From 8b09dee67f484e9b42114b1a1f068e080fd7aa56 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 12 May 2008 21:21:05 +0200 Subject: rcupreempt: remove duplicate prototypes rcu_batches_completed and rcu_patches_completed_bh are both declared in rcuclassic.h and rcupreempt.h. This patch removes the extra prototypes for them from rcupdate.h. rcu_batches_completed_bh is defined as a static inline in the rcupreempt.h header file. Trying to export this as EXPORT_SYMBOL_GPL causes linking problems with the powerpc linker. There's no need to export a static inlined function. Modules must be compiled with the same type of RCU implementation as the kernel they are for. Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar --- include/linux/rcupdate.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index d42dbec06083..ec2fc5b32646 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -224,8 +224,6 @@ extern void call_rcu_bh(struct rcu_head *head, /* Exported common interfaces */ extern void synchronize_rcu(void); extern void rcu_barrier(void); -extern long rcu_batches_completed(void); -extern long rcu_batches_completed_bh(void); /* Internal to kernel */ extern void rcu_init(void); -- cgit v1.2.3 From 4446a36ff8c74ac3b32feb009b651048e129c6af Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 12 May 2008 21:21:05 +0200 Subject: rcu: add call_rcu_sched() Fourth cut of patch to provide the call_rcu_sched(). This is again to synchronize_sched() as call_rcu() is to synchronize_rcu(). Should be fine for experimental and -rt use, but not ready for inclusion. With some luck, I will be able to tell Andrew to come out of hiding on the next round. Passes multi-day rcutorture sessions with concurrent CPU hotplugging. Fixes since the first version include a bug that could result in indefinite blocking (spotted by Gautham Shenoy), better resiliency against CPU-hotplug operations, and other minor fixes. Fixes since the second version include reworking grace-period detection to avoid deadlocks that could happen when running concurrently with CPU hotplug, adding Mathieu's fix to avoid the softlockup messages, as well as Mathieu's fix to allow use earlier in boot. Fixes since the third version include a wrong-CPU bug spotted by Andrew, getting rid of the obsolete synchronize_kernel API that somehow snuck back in, merging spin_unlock() and local_irq_restore() in a few places, commenting the code that checks for quiescent states based on interrupting from user-mode execution or the idle loop, removing some inline attributes, and some code-style changes. Known/suspected shortcomings: o I still do not entirely trust the sleep/wakeup logic. Next step will be to use a private snapshot of the CPU online mask in rcu_sched_grace_period() -- if the CPU wasn't there at the start of the grace period, we don't need to hear from it. And the bit about accounting for changes in online CPUs inside of rcu_sched_grace_period() is ugly anyway. o It might be good for rcu_sched_grace_period() to invoke resched_cpu() when a given CPU wasn't responding quickly, but resched_cpu() is declared static... This patch also fixes a long-standing bug in the earlier preemptable-RCU implementation of synchronize_rcu() that could result in loss of concurrent external changes to a task's CPU affinity mask. I still cannot remember who reported this... Signed-off-by: Paul E. McKenney Signed-off-by: Mathieu Desnoyers Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/rcuclassic.h | 3 +++ include/linux/rcupdate.h | 22 ++++++++++++++++++++++ include/linux/rcupreempt.h | 42 ++++++++++++++++++++++++++++++++++++------ 3 files changed, 61 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcuclassic.h b/include/linux/rcuclassic.h index b3aa05baab8a..8c774905dcfe 100644 --- a/include/linux/rcuclassic.h +++ b/include/linux/rcuclassic.h @@ -151,7 +151,10 @@ extern struct lockdep_map rcu_lock_map; #define __synchronize_sched() synchronize_rcu() +#define call_rcu_sched(head, func) call_rcu(head, func) + extern void __rcu_init(void); +#define rcu_init_sched() do { } while (0) extern void rcu_check_callbacks(int cpu, int user); extern void rcu_restart_cpu(int cpu); diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index ec2fc5b32646..411969cb5243 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -40,6 +40,7 @@ #include #include #include +#include /** * struct rcu_head - callback structure for use with RCU @@ -168,6 +169,27 @@ struct rcu_head { (p) = (v); \ }) +/* Infrastructure to implement the synchronize_() primitives. */ + +struct rcu_synchronize { + struct rcu_head head; + struct completion completion; +}; + +extern void wakeme_after_rcu(struct rcu_head *head); + +#define synchronize_rcu_xxx(name, func) \ +void name(void) \ +{ \ + struct rcu_synchronize rcu; \ + \ + init_completion(&rcu.completion); \ + /* Will wake me after RCU finished. */ \ + func(&rcu.head, wakeme_after_rcu); \ + /* Wait for it. */ \ + wait_for_completion(&rcu.completion); \ +} + /** * synchronize_sched - block until all CPUs have exited any non-preemptive * kernel code sequences. diff --git a/include/linux/rcupreempt.h b/include/linux/rcupreempt.h index 8a05c7e20bc4..f04b64eca636 100644 --- a/include/linux/rcupreempt.h +++ b/include/linux/rcupreempt.h @@ -40,10 +40,39 @@ #include #include -#define rcu_qsctr_inc(cpu) +struct rcu_dyntick_sched { + int dynticks; + int dynticks_snap; + int sched_qs; + int sched_qs_snap; + int sched_dynticks_snap; +}; + +DECLARE_PER_CPU(struct rcu_dyntick_sched, rcu_dyntick_sched); + +static inline void rcu_qsctr_inc(int cpu) +{ + struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu); + + rdssp->sched_qs++; +} #define rcu_bh_qsctr_inc(cpu) #define call_rcu_bh(head, rcu) call_rcu(head, rcu) +/** + * call_rcu_sched - Queue RCU callback for invocation after sched grace period. + * @head: structure to be used for queueing the RCU updates. + * @func: actual update function to be invoked after the grace period + * + * The update function will be invoked some time after a full + * synchronize_sched()-style grace period elapses, in other words after + * all currently executing preempt-disabled sections of code (including + * hardirq handlers, NMI handlers, and local_irq_save() blocks) have + * completed. + */ +extern void call_rcu_sched(struct rcu_head *head, + void (*func)(struct rcu_head *head)); + extern void __rcu_read_lock(void) __acquires(RCU); extern void __rcu_read_unlock(void) __releases(RCU); extern int rcu_pending(int cpu); @@ -55,6 +84,7 @@ extern int rcu_needs_cpu(int cpu); extern void __synchronize_sched(void); extern void __rcu_init(void); +extern void rcu_init_sched(void); extern void rcu_check_callbacks(int cpu, int user); extern void rcu_restart_cpu(int cpu); extern long rcu_batches_completed(void); @@ -81,20 +111,20 @@ extern struct rcupreempt_trace *rcupreempt_trace_cpu(int cpu); struct softirq_action; #ifdef CONFIG_NO_HZ -DECLARE_PER_CPU(long, dynticks_progress_counter); +DECLARE_PER_CPU(struct rcu_dyntick_sched, rcu_dyntick_sched); static inline void rcu_enter_nohz(void) { smp_mb(); /* CPUs seeing ++ must see prior RCU read-side crit sects */ - __get_cpu_var(dynticks_progress_counter)++; - WARN_ON(__get_cpu_var(dynticks_progress_counter) & 0x1); + __get_cpu_var(rcu_dyntick_sched).dynticks++; + WARN_ON(__get_cpu_var(rcu_dyntick_sched).dynticks & 0x1); } static inline void rcu_exit_nohz(void) { - __get_cpu_var(dynticks_progress_counter)++; smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */ - WARN_ON(!(__get_cpu_var(dynticks_progress_counter) & 0x1)); + __get_cpu_var(rcu_dyntick_sched).dynticks++; + WARN_ON(!(__get_cpu_var(rcu_dyntick_sched).dynticks & 0x1)); } #else /* CONFIG_NO_HZ */ -- cgit v1.2.3 From 70f12f848d3e981479b4f6f751e73c14f7c13e5b Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 12 May 2008 21:21:05 +0200 Subject: rcu: add rcu_barrier_sched() and rcu_barrier_bh() Add rcu_barrier_sched() and rcu_barrier_bh(). With these in place, rcutorture no longer gives the occasional oops when repeatedly starting and stopping torturing rcu_bh. Also adds the API needed to flush out pre-existing call_rcu_sched() callbacks. Signed-off-by: Paul E. McKenney Signed-off-by: Mathieu Desnoyers Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/rcupdate.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 411969cb5243..e8b4039cfb2f 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -246,6 +246,8 @@ extern void call_rcu_bh(struct rcu_head *head, /* Exported common interfaces */ extern void synchronize_rcu(void); extern void rcu_barrier(void); +extern void rcu_barrier_bh(void); +extern void rcu_barrier_sched(void); /* Internal to kernel */ extern void rcu_init(void); -- cgit v1.2.3 From 82524746c27fa418c250a56dd7606b9d3fc79826 Mon Sep 17 00:00:00 2001 From: Franck Bui-Huu Date: Mon, 12 May 2008 21:21:05 +0200 Subject: rcu: split list.h and move rcu-protected lists into rculist.h Move rcu-protected lists from list.h into a new header file rculist.h. This is done because list are a very used primitive structure all over the kernel and it's currently impossible to include other header files in this list.h without creating some circular dependencies. For example, list.h implements rcu-protected list and uses rcu_dereference() without including rcupdate.h. It actually compiles because users of rcu_dereference() are macros. Others RCU functions could be used too but aren't probably because of this. Therefore this patch creates rculist.h which includes rcupdates without to many changes/troubles. Signed-off-by: Franck Bui-Huu Acked-by: Paul E. McKenney Acked-by: Josh Triplett Signed-off-by: Andrew Morton Signed-off-by: Ingo Molnar --- include/linux/dcache.h | 1 + include/linux/list.h | 367 -------------------------------------------- include/linux/rculist.h | 396 ++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 397 insertions(+), 367 deletions(-) create mode 100644 include/linux/rculist.h (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 2a6639407c80..1f5cebf10a23 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -3,6 +3,7 @@ #include #include +#include #include #include #include diff --git a/include/linux/list.h b/include/linux/list.h index 08cf4f651889..139ec41d9c2e 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -84,65 +84,6 @@ static inline void list_add_tail(struct list_head *new, struct list_head *head) __list_add(new, head->prev, head); } -/* - * Insert a new entry between two known consecutive entries. - * - * This is only for internal list manipulation where we know - * the prev/next entries already! - */ -static inline void __list_add_rcu(struct list_head * new, - struct list_head * prev, struct list_head * next) -{ - new->next = next; - new->prev = prev; - smp_wmb(); - next->prev = new; - prev->next = new; -} - -/** - * list_add_rcu - add a new entry to rcu-protected list - * @new: new entry to be added - * @head: list head to add it after - * - * Insert a new entry after the specified head. - * This is good for implementing stacks. - * - * The caller must take whatever precautions are necessary - * (such as holding appropriate locks) to avoid racing - * with another list-mutation primitive, such as list_add_rcu() - * or list_del_rcu(), running on this same list. - * However, it is perfectly legal to run concurrently with - * the _rcu list-traversal primitives, such as - * list_for_each_entry_rcu(). - */ -static inline void list_add_rcu(struct list_head *new, struct list_head *head) -{ - __list_add_rcu(new, head, head->next); -} - -/** - * list_add_tail_rcu - add a new entry to rcu-protected list - * @new: new entry to be added - * @head: list head to add it before - * - * Insert a new entry before the specified head. - * This is useful for implementing queues. - * - * The caller must take whatever precautions are necessary - * (such as holding appropriate locks) to avoid racing - * with another list-mutation primitive, such as list_add_tail_rcu() - * or list_del_rcu(), running on this same list. - * However, it is perfectly legal to run concurrently with - * the _rcu list-traversal primitives, such as - * list_for_each_entry_rcu(). - */ -static inline void list_add_tail_rcu(struct list_head *new, - struct list_head *head) -{ - __list_add_rcu(new, head->prev, head); -} - /* * Delete a list entry by making the prev/next entries * point to each other. @@ -173,36 +114,6 @@ static inline void list_del(struct list_head *entry) extern void list_del(struct list_head *entry); #endif -/** - * list_del_rcu - deletes entry from list without re-initialization - * @entry: the element to delete from the list. - * - * Note: list_empty() on entry does not return true after this, - * the entry is in an undefined state. It is useful for RCU based - * lockfree traversal. - * - * In particular, it means that we can not poison the forward - * pointers that may still be used for walking the list. - * - * The caller must take whatever precautions are necessary - * (such as holding appropriate locks) to avoid racing - * with another list-mutation primitive, such as list_del_rcu() - * or list_add_rcu(), running on this same list. - * However, it is perfectly legal to run concurrently with - * the _rcu list-traversal primitives, such as - * list_for_each_entry_rcu(). - * - * Note that the caller is not permitted to immediately free - * the newly deleted entry. Instead, either synchronize_rcu() - * or call_rcu() must be used to defer freeing until an RCU - * grace period has elapsed. - */ -static inline void list_del_rcu(struct list_head *entry) -{ - __list_del(entry->prev, entry->next); - entry->prev = LIST_POISON2; -} - /** * list_replace - replace old entry by new one * @old : the element to be replaced @@ -226,25 +137,6 @@ static inline void list_replace_init(struct list_head *old, INIT_LIST_HEAD(old); } -/** - * list_replace_rcu - replace old entry by new one - * @old : the element to be replaced - * @new : the new element to insert - * - * The @old entry will be replaced with the @new entry atomically. - * Note: @old should not be empty. - */ -static inline void list_replace_rcu(struct list_head *old, - struct list_head *new) -{ - new->next = old->next; - new->prev = old->prev; - smp_wmb(); - new->next->prev = new; - new->prev->next = new; - old->prev = LIST_POISON2; -} - /** * list_del_init - deletes entry from list and reinitialize it. * @entry: the element to delete from the list. @@ -368,62 +260,6 @@ static inline void list_splice_init(struct list_head *list, } } -/** - * list_splice_init_rcu - splice an RCU-protected list into an existing list. - * @list: the RCU-protected list to splice - * @head: the place in the list to splice the first list into - * @sync: function to sync: synchronize_rcu(), synchronize_sched(), ... - * - * @head can be RCU-read traversed concurrently with this function. - * - * Note that this function blocks. - * - * Important note: the caller must take whatever action is necessary to - * prevent any other updates to @head. In principle, it is possible - * to modify the list as soon as sync() begins execution. - * If this sort of thing becomes necessary, an alternative version - * based on call_rcu() could be created. But only if -really- - * needed -- there is no shortage of RCU API members. - */ -static inline void list_splice_init_rcu(struct list_head *list, - struct list_head *head, - void (*sync)(void)) -{ - struct list_head *first = list->next; - struct list_head *last = list->prev; - struct list_head *at = head->next; - - if (list_empty(head)) - return; - - /* "first" and "last" tracking list, so initialize it. */ - - INIT_LIST_HEAD(list); - - /* - * At this point, the list body still points to the source list. - * Wait for any readers to finish using the list before splicing - * the list body into the new list. Any new readers will see - * an empty list. - */ - - sync(); - - /* - * Readers are finished with the source list, so perform splice. - * The order is important if the new list is global and accessible - * to concurrent RCU readers. Note that RCU readers are not - * permitted to traverse the prev pointers without excluding - * this function. - */ - - last->next = at; - smp_wmb(); - head->next = first; - first->prev = head; - at->prev = last; -} - /** * list_entry - get the struct for this entry * @ptr: the &struct list_head pointer. @@ -629,57 +465,6 @@ static inline void list_splice_init_rcu(struct list_head *list, &pos->member != (head); \ pos = n, n = list_entry(n->member.prev, typeof(*n), member)) -/** - * list_for_each_rcu - iterate over an rcu-protected list - * @pos: the &struct list_head to use as a loop cursor. - * @head: the head for your list. - * - * This list-traversal primitive may safely run concurrently with - * the _rcu list-mutation primitives such as list_add_rcu() - * as long as the traversal is guarded by rcu_read_lock(). - */ -#define list_for_each_rcu(pos, head) \ - for (pos = rcu_dereference((head)->next); \ - prefetch(pos->next), pos != (head); \ - pos = rcu_dereference(pos->next)) - -#define __list_for_each_rcu(pos, head) \ - for (pos = rcu_dereference((head)->next); \ - pos != (head); \ - pos = rcu_dereference(pos->next)) - -/** - * list_for_each_entry_rcu - iterate over rcu list of given type - * @pos: the type * to use as a loop cursor. - * @head: the head for your list. - * @member: the name of the list_struct within the struct. - * - * This list-traversal primitive may safely run concurrently with - * the _rcu list-mutation primitives such as list_add_rcu() - * as long as the traversal is guarded by rcu_read_lock(). - */ -#define list_for_each_entry_rcu(pos, head, member) \ - for (pos = list_entry(rcu_dereference((head)->next), typeof(*pos), member); \ - prefetch(pos->member.next), &pos->member != (head); \ - pos = list_entry(rcu_dereference(pos->member.next), typeof(*pos), member)) - - -/** - * list_for_each_continue_rcu - * @pos: the &struct list_head to use as a loop cursor. - * @head: the head for your list. - * - * Iterate over an rcu-protected list, continuing after current point. - * - * This list-traversal primitive may safely run concurrently with - * the _rcu list-mutation primitives such as list_add_rcu() - * as long as the traversal is guarded by rcu_read_lock(). - */ -#define list_for_each_continue_rcu(pos, head) \ - for ((pos) = rcu_dereference((pos)->next); \ - prefetch((pos)->next), (pos) != (head); \ - (pos) = rcu_dereference((pos)->next)) - /* * Double linked lists with a single pointer list head. * Mostly useful for hash tables where the two pointer list head is @@ -730,31 +515,6 @@ static inline void hlist_del(struct hlist_node *n) n->pprev = LIST_POISON2; } -/** - * hlist_del_rcu - deletes entry from hash list without re-initialization - * @n: the element to delete from the hash list. - * - * Note: list_unhashed() on entry does not return true after this, - * the entry is in an undefined state. It is useful for RCU based - * lockfree traversal. - * - * In particular, it means that we can not poison the forward - * pointers that may still be used for walking the hash list. - * - * The caller must take whatever precautions are necessary - * (such as holding appropriate locks) to avoid racing - * with another list-mutation primitive, such as hlist_add_head_rcu() - * or hlist_del_rcu(), running on this same list. - * However, it is perfectly legal to run concurrently with - * the _rcu list-traversal primitives, such as - * hlist_for_each_entry(). - */ -static inline void hlist_del_rcu(struct hlist_node *n) -{ - __hlist_del(n); - n->pprev = LIST_POISON2; -} - static inline void hlist_del_init(struct hlist_node *n) { if (!hlist_unhashed(n)) { @@ -763,27 +523,6 @@ static inline void hlist_del_init(struct hlist_node *n) } } -/** - * hlist_replace_rcu - replace old entry by new one - * @old : the element to be replaced - * @new : the new element to insert - * - * The @old entry will be replaced with the @new entry atomically. - */ -static inline void hlist_replace_rcu(struct hlist_node *old, - struct hlist_node *new) -{ - struct hlist_node *next = old->next; - - new->next = next; - new->pprev = old->pprev; - smp_wmb(); - if (next) - new->next->pprev = &new->next; - *new->pprev = new; - old->pprev = LIST_POISON2; -} - static inline void hlist_add_head(struct hlist_node *n, struct hlist_head *h) { struct hlist_node *first = h->first; @@ -794,38 +533,6 @@ static inline void hlist_add_head(struct hlist_node *n, struct hlist_head *h) n->pprev = &h->first; } - -/** - * hlist_add_head_rcu - * @n: the element to add to the hash list. - * @h: the list to add to. - * - * Description: - * Adds the specified element to the specified hlist, - * while permitting racing traversals. - * - * The caller must take whatever precautions are necessary - * (such as holding appropriate locks) to avoid racing - * with another list-mutation primitive, such as hlist_add_head_rcu() - * or hlist_del_rcu(), running on this same list. - * However, it is perfectly legal to run concurrently with - * the _rcu list-traversal primitives, such as - * hlist_for_each_entry_rcu(), used to prevent memory-consistency - * problems on Alpha CPUs. Regardless of the type of CPU, the - * list-traversal primitive must be guarded by rcu_read_lock(). - */ -static inline void hlist_add_head_rcu(struct hlist_node *n, - struct hlist_head *h) -{ - struct hlist_node *first = h->first; - n->next = first; - n->pprev = &h->first; - smp_wmb(); - if (first) - first->pprev = &n->next; - h->first = n; -} - /* next must be != NULL */ static inline void hlist_add_before(struct hlist_node *n, struct hlist_node *next) @@ -847,63 +554,6 @@ static inline void hlist_add_after(struct hlist_node *n, next->next->pprev = &next->next; } -/** - * hlist_add_before_rcu - * @n: the new element to add to the hash list. - * @next: the existing element to add the new element before. - * - * Description: - * Adds the specified element to the specified hlist - * before the specified node while permitting racing traversals. - * - * The caller must take whatever precautions are necessary - * (such as holding appropriate locks) to avoid racing - * with another list-mutation primitive, such as hlist_add_head_rcu() - * or hlist_del_rcu(), running on this same list. - * However, it is perfectly legal to run concurrently with - * the _rcu list-traversal primitives, such as - * hlist_for_each_entry_rcu(), used to prevent memory-consistency - * problems on Alpha CPUs. - */ -static inline void hlist_add_before_rcu(struct hlist_node *n, - struct hlist_node *next) -{ - n->pprev = next->pprev; - n->next = next; - smp_wmb(); - next->pprev = &n->next; - *(n->pprev) = n; -} - -/** - * hlist_add_after_rcu - * @prev: the existing element to add the new element after. - * @n: the new element to add to the hash list. - * - * Description: - * Adds the specified element to the specified hlist - * after the specified node while permitting racing traversals. - * - * The caller must take whatever precautions are necessary - * (such as holding appropriate locks) to avoid racing - * with another list-mutation primitive, such as hlist_add_head_rcu() - * or hlist_del_rcu(), running on this same list. - * However, it is perfectly legal to run concurrently with - * the _rcu list-traversal primitives, such as - * hlist_for_each_entry_rcu(), used to prevent memory-consistency - * problems on Alpha CPUs. - */ -static inline void hlist_add_after_rcu(struct hlist_node *prev, - struct hlist_node *n) -{ - n->next = prev->next; - n->pprev = &prev->next; - smp_wmb(); - prev->next = n; - if (n->next) - n->next->pprev = &n->next; -} - #define hlist_entry(ptr, type, member) container_of(ptr,type,member) #define hlist_for_each(pos, head) \ @@ -964,21 +614,4 @@ static inline void hlist_add_after_rcu(struct hlist_node *prev, ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1;}); \ pos = n) -/** - * hlist_for_each_entry_rcu - iterate over rcu list of given type - * @tpos: the type * to use as a loop cursor. - * @pos: the &struct hlist_node to use as a loop cursor. - * @head: the head for your list. - * @member: the name of the hlist_node within the struct. - * - * This list-traversal primitive may safely run concurrently with - * the _rcu list-mutation primitives such as hlist_add_head_rcu() - * as long as the traversal is guarded by rcu_read_lock(). - */ -#define hlist_for_each_entry_rcu(tpos, pos, head, member) \ - for (pos = rcu_dereference((head)->first); \ - pos && ({ prefetch(pos->next); 1;}) && \ - ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1;}); \ - pos = rcu_dereference(pos->next)) - #endif diff --git a/include/linux/rculist.h b/include/linux/rculist.h new file mode 100644 index 000000000000..aa9b3eb15683 --- /dev/null +++ b/include/linux/rculist.h @@ -0,0 +1,396 @@ +#ifndef _LINUX_RCULIST_H +#define _LINUX_RCULIST_H + +#ifdef __KERNEL__ + +/* + * RCU-protected list version + */ +#include + +/* + * Insert a new entry between two known consecutive entries. + * + * This is only for internal list manipulation where we know + * the prev/next entries already! + */ +static inline void __list_add_rcu(struct list_head *new, + struct list_head *prev, struct list_head *next) +{ + new->next = next; + new->prev = prev; + smp_wmb(); + next->prev = new; + prev->next = new; +} + +/** + * list_add_rcu - add a new entry to rcu-protected list + * @new: new entry to be added + * @head: list head to add it after + * + * Insert a new entry after the specified head. + * This is good for implementing stacks. + * + * The caller must take whatever precautions are necessary + * (such as holding appropriate locks) to avoid racing + * with another list-mutation primitive, such as list_add_rcu() + * or list_del_rcu(), running on this same list. + * However, it is perfectly legal to run concurrently with + * the _rcu list-traversal primitives, such as + * list_for_each_entry_rcu(). + */ +static inline void list_add_rcu(struct list_head *new, struct list_head *head) +{ + __list_add_rcu(new, head, head->next); +} + +/** + * list_add_tail_rcu - add a new entry to rcu-protected list + * @new: new entry to be added + * @head: list head to add it before + * + * Insert a new entry before the specified head. + * This is useful for implementing queues. + * + * The caller must take whatever precautions are necessary + * (such as holding appropriate locks) to avoid racing + * with another list-mutation primitive, such as list_add_tail_rcu() + * or list_del_rcu(), running on this same list. + * However, it is perfectly legal to run concurrently with + * the _rcu list-traversal primitives, such as + * list_for_each_entry_rcu(). + */ +static inline void list_add_tail_rcu(struct list_head *new, + struct list_head *head) +{ + __list_add_rcu(new, head->prev, head); +} + +/** + * list_del_rcu - deletes entry from list without re-initialization + * @entry: the element to delete from the list. + * + * Note: list_empty() on entry does not return true after this, + * the entry is in an undefined state. It is useful for RCU based + * lockfree traversal. + * + * In particular, it means that we can not poison the forward + * pointers that may still be used for walking the list. + * + * The caller must take whatever precautions are necessary + * (such as holding appropriate locks) to avoid racing + * with another list-mutation primitive, such as list_del_rcu() + * or list_add_rcu(), running on this same list. + * However, it is perfectly legal to run concurrently with + * the _rcu list-traversal primitives, such as + * list_for_each_entry_rcu(). + * + * Note that the caller is not permitted to immediately free + * the newly deleted entry. Instead, either synchronize_rcu() + * or call_rcu() must be used to defer freeing until an RCU + * grace period has elapsed. + */ +static inline void list_del_rcu(struct list_head *entry) +{ + __list_del(entry->prev, entry->next); + entry->prev = LIST_POISON2; +} + +/** + * list_replace_rcu - replace old entry by new one + * @old : the element to be replaced + * @new : the new element to insert + * + * The @old entry will be replaced with the @new entry atomically. + * Note: @old should not be empty. + */ +static inline void list_replace_rcu(struct list_head *old, + struct list_head *new) +{ + new->next = old->next; + new->prev = old->prev; + smp_wmb(); + new->next->prev = new; + new->prev->next = new; + old->prev = LIST_POISON2; +} + +/** + * list_splice_init_rcu - splice an RCU-protected list into an existing list. + * @list: the RCU-protected list to splice + * @head: the place in the list to splice the first list into + * @sync: function to sync: synchronize_rcu(), synchronize_sched(), ... + * + * @head can be RCU-read traversed concurrently with this function. + * + * Note that this function blocks. + * + * Important note: the caller must take whatever action is necessary to + * prevent any other updates to @head. In principle, it is possible + * to modify the list as soon as sync() begins execution. + * If this sort of thing becomes necessary, an alternative version + * based on call_rcu() could be created. But only if -really- + * needed -- there is no shortage of RCU API members. + */ +static inline void list_splice_init_rcu(struct list_head *list, + struct list_head *head, + void (*sync)(void)) +{ + struct list_head *first = list->next; + struct list_head *last = list->prev; + struct list_head *at = head->next; + + if (list_empty(head)) + return; + + /* "first" and "last" tracking list, so initialize it. */ + + INIT_LIST_HEAD(list); + + /* + * At this point, the list body still points to the source list. + * Wait for any readers to finish using the list before splicing + * the list body into the new list. Any new readers will see + * an empty list. + */ + + sync(); + + /* + * Readers are finished with the source list, so perform splice. + * The order is important if the new list is global and accessible + * to concurrent RCU readers. Note that RCU readers are not + * permitted to traverse the prev pointers without excluding + * this function. + */ + + last->next = at; + smp_wmb(); + head->next = first; + first->prev = head; + at->prev = last; +} + +/** + * list_for_each_rcu - iterate over an rcu-protected list + * @pos: the &struct list_head to use as a loop cursor. + * @head: the head for your list. + * + * This list-traversal primitive may safely run concurrently with + * the _rcu list-mutation primitives such as list_add_rcu() + * as long as the traversal is guarded by rcu_read_lock(). + */ +#define list_for_each_rcu(pos, head) \ + for (pos = (head)->next; \ + prefetch(rcu_dereference(pos)->next), pos != (head); \ + pos = pos->next) + +#define __list_for_each_rcu(pos, head) \ + for (pos = (head)->next; \ + rcu_dereference(pos) != (head); \ + pos = pos->next) + +/** + * list_for_each_safe_rcu + * @pos: the &struct list_head to use as a loop cursor. + * @n: another &struct list_head to use as temporary storage + * @head: the head for your list. + * + * Iterate over an rcu-protected list, safe against removal of list entry. + * + * This list-traversal primitive may safely run concurrently with + * the _rcu list-mutation primitives such as list_add_rcu() + * as long as the traversal is guarded by rcu_read_lock(). + */ +#define list_for_each_safe_rcu(pos, n, head) \ + for (pos = (head)->next; \ + n = rcu_dereference(pos)->next, pos != (head); \ + pos = n) + +/** + * list_for_each_entry_rcu - iterate over rcu list of given type + * @pos: the type * to use as a loop cursor. + * @head: the head for your list. + * @member: the name of the list_struct within the struct. + * + * This list-traversal primitive may safely run concurrently with + * the _rcu list-mutation primitives such as list_add_rcu() + * as long as the traversal is guarded by rcu_read_lock(). + */ +#define list_for_each_entry_rcu(pos, head, member) \ + for (pos = list_entry((head)->next, typeof(*pos), member); \ + prefetch(rcu_dereference(pos)->member.next), \ + &pos->member != (head); \ + pos = list_entry(pos->member.next, typeof(*pos), member)) + + +/** + * list_for_each_continue_rcu + * @pos: the &struct list_head to use as a loop cursor. + * @head: the head for your list. + * + * Iterate over an rcu-protected list, continuing after current point. + * + * This list-traversal primitive may safely run concurrently with + * the _rcu list-mutation primitives such as list_add_rcu() + * as long as the traversal is guarded by rcu_read_lock(). + */ +#define list_for_each_continue_rcu(pos, head) \ + for ((pos) = (pos)->next; \ + prefetch(rcu_dereference((pos))->next), (pos) != (head); \ + (pos) = (pos)->next) + +/** + * hlist_del_rcu - deletes entry from hash list without re-initialization + * @n: the element to delete from the hash list. + * + * Note: list_unhashed() on entry does not return true after this, + * the entry is in an undefined state. It is useful for RCU based + * lockfree traversal. + * + * In particular, it means that we can not poison the forward + * pointers that may still be used for walking the hash list. + * + * The caller must take whatever precautions are necessary + * (such as holding appropriate locks) to avoid racing + * with another list-mutation primitive, such as hlist_add_head_rcu() + * or hlist_del_rcu(), running on this same list. + * However, it is perfectly legal to run concurrently with + * the _rcu list-traversal primitives, such as + * hlist_for_each_entry(). + */ +static inline void hlist_del_rcu(struct hlist_node *n) +{ + __hlist_del(n); + n->pprev = LIST_POISON2; +} + +/** + * hlist_replace_rcu - replace old entry by new one + * @old : the element to be replaced + * @new : the new element to insert + * + * The @old entry will be replaced with the @new entry atomically. + */ +static inline void hlist_replace_rcu(struct hlist_node *old, + struct hlist_node *new) +{ + struct hlist_node *next = old->next; + + new->next = next; + new->pprev = old->pprev; + smp_wmb(); + if (next) + new->next->pprev = &new->next; + *new->pprev = new; + old->pprev = LIST_POISON2; +} + +/** + * hlist_add_head_rcu + * @n: the element to add to the hash list. + * @h: the list to add to. + * + * Description: + * Adds the specified element to the specified hlist, + * while permitting racing traversals. + * + * The caller must take whatever precautions are necessary + * (such as holding appropriate locks) to avoid racing + * with another list-mutation primitive, such as hlist_add_head_rcu() + * or hlist_del_rcu(), running on this same list. + * However, it is perfectly legal to run concurrently with + * the _rcu list-traversal primitives, such as + * hlist_for_each_entry_rcu(), used to prevent memory-consistency + * problems on Alpha CPUs. Regardless of the type of CPU, the + * list-traversal primitive must be guarded by rcu_read_lock(). + */ +static inline void hlist_add_head_rcu(struct hlist_node *n, + struct hlist_head *h) +{ + struct hlist_node *first = h->first; + n->next = first; + n->pprev = &h->first; + smp_wmb(); + if (first) + first->pprev = &n->next; + h->first = n; +} + +/** + * hlist_add_before_rcu + * @n: the new element to add to the hash list. + * @next: the existing element to add the new element before. + * + * Description: + * Adds the specified element to the specified hlist + * before the specified node while permitting racing traversals. + * + * The caller must take whatever precautions are necessary + * (such as holding appropriate locks) to avoid racing + * with another list-mutation primitive, such as hlist_add_head_rcu() + * or hlist_del_rcu(), running on this same list. + * However, it is perfectly legal to run concurrently with + * the _rcu list-traversal primitives, such as + * hlist_for_each_entry_rcu(), used to prevent memory-consistency + * problems on Alpha CPUs. + */ +static inline void hlist_add_before_rcu(struct hlist_node *n, + struct hlist_node *next) +{ + n->pprev = next->pprev; + n->next = next; + smp_wmb(); + next->pprev = &n->next; + *(n->pprev) = n; +} + +/** + * hlist_add_after_rcu + * @prev: the existing element to add the new element after. + * @n: the new element to add to the hash list. + * + * Description: + * Adds the specified element to the specified hlist + * after the specified node while permitting racing traversals. + * + * The caller must take whatever precautions are necessary + * (such as holding appropriate locks) to avoid racing + * with another list-mutation primitive, such as hlist_add_head_rcu() + * or hlist_del_rcu(), running on this same list. + * However, it is perfectly legal to run concurrently with + * the _rcu list-traversal primitives, such as + * hlist_for_each_entry_rcu(), used to prevent memory-consistency + * problems on Alpha CPUs. + */ +static inline void hlist_add_after_rcu(struct hlist_node *prev, + struct hlist_node *n) +{ + n->next = prev->next; + n->pprev = &prev->next; + smp_wmb(); + prev->next = n; + if (n->next) + n->next->pprev = &n->next; +} + +/** + * hlist_for_each_entry_rcu - iterate over rcu list of given type + * @tpos: the type * to use as a loop cursor. + * @pos: the &struct hlist_node to use as a loop cursor. + * @head: the head for your list. + * @member: the name of the hlist_node within the struct. + * + * This list-traversal primitive may safely run concurrently with + * the _rcu list-mutation primitives such as hlist_add_head_rcu() + * as long as the traversal is guarded by rcu_read_lock(). + */ +#define hlist_for_each_entry_rcu(tpos, pos, head, member) \ + for (pos = (head)->first; \ + rcu_dereference(pos) && ({ prefetch(pos->next); 1; }) && \ + ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1; }); \ + pos = pos->next) + +#endif /* __KERNEL__ */ +#endif -- cgit v1.2.3 From 10aa9d2cf9878757b003023d33ff90a37aa3044b Mon Sep 17 00:00:00 2001 From: Franck Bui-Huu Date: Mon, 12 May 2008 21:21:06 +0200 Subject: rculist.h: use the rcu API Make almost all list mutation primitives use rcu_assign_pointer(). The main point of this being readability improvement. Signed-off-by: Franck Bui-Huu Cc: "Paul E. McKenney" Cc: Josh Triplett Signed-off-by: Andrew Morton Signed-off-by: Ingo Molnar --- include/linux/rculist.h | 23 +++++++++-------------- 1 file changed, 9 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rculist.h b/include/linux/rculist.h index aa9b3eb15683..8d2c81fccfe5 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -7,6 +7,7 @@ * RCU-protected list version */ #include +#include /* * Insert a new entry between two known consecutive entries. @@ -19,9 +20,8 @@ static inline void __list_add_rcu(struct list_head *new, { new->next = next; new->prev = prev; - smp_wmb(); + rcu_assign_pointer(prev->next, new); next->prev = new; - prev->next = new; } /** @@ -110,9 +110,8 @@ static inline void list_replace_rcu(struct list_head *old, { new->next = old->next; new->prev = old->prev; - smp_wmb(); + rcu_assign_pointer(new->prev->next, new); new->next->prev = new; - new->prev->next = new; old->prev = LIST_POISON2; } @@ -166,8 +165,7 @@ static inline void list_splice_init_rcu(struct list_head *list, */ last->next = at; - smp_wmb(); - head->next = first; + rcu_assign_pointer(head->next, first); first->prev = head; at->prev = last; } @@ -280,10 +278,9 @@ static inline void hlist_replace_rcu(struct hlist_node *old, new->next = next; new->pprev = old->pprev; - smp_wmb(); + rcu_assign_pointer(*new->pprev, new); if (next) new->next->pprev = &new->next; - *new->pprev = new; old->pprev = LIST_POISON2; } @@ -310,12 +307,12 @@ static inline void hlist_add_head_rcu(struct hlist_node *n, struct hlist_head *h) { struct hlist_node *first = h->first; + n->next = first; n->pprev = &h->first; - smp_wmb(); + rcu_assign_pointer(h->first, n); if (first) first->pprev = &n->next; - h->first = n; } /** @@ -341,9 +338,8 @@ static inline void hlist_add_before_rcu(struct hlist_node *n, { n->pprev = next->pprev; n->next = next; - smp_wmb(); + rcu_assign_pointer(*(n->pprev), n); next->pprev = &n->next; - *(n->pprev) = n; } /** @@ -369,8 +365,7 @@ static inline void hlist_add_after_rcu(struct hlist_node *prev, { n->next = prev->next; n->pprev = &prev->next; - smp_wmb(); - prev->next = n; + rcu_assign_pointer(prev->next, n); if (n->next) n->next->pprev = &n->next; } -- cgit v1.2.3 From 78b0e0e9b27b62c4b22f05a147f7a80fa58b1ae3 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 12 May 2008 21:21:06 +0200 Subject: RCU, rculist.h: fix list iterators RCU list iterators: should prefetch ever be optimised out with no side-effects, the current version will lose the barrier completely. Pointed-out-by: Linus Torvalds Signed-off-by: Paul E. McKenney Signed-off-by: Ingo Molnar --- include/linux/rculist.h | 48 +++++++++++++++--------------------------------- 1 file changed, 15 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rculist.h b/include/linux/rculist.h index 8d2c81fccfe5..b0f39be08b6c 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -180,31 +180,14 @@ static inline void list_splice_init_rcu(struct list_head *list, * as long as the traversal is guarded by rcu_read_lock(). */ #define list_for_each_rcu(pos, head) \ - for (pos = (head)->next; \ - prefetch(rcu_dereference(pos)->next), pos != (head); \ - pos = pos->next) + for (pos = rcu_dereference((head)->next); \ + prefetch(pos->next), pos != (head); \ + pos = rcu_dereference(pos->next)) #define __list_for_each_rcu(pos, head) \ - for (pos = (head)->next; \ - rcu_dereference(pos) != (head); \ - pos = pos->next) - -/** - * list_for_each_safe_rcu - * @pos: the &struct list_head to use as a loop cursor. - * @n: another &struct list_head to use as temporary storage - * @head: the head for your list. - * - * Iterate over an rcu-protected list, safe against removal of list entry. - * - * This list-traversal primitive may safely run concurrently with - * the _rcu list-mutation primitives such as list_add_rcu() - * as long as the traversal is guarded by rcu_read_lock(). - */ -#define list_for_each_safe_rcu(pos, n, head) \ - for (pos = (head)->next; \ - n = rcu_dereference(pos)->next, pos != (head); \ - pos = n) + for (pos = rcu_dereference((head)->next); \ + pos != (head); \ + pos = rcu_dereference(pos->next)) /** * list_for_each_entry_rcu - iterate over rcu list of given type @@ -217,10 +200,9 @@ static inline void list_splice_init_rcu(struct list_head *list, * as long as the traversal is guarded by rcu_read_lock(). */ #define list_for_each_entry_rcu(pos, head, member) \ - for (pos = list_entry((head)->next, typeof(*pos), member); \ - prefetch(rcu_dereference(pos)->member.next), \ - &pos->member != (head); \ - pos = list_entry(pos->member.next, typeof(*pos), member)) + for (pos = list_entry(rcu_dereference((head)->next), typeof(*pos), member); \ + prefetch(pos->member.next), &pos->member != (head); \ + pos = list_entry(rcu_dereference(pos->member.next), typeof(*pos), member)) /** @@ -235,9 +217,9 @@ static inline void list_splice_init_rcu(struct list_head *list, * as long as the traversal is guarded by rcu_read_lock(). */ #define list_for_each_continue_rcu(pos, head) \ - for ((pos) = (pos)->next; \ - prefetch(rcu_dereference((pos))->next), (pos) != (head); \ - (pos) = (pos)->next) + for ((pos) = rcu_dereference((pos)->next); \ + prefetch((pos)->next), (pos) != (head); \ + (pos) = rcu_dereference((pos)->next)) /** * hlist_del_rcu - deletes entry from hash list without re-initialization @@ -382,10 +364,10 @@ static inline void hlist_add_after_rcu(struct hlist_node *prev, * as long as the traversal is guarded by rcu_read_lock(). */ #define hlist_for_each_entry_rcu(tpos, pos, head, member) \ - for (pos = (head)->first; \ - rcu_dereference(pos) && ({ prefetch(pos->next); 1; }) && \ + for (pos = rcu_dereference((head)->first); \ + pos && ({ prefetch(pos->next); 1; }) && \ ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1; }); \ - pos = pos->next) + pos = rcu_dereference(pos->next)) #endif /* __KERNEL__ */ #endif -- cgit v1.2.3 From 18404756765c713a0be4eb1082920c04822ce588 Mon Sep 17 00:00:00 2001 From: Max Krasnyansky Date: Thu, 29 May 2008 11:02:52 -0700 Subject: genirq: Expose default irq affinity mask (take 3) Current IRQ affinity interface does not provide a way to set affinity for the IRQs that will be allocated/activated in the future. This patch creates /proc/irq/default_smp_affinity that lets users set default affinity mask for the newly allocated IRQs. Changing the default does not affect affinity masks for the currently active IRQs, they have to be changed explicitly. Updated based on Paul J's comments and added some more documentation. Signed-off-by: Max Krasnyansky Cc: pj@sgi.com Cc: a.p.zijlstra@chello.nl Cc: tglx@linutronix.de Cc: rdunlap@xenotime.net Cc: mingo@elte.hu Signed-off-by: Thomas Gleixner --- include/linux/interrupt.h | 5 +++++ include/linux/irq.h | 9 --------- 2 files changed, 5 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index f1fc7470d26c..043400f3d458 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -104,8 +104,11 @@ extern void enable_irq(unsigned int irq); #if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_HARDIRQS) +extern cpumask_t irq_default_affinity; + extern int irq_set_affinity(unsigned int irq, cpumask_t cpumask); extern int irq_can_set_affinity(unsigned int irq); +extern int irq_select_affinity(unsigned int irq); #else /* CONFIG_SMP */ @@ -119,6 +122,8 @@ static inline int irq_can_set_affinity(unsigned int irq) return 0; } +static inline int irq_select_affinity(unsigned int irq) { return 0; } + #endif /* CONFIG_SMP && CONFIG_GENERIC_HARDIRQS */ #ifdef CONFIG_GENERIC_HARDIRQS diff --git a/include/linux/irq.h b/include/linux/irq.h index 552e0ec269c9..8ccb462ea42c 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -244,15 +244,6 @@ static inline void set_balance_irq_affinity(unsigned int irq, cpumask_t mask) } #endif -#ifdef CONFIG_AUTO_IRQ_AFFINITY -extern int select_smp_affinity(unsigned int irq); -#else -static inline int select_smp_affinity(unsigned int irq) -{ - return 1; -} -#endif - extern int no_irq_affinity; static inline int irq_balancing_disabled(unsigned int irq) -- cgit v1.2.3 From c50cbb05a05cf1f9ca3592272eff053c847727d8 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Wed, 4 Jun 2008 21:47:29 -0700 Subject: cpu topology: always define CPU topology information This can result in an empty topology directory in sysfs, and requires in-kernel users to protect all uses with #ifdef - see . The documentation of CPU topology specifies what the defaults should be if only partial information is available from the hardware. So we can provide these defaults as a fallback. This patch: - Adds default definitions of the 4 topology macros to - Changes drivers/base/topology.c to use the topology macros unconditionally and to cope with definitions that aren't lvalues - Updates documentation accordingly [ From: Andrew Morton - fold now-duplicated code - fix layout ] Signed-off-by: Ben Hutchings Cc: Vegard Nossum Cc: Nick Piggin Cc: Chandra Seetharaman Cc: Suresh Siddha Cc: Mike Travis Cc: Christoph Lameter Cc: John Hawkes Cc: Zhang, Yanmin Signed-off-by: Andrew Morton Signed-off-by: Ingo Molnar --- include/linux/topology.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/topology.h b/include/linux/topology.h index 24f3d2282e11..2158fc0d5a56 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -179,4 +179,17 @@ void arch_update_cpu_topology(void); #endif #endif /* CONFIG_NUMA */ +#ifndef topology_physical_package_id +#define topology_physical_package_id(cpu) ((void)(cpu), -1) +#endif +#ifndef topology_core_id +#define topology_core_id(cpu) ((void)(cpu), 0) +#endif +#ifndef topology_thread_siblings +#define topology_thread_siblings(cpu) cpumask_of_cpu(cpu) +#endif +#ifndef topology_core_siblings +#define topology_core_siblings(cpu) cpumask_of_cpu(cpu) +#endif + #endif /* _LINUX_TOPOLOGY_H */ -- cgit v1.2.3 From 3d4422332711ef48ef0f132f1fcbfcbd56c7f3d1 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 26 Jun 2008 11:21:34 +0200 Subject: Add generic helpers for arch IPI function calls This adds kernel/smp.c which contains helpers for IPI function calls. In addition to supporting the existing smp_call_function() in a more efficient manner, it also adds a more scalable variant called smp_call_function_single() for calling a given function on a single CPU only. The core of this is based on the x86-64 patch from Nick Piggin, lots of changes since then. "Alan D. Brunelle" has contributed lots of fixes and suggestions as well. Also thanks to Paul E. McKenney for reviewing RCU usage and getting rid of the data allocation fallback deadlock. Acked-by: Ingo Molnar Reviewed-by: Paul E. McKenney Signed-off-by: Jens Axboe --- include/linux/smp.h | 35 +++++++++++++++++++++++++++++++++-- 1 file changed, 33 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/smp.h b/include/linux/smp.h index 55232ccf9cfd..eac3e062250f 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -7,9 +7,19 @@ */ #include +#include +#include +#include extern void cpu_idle(void); +struct call_single_data { + struct list_head list; + void (*func) (void *info); + void *info; + unsigned int flags; +}; + #ifdef CONFIG_SMP #include @@ -53,9 +63,28 @@ extern void smp_cpus_done(unsigned int max_cpus); * Call a function on all other processors */ int smp_call_function(void(*func)(void *info), void *info, int retry, int wait); - +int smp_call_function_mask(cpumask_t mask, void(*func)(void *info), void *info, + int wait); int smp_call_function_single(int cpuid, void (*func) (void *info), void *info, int retry, int wait); +void __smp_call_function_single(int cpuid, struct call_single_data *data); + +/* + * Generic and arch helpers + */ +#ifdef CONFIG_USE_GENERIC_SMP_HELPERS +void generic_smp_call_function_single_interrupt(void); +void generic_smp_call_function_interrupt(void); +void init_call_single_data(void); +void ipi_call_lock(void); +void ipi_call_unlock(void); +void ipi_call_lock_irq(void); +void ipi_call_unlock_irq(void); +#else +static inline void init_call_single_data(void) +{ +} +#endif /* * Call a function on all processors @@ -112,7 +141,9 @@ static inline void smp_send_reschedule(int cpu) { } }) #define smp_call_function_mask(mask, func, info, wait) \ (up_smp_call_function(func, info)) - +static inline void init_call_single_data(void) +{ +} #endif /* !SMP */ /* -- cgit v1.2.3 From 8691e5a8f691cc2a4fda0651e8d307aaba0e7d68 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 6 Jun 2008 11:18:06 +0200 Subject: smp_call_function: get rid of the unused nonatomic/retry argument It's never used and the comments refer to nonatomic and retry interchangably. So get rid of it. Acked-by: Jeremy Fitzhardinge Signed-off-by: Jens Axboe --- include/linux/smp.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/smp.h b/include/linux/smp.h index eac3e062250f..338cad1b9548 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -62,11 +62,11 @@ extern void smp_cpus_done(unsigned int max_cpus); /* * Call a function on all other processors */ -int smp_call_function(void(*func)(void *info), void *info, int retry, int wait); +int smp_call_function(void(*func)(void *info), void *info, int wait); int smp_call_function_mask(cpumask_t mask, void(*func)(void *info), void *info, int wait); int smp_call_function_single(int cpuid, void (*func) (void *info), void *info, - int retry, int wait); + int wait); void __smp_call_function_single(int cpuid, struct call_single_data *data); /* @@ -119,7 +119,7 @@ static inline int up_smp_call_function(void (*func)(void *), void *info) { return 0; } -#define smp_call_function(func, info, retry, wait) \ +#define smp_call_function(func, info, wait) \ (up_smp_call_function(func, info)) #define on_each_cpu(func,info,retry,wait) \ ({ \ @@ -131,7 +131,7 @@ static inline int up_smp_call_function(void (*func)(void *), void *info) static inline void smp_send_reschedule(int cpu) { } #define num_booting_cpus() 1 #define smp_prepare_boot_cpu() do {} while (0) -#define smp_call_function_single(cpuid, func, info, retry, wait) \ +#define smp_call_function_single(cpuid, func, info, wait) \ ({ \ WARN_ON(cpuid != 0); \ local_irq_disable(); \ -- cgit v1.2.3 From 15c8b6c1aaaf1c4edd67e2f02e4d8e1bd1a51c0d Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 9 May 2008 09:39:44 +0200 Subject: on_each_cpu(): kill unused 'retry' parameter It's not even passed on to smp_call_function() anymore, since that was removed. So kill it. Acked-by: Jeremy Fitzhardinge Reviewed-by: Paul E. McKenney Signed-off-by: Jens Axboe --- include/linux/smp.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/smp.h b/include/linux/smp.h index 338cad1b9548..55261101d09a 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -89,7 +89,7 @@ static inline void init_call_single_data(void) /* * Call a function on all processors */ -int on_each_cpu(void (*func) (void *info), void *info, int retry, int wait); +int on_each_cpu(void (*func) (void *info), void *info, int wait); #define MSG_ALL_BUT_SELF 0x8000 /* Assume <32768 CPU's */ #define MSG_ALL 0x8001 @@ -121,7 +121,7 @@ static inline int up_smp_call_function(void (*func)(void *), void *info) } #define smp_call_function(func, info, wait) \ (up_smp_call_function(func, info)) -#define on_each_cpu(func,info,retry,wait) \ +#define on_each_cpu(func,info,wait) \ ({ \ local_irq_disable(); \ func(info); \ -- cgit v1.2.3 From 1bdad606338debc6384b2844f1b53cc436b3ac90 Mon Sep 17 00:00:00 2001 From: Steven Whitehouse Date: Tue, 3 Jun 2008 14:09:53 +0100 Subject: [GFS2] Remove remote lock dropping code There are several reasons why this is undesirable: 1. It never happens during normal operation anyway 2. If it does happen it causes performance to be very, very poor 3. It isn't likely to solve the original problem (memory shortage on remote DLM node) it was supposed to solve 4. It uses a bunch of arbitrary constants which are unlikely to be correct for any particular situation and for which the tuning seems to be a black art. 5. In an N node cluster, only 1/N of the dropped locked will actually contribute to solving the problem on average. So all in all we are better off without it. This also makes merging the lock_dlm module into GFS2 a bit easier. Signed-off-by: Steven Whitehouse --- include/linux/lm_interface.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lm_interface.h b/include/linux/lm_interface.h index f274997bc283..d0a7112b9719 100644 --- a/include/linux/lm_interface.h +++ b/include/linux/lm_interface.h @@ -138,9 +138,6 @@ typedef void (*lm_callback_t) (void *ptr, unsigned int type, void *data); * LM_CB_NEED_RECOVERY * The given journal needs to be recovered. * - * LM_CB_DROPLOCKS - * Reduce the number of cached locks. - * * LM_CB_ASYNC * The given lock has been granted. */ @@ -149,7 +146,6 @@ typedef void (*lm_callback_t) (void *ptr, unsigned int type, void *data); #define LM_CB_NEED_D 258 #define LM_CB_NEED_S 259 #define LM_CB_NEED_RECOVERY 260 -#define LM_CB_DROPLOCKS 261 #define LM_CB_ASYNC 262 /* -- cgit v1.2.3 From b2cad26cfc2091050574a460b304ed103a35dbda Mon Sep 17 00:00:00 2001 From: Steven Whitehouse Date: Tue, 3 Jun 2008 14:34:14 +0100 Subject: [GFS2] Remove obsolete conversion deadlock avoidance code This is only used by GFS1 so can be removed. Signed-off-by: Steven Whitehouse --- include/linux/lm_interface.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lm_interface.h b/include/linux/lm_interface.h index d0a7112b9719..2ed8fa1b762b 100644 --- a/include/linux/lm_interface.h +++ b/include/linux/lm_interface.h @@ -122,11 +122,9 @@ typedef void (*lm_callback_t) (void *ptr, unsigned int type, void *data); */ #define LM_OUT_ST_MASK 0x00000003 -#define LM_OUT_CACHEABLE 0x00000004 #define LM_OUT_CANCELED 0x00000008 #define LM_OUT_ASYNC 0x00000080 #define LM_OUT_ERROR 0x00000100 -#define LM_OUT_CONV_DEADLK 0x00000200 /* * lm_callback_t types -- cgit v1.2.3 From ba8dd03ac09f51a69c154b8cb508b701d713a2cd Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Fri, 4 Jul 2008 11:26:40 +0200 Subject: generic-ipi: fix s390 build bug forgot to remove #include from linux/smp.h while fixing the original s390 build bug. Patch below fixes this build bug caused by header inclusion dependencies: CC kernel/timer.o In file included from include/linux/spinlock.h:87, from include/linux/smp.h:11, from include/linux/kernel_stat.h:4, from kernel/timer.c:22: include/asm/spinlock.h: In function '__raw_spin_lock': include/asm/spinlock.h:69: error: implicit declaration of function 'smp_processor_id' Signed-off-by: Heiko Carstens Signed-off-by: Ingo Molnar --- include/linux/smp.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/smp.h b/include/linux/smp.h index 55261101d09a..48262f86c969 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -8,7 +8,6 @@ #include #include -#include #include extern void cpu_idle(void); -- cgit v1.2.3 From b7a39bd0afc4021e8ad2b1189e884551e147427f Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Fri, 23 May 2008 18:38:49 +0100 Subject: firmware: make fw->data const In preparation for supporting firmware files linked into the static kernel, make fw->data const to ensure that users aren't modifying it (so that we can pass a pointer to the original in-kernel copy, rather than having to copy it). Signed-off-by: David Woodhouse --- include/linux/firmware.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/firmware.h b/include/linux/firmware.h index 6c7eff2ebada..88718d60153c 100644 --- a/include/linux/firmware.h +++ b/include/linux/firmware.h @@ -8,7 +8,7 @@ struct firmware { size_t size; - u8 *data; + const u8 *data; }; struct device; -- cgit v1.2.3 From 5658c769443d543728b6c5c673dffc2df8676317 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Fri, 23 May 2008 13:52:42 +0100 Subject: firmware: allow firmware files to be built into kernel image Some drivers have their own hacks to bypass the kernel's firmware loader and build their firmware into the kernel; this renders those unnecessary. Other drivers don't use the firmware loader at all, because they always want the firmware to be available. This allows them to start using the firmware loader. A third set of drivers already use the firmware loader, but can't be used without help from userspace, which sometimes requires an initrd. This allows them to work in a static kernel. Signed-off-by: David Woodhouse --- include/linux/firmware.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/firmware.h b/include/linux/firmware.h index 88718d60153c..c8ecf5b2a207 100644 --- a/include/linux/firmware.h +++ b/include/linux/firmware.h @@ -1,7 +1,10 @@ #ifndef _LINUX_FIRMWARE_H #define _LINUX_FIRMWARE_H + #include #include +#include + #define FIRMWARE_NAME_MAX 30 #define FW_ACTION_NOHOTPLUG 0 #define FW_ACTION_HOTPLUG 1 @@ -13,6 +16,24 @@ struct firmware { struct device; +struct builtin_fw { + char *name; + void *data; + unsigned long size; +}; + +/* We have to play tricks here much like stringify() to get the + __COUNTER__ macro to be expanded as we want it */ +#define __fw_concat1(x, y) x##y +#define __fw_concat(x, y) __fw_concat1(x, y) + +#define DECLARE_BUILTIN_FIRMWARE(name, blob) \ + DECLARE_BUILTIN_FIRMWARE_SIZE(name, &(blob), sizeof(blob)) + +#define DECLARE_BUILTIN_FIRMWARE_SIZE(name, blob, size) \ + static const struct builtin_fw __fw_concat(__builtin_fw,__COUNTER__) \ + __used __section(.builtin_fw) = { name, blob, size } + #if defined(CONFIG_FW_LOADER) || (defined(CONFIG_FW_LOADER_MODULE) && defined(MODULE)) int request_firmware(const struct firmware **fw, const char *name, struct device *device); -- cgit v1.2.3 From bacfe09dd7545467965e8d8f1eab20bc62dce00d Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Fri, 30 May 2008 13:57:27 +0300 Subject: ihex.h: binary representation of ihex records Some devices need their firmware as a set of {address, len, data...} records in some specific order rather than a simple blob. The normal way of doing this kind of thing is 'ihex', which is a text format and not entirely suitable for use in the kernel. This provides a binary representation which is very similar, but much more compact -- and a helper routine to skip to the next record, because the alignment constraints mean that everybody will screw it up for themselves otherwise. Also a helper function which can verify that a 'struct firmware' contains a valid set of ihex records, and that following them won't run off the end of the loaded data. Signed-off-by: David Woodhouse --- include/linux/ihex.h | 50 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 50 insertions(+) create mode 100644 include/linux/ihex.h (limited to 'include/linux') diff --git a/include/linux/ihex.h b/include/linux/ihex.h new file mode 100644 index 000000000000..df89edd890ae --- /dev/null +++ b/include/linux/ihex.h @@ -0,0 +1,50 @@ +/* + * Compact binary representation of ihex records. Some devices need their + * firmware loaded in strange orders rather than a single big blob, but + * actually parsing ihex-as-text within the kernel seems silly. Thus,... + */ + +#ifndef __LINUX_IHEX_H__ +#define __LINUX_IHEX_H__ + +#include +#include + +/* Intel HEX files actually limit the length to 256 bytes, but we have + drivers which would benefit from using separate records which are + longer than that, so we extend to 16 bits of length */ +struct ihex_binrec { + __be32 addr; + __be16 len; + uint8_t data[0]; +} __attribute__((aligned(4))); + +/* Find the next record, taking into account the 4-byte alignment */ +static inline const struct ihex_binrec * +ihex_next_binrec(const struct ihex_binrec *rec) +{ + int next = ((be16_to_cpu(rec->len) + 5) & ~3) - 2; + rec = (void *)&rec->data[next]; + + return be16_to_cpu(rec->len) ? rec : NULL; +} + +/* Check that ihex_next_binrec() won't take us off the end of the image... */ +static inline int ihex_validate_fw(const struct firmware *fw) +{ + const struct ihex_binrec *rec; + size_t ofs = 0; + + while (ofs <= fw->size - sizeof(*rec)) { + rec = (void *)&fw->data[ofs]; + + /* Zero length marks end of records */ + if (!be16_to_cpu(rec->len)) + return 0; + + /* Point to next record... */ + ofs += (sizeof(*rec) + be16_to_cpu(rec->len) + 3) & ~3; + } + return -EINVAL; +} +#endif /* __LINUX_IHEX_H__ */ -- cgit v1.2.3 From f1485f3deb89e6ae10c4d34662ec9e692855ab5d Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Sat, 31 May 2008 15:20:37 +0300 Subject: ihex: request_ihex_firmware() function to load and validate firmware Provide a helper to load the file and validate it in one call, to simplify error handling in the drivers which are going to use it. Signed-off-by: David Woodhouse --- include/linux/ihex.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ihex.h b/include/linux/ihex.h index df89edd890ae..2baace2788a7 100644 --- a/include/linux/ihex.h +++ b/include/linux/ihex.h @@ -9,6 +9,7 @@ #include #include +#include /* Intel HEX files actually limit the length to 256 bytes, but we have drivers which would benefit from using separate records which are @@ -47,4 +48,27 @@ static inline int ihex_validate_fw(const struct firmware *fw) } return -EINVAL; } + +/* Request firmware and validate it so that we can trust we won't + * run off the end while reading records... */ +static inline int request_ihex_firmware(const struct firmware **fw, + const char *fw_name, + struct device *dev) +{ + const struct firmware *lfw; + int ret; + + ret = request_firmware(&lfw, fw_name, dev); + if (ret) + return ret; + ret = ihex_validate_fw(lfw); + if (ret) { + dev_err(dev, "Firmware \"%s\" not valid IHEX records\n", + fw_name); + release_firmware(lfw); + return ret; + } + *fw = lfw; + return 0; +} #endif /* __LINUX_IHEX_H__ */ -- cgit v1.2.3 From 736603ab297506f4396cb5af592004499950fcfd Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Fri, 11 Jul 2008 19:27:31 -0400 Subject: jbd2: Add commit time into the commit block Carlo Wood has demonstrated that it's possible to recover deleted files from the journal. Something that will make this easier is if we can put the time of the commit into commit block. Signed-off-by: "Theodore Ts'o" --- include/linux/jbd2.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index d147f0f90360..ec9cadf58227 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -168,6 +168,8 @@ struct commit_header { unsigned char h_chksum_size; unsigned char h_padding[2]; __be32 h_chksum[JBD2_CHECKSUM_BYTES]; + __be64 h_commit_sec; + __be32 h_commit_nsec; }; /* -- cgit v1.2.3 From f4c0a0fdfae708f7aa438c27a380ed4071294e11 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 11 Jul 2008 19:27:31 -0400 Subject: vfs: export filemap_fdatawrite_range() Make filemap_fdatawrite_range() function public, so that it can later be used in ordered mode rewrite by JBD/JBD2. Signed-off-by: Jan Kara --- include/linux/fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index d8e2762ed14d..97f992adc62d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1740,6 +1740,8 @@ extern int wait_on_page_writeback_range(struct address_space *mapping, pgoff_t start, pgoff_t end); extern int __filemap_fdatawrite_range(struct address_space *mapping, loff_t start, loff_t end, int sync_mode); +extern int filemap_fdatawrite_range(struct address_space *mapping, + loff_t start, loff_t end); extern long do_fsync(struct file *file, int datasync); extern void sync_supers(void); -- cgit v1.2.3 From c851ed540173736e60d48b53b91a16ea5c903896 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 11 Jul 2008 19:27:31 -0400 Subject: jbd2: Implement data=ordered mode handling via inodes This patch adds necessary framework into JBD2 to be able to track inodes with each transaction and write-out their dirty data during transaction commit time. This new ordered mode brings all sorts of advantages such as possibility to get rid of journal heads and buffer heads for data buffers in ordered mode, better ordering of writes on transaction commit, simplification of some JBD code, no more anonymous pages when truncate of data being committed happens. Also with this new ordered mode, delayed allocation on ordered mode is much simpler. Signed-off-by: Jan Kara --- include/linux/jbd2.h | 42 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 42 insertions(+) (limited to 'include/linux') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index ec9cadf58227..622c3d8ca4ed 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -381,6 +381,38 @@ static inline void jbd_unlock_bh_journal_head(struct buffer_head *bh) bit_spin_unlock(BH_JournalHead, &bh->b_state); } +/* Flags in jbd_inode->i_flags */ +#define __JI_COMMIT_RUNNING 0 +/* Commit of the inode data in progress. We use this flag to protect us from + * concurrent deletion of inode. We cannot use reference to inode for this + * since we cannot afford doing last iput() on behalf of kjournald + */ +#define JI_COMMIT_RUNNING (1 << __JI_COMMIT_RUNNING) + +/** + * struct jbd_inode is the structure linking inodes in ordered mode + * present in a transaction so that we can sync them during commit. + */ +struct jbd2_inode { + /* Which transaction does this inode belong to? Either the running + * transaction or the committing one. [j_list_lock] */ + transaction_t *i_transaction; + + /* Pointer to the running transaction modifying inode's data in case + * there is already a committing transaction touching it. [j_list_lock] */ + transaction_t *i_next_transaction; + + /* List of inodes in the i_transaction [j_list_lock] */ + struct list_head i_list; + + /* VFS inode this inode belongs to [constant during the lifetime + * of the structure] */ + struct inode *i_vfs_inode; + + /* Flags of inode [j_list_lock] */ + unsigned int i_flags; +}; + struct jbd2_revoke_table_s; /** @@ -566,6 +598,12 @@ struct transaction_s */ struct journal_head *t_log_list; + /* + * List of inodes whose data we've modified in data=ordered mode. + * [j_list_lock] + */ + struct list_head t_inode_list; + /* * Protects info related to handles */ @@ -1046,6 +1084,10 @@ extern void jbd2_journal_ack_err (journal_t *); extern int jbd2_journal_clear_err (journal_t *); extern int jbd2_journal_bmap(journal_t *, unsigned long, unsigned long long *); extern int jbd2_journal_force_commit(journal_t *); +extern int jbd2_journal_file_inode(handle_t *handle, struct jbd2_inode *inode); +extern int jbd2_journal_begin_ordered_truncate(struct jbd2_inode *inode, loff_t new_size); +extern void jbd2_journal_init_jbd_inode(struct jbd2_inode *jinode, struct inode *inode); +extern void jbd2_journal_release_jbd_inode(journal_t *journal, struct jbd2_inode *jinode); /* * journal_head management -- cgit v1.2.3 From 87c89c232c8f7b3820c33c3b9bc803e9358027da Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 11 Jul 2008 19:27:31 -0400 Subject: jbd2: Remove data=ordered mode support using jbd buffer heads Signed-off-by: Jan Kara --- include/linux/jbd2.h | 29 +++++++---------------------- 1 file changed, 7 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 622c3d8ca4ed..3dd209007098 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -542,24 +542,12 @@ struct transaction_s */ struct journal_head *t_reserved_list; - /* - * Doubly-linked circular list of all buffers under writeout during - * commit [j_list_lock] - */ - struct journal_head *t_locked_list; - /* * Doubly-linked circular list of all metadata buffers owned by this * transaction [j_list_lock] */ struct journal_head *t_buffers; - /* - * Doubly-linked circular list of all data buffers still to be - * flushed before this transaction can be committed [j_list_lock] - */ - struct journal_head *t_sync_datalist; - /* * Doubly-linked circular list of all forget buffers (superseded * buffers which we can un-checkpoint once this transaction commits) @@ -1044,7 +1032,6 @@ extern int jbd2_journal_extend (handle_t *, int nblocks); extern int jbd2_journal_get_write_access(handle_t *, struct buffer_head *); extern int jbd2_journal_get_create_access (handle_t *, struct buffer_head *); extern int jbd2_journal_get_undo_access(handle_t *, struct buffer_head *); -extern int jbd2_journal_dirty_data (handle_t *, struct buffer_head *); extern int jbd2_journal_dirty_metadata (handle_t *, struct buffer_head *); extern void jbd2_journal_release_buffer (handle_t *, struct buffer_head *); extern int jbd2_journal_forget (handle_t *, struct buffer_head *); @@ -1223,15 +1210,13 @@ static inline int jbd_space_needed(journal_t *journal) /* journaling buffer types */ #define BJ_None 0 /* Not journaled */ -#define BJ_SyncData 1 /* Normal data: flush before commit */ -#define BJ_Metadata 2 /* Normal journaled metadata */ -#define BJ_Forget 3 /* Buffer superseded by this transaction */ -#define BJ_IO 4 /* Buffer is for temporary IO use */ -#define BJ_Shadow 5 /* Buffer contents being shadowed to the log */ -#define BJ_LogCtl 6 /* Buffer contains log descriptors */ -#define BJ_Reserved 7 /* Buffer is reserved for access by journal */ -#define BJ_Locked 8 /* Locked for I/O during commit */ -#define BJ_Types 9 +#define BJ_Metadata 1 /* Normal journaled metadata */ +#define BJ_Forget 2 /* Buffer superseded by this transaction */ +#define BJ_IO 3 /* Buffer is for temporary IO use */ +#define BJ_Shadow 4 /* Buffer contents being shadowed to the log */ +#define BJ_LogCtl 5 /* Buffer contains log descriptors */ +#define BJ_Reserved 6 /* Buffer is reserved for access by journal */ +#define BJ_Types 7 extern int jbd_blocks_per_page(struct inode *inode); -- cgit v1.2.3 From 29a814d2ee0e43c2980f33f91c1311ec06c0aa35 Mon Sep 17 00:00:00 2001 From: Alex Tomas Date: Fri, 11 Jul 2008 19:27:31 -0400 Subject: vfs: add hooks for ext4's delayed allocation support Export mpage_bio_submit() and __mpage_writepage() for the benefit of ext4's delayed allocation support. Also change __block_write_full_page so that if buffers that have the BH_Delay flag set it will call get_block() to get the physical block allocated, just as in the !BH_Mapped case. Signed-off-by: Alex Tomas Signed-off-by: "Theodore Ts'o" --- include/linux/mpage.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mpage.h b/include/linux/mpage.h index 068a0c9946af..5c42821da2d1 100644 --- a/include/linux/mpage.h +++ b/include/linux/mpage.h @@ -11,11 +11,21 @@ */ #ifdef CONFIG_BLOCK +struct mpage_data { + struct bio *bio; + sector_t last_block_in_bio; + get_block_t *get_block; + unsigned use_writepage; +}; + struct writeback_control; +struct bio *mpage_bio_submit(int rw, struct bio *bio); int mpage_readpages(struct address_space *mapping, struct list_head *pages, unsigned nr_pages, get_block_t get_block); int mpage_readpage(struct page *page, get_block_t get_block); +int __mpage_writepage(struct page *page, struct writeback_control *wbc, + void *data); int mpage_writepages(struct address_space *mapping, struct writeback_control *wbc, get_block_t get_block); int mpage_writepage(struct page *page, get_block_t *get_block, -- cgit v1.2.3 From e8ced39d5e8911c662d4d69a342b9d053eaaac4e Mon Sep 17 00:00:00 2001 From: Mingming Cao Date: Fri, 11 Jul 2008 19:27:31 -0400 Subject: percpu_counter: new function percpu_counter_sum_and_set Delayed allocation need to check free blocks at every write time. percpu_counter_read_positive() is not quit accurate. delayed allocation need a more accurate accounting, but using percpu_counter_sum_positive() is frequently is quite expensive. This patch added a new function to update center counter when sum per-cpu counter, to increase the accurate rate for next percpu_counter_read() and require less calling expensive percpu_counter_sum(). Signed-off-by: Mingming Cao Signed-off-by: "Theodore Ts'o" --- include/linux/percpu_counter.h | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h index 9007ccdfc112..208388835357 100644 --- a/include/linux/percpu_counter.h +++ b/include/linux/percpu_counter.h @@ -35,7 +35,7 @@ int percpu_counter_init_irq(struct percpu_counter *fbc, s64 amount); void percpu_counter_destroy(struct percpu_counter *fbc); void percpu_counter_set(struct percpu_counter *fbc, s64 amount); void __percpu_counter_add(struct percpu_counter *fbc, s64 amount, s32 batch); -s64 __percpu_counter_sum(struct percpu_counter *fbc); +s64 __percpu_counter_sum(struct percpu_counter *fbc, int set); static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount) { @@ -44,13 +44,19 @@ static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount) static inline s64 percpu_counter_sum_positive(struct percpu_counter *fbc) { - s64 ret = __percpu_counter_sum(fbc); + s64 ret = __percpu_counter_sum(fbc, 0); return ret < 0 ? 0 : ret; } +static inline s64 percpu_counter_sum_and_set(struct percpu_counter *fbc) +{ + return __percpu_counter_sum(fbc, 1); +} + + static inline s64 percpu_counter_sum(struct percpu_counter *fbc) { - return __percpu_counter_sum(fbc); + return __percpu_counter_sum(fbc, 0); } static inline s64 percpu_counter_read(struct percpu_counter *fbc) -- cgit v1.2.3 From 06d6cf6959d22037fcec598f4f954db5db3d7356 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Fri, 11 Jul 2008 19:27:31 -0400 Subject: mm: Add range_cont mode for writeback Filesystems like ext4 needs to start a new transaction in the writepages for block allocation. This happens with delayed allocation and there is limit to how many credits we can request from the journal layer. So we call write_cache_pages multiple times with wbc->nr_to_write set to the maximum possible value limitted by the max journal credits available. Add a new mode to writeback that enables us to handle this behaviour. In the new mode we update the wbc->range_start to point to the new offset to be written. Next call to call to write_cache_pages will start writeout from specified range_start offset. In the new mode we also limit writing to the specified wbc->range_end. Signed-off-by: Aneesh Kumar K.V Signed-off-by: Mingming Cao Acked-by: Jan Kara Signed-off-by: "Theodore Ts'o" --- include/linux/writeback.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index f462439cc288..0d8573e6b9ec 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -63,6 +63,7 @@ struct writeback_control { unsigned for_writepages:1; /* This is a writepages() call */ unsigned range_cyclic:1; /* range_start is cyclic */ unsigned more_io:1; /* more io to be dispatched */ + unsigned range_cont:1; }; /* -- cgit v1.2.3 From 341c2c958ec7bdd9f54733a8b0b432fe76842a82 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 20 May 2008 02:17:51 +0900 Subject: libata: consistently use msecs for time durations libata has been using mix of jiffies and msecs for time druations. This is getting confusing. As writing sub HZ values in jiffies is PITA and msecs_to_jiffies() can't be used as initializer, unify unit for all time durations to msecs. So, durations are in msecs and deadlines are in jiffies. ata_deadline() is added to compute deadline from a start time and duration in msecs. While at it, drop now superflous _msec suffix from arguments and rename @timeout to @deadline if it represents a fixed point in time rather than duration. Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- include/linux/libata.h | 26 ++++++++++++++++---------- 1 file changed, 16 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index e57e5d08312d..94110b652b30 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -27,6 +27,7 @@ #define __LINUX_LIBATA_H__ #include +#include #include #include #include @@ -115,7 +116,7 @@ enum { /* tag ATA_MAX_QUEUE - 1 is reserved for internal commands */ ATA_MAX_QUEUE = 32, ATA_TAG_INTERNAL = ATA_MAX_QUEUE - 1, - ATA_SHORT_PAUSE = (HZ >> 6) + 1, + ATA_SHORT_PAUSE = 16, ATAPI_MAX_DRAIN = 16 << 10, @@ -234,17 +235,17 @@ enum { /* bits 24:31 of host->flags are reserved for LLD specific flags */ /* various lengths of time */ - ATA_TMOUT_BOOT = 30 * HZ, /* heuristic */ - ATA_TMOUT_BOOT_QUICK = 7 * HZ, /* heuristic */ - ATA_TMOUT_INTERNAL = 30 * HZ, - ATA_TMOUT_INTERNAL_QUICK = 5 * HZ, + ATA_TMOUT_BOOT = 30000, /* heuristic */ + ATA_TMOUT_BOOT_QUICK = 7000, /* heuristic */ + ATA_TMOUT_INTERNAL = 30000, + ATA_TMOUT_INTERNAL_QUICK = 5000, /* FIXME: GoVault needs 2s but we can't afford that without * parallel probing. 800ms is enough for iVDR disk * HHD424020F7SV00. Increase to 2secs when parallel probing * is in place. */ - ATA_TMOUT_FF_WAIT = 4 * HZ / 5, + ATA_TMOUT_FF_WAIT = 800, /* Spec mandates to wait for ">= 2ms" before checking status * after reset. We wait 150ms, because that was the magic @@ -256,14 +257,14 @@ enum { * * Old drivers/ide uses the 2mS rule and then waits for ready. */ - ATA_WAIT_AFTER_RESET_MSECS = 150, + ATA_WAIT_AFTER_RESET = 150, /* If PMP is supported, we have to do follow-up SRST. As some * PMPs don't send D2H Reg FIS after hardreset, LLDs are * advised to wait only for the following duration before * doing SRST. */ - ATA_TMOUT_PMP_SRST_WAIT = 1 * HZ, + ATA_TMOUT_PMP_SRST_WAIT = 1000, /* ATA bus states */ BUS_UNKNOWN = 0, @@ -895,8 +896,7 @@ extern void ata_host_resume(struct ata_host *host); #endif extern int ata_ratelimit(void); extern u32 ata_wait_register(void __iomem *reg, u32 mask, u32 val, - unsigned long interval_msec, - unsigned long timeout_msec); + unsigned long interval, unsigned long timeout); extern int atapi_cmd_type(u8 opcode); extern void ata_tf_to_fis(const struct ata_taskfile *tf, u8 pmp, int is_cmd, u8 *fis); @@ -1389,6 +1389,12 @@ static inline int ata_check_ready(u8 status) return 0; } +static inline unsigned long ata_deadline(unsigned long from_jiffies, + unsigned long timeout_msecs) +{ + return from_jiffies + msecs_to_jiffies(timeout_msecs); +} + /************************************************************************** * PMP - drivers/ata/libata-pmp.c -- cgit v1.2.3 From 0a2c0f56159999e20015241d3b8fa89b1ab14309 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 20 May 2008 02:17:52 +0900 Subject: libata: improve EH retry delay handling EH retries were delayed by 5 seconds to ensure that resets don't occur back-to-back. However, this 5 second delay is superflous or excessive in many cases. For example, after IDENTIFY times out, there's no reason to wait five more seconds before retrying. This patch adds ehc->last_reset timestamp and record the timestamp for the last reset trial or success and uses it to space resets by ATA_EH_RESET_COOL_DOWN which is 5 secs and removes unconditional 5 sec sleeps. As this change makes inter-try waits often shorter and they're redundant in nature, this patch also removes the "retrying..." messages. While at it, convert explicit rounding up division to DIV_ROUND_UP(). This change speeds up EH in many cases w/o sacrificing robustness. Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- include/linux/libata.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 94110b652b30..9058c2a325a9 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -602,6 +602,8 @@ struct ata_eh_context { unsigned int did_probe_mask; unsigned int saved_ncq_enabled; u8 saved_xfer_mode[ATA_MAX_DEVICES]; + /* timestamp for the last reset attempt or success */ + unsigned long last_reset; }; struct ata_acpi_drive -- cgit v1.2.3 From 87fbc5a060faf2394bee88a93519f9b9d434727c Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 20 May 2008 02:17:54 +0900 Subject: libata: improve EH internal command timeout handling ATA_TMOUT_INTERNAL which was 30secs were used for all internal commands which is way too long when something goes wrong. This patch implements command type based stepped timeouts. Different command types can use different timeouts and each command type can use different timeout values after timeouts. ie. the initial timeout is set to a value which should cover most of the cases but not too long so that run away cases don't delay things too much. After the first try times out, the second try can use longer timeout and if that one times out too, it can go for full 30sec timeout. IDENTIFYs use 5s - 10s - 30s timeout and all other commands use 5s - 10s timeouts. This patch significantly cuts down the needed time to handle failure cases while still allowing libata to work with nut job devices through retries. Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- include/linux/libata.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 9058c2a325a9..035f8e1cd0ac 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -237,7 +237,6 @@ enum { /* various lengths of time */ ATA_TMOUT_BOOT = 30000, /* heuristic */ ATA_TMOUT_BOOT_QUICK = 7000, /* heuristic */ - ATA_TMOUT_INTERNAL = 30000, ATA_TMOUT_INTERNAL_QUICK = 5000, /* FIXME: GoVault needs 2s but we can't afford that without @@ -341,6 +340,11 @@ enum { SATA_PMP_RW_TIMEOUT = 3000, /* PMP read/write timeout */ + /* This should match the actual table size of + * ata_eh_cmd_timeout_table in libata-eh.c. + */ + ATA_EH_CMD_TIMEOUT_TABLE_SIZE = 5, + /* Horkage types. May be set by libata or controller on drives (some horkage may be drive/controller pair dependant */ @@ -598,6 +602,8 @@ struct ata_eh_info { struct ata_eh_context { struct ata_eh_info i; int tries[ATA_MAX_DEVICES]; + int cmd_timeout_idx[ATA_MAX_DEVICES] + [ATA_EH_CMD_TIMEOUT_TABLE_SIZE]; unsigned int classes[ATA_MAX_DEVICES]; unsigned int did_probe_mask; unsigned int saved_ncq_enabled; -- cgit v1.2.3 From 18f7ba4c2f4be6b37d925931f04d6cc28d88d1ee Mon Sep 17 00:00:00 2001 From: Kristen Carlson Accardi Date: Tue, 3 Jun 2008 10:33:55 -0700 Subject: libata/ahci: enclosure management support Add Enclosure Management support to libata and ahci. Signed-off-by: Kristen Carlson Accardi Signed-off-by: Jeff Garzik --- include/linux/libata.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 035f8e1cd0ac..5b247b8a6b3b 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -169,6 +169,7 @@ enum { ATA_LFLAG_ASSUME_CLASS = ATA_LFLAG_ASSUME_ATA | ATA_LFLAG_ASSUME_SEMB, ATA_LFLAG_NO_RETRY = (1 << 5), /* don't retry this link */ ATA_LFLAG_DISABLED = (1 << 6), /* link is disabled */ + ATA_LFLAG_SW_ACTIVITY = (1 << 7), /* keep activity stats */ /* struct ata_port flags */ ATA_FLAG_SLAVE_POSS = (1 << 0), /* host supports slave dev */ @@ -191,6 +192,10 @@ enum { ATA_FLAG_AN = (1 << 18), /* controller supports AN */ ATA_FLAG_PMP = (1 << 19), /* controller supports PMP */ ATA_FLAG_IPM = (1 << 20), /* driver can handle IPM */ + ATA_FLAG_EM = (1 << 21), /* driver supports enclosure + * management */ + ATA_FLAG_SW_ACTIVITY = (1 << 22), /* driver supports sw activity + * led */ /* The following flag belongs to ap->pflags but is kept in * ap->flags because it's referenced in many LLDs and will be @@ -446,6 +451,15 @@ enum link_pm { MEDIUM_POWER, }; extern struct device_attribute dev_attr_link_power_management_policy; +extern struct device_attribute dev_attr_em_message_type; +extern struct device_attribute dev_attr_em_message; +extern struct device_attribute dev_attr_sw_activity; + +enum sw_activity { + OFF, + BLINK_ON, + BLINK_OFF, +}; #ifdef CONFIG_ATA_SFF struct ata_ioports { @@ -701,6 +715,7 @@ struct ata_port { struct timer_list fastdrain_timer; unsigned long fastdrain_cnt; + int em_message_type; void *private_data; #ifdef CONFIG_ATA_ACPI @@ -792,6 +807,12 @@ struct ata_port_operations { u8 (*bmdma_status)(struct ata_port *ap); #endif /* CONFIG_ATA_SFF */ + ssize_t (*em_show)(struct ata_port *ap, char *buf); + ssize_t (*em_store)(struct ata_port *ap, const char *message, + size_t size); + ssize_t (*sw_activity_show)(struct ata_device *dev, char *buf); + ssize_t (*sw_activity_store)(struct ata_device *dev, + enum sw_activity val); /* * Obsolete */ -- cgit v1.2.3 From 20a9b6e7c303f2a6f9afe17c0997bc9a3c734442 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Mon, 14 Jul 2008 22:38:22 +0200 Subject: i2c: Remove 3 deprecated bus drivers This patch contains the scheduled removal of i2c-i810, i2c-prosavage and i2c-savage4. Signed-off-by: Adrian Bunk Signed-off-by: Jean Delvare --- include/linux/i2c-id.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/i2c-id.h b/include/linux/i2c-id.h index 580acc93903e..988e566d3ed5 100644 --- a/include/linux/i2c-id.h +++ b/include/linux/i2c-id.h @@ -111,7 +111,6 @@ #define I2C_HW_B_RIVA 0x010010 /* Riva based graphics cards */ #define I2C_HW_B_IOC 0x010011 /* IOC bit-wiggling */ #define I2C_HW_B_IXP2000 0x010016 /* GPIO on IXP2000 systems */ -#define I2C_HW_B_S3VIA 0x010018 /* S3Via ProSavage adapter */ #define I2C_HW_B_ZR36067 0x010019 /* Zoran-36057/36067 based boards */ #define I2C_HW_B_PCILYNX 0x01001a /* TI PCILynx I2C adapter */ #define I2C_HW_B_CX2388x 0x01001b /* connexant 2388x based tv cards */ -- cgit v1.2.3 From 67c2e66571c383404a5acd08189194da660da942 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Mon, 14 Jul 2008 22:38:23 +0200 Subject: i2c: Delete unused function i2c_smbus_write_quick Function i2c_smbus_write_quick has no users left, so we can delete it. Also update the list of these helper functions which are gone but could be added back if needed. Signed-off-by: Jean Delvare --- include/linux/i2c.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 8dc730132192..b3695f353f79 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -71,7 +71,6 @@ extern s32 i2c_smbus_xfer (struct i2c_adapter * adapter, u16 addr, /* Now follow the 'nice' access routines. These also document the calling conventions of smbus_access. */ -extern s32 i2c_smbus_write_quick(struct i2c_client * client, u8 value); extern s32 i2c_smbus_read_byte(struct i2c_client * client); extern s32 i2c_smbus_write_byte(struct i2c_client * client, u8 value); extern s32 i2c_smbus_read_byte_data(struct i2c_client * client, u8 command); -- cgit v1.2.3 From ae7193f7fa3e1735ab70807eb6e35a2a6575623f Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Mon, 14 Jul 2008 22:38:24 +0200 Subject: i2c: Update stray references to smbus_access That function is actually named i2c_smbus_xfer. Signed-off-by: Jean Delvare --- include/linux/i2c.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index b3695f353f79..7c36d5188d39 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -69,7 +69,7 @@ extern s32 i2c_smbus_xfer (struct i2c_adapter * adapter, u16 addr, union i2c_smbus_data * data); /* Now follow the 'nice' access routines. These also document the calling - conventions of smbus_access. */ + conventions of i2c_smbus_xfer. */ extern s32 i2c_smbus_read_byte(struct i2c_client * client); extern s32 i2c_smbus_write_byte(struct i2c_client * client, u8 value); @@ -536,7 +536,7 @@ union i2c_smbus_data { /* and one more for user-space compatibility */ }; -/* smbus_access read or write markers */ +/* i2c_smbus_xfer read or write markers */ #define I2C_SMBUS_READ 1 #define I2C_SMBUS_WRITE 0 -- cgit v1.2.3 From c1b6b4f2342d073698dfc2547240c35045a1d00e Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Mon, 14 Jul 2008 22:38:28 +0200 Subject: i2c: Let framebuffer drivers set their I2C bus class to DDC Let framebuffer drivers set their I2C bus class to DDC. Once this is done, we will be able to tell the eeprom driver to only probe for EDID EEPROMs on these buses. Signed-off-by: Jean Delvare --- include/linux/i2c.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 7c36d5188d39..145797fe6a31 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -349,7 +349,7 @@ static inline void i2c_set_adapdata (struct i2c_adapter *dev, void *data) #define I2C_CLASS_HWMON (1<<0) /* lm_sensors, ... */ #define I2C_CLASS_TV_ANALOG (1<<1) /* bttv + friends */ #define I2C_CLASS_TV_DIGITAL (1<<2) /* dvb cards */ -#define I2C_CLASS_DDC (1<<3) /* i2c-matroxfb ? */ +#define I2C_CLASS_DDC (1<<3) /* DDC bus on graphics adapters */ #define I2C_CLASS_CAM_ANALOG (1<<4) /* camera with analog CCD */ #define I2C_CLASS_CAM_DIGITAL (1<<5) /* most webcams */ #define I2C_CLASS_SOUND (1<<6) /* sound devices */ -- cgit v1.2.3 From 3401b2fff38fbb8b73ea6bcc69a8370ae5d2a7a0 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Mon, 14 Jul 2008 22:38:29 +0200 Subject: i2c: Let bus drivers add SPD to their class Let general purpose I2C/SMBus bus drivers add SPD to their class. Once this is done, we will be able to tell the eeprom driver to only probe for SPD EEPROMs and similar on these buses. Note that I took a conservative approach here, adding I2C_CLASS_SPD to many drivers that have no idea whether they can host SPD EEPROMs or not. This is to make sure that the eeprom driver doesn't stop probing buses where SPD EEPROMs or equivalent live. So, bus driver maintainers and users should feel free to remove the SPD class from drivers those buses never have SPD EEPROMs or they don't want the eeprom driver to bind to them. Likewise, feel free to add the SPD class to any bus driver I might have missed. Signed-off-by: Jean Delvare --- include/linux/i2c.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 145797fe6a31..839d0ea3dca3 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -353,6 +353,7 @@ static inline void i2c_set_adapdata (struct i2c_adapter *dev, void *data) #define I2C_CLASS_CAM_ANALOG (1<<4) /* camera with analog CCD */ #define I2C_CLASS_CAM_DIGITAL (1<<5) /* most webcams */ #define I2C_CLASS_SOUND (1<<6) /* sound devices */ +#define I2C_CLASS_SPD (1<<7) /* SPD EEPROMs and similar */ #define I2C_CLASS_ALL (UINT_MAX) /* all of the above */ /* i2c_client_address_data is the struct for holding default client -- cgit v1.2.3 From 0573d11b2bbd0e4774f33f4c1959c1939c055e96 Mon Sep 17 00:00:00 2001 From: Eric Brower Date: Mon, 14 Jul 2008 22:38:31 +0200 Subject: i2c-algo-pcf: Multi-master lost-arbitration improvement Improve lost-arbitration handling of PCF8584. This is necessary for support of a currently out-of-kernel driver for Sun Microsystems E250 environmental management; perhaps others. Signed-off-by: Eric Brower Acked-by: Dan Smolik Signed-off-by: Jean Delvare --- include/linux/i2c-algo-pcf.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/i2c-algo-pcf.h b/include/linux/i2c-algo-pcf.h index 77afbb60fd11..74fb6f889a77 100644 --- a/include/linux/i2c-algo-pcf.h +++ b/include/linux/i2c-algo-pcf.h @@ -36,6 +36,12 @@ struct i2c_algo_pcf_data { /* local settings */ int udelay; int timeout; + + /* Multi-master lost arbitration back-off delay (msecs) + * This should be set by the bus adapter or knowledgable client + * if bus is multi-mastered, else zero + */ + unsigned long lab_mdelay; }; int i2c_pcf_add_bus(struct i2c_adapter *); -- cgit v1.2.3 From e3e7fc3c401a5d53f0599a357b3cf65d6a4f52e3 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Mon, 14 Jul 2008 22:38:31 +0200 Subject: i2c-algo-pcf: Drop unused struct members Struct members udelay and timeout aren't used anywhere, so drop them. Signed-off-by: Jean Delvare Acked-by: Eric Brower --- include/linux/i2c-algo-pcf.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c-algo-pcf.h b/include/linux/i2c-algo-pcf.h index 74fb6f889a77..0177d280f733 100644 --- a/include/linux/i2c-algo-pcf.h +++ b/include/linux/i2c-algo-pcf.h @@ -33,10 +33,6 @@ struct i2c_algo_pcf_data { int (*getclock) (void *data); void (*waitforpin) (void); - /* local settings */ - int udelay; - int timeout; - /* Multi-master lost arbitration back-off delay (msecs) * This should be set by the bus adapter or knowledgable client * if bus is multi-mastered, else zero -- cgit v1.2.3 From f6a7110520037ba786f17b53790c6eb8a3d4ef55 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Mon, 14 Jul 2008 22:38:34 +0200 Subject: i2c-dev: Delete empty detach_client callback Implementing detach_client is optional, so there is no point in an empty implementation. Likewise, i2c driver IDs are optional, and we don't need one. Signed-off-by: Jean Delvare --- include/linux/i2c-id.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c-id.h b/include/linux/i2c-id.h index 988e566d3ed5..ef13b7c66df3 100644 --- a/include/linux/i2c-id.h +++ b/include/linux/i2c-id.h @@ -91,8 +91,6 @@ #define I2C_DRIVERID_M52790 95 /* Mitsubishi M52790SP/FP AV switch */ #define I2C_DRIVERID_CS5345 96 /* cs5345 audio processor */ -#define I2C_DRIVERID_I2CDEV 900 - #define I2C_DRIVERID_OV7670 1048 /* Omnivision 7670 camera */ /* -- cgit v1.2.3 From e9ca9eb9d7fc7bf3dc3cec5ba7edb089c4625f7b Mon Sep 17 00:00:00 2001 From: Jon Smirl Date: Mon, 14 Jul 2008 22:38:35 +0200 Subject: i2c: Export the i2c_bus_type symbol Export the root of the i2c bus so that PowerPC device tree code can iterate over devices on the i2c bus. Signed-off-by: Jon Smirl Signed-off-by: Jean Delvare --- include/linux/i2c.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 839d0ea3dca3..50cbab4b62b0 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -35,6 +35,8 @@ #include /* for completion */ #include +extern struct bus_type i2c_bus_type; + /* --- General options ------------------------------------------------ */ struct i2c_msg; -- cgit v1.2.3 From 2b7a5056a0a7ff17d5d2004c29c852a92a6bd632 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Mon, 14 Jul 2008 22:38:35 +0200 Subject: i2c: New-style EEPROM driver using device IDs Add a new-style driver for most I2C EEPROMs, giving sysfs read/write access to their data. Tested with various chips and clock rates. Signed-off-by: Wolfram Sang Signed-off-by: Jean Delvare --- include/linux/i2c/at24.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) create mode 100644 include/linux/i2c/at24.h (limited to 'include/linux') diff --git a/include/linux/i2c/at24.h b/include/linux/i2c/at24.h new file mode 100644 index 000000000000..f6edd522a929 --- /dev/null +++ b/include/linux/i2c/at24.h @@ -0,0 +1,28 @@ +#ifndef _LINUX_AT24_H +#define _LINUX_AT24_H + +#include + +/* + * As seen through Linux I2C, differences between the most common types of I2C + * memory include: + * - How much memory is available (usually specified in bit)? + * - What write page size does it support? + * - Special flags (16 bit addresses, read_only, world readable...)? + * + * If you set up a custom eeprom type, please double-check the parameters. + * Especially page_size needs extra care, as you risk data loss if your value + * is bigger than what the chip actually supports! + */ + +struct at24_platform_data { + u32 byte_len; /* size (sum of all addr) */ + u16 page_size; /* for writes */ + u8 flags; +#define AT24_FLAG_ADDR16 0x80 /* address pointer is 16 bit */ +#define AT24_FLAG_READONLY 0x40 /* sysfs-entry will be read-only */ +#define AT24_FLAG_IRUGO 0x20 /* sysfs-entry will be world-readable */ +#define AT24_FLAG_TAKE8ADDR 0x10 /* take always 8 addresses (24c00) */ +}; + +#endif /* _LINUX_AT24_H */ -- cgit v1.2.3 From 4735c98f8447acb1c8977e2b8024640f7bf36dd6 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Mon, 14 Jul 2008 22:38:36 +0200 Subject: i2c: Add detection capability to new-style drivers Add a mechanism to let new-style i2c drivers optionally autodetect devices they would support on selected buses and ask i2c-core to instantiate them. This is a replacement for legacy i2c drivers, much cleaner. Where drivers had to implement both a legacy i2c_driver and a new-style i2c_driver so far, this mechanism makes it possible to get rid of the legacy i2c_driver and implement both enumerated and detected device support with just one (new-style) i2c_driver. Here is a quick conversion guide for these drivers, step by step: * Delete the legacy driver definition, registration and removal. Delete the attach_adapter and detach_client methods of the legacy driver. * Change the prototype of the legacy detect function from static int foo_detect(struct i2c_adapter *adapter, int address, int kind); to static int foo_detect(struct i2c_client *client, int kind, struct i2c_board_info *info); * Set the new-style driver detect callback to this new function, and set its address_data to &addr_data (addr_data is generally provided by I2C_CLIENT_INSMOD.) * Add the appropriate class to the new-style driver. This is typically the class the legacy attach_adapter method was checking for. Class checking is now mandatory (done by i2c-core.) See for the list of available classes. * Remove the i2c_client allocation and freeing from the detect function. A pre-allocated client is now handed to you by i2c-core, and is freed automatically. * Make the detect function fill the type field of the i2c_board_info structure it was passed as a parameter, and return 0, on success. If the detection fails, return -ENODEV. Signed-off-by: Jean Delvare --- include/linux/i2c.h | 36 +++++++++++++++++++++++++++++++----- 1 file changed, 31 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 50cbab4b62b0..08be0d21864c 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -45,6 +45,7 @@ struct i2c_adapter; struct i2c_client; struct i2c_driver; union i2c_smbus_data; +struct i2c_board_info; /* * The master routines are the ones normally used to transmit data to devices @@ -94,15 +95,33 @@ extern s32 i2c_smbus_write_i2c_block_data(struct i2c_client * client, u8 command, u8 length, const u8 *values); -/* - * A driver is capable of handling one or more physical devices present on - * I2C adapters. This information is used to inform the driver of adapter - * events. +/** + * struct i2c_driver - represent an I2C device driver + * @class: What kind of i2c device we instantiate (for detect) + * @detect: Callback for device detection + * @address_data: The I2C addresses to probe, ignore or force (for detect) + * @clients: List of detected clients we created (for i2c-core use only) * * The driver.owner field should be set to the module owner of this driver. * The driver.name field should be set to the name of this driver. + * + * For automatic device detection, both @detect and @address_data must + * be defined. @class should also be set, otherwise only devices forced + * with module parameters will be created. The detect function must + * fill at least the name field of the i2c_board_info structure it is + * handed upon successful detection, and possibly also the flags field. + * + * If @detect is missing, the driver will still work fine for enumerated + * devices. Detected devices simply won't be supported. This is expected + * for the many I2C/SMBus devices which can't be detected reliably, and + * the ones which can always be enumerated in practice. + * + * The i2c_client structure which is handed to the @detect callback is + * not a real i2c_client. It is initialized just enough so that you can + * call i2c_smbus_read_byte_data and friends on it. Don't do anything + * else with it. In particular, calling dev_dbg and friends on it is + * not allowed. */ - struct i2c_driver { int id; unsigned int class; @@ -142,6 +161,11 @@ struct i2c_driver { struct device_driver driver; const struct i2c_device_id *id_table; + + /* Device detection callback for automatic device creation */ + int (*detect)(struct i2c_client *, int kind, struct i2c_board_info *); + const struct i2c_client_address_data *address_data; + struct list_head clients; }; #define to_i2c_driver(d) container_of(d, struct i2c_driver, driver) @@ -157,6 +181,7 @@ struct i2c_driver { * @dev: Driver model device node for the slave. * @irq: indicates the IRQ generated by this device (if any) * @list: list of active/busy clients (DEPRECATED) + * @detected: member of an i2c_driver.clients list * @released: used to synchronize client releases & detaches and references * * An i2c_client identifies a single device (i.e. chip) connected to an @@ -174,6 +199,7 @@ struct i2c_client { struct device dev; /* the device structure */ int irq; /* irq issued by device */ struct list_head list; /* DEPRECATED */ + struct list_head detected; struct completion released; }; #define to_i2c_client(d) container_of(d, struct i2c_client, dev) -- cgit v1.2.3 From 521e575b9a7324a0bca762622139f69582a042bf Mon Sep 17 00:00:00 2001 From: Ron Livne Date: Mon, 14 Jul 2008 23:48:48 -0700 Subject: IB/mlx4: Add support for blocking multicast loopback packets Add support for handling the IB_QP_CREATE_MULTICAST_BLOCK_LOOPBACK flag by using the per-multicast group loopback blocking feature of mlx4 hardware. Signed-off-by: Ron Livne Signed-off-by: Roland Dreier --- include/linux/mlx4/device.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index a744383d16e9..81b3dd5206e0 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -398,7 +398,8 @@ int mlx4_srq_query(struct mlx4_dev *dev, struct mlx4_srq *srq, int *limit_waterm int mlx4_INIT_PORT(struct mlx4_dev *dev, int port); int mlx4_CLOSE_PORT(struct mlx4_dev *dev, int port); -int mlx4_multicast_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16]); +int mlx4_multicast_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16], + int block_mcast_loopback); int mlx4_multicast_detach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16]); int mlx4_map_phys_fmr(struct mlx4_dev *dev, struct mlx4_fmr *fmr, u64 *page_list, -- cgit v1.2.3 From 124cafc5eb973e748c4ce3dc1caad29274e64613 Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Tue, 15 Jul 2008 21:21:44 +0200 Subject: ide: remove ide_init_drive_cmd ide_init_drive_cmd just calls blk_rq_init. This converts the users of ide_init_drive_cmd to use blk_rq_init directly and removes ide_init_drive_cmd. Signed-off-by: FUJITA Tomonori Cc: Borislav Petkov Cc: Jens Axboe Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index eddb6daadf4a..3261c6691759 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -857,8 +857,6 @@ int ide_wait_stat(ide_startstop_t *, ide_drive_t *, u8, u8, unsigned long); extern ide_startstop_t ide_do_reset (ide_drive_t *); -extern void ide_init_drive_cmd (struct request *rq); - /* * "action" parameter type for ide_do_drive_cmd() below. */ -- cgit v1.2.3 From 681a561b7ec7fdcd8f35b68e44ac6d6c70aecc04 Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Tue, 15 Jul 2008 21:21:45 +0200 Subject: block: unexport blk_end_sync_rq All the users of blk_end_sync_rq has gone (they are converted to use blk_execute_rq). This unexports blk_end_sync_rq. Signed-off-by: FUJITA Tomonori Cc: Borislav Petkov Signed-off-by: Jens Axboe Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/blkdev.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d2a1b71e93c3..1171abd7eb17 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -623,7 +623,6 @@ extern void generic_make_request(struct bio *bio); extern void blk_rq_init(struct request_queue *q, struct request *rq); extern void blk_put_request(struct request *); extern void __blk_put_request(struct request_queue *, struct request *); -extern void blk_end_sync_rq(struct request *rq, int error); extern struct request *blk_get_request(struct request_queue *, int, gfp_t); extern void blk_insert_request(struct request_queue *, struct request *, int, void *); extern void blk_requeue_request(struct request_queue *, struct request *); -- cgit v1.2.3 From 30e5ee4d1a651a0c66e86c6612c003034bd20ba2 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Tue, 15 Jul 2008 21:21:46 +0200 Subject: ide: remove obsoleted "idebus=" kernel parameter * Remove obsoleted "idebus=" kernel parameter. * Remove no longer needed ide_system_bus_speed() and system_bus_clock() (together with idebus_parameter and system_bus_speed variables). Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 3261c6691759..dad535659249 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -994,8 +994,6 @@ int ide_taskfile_ioctl(ide_drive_t *, unsigned int, unsigned long); int ide_cmd_ioctl(ide_drive_t *, unsigned int, unsigned long); int ide_task_ioctl(ide_drive_t *, unsigned int, unsigned long); -extern int system_bus_clock(void); - extern int ide_driveid_update(ide_drive_t *); extern int ide_config_drive_speed(ide_drive_t *, u8); extern u8 eighty_ninty_three (ide_drive_t *); -- cgit v1.2.3 From 931ee0dc5c69e8113233d21942681ab8fecde7f9 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Tue, 15 Jul 2008 21:21:47 +0200 Subject: ide: remove obsoleted "ide=" kernel parameters * Remove obsoleted "ide=" kernel parameters. * Remove no longer needed: - ide_setup() - parse_options() - __setup("", ...) - module_param(options, ...) * Use module_{init,exit}() for MODULE=y case and remove MODULE ifdef. * Make ide_*acpi* and ide_doubler variables static. Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index dad535659249..0fa1812d0438 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -813,10 +813,6 @@ int generic_ide_ioctl(ide_drive_t *, struct file *, struct block_device *, unsig #ifndef _IDE_C extern ide_hwif_t ide_hwifs[]; /* master data repository */ #endif -extern int ide_noacpi; -extern int ide_acpigtf; -extern int ide_acpionboot; -extern int noautodma; extern int ide_vlb_clk; extern int ide_pci_clk; -- cgit v1.2.3 From 9a410e79b552bacb4481f85618aa7333b7776ed7 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Tue, 15 Jul 2008 21:21:48 +0200 Subject: ide: remove IDE_TFLAG_NO_SELECT_MASK taskfile flag Always call SELECT_MASK(..., 0) in ide_tf_load() (needs to be done to match ide_set_irq(..., 1)) and then remove IDE_TFLAG_NO_SELECT_MASK taskfile flag. This change should only affect hpt366 and icside host drivers since ->maskproc(..., 0) for sgiioc4 is equivalent to ide_set_irq(..., 1). Cc: Sergei Shtylyov Cc: Russell King Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 0fa1812d0438..d4a910cdb907 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -869,7 +869,6 @@ extern void ide_end_drive_cmd(ide_drive_t *, u8, u8); enum { IDE_TFLAG_LBA48 = (1 << 0), - IDE_TFLAG_NO_SELECT_MASK = (1 << 1), IDE_TFLAG_FLAGGED = (1 << 2), IDE_TFLAG_OUT_DATA = (1 << 3), IDE_TFLAG_OUT_HOB_FEATURE = (1 << 4), -- cgit v1.2.3 From ed4af48fd660176680da905817f6e40d51436e4c Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Tue, 15 Jul 2008 21:21:48 +0200 Subject: ide: move IRQ unmasking out from ->tf_load method Move IRQ unmasking out from ->tf_load method to its users. There should be no functional changes caused by this patch (SELECT_MASK() is NOP except for hpt366, icside and sgiioc4). Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index d4a910cdb907..56d0bc2dffee 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -973,6 +973,7 @@ typedef struct ide_task_s { void ide_tf_dump(const char *, struct ide_taskfile *); extern void SELECT_DRIVE(ide_drive_t *); +void SELECT_MASK(ide_drive_t *, int); extern int drive_is_ready(ide_drive_t *); -- cgit v1.2.3 From 135721446144af005109c25eeacca4fdddcd9a66 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Tue, 15 Jul 2008 21:21:49 +0200 Subject: ide: remove ->mmio flag from ide_hwif_t Since scc_pata host driver no longer uses IDE PCI layer / ide_dma_setup() and all other ->mmio users set also IDE_HFLAG_MMIO host flag we can safely remove ->mmio flag. There should be no functional changes caused by this patch. Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 56d0bc2dffee..b01b102be4de 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -532,7 +532,6 @@ typedef struct hwif_s { unsigned serialized : 1; /* serialized all channel operation */ unsigned sharing_irq: 1; /* 1 = sharing irq with another hwif */ unsigned sg_mapped : 1; /* sg_table and sg_nents are ready */ - unsigned mmio : 1; /* host uses MMIO */ struct device gendev; struct device *portdev; -- cgit v1.2.3 From f8c4bd0ab2b8783c0f080957781e9f70bee48eaa Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Tue, 15 Jul 2008 21:21:49 +0200 Subject: ide: pass 'hwif *' instead of 'drive *' to ->OUTBSYNC method There should be no functional changes caused by this patch. Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index b01b102be4de..1c3431469649 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -493,7 +493,7 @@ typedef struct hwif_s { void (*ide_dma_clear_irq)(ide_drive_t *drive); void (*OUTB)(u8 addr, unsigned long port); - void (*OUTBSYNC)(ide_drive_t *drive, u8 addr, unsigned long port); + void (*OUTBSYNC)(struct hwif_s *hwif, u8 addr, unsigned long port); u8 (*INB)(unsigned long port); -- cgit v1.2.3 From 0fd04dcc2ebb6ec9088c24b368b0ce1f42a98ef5 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Tue, 15 Jul 2008 21:21:50 +0200 Subject: ide: use ->OUTBSYNC in ide_set_irq() Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 1c3431469649..4d1c9714f1d9 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -1340,7 +1340,8 @@ static inline void ide_set_irq(ide_drive_t *drive, int on) { ide_hwif_t *hwif = drive->hwif; - hwif->OUTB(drive->ctl | (on ? 0 : 2), hwif->io_ports.ctl_addr); + hwif->OUTBSYNC(hwif, drive->ctl | (on ? 0 : 2), + hwif->io_ports.ctl_addr); } static inline u8 ide_read_status(ide_drive_t *drive) -- cgit v1.2.3 From ff07488346702f554aaeb6aae982540aa0302373 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Tue, 15 Jul 2008 21:21:50 +0200 Subject: ide: remove drive->ctl Remove drive->ctl (it is always equal to 0x08 after init time). While at it: * Use ATA_DEVCTL_OBS define. There should be no functional changes caused by this patch. Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 4d1c9714f1d9..d8c86f0362c4 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -364,7 +364,6 @@ typedef struct ide_drive_s { u8 wcache; /* status of write cache */ u8 acoustic; /* acoustic management */ u8 media; /* disk, cdrom, tape, floppy, ... */ - u8 ctl; /* "normal" value for Control register */ u8 ready_stat; /* min status value for drive ready */ u8 mult_count; /* current multiple sector setting */ u8 mult_req; /* requested multiple sector setting */ @@ -1340,7 +1339,7 @@ static inline void ide_set_irq(ide_drive_t *drive, int on) { ide_hwif_t *hwif = drive->hwif; - hwif->OUTBSYNC(hwif, drive->ctl | (on ? 0 : 2), + hwif->OUTBSYNC(hwif, ATA_DEVCTL_OBS | (on ? 0 : 2), hwif->io_ports.ctl_addr); } -- cgit v1.2.3 From 63f5abb0959337db0d5bece9cefba03cdcadec51 Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Tue, 15 Jul 2008 21:21:51 +0200 Subject: ide: remove action argument in ide_do_drive_cmd ide_do_drive_cmd is called only with ide_preempt action argument. So we can remove the action argument in ide_do_drive_cmd and ide_action_t typedef. This patch also includes two minor cleanups: 1) ide_do_drive_cmd always succeeds so we don't need the return value; 2) the callers use blk_rq_init before ide_do_drive_cmd so there is no need to initialize rq->errors. Signed-off-by: FUJITA Tomonori Cc: Borislav Petkov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 12 +----------- 1 file changed, 1 insertion(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index d8c86f0362c4..04267dc1edf2 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -851,17 +851,7 @@ int ide_wait_stat(ide_startstop_t *, ide_drive_t *, u8, u8, unsigned long); extern ide_startstop_t ide_do_reset (ide_drive_t *); -/* - * "action" parameter type for ide_do_drive_cmd() below. - */ -typedef enum { - ide_wait, /* insert rq at end of list, and wait for it */ - ide_preempt, /* insert rq in front of current request */ - ide_head_wait, /* insert rq in front of current request and wait for it */ - ide_end /* insert rq at end of list, but don't wait for it */ -} ide_action_t; - -extern int ide_do_drive_cmd(ide_drive_t *, struct request *, ide_action_t); +extern void ide_do_drive_cmd(ide_drive_t *, struct request *); extern void ide_end_drive_cmd(ide_drive_t *, u8, u8); -- cgit v1.2.3 From 92f5daff2b8439fa4c57c57f47823ffc459c3bd9 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Tue, 15 Jul 2008 21:21:55 +0200 Subject: ide-tape: make pc->idetape_callback void There should be no functional changes caused by this patch. Cc: Borislav Petkov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 04267dc1edf2..8936b21a7030 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -641,7 +641,7 @@ struct ide_atapi_pc { */ u8 pc_buf[256]; void (*idefloppy_callback) (ide_drive_t *); - ide_startstop_t (*idetape_callback) (ide_drive_t *); + void (*idetape_callback) (ide_drive_t *); /* idetape only */ struct idetape_bh *bh; -- cgit v1.2.3 From 1b06e92aa03018e4b3ba281e03a7711d9b71a998 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Tue, 15 Jul 2008 21:21:56 +0200 Subject: ide-{floppy,tape}: merge pc->idefloppy_callback and pc->idetape_callback Merge pc->idefloppy_callback and pc->idetape_callback into pc->callback. There should be no functional changes caused by this patch. Cc: Borislav Petkov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 8936b21a7030..f079456adfdb 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -640,8 +640,8 @@ struct ide_atapi_pc { * to change/removal later. */ u8 pc_buf[256]; - void (*idefloppy_callback) (ide_drive_t *); - void (*idetape_callback) (ide_drive_t *); + + void (*callback)(ide_drive_t *); /* idetape only */ struct idetape_bh *bh; -- cgit v1.2.3 From 5e3310958204912f3f00be2592c945fbc37db6ae Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Tue, 15 Jul 2008 21:21:56 +0200 Subject: ide-{floppy,tape}: PC_FLAG_DMA_RECOMMENDED -> PC_FLAG_DMA_OK * Use PC_FLAG_DMA_OK flag instead of PC_FLAG_DMA_RECOMMENDED one. * Remove no longer used PC_FLAG_DMA_RECOMMENDED flag. There should be no functional changes caused by this patch. Cc: Borislav Petkov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index f079456adfdb..63cee2947f60 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -602,12 +602,11 @@ enum { PC_FLAG_SUPPRESS_ERROR = (1 << 1), PC_FLAG_WAIT_FOR_DSC = (1 << 2), PC_FLAG_DMA_OK = (1 << 3), - PC_FLAG_DMA_RECOMMENDED = (1 << 4), - PC_FLAG_DMA_IN_PROGRESS = (1 << 5), - PC_FLAG_DMA_ERROR = (1 << 6), - PC_FLAG_WRITING = (1 << 7), + PC_FLAG_DMA_IN_PROGRESS = (1 << 4), + PC_FLAG_DMA_ERROR = (1 << 5), + PC_FLAG_WRITING = (1 << 6), /* command timed out */ - PC_FLAG_TIMEDOUT = (1 << 8), + PC_FLAG_TIMEDOUT = (1 << 7), }; struct ide_atapi_pc { -- cgit v1.2.3 From 5d41893c0f9caf94b449eada0279a08c86f0212e Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Tue, 15 Jul 2008 21:21:57 +0200 Subject: ide: add PC_FLAG_ZIP_DRIVE pc flag Add PC_FLAG_ZIP_DRIVE pc flag, set it in idefloppy_do_request() and check for it (instead of checking for IDEFLOPPY_FLAG_ZIP_DRIVE) in idefloppy_transfer_pc(). This is a preparation for adding generic ide_transfer_pc() helper. There should be no functional changes caused by this patch. Cc: Borislav Petkov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 63cee2947f60..89feaea9e20b 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -607,6 +607,7 @@ enum { PC_FLAG_WRITING = (1 << 6), /* command timed out */ PC_FLAG_TIMEDOUT = (1 << 7), + PC_FLAG_ZIP_DRIVE = (1 << 8), }; struct ide_atapi_pc { -- cgit v1.2.3 From 594c16d8dd54cd7b1c5ef1ec3ac0f6bf34301dad Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Tue, 15 Jul 2008 21:21:58 +0200 Subject: ide: add ide_transfer_pc() helper * Add ide-atapi.c file for generic ATAPI support together with CONFIG_IDE_ATAPI config option. * Add generic ide_transfer_pc() helper to ide-atapi.c and then convert ide-{floppy,tape,scsi} device drivers to use it. There should be no functional changes caused by this patch. Cc: Borislav Petkov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 89feaea9e20b..bed3c58798ae 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -967,6 +967,9 @@ extern int drive_is_ready(ide_drive_t *); void ide_pktcmd_tf_load(ide_drive_t *, u32, u16, u8); +ide_startstop_t ide_transfer_pc(ide_drive_t *, struct ide_atapi_pc *, + ide_handler_t *, unsigned int, ide_expiry_t *); + ide_startstop_t do_rw_taskfile(ide_drive_t *, ide_task_t *); void task_end_request(ide_drive_t *, struct request *, u8); -- cgit v1.2.3 From 28c7214bd8c2bbd4873b8f1e7f58d86d3731124f Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Tue, 15 Jul 2008 21:21:59 +0200 Subject: ide: add PC_FLAG_DRQ_INTERRUPT pc flag Add PC_FLAG_DRQ_INTERRUPT pc flag, set it in ide*_do_request() and check for it (instead of checking for IDE*_FLAG_DRQ_INTERRUPT) in ide*_issue_pc(). This is a preparation for adding generic ide_issue_pc() helper. There should be no functional changes caused by this patch. Cc: Borislav Petkov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index bed3c58798ae..c2274ad44b2e 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -608,6 +608,7 @@ enum { /* command timed out */ PC_FLAG_TIMEDOUT = (1 << 7), PC_FLAG_ZIP_DRIVE = (1 << 8), + PC_FLAG_DRQ_INTERRUPT = (1 << 9), }; struct ide_atapi_pc { -- cgit v1.2.3 From 6bf1641ca1c7554f0da54aaf89788731b541bacc Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Tue, 15 Jul 2008 21:22:00 +0200 Subject: ide: add ide_issue_pc() helper Add generic ide_issue_pc() helper to ide-atapi.c and then convert ide-{floppy,tape,scsi} device drivers to use it. There should be no functional changes caused by this patch. Cc: Borislav Petkov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index c2274ad44b2e..fee07a7edb19 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -970,6 +970,8 @@ void ide_pktcmd_tf_load(ide_drive_t *, u32, u16, u8); ide_startstop_t ide_transfer_pc(ide_drive_t *, struct ide_atapi_pc *, ide_handler_t *, unsigned int, ide_expiry_t *); +ide_startstop_t ide_issue_pc(ide_drive_t *, struct ide_atapi_pc *, + ide_handler_t *, unsigned int, ide_expiry_t *); ide_startstop_t do_rw_taskfile(ide_drive_t *, ide_task_t *); -- cgit v1.2.3 From 646c0cb6c430f8d3ad3769dd1518fe664ff0ce27 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Tue, 15 Jul 2008 21:22:03 +0200 Subject: ide: add ide_pc_intr() helper * ide-tape.c: add 'drive' argument to idetape_update_buffers(). * Add generic ide_pc_intr() helper to ide-atapi.c and then convert ide-{floppy,tape,scsi} device drivers to use it. * ide-tape.c: remove no longer needed DBG_PC_INTR. There should be no functional changes caused by this patch (unless the debugging is explicitely compiled in). Cc: Borislav Petkov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index fee07a7edb19..ac4eeb2932ef 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -968,6 +968,12 @@ extern int drive_is_ready(ide_drive_t *); void ide_pktcmd_tf_load(ide_drive_t *, u32, u16, u8); +ide_startstop_t ide_pc_intr(ide_drive_t *drive, struct ide_atapi_pc *pc, + ide_handler_t *handler, unsigned int timeout, ide_expiry_t *expiry, + void (*update_buffers)(ide_drive_t *, struct ide_atapi_pc *), + void (*retry_pc)(ide_drive_t *), void (*dsc_handle)(ide_drive_t *), + void (*io_buffers)(ide_drive_t *, struct ide_atapi_pc *, unsigned int, + int)); ide_startstop_t ide_transfer_pc(ide_drive_t *, struct ide_atapi_pc *, ide_handler_t *, unsigned int, ide_expiry_t *); ide_startstop_t ide_issue_pc(ide_drive_t *, struct ide_atapi_pc *, -- cgit v1.2.3