * transmit an arbitrary number of messages without interruption. */ extern int i2c_master_send(struct i2c_client *,const char* ,int); @@ -67,10 +67,10 @@ extern int i2c_transfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num) /* This is the very generalized SMBus access routine. You probably do not want to use this, though; one of the functions below may be much easier, - and probably just as fast. + and probably just as fast. Note that we use i2c_adapter here, because you do not need a specific smbus adapter to call this function. */ -extern s32 i2c_smbus_xfer (struct i2c_adapter * adapter, u16 addr, +extern s32 i2c_smbus_xfer (struct i2c_adapter * adapter, u16 addr, unsigned short flags, char read_write, u8 command, int size, union i2c_smbus_data * data); @@ -112,14 +112,14 @@ struct i2c_driver { /* Notifies the driver that a new bus has appeared. This routine * can be used by the driver to test if the bus meets its conditions - * & seek for the presence of the chip(s) it supports. If found, it + * & seek for the presence of the chip(s) it supports. If found, it * registers the client(s) that are on the bus to the i2c admin. via * i2c_attach_client. */ int (*attach_adapter)(struct i2c_adapter *); int (*detach_adapter)(struct i2c_adapter *); - /* tells the driver that a client is about to be deleted & gives it + /* tells the driver that a client is about to be deleted & gives it * the chance to remove its private data. Also, if the client struct * has been dynamically allocated by the driver in the function above, * it must be freed here. @@ -139,13 +139,13 @@ struct i2c_driver { #define I2C_NAME_SIZE 50 /* - * i2c_client identifies a single device (i.e. chip) that is connected to an + * i2c_client identifies a single device (i.e. chip) that is connected to an * i2c bus. The behaviour is defined by the routines of the driver. This * function is mainly used for lookup & other admin. functions. */ struct i2c_client { unsigned int flags; /* div., see below */ - unsigned short addr; /* chip address - NOTE: 7bit */ + unsigned short addr; /* chip address - NOTE: 7bit */ /* addresses are stored in the */ /* _LOWER_ 7 bits */ struct i2c_adapter *adapter; /* the adapter we sit on */ @@ -182,14 +182,14 @@ static inline void i2c_set_clientdata (struct i2c_client *dev, void *data) */ struct i2c_algorithm { /* If an adapter algorithm can't do I2C-level access, set master_xfer - to NULL. If an adapter algorithm can do SMBus access, set + to NULL. If an adapter algorithm can do SMBus access, set smbus_xfer. If set to NULL, the SMBus protocol is simulated using common I2C messages */ /* master_xfer should return the number of messages successfully processed, or a negative value on error */ - int (*master_xfer)(struct i2c_adapter *adap,struct i2c_msg *msgs, + int (*master_xfer)(struct i2c_adapter *adap,struct i2c_msg *msgs, int num); - int (*smbus_xfer) (struct i2c_adapter *adap, u16 addr, + int (*smbus_xfer) (struct i2c_adapter *adap, u16 addr, unsigned short flags, char read_write, u8 command, int size, union i2c_smbus_data * data); @@ -317,7 +317,7 @@ extern int i2c_check_addr (struct i2c_adapter *adapter, int addr); * It will only call found_proc if some client is connected at the * specific address (unless a 'force' matched); */ -extern int i2c_probe(struct i2c_adapter *adapter, +extern int i2c_probe(struct i2c_adapter *adapter, struct i2c_client_address_data *address_data, int (*found_proc) (struct i2c_adapter *, int, int)); @@ -353,15 +353,15 @@ static inline int i2c_adapter_id(struct i2c_adapter *adap) */ struct i2c_msg { __u16 addr; /* slave address */ - __u16 flags; + __u16 flags; #define I2C_M_TEN 0x10 /* we have a ten bit chip address */ #define I2C_M_RD 0x01 #define I2C_M_NOSTART 0x4000 #define I2C_M_REV_DIR_ADDR 0x2000 #define I2C_M_IGNORE_NAK 0x1000 #define I2C_M_NO_RD_ACK 0x0800 - __u16 len; /* msg length */ - __u8 *buf; /* pointer to msg data */ + __u16 len; /* msg length */ + __u8 *buf; /* pointer to msg data */ }; /* To determine what functionality is present */ @@ -371,16 +371,16 @@ struct i2c_msg { #define I2C_FUNC_PROTOCOL_MANGLING 0x00000004 /* I2C_M_{REV_DIR_ADDR,NOSTART,..} */ #define I2C_FUNC_SMBUS_HWPEC_CALC 0x00000008 /* SMBus 2.0 */ #define I2C_FUNC_SMBUS_BLOCK_PROC_CALL 0x00008000 /* SMBus 2.0 */ -#define I2C_FUNC_SMBUS_QUICK 0x00010000 -#define I2C_FUNC_SMBUS_READ_BYTE 0x00020000 -#define I2C_FUNC_SMBUS_WRITE_BYTE 0x00040000 -#define I2C_FUNC_SMBUS_READ_BYTE_DATA 0x00080000 -#define I2C_FUNC_SMBUS_WRITE_BYTE_DATA 0x00100000 -#define I2C_FUNC_SMBUS_READ_WORD_DATA 0x00200000 -#define I2C_FUNC_SMBUS_WRITE_WORD_DATA 0x00400000 -#define I2C_FUNC_SMBUS_PROC_CALL 0x00800000 -#define I2C_FUNC_SMBUS_READ_BLOCK_DATA 0x01000000 -#define I2C_FUNC_SMBUS_WRITE_BLOCK_DATA 0x02000000 +#define I2C_FUNC_SMBUS_QUICK 0x00010000 +#define I2C_FUNC_SMBUS_READ_BYTE 0x00020000 +#define I2C_FUNC_SMBUS_WRITE_BYTE 0x00040000 +#define I2C_FUNC_SMBUS_READ_BYTE_DATA 0x00080000 +#define I2C_FUNC_SMBUS_WRITE_BYTE_DATA 0x00100000 +#define I2C_FUNC_SMBUS_READ_WORD_DATA 0x00200000 +#define I2C_FUNC_SMBUS_WRITE_WORD_DATA 0x00400000 +#define I2C_FUNC_SMBUS_PROC_CALL 0x00800000 +#define I2C_FUNC_SMBUS_READ_BLOCK_DATA 0x01000000 +#define I2C_FUNC_SMBUS_WRITE_BLOCK_DATA 0x02000000 #define I2C_FUNC_SMBUS_READ_I2C_BLOCK 0x04000000 /* I2C-like block xfer */ #define I2C_FUNC_SMBUS_WRITE_I2C_BLOCK 0x08000000 /* w/ 1-byte reg. addr. */ #define I2C_FUNC_SMBUS_READ_I2C_BLOCK_2 0x10000000 /* I2C-like block xfer */ @@ -407,10 +407,10 @@ struct i2c_msg { I2C_FUNC_SMBUS_WRITE_BLOCK_DATA | \ I2C_FUNC_SMBUS_I2C_BLOCK) -/* - * Data for SMBus Messages +/* + * Data for SMBus Messages */ -#define I2C_SMBUS_BLOCK_MAX 32 /* As specified in SMBus standard */ +#define I2C_SMBUS_BLOCK_MAX 32 /* As specified in SMBus standard */ union i2c_smbus_data { __u8 byte; __u16 word; @@ -422,11 +422,11 @@ union i2c_smbus_data { #define I2C_SMBUS_READ 1 #define I2C_SMBUS_WRITE 0 -/* SMBus transaction types (size parameter in the above functions) +/* SMBus transaction types (size parameter in the above functions) Note: these no longer correspond to the (arbitrary) PIIX4 internal codes! */ #define I2C_SMBUS_QUICK 0 #define I2C_SMBUS_BYTE 1 -#define I2C_SMBUS_BYTE_DATA 2 +#define I2C_SMBUS_BYTE_DATA 2 #define I2C_SMBUS_WORD_DATA 3 #define I2C_SMBUS_PROC_CALL 4 #define I2C_SMBUS_BLOCK_DATA 5 @@ -435,15 +435,15 @@ union i2c_smbus_data { /* ----- commands for the ioctl like i2c_command call: - * note that additional calls are defined in the algorithm and hw - * dependent layers - these can be listed here, or see the + * note that additional calls are defined in the algorithm and hw + * dependent layers - these can be listed here, or see the * corresponding header files. */ /* -> bit-adapter specific ioctls */ #define I2C_RETRIES 0x0701 /* number of times a device address */ /* should be polled when not */ - /* acknowledging */ -#define I2C_TIMEOUT 0x0702 /* set timeout - call with int */ + /* acknowledging */ +#define I2C_TIMEOUT 0x0702 /* set timeout - call with int */ /* this is for i2c-dev.c */ -- cgit v1.2.3 From 3269711b76ba27b78862c48398b0d313ccaa99c2 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Sun, 10 Dec 2006 21:21:33 +0100 Subject: i2c: Discard the i2c algo del_bus wrappers They are all only calling i2c_del_adapter, so we may as well do it directly. Signed-off-by: Jean Delvare --- include/linux/i2c-algo-bit.h | 1 - include/linux/i2c-algo-pca.h | 1 - include/linux/i2c-algo-pcf.h | 1 - include/linux/i2c-algo-sgi.h | 1 - 4 files changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c-algo-bit.h b/include/linux/i2c-algo-bit.h index a99e28a86c3b..937da70cb4c4 100644 --- a/include/linux/i2c-algo-bit.h +++ b/include/linux/i2c-algo-bit.h @@ -44,6 +44,5 @@ struct i2c_algo_bit_data { }; int i2c_bit_add_bus(struct i2c_adapter *); -int i2c_bit_del_bus(struct i2c_adapter *); #endif /* _LINUX_I2C_ALGO_BIT_H */ diff --git a/include/linux/i2c-algo-pca.h b/include/linux/i2c-algo-pca.h index 226693e0d88b..fce47c051bb1 100644 --- a/include/linux/i2c-algo-pca.h +++ b/include/linux/i2c-algo-pca.h @@ -10,6 +10,5 @@ struct i2c_algo_pca_data { }; int i2c_pca_add_bus(struct i2c_adapter *); -int i2c_pca_del_bus(struct i2c_adapter *); #endif /* _LINUX_I2C_ALGO_PCA_H */ diff --git a/include/linux/i2c-algo-pcf.h b/include/linux/i2c-algo-pcf.h index 7d7045cbb344..994eb86f882c 100644 --- a/include/linux/i2c-algo-pcf.h +++ b/include/linux/i2c-algo-pcf.h @@ -39,6 +39,5 @@ struct i2c_algo_pcf_data { }; int i2c_pcf_add_bus(struct i2c_adapter *); -int i2c_pcf_del_bus(struct i2c_adapter *); #endif /* _LINUX_I2C_ALGO_PCF_H */ diff --git a/include/linux/i2c-algo-sgi.h b/include/linux/i2c-algo-sgi.h index 4a0113d64064..3b7715024e69 100644 --- a/include/linux/i2c-algo-sgi.h +++ b/include/linux/i2c-algo-sgi.h @@ -22,6 +22,5 @@ struct i2c_algo_sgi_data { }; int i2c_sgi_add_bus(struct i2c_adapter *); -int i2c_sgi_del_bus(struct i2c_adapter *); #endif /* I2C_ALGO_SGI_H */ -- cgit v1.2.3 From d10f73480b991da2aa1c000ed38eda3e4a987292 Mon Sep 17 00:00:00 2001 From: Kumar Gala Date: Sun, 10 Dec 2006 23:26:16 -0600 Subject: [PPC] Fix compile failure do to introduction of PHY_POLL PHY_POLL is defined in include it in so board code will have it defined. Signed-off-by: Kumar Gala --- include/linux/fsl_devices.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fsl_devices.h b/include/linux/fsl_devices.h index 3da29e2d524a..abb64c437f6f 100644 --- a/include/linux/fsl_devices.h +++ b/include/linux/fsl_devices.h @@ -19,6 +19,7 @@ #define _FSL_DEVICE_H_ #include +#include /* * Some conventions on how we handle peripherals on Freescale chips -- cgit v1.2.3 From 8993780a6e44fb4e7ed34e33458506a775356c6e Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 11 Dec 2006 09:28:46 -0800 Subject: Make SLES9 "get_kernel_version" work on the kernel binary again As reported by Andy Whitcroft, at least the SLES9 initrd build process depends on getting the kernel version from the kernel binary. It does that by simply trawling the binary and looking for the signature of the "linux_banner" string (the string "Linux version " to be exact. Which is really broken in itself, but whatever..) That got broken when the string was changed to allow /proc/version to change the UTS release information dynamically, and "get_kernel_version" thus returned "%s" (see commit a2ee8649ba6d71416712e798276bf7c40b64e6e5: "[PATCH] Fix linux banner utsname information"). This just restores "linux_banner" as a static string, which should fix the version finding. And /proc/version simply uses a different string. To avoid wasting even that miniscule amount of memory, the early boot string should really be marked __initdata, but that just causes the same bug in SLES9 to re-appear, since it will then find other occurrences of "Linux version " first. Cc: Andy Whitcroft Acked-by: Herbert Poetzl Cc: Andi Kleen Cc: Andrew Morton Cc: Steve Fox Acked-by: Olaf Hering Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index e8bfac34d2ba..b0c4a05a4b0c 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -17,8 +17,6 @@ #include #include -extern const char linux_banner[]; - #define INT_MAX ((int)(~0U>>1)) #define INT_MIN (-INT_MAX - 1) #define UINT_MAX (~0U) -- cgit v1.2.3 From 8d610dd52dd1da696e199e4b4545f33a2a5de5c6 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 11 Dec 2006 12:12:04 -0800 Subject: Make sure we populate the initroot filesystem late enough We should not initialize rootfs before all the core initializers have run. So do it as a separate stage just before starting the regular driver initializers. Signed-off-by: Linus Torvalds --- include/linux/init.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/init.h b/include/linux/init.h index 5eb5d24b7680..5a593a1dec1e 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -111,6 +111,7 @@ extern void setup_arch(char **); #define subsys_initcall_sync(fn) __define_initcall("4s",fn,4s) #define fs_initcall(fn) __define_initcall("5",fn,5) #define fs_initcall_sync(fn) __define_initcall("5s",fn,5s) +#define rootfs_initcall(fn) __define_initcall("rootfs",fn,rootfs) #define device_initcall(fn) __define_initcall("6",fn,6) #define device_initcall_sync(fn) __define_initcall("6s",fn,6s) #define late_initcall(fn) __define_initcall("7",fn,7) -- cgit v1.2.3 From 1a21e49a8d60f588c1276f765198b14d5688a778 Mon Sep 17 00:00:00 2001 From: Gerrit Renker Date: Sun, 10 Dec 2006 00:02:12 -0200 Subject: [DCCP] ccid3: Finer-grained resolution of sending rates This patch * resolves a bug where packets smaller than 32/64 bytes resulted in sending rates of 0 * supports all sending rates from 1/64 bytes/second up to 4Gbyte/second * simplifies the present overflow problems in calculations Current sending rate X and the cached value X_recv of the receiver-estimated sending rate are both scaled by 64 (2^6) in order to * cope with low sending rates (minimally 1 byte/second) * allow upgrading to use a packets-per-second implementation of CCID 3 * avoid calculation errors due to integer arithmetic cut-off The patch implements a revised strategy from http://www.mail-archive.com/dccp@vger.kernel.org/msg01040.html The only difference with regard to that strategy is that t_ipi is already used in the calculation of the nofeedback timeout, which saves one division. Signed-off-by: Gerrit Renker Acked-by: Ian McDonald Signed-off-by: Arnaldo Carvalho de Melo --- include/linux/tfrc.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tfrc.h b/include/linux/tfrc.h index 31a9b25276fe..8a8462b4a4dd 100644 --- a/include/linux/tfrc.h +++ b/include/linux/tfrc.h @@ -37,10 +37,14 @@ struct tfrc_rx_info { * @tfrctx_p: current loss event rate (5.4) * @tfrctx_rto: estimate of RTO, equals 4*RTT (4.3) * @tfrctx_ipi: inter-packet interval (4.6) + * + * Note: X and X_recv are both maintained in units of 64 * bytes/second. This + * enables a finer resolution of sending rates and avoids problems with + * integer arithmetic; u32 is not sufficient as scaling consumes 6 bits. */ struct tfrc_tx_info { - __u32 tfrctx_x; - __u32 tfrctx_x_recv; + __u64 tfrctx_x; + __u64 tfrctx_x_recv; __u32 tfrctx_x_calc; __u32 tfrctx_rtt; __u32 tfrctx_p; -- cgit v1.2.3 From 8109b02b5397ed52a32c116163a62a34f4768b26 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Sun, 10 Dec 2006 16:01:18 -0200 Subject: [DCCP]: Whitespace cleanups That accumulated over the last months hackaton, shame on me for not using git-apply whitespace helping hand, will do that from now on. Signed-off-by: Arnaldo Carvalho de Melo --- include/linux/dccp.h | 26 +++++++++++++------------- 1 file changed, 13 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dccp.h b/include/linux/dccp.h index ed6cc8962d87..1cb054bd93f2 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -176,20 +176,20 @@ enum { }; /* DCCP features (RFC 4340 section 6.4) */ - enum { - DCCPF_RESERVED = 0, - DCCPF_CCID = 1, +enum { + DCCPF_RESERVED = 0, + DCCPF_CCID = 1, DCCPF_SHORT_SEQNOS = 2, /* XXX: not yet implemented */ - DCCPF_SEQUENCE_WINDOW = 3, + DCCPF_SEQUENCE_WINDOW = 3, DCCPF_ECN_INCAPABLE = 4, /* XXX: not yet implemented */ - DCCPF_ACK_RATIO = 5, - DCCPF_SEND_ACK_VECTOR = 6, - DCCPF_SEND_NDP_COUNT = 7, + DCCPF_ACK_RATIO = 5, + DCCPF_SEND_ACK_VECTOR = 6, + DCCPF_SEND_NDP_COUNT = 7, DCCPF_MIN_CSUM_COVER = 8, DCCPF_DATA_CHECKSUM = 9, /* XXX: not yet implemented */ - /* 10-127 reserved */ - DCCPF_MIN_CCID_SPECIFIC = 128, - DCCPF_MAX_CCID_SPECIFIC = 255, + /* 10-127 reserved */ + DCCPF_MIN_CCID_SPECIFIC = 128, + DCCPF_MAX_CCID_SPECIFIC = 255, }; /* this structure is argument to DCCP_SOCKOPT_CHANGE_X */ @@ -427,7 +427,7 @@ struct dccp_service_list { }; #define DCCP_SERVICE_INVALID_VALUE htonl((__u32)-1) -#define DCCP_SERVICE_CODE_IS_ABSENT 0 +#define DCCP_SERVICE_CODE_IS_ABSENT 0 static inline int dccp_list_has_service(const struct dccp_service_list *sl, const __be32 service) @@ -436,7 +436,7 @@ static inline int dccp_list_has_service(const struct dccp_service_list *sl, u32 i = sl->dccpsl_nr; while (i--) if (sl->dccpsl_list[i] == service) - return 1; + return 1; } return 0; } @@ -511,7 +511,7 @@ struct dccp_sock { __u8 dccps_hc_tx_insert_options:1; struct timer_list dccps_xmit_timer; }; - + static inline struct dccp_sock *dccp_sk(const struct sock *sk) { return (struct dccp_sock *)sk; -- cgit v1.2.3 From 2b02a1792000900ead4638f4d42fcdd742062cfa Mon Sep 17 00:00:00 2001 From: Boaz Harrosh Date: Tue, 5 Dec 2006 10:19:14 +0100 Subject: [PATCH] remove blk_queue_activity_fn While working on bidi support at struct request level I have found that blk_queue_activity_fn is actually never used. The only user is in ide-probe.c with this code: /* enable led activity for disk drives only */ if (drive->media == ide_disk && hwif->led_act) blk_queue_activity_fn(q, hwif->led_act, drive); And led_act is never initialized anywhere. (Looking back at older kernels it was used in the PPC arch, but was removed around 2.6.18) Unless it is all for future use off course. (this patch is against linux-2.6-block.git as off 2006/12/4) Signed-off-by: Boaz Harrosh Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 5 ----- include/linux/ide.h | 2 -- 2 files changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index e1c7286165ff..ea330d7b46c0 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -342,7 +342,6 @@ typedef void (unplug_fn) (request_queue_t *); struct bio_vec; typedef int (merge_bvec_fn) (request_queue_t *, struct bio *, struct bio_vec *); -typedef void (activity_fn) (void *data, int rw); typedef int (issue_flush_fn) (request_queue_t *, struct gendisk *, sector_t *); typedef void (prepare_flush_fn) (request_queue_t *, struct request *); typedef void (softirq_done_fn)(struct request *); @@ -384,7 +383,6 @@ struct request_queue prep_rq_fn *prep_rq_fn; unplug_fn *unplug_fn; merge_bvec_fn *merge_bvec_fn; - activity_fn *activity_fn; issue_flush_fn *issue_flush_fn; prepare_flush_fn *prepare_flush_fn; softirq_done_fn *softirq_done_fn; @@ -411,8 +409,6 @@ struct request_queue */ void *queuedata; - void *activity_data; - /* * queue needs bounce pages for pages above this limit */ @@ -677,7 +673,6 @@ extern void blk_sync_queue(struct request_queue *q); extern void __blk_stop_queue(request_queue_t *q); extern void blk_run_queue(request_queue_t *); extern void blk_start_queueing(request_queue_t *); -extern void blk_queue_activity_fn(request_queue_t *, activity_fn *, void *); extern int blk_rq_map_user(request_queue_t *, struct request *, void __user *, unsigned long); extern int blk_rq_unmap_user(struct request *); extern int blk_rq_map_kern(request_queue_t *, struct request *, void *, unsigned int, gfp_t); diff --git a/include/linux/ide.h b/include/linux/ide.h index 64e070f62a87..e26a03981a94 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -804,8 +804,6 @@ typedef struct hwif_s { void *hwif_data; /* extra hwif data */ unsigned dma; - - void (*led_act)(void *data, int rw); } ____cacheline_internodealigned_in_smp ide_hwif_t; /* -- cgit v1.2.3 From 99a3eb3845f034eb55640a3da73e5e28349678c6 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Tue, 12 Dec 2006 12:10:28 +0100 Subject: [PATCH] lockdep: fix seqlock_init() seqlock_init() needs to use spin_lock_init() for dynamic locks, so that lockdep is notified about the presence of a new lock. (this is a fallout of the recent networking merge, which started using the so-far unused seqlock_init() API.) This fix solves the following lockdep-internal warning on current -git: INFO: trying to register non-static key. the code is fine but needs lockdep annotation. turning off the locking correctness validator. __lock_acquire+0x10c/0x9f9 lock_acquire+0x56/0x72 _spin_lock+0x35/0x42 neigh_destroy+0x9d/0x12e neigh_periodic_timer+0x10a/0x15c run_timer_softirq+0x126/0x18e __do_softirq+0x6b/0xe6 do_softirq+0x64/0xd2 ksoftirqd+0x82/0x138 Signed-off-by: Ingo Molnar Signed-off-by: Linus Torvalds --- include/linux/seqlock.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index 46000936f8f1..6b0648cfdffc 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -44,8 +44,11 @@ typedef struct { #define SEQLOCK_UNLOCKED \ __SEQLOCK_UNLOCKED(old_style_seqlock_init) -#define seqlock_init(x) \ - do { *(x) = (seqlock_t) __SEQLOCK_UNLOCKED(x); } while (0) +#define seqlock_init(x) \ + do { \ + (x)->sequence = 0; \ + spin_lock_init(&(x)->lock); \ + } while (0) #define DEFINE_SEQLOCK(x) \ seqlock_t x = __SEQLOCK_UNLOCKED(x) -- cgit v1.2.3