From fbb18a277a6f192404aa20ece49529acb1e1e76d Mon Sep 17 00:00:00 2001 From: Russell King Date: Sun, 26 Mar 2006 23:13:39 +0100 Subject: [SERIAL] amba-pl010: allow platforms to specify modem control method The amba-pl010 hardware does not provide RTS and DTR control lines; it is expected that these will be implemented using GPIO. Allow platforms to supply a function to implement manipulation of modem control lines. Signed-off-by: Russell King --- include/linux/amba/serial.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/amba/serial.h b/include/linux/amba/serial.h index dc726ffccebd..48ee32a18ac5 100644 --- a/include/linux/amba/serial.h +++ b/include/linux/amba/serial.h @@ -158,4 +158,10 @@ #define UART01x_RSR_ANY (UART01x_RSR_OE|UART01x_RSR_BE|UART01x_RSR_PE|UART01x_RSR_FE) #define UART01x_FR_MODEM_ANY (UART01x_FR_DCD|UART01x_FR_DSR|UART01x_FR_CTS) +#ifndef __ASSEMBLY__ +struct amba_pl010_data { + void (*set_mctrl)(struct amba_device *dev, void __iomem *base, unsigned int mctrl); +}; +#endif + #endif -- cgit v1.2.3 From 837c7878771c15ed8d85ecf814ece7fcb4551b46 Mon Sep 17 00:00:00 2001 From: Ben Woodard Date: Wed, 22 Mar 2006 08:09:31 +0100 Subject: [BLOCK] increase size of disk stat counters The kernel's representation of the disk statistics uses the type unsigned which is 32b on both 32b and 64b platforms. Unfortunately, most system tools that work with these numbers that are exported in /proc/diskstats including iostat read these numbers into unsigned longs. This works fine on 32b platforms and when the number of IO transactions are small on 64b platforms. However, when the numbers wrap on 64b platforms & you read the numbers into unsigned longs, and compare the numbers to previous readings, then you get an unsigned representation of a negative number. This looks like a very large 64b number & gives you bizarre readouts in iostat: ilc4: Device: rrqm/s wrqm/s r/s w/s rsec/s wsec/s rkB/s wkB/s avgrq-sz avgqu-sz await svctm %util ilc4: sda 5.50 0.00 143.96 0.00 307496983987862656.00 0.00 153748491993931328.00 0.00 2136028725038430.00 7.94 55.12 5.59 80.42 Though fixing iostat in user space is possible, and a quick survey indicates that several other similar tools also use unsigned longs when processing /proc/diskstats. Therefore, it seems like a better approach would be to extend the length of the disk_stats structure on 64b architectures to 64b. The following patch does that. It should not affect the operation on 32b platforms. Signed-off-by: Ben Woodard Cc: Rick Lindsley Signed-off-by: Andrew Morton Signed-off-by: Jens Axboe --- include/linux/genhd.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index fd647fde5ec1..179fea53fc81 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -89,12 +89,12 @@ struct hd_struct { #define GENHD_FL_SUPPRESS_PARTITION_INFO 32 struct disk_stats { - unsigned sectors[2]; /* READs and WRITEs */ - unsigned ios[2]; - unsigned merges[2]; - unsigned ticks[2]; - unsigned io_ticks; - unsigned time_in_queue; + unsigned long sectors[2]; /* READs and WRITEs */ + unsigned long ios[2]; + unsigned long merges[2]; + unsigned long ticks[2]; + unsigned long io_ticks; + unsigned long time_in_queue; }; struct gendisk { -- cgit v1.2.3 From f75ba3ade8a4599d67040a9493d75a864e7b329c Mon Sep 17 00:00:00 2001 From: Ian Kent Date: Mon, 27 Mar 2006 01:14:52 -0800 Subject: [PATCH] autofs4: increase module version Update autofs4 version. Signed-off-by: Ian Kent Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/auto_fs4.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/auto_fs4.h b/include/linux/auto_fs4.h index 9343c89d843c..d998ddcf7288 100644 --- a/include/linux/auto_fs4.h +++ b/include/linux/auto_fs4.h @@ -23,7 +23,7 @@ #define AUTOFS_MIN_PROTO_VERSION 3 #define AUTOFS_MAX_PROTO_VERSION 4 -#define AUTOFS_PROTO_SUBVERSION 7 +#define AUTOFS_PROTO_SUBVERSION 10 /* Mask for expire behaviour */ #define AUTOFS_EXP_IMMEDIATE 1 -- cgit v1.2.3 From 5c0a32fc2cd0be912511199449a37a4a6f0f582d Mon Sep 17 00:00:00 2001 From: Ian Kent Date: Mon, 27 Mar 2006 01:14:55 -0800 Subject: [PATCH] autofs4: add new packet type for v5 communications This patch define a new autofs packet for autofs v5 and updates the waitq.c functions to handle the additional packet type. Signed-off-by: Ian Kent Cc: Al Viro Cc: Christoph Hellwig Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/auto_fs4.h | 51 +++++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 46 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/auto_fs4.h b/include/linux/auto_fs4.h index d998ddcf7288..0a6bc52ffe88 100644 --- a/include/linux/auto_fs4.h +++ b/include/linux/auto_fs4.h @@ -19,18 +19,37 @@ #undef AUTOFS_MIN_PROTO_VERSION #undef AUTOFS_MAX_PROTO_VERSION -#define AUTOFS_PROTO_VERSION 4 +#define AUTOFS_PROTO_VERSION 5 #define AUTOFS_MIN_PROTO_VERSION 3 -#define AUTOFS_MAX_PROTO_VERSION 4 +#define AUTOFS_MAX_PROTO_VERSION 5 -#define AUTOFS_PROTO_SUBVERSION 10 +#define AUTOFS_PROTO_SUBVERSION 0 /* Mask for expire behaviour */ #define AUTOFS_EXP_IMMEDIATE 1 #define AUTOFS_EXP_LEAVES 2 -/* New message type */ -#define autofs_ptype_expire_multi 2 /* Expire entry (umount request) */ +/* Daemon notification packet types */ +enum autofs_notify { + NFY_NONE, + NFY_MOUNT, + NFY_EXPIRE +}; + +/* Kernel protocol version 4 packet types */ + +/* Expire entry (umount request) */ +#define autofs_ptype_expire_multi 2 + +/* Kernel protocol version 5 packet types */ + +/* Indirect mount missing and expire requests. */ +#define autofs_ptype_missing_indirect 3 +#define autofs_ptype_expire_indirect 4 + +/* Direct mount missing and expire requests */ +#define autofs_ptype_missing_direct 5 +#define autofs_ptype_expire_direct 6 /* v4 multi expire (via pipe) */ struct autofs_packet_expire_multi { @@ -40,14 +59,36 @@ struct autofs_packet_expire_multi { char name[NAME_MAX+1]; }; +/* autofs v5 common packet struct */ +struct autofs_v5_packet { + struct autofs_packet_hdr hdr; + autofs_wqt_t wait_queue_token; + __u32 dev; + __u64 ino; + __u32 uid; + __u32 gid; + __u32 pid; + __u32 tgid; + __u32 len; + char name[NAME_MAX+1]; +}; + +typedef struct autofs_v5_packet autofs_packet_missing_indirect_t; +typedef struct autofs_v5_packet autofs_packet_expire_indirect_t; +typedef struct autofs_v5_packet autofs_packet_missing_direct_t; +typedef struct autofs_v5_packet autofs_packet_expire_direct_t; + union autofs_packet_union { struct autofs_packet_hdr hdr; struct autofs_packet_missing missing; struct autofs_packet_expire expire; struct autofs_packet_expire_multi expire_multi; + struct autofs_v5_packet v5_packet; }; #define AUTOFS_IOC_EXPIRE_MULTI _IOW(0x93,0x66,int) +#define AUTOFS_IOC_EXPIRE_INDIRECT AUTOFS_IOC_EXPIRE_MULTI +#define AUTOFS_IOC_EXPIRE_DIRECT AUTOFS_IOC_EXPIRE_MULTI #define AUTOFS_IOC_PROTOSUBVER _IOR(0x93,0x67,int) #define AUTOFS_IOC_ASKREGHOST _IOR(0x93,0x68,int) #define AUTOFS_IOC_TOGGLEREGHOST _IOR(0x93,0x69,int) -- cgit v1.2.3 From efc36aa5608f5717338747e152c23f2cfdb14697 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 27 Mar 2006 01:14:59 -0800 Subject: [PATCH] knfsd: Change the store of auth_domains to not be a 'cache' The 'auth_domain's are simply handles on internal data structures. They do not cache information from user-space, and forcing them into the mold of a 'cache' misrepresents their true nature and causes confusion. Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sunrpc/svcauth.h | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svcauth.h b/include/linux/sunrpc/svcauth.h index c119ce7cbd22..2fe2087edd66 100644 --- a/include/linux/sunrpc/svcauth.h +++ b/include/linux/sunrpc/svcauth.h @@ -45,9 +45,10 @@ struct svc_rqst; /* forward decl */ * of ip addresses to the given client. */ struct auth_domain { - struct cache_head h; + struct kref ref; + struct hlist_node hash; char *name; - int flavour; + struct auth_ops *flavour; }; /* @@ -86,6 +87,9 @@ struct auth_domain { * * domain_release() * This call releases a domain. + * set_client() + * Givens a pending request (struct svc_rqst), finds and assigns + * an appropriate 'auth_domain' as the client. */ struct auth_ops { char * name; @@ -117,7 +121,7 @@ extern void svc_auth_unregister(rpc_authflavor_t flavor); extern struct auth_domain *unix_domain_find(char *name); extern void auth_domain_put(struct auth_domain *item); extern int auth_unix_add_addr(struct in_addr addr, struct auth_domain *dom); -extern struct auth_domain *auth_domain_lookup(struct auth_domain *item, int set); +extern struct auth_domain *auth_domain_lookup(char *name, struct auth_domain *new); 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); @@ -160,8 +164,6 @@ static inline unsigned long hash_mem(char *buf, int length, int bits) return hash >> (BITS_PER_LONG - bits); } -extern struct cache_detail auth_domain_cache, ip_map_cache; - #endif /* __KERNEL__ */ #endif /* _LINUX_SUNRPC_SVCAUTH_H_ */ -- cgit v1.2.3 From eab7e2e647c348b418e8715ecaca0177e1b473c7 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 27 Mar 2006 01:15:00 -0800 Subject: [PATCH] knfsd: Break the hard linkage from svc_expkey to svc_export Current svc_expkey holds a pointer to the svc_export structure, so updates to that structure have to be in-place, which is a wart on the whole cache infrastruct. So we break that linkage and just do a second lookup. If this became a performance issue, it would be possible to put a direct link back in which was only used conditionally. i.e. when an object is replaced in the cache, we set a flag in the old object. When dereferencing the link from svc_expkey, if the flag is set, we drop the reference and do a fresh lookup. Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nfsd/export.h | 20 ++++---------------- 1 file changed, 4 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfsd/export.h b/include/linux/nfsd/export.h index 6bad4766d3d9..d52e0b7ad37b 100644 --- a/include/linux/nfsd/export.h +++ b/include/linux/nfsd/export.h @@ -67,7 +67,8 @@ struct svc_expkey { int ek_fsidtype; u32 ek_fsid[3]; - struct svc_export * ek_export; + struct vfsmount * ek_mnt; + struct dentry * ek_dentry; }; #define EX_SECURE(exp) (!((exp)->ex_flags & NFSEXP_INSECURE_PORT)) @@ -114,22 +115,9 @@ static inline void exp_get(struct svc_export *exp) { cache_get(&exp->h); } -static inline struct svc_export * +extern struct svc_export * exp_find(struct auth_domain *clp, int fsid_type, u32 *fsidv, - struct cache_req *reqp) -{ - struct svc_expkey *ek = exp_find_key(clp, fsid_type, fsidv, reqp); - if (ek && !IS_ERR(ek)) { - struct svc_export *exp = ek->ek_export; - int err; - exp_get(exp); - expkey_put(&ek->h, &svc_expkey_cache); - if ((err = cache_check(&svc_export_cache, &exp->h, reqp))) - exp = ERR_PTR(err); - return exp; - } else - return ERR_PTR(PTR_ERR(ek)); -} + struct cache_req *reqp); #endif /* __KERNEL__ */ -- cgit v1.2.3 From 7d317f2c9f1e9dcf4f632fa98f91d1d4a36c4cae Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 27 Mar 2006 01:15:01 -0800 Subject: [PATCH] knfsd: Get rid of 'inplace' sunrpc caches These were an unnecessary wart. Also only have one 'DefineSimpleCache..' instead of two. Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sunrpc/cache.h | 28 +++++++++++----------------- 1 file changed, 11 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h index c4e3ea7cf154..405ac14e509a 100644 --- a/include/linux/sunrpc/cache.h +++ b/include/linux/sunrpc/cache.h @@ -133,14 +133,11 @@ struct cache_deferred_req { * If "set" == 0 : * If an entry is found, it is returned * If no entry is found, a new non-VALID entry is created. - * If "set" == 1 and INPLACE == 0 : + * If "set" == 1 : * If no entry is found a new one is inserted with data from "template" * If a non-CACHE_VALID entry is found, it is updated from template using UPDATE * If a CACHE_VALID entry is found, a new entry is swapped in with data * from "template" - * If set == 1, and INPLACE == 1 : - * As above, except that if a CACHE_VALID entry is found, we UPDATE in place - * instead of swapping in a new entry. * * If the passed handle has the CACHE_NEGATIVE flag set, then UPDATE is not * run but insteead CACHE_NEGATIVE is set in any new item. @@ -159,13 +156,8 @@ struct cache_deferred_req { * TEST tests if "tmp" matches "item" * INIT copies key information from "item" to "new" * UPDATE copies content information from "item" to "tmp" - * INPLACE is true if updates can happen inplace rather than allocating a new structure - * - * WARNING: any substantial changes to this must be reflected in - * net/sunrpc/svcauth.c(auth_domain_lookup) - * which is a similar routine that is open-coded. */ -#define DefineCacheLookup(RTN,MEMBER,FNAME,ARGS,SETUP,DETAIL,HASHFN,TEST,INIT,UPDATE,INPLACE) \ +#define DefineCacheLookup(RTN,MEMBER,FNAME,ARGS,SETUP,DETAIL,HASHFN,TEST,INIT,UPDATE) \ RTN *FNAME ARGS \ { \ RTN *tmp, *new=NULL; \ @@ -179,13 +171,13 @@ RTN *FNAME ARGS \ tmp = container_of(*hp, RTN, MEMBER); \ if (TEST) { /* found a match */ \ \ - if (set && !INPLACE && test_bit(CACHE_VALID, &tmp->MEMBER.flags) && !new) \ + if (set && test_bit(CACHE_VALID, &tmp->MEMBER.flags) && !new) \ break; \ \ if (new) \ {INIT;} \ if (set) { \ - if (!INPLACE && test_bit(CACHE_VALID, &tmp->MEMBER.flags))\ + if (test_bit(CACHE_VALID, &tmp->MEMBER.flags))\ { /* need to swap in new */ \ RTN *t2; \ \ @@ -206,7 +198,7 @@ RTN *FNAME ARGS \ else read_unlock(&(DETAIL)->hash_lock); \ if (set) \ cache_fresh(DETAIL, &tmp->MEMBER, item->MEMBER.expiry_time); \ - if (set && !INPLACE && new) cache_fresh(DETAIL, &new->MEMBER, 0); \ + if (set && new) cache_fresh(DETAIL, &new->MEMBER, 0); \ if (new) (DETAIL)->cache_put(&new->MEMBER, DETAIL); \ return tmp; \ } \ @@ -239,10 +231,12 @@ RTN *FNAME ARGS \ return NULL; \ } -#define DefineSimpleCacheLookup(STRUCT,INPLACE) \ - DefineCacheLookup(struct STRUCT, h, STRUCT##_lookup, (struct STRUCT *item, int set), /*no setup */, \ - & STRUCT##_cache, STRUCT##_hash(item), STRUCT##_match(item, tmp),\ - STRUCT##_init(new, item), STRUCT##_update(tmp, item),INPLACE) +#define DefineSimpleCacheLookup(STRUCT, FUNC) \ + DefineCacheLookup(struct STRUCT, h, FUNC##_lookup, \ + (struct STRUCT *item, int set), /*no setup */, \ + & FUNC##_cache, FUNC##_hash(item), FUNC##_match(item, tmp), \ + STRUCT##_init(new, item), STRUCT##_update(tmp, item)) + #define cache_for_each(pos, detail, index, member) \ for (({read_lock(&(detail)->hash_lock); index = (detail)->hash_size;}) ; \ -- cgit v1.2.3 From 15a5f6bd23eddd5b3be80366f364be04fb1c1c99 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 27 Mar 2006 01:15:02 -0800 Subject: [PATCH] knfsd: Create cache_lookup function instead of using a macro to declare one The C++-like 'template' approach proves to be too ugly and hard to work with. The old 'template' won't go away until all users are updated. Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sunrpc/cache.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h index 405ac14e509a..3e17a5ff1dea 100644 --- a/include/linux/sunrpc/cache.h +++ b/include/linux/sunrpc/cache.h @@ -81,6 +81,11 @@ struct cache_detail { struct cache_detail *cd, struct cache_head *h); + struct cache_head * (*alloc)(void); + int (*match)(struct cache_head *orig, struct cache_head *new); + void (*init)(struct cache_head *orig, struct cache_head *new); + void (*update)(struct cache_head *orig, struct cache_head *new); + /* fields below this comment are for internal use * and should not be touched by cache owners */ @@ -237,6 +242,13 @@ RTN *FNAME ARGS \ & FUNC##_cache, FUNC##_hash(item), FUNC##_match(item, tmp), \ STRUCT##_init(new, item), STRUCT##_update(tmp, item)) +extern struct cache_head * +sunrpc_cache_lookup(struct cache_detail *detail, + struct cache_head *key, int hash); +extern struct cache_head * +sunrpc_cache_update(struct cache_detail *detail, + struct cache_head *new, struct cache_head *old, int hash); + #define cache_for_each(pos, detail, index, member) \ for (({read_lock(&(detail)->hash_lock); index = (detail)->hash_size;}) ; \ -- cgit v1.2.3 From 4d90452cb23b08a9a9dd001010f0ee6b1ee83a45 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 27 Mar 2006 01:15:07 -0800 Subject: [PATCH] knfsd: Remove DefineCacheLookup This has been replaced by more traditional code. Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sunrpc/cache.h | 113 ------------------------------------------- 1 file changed, 113 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h index 3e17a5ff1dea..afc481dd02dd 100644 --- a/include/linux/sunrpc/cache.h +++ b/include/linux/sunrpc/cache.h @@ -128,119 +128,6 @@ struct cache_deferred_req { int too_many); }; -/* - * just like a template in C++, this macro does cache lookup - * for us. - * The function is passed some sort of HANDLE from which a cache_detail - * structure can be determined (via SETUP, DETAIL), a template - * cache entry (type RTN*), and a "set" flag. Using the HASHFN and the - * TEST, the function will try to find a matching cache entry in the cache. - * If "set" == 0 : - * If an entry is found, it is returned - * If no entry is found, a new non-VALID entry is created. - * If "set" == 1 : - * If no entry is found a new one is inserted with data from "template" - * If a non-CACHE_VALID entry is found, it is updated from template using UPDATE - * If a CACHE_VALID entry is found, a new entry is swapped in with data - * from "template" - * - * If the passed handle has the CACHE_NEGATIVE flag set, then UPDATE is not - * run but insteead CACHE_NEGATIVE is set in any new item. - - * In any case, the new entry is returned with a reference count. - * - * - * RTN is a struct type for a cache entry - * MEMBER is the member of the cache which is cache_head, which must be first - * FNAME is the name for the function - * ARGS are arguments to function and must contain RTN *item, int set. May - * also contain something to be usedby SETUP or DETAIL to find cache_detail. - * SETUP locates the cache detail and makes it available as... - * DETAIL identifies the cache detail, possibly set up by SETUP - * HASHFN returns a hash value of the cache entry "item" - * TEST tests if "tmp" matches "item" - * INIT copies key information from "item" to "new" - * UPDATE copies content information from "item" to "tmp" - */ -#define DefineCacheLookup(RTN,MEMBER,FNAME,ARGS,SETUP,DETAIL,HASHFN,TEST,INIT,UPDATE) \ -RTN *FNAME ARGS \ -{ \ - RTN *tmp, *new=NULL; \ - struct cache_head **hp, **head; \ - SETUP; \ - head = &(DETAIL)->hash_table[HASHFN]; \ - retry: \ - if (set||new) write_lock(&(DETAIL)->hash_lock); \ - else read_lock(&(DETAIL)->hash_lock); \ - for(hp=head; *hp != NULL; hp = &tmp->MEMBER.next) { \ - tmp = container_of(*hp, RTN, MEMBER); \ - if (TEST) { /* found a match */ \ - \ - if (set && test_bit(CACHE_VALID, &tmp->MEMBER.flags) && !new) \ - break; \ - \ - if (new) \ - {INIT;} \ - if (set) { \ - if (test_bit(CACHE_VALID, &tmp->MEMBER.flags))\ - { /* need to swap in new */ \ - RTN *t2; \ - \ - new->MEMBER.next = tmp->MEMBER.next; \ - *hp = &new->MEMBER; \ - tmp->MEMBER.next = NULL; \ - t2 = tmp; tmp = new; new = t2; \ - } \ - if (test_bit(CACHE_NEGATIVE, &item->MEMBER.flags)) \ - set_bit(CACHE_NEGATIVE, &tmp->MEMBER.flags); \ - else { \ - UPDATE; \ - clear_bit(CACHE_NEGATIVE, &tmp->MEMBER.flags); \ - } \ - } \ - cache_get(&tmp->MEMBER); \ - if (set||new) write_unlock(&(DETAIL)->hash_lock); \ - else read_unlock(&(DETAIL)->hash_lock); \ - if (set) \ - cache_fresh(DETAIL, &tmp->MEMBER, item->MEMBER.expiry_time); \ - if (set && new) cache_fresh(DETAIL, &new->MEMBER, 0); \ - if (new) (DETAIL)->cache_put(&new->MEMBER, DETAIL); \ - return tmp; \ - } \ - } \ - /* Didn't find anything */ \ - if (new) { \ - INIT; \ - new->MEMBER.next = *head; \ - *head = &new->MEMBER; \ - (DETAIL)->entries ++; \ - cache_get(&new->MEMBER); \ - if (set) { \ - tmp = new; \ - if (test_bit(CACHE_NEGATIVE, &item->MEMBER.flags)) \ - set_bit(CACHE_NEGATIVE, &tmp->MEMBER.flags); \ - else {UPDATE;} \ - } \ - } \ - if (set||new) write_unlock(&(DETAIL)->hash_lock); \ - else read_unlock(&(DETAIL)->hash_lock); \ - if (new && set) \ - cache_fresh(DETAIL, &new->MEMBER, item->MEMBER.expiry_time); \ - if (new) \ - return new; \ - new = kmalloc(sizeof(*new), GFP_KERNEL); \ - if (new) { \ - cache_init(&new->MEMBER); \ - goto retry; \ - } \ - return NULL; \ -} - -#define DefineSimpleCacheLookup(STRUCT, FUNC) \ - DefineCacheLookup(struct STRUCT, h, FUNC##_lookup, \ - (struct STRUCT *item, int set), /*no setup */, \ - & FUNC##_cache, FUNC##_hash(item), FUNC##_match(item, tmp), \ - STRUCT##_init(new, item), STRUCT##_update(tmp, item)) extern struct cache_head * sunrpc_cache_lookup(struct cache_detail *detail, -- cgit v1.2.3 From ebd0cb1af3be2729cc1f574681dfba01fcf458d9 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 27 Mar 2006 01:15:08 -0800 Subject: [PATCH] knfsd: Unexport cache_fresh and fix a small race Cache_fresh is now only used in cache.c, so unexport it. Part of cache_fresh (setting CACHE_VALID) should really be done under the lock, while part (calling cache_revisit_request etc) must be done outside the lock. So we split it up appropriately. Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sunrpc/cache.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h index afc481dd02dd..a37fead1873b 100644 --- a/include/linux/sunrpc/cache.h +++ b/include/linux/sunrpc/cache.h @@ -165,8 +165,6 @@ static inline int cache_put(struct cache_head *h, struct cache_detail *cd) } extern void cache_init(struct cache_head *h); -extern void cache_fresh(struct cache_detail *detail, - struct cache_head *head, time_t expiry); extern int cache_check(struct cache_detail *detail, struct cache_head *h, struct cache_req *rqstp); extern void cache_flush(void); -- cgit v1.2.3 From baab935ff3bdac20c558809da0d8e8f761840219 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 27 Mar 2006 01:15:09 -0800 Subject: [PATCH] knfsd: Convert sunrpc_cache to use krefs .. it makes some of the code nicer. Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nfsd/export.h | 4 +--- include/linux/sunrpc/cache.h | 13 ++++++------- 2 files changed, 7 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfsd/export.h b/include/linux/nfsd/export.h index d52e0b7ad37b..a6c08a47b25c 100644 --- a/include/linux/nfsd/export.h +++ b/include/linux/nfsd/export.h @@ -102,13 +102,11 @@ int exp_rootfh(struct auth_domain *, int exp_pseudoroot(struct auth_domain *, struct svc_fh *fhp, struct cache_req *creq); int nfserrno(int errno); -extern void expkey_put(struct cache_head *item, struct cache_detail *cd); -extern void svc_export_put(struct cache_head *item, struct cache_detail *cd); extern struct cache_detail svc_export_cache, svc_expkey_cache; static inline void exp_put(struct svc_export *exp) { - svc_export_put(&exp->h, &svc_export_cache); + cache_put(&exp->h, &svc_export_cache); } static inline void exp_get(struct svc_export *exp) diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h index a37fead1873b..ad3f5cbdb770 100644 --- a/include/linux/sunrpc/cache.h +++ b/include/linux/sunrpc/cache.h @@ -50,7 +50,7 @@ struct cache_head { time_t last_refresh; /* If CACHE_PENDING, this is when upcall * was sent, else this is when update was received */ - atomic_t refcnt; + struct kref ref; unsigned long flags; }; #define CACHE_VALID 0 /* Entry contains valid data */ @@ -68,8 +68,7 @@ struct cache_detail { atomic_t inuse; /* active user-space update or lookup */ char *name; - void (*cache_put)(struct cache_head *, - struct cache_detail*); + void (*cache_put)(struct kref *); void (*cache_request)(struct cache_detail *cd, struct cache_head *h, @@ -151,17 +150,17 @@ extern void cache_clean_deferred(void *owner); static inline struct cache_head *cache_get(struct cache_head *h) { - atomic_inc(&h->refcnt); + kref_get(&h->ref); return h; } -static inline int cache_put(struct cache_head *h, struct cache_detail *cd) +static inline void cache_put(struct cache_head *h, struct cache_detail *cd) { - if (atomic_read(&h->refcnt) <= 2 && + if (atomic_read(&h->ref.refcount) <= 2 && h->expiry_time < cd->nextcheck) cd->nextcheck = h->expiry_time; - return atomic_dec_and_test(&h->refcnt); + kref_put(&h->ref, cd->cache_put); } extern void cache_init(struct cache_head *h); -- cgit v1.2.3 From 74cae61ab45f19a3e8c4d9f53c0e94df129c7915 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Mon, 27 Mar 2006 01:15:10 -0800 Subject: [PATCH] fs/nfsd/export.c,net/sunrpc/cache.c: make needlessly global code static We can now make some code static. Signed-off-by: Adrian Bunk Cc: Neil Brown Cc: Trond Myklebust Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nfsd/export.h | 5 +---- include/linux/sunrpc/cache.h | 1 - 2 files changed, 1 insertion(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfsd/export.h b/include/linux/nfsd/export.h index a6c08a47b25c..d2a8abb5011a 100644 --- a/include/linux/nfsd/export.h +++ b/include/linux/nfsd/export.h @@ -86,9 +86,6 @@ void nfsd_export_shutdown(void); void nfsd_export_flush(void); void exp_readlock(void); void exp_readunlock(void); -struct svc_expkey * exp_find_key(struct auth_domain *clp, - int fsid_type, u32 *fsidv, - struct cache_req *reqp); struct svc_export * exp_get_by_name(struct auth_domain *clp, struct vfsmount *mnt, struct dentry *dentry, @@ -102,7 +99,7 @@ int exp_rootfh(struct auth_domain *, int exp_pseudoroot(struct auth_domain *, struct svc_fh *fhp, struct cache_req *creq); int nfserrno(int errno); -extern struct cache_detail svc_export_cache, svc_expkey_cache; +extern struct cache_detail svc_export_cache; static inline void exp_put(struct svc_export *exp) { diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h index ad3f5cbdb770..b5612c958cce 100644 --- a/include/linux/sunrpc/cache.h +++ b/include/linux/sunrpc/cache.h @@ -163,7 +163,6 @@ static inline void cache_put(struct cache_head *h, struct cache_detail *cd) kref_put(&h->ref, cd->cache_put); } -extern void cache_init(struct cache_head *h); extern int cache_check(struct cache_detail *detail, struct cache_head *h, struct cache_req *rqstp); extern void cache_flush(void); -- cgit v1.2.3 From 1e9f28fa1eb9773bf65bae08288c6a0a38eef4a7 Mon Sep 17 00:00:00 2001 From: "Siddha, Suresh B" Date: Mon, 27 Mar 2006 01:15:22 -0800 Subject: [PATCH] sched: new sched domain for representing multi-core Add a new sched domain for representing multi-core with shared caches between cores. Consider a dual package system, each package containing two cores and with last level cache shared between cores with in a package. If there are two runnable processes, with this appended patch those two processes will be scheduled on different packages. On such systems, with this patch we have observed 8% perf improvement with specJBB(2 warehouse) benchmark and 35% improvement with CFP2000 rate(with 2 users). This new domain will come into play only on multi-core systems with shared caches. On other systems, this sched domain will be removed by domain degeneration code. This new domain can be also used for implementing power savings policy (see OLS 2005 CMP kernel scheduler paper for more details.. I will post another patch for power savings policy soon) Most of the arch/* file changes are for cpu_coregroup_map() implementation. Signed-off-by: Suresh Siddha Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/topology.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/topology.h b/include/linux/topology.h index e8eb0040ce3a..a305ae2e44b6 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -164,6 +164,15 @@ .nr_balance_failed = 0, \ } +#ifdef CONFIG_SCHED_MC +#ifndef SD_MC_INIT +/* for now its same as SD_CPU_INIT. + * TBD: Tune Domain parameters! + */ +#define SD_MC_INIT SD_CPU_INIT +#endif +#endif + #ifdef CONFIG_NUMA #ifndef SD_NODE_INIT #error Please define an appropriate SD_NODE_INIT in include/asm/topology.h!!! -- cgit v1.2.3 From a117e66ed45ac0569c039ea60bd7a9a61e031858 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Mon, 27 Mar 2006 01:15:25 -0800 Subject: [PATCH] unify pfn_to_page: generic functions There are 3 memory models, FLATMEM, DISCONTIGMEM, SPARSEMEM. Each arch has its own page_to_pfn(), pfn_to_page() for each models. But most of them can use the same arithmetic. This patch adds asm-generic/memory_model.h, which includes generic page_to_pfn(), pfn_to_page() definitions for each memory model. When CONFIG_OUT_OF_LINE_PFN_TO_PAGE=y, out-of-line functions are used instead of macro. This is enabled by some archs and reduces text size. Signed-off-by: KAMEZAWA Hiroyuki Cc: Hugh Dickins Cc: Andi Kleen Cc: Paul Mackerras Cc: Benjamin Herrenschmidt Cc: Richard Henderson Cc: Ivan Kokshaysky Cc: Russell King Cc: Ian Molton Cc: Mikael Starvik Cc: David Howells Cc: Yoshinori Sato Cc: Hirokazu Takata Cc: Ralf Baechle Cc: Kyle McMartin Cc: Heiko Carstens Cc: Martin Schwidefsky Cc: Paul Mundt Cc: Kazumoto Kojima Cc: Richard Curnow Cc: William Lee Irwin III Cc: "David S. Miller" Cc: Jeff Dike Cc: Paolo 'Blaisorblade' Giarrusso Cc: Miles Bader Cc: Chris Zankel Cc: "Luck, Tony" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index ebfc238cc243..0c1c0c0cce65 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -602,17 +602,6 @@ static inline struct mem_section *__pfn_to_section(unsigned long pfn) return __nr_to_section(pfn_to_section_nr(pfn)); } -#define pfn_to_page(pfn) \ -({ \ - unsigned long __pfn = (pfn); \ - __section_mem_map_addr(__pfn_to_section(__pfn)) + __pfn; \ -}) -#define page_to_pfn(page) \ -({ \ - page - __section_mem_map_addr(__nr_to_section( \ - page_to_section(page))); \ -}) - static inline int pfn_valid(unsigned long pfn) { if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS) -- cgit v1.2.3 From a0140c1d85637ee5f4ea7c78f066e3611a6a79dc Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Mon, 27 Mar 2006 01:15:55 -0800 Subject: [PATCH] remove zone_mem_map This patch removes zone_mem_map. pfn_to_page uses pgdat, page_to_pfn uses zone. page_to_pfn can use pgdat instead of zone, which is only one user of zone_mem_map. By modifing it, we can remove zone_mem_map. Signed-off-by: KAMEZAWA Hiroyuki Cc: Dave Hansen Cc: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 0c1c0c0cce65..ace31c515a8c 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -225,7 +225,6 @@ struct zone { * Discontig memory support fields. */ struct pglist_data *zone_pgdat; - struct page *zone_mem_map; /* zone_start_pfn == zone_start_paddr >> PAGE_SHIFT */ unsigned long zone_start_pfn; -- cgit v1.2.3 From 8357f8695d58b50fbf2bd507b4b0fc2cd1e43bd6 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Mon, 27 Mar 2006 01:15:57 -0800 Subject: [PATCH] define for_each_online_pgdat This patch defines for_each_online_pgdat() as a replacement of for_each_pgdat() Now, online nodes are managed by node_online_map. But for_each_pgdat() uses pgdat_link to iterate over all nodes(pgdat). This means management structure for online pgdat is duplicated. I think using node_online_map for for_each_pgdat() is simple and sane rather ather than pgdat_link. New macro is named as for_each_online_pgdat(). Following patch will fix callers of for_each_pgdat(). The bootmem allocater uses for_each_pgdat() before pgdat initialization. I don't think it's sane. Following patch will fix it. Signed-off-by: Yasunori Goto Signed-off-by: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 108 +++++++++++++++++++++++++---------------------- include/linux/nodemask.h | 4 ++ 2 files changed, 61 insertions(+), 51 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index ace31c515a8c..96eb08025092 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -13,6 +13,7 @@ #include #include #include +#include #include /* Free memory management - zoned buddy allocator. */ @@ -349,57 +350,6 @@ unsigned long __init node_memmap_size_bytes(int, unsigned long, unsigned long); */ #define zone_idx(zone) ((zone) - (zone)->zone_pgdat->node_zones) -/** - * for_each_pgdat - helper macro to iterate over all nodes - * @pgdat - pointer to a pg_data_t variable - * - * Meant to help with common loops of the form - * pgdat = pgdat_list; - * while(pgdat) { - * ... - * pgdat = pgdat->pgdat_next; - * } - */ -#define for_each_pgdat(pgdat) \ - for (pgdat = pgdat_list; pgdat; pgdat = pgdat->pgdat_next) - -/* - * next_zone - helper magic for for_each_zone() - * Thanks to William Lee Irwin III for this piece of ingenuity. - */ -static inline struct zone *next_zone(struct zone *zone) -{ - pg_data_t *pgdat = zone->zone_pgdat; - - if (zone < pgdat->node_zones + MAX_NR_ZONES - 1) - zone++; - else if (pgdat->pgdat_next) { - pgdat = pgdat->pgdat_next; - zone = pgdat->node_zones; - } else - zone = NULL; - - return zone; -} - -/** - * for_each_zone - helper macro to iterate over all memory zones - * @zone - pointer to struct zone variable - * - * The user only needs to declare the zone variable, for_each_zone - * fills it in. This basically means for_each_zone() is an - * easier to read version of this piece of code: - * - * for (pgdat = pgdat_list; pgdat; pgdat = pgdat->node_next) - * for (i = 0; i < MAX_NR_ZONES; ++i) { - * struct zone * z = pgdat->node_zones + i; - * ... - * } - * } - */ -#define for_each_zone(zone) \ - for (zone = pgdat_list->node_zones; zone; zone = next_zone(zone)) - static inline int populated_zone(struct zone *zone) { return (!!zone->present_pages); @@ -471,6 +421,62 @@ extern struct pglist_data contig_page_data; #endif /* !CONFIG_NEED_MULTIPLE_NODES */ +static inline struct pglist_data *first_online_pgdat(void) +{ + return NODE_DATA(first_online_node); +} + +static inline struct pglist_data *next_online_pgdat(struct pglist_data *pgdat) +{ + int nid = next_online_node(pgdat->node_id); + + if (nid == MAX_NUMNODES) + return NULL; + return NODE_DATA(nid); +} + + +/** + * for_each_pgdat - helper macro to iterate over all nodes + * @pgdat - pointer to a pg_data_t variable + */ +#define for_each_online_pgdat(pgdat) \ + for (pgdat = first_online_pgdat(); \ + pgdat; \ + pgdat = next_online_pgdat(pgdat)) + +/* + * next_zone - helper magic for for_each_zone() + * Thanks to William Lee Irwin III for this piece of ingenuity. + */ +static inline struct zone *next_zone(struct zone *zone) +{ + pg_data_t *pgdat = zone->zone_pgdat; + + if (zone < pgdat->node_zones + MAX_NR_ZONES - 1) + zone++; + else { + pgdat = next_online_pgdat(pgdat); + if (pgdat) + zone = pgdat->node_zones; + else + zone = NULL; + } + return zone; +} + +/** + * for_each_zone - helper macro to iterate over all memory zones + * @zone - pointer to struct zone variable + * + * The user only needs to declare the zone variable, for_each_zone + * fills it in. + */ +#define for_each_zone(zone) \ + for (zone = (first_online_pgdat())->node_zones; \ + zone; \ + zone = next_zone(zone)) + #ifdef CONFIG_SPARSEMEM #include #endif diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index b959a4525cbd..1a9ef3e627d1 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -350,11 +350,15 @@ extern nodemask_t node_possible_map; #define num_possible_nodes() nodes_weight(node_possible_map) #define node_online(node) node_isset((node), node_online_map) #define node_possible(node) node_isset((node), node_possible_map) +#define first_online_node first_node(node_online_map) +#define next_online_node(nid) next_node((nid), node_online_map) #else #define num_online_nodes() 1 #define num_possible_nodes() 1 #define node_online(node) ((node) == 0) #define node_possible(node) ((node) == 0) +#define first_online_node 0 +#define next_online_node(nid) (MAX_NUMNODES) #endif #define any_online_node(mask) \ -- cgit v1.2.3 From 679bc9fbb508a0aac9539b2de747eb5849feb428 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Mon, 27 Mar 2006 01:15:58 -0800 Subject: [PATCH] for_each_online_pgdat: for_each_bootmem Add a list_head to bootmem_data_t and make bootmems use it. bootmem list is sorted by node_boot_start. Only nodes against which init_bootmem() is called are linked to the list. (i386 allocates bootmem only from one node(0) not from all online nodes.) A summary: 1. for_each_online_pgdat() traverses all *online* nodes. 2. alloc_bootmem() allocates memory only from initialized-for-bootmem nodes. Signed-off-by: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootmem.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 7155452fb4a8..de3eb8d8ae26 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -38,6 +38,7 @@ typedef struct bootmem_data { unsigned long last_pos; unsigned long last_success; /* Previous allocation point. To speed * up searching */ + struct list_head list; } bootmem_data_t; extern unsigned long __init bootmem_bootmap_pages (unsigned long); -- cgit v1.2.3 From ae0f15fb91274e67d78836d38c99ec363df33073 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Mon, 27 Mar 2006 01:16:01 -0800 Subject: [PATCH] for_each_online_pgdat: remove pgdat_list By using for_each_online_pgdat(), pgdat_list is not necessary now. This patch removes it. Signed-off-by: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 96eb08025092..0d12c3cf1f86 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -307,7 +307,6 @@ typedef struct pglist_data { unsigned long node_spanned_pages; /* total size of physical page range, including holes */ int node_id; - struct pglist_data *pgdat_next; wait_queue_head_t kswapd_wait; struct task_struct *kswapd; int kswapd_max_order; @@ -324,8 +323,6 @@ typedef struct pglist_data { #include -extern struct pglist_data *pgdat_list; - void __get_zone_counts(unsigned long *active, unsigned long *inactive, unsigned long *free, struct pglist_data *pgdat); void get_zone_counts(unsigned long *active, unsigned long *inactive, -- cgit v1.2.3 From 95144c788dc01b6a0ff2c9c2222e37ffdab358b8 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Mon, 27 Mar 2006 01:16:02 -0800 Subject: [PATCH] uninline zone helpers Helper functions for for_each_online_pgdat/for_each_zone look too big to be inlined. Speed of these helper macro itself is not very important. (inner loops are tend to do more work than this) This patch make helper function to be out-of-lined. inline out-of-line .text 005c0680 005bf6a0 005c0680 - 005bf6a0 = FE0 = 4Kbytes. Signed-off-by: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 38 +++----------------------------------- 1 file changed, 3 insertions(+), 35 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 0d12c3cf1f86..b5c21122c299 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -418,20 +418,9 @@ extern struct pglist_data contig_page_data; #endif /* !CONFIG_NEED_MULTIPLE_NODES */ -static inline struct pglist_data *first_online_pgdat(void) -{ - return NODE_DATA(first_online_node); -} - -static inline struct pglist_data *next_online_pgdat(struct pglist_data *pgdat) -{ - int nid = next_online_node(pgdat->node_id); - - if (nid == MAX_NUMNODES) - return NULL; - return NODE_DATA(nid); -} - +extern struct pglist_data *first_online_pgdat(void); +extern struct pglist_data *next_online_pgdat(struct pglist_data *pgdat); +extern struct zone *next_zone(struct zone *zone); /** * for_each_pgdat - helper macro to iterate over all nodes @@ -441,27 +430,6 @@ static inline struct pglist_data *next_online_pgdat(struct pglist_data *pgdat) for (pgdat = first_online_pgdat(); \ pgdat; \ pgdat = next_online_pgdat(pgdat)) - -/* - * next_zone - helper magic for for_each_zone() - * Thanks to William Lee Irwin III for this piece of ingenuity. - */ -static inline struct zone *next_zone(struct zone *zone) -{ - pg_data_t *pgdat = zone->zone_pgdat; - - if (zone < pgdat->node_zones + MAX_NR_ZONES - 1) - zone++; - else { - pgdat = next_online_pgdat(pgdat); - if (pgdat) - zone = pgdat->node_zones; - else - zone = NULL; - } - return zone; -} - /** * for_each_zone - helper macro to iterate over all memory zones * @zone - pointer to struct zone variable -- cgit v1.2.3 From 22a9835c350782a5c3257343713932af3ac92ee0 Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Mon, 27 Mar 2006 01:16:04 -0800 Subject: [PATCH] unify PFN_* macros Just about every architecture defines some macros to do operations on pfns. They're all virtually identical. This patch consolidates all of them. One minor glitch is that at least i386 uses them in a very skeletal header file. To keep away from #include dependency hell, I stuck the new definitions in a new, isolated header. Of all of the implementations, sh64 is the only one that varied by a bit. It used some masks to ensure that any sign-extension got ripped away before the arithmetic is done. This has been posted to that sh64 maintainers and the development list. Compiles on x86, x86_64, ia64 and ppc64. Signed-off-by: Dave Hansen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pfn.h | 9 +++++++++ 1 file changed, 9 insertions(+) create mode 100644 include/linux/pfn.h (limited to 'include/linux') diff --git a/include/linux/pfn.h b/include/linux/pfn.h new file mode 100644 index 000000000000..bb01f8b92b56 --- /dev/null +++ b/include/linux/pfn.h @@ -0,0 +1,9 @@ +#ifndef _LINUX_PFN_H_ +#define _LINUX_PFN_H_ + +#define PFN_ALIGN(x) (((unsigned long)(x) + (PAGE_SIZE - 1)) & PAGE_MASK) +#define PFN_UP(x) (((x) + PAGE_SIZE-1) >> PAGE_SHIFT) +#define PFN_DOWN(x) ((x) >> PAGE_SHIFT) +#define PFN_PHYS(x) ((x) << PAGE_SHIFT) + +#endif -- cgit v1.2.3 From 0771dfefc9e538f077d0b43b6dec19a5a67d0e70 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 27 Mar 2006 01:16:22 -0800 Subject: [PATCH] lightweight robust futexes: core Add the core infrastructure for robust futexes: structure definitions, the new syscalls and the do_exit() based cleanup mechanism. Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner Signed-off-by: Arjan van de Ven Acked-by: Ulrich Drepper Cc: Michael Kerrisk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/futex.h | 95 +++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/sched.h | 3 ++ include/linux/threads.h | 3 +- 3 files changed, 100 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/futex.h b/include/linux/futex.h index 10f96c31971e..20face6b798d 100644 --- a/include/linux/futex.h +++ b/include/linux/futex.h @@ -1,6 +1,8 @@ #ifndef _LINUX_FUTEX_H #define _LINUX_FUTEX_H +#include + /* Second argument to futex syscall */ @@ -11,10 +13,103 @@ #define FUTEX_CMP_REQUEUE 4 #define FUTEX_WAKE_OP 5 +/* + * Support for robust futexes: the kernel cleans up held futexes at + * thread exit time. + */ + +/* + * Per-lock list entry - embedded in user-space locks, somewhere close + * to the futex field. (Note: user-space uses a double-linked list to + * achieve O(1) list add and remove, but the kernel only needs to know + * about the forward link) + * + * NOTE: this structure is part of the syscall ABI, and must not be + * changed. + */ +struct robust_list { + struct robust_list __user *next; +}; + +/* + * Per-thread list head: + * + * NOTE: this structure is part of the syscall ABI, and must only be + * changed if the change is first communicated with the glibc folks. + * (When an incompatible change is done, we'll increase the structure + * size, which glibc will detect) + */ +struct robust_list_head { + /* + * The head of the list. Points back to itself if empty: + */ + struct robust_list list; + + /* + * This relative offset is set by user-space, it gives the kernel + * the relative position of the futex field to examine. This way + * we keep userspace flexible, to freely shape its data-structure, + * without hardcoding any particular offset into the kernel: + */ + long futex_offset; + + /* + * The death of the thread may race with userspace setting + * up a lock's links. So to handle this race, userspace first + * sets this field to the address of the to-be-taken lock, + * then does the lock acquire, and then adds itself to the + * list, and then clears this field. Hence the kernel will + * always have full knowledge of all locks that the thread + * _might_ have taken. We check the owner TID in any case, + * so only truly owned locks will be handled. + */ + struct robust_list __user *list_op_pending; +}; + +/* + * Are there any waiters for this robust futex: + */ +#define FUTEX_WAITERS 0x80000000 + +/* + * The kernel signals via this bit that a thread holding a futex + * has exited without unlocking the futex. The kernel also does + * a FUTEX_WAKE on such futexes, after setting the bit, to wake + * up any possible waiters: + */ +#define FUTEX_OWNER_DIED 0x40000000 + +/* + * Reserved bit: + */ +#define FUTEX_OWNER_PENDING 0x20000000 + +/* + * The rest of the robust-futex field is for the TID: + */ +#define FUTEX_TID_MASK 0x1fffffff + +/* + * A limit of one million locks held per thread (!) ought to be enough + * for some time. This also protects against a deliberately circular + * list. Not worth introducing an rlimit for this: + */ +#define ROBUST_LIST_LIMIT 1048576 + long do_futex(unsigned long uaddr, int op, int val, unsigned long timeout, unsigned long uaddr2, int val2, int val3); +extern int handle_futex_death(unsigned int *uaddr, struct task_struct *curr); + +#ifdef CONFIG_FUTEX +extern void exit_robust_list(struct task_struct *curr); +#else +static inline void exit_robust_list(struct task_struct *curr) +{ +} +#endif + #define FUTEX_OP_SET 0 /* *(int *)UADDR2 = OPARG; */ #define FUTEX_OP_ADD 1 /* *(int *)UADDR2 += OPARG; */ #define FUTEX_OP_OR 2 /* *(int *)UADDR2 |= OPARG; */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 036d14d2bf90..fd4848f2d750 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -35,6 +35,7 @@ #include #include #include +#include #include /* For AT_VECTOR_SIZE */ @@ -872,6 +873,8 @@ struct task_struct { int cpuset_mems_generation; int cpuset_mem_spread_rotor; #endif + struct robust_list_head __user *robust_list; + atomic_t fs_excl; /* holding fs exclusive resources */ struct rcu_head rcu; }; diff --git a/include/linux/threads.h b/include/linux/threads.h index b59738ac6197..e646bcdf2614 100644 --- a/include/linux/threads.h +++ b/include/linux/threads.h @@ -28,7 +28,8 @@ #define PID_MAX_DEFAULT (CONFIG_BASE_SMALL ? 0x1000 : 0x8000) /* - * A maximum of 4 million PIDs should be enough for a while: + * A maximum of 4 million PIDs should be enough for a while. + * [NOTE: PID/TIDs are limited to 2^29 ~= 500+ million, see futex.h.] */ #define PID_MAX_LIMIT (CONFIG_BASE_SMALL ? PAGE_SIZE * 8 : \ (sizeof(long) > 4 ? 4 * 1024 * 1024 : PID_MAX_DEFAULT)) -- cgit v1.2.3 From 34f192c6527f20c47ccec239e7d51a27691b93fc Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 27 Mar 2006 01:16:24 -0800 Subject: [PATCH] lightweight robust futexes: compat 32-bit syscall compatibility support. (This patch also moves all futex related compat functionality into kernel/futex_compat.c.) Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner Signed-off-by: Arjan van de Ven Acked-by: Ulrich Drepper Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compat.h | 18 ++++++++++++++++++ include/linux/sched.h | 3 +++ 2 files changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 24d659cdbafe..6d3a654be1ae 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -147,6 +147,24 @@ typedef struct compat_sigevent { } _sigev_un; } compat_sigevent_t; +struct compat_robust_list { + compat_uptr_t next; +}; + +struct compat_robust_list_head { + struct compat_robust_list list; + compat_long_t futex_offset; + compat_uptr_t list_op_pending; +}; + +extern void compat_exit_robust_list(struct task_struct *curr); + +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_size_t __user *len_ptr); long compat_sys_semctl(int first, int second, int third, void __user *uptr); long compat_sys_msgsnd(int first, int second, int third, void __user *uptr); diff --git a/include/linux/sched.h b/include/linux/sched.h index fd4848f2d750..20b4f0372e44 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -874,6 +874,9 @@ struct task_struct { int cpuset_mem_spread_rotor; #endif struct robust_list_head __user *robust_list; +#ifdef CONFIG_COMPAT + struct compat_robust_list_head __user *compat_robust_list; +#endif atomic_t fs_excl; /* holding fs exclusive resources */ struct rcu_head rcu; -- cgit v1.2.3 From 8f17d3a5049d32392b79925c73a0cf99ce6d5af0 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 27 Mar 2006 01:16:27 -0800 Subject: [PATCH] lightweight robust futexes updates - fix: initialize the robust list(s) to NULL in copy_process. - doc update - cleanup: rename _inuser to _inatomic - __user cleanups and other small cleanups Signed-off-by: Ingo Molnar Cc: Thomas Gleixner Cc: Arjan van de Ven Cc: Ulrich Drepper Cc: Andi Kleen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/futex.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/futex.h b/include/linux/futex.h index 20face6b798d..55fff96ae859 100644 --- a/include/linux/futex.h +++ b/include/linux/futex.h @@ -100,7 +100,7 @@ long do_futex(unsigned long uaddr, int op, int val, unsigned long timeout, unsigned long uaddr2, int val2, int val3); -extern int handle_futex_death(unsigned int *uaddr, struct task_struct *curr); +extern int handle_futex_death(u32 __user *uaddr, struct task_struct *curr); #ifdef CONFIG_FUTEX extern void exit_robust_list(struct task_struct *curr); -- cgit v1.2.3 From 76b81e2b0e2241accebcc68e126bc5ab958661b9 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 27 Mar 2006 01:16:28 -0800 Subject: [PATCH] lightweight robust futexes updates 2 futex.h updates: - get rid of FUTEX_OWNER_PENDING - it's not used - reduce ROBUST_LIST_LIMIT to a saner value Signed-off-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/futex.h | 14 ++++---------- 1 file changed, 4 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/futex.h b/include/linux/futex.h index 55fff96ae859..966a5b3da439 100644 --- a/include/linux/futex.h +++ b/include/linux/futex.h @@ -79,22 +79,16 @@ struct robust_list_head { */ #define FUTEX_OWNER_DIED 0x40000000 -/* - * Reserved bit: - */ -#define FUTEX_OWNER_PENDING 0x20000000 - /* * The rest of the robust-futex field is for the TID: */ -#define FUTEX_TID_MASK 0x1fffffff +#define FUTEX_TID_MASK 0x3fffffff /* - * A limit of one million locks held per thread (!) ought to be enough - * for some time. This also protects against a deliberately circular - * list. Not worth introducing an rlimit for this: + * This limit protects against a deliberately circular list. + * (Not worth introducing an rlimit for it) */ -#define ROBUST_LIST_LIMIT 1048576 +#define ROBUST_LIST_LIMIT 2048 long do_futex(unsigned long uaddr, int op, int val, unsigned long timeout, unsigned long uaddr2, int val2, -- cgit v1.2.3 From e041c683412d5bf44dc2b109053e3b837b71742d Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Mon, 27 Mar 2006 01:16:30 -0800 Subject: [PATCH] Notifier chain update: API changes The kernel's implementation of notifier chains is unsafe. There is no protection against entries being added to or removed from a chain while the chain is in use. The issues were discussed in this thread: http://marc.theaimsgroup.com/?l=linux-kernel&m=113018709002036&w=2 We noticed that notifier chains in the kernel fall into two basic usage classes: "Blocking" chains are always called from a process context and the callout routines are allowed to sleep; "Atomic" chains can be called from an atomic context and the callout routines are not allowed to sleep. We decided to codify this distinction and make it part of the API. Therefore this set of patches introduces three new, parallel APIs: one for blocking notifiers, one for atomic notifiers, and one for "raw" notifiers (which is really just the old API under a new name). New kinds of data structures are used for the heads of the chains, and new routines are defined for registration, unregistration, and calling a chain. The three APIs are explained in include/linux/notifier.h and their implementation is in kernel/sys.c. With atomic and blocking chains, the implementation guarantees that the chain links will not be corrupted and that chain callers will not get messed up by entries being added or removed. For raw chains the implementation provides no guarantees at all; users of this API must provide their own protections. (The idea was that situations may come up where the assumptions of the atomic and blocking APIs are not appropriate, so it should be possible for users to handle these things in their own way.) There are some limitations, which should not be too hard to live with. For atomic/blocking chains, registration and unregistration must always be done in a process context since the chain is protected by a mutex/rwsem. Also, a callout routine for a non-raw chain must not try to register or unregister entries on its own chain. (This did happen in a couple of places and the code had to be changed to avoid it.) Since atomic chains may be called from within an NMI handler, they cannot use spinlocks for synchronization. Instead we use RCU. The overhead falls almost entirely in the unregister routine, which is okay since unregistration is much less frequent that calling a chain. Here is the list of chains that we adjusted and their classifications. None of them use the raw API, so for the moment it is only a placeholder. ATOMIC CHAINS ------------- arch/i386/kernel/traps.c: i386die_chain arch/ia64/kernel/traps.c: ia64die_chain arch/powerpc/kernel/traps.c: powerpc_die_chain arch/sparc64/kernel/traps.c: sparc64die_chain arch/x86_64/kernel/traps.c: die_chain drivers/char/ipmi/ipmi_si_intf.c: xaction_notifier_list kernel/panic.c: panic_notifier_list kernel/profile.c: task_free_notifier net/bluetooth/hci_core.c: hci_notifier net/ipv4/netfilter/ip_conntrack_core.c: ip_conntrack_chain net/ipv4/netfilter/ip_conntrack_core.c: ip_conntrack_expect_chain net/ipv6/addrconf.c: inet6addr_chain net/netfilter/nf_conntrack_core.c: nf_conntrack_chain net/netfilter/nf_conntrack_core.c: nf_conntrack_expect_chain net/netlink/af_netlink.c: netlink_chain BLOCKING CHAINS --------------- arch/powerpc/platforms/pseries/reconfig.c: pSeries_reconfig_chain arch/s390/kernel/process.c: idle_chain arch/x86_64/kernel/process.c idle_notifier drivers/base/memory.c: memory_chain drivers/cpufreq/cpufreq.c cpufreq_policy_notifier_list drivers/cpufreq/cpufreq.c cpufreq_transition_notifier_list drivers/macintosh/adb.c: adb_client_list drivers/macintosh/via-pmu.c sleep_notifier_list drivers/macintosh/via-pmu68k.c sleep_notifier_list drivers/macintosh/windfarm_core.c wf_client_list drivers/usb/core/notify.c usb_notifier_list drivers/video/fbmem.c fb_notifier_list kernel/cpu.c cpu_chain kernel/module.c module_notify_list kernel/profile.c munmap_notifier kernel/profile.c task_exit_notifier kernel/sys.c reboot_notifier_list net/core/dev.c netdev_chain net/decnet/dn_dev.c: dnaddr_chain net/ipv4/devinet.c: inetaddr_chain It's possible that some of these classifications are wrong. If they are, please let us know or submit a patch to fix them. Note that any chain that gets called very frequently should be atomic, because the rwsem read-locking used for blocking chains is very likely to incur cache misses on SMP systems. (However, if the chain's callout routines may sleep then the chain cannot be atomic.) The patch set was written by Alan Stern and Chandra Seetharaman, incorporating material written by Keith Owens and suggestions from Paul McKenney and Andrew Morton. [jes@sgi.com: restructure the notifier chain initialization macros] Signed-off-by: Alan Stern Signed-off-by: Chandra Seetharaman Signed-off-by: Jes Sorensen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/adb.h | 2 +- include/linux/kernel.h | 2 +- include/linux/memory.h | 1 - include/linux/netfilter_ipv4/ip_conntrack.h | 17 ++--- include/linux/notifier.h | 96 ++++++++++++++++++++++++++--- 5 files changed, 100 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/adb.h b/include/linux/adb.h index e9fdc63483c7..b7305b178279 100644 --- a/include/linux/adb.h +++ b/include/linux/adb.h @@ -85,7 +85,7 @@ enum adb_message { ADB_MSG_POST_RESET /* Called after resetting the bus (re-do init & register) */ }; extern struct adb_driver *adb_controller; -extern struct notifier_block *adb_client_list; +extern struct blocking_notifier_head adb_client_list; int adb_request(struct adb_request *req, void (*done)(struct adb_request *), int flags, int nbytes, ...); diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 03d6cfaa5b8a..a3720f973ea5 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -87,7 +87,7 @@ extern int cond_resched(void); (__x < 0) ? -__x : __x; \ }) -extern struct notifier_block *panic_notifier_list; +extern struct atomic_notifier_head panic_notifier_list; extern long (*panic_blink)(long time); NORET_TYPE void panic(const char * fmt, ...) __attribute__ ((NORET_AND format (printf, 1, 2))); diff --git a/include/linux/memory.h b/include/linux/memory.h index e251dc43d0f5..8f04143ca363 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -77,7 +77,6 @@ extern int remove_memory_block(unsigned long, struct mem_section *, int); #define CONFIG_MEM_BLOCK_SIZE (PAGES_PER_SECTION< +#include +#include -struct notifier_block -{ - int (*notifier_call)(struct notifier_block *self, unsigned long, void *); +/* + * Notifier chains are of three types: + * + * Atomic notifier chains: Chain callbacks run in interrupt/atomic + * context. Callouts are not allowed to block. + * Blocking notifier chains: Chain callbacks run in process context. + * Callouts are allowed to block. + * Raw notifier chains: There are no restrictions on callbacks, + * registration, or unregistration. All locking and protection + * must be provided by the caller. + * + * 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. + * + * atomic_notifier_chain_unregister() and blocking_notifier_chain_unregister() + * _must not_ be called from within the call chain. + */ + +struct notifier_block { + int (*notifier_call)(struct notifier_block *, unsigned long, void *); struct notifier_block *next; int priority; }; +struct atomic_notifier_head { + spinlock_t lock; + struct notifier_block *head; +}; + +struct blocking_notifier_head { + struct rw_semaphore rwsem; + struct notifier_block *head; +}; + +struct raw_notifier_head { + struct notifier_block *head; +}; + +#define ATOMIC_INIT_NOTIFIER_HEAD(name) do { \ + spin_lock_init(&(name)->lock); \ + (name)->head = NULL; \ + } while (0) +#define BLOCKING_INIT_NOTIFIER_HEAD(name) do { \ + init_rwsem(&(name)->rwsem); \ + (name)->head = NULL; \ + } while (0) +#define RAW_INIT_NOTIFIER_HEAD(name) do { \ + (name)->head = NULL; \ + } while (0) + +#define ATOMIC_NOTIFIER_INIT(name) { \ + .lock = SPIN_LOCK_UNLOCKED, \ + .head = NULL } +#define BLOCKING_NOTIFIER_INIT(name) { \ + .rwsem = __RWSEM_INITIALIZER((name).rwsem), \ + .head = NULL } +#define RAW_NOTIFIER_INIT(name) { \ + .head = NULL } + +#define ATOMIC_NOTIFIER_HEAD(name) \ + struct atomic_notifier_head name = \ + ATOMIC_NOTIFIER_INIT(name) +#define BLOCKING_NOTIFIER_HEAD(name) \ + struct blocking_notifier_head name = \ + BLOCKING_NOTIFIER_INIT(name) +#define RAW_NOTIFIER_HEAD(name) \ + struct raw_notifier_head name = \ + RAW_NOTIFIER_INIT(name) #ifdef __KERNEL__ -extern int notifier_chain_register(struct notifier_block **list, struct notifier_block *n); -extern int notifier_chain_unregister(struct notifier_block **nl, struct notifier_block *n); -extern int notifier_call_chain(struct notifier_block **n, unsigned long val, void *v); +extern int atomic_notifier_chain_register(struct atomic_notifier_head *, + struct notifier_block *); +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 atomic_notifier_chain_unregister(struct atomic_notifier_head *, + struct notifier_block *); +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 atomic_notifier_call_chain(struct atomic_notifier_head *, + unsigned long val, void *v); +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); #define NOTIFY_DONE 0x0000 /* Don't care */ #define NOTIFY_OK 0x0001 /* Suits me */ #define NOTIFY_STOP_MASK 0x8000 /* Don't call further */ -#define NOTIFY_BAD (NOTIFY_STOP_MASK|0x0002) /* Bad/Veto action */ +#define NOTIFY_BAD (NOTIFY_STOP_MASK|0x0002) + /* Bad/Veto action */ /* * Clean way to return from the notifier and stop further calls. */ -- cgit v1.2.3 From c58411e95d7f5062dedd1a3064af4d359da1e633 Mon Sep 17 00:00:00 2001 From: Alessandro Zummo Date: Mon, 27 Mar 2006 01:16:34 -0800 Subject: [PATCH] RTC Subsystem: library functions RTC and date/time related functions. Signed-off-by: Alessandro Zummo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rtc.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rtc.h b/include/linux/rtc.h index b739ac1f7ca0..8454337c7058 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -95,6 +95,11 @@ struct rtc_pll_info { #include +extern int rtc_month_days(unsigned int month, unsigned int year); +extern int rtc_valid_tm(struct rtc_time *tm); +extern int rtc_tm_to_time(struct rtc_time *tm, unsigned long *time); +extern void rtc_time_to_tm(unsigned long time, struct rtc_time *tm); + typedef struct rtc_task { void (*func)(void *private_data); void *private_data; -- cgit v1.2.3 From 0c86edc0d4970649f39748c4ce4f2895f728468f Mon Sep 17 00:00:00 2001 From: Alessandro Zummo Date: Mon, 27 Mar 2006 01:16:37 -0800 Subject: [PATCH] RTC subsystem: class Add the basic RTC subsystem infrastructure to the kernel. rtc/class.c - registration facilities for RTC drivers rtc/interface.c - kernel/rtc interface functions rtc/hctosys.c - snippet of code that copies hw clock to sw clock at bootup, if configured to do so. Signed-off-by: Alessandro Zummo Acked-by: Greg Kroah-Hartman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rtc.h | 87 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 87 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rtc.h b/include/linux/rtc.h index 8454337c7058..ab61cd1199f2 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -91,6 +91,12 @@ struct rtc_pll_info { #define RTC_PLL_GET _IOR('p', 0x11, struct rtc_pll_info) /* Get PLL correction */ #define RTC_PLL_SET _IOW('p', 0x12, struct rtc_pll_info) /* Set PLL correction */ +/* interrupt flags */ +#define RTC_IRQF 0x80 /* any of the following is active */ +#define RTC_PF 0x40 +#define RTC_AF 0x20 +#define RTC_UF 0x10 + #ifdef __KERNEL__ #include @@ -100,6 +106,87 @@ extern int rtc_valid_tm(struct rtc_time *tm); extern int rtc_tm_to_time(struct rtc_time *tm, unsigned long *time); extern void rtc_time_to_tm(unsigned long time, struct rtc_time *tm); +#include +#include +#include +#include +#include + +extern struct class *rtc_class; + +struct rtc_class_ops { + int (*open)(struct device *); + void (*release)(struct device *); + int (*ioctl)(struct device *, unsigned int, unsigned long); + int (*read_time)(struct device *, struct rtc_time *); + int (*set_time)(struct device *, struct rtc_time *); + int (*read_alarm)(struct device *, struct rtc_wkalrm *); + int (*set_alarm)(struct device *, struct rtc_wkalrm *); + int (*proc)(struct device *, struct seq_file *); + int (*set_mmss)(struct device *, unsigned long secs); + int (*irq_set_state)(struct device *, int enabled); + int (*irq_set_freq)(struct device *, int freq); + int (*read_callback)(struct device *, int data); +}; + +#define RTC_DEVICE_NAME_SIZE 20 +struct rtc_task; + +struct rtc_device +{ + struct class_device class_dev; + struct module *owner; + + int id; + char name[RTC_DEVICE_NAME_SIZE]; + + struct rtc_class_ops *ops; + struct mutex ops_lock; + + struct class_device *rtc_dev; + struct cdev char_dev; + struct mutex char_lock; + + unsigned long irq_data; + spinlock_t irq_lock; + wait_queue_head_t irq_queue; + struct fasync_struct *async_queue; + + struct rtc_task *irq_task; + spinlock_t irq_task_lock; + int irq_freq; +}; +#define to_rtc_device(d) container_of(d, struct rtc_device, class_dev) + +extern struct rtc_device *rtc_device_register(const char *name, + struct device *dev, + struct rtc_class_ops *ops, + struct module *owner); +extern void rtc_device_unregister(struct rtc_device *rdev); +extern int rtc_interface_register(struct class_interface *intf); + +extern int rtc_read_time(struct class_device *class_dev, struct rtc_time *tm); +extern int rtc_set_time(struct class_device *class_dev, struct rtc_time *tm); +extern int rtc_set_mmss(struct class_device *class_dev, unsigned long secs); +extern int rtc_read_alarm(struct class_device *class_dev, + struct rtc_wkalrm *alrm); +extern int rtc_set_alarm(struct class_device *class_dev, + struct rtc_wkalrm *alrm); +extern void rtc_update_irq(struct class_device *class_dev, + unsigned long num, unsigned long events); + +extern struct class_device *rtc_class_open(char *name); +extern void rtc_class_close(struct class_device *class_dev); + +extern int rtc_irq_register(struct class_device *class_dev, + struct rtc_task *task); +extern void rtc_irq_unregister(struct class_device *class_dev, + struct rtc_task *task); +extern int rtc_irq_set_state(struct class_device *class_dev, + struct rtc_task *task, int enabled); +extern int rtc_irq_set_freq(struct class_device *class_dev, + struct rtc_task *task, int freq); + typedef struct rtc_task { void (*func)(void *private_data); void *private_data; -- cgit v1.2.3 From 6fc7f10cee28c7fa190920fefda8c696d5bf3074 Mon Sep 17 00:00:00 2001 From: Alessandro Zummo Date: Mon, 27 Mar 2006 01:16:37 -0800 Subject: [PATCH] RTC subsystem: I2C cleanup This patch, completely optional, removes from drivers/i2c/chips all the drivers that are implemented in the new RTC subsystem. It should be noted that none of the current driver is actually integrated, i.e. usable without further patches. Signed-off-by: Alessandro Zummo Acked-by: Greg Kroah-Hartman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/x1205.h | 31 ------------------------------- 1 file changed, 31 deletions(-) delete mode 100644 include/linux/x1205.h (limited to 'include/linux') diff --git a/include/linux/x1205.h b/include/linux/x1205.h deleted file mode 100644 index 64fd3af894a5..000000000000 --- a/include/linux/x1205.h +++ /dev/null @@ -1,31 +0,0 @@ -/* - * x1205.h - defines for drivers/i2c/chips/x1205.c - * Copyright 2004 Karen Spearel - * Copyright 2005 Alessandro Zummo - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - */ - -#ifndef __LINUX_X1205_H__ -#define __LINUX_X1205_H__ - -/* commands */ - -#define X1205_CMD_GETDATETIME 0 -#define X1205_CMD_SETTIME 1 -#define X1205_CMD_SETDATETIME 2 -#define X1205_CMD_GETALARM 3 -#define X1205_CMD_SETALARM 4 -#define X1205_CMD_GETDTRIM 5 -#define X1205_CMD_SETDTRIM 6 -#define X1205_CMD_GETATRIM 7 -#define X1205_CMD_SETATRIM 8 - -extern int x1205_do_command(unsigned int cmd, void *arg); -extern int x1205_direct_attach(int adapter_id, - struct i2c_client_address_data *address_data); - -#endif /* __LINUX_X1205_H__ */ -- cgit v1.2.3 From f7f3682fb2f8bc8a9c912baeea15454416ca1972 Mon Sep 17 00:00:00 2001 From: Alessandro Zummo Date: Mon, 27 Mar 2006 01:16:38 -0800 Subject: [PATCH] RTC subsystem: I2C driver ids This patch adds the I2C driver ids to i2c-id.h in preparation of the I2C direct probing method. This is kept separate so that it can be integrated to Signed-off-by: Alessandro Zummo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/i2c-id.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/i2c-id.h b/include/linux/i2c-id.h index 679b46a6a565..c8b81f419fd8 100644 --- a/include/linux/i2c-id.h +++ b/include/linux/i2c-id.h @@ -108,6 +108,10 @@ #define I2C_DRIVERID_UPD64083 78 /* upd64083 video processor */ #define I2C_DRIVERID_UPD64031A 79 /* upd64031a video processor */ #define I2C_DRIVERID_SAA717X 80 /* saa717x video encoder */ +#define I2C_DRIVERID_DS1672 81 /* Dallas/Maxim DS1672 RTC */ +#define I2C_DRIVERID_X1205 82 /* Xicor/Intersil X1205 RTC */ +#define I2C_DRIVERID_PCF8563 83 /* Philips PCF8563 RTC */ +#define I2C_DRIVERID_RS5C372 84 /* Ricoh RS5C372 RTC */ #define I2C_DRIVERID_I2CDEV 900 #define I2C_DRIVERID_ARP 902 /* SMBus ARP Client */ -- cgit v1.2.3 From 1d98af87270cc08bb8251e004b9dc63cc838f24b Mon Sep 17 00:00:00 2001 From: Alessandro Zummo Date: Mon, 27 Mar 2006 01:16:47 -0800 Subject: [PATCH] RTC subsystem: M48T86 driver Add a driver for the ST M48T86 / Dallas DS12887 RTC. This is a platform driver. The platform device must provide I/O routines to access the RTC. Signed-off-by: Alessandro Zummo Cc: Greg KH Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/m48t86.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) create mode 100644 include/linux/m48t86.h (limited to 'include/linux') diff --git a/include/linux/m48t86.h b/include/linux/m48t86.h new file mode 100644 index 000000000000..9065199319d0 --- /dev/null +++ b/include/linux/m48t86.h @@ -0,0 +1,16 @@ +/* + * ST M48T86 / Dallas DS12887 RTC driver + * Copyright (c) 2006 Tower Technologies + * + * Author: Alessandro Zummo + * + * 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. +*/ + +struct m48t86_ops +{ + void (*writeb)(unsigned char value, unsigned long addr); + unsigned char (*readb)(unsigned long addr); +}; -- cgit v1.2.3 From ed49843b897da9969e349c279ffc832efcb93213 Mon Sep 17 00:00:00 2001 From: Pavel Roskin Date: Mon, 27 Mar 2006 01:17:36 -0800 Subject: [PATCH] Add ID for Quadro NVS280 Quadro NVS280 is a dual-head PCIe card with PCI ID 10de:00fd and subsystem ID 10de:0215. Signed-off-by: Pavel Roskin Signed-off-by: Antonino Daplas Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pci_ids.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 6f080ae59286..02f6cf20b141 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1052,6 +1052,7 @@ #define PCIE_DEVICE_ID_NVIDIA_GEFORCE_6600_ALT2 0x00f2 #define PCIE_DEVICE_ID_NVIDIA_GEFORCE_6200_ALT1 0x00f3 #define PCIE_DEVICE_ID_NVIDIA_GEFORCE_6800_GT 0x00f9 +#define PCIE_DEVICE_ID_NVIDIA_QUADRO_NVS280 0x00fd #define PCI_DEVICE_ID_NVIDIA_GEFORCE_SDR 0x0100 #define PCI_DEVICE_ID_NVIDIA_GEFORCE_DDR 0x0101 #define PCI_DEVICE_ID_NVIDIA_QUADRO 0x0103 -- cgit v1.2.3 From 969429b504ae866d3f8b1cafd68a2c099e305093 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 27 Mar 2006 01:17:49 -0800 Subject: [PATCH] dm: make sure QUEUE_FLAG_CLUSTER is set properly This flag should be set for a virtual device iff it is set for all underlying devices. Signed-off-by: Neil Brown Acked-by: Alasdair G Kergon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/device-mapper.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 51e0e95a421a..aee10b2ea4c6 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -97,6 +97,7 @@ struct io_restrictions { unsigned short hardsect_size; unsigned int max_segment_size; unsigned long seg_boundary_mask; + unsigned char no_cluster; /* inverted so that 0 is default */ }; struct dm_target { -- cgit v1.2.3 From 3ac51e741a46af7a20f55e79d3e3aeaa93c6c544 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Mon, 27 Mar 2006 01:17:54 -0800 Subject: [PATCH] dm store geometry Allow drive geometry to be stored with a new DM_DEV_SET_GEOMETRY ioctl. Device-mapper will now respond to HDIO_GETGEO. If the geometry information is not available, zero will be returned for all of the parameters. Signed-off-by: Darrick J. Wong Signed-off-by: Alasdair G Kergon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compat_ioctl.h | 2 ++ include/linux/dm-ioctl.h | 17 +++++++++++++++-- 2 files changed, 17 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compat_ioctl.h b/include/linux/compat_ioctl.h index efb518f16bb3..89ab677cb993 100644 --- a/include/linux/compat_ioctl.h +++ b/include/linux/compat_ioctl.h @@ -140,6 +140,7 @@ COMPATIBLE_IOCTL(DM_TABLE_DEPS_32) COMPATIBLE_IOCTL(DM_TABLE_STATUS_32) COMPATIBLE_IOCTL(DM_LIST_VERSIONS_32) COMPATIBLE_IOCTL(DM_TARGET_MSG_32) +COMPATIBLE_IOCTL(DM_DEV_SET_GEOMETRY_32) COMPATIBLE_IOCTL(DM_VERSION) COMPATIBLE_IOCTL(DM_REMOVE_ALL) COMPATIBLE_IOCTL(DM_LIST_DEVICES) @@ -155,6 +156,7 @@ COMPATIBLE_IOCTL(DM_TABLE_DEPS) COMPATIBLE_IOCTL(DM_TABLE_STATUS) COMPATIBLE_IOCTL(DM_LIST_VERSIONS) COMPATIBLE_IOCTL(DM_TARGET_MSG) +COMPATIBLE_IOCTL(DM_DEV_SET_GEOMETRY) /* Big K */ COMPATIBLE_IOCTL(PIO_FONT) COMPATIBLE_IOCTL(GIO_FONT) diff --git a/include/linux/dm-ioctl.h b/include/linux/dm-ioctl.h index fa75ba0d635e..c67c6786612a 100644 --- a/include/linux/dm-ioctl.h +++ b/include/linux/dm-ioctl.h @@ -80,6 +80,16 @@ * * DM_TARGET_MSG: * Pass a message string to the target at a specific offset of a device. + * + * DM_DEV_SET_GEOMETRY: + * Set the geometry of a device by passing in a string in this format: + * + * "cylinders heads sectors_per_track start_sector" + * + * Beware that CHS geometry is nearly obsolete and only provided + * for compatibility with dm devices that can be booted by a PC + * BIOS. See struct hd_geometry for range limits. Also note that + * the geometry is erased if the device size changes. */ /* @@ -218,6 +228,7 @@ enum { /* Added later */ DM_LIST_VERSIONS_CMD, DM_TARGET_MSG_CMD, + DM_DEV_SET_GEOMETRY_CMD }; /* @@ -247,6 +258,7 @@ typedef char ioctl_struct[308]; #define DM_TABLE_STATUS_32 _IOWR(DM_IOCTL, DM_TABLE_STATUS_CMD, ioctl_struct) #define DM_LIST_VERSIONS_32 _IOWR(DM_IOCTL, DM_LIST_VERSIONS_CMD, ioctl_struct) #define DM_TARGET_MSG_32 _IOWR(DM_IOCTL, DM_TARGET_MSG_CMD, ioctl_struct) +#define DM_DEV_SET_GEOMETRY_32 _IOWR(DM_IOCTL, DM_DEV_SET_GEOMETRY_CMD, ioctl_struct) #endif #define DM_IOCTL 0xfd @@ -270,11 +282,12 @@ typedef char ioctl_struct[308]; #define DM_LIST_VERSIONS _IOWR(DM_IOCTL, DM_LIST_VERSIONS_CMD, struct dm_ioctl) #define DM_TARGET_MSG _IOWR(DM_IOCTL, DM_TARGET_MSG_CMD, struct dm_ioctl) +#define DM_DEV_SET_GEOMETRY _IOWR(DM_IOCTL, DM_DEV_SET_GEOMETRY_CMD, struct dm_ioctl) #define DM_VERSION_MAJOR 4 -#define DM_VERSION_MINOR 5 +#define DM_VERSION_MINOR 6 #define DM_VERSION_PATCHLEVEL 0 -#define DM_VERSION_EXTRA "-ioctl (2005-10-04)" +#define DM_VERSION_EXTRA "-ioctl (2006-02-17)" /* Status bits */ #define DM_READONLY_FLAG (1 << 0) /* In/Out */ -- cgit v1.2.3 From 6a4d44c1f1108d6c9e8850e8cf166aaba0e56eae Mon Sep 17 00:00:00 2001 From: Jun'ichi Nomura Date: Mon, 27 Mar 2006 01:17:55 -0800 Subject: [PATCH] dm/md dependency tree in sysfs: holders/slaves subdirectory Creating "slaves" and "holders" directories in /sys/block/ and creating "holders" directory under /sys/block// Signed-off-by: Jun'ichi Nomura Cc: Alasdair G Kergon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/genhd.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index fd647fde5ec1..eea61cc8fac1 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -78,6 +78,9 @@ struct hd_struct { sector_t start_sect; sector_t nr_sects; struct kobject kobj; +#ifdef CONFIG_SYSFS + struct kobject *holder_dir; +#endif unsigned ios[2], sectors[2]; /* READs and WRITEs */ int policy, partno; }; @@ -114,6 +117,10 @@ struct gendisk { int number; /* more of the same */ struct device *driverfs_dev; struct kobject kobj; +#ifdef CONFIG_SYSFS + struct kobject *holder_dir; + struct kobject *slave_dir; +#endif struct timer_rand_state *random; int policy; -- cgit v1.2.3 From 100873687d81d4ce7b1299b447d33e87ba1e9583 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Mon, 27 Mar 2006 01:17:56 -0800 Subject: [PATCH] dm-md-dependency-tree-in-sysfs-holders-slaves-subdirectory-tidy Remove all the CONFIG_SYSFS stuff. That's supposed to all be implemented up in header files. Yes, the CONFIG_SYSFS=n data structures will be a little larger than necessary, but that's a tradeoff we can decide to make. Cc: Jun'ichi Nomura Cc: Alasdair G Kergon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/genhd.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index eea61cc8fac1..bd7db861041e 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -78,9 +78,7 @@ struct hd_struct { sector_t start_sect; sector_t nr_sects; struct kobject kobj; -#ifdef CONFIG_SYSFS struct kobject *holder_dir; -#endif unsigned ios[2], sectors[2]; /* READs and WRITEs */ int policy, partno; }; @@ -117,10 +115,8 @@ struct gendisk { int number; /* more of the same */ struct device *driverfs_dev; struct kobject kobj; -#ifdef CONFIG_SYSFS struct kobject *holder_dir; struct kobject *slave_dir; -#endif struct timer_rand_state *random; int policy; -- cgit v1.2.3 From 641dc636b0475582e48584340b774bd1e90d40d9 Mon Sep 17 00:00:00 2001 From: Jun'ichi Nomura Date: Mon, 27 Mar 2006 01:17:57 -0800 Subject: [PATCH] dm/md dependency tree in sysfs: bd_claim_by_kobject Adding bd_claim_by_kobject() function which takes kobject as additional signature of holder device and creates sysfs symlinks between holder device and claimed device. bd_release_from_kobject() is a counterpart of bd_claim_by_kobject. Signed-off-by: Jun'ichi Nomura Cc: Alasdair G Kergon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 9d9674946956..680d913350e7 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -410,6 +410,9 @@ struct block_device { struct list_head bd_inodes; void * bd_holder; int bd_holders; +#ifdef CONFIG_SYSFS + struct list_head bd_holder_list; +#endif struct block_device * bd_contains; unsigned bd_block_size; struct hd_struct * bd_part; @@ -1399,6 +1402,13 @@ extern int blkdev_get(struct block_device *, mode_t, unsigned); extern int blkdev_put(struct block_device *); extern int bd_claim(struct block_device *, void *); extern void bd_release(struct block_device *); +#ifdef CONFIG_SYSFS +extern int bd_claim_by_disk(struct block_device *, void *, struct gendisk *); +extern void bd_release_from_disk(struct block_device *, struct gendisk *); +#else +#define bd_claim_by_disk(bdev, holder, disk) bd_claim(bdev, holder) +#define bd_release_from_disk(bdev, disk) bd_release(bdev) +#endif /* fs/char_dev.c */ extern int alloc_chrdev_region(dev_t *, unsigned, unsigned, const char *); -- cgit v1.2.3 From b55e6bfcd23cb2f7249095050c649f7aea813f9f Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 27 Mar 2006 01:18:06 -0800 Subject: [PATCH] md: Split disks array out of raid5 conf structure so it is easier to grow The remainder of this batch implements raid5 reshaping. Currently the only shape change that is supported is added a device, but it is envisioned that changing the chunksize and layout will also be supported, as well as changing the level (e.g. 1->5, 5->6). The reshape process naturally has to move all of the data in the array, and so should be used with caution. It is believed to work, and some testing does support this, but wider testing would be great for increasing my confidence. You will need a version of mdadm newer than 2.3.1 to make use of raid5 growth. This is because mdadm need to take a copy of a 'critical section' at the start of the array incase there is a crash at an awkward moment. On restart, mdadm will restore the critical section and allow reshape to continue. I hope to release a 2.4-pre by early next week - it still needs a little more polishing. This patch: Previously the array of disk information was included in the raid5 'conf' structure which was allocated to an appropriate size. This makes it awkward to change the size of that array. So we split it off into a separate kmalloced array which will require a little extra indexing, but is much easier to grow. Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/raid/raid5.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/raid/raid5.h b/include/linux/raid/raid5.h index 394da8207b34..94dbdd406f12 100644 --- a/include/linux/raid/raid5.h +++ b/include/linux/raid/raid5.h @@ -240,7 +240,7 @@ struct raid5_private_data { * waiting for 25% to be free */ spinlock_t device_lock; - struct disk_info disks[0]; + struct disk_info *disks; }; typedef struct raid5_private_data raid5_conf_t; -- cgit v1.2.3 From ad01c9e3752f4ba4f3d99c89b7370fa4983a25b5 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 27 Mar 2006 01:18:07 -0800 Subject: [PATCH] md: Allow stripes to be expanded in preparation for expanding an array Before a RAID-5 can be expanded, we need to be able to expand the stripe-cache data structure. This requires allocating new stripes in a new kmem_cache. If this succeeds, we copy cache pages over and release the old stripes and kmem_cache. We then allocate new pages. If that fails, we leave the stripe cache at it's new size. It isn't worth the effort to shrink it back again. Unfortuanately this means we need two kmem_cache names as we, for a short period of time, we have two kmem_caches. So they are raid5/%s and raid5/%s-alt Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/raid/raid5.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/raid/raid5.h b/include/linux/raid/raid5.h index 94dbdd406f12..b7b2653af7bb 100644 --- a/include/linux/raid/raid5.h +++ b/include/linux/raid/raid5.h @@ -216,7 +216,11 @@ struct raid5_private_data { struct list_head bitmap_list; /* stripes delaying awaiting bitmap update */ atomic_t preread_active_stripes; /* stripes with scheduled io */ - char cache_name[20]; + /* unfortunately we need two cache names as we temporarily have + * two caches. + */ + int active_name; + char cache_name[2][20]; kmem_cache_t *slab_cache; /* for allocating stripes */ int seq_flush, seq_write; @@ -238,7 +242,8 @@ struct raid5_private_data { wait_queue_head_t wait_for_overlap; int inactive_blocked; /* release of inactive stripes blocked, * waiting for 25% to be free - */ + */ + int pool_size; /* number of disks in stripeheads in pool */ spinlock_t device_lock; struct disk_info *disks; }; -- cgit v1.2.3 From 7ecaa1e6a1ad69862e9980b6c777e11f26c4782d Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 27 Mar 2006 01:18:08 -0800 Subject: [PATCH] md: Infrastructure to allow normal IO to continue while array is expanding We need to allow that different stripes are of different effective sizes, and use the appropriate size. Also, when a stripe is being expanded, we must block any IO attempts until the stripe is stable again. Key elements in this change are: - each stripe_head gets a 'disk' field which is part of the key, thus there can sometimes be two stripe heads of the same area of the array, but covering different numbers of devices. One of these will be marked STRIPE_EXPANDING and so won't accept new requests. - conf->expand_progress tracks how the expansion is progressing and is used to determine whether the target part of the array has been expanded yet or not. Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/raid/raid5.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/raid/raid5.h b/include/linux/raid/raid5.h index b7b2653af7bb..6fa274aea2a0 100644 --- a/include/linux/raid/raid5.h +++ b/include/linux/raid/raid5.h @@ -135,6 +135,7 @@ struct stripe_head { atomic_t count; /* nr of active thread/requests */ spinlock_t lock; int bm_seq; /* sequence number for bitmap flushes */ + int disks; /* disks in stripe */ struct r5dev { struct bio req; struct bio_vec vec; @@ -174,6 +175,7 @@ struct stripe_head { #define STRIPE_DELAYED 6 #define STRIPE_DEGRADED 7 #define STRIPE_BIT_DELAY 8 +#define STRIPE_EXPANDING 9 /* * Plugging: @@ -211,6 +213,10 @@ struct raid5_private_data { int raid_disks, working_disks, failed_disks; int max_nr_stripes; + /* used during an expand */ + sector_t expand_progress; /* MaxSector when no expand happening */ + int previous_raid_disks; + struct list_head handle_list; /* stripes needing handling */ struct list_head delayed_list; /* stripes that have plugged requests */ struct list_head bitmap_list; /* stripes delaying awaiting bitmap update */ -- cgit v1.2.3 From ccfcc3c10b2a5cb8fd3c918199a4ff904fc6fb3e Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 27 Mar 2006 01:18:09 -0800 Subject: [PATCH] md: Core of raid5 resize process This patch provides the core of the resize/expand process. sync_request notices if a 'reshape' is happening and acts accordingly. It allocated new stripe_heads for the next chunk-wide-stripe in the target geometry, marking them STRIPE_EXPANDING. Then it finds which stripe heads in the old geometry can provide data needed by these and marks them STRIPE_EXPAND_SOURCE. This causes stripe_handle to read all blocks on those stripes. Once all blocks on a STRIPE_EXPAND_SOURCE stripe_head are read, any that are needed are copied into the corresponding STRIPE_EXPANDING stripe_head. Once a STRIPE_EXPANDING stripe_head is full, it is marks STRIPE_EXPAND_READY and then is written out and released. Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/raid/md_k.h | 4 ++++ include/linux/raid/raid5.h | 4 +++- 2 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/raid/md_k.h b/include/linux/raid/md_k.h index 617b9506c760..4e26ef2cacca 100644 --- a/include/linux/raid/md_k.h +++ b/include/linux/raid/md_k.h @@ -157,6 +157,9 @@ struct mddev_s * DONE: thread is done and is waiting to be reaped * REQUEST: user-space has requested a sync (used with SYNC) * CHECK: user-space request for for check-only, no repair + * RESHAPE: A reshape is happening + * + * If neither SYNC or RESHAPE are set, then it is a recovery. */ #define MD_RECOVERY_RUNNING 0 #define MD_RECOVERY_SYNC 1 @@ -166,6 +169,7 @@ struct mddev_s #define MD_RECOVERY_NEEDED 5 #define MD_RECOVERY_REQUESTED 6 #define MD_RECOVERY_CHECK 7 +#define MD_RECOVERY_RESHAPE 8 unsigned long recovery; int in_sync; /* know to not need resync */ diff --git a/include/linux/raid/raid5.h b/include/linux/raid/raid5.h index 6fa274aea2a0..55c738d50508 100644 --- a/include/linux/raid/raid5.h +++ b/include/linux/raid/raid5.h @@ -157,6 +157,7 @@ struct stripe_head { #define R5_ReadError 8 /* seen a read error here recently */ #define R5_ReWrite 9 /* have tried to over-write the readerror */ +#define R5_Expanded 10 /* This block now has post-expand data */ /* * Write method */ @@ -176,7 +177,8 @@ struct stripe_head { #define STRIPE_DEGRADED 7 #define STRIPE_BIT_DELAY 8 #define STRIPE_EXPANDING 9 - +#define STRIPE_EXPAND_SOURCE 10 +#define STRIPE_EXPAND_READY 11 /* * Plugging: * -- cgit v1.2.3 From 292695531ae4019bb15deedc121b218d1908b648 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 27 Mar 2006 01:18:10 -0800 Subject: [PATCH] md: Final stages of raid5 expand code This patch adds raid5_reshape and end_reshape which will start and finish the reshape processes. raid5_reshape is only enabled in CONFIG_MD_RAID5_RESHAPE is set, to discourage accidental use. Read the 'help' for the CONFIG_MD_RAID5_RESHAPE entry. and Make sure that you have backups, just in case. Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/raid/md.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/raid/md.h b/include/linux/raid/md.h index b6e0bcad84e1..9c77cde5a795 100644 --- a/include/linux/raid/md.h +++ b/include/linux/raid/md.h @@ -92,7 +92,8 @@ extern void md_super_write(mddev_t *mddev, mdk_rdev_t *rdev, extern void md_super_wait(mddev_t *mddev); extern int sync_page_io(struct block_device *bdev, sector_t sector, int size, struct page *page, int rw); - +extern void md_do_sync(mddev_t *mddev); +extern void md_new_event(mddev_t *mddev); #define MD_BUG(x...) { printk("md: bug in file %s, line %d\n", __FILE__, __LINE__); md_print_devices(); } -- cgit v1.2.3 From f67055780caac6a99f43834795c43acf99eba6a6 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 27 Mar 2006 01:18:11 -0800 Subject: [PATCH] md: Checkpoint and allow restart of raid5 reshape We allow the superblock to record an 'old' and a 'new' geometry, and a position where any conversion is up to. The geometry allows for changing chunksize, layout and level as well as number of devices. When using verion-0.90 superblock, we convert the version to 0.91 while the conversion is happening so that an old kernel will refuse the assemble the array. For version-1, we use a feature bit for the same effect. When starting an array we check for an incomplete reshape and restart the reshape process if needed. If the reshape stopped at an awkward time (like when updating the first stripe) we refuse to assemble the array, and let user-space worry about it. Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/raid/md.h | 2 ++ include/linux/raid/md_k.h | 8 ++++++++ include/linux/raid/md_p.h | 32 +++++++++++++++++++++++++++++--- include/linux/raid/raid5.h | 1 + 4 files changed, 40 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/raid/md.h b/include/linux/raid/md.h index 9c77cde5a795..66b44e5e0d6e 100644 --- a/include/linux/raid/md.h +++ b/include/linux/raid/md.h @@ -95,6 +95,8 @@ extern int sync_page_io(struct block_device *bdev, sector_t sector, int size, extern void md_do_sync(mddev_t *mddev); extern void md_new_event(mddev_t *mddev); +extern void md_update_sb(mddev_t * mddev); + #define MD_BUG(x...) { printk("md: bug in file %s, line %d\n", __FILE__, __LINE__); md_print_devices(); } #endif diff --git a/include/linux/raid/md_k.h b/include/linux/raid/md_k.h index 4e26ef2cacca..1a6f9f2f6282 100644 --- a/include/linux/raid/md_k.h +++ b/include/linux/raid/md_k.h @@ -132,6 +132,14 @@ struct mddev_s char uuid[16]; + /* If the array is being reshaped, we need to record the + * new shape and an indication of where we are up to. + * This is written to the superblock. + * If reshape_position is MaxSector, then no reshape is happening (yet). + */ + sector_t reshape_position; + int delta_disks, new_level, new_layout, new_chunk; + struct mdk_thread_s *thread; /* management thread */ struct mdk_thread_s *sync_thread; /* doing resync or reconstruct */ sector_t curr_resync; /* blocks scheduled */ diff --git a/include/linux/raid/md_p.h b/include/linux/raid/md_p.h index c100fa5d4bfa..774e1acfb8c4 100644 --- a/include/linux/raid/md_p.h +++ b/include/linux/raid/md_p.h @@ -102,6 +102,18 @@ typedef struct mdp_device_descriptor_s { #define MD_SB_ERRORS 1 #define MD_SB_BITMAP_PRESENT 8 /* bitmap may be present nearby */ + +/* + * Notes: + * - if an array is being reshaped (restriped) in order to change the + * the number of active devices in the array, 'raid_disks' will be + * the larger of the old and new numbers. 'delta_disks' will + * be the "new - old". So if +ve, raid_disks is the new value, and + * "raid_disks-delta_disks" is the old. If -ve, raid_disks is the + * old value and "raid_disks+delta_disks" is the new (smaller) value. + */ + + typedef struct mdp_superblock_s { /* * Constant generic information @@ -146,7 +158,13 @@ typedef struct mdp_superblock_s { __u32 cp_events_hi; /* 10 high-order of checkpoint update count */ #endif __u32 recovery_cp; /* 11 recovery checkpoint sector count */ - __u32 gstate_sreserved[MD_SB_GENERIC_STATE_WORDS - 12]; + /* There are only valid for minor_version > 90 */ + __u64 reshape_position; /* 12,13 next address in array-space for reshape */ + __u32 new_level; /* 14 new level we are reshaping to */ + __u32 delta_disks; /* 15 change in number of raid_disks */ + __u32 new_layout; /* 16 new layout */ + __u32 new_chunk; /* 17 new chunk size (bytes) */ + __u32 gstate_sreserved[MD_SB_GENERIC_STATE_WORDS - 18]; /* * Personality information @@ -207,7 +225,14 @@ struct mdp_superblock_1 { * NOTE: signed, so bitmap can be before superblock * only meaningful of feature_map[0] is set. */ - __u8 pad1[128-100]; /* set to 0 when written */ + + /* These are only valid with feature bit '4' */ + __u64 reshape_position; /* next address in array-space for reshape */ + __u32 new_level; /* new level we are reshaping to */ + __u32 delta_disks; /* change in number of raid_disks */ + __u32 new_layout; /* new layout */ + __u32 new_chunk; /* new chunk size (bytes) */ + __u8 pad1[128-124]; /* set to 0 when written */ /* constant this-device information - 64 bytes */ __u64 data_offset; /* sector start of data, often 0 */ @@ -240,8 +265,9 @@ struct mdp_superblock_1 { /* feature_map bits */ #define MD_FEATURE_BITMAP_OFFSET 1 +#define MD_FEATURE_RESHAPE_ACTIVE 4 -#define MD_FEATURE_ALL 1 +#define MD_FEATURE_ALL 5 #endif diff --git a/include/linux/raid/raid5.h b/include/linux/raid/raid5.h index 55c738d50508..abcdf0d0658a 100644 --- a/include/linux/raid/raid5.h +++ b/include/linux/raid/raid5.h @@ -224,6 +224,7 @@ struct raid5_private_data { struct list_head bitmap_list; /* stripes delaying awaiting bitmap update */ atomic_t preread_active_stripes; /* stripes with scheduled io */ + atomic_t reshape_stripes; /* stripes with pending writes for reshape */ /* unfortunately we need two cache names as we temporarily have * two caches. */ -- cgit v1.2.3 From b578d55fdd80140f657130abd85aebeb345755fb Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 27 Mar 2006 01:18:12 -0800 Subject: [PATCH] md: Only checkpoint expansion progress occasionally Instead of checkpointing at each stripe, only checkpoint when a new write would overwrite uncheckpointed data. Block any write to the uncheckpointed area. Arbitrarily checkpoint at least every 3Meg. Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/raid/raid5.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/raid/raid5.h b/include/linux/raid/raid5.h index abcdf0d0658a..914af667044f 100644 --- a/include/linux/raid/raid5.h +++ b/include/linux/raid/raid5.h @@ -217,6 +217,9 @@ struct raid5_private_data { /* used during an expand */ sector_t expand_progress; /* MaxSector when no expand happening */ + sector_t expand_lo; /* from here up to expand_progress it out-of-bounds + * as we haven't flushed the metadata yet + */ int previous_raid_disks; struct list_head handle_list; /* stripes needing handling */ -- cgit v1.2.3 From 63c70c4f3a30e77e6f445bd16eff7934a031ebd3 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 27 Mar 2006 01:18:13 -0800 Subject: [PATCH] md: Split reshape handler in check_reshape and start_reshape check_reshape checks validity and does things that can be done instantly - like adding devices to raid1. start_reshape initiates a restriping process to convert the whole array. Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/raid/md_k.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/raid/md_k.h b/include/linux/raid/md_k.h index 1a6f9f2f6282..002ee631fabb 100644 --- a/include/linux/raid/md_k.h +++ b/include/linux/raid/md_k.h @@ -261,7 +261,8 @@ struct mdk_personality int (*spare_active) (mddev_t *mddev); sector_t (*sync_request)(mddev_t *mddev, sector_t sector_nr, int *skipped, int go_faster); int (*resize) (mddev_t *mddev, sector_t sectors); - int (*reshape) (mddev_t *mddev, int raid_disks); + int (*check_reshape) (mddev_t *mddev); + int (*start_reshape) (mddev_t *mddev); int (*reconfig) (mddev_t *mddev, int layout, int chunk_size); /* quiesce moves between quiescence states * 0 - fully active -- cgit v1.2.3 From e464eafdb4400c6d6576ba3840d8bd40340f8a96 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 27 Mar 2006 01:18:14 -0800 Subject: [PATCH] md: Support suspending of IO to regions of an md array This allows user-space to access data safely. This is needed for raid5 reshape as user-space needs to take a backup of the first few stripes before allowing reshape to commence. It will also be useful in cluster-aware raid1 configurations so that all cluster members can leave a section of the array untouched while a resync/recovery happens. A 'start' and 'end' of the suspended range are written to 2 sysfs attributes. Note that only one range can be suspended at a time. Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/raid/md_k.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/raid/md_k.h b/include/linux/raid/md_k.h index 002ee631fabb..c0d3097846a7 100644 --- a/include/linux/raid/md_k.h +++ b/include/linux/raid/md_k.h @@ -151,6 +151,10 @@ struct mddev_s sector_t resync_mismatches; /* count of sectors where * parity/replica mismatch found */ + + /* allow user-space to request suspension of IO to regions of the array */ + sector_t suspend_lo; + sector_t suspend_hi; /* if zero, use the system-wide default */ int sync_speed_min; int sync_speed_max; -- cgit v1.2.3 From df5b89b323b922f56650b4b4d7c41899b937cf19 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 27 Mar 2006 01:18:20 -0800 Subject: [PATCH] md: Convert reconfig_sem to reconfig_mutex ... being careful that mutex_trylock is inverted wrt down_trylock Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/raid/md_k.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/raid/md_k.h b/include/linux/raid/md_k.h index c0d3097846a7..e2df61f5b09a 100644 --- a/include/linux/raid/md_k.h +++ b/include/linux/raid/md_k.h @@ -185,7 +185,7 @@ struct mddev_s unsigned long recovery; int in_sync; /* know to not need resync */ - struct semaphore reconfig_sem; + struct mutex reconfig_mutex; atomic_t active; int changed; /* true if we might need to reread partition info */ -- cgit v1.2.3 From e2d74ac0664c89757bde8fb18c98cd7bf53da61c Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 28 Mar 2006 08:59:01 +0200 Subject: [PATCH] [BLOCK] cfq-iosched: change cfq io context linking from list to tree On setups with many disks, we spend a considerable amount of time looking up the process-disk mapping on each queue of io. Testing with a NULL based block driver, this costs 40-50% reduction in throughput for 1000 disks. Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c179966f1a2f..ed0ffa673568 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -55,13 +55,11 @@ struct as_io_context { struct cfq_queue; struct cfq_io_context { - /* - * circular list of cfq_io_contexts belonging to a process io context - */ - struct list_head list; - struct cfq_queue *cfqq[2]; + struct rb_node rb_node; void *key; + struct cfq_queue *cfqq[2]; + struct io_context *ioc; unsigned long last_end_request; @@ -72,8 +70,8 @@ struct cfq_io_context { struct list_head queue_list; - void (*dtor)(struct cfq_io_context *); - void (*exit)(struct cfq_io_context *); + void (*dtor)(struct io_context *); /* destructor */ + void (*exit)(struct io_context *); /* called on task exit */ }; /* @@ -94,7 +92,7 @@ struct io_context { int nr_batch_requests; /* Number of requests left in the batch */ struct as_io_context *aic; - struct cfq_io_context *cic; + struct rb_root cic_root; }; void put_io_context(struct io_context *ioc); -- cgit v1.2.3 From 206dc69b31ca05baac68c75b8ed2ba7dd857d273 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 28 Mar 2006 13:03:44 +0200 Subject: [BLOCK] cfq-iosched: seek and async performance fixes Detect whether a given process is seeky and if so disable (mostly) the idle window if it is. We still allow just a little idle time, just enough to allow that process to submit a new request. That is needed to maintain fairness across priority groups. In some cases, we could setup several async queues. This is not optimal from a performance POV, since we want all async io in one queue to perform good sorting on it. It also impacted sync queues, as async io got too much slice time. Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index ed0ffa673568..d0cac8b58de7 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -63,11 +63,17 @@ struct cfq_io_context { struct io_context *ioc; unsigned long last_end_request; - unsigned long last_queue; + sector_t last_request_pos; + unsigned long last_queue; + unsigned long ttime_total; unsigned long ttime_samples; unsigned long ttime_mean; + unsigned int seek_samples; + u64 seek_total; + sector_t seek_mean; + struct list_head queue_list; void (*dtor)(struct io_context *); /* destructor */ -- cgit v1.2.3 From 0080b7aae88c75e2a6b38dfcb228b0f239e18e3c Mon Sep 17 00:00:00 2001 From: Paul Fulghum Date: Tue, 28 Mar 2006 01:56:15 -0800 Subject: [PATCH] synclink_gt add gpio feature Add driver support for general purpose I/O feature of the Synclink GT adapters. Signed-off-by: Paul Fulghum Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/synclink.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/synclink.h b/include/linux/synclink.h index 1b7cd8d1a71b..2993302f7923 100644 --- a/include/linux/synclink.h +++ b/include/linux/synclink.h @@ -1,7 +1,7 @@ /* * SyncLink Multiprotocol Serial Adapter Driver * - * $Id: synclink.h,v 3.10 2005/11/08 19:50:54 paulkf Exp $ + * $Id: synclink.h,v 3.11 2006/02/06 21:20:29 paulkf Exp $ * * Copyright (C) 1998-2000 by Microgate Corporation * @@ -221,6 +221,12 @@ struct mgsl_icount { __u32 rxidle; }; +struct gpio_desc { + __u32 state; + __u32 smask; + __u32 dir; + __u32 dmask; +}; #define DEBUG_LEVEL_DATA 1 #define DEBUG_LEVEL_ERROR 2 @@ -276,5 +282,8 @@ struct mgsl_icount { #define MGSL_IOCLOOPTXDONE _IO(MGSL_MAGIC_IOC,9) #define MGSL_IOCSIF _IO(MGSL_MAGIC_IOC,10) #define MGSL_IOCGIF _IO(MGSL_MAGIC_IOC,11) +#define MGSL_IOCSGPIO _IOW(MGSL_MAGIC_IOC,16,struct gpio_desc) +#define MGSL_IOCGGPIO _IOR(MGSL_MAGIC_IOC,17,struct gpio_desc) +#define MGSL_IOCWAITGPIO _IOWR(MGSL_MAGIC_IOC,18,struct gpio_desc) #endif /* _SYNCLINK_H_ */ -- cgit v1.2.3 From 273577165cd206d2d6689ee4b18aa13de1ec4bde Mon Sep 17 00:00:00 2001 From: Brian Rogan Date: Tue, 28 Mar 2006 01:56:20 -0800 Subject: [PATCH] Add oprofile_add_ext_sample On ppc64 we look at a profiling register to work out the sample address and if it was in userspace or kernel. The backtrace interface oprofile_add_sample does not allow this. Create oprofile_add_ext_sample and make oprofile_add_sample use it too. Signed-off-by: Anton Blanchard Cc: Philippe Elie Cc: John Levon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/oprofile.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/oprofile.h b/include/linux/oprofile.h index 559c4c38a9c7..b5b3197dfd4f 100644 --- a/include/linux/oprofile.h +++ b/include/linux/oprofile.h @@ -61,6 +61,16 @@ void oprofile_arch_exit(void); */ void oprofile_add_sample(struct pt_regs * const regs, unsigned long event); +/** + * Add an extended sample. Use this when the PC is not from the regs, and + * we cannot determine if we're in kernel mode from the regs. + * + * This function does perform a backtrace. + * + */ +void oprofile_add_ext_sample(unsigned long pc, struct pt_regs * const regs, + unsigned long event, int is_kernel); + /* Use this instead when the PC value is not from the regs. Doesn't * backtrace. */ void oprofile_add_pc(unsigned long pc, int is_kernel, unsigned long event); -- cgit v1.2.3 From a28af471b8946de052a0eb0c080d5457be93f168 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Tue, 28 Mar 2006 01:56:26 -0800 Subject: [PATCH] fs/fat/: proper prototypes for two functions Add proper prototypes for fat_cache_init() and fat_cache_destroy() in msdos_fs.h. Signed-off-by: Adrian Bunk Acked-by: OGAWA Hirofumi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/msdos_fs.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/msdos_fs.h b/include/linux/msdos_fs.h index 779e6a5744c7..53cee1581650 100644 --- a/include/linux/msdos_fs.h +++ b/include/linux/msdos_fs.h @@ -420,6 +420,9 @@ extern int date_dos2unix(unsigned short time, unsigned short date); extern void fat_date_unix2dos(int unix_date, __le16 *time, __le16 *date); extern int fat_sync_bhs(struct buffer_head **bhs, int nr_bhs); +int fat_cache_init(void); +void fat_cache_destroy(void); + #endif /* __KERNEL__ */ #endif -- cgit v1.2.3 From e51236092d2f7e40e87e88804b5b42e5f8025415 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Tue, 28 Mar 2006 01:56:27 -0800 Subject: [PATCH] remove relayfs_fs.h This is obsolete. Cc: Tom Zanussi Cc: Jens Axboe Cc: Greg KH Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/relayfs_fs.h | 287 --------------------------------------------- 1 file changed, 287 deletions(-) delete mode 100644 include/linux/relayfs_fs.h (limited to 'include/linux') diff --git a/include/linux/relayfs_fs.h b/include/linux/relayfs_fs.h deleted file mode 100644 index 7342e66247fb..000000000000 --- a/include/linux/relayfs_fs.h +++ /dev/null @@ -1,287 +0,0 @@ -/* - * linux/include/linux/relayfs_fs.h - * - * Copyright (C) 2002, 2003 - Tom Zanussi (zanussi@us.ibm.com), IBM Corp - * Copyright (C) 1999, 2000, 2001, 2002 - Karim Yaghmour (karim@opersys.com) - * - * RelayFS definitions and declarations - */ - -#ifndef _LINUX_RELAYFS_FS_H -#define _LINUX_RELAYFS_FS_H - -#include -#include -#include -#include -#include -#include -#include -#include - -/* - * Tracks changes to rchan/rchan_buf structs - */ -#define RELAYFS_CHANNEL_VERSION 6 - -/* - * Per-cpu relay channel buffer - */ -struct rchan_buf -{ - void *start; /* start of channel buffer */ - void *data; /* start of current sub-buffer */ - size_t offset; /* current offset into sub-buffer */ - size_t subbufs_produced; /* count of sub-buffers produced */ - size_t subbufs_consumed; /* count of sub-buffers consumed */ - struct rchan *chan; /* associated channel */ - wait_queue_head_t read_wait; /* reader wait queue */ - struct work_struct wake_readers; /* reader wake-up work struct */ - struct dentry *dentry; /* channel file dentry */ - struct kref kref; /* channel buffer refcount */ - struct page **page_array; /* array of current buffer pages */ - unsigned int page_count; /* number of current buffer pages */ - unsigned int finalized; /* buffer has been finalized */ - size_t *padding; /* padding counts per sub-buffer */ - size_t prev_padding; /* temporary variable */ - size_t bytes_consumed; /* bytes consumed in cur read subbuf */ - unsigned int cpu; /* this buf's cpu */ -} ____cacheline_aligned; - -/* - * Relay channel data structure - */ -struct rchan -{ - u32 version; /* the version of this struct */ - size_t subbuf_size; /* sub-buffer size */ - size_t n_subbufs; /* number of sub-buffers per buffer */ - size_t alloc_size; /* total buffer size allocated */ - struct rchan_callbacks *cb; /* client callbacks */ - struct kref kref; /* channel refcount */ - void *private_data; /* for user-defined data */ - size_t last_toobig; /* tried to log event > subbuf size */ - struct rchan_buf *buf[NR_CPUS]; /* per-cpu channel buffers */ -}; - -/* - * Relay channel client callbacks - */ -struct rchan_callbacks -{ - /* - * subbuf_start - called on buffer-switch to a new sub-buffer - * @buf: the channel buffer containing the new sub-buffer - * @subbuf: the start of the new sub-buffer - * @prev_subbuf: the start of the previous sub-buffer - * @prev_padding: unused space at the end of previous sub-buffer - * - * The client should return 1 to continue logging, 0 to stop - * logging. - * - * NOTE: subbuf_start will also be invoked when the buffer is - * created, so that the first sub-buffer can be initialized - * if necessary. In this case, prev_subbuf will be NULL. - * - * NOTE: the client can reserve bytes at the beginning of the new - * sub-buffer by calling subbuf_start_reserve() in this callback. - */ - int (*subbuf_start) (struct rchan_buf *buf, - void *subbuf, - void *prev_subbuf, - size_t prev_padding); - - /* - * buf_mapped - relayfs buffer mmap notification - * @buf: the channel buffer - * @filp: relayfs file pointer - * - * Called when a relayfs file is successfully mmapped - */ - void (*buf_mapped)(struct rchan_buf *buf, - struct file *filp); - - /* - * buf_unmapped - relayfs buffer unmap notification - * @buf: the channel buffer - * @filp: relayfs file pointer - * - * Called when a relayfs file is successfully unmapped - */ - void (*buf_unmapped)(struct rchan_buf *buf, - struct file *filp); - /* - * create_buf_file - create file to represent a relayfs channel buffer - * @filename: the name of the file to create - * @parent: the parent of the file to create - * @mode: the mode of the file to create - * @buf: the channel buffer - * @is_global: outparam - set non-zero if the buffer should be global - * - * Called during relay_open(), once for each per-cpu buffer, - * to allow the client to create a file to be used to - * represent the corresponding channel buffer. If the file is - * created outside of relayfs, the parent must also exist in - * that filesystem. - * - * The callback should return the dentry of the file created - * to represent the relay buffer. - * - * Setting the is_global outparam to a non-zero value will - * cause relay_open() to create a single global buffer rather - * than the default set of per-cpu buffers. - * - * See Documentation/filesystems/relayfs.txt for more info. - */ - struct dentry *(*create_buf_file)(const char *filename, - struct dentry *parent, - int mode, - struct rchan_buf *buf, - int *is_global); - - /* - * remove_buf_file - remove file representing a relayfs channel buffer - * @dentry: the dentry of the file to remove - * - * Called during relay_close(), once for each per-cpu buffer, - * to allow the client to remove a file used to represent a - * channel buffer. - * - * The callback should return 0 if successful, negative if not. - */ - int (*remove_buf_file)(struct dentry *dentry); -}; - -/* - * relayfs kernel API, fs/relayfs/relay.c - */ - -struct rchan *relay_open(const char *base_filename, - struct dentry *parent, - size_t subbuf_size, - size_t n_subbufs, - struct rchan_callbacks *cb); -extern void relay_close(struct rchan *chan); -extern void relay_flush(struct rchan *chan); -extern void relay_subbufs_consumed(struct rchan *chan, - unsigned int cpu, - size_t consumed); -extern void relay_reset(struct rchan *chan); -extern int relay_buf_full(struct rchan_buf *buf); - -extern size_t relay_switch_subbuf(struct rchan_buf *buf, - size_t length); -extern struct dentry *relayfs_create_dir(const char *name, - struct dentry *parent); -extern int relayfs_remove_dir(struct dentry *dentry); -extern struct dentry *relayfs_create_file(const char *name, - struct dentry *parent, - int mode, - struct file_operations *fops, - void *data); -extern int relayfs_remove_file(struct dentry *dentry); - -/** - * relay_write - write data into the channel - * @chan: relay channel - * @data: data to be written - * @length: number of bytes to write - * - * Writes data into the current cpu's channel buffer. - * - * Protects the buffer by disabling interrupts. Use this - * if you might be logging from interrupt context. Try - * __relay_write() if you know you won't be logging from - * interrupt context. - */ -static inline void relay_write(struct rchan *chan, - const void *data, - size_t length) -{ - unsigned long flags; - struct rchan_buf *buf; - - local_irq_save(flags); - buf = chan->buf[smp_processor_id()]; - if (unlikely(buf->offset + length > chan->subbuf_size)) - length = relay_switch_subbuf(buf, length); - memcpy(buf->data + buf->offset, data, length); - buf->offset += length; - local_irq_restore(flags); -} - -/** - * __relay_write - write data into the channel - * @chan: relay channel - * @data: data to be written - * @length: number of bytes to write - * - * Writes data into the current cpu's channel buffer. - * - * Protects the buffer by disabling preemption. Use - * relay_write() if you might be logging from interrupt - * context. - */ -static inline void __relay_write(struct rchan *chan, - const void *data, - size_t length) -{ - struct rchan_buf *buf; - - buf = chan->buf[get_cpu()]; - if (unlikely(buf->offset + length > buf->chan->subbuf_size)) - length = relay_switch_subbuf(buf, length); - memcpy(buf->data + buf->offset, data, length); - buf->offset += length; - put_cpu(); -} - -/** - * relay_reserve - reserve slot in channel buffer - * @chan: relay channel - * @length: number of bytes to reserve - * - * Returns pointer to reserved slot, NULL if full. - * - * Reserves a slot in the current cpu's channel buffer. - * Does not protect the buffer at all - caller must provide - * appropriate synchronization. - */ -static inline void *relay_reserve(struct rchan *chan, size_t length) -{ - void *reserved; - struct rchan_buf *buf = chan->buf[smp_processor_id()]; - - if (unlikely(buf->offset + length > buf->chan->subbuf_size)) { - length = relay_switch_subbuf(buf, length); - if (!length) - return NULL; - } - reserved = buf->data + buf->offset; - buf->offset += length; - - return reserved; -} - -/** - * subbuf_start_reserve - reserve bytes at the start of a sub-buffer - * @buf: relay channel buffer - * @length: number of bytes to reserve - * - * Helper function used to reserve bytes at the beginning of - * a sub-buffer in the subbuf_start() callback. - */ -static inline void subbuf_start_reserve(struct rchan_buf *buf, - size_t length) -{ - BUG_ON(length >= buf->chan->subbuf_size - 1); - buf->offset = length; -} - -/* - * exported relay file operations, fs/relayfs/inode.c - */ -extern struct file_operations relay_file_operations; - -#endif /* _LINUX_RELAYFS_FS_H */ - -- cgit v1.2.3 From d266ab88938e49aa95f1965ee020df1b1d4c5761 Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Tue, 28 Mar 2006 01:56:31 -0800 Subject: [PATCH] Small fixes backported to old IDE SiS driver Some quick backport bits from the libata PATA work to fix things found in the sis driver. The piix driver needs some fixes too but those are way to large and need someone working on old IDE with time to do them. This patch fixes the case where random bits get loaded into SIS timing registers according to the description of the correct behaviour from Vojtech Pavlik. It also adds the SiS5517 ATA16 chipset which is not currently supported by the driver. Thanks to Conrad Harriss for loaning me the machine with the 5517 chipset. Signed-off-by: Alan Cox Acked-by: Bartlomiej Zolnierkiewicz Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pci_ids.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 02f6cf20b141..e2ab2ac18d6b 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -642,6 +642,7 @@ #define PCI_DEVICE_ID_SI_965 0x0965 #define PCI_DEVICE_ID_SI_5511 0x5511 #define PCI_DEVICE_ID_SI_5513 0x5513 +#define PCI_DEVICE_ID_SI_5517 0x5517 #define PCI_DEVICE_ID_SI_5518 0x5518 #define PCI_DEVICE_ID_SI_5571 0x5571 #define PCI_DEVICE_ID_SI_5581 0x5581 -- cgit v1.2.3 From 70674f95c0a2ea694d5c39f4e514f538a09be36f Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Tue, 28 Mar 2006 01:56:33 -0800 Subject: [PATCH] Optimize select/poll by putting small data sets on the stack Optimize select and poll by a using stack space for small fd sets This brings back an old optimization from Linux 2.0. Using the stack is faster than kmalloc. On a Intel P4 system it speeds up a select of a single pty fd by about 13% (~4000 cycles -> ~3500) It also saves memory because a daemon hanging in select or poll will usually save one or two less pages. This can add up - e.g. if you have 10 daemons blocking in poll/select you save 40KB of memory. I did a patch for this long ago, but it was never applied. This version is a reimplementation of the old patch that tries to be less intrusive. I only did the minimal changes needed for the stack allocation. The cut off point before external memory is allocated is currently at 832bytes. The system calls always allocate this much memory on the stack. These 832 bytes are divided into 256 bytes frontend data (for the select bitmaps of the pollfds) and the rest of the space for the wait queues used by the low level drivers. There are some extreme cases where this won't work out for select and it falls back to allocating memory too early - especially with very sparse large select bitmaps - but the majority of processes who only have a small number of file descriptors should be ok. [TBD: 832/256 might not be the best split for select or poll] I suspect more optimizations might be possible, but they would be more complicated. One way would be to cache the select/poll context over multiple system calls because typically the input values should be similar. Problem is when to flush the file descriptors out though. Signed-off-by: Andi Kleen Cc: Eric Dumazet Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/poll.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/poll.h b/include/linux/poll.h index 8e8f6098508a..51e1b56741fb 100644 --- a/include/linux/poll.h +++ b/include/linux/poll.h @@ -11,6 +11,15 @@ #include #include +/* ~832 bytes of stack space used max in sys_select/sys_poll before allocating + additional memory. */ +#define MAX_STACK_ALLOC 832 +#define FRONTEND_STACK_ALLOC 256 +#define SELECT_STACK_ALLOC FRONTEND_STACK_ALLOC +#define POLL_STACK_ALLOC FRONTEND_STACK_ALLOC +#define WQUEUES_STACK_ALLOC (MAX_STACK_ALLOC - FRONTEND_STACK_ALLOC) +#define N_INLINE_POLL_ENTRIES (WQUEUES_STACK_ALLOC / sizeof(struct poll_table_entry)) + struct poll_table_struct; /* @@ -33,6 +42,12 @@ static inline void init_poll_funcptr(poll_table *pt, poll_queue_proc qproc) pt->qproc = qproc; } +struct poll_table_entry { + struct file * filp; + wait_queue_t wait; + wait_queue_head_t * wait_address; +}; + /* * Structures and helpers for sys_poll/sys_poll */ @@ -40,6 +55,8 @@ struct poll_wqueues { poll_table pt; struct poll_table_page * table; int error; + int inline_index; + struct poll_table_entry inline_entries[N_INLINE_POLL_ENTRIES]; }; extern void poll_initwait(struct poll_wqueues *pwq); -- cgit v1.2.3 From 631d6747e1d877a4baa924cb373b8b9511a53e5e Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Tue, 28 Mar 2006 01:56:36 -0800 Subject: [PATCH] for_each_possible_cpu: defines for_each_possible_cpu for_each_cpu() is a for-loop over cpu_possible_map. for_each_online_cpu is for-loop cpu over cpu_online_map. .....for_each_cpu() is not sufficiently explicit and can lead to mistakes. This patch adds for_each_possible_cpu() in preparation for the removal of for_each_cpu(). Signed-off-by: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cpumask.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 99e6115d8e52..9cbb781d6f80 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -67,7 +67,7 @@ * * int any_online_cpu(mask) First online cpu in mask * - * for_each_cpu(cpu) for-loop cpu over cpu_possible_map + * for_each_possible_cpu(cpu) for-loop cpu over cpu_possible_map * for_each_online_cpu(cpu) for-loop cpu over cpu_online_map * for_each_present_cpu(cpu) for-loop cpu over cpu_present_map * @@ -405,7 +405,8 @@ int __any_online_cpu(const cpumask_t *mask); #define any_online_cpu(mask) 0 #endif -#define for_each_cpu(cpu) for_each_cpu_mask((cpu), cpu_possible_map) +#define for_each_cpu(cpu) for_each_cpu_mask((cpu), cpu_possible_map) +#define for_each_possible_cpu(cpu) for_each_cpu_mask((cpu), cpu_possible_map) #define for_each_online_cpu(cpu) for_each_cpu_mask((cpu), cpu_online_map) #define for_each_present_cpu(cpu) for_each_cpu_mask((cpu), cpu_present_map) -- cgit v1.2.3 From 0a945022778f100115d0cb6234eb28fc1b15ccaf Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Tue, 28 Mar 2006 01:56:37 -0800 Subject: [PATCH] for_each_possible_cpu: fixes for generic part replaces for_each_cpu with for_each_possible_cpu(). Signed-off-by: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/genhd.h | 4 ++-- include/linux/kernel_stat.h | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 3c1b0294a742..10a27f29d692 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -152,14 +152,14 @@ struct disk_attribute { ({ \ typeof(gendiskp->dkstats->field) res = 0; \ int i; \ - for_each_cpu(i) \ + for_each_possible_cpu(i) \ res += per_cpu_ptr(gendiskp->dkstats, i)->field; \ res; \ }) static inline void disk_stat_set_all(struct gendisk *gendiskp, int value) { int i; - for_each_cpu(i) + for_each_possible_cpu(i) memset(per_cpu_ptr(gendiskp->dkstats, i), value, sizeof (struct disk_stats)); } diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h index a484572c302e..b46249082cca 100644 --- a/include/linux/kernel_stat.h +++ b/include/linux/kernel_stat.h @@ -46,7 +46,7 @@ static inline int kstat_irqs(int irq) { int cpu, sum = 0; - for_each_cpu(cpu) + for_each_possible_cpu(cpu) sum += kstat_cpu(cpu).irqs[irq]; return sum; -- cgit v1.2.3 From 99ac48f54a91d02140c497edc31dc57d4bc5c85d Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Tue, 28 Mar 2006 01:56:41 -0800 Subject: [PATCH] mark f_ops const in the inode Mark the f_ops members of inodes as const, as well as fix the ripple-through this causes by places that copy this f_ops and then "do stuff" with it. Signed-off-by: Arjan van de Ven Signed-off-by: Alexey Dobriyan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cdev.h | 4 ++-- include/linux/debugfs.h | 2 +- include/linux/fs.h | 6 +++--- include/linux/input.h | 2 +- include/linux/miscdevice.h | 2 +- include/linux/oprofile.h | 4 ++-- include/linux/proc_fs.h | 4 ++-- include/linux/sound.h | 12 ++++++------ include/linux/sunrpc/stats.h | 4 ++-- include/linux/usb.h | 2 +- include/linux/videodev2.h | 2 +- 11 files changed, 22 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cdev.h b/include/linux/cdev.h index 8da37e29cb87..2216638962d2 100644 --- a/include/linux/cdev.h +++ b/include/linux/cdev.h @@ -5,13 +5,13 @@ struct cdev { struct kobject kobj; struct module *owner; - struct file_operations *ops; + const struct file_operations *ops; struct list_head list; dev_t dev; unsigned int count; }; -void cdev_init(struct cdev *, struct file_operations *); +void cdev_init(struct cdev *, const struct file_operations *); struct cdev *cdev_alloc(void); diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h index 4b0428e335be..176e2d371577 100644 --- a/include/linux/debugfs.h +++ b/include/linux/debugfs.h @@ -29,7 +29,7 @@ struct debugfs_blob_wrapper { #if defined(CONFIG_DEBUG_FS) struct dentry *debugfs_create_file(const char *name, mode_t mode, struct dentry *parent, void *data, - struct file_operations *fops); + const struct file_operations *fops); struct dentry *debugfs_create_dir(const char *name, struct dentry *parent); diff --git a/include/linux/fs.h b/include/linux/fs.h index 680d913350e7..ef355bc73714 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -496,7 +496,7 @@ struct inode { struct mutex i_mutex; struct rw_semaphore i_alloc_sem; struct inode_operations *i_op; - struct file_operations *i_fop; /* former ->i_op->default_file_ops */ + const struct file_operations *i_fop; /* former ->i_op->default_file_ops */ struct super_block *i_sb; struct file_lock *i_flock; struct address_space *i_mapping; @@ -636,7 +636,7 @@ struct file { } f_u; struct dentry *f_dentry; struct vfsmount *f_vfsmnt; - struct file_operations *f_op; + const struct file_operations *f_op; atomic_t f_count; unsigned int f_flags; mode_t f_mode; @@ -1414,7 +1414,7 @@ extern void bd_release_from_disk(struct block_device *, struct gendisk *); extern int alloc_chrdev_region(dev_t *, unsigned, unsigned, const char *); extern int register_chrdev_region(dev_t, unsigned, const char *); extern int register_chrdev(unsigned int, const char *, - struct file_operations *); + const struct file_operations *); extern int unregister_chrdev(unsigned int, const char *); extern void unregister_chrdev_region(dev_t, unsigned); extern int chrdev_open(struct inode *, struct file *); diff --git a/include/linux/input.h b/include/linux/input.h index 6d4cc3c110d6..1d4e341b72e6 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -957,7 +957,7 @@ struct input_handler { struct input_handle* (*connect)(struct input_handler *handler, struct input_dev *dev, struct input_device_id *id); void (*disconnect)(struct input_handle *handle); - struct file_operations *fops; + const struct file_operations *fops; int minor; char *name; diff --git a/include/linux/miscdevice.h b/include/linux/miscdevice.h index 14ceebfc1efa..5b584dafb5a6 100644 --- a/include/linux/miscdevice.h +++ b/include/linux/miscdevice.h @@ -36,7 +36,7 @@ struct class_device; struct miscdevice { int minor; const char *name; - struct file_operations *fops; + const struct file_operations *fops; struct list_head list; struct device *dev; struct class_device *class; diff --git a/include/linux/oprofile.h b/include/linux/oprofile.h index b5b3197dfd4f..0d514b252454 100644 --- a/include/linux/oprofile.h +++ b/include/linux/oprofile.h @@ -84,10 +84,10 @@ void oprofile_add_trace(unsigned long eip); * the specified file operations. */ int oprofilefs_create_file(struct super_block * sb, struct dentry * root, - char const * name, struct file_operations * fops); + char const * name, const struct file_operations * fops); int oprofilefs_create_file_perm(struct super_block * sb, struct dentry * root, - char const * name, struct file_operations * fops, int perm); + char const * name, const struct file_operations * fops, int perm); /** Create a file for read/write access to an unsigned long. */ int oprofilefs_create_ulong(struct super_block * sb, struct dentry * root, diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index cb224cf653b1..6d03d025fcd5 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -58,7 +58,7 @@ struct proc_dir_entry { gid_t gid; loff_t size; struct inode_operations * proc_iops; - struct file_operations * proc_fops; + const struct file_operations * proc_fops; get_info_t *get_info; struct module *owner; struct proc_dir_entry *next, *parent, *subdir; @@ -189,7 +189,7 @@ static inline struct proc_dir_entry *proc_net_create(const char *name, } static inline struct proc_dir_entry *proc_net_fops_create(const char *name, - mode_t mode, struct file_operations *fops) + mode_t mode, const struct file_operations *fops) { struct proc_dir_entry *res = create_proc_entry(name, mode, proc_net); if (res) diff --git a/include/linux/sound.h b/include/linux/sound.h index 72b9af4c3fd4..f63d8342ffa3 100644 --- a/include/linux/sound.h +++ b/include/linux/sound.h @@ -30,12 +30,12 @@ */ struct device; -extern int register_sound_special(struct file_operations *fops, int unit); -extern int register_sound_special_device(struct file_operations *fops, int unit, struct device *dev); -extern int register_sound_mixer(struct file_operations *fops, int dev); -extern int register_sound_midi(struct file_operations *fops, int dev); -extern int register_sound_dsp(struct file_operations *fops, int dev); -extern int register_sound_synth(struct file_operations *fops, int dev); +extern int register_sound_special(const struct file_operations *fops, int unit); +extern int register_sound_special_device(const struct file_operations *fops, int unit, struct device *dev); +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); diff --git a/include/linux/sunrpc/stats.h b/include/linux/sunrpc/stats.h index 0d6ed3c8bdc4..d93c24b47f3f 100644 --- a/include/linux/sunrpc/stats.h +++ b/include/linux/sunrpc/stats.h @@ -50,7 +50,7 @@ struct proc_dir_entry * rpc_proc_register(struct rpc_stat *); void rpc_proc_unregister(const char *); void rpc_proc_zero(struct rpc_program *); struct proc_dir_entry * svc_proc_register(struct svc_stat *, - struct file_operations *); + const struct file_operations *); void svc_proc_unregister(const char *); void svc_seq_show(struct seq_file *, @@ -65,7 +65,7 @@ static inline void rpc_proc_unregister(const char *p) {} static inline void rpc_proc_zero(struct rpc_program *p) {} static inline struct proc_dir_entry *svc_proc_register(struct svc_stat *s, - struct file_operations *f) { return NULL; } + const struct file_operations *f) { return NULL; } static inline void svc_proc_unregister(const char *p) {} static inline void svc_seq_show(struct seq_file *seq, diff --git a/include/linux/usb.h b/include/linux/usb.h index 130d125fda12..e34e5e3dce52 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -615,7 +615,7 @@ extern struct bus_type usb_bus_type; */ struct usb_class_driver { char *name; - struct file_operations *fops; + const struct file_operations *fops; int minor_base; }; diff --git a/include/linux/videodev2.h b/include/linux/videodev2.h index 2275bfec5b68..af2d6155d3fe 100644 --- a/include/linux/videodev2.h +++ b/include/linux/videodev2.h @@ -75,7 +75,7 @@ struct video_device int minor; /* device ops + callbacks */ - struct file_operations *fops; + const struct file_operations *fops; void (*release)(struct video_device *vfd); -- cgit v1.2.3 From 4b6f5d20b04dcbc3d888555522b90ba6d36c4106 Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Tue, 28 Mar 2006 01:56:42 -0800 Subject: [PATCH] Make most file operations structs in fs/ const This is a conversion to make the various file_operations structs in fs/ const. Basically a regexp job, with a few manual fixups The goal is both to increase correctness (harder to accidentally write to shared datastructures) and reducing the false sharing of cachelines with things that get dirty in .data (while .rodata is nicely read only and thus cache clean) Signed-off-by: Arjan van de Ven Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/coda_linux.h | 6 +++--- include/linux/crash_dump.h | 2 +- include/linux/efs_fs.h | 2 +- include/linux/ext3_fs.h | 4 ++-- include/linux/fs.h | 20 ++++++++++---------- include/linux/hugetlb.h | 2 +- include/linux/msdos_fs.h | 4 ++-- include/linux/ncp_fs.h | 4 ++-- include/linux/nfs_fs.h | 4 ++-- include/linux/proc_fs.h | 6 +++--- include/linux/qnx4_fs.h | 4 ++-- include/linux/ramfs.h | 2 +- include/linux/reiserfs_fs.h | 4 ++-- include/linux/ufs_fs.h | 4 ++-- 14 files changed, 34 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/include/linux/coda_linux.h b/include/linux/coda_linux.h index cc621ec409d8..b3ecf8f71d97 100644 --- a/include/linux/coda_linux.h +++ b/include/linux/coda_linux.h @@ -30,9 +30,9 @@ extern struct inode_operations coda_ioctl_inode_operations; extern struct address_space_operations coda_file_aops; extern struct address_space_operations coda_symlink_aops; -extern struct file_operations coda_dir_operations; -extern struct file_operations coda_file_operations; -extern struct file_operations coda_ioctl_operations; +extern const struct file_operations coda_dir_operations; +extern const struct file_operations coda_file_operations; +extern const struct file_operations coda_ioctl_operations; /* operations shared over more than one file */ int coda_open(struct inode *i, struct file *f); diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h index 534d750d922d..32503657f14f 100644 --- a/include/linux/crash_dump.h +++ b/include/linux/crash_dump.h @@ -11,7 +11,7 @@ extern unsigned long long elfcorehdr_addr; extern ssize_t copy_oldmem_page(unsigned long, char *, size_t, unsigned long, int); -extern struct file_operations proc_vmcore_operations; +extern const struct file_operations proc_vmcore_operations; extern struct proc_dir_entry *proc_vmcore; #endif /* CONFIG_CRASH_DUMP */ diff --git a/include/linux/efs_fs.h b/include/linux/efs_fs.h index 28f368c526fb..fbfa6b52e2fb 100644 --- a/include/linux/efs_fs.h +++ b/include/linux/efs_fs.h @@ -37,7 +37,7 @@ static inline struct efs_sb_info *SUPER_INFO(struct super_block *sb) struct statfs; extern struct inode_operations efs_dir_inode_operations; -extern struct file_operations efs_dir_operations; +extern const struct file_operations efs_dir_operations; extern struct address_space_operations efs_symlink_aops; extern void efs_read_inode(struct inode *); diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h index 8bb4f842cded..3ade6a4e3bdd 100644 --- a/include/linux/ext3_fs.h +++ b/include/linux/ext3_fs.h @@ -833,11 +833,11 @@ do { \ */ /* dir.c */ -extern struct file_operations ext3_dir_operations; +extern const struct file_operations ext3_dir_operations; /* file.c */ extern struct inode_operations ext3_file_inode_operations; -extern struct file_operations ext3_file_operations; +extern const struct file_operations ext3_file_operations; /* namei.c */ extern struct inode_operations ext3_dir_inode_operations; diff --git a/include/linux/fs.h b/include/linux/fs.h index ef355bc73714..408fe89498f4 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1390,11 +1390,11 @@ extern void bd_set_size(struct block_device *, loff_t size); extern void bd_forget(struct inode *inode); extern void bdput(struct block_device *); extern struct block_device *open_by_devnum(dev_t, unsigned); -extern struct file_operations def_blk_fops; +extern const struct file_operations def_blk_fops; extern struct address_space_operations def_blk_aops; -extern struct file_operations def_chr_fops; -extern struct file_operations bad_sock_fops; -extern struct file_operations def_fifo_fops; +extern const struct file_operations def_chr_fops; +extern const struct file_operations bad_sock_fops; +extern const struct file_operations def_fifo_fops; extern int ioctl_by_bdev(struct block_device *, unsigned, unsigned long); extern int blkdev_ioctl(struct inode *, struct file *, unsigned, unsigned long); extern long compat_blkdev_ioctl(struct file *, unsigned, unsigned long); @@ -1444,9 +1444,9 @@ extern void init_special_inode(struct inode *, umode_t, dev_t); extern void make_bad_inode(struct inode *); extern int is_bad_inode(struct inode *); -extern struct file_operations read_fifo_fops; -extern struct file_operations write_fifo_fops; -extern struct file_operations rdwr_fifo_fops; +extern const struct file_operations read_fifo_fops; +extern const struct file_operations write_fifo_fops; +extern const struct file_operations rdwr_fifo_fops; extern int fs_may_remount_ro(struct super_block *); @@ -1688,7 +1688,7 @@ static inline ssize_t blockdev_direct_IO_own_locking(int rw, struct kiocb *iocb, nr_segs, get_block, end_io, DIO_OWN_LOCKING); } -extern struct file_operations generic_ro_fops; +extern const struct file_operations generic_ro_fops; #define special_file(m) (S_ISCHR(m)||S_ISBLK(m)||S_ISFIFO(m)||S_ISSOCK(m)) @@ -1744,9 +1744,9 @@ extern int simple_commit_write(struct file *file, struct page *page, extern struct dentry *simple_lookup(struct inode *, struct dentry *, struct nameidata *); extern ssize_t generic_read_dir(struct file *, char __user *, size_t, loff_t *); -extern struct file_operations simple_dir_operations; +extern const struct file_operations simple_dir_operations; extern struct inode_operations simple_dir_inode_operations; -struct tree_descr { char *name; struct file_operations *ops; int mode; }; +struct tree_descr { char *name; const struct file_operations *ops; int mode; }; struct dentry *d_alloc_name(struct dentry *, const char *); extern int simple_fill_super(struct super_block *, int, struct tree_descr *); extern int simple_pin_fs(char *name, struct vfsmount **mount, int *count); diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index d6f1019625af..4c5e610fe442 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -154,7 +154,7 @@ static inline struct hugetlbfs_sb_info *HUGETLBFS_SB(struct super_block *sb) return sb->s_fs_info; } -extern struct file_operations hugetlbfs_file_operations; +extern const struct file_operations hugetlbfs_file_operations; extern struct vm_operations_struct hugetlb_vm_ops; struct file *hugetlb_zero_setup(size_t); int hugetlb_extend_reservation(struct hugetlbfs_inode_info *info, diff --git a/include/linux/msdos_fs.h b/include/linux/msdos_fs.h index 53cee1581650..d9035c73e5d1 100644 --- a/include/linux/msdos_fs.h +++ b/include/linux/msdos_fs.h @@ -334,7 +334,7 @@ extern int fat_bmap(struct inode *inode, sector_t sector, sector_t *phys, unsigned long *mapped_blocks); /* fat/dir.c */ -extern struct file_operations fat_dir_operations; +extern const struct file_operations fat_dir_operations; extern int fat_search_long(struct inode *inode, const unsigned char *name, int name_len, struct fat_slot_info *sinfo); extern int fat_dir_empty(struct inode *dir); @@ -397,7 +397,7 @@ extern int fat_count_free_clusters(struct super_block *sb); /* fat/file.c */ extern int fat_generic_ioctl(struct inode *inode, struct file *filp, unsigned int cmd, unsigned long arg); -extern struct file_operations fat_file_operations; +extern const struct file_operations fat_file_operations; extern struct inode_operations fat_file_inode_operations; extern int fat_notify_change(struct dentry * dentry, struct iattr * attr); extern void fat_truncate(struct inode *inode); diff --git a/include/linux/ncp_fs.h b/include/linux/ncp_fs.h index e01342568530..96dc237b8f03 100644 --- a/include/linux/ncp_fs.h +++ b/include/linux/ncp_fs.h @@ -209,7 +209,7 @@ void ncp_update_inode2(struct inode *, struct ncp_entry_info *); /* linux/fs/ncpfs/dir.c */ extern struct inode_operations ncp_dir_inode_operations; -extern struct file_operations ncp_dir_operations; +extern const struct file_operations ncp_dir_operations; int ncp_conn_logged_in(struct super_block *); int ncp_date_dos2unix(__le16 time, __le16 date); void ncp_date_unix2dos(int unix_date, __le16 * time, __le16 * date); @@ -230,7 +230,7 @@ void ncp_unlock_server(struct ncp_server *server); /* linux/fs/ncpfs/file.c */ extern struct inode_operations ncp_file_inode_operations; -extern struct file_operations ncp_file_operations; +extern const struct file_operations ncp_file_operations; int ncp_make_open(struct inode *, int); /* linux/fs/ncpfs/mmap.c */ diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index cbebd7d1b9e8..c71227dd4389 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -324,7 +324,7 @@ extern struct inode_operations nfs_file_inode_operations; #ifdef CONFIG_NFS_V3 extern struct inode_operations nfs3_file_inode_operations; #endif /* CONFIG_NFS_V3 */ -extern struct file_operations nfs_file_operations; +extern const struct file_operations nfs_file_operations; extern struct address_space_operations nfs_file_aops; static inline struct rpc_cred *nfs_file_cred(struct file *file) @@ -371,7 +371,7 @@ extern struct inode_operations nfs_dir_inode_operations; #ifdef CONFIG_NFS_V3 extern struct inode_operations nfs3_dir_inode_operations; #endif /* CONFIG_NFS_V3 */ -extern struct file_operations nfs_dir_operations; +extern const struct file_operations nfs_dir_operations; extern struct dentry_operations nfs_dentry_operations; extern int nfs_instantiate(struct dentry *dentry, struct nfs_fh *fh, struct nfs_fattr *fattr); diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 6d03d025fcd5..135871df9911 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -128,9 +128,9 @@ extern int proc_match(int, const char *,struct proc_dir_entry *); extern int proc_readdir(struct file *, void *, filldir_t); extern struct dentry *proc_lookup(struct inode *, struct dentry *, struct nameidata *); -extern struct file_operations proc_kcore_operations; -extern struct file_operations proc_kmsg_operations; -extern struct file_operations ppc_htab_operations; +extern const struct file_operations proc_kcore_operations; +extern const struct file_operations proc_kmsg_operations; +extern const struct file_operations ppc_htab_operations; /* * proc_tty.c diff --git a/include/linux/qnx4_fs.h b/include/linux/qnx4_fs.h index fc610bb0f733..27f49c85d5d6 100644 --- a/include/linux/qnx4_fs.h +++ b/include/linux/qnx4_fs.h @@ -118,8 +118,8 @@ extern struct buffer_head *qnx4_bread(struct inode *, int, int); extern struct inode_operations qnx4_file_inode_operations; extern struct inode_operations qnx4_dir_inode_operations; -extern struct file_operations qnx4_file_operations; -extern struct file_operations qnx4_dir_operations; +extern const struct file_operations qnx4_file_operations; +extern const struct file_operations qnx4_dir_operations; extern int qnx4_is_free(struct super_block *sb, long block); extern int qnx4_set_bitmap(struct super_block *sb, long block, int busy); extern int qnx4_create(struct inode *inode, struct dentry *dentry, int mode, struct nameidata *nd); diff --git a/include/linux/ramfs.h b/include/linux/ramfs.h index 953b6df5d037..78ecfa28b1c2 100644 --- a/include/linux/ramfs.h +++ b/include/linux/ramfs.h @@ -15,7 +15,7 @@ extern unsigned long ramfs_nommu_get_unmapped_area(struct file *file, extern int ramfs_nommu_mmap(struct file *file, struct vm_area_struct *vma); #endif -extern struct file_operations ramfs_file_operations; +extern const struct file_operations ramfs_file_operations; extern struct vm_operations_struct generic_file_vm_ops; #endif diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h index 912f1b7cb18f..5676c4210e2c 100644 --- a/include/linux/reiserfs_fs.h +++ b/include/linux/reiserfs_fs.h @@ -1960,7 +1960,7 @@ int reiserfs_global_version_in_proc(char *buffer, char **start, off_t offset, extern struct inode_operations reiserfs_dir_inode_operations; extern struct inode_operations reiserfs_symlink_inode_operations; extern struct inode_operations reiserfs_special_inode_operations; -extern struct file_operations reiserfs_dir_operations; +extern const struct file_operations reiserfs_dir_operations; /* tail_conversion.c */ int direct2indirect(struct reiserfs_transaction_handle *, struct inode *, @@ -1972,7 +1972,7 @@ void reiserfs_unmap_buffer(struct buffer_head *); /* file.c */ extern struct inode_operations reiserfs_file_inode_operations; -extern struct file_operations reiserfs_file_operations; +extern const struct file_operations reiserfs_file_operations; extern struct address_space_operations reiserfs_address_space_operations; /* fix_nodes.c */ diff --git a/include/linux/ufs_fs.h b/include/linux/ufs_fs.h index b0ffe4356e5a..843aeaaa79d4 100644 --- a/include/linux/ufs_fs.h +++ b/include/linux/ufs_fs.h @@ -895,7 +895,7 @@ extern void ufs_set_link(struct inode *, struct ufs_dir_entry *, struct buffer_h /* file.c */ extern struct inode_operations ufs_file_inode_operations; -extern struct file_operations ufs_file_operations; +extern const struct file_operations ufs_file_operations; extern struct address_space_operations ufs_aops; @@ -915,7 +915,7 @@ extern struct buffer_head * ufs_bread (struct inode *, unsigned, int, int *); extern int ufs_getfrag_block (struct inode *inode, sector_t fragment, struct buffer_head *bh_result, int create); /* namei.c */ -extern struct file_operations ufs_dir_operations; +extern const struct file_operations ufs_dir_operations; /* super.c */ extern void ufs_warning (struct super_block *, const char *, const char *, ...) __attribute__ ((format (printf, 3, 4))); -- cgit v1.2.3 From 910638ae7ed4be27d6af55f6c9b5bf54b838e78b Mon Sep 17 00:00:00 2001 From: Matthias Gehre Date: Tue, 28 Mar 2006 01:56:48 -0800 Subject: [PATCH] Replace 0xff.. with correct DMA_xBIT_MASK Replace all occurences of 0xff.. in calls to function pci_set_dma_mask() and pci_set_consistant_dma_mask() with the corresponding DMA_xBIT_MASK from linux/dma-mapping.h. Signed-off-by: Matthias Gehre Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/dma-mapping.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index a8731062a74c..9b4751aecc23 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -21,6 +21,7 @@ enum dma_data_direction { #define DMA_30BIT_MASK 0x000000003fffffffULL #define DMA_29BIT_MASK 0x000000001fffffffULL #define DMA_28BIT_MASK 0x000000000fffffffULL +#define DMA_24BIT_MASK 0x0000000000ffffffULL #include -- cgit v1.2.3 From 7f927fcc2fd1575d01efb4b76665975007945690 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Tue, 28 Mar 2006 01:56:53 -0800 Subject: [PATCH] Typo fixes Fix a lot of typos. Eyeballed by jmc@ in OpenBSD. Signed-off-by: Alexey Dobriyan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fb.h b/include/linux/fb.h index 2cb19e6503aa..d03fadfcafe3 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -734,7 +734,7 @@ struct fb_tile_ops { /* A driver may set this flag to indicate that it does want a set_par to be * called every time when fbcon_switch is executed. The advantage is that with - * this flag set you can really be shure that set_par is always called before + * this flag set you can really be sure that set_par is always called before * any of the functions dependant on the correct hardware state or altering * that state, even if you are using some broken X releases. The disadvantage * is that it introduces unwanted delays to every console switch if set_par -- cgit v1.2.3