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 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 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 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 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 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 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 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 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 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 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