X-Git-Url: https://git.openpandora.org/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=kernel%2Fpid.c;h=b914392085f9a171f08a3e202dc14145e1563929;hb=5a3e3b2230980cf2ce6e5e56b816dde19b993939;hp=93e212f20671fd3b19838327366c45e3ad54ced8;hpb=5e66dd6d66ffe758b39b6dcadf2330753ee1159b;p=pandora-kernel.git diff --git a/kernel/pid.c b/kernel/pid.c index 93e212f20671..b914392085f9 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -26,6 +26,7 @@ #include #include #include +#include #define pid_hashfn(nr) hash_long((unsigned long)nr, pidhash_shift) static struct hlist_head *pid_hash; @@ -33,17 +34,20 @@ static int pidhash_shift; static kmem_cache_t *pid_cachep; int pid_max = PID_MAX_DEFAULT; -int last_pid; #define RESERVED_PIDS 300 int pid_max_min = RESERVED_PIDS + 1; int pid_max_max = PID_MAX_LIMIT; -#define PIDMAP_ENTRIES ((PID_MAX_LIMIT + 8*PAGE_SIZE - 1)/PAGE_SIZE/8) #define BITS_PER_PAGE (PAGE_SIZE*8) #define BITS_PER_PAGE_MASK (BITS_PER_PAGE-1) -#define mk_pid(map, off) (((map) - pidmap_array)*BITS_PER_PAGE + (off)) + +static inline int mk_pid(struct pspace *pspace, struct pidmap *map, int off) +{ + return (map - pspace->pidmap)*BITS_PER_PAGE + off; +} + #define find_next_offset(map, off) \ find_next_zero_bit((map)->page, BITS_PER_PAGE, off) @@ -53,13 +57,12 @@ int pid_max_max = PID_MAX_LIMIT; * value does not cause lots of bitmaps to be allocated, but * the scheme scales to up to 4 million PIDs, runtime. */ -typedef struct pidmap { - atomic_t nr_free; - void *page; -} pidmap_t; - -static pidmap_t pidmap_array[PIDMAP_ENTRIES] = - { [ 0 ... PIDMAP_ENTRIES-1 ] = { ATOMIC_INIT(BITS_PER_PAGE), NULL } }; +struct pspace init_pspace = { + .pidmap = { + [ 0 ... PIDMAP_ENTRIES-1] = { ATOMIC_INIT(BITS_PER_PAGE), NULL } + }, + .last_pid = 0 +}; /* * Note: disable interrupts while the pidmap_lock is held as an @@ -74,40 +77,41 @@ static pidmap_t pidmap_array[PIDMAP_ENTRIES] = * irq handlers that take it we can leave the interrupts enabled. * For now it is easier to be safe than to prove it can't happen. */ + static __cacheline_aligned_in_smp DEFINE_SPINLOCK(pidmap_lock); -static fastcall void free_pidmap(int pid) +static fastcall void free_pidmap(struct pspace *pspace, int pid) { - pidmap_t *map = pidmap_array + pid / BITS_PER_PAGE; + struct pidmap *map = pspace->pidmap + pid / BITS_PER_PAGE; int offset = pid & BITS_PER_PAGE_MASK; clear_bit(offset, map->page); atomic_inc(&map->nr_free); } -static int alloc_pidmap(void) +static int alloc_pidmap(struct pspace *pspace) { - int i, offset, max_scan, pid, last = last_pid; - pidmap_t *map; + int i, offset, max_scan, pid, last = pspace->last_pid; + struct pidmap *map; pid = last + 1; if (pid >= pid_max) pid = RESERVED_PIDS; offset = pid & BITS_PER_PAGE_MASK; - map = &pidmap_array[pid/BITS_PER_PAGE]; + map = &pspace->pidmap[pid/BITS_PER_PAGE]; max_scan = (pid_max + BITS_PER_PAGE - 1)/BITS_PER_PAGE - !offset; for (i = 0; i <= max_scan; ++i) { if (unlikely(!map->page)) { - unsigned long page = get_zeroed_page(GFP_KERNEL); + void *page = kzalloc(PAGE_SIZE, GFP_KERNEL); /* * Free the page if someone raced with us * installing it: */ spin_lock_irq(&pidmap_lock); if (map->page) - free_page(page); + kfree(page); else - map->page = (void *)page; + map->page = page; spin_unlock_irq(&pidmap_lock); if (unlikely(!map->page)) break; @@ -116,11 +120,11 @@ static int alloc_pidmap(void) do { if (!test_and_set_bit(offset, map->page)) { atomic_dec(&map->nr_free); - last_pid = pid; + pspace->last_pid = pid; return pid; } offset = find_next_offset(map, offset); - pid = mk_pid(map, offset); + pid = mk_pid(pspace, map, offset); /* * find_next_offset() found a bit, the pid from it * is in-bounds, and if we fell back to the last @@ -131,16 +135,34 @@ static int alloc_pidmap(void) (i != max_scan || pid < last || !((last+1) & BITS_PER_PAGE_MASK))); } - if (map < &pidmap_array[(pid_max-1)/BITS_PER_PAGE]) { + if (map < &pspace->pidmap[(pid_max-1)/BITS_PER_PAGE]) { ++map; offset = 0; } else { - map = &pidmap_array[0]; + map = &pspace->pidmap[0]; offset = RESERVED_PIDS; if (unlikely(last == offset)) break; } - pid = mk_pid(map, offset); + pid = mk_pid(pspace, map, offset); + } + return -1; +} + +static int next_pidmap(struct pspace *pspace, int last) +{ + int offset; + struct pidmap *map, *end; + + offset = (last + 1) & BITS_PER_PAGE_MASK; + map = &pspace->pidmap[(last + 1)/BITS_PER_PAGE]; + end = &pspace->pidmap[PIDMAP_ENTRIES]; + for (; map < end; map++, offset = 0) { + if (unlikely(!map->page)) + continue; + offset = find_next_bit((map)->page, BITS_PER_PAGE, offset); + if (offset < BITS_PER_PAGE) + return mk_pid(pspace, map, offset); } return -1; } @@ -153,6 +175,7 @@ fastcall void put_pid(struct pid *pid) atomic_dec_and_test(&pid->count)) kmem_cache_free(pid_cachep, pid); } +EXPORT_SYMBOL_GPL(put_pid); static void delayed_put_pid(struct rcu_head *rhp) { @@ -169,7 +192,7 @@ fastcall void free_pid(struct pid *pid) hlist_del_rcu(&pid->pid_chain); spin_unlock_irqrestore(&pidmap_lock, flags); - free_pidmap(pid->nr); + free_pidmap(&init_pspace, pid->nr); call_rcu(&pid->rcu, delayed_put_pid); } @@ -183,7 +206,7 @@ struct pid *alloc_pid(void) if (!pid) goto out; - nr = alloc_pidmap(); + nr = alloc_pidmap(&init_pspace); if (nr < 0) goto out_free; @@ -217,15 +240,13 @@ struct pid * fastcall find_pid(int nr) } return NULL; } +EXPORT_SYMBOL_GPL(find_pid); int fastcall attach_pid(struct task_struct *task, enum pid_type type, int nr) { struct pid_link *link; struct pid *pid; - WARN_ON(!task->pid); /* to be removed soon */ - WARN_ON(!nr); /* to be removed soon */ - link = &task->pids[type]; link->pid = pid = find_pid(nr); hlist_add_head_rcu(&link->node, &pid->tasks[type]); @@ -252,6 +273,15 @@ void fastcall detach_pid(struct task_struct *task, enum pid_type type) free_pid(pid); } +/* transfer_pid is an optimization of attach_pid(new), detach_pid(old) */ +void fastcall transfer_pid(struct task_struct *old, struct task_struct *new, + enum pid_type type) +{ + new->pids[type].pid = old->pids[type].pid; + hlist_replace_rcu(&old->pids[type].node, &new->pids[type].node); + old->pids[type].pid = NULL; +} + struct task_struct * fastcall pid_task(struct pid *pid, enum pid_type type) { struct task_struct *result = NULL; @@ -274,6 +304,15 @@ struct task_struct *find_task_by_pid_type(int type, int nr) EXPORT_SYMBOL(find_task_by_pid_type); +struct pid *get_task_pid(struct task_struct *task, enum pid_type type) +{ + struct pid *pid; + rcu_read_lock(); + pid = get_pid(task->pids[type].pid); + rcu_read_unlock(); + return pid; +} + struct task_struct *fastcall get_pid_task(struct pid *pid, enum pid_type type) { struct task_struct *result; @@ -296,6 +335,26 @@ struct pid *find_get_pid(pid_t nr) return pid; } +/* + * Used by proc to find the first pid that is greater then or equal to nr. + * + * If there is a pid at nr this function is exactly the same as find_pid. + */ +struct pid *find_ge_pid(int nr) +{ + struct pid *pid; + + do { + pid = find_pid(nr); + if (pid) + break; + nr = next_pidmap(&init_pspace, nr); + } while (nr > 0); + + return pid; +} +EXPORT_SYMBOL_GPL(find_get_pid); + /* * The pid hash table is scaled according to the amount of memory in the * machine. From a minimum of 16 slots up to 4096 slots at one gigabyte or @@ -323,10 +382,10 @@ void __init pidhash_init(void) void __init pidmap_init(void) { - pidmap_array->page = (void *)get_zeroed_page(GFP_KERNEL); + init_pspace.pidmap[0].page = kzalloc(PAGE_SIZE, GFP_KERNEL); /* Reserve PID 0. We never call free_pidmap(0) */ - set_bit(0, pidmap_array->page); - atomic_dec(&pidmap_array->nr_free); + set_bit(0, init_pspace.pidmap[0].page); + atomic_dec(&init_pspace.pidmap[0].nr_free); pid_cachep = kmem_cache_create("pid", sizeof(struct pid), __alignof__(struct pid),