From 36d8593ec74dc04d3bd7c1c897a7b7cfbd0b0dc6 Mon Sep 17 00:00:00 2001 From: Russell King - ARM Linux Date: Sat, 19 Feb 2011 15:34:50 +0000 Subject: Make clocksource name const As nothing should be writing to the clocksource name string, make the clocksource name pointer const. Build-tested on ARM Versatile Express. Signed-off-by: Russell King Signed-off-by: John Stultz --- include/linux/clocksource.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index c37b21ad5a3..94c1f38e922 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -161,7 +161,7 @@ struct clocksource { /* * First part of structure is read mostly */ - char *name; + const char *name; struct list_head list; int rating; cycle_t (*read)(struct clocksource *cs); -- cgit v1.2.3-70-g09d2 From d430d3d7e646eb1eac2bb4aa244a644312e67c76 Mon Sep 17 00:00:00 2001 From: Jason Baron Date: Wed, 16 Mar 2011 17:29:47 -0400 Subject: jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron Suggested-by: H. Peter Anvin Tested-by: David Daney Acked-by: Ralf Baechle Acked-by: David S. Miller Acked-by: Mathieu Desnoyers Signed-off-by: Steven Rostedt --- arch/mips/include/asm/jump_label.h | 22 +- arch/sparc/include/asm/jump_label.h | 25 +- arch/x86/include/asm/alternative.h | 3 +- arch/x86/include/asm/jump_label.h | 26 +- arch/x86/kernel/alternative.c | 2 +- arch/x86/kernel/module.c | 1 + include/asm-generic/vmlinux.lds.h | 14 +- include/linux/dynamic_debug.h | 2 - include/linux/jump_label.h | 89 +++--- include/linux/jump_label_ref.h | 44 --- include/linux/perf_event.h | 26 +- include/linux/tracepoint.h | 22 +- kernel/jump_label.c | 539 +++++++++++++++--------------------- kernel/perf_event.c | 4 +- kernel/tracepoint.c | 23 +- 15 files changed, 356 insertions(+), 486 deletions(-) delete mode 100644 include/linux/jump_label_ref.h (limited to 'include') diff --git a/arch/mips/include/asm/jump_label.h b/arch/mips/include/asm/jump_label.h index 7622ccf7507..1881b316ca4 100644 --- a/arch/mips/include/asm/jump_label.h +++ b/arch/mips/include/asm/jump_label.h @@ -20,16 +20,18 @@ #define WORD_INSN ".word" #endif -#define JUMP_LABEL(key, label) \ - do { \ - asm goto("1:\tnop\n\t" \ - "nop\n\t" \ - ".pushsection __jump_table, \"a\"\n\t" \ - WORD_INSN " 1b, %l[" #label "], %0\n\t" \ - ".popsection\n\t" \ - : : "i" (key) : : label); \ - } while (0) - +static __always_inline bool arch_static_branch(struct jump_label_key *key) +{ + asm goto("1:\tnop\n\t" + "nop\n\t" + ".pushsection __jump_table, \"aw\"\n\t" + WORD_INSN " 1b, %l[l_yes], %0\n\t" + ".popsection\n\t" + : : "i" (key) : : l_yes); + return false; +l_yes: + return true; +} #endif /* __KERNEL__ */ diff --git a/arch/sparc/include/asm/jump_label.h b/arch/sparc/include/asm/jump_label.h index 427d4684e0d..fc73a82366f 100644 --- a/arch/sparc/include/asm/jump_label.h +++ b/arch/sparc/include/asm/jump_label.h @@ -7,17 +7,20 @@ #define JUMP_LABEL_NOP_SIZE 4 -#define JUMP_LABEL(key, label) \ - do { \ - asm goto("1:\n\t" \ - "nop\n\t" \ - "nop\n\t" \ - ".pushsection __jump_table, \"a\"\n\t"\ - ".align 4\n\t" \ - ".word 1b, %l[" #label "], %c0\n\t" \ - ".popsection \n\t" \ - : : "i" (key) : : label);\ - } while (0) +static __always_inline bool arch_static_branch(struct jump_label_key *key) +{ + asm goto("1:\n\t" + "nop\n\t" + "nop\n\t" + ".pushsection __jump_table, \"aw\"\n\t" + ".align 4\n\t" + ".word 1b, %l[l_yes], %c0\n\t" + ".popsection \n\t" + : : "i" (key) : : l_yes); + return false; +l_yes: + return true; +} #endif /* __KERNEL__ */ diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index 13009d1af99..8cdd1e24797 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -4,7 +4,6 @@ #include #include #include -#include #include /* @@ -191,7 +190,7 @@ extern void *text_poke(void *addr, const void *opcode, size_t len); extern void *text_poke_smp(void *addr, const void *opcode, size_t len); extern void text_poke_smp_batch(struct text_poke_param *params, int n); -#if defined(CONFIG_DYNAMIC_FTRACE) || defined(HAVE_JUMP_LABEL) +#if defined(CONFIG_DYNAMIC_FTRACE) || defined(CONFIG_JUMP_LABEL) #define IDEAL_NOP_SIZE_5 5 extern unsigned char ideal_nop5[IDEAL_NOP_SIZE_5]; extern void arch_init_ideal_nop5(void); diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h index 574dbc22893..f217cee8653 100644 --- a/arch/x86/include/asm/jump_label.h +++ b/arch/x86/include/asm/jump_label.h @@ -5,20 +5,24 @@ #include #include +#include #define JUMP_LABEL_NOP_SIZE 5 -# define JUMP_LABEL_INITIAL_NOP ".byte 0xe9 \n\t .long 0\n\t" - -# define JUMP_LABEL(key, label) \ - do { \ - asm goto("1:" \ - JUMP_LABEL_INITIAL_NOP \ - ".pushsection __jump_table, \"aw\" \n\t"\ - _ASM_PTR "1b, %l[" #label "], %c0 \n\t" \ - ".popsection \n\t" \ - : : "i" (key) : : label); \ - } while (0) +#define JUMP_LABEL_INITIAL_NOP ".byte 0xe9 \n\t .long 0\n\t" + +static __always_inline bool arch_static_branch(struct jump_label_key *key) +{ + asm goto("1:" + JUMP_LABEL_INITIAL_NOP + ".pushsection __jump_table, \"aw\" \n\t" + _ASM_PTR "1b, %l[l_yes], %c0 \n\t" + ".popsection \n\t" + : : "i" (key) : : l_yes); + return false; +l_yes: + return true; +} #endif /* __KERNEL__ */ diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 4a234677e21..651454b0c81 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -679,7 +679,7 @@ void __kprobes text_poke_smp_batch(struct text_poke_param *params, int n) __stop_machine(stop_machine_text_poke, (void *)&tpp, NULL); } -#if defined(CONFIG_DYNAMIC_FTRACE) || defined(HAVE_JUMP_LABEL) +#if defined(CONFIG_DYNAMIC_FTRACE) || defined(CONFIG_JUMP_LABEL) #ifdef CONFIG_X86_64 unsigned char ideal_nop5[5] = { 0x66, 0x66, 0x66, 0x66, 0x90 }; diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index ab23f1ad4bf..52f256f2cc8 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 32c45e5fe0a..79522166d7f 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -170,6 +170,10 @@ STRUCT_ALIGN(); \ *(__tracepoints) \ /* implement dynamic printk debug */ \ + . = ALIGN(8); \ + VMLINUX_SYMBOL(__start___jump_table) = .; \ + *(__jump_table) \ + VMLINUX_SYMBOL(__stop___jump_table) = .; \ . = ALIGN(8); \ VMLINUX_SYMBOL(__start___verbose) = .; \ *(__verbose) \ @@ -228,8 +232,6 @@ \ BUG_TABLE \ \ - JUMP_TABLE \ - \ /* PCI quirks */ \ .pci_fixup : AT(ADDR(.pci_fixup) - LOAD_OFFSET) { \ VMLINUX_SYMBOL(__start_pci_fixups_early) = .; \ @@ -589,14 +591,6 @@ #define BUG_TABLE #endif -#define JUMP_TABLE \ - . = ALIGN(8); \ - __jump_table : AT(ADDR(__jump_table) - LOAD_OFFSET) { \ - VMLINUX_SYMBOL(__start___jump_table) = .; \ - *(__jump_table) \ - VMLINUX_SYMBOL(__stop___jump_table) = .; \ - } - #ifdef CONFIG_PM_TRACE #define TRACEDATA \ . = ALIGN(4); \ diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h index 0c9653f11c1..e747ecd48e1 100644 --- a/include/linux/dynamic_debug.h +++ b/include/linux/dynamic_debug.h @@ -1,8 +1,6 @@ #ifndef _DYNAMIC_DEBUG_H #define _DYNAMIC_DEBUG_H -#include - /* dynamic_printk_enabled, and dynamic_printk_enabled2 are bitmasks in which * bit n is set to 1 if any modname hashes into the bucket n, 0 otherwise. They * use independent hash functions, to reduce the chance of false positives. diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index 7880f18e4b8..83e745f3ead 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -1,20 +1,43 @@ #ifndef _LINUX_JUMP_LABEL_H #define _LINUX_JUMP_LABEL_H +#include +#include + #if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_JUMP_LABEL) + +struct jump_label_key { + atomic_t enabled; + struct jump_entry *entries; +#ifdef CONFIG_MODULES + struct jump_label_mod *next; +#endif +}; + # include # define HAVE_JUMP_LABEL #endif enum jump_label_type { + JUMP_LABEL_DISABLE = 0, JUMP_LABEL_ENABLE, - JUMP_LABEL_DISABLE }; struct module; #ifdef HAVE_JUMP_LABEL +#ifdef CONFIG_MODULES +#define JUMP_LABEL_INIT {{ 0 }, NULL, NULL} +#else +#define JUMP_LABEL_INIT {{ 0 }, NULL} +#endif + +static __always_inline bool static_branch(struct jump_label_key *key) +{ + return arch_static_branch(key); +} + extern struct jump_entry __start___jump_table[]; extern struct jump_entry __stop___jump_table[]; @@ -23,37 +46,37 @@ extern void jump_label_unlock(void); extern void arch_jump_label_transform(struct jump_entry *entry, enum jump_label_type type); extern void arch_jump_label_text_poke_early(jump_label_t addr); -extern void jump_label_update(unsigned long key, enum jump_label_type type); -extern void jump_label_apply_nops(struct module *mod); extern int jump_label_text_reserved(void *start, void *end); +extern void jump_label_inc(struct jump_label_key *key); +extern void jump_label_dec(struct jump_label_key *key); +extern bool jump_label_enabled(struct jump_label_key *key); +extern void jump_label_apply_nops(struct module *mod); -#define jump_label_enable(key) \ - jump_label_update((unsigned long)key, JUMP_LABEL_ENABLE); +#else -#define jump_label_disable(key) \ - jump_label_update((unsigned long)key, JUMP_LABEL_DISABLE); +#include -#else +#define JUMP_LABEL_INIT {ATOMIC_INIT(0)} -#define JUMP_LABEL(key, label) \ -do { \ - if (unlikely(*key)) \ - goto label; \ -} while (0) +struct jump_label_key { + atomic_t enabled; +}; -#define jump_label_enable(cond_var) \ -do { \ - *(cond_var) = 1; \ -} while (0) +static __always_inline bool static_branch(struct jump_label_key *key) +{ + if (unlikely(atomic_read(&key->enabled))) + return true; + return false; +} -#define jump_label_disable(cond_var) \ -do { \ - *(cond_var) = 0; \ -} while (0) +static inline void jump_label_inc(struct jump_label_key *key) +{ + atomic_inc(&key->enabled); +} -static inline int jump_label_apply_nops(struct module *mod) +static inline void jump_label_dec(struct jump_label_key *key) { - return 0; + atomic_dec(&key->enabled); } static inline int jump_label_text_reserved(void *start, void *end) @@ -64,16 +87,16 @@ static inline int jump_label_text_reserved(void *start, void *end) static inline void jump_label_lock(void) {} static inline void jump_label_unlock(void) {} -#endif +static inline bool jump_label_enabled(struct jump_label_key *key) +{ + return !!atomic_read(&key->enabled); +} -#define COND_STMT(key, stmt) \ -do { \ - __label__ jl_enabled; \ - JUMP_LABEL(key, jl_enabled); \ - if (0) { \ -jl_enabled: \ - stmt; \ - } \ -} while (0) +static inline int jump_label_apply_nops(struct module *mod) +{ + return 0; +} + +#endif #endif diff --git a/include/linux/jump_label_ref.h b/include/linux/jump_label_ref.h deleted file mode 100644 index e5d012ad92c..00000000000 --- a/include/linux/jump_label_ref.h +++ /dev/null @@ -1,44 +0,0 @@ -#ifndef _LINUX_JUMP_LABEL_REF_H -#define _LINUX_JUMP_LABEL_REF_H - -#include -#include - -#ifdef HAVE_JUMP_LABEL - -static inline void jump_label_inc(atomic_t *key) -{ - if (atomic_add_return(1, key) == 1) - jump_label_enable(key); -} - -static inline void jump_label_dec(atomic_t *key) -{ - if (atomic_dec_and_test(key)) - jump_label_disable(key); -} - -#else /* !HAVE_JUMP_LABEL */ - -static inline void jump_label_inc(atomic_t *key) -{ - atomic_inc(key); -} - -static inline void jump_label_dec(atomic_t *key) -{ - atomic_dec(key); -} - -#undef JUMP_LABEL -#define JUMP_LABEL(key, label) \ -do { \ - if (unlikely(__builtin_choose_expr( \ - __builtin_types_compatible_p(typeof(key), atomic_t *), \ - atomic_read((atomic_t *)(key)), *(key)))) \ - goto label; \ -} while (0) - -#endif /* HAVE_JUMP_LABEL */ - -#endif /* _LINUX_JUMP_LABEL_REF_H */ diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 311b4dc785a..730b7821690 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -505,7 +505,7 @@ struct perf_guest_info_callbacks { #include #include #include -#include +#include #include #include @@ -1034,7 +1034,7 @@ static inline int is_software_event(struct perf_event *event) return event->pmu->task_ctx_nr == perf_sw_context; } -extern atomic_t perf_swevent_enabled[PERF_COUNT_SW_MAX]; +extern struct jump_label_key perf_swevent_enabled[PERF_COUNT_SW_MAX]; extern void __perf_sw_event(u32, u64, int, struct pt_regs *, u64); @@ -1063,22 +1063,21 @@ perf_sw_event(u32 event_id, u64 nr, int nmi, struct pt_regs *regs, u64 addr) { struct pt_regs hot_regs; - JUMP_LABEL(&perf_swevent_enabled[event_id], have_event); - return; - -have_event: - if (!regs) { - perf_fetch_caller_regs(&hot_regs); - regs = &hot_regs; + if (static_branch(&perf_swevent_enabled[event_id])) { + if (!regs) { + perf_fetch_caller_regs(&hot_regs); + regs = &hot_regs; + } + __perf_sw_event(event_id, nr, nmi, regs, addr); } - __perf_sw_event(event_id, nr, nmi, regs, addr); } -extern atomic_t perf_sched_events; +extern struct jump_label_key perf_sched_events; static inline void perf_event_task_sched_in(struct task_struct *task) { - COND_STMT(&perf_sched_events, __perf_event_task_sched_in(task)); + if (static_branch(&perf_sched_events)) + __perf_event_task_sched_in(task); } static inline @@ -1086,7 +1085,8 @@ void perf_event_task_sched_out(struct task_struct *task, struct task_struct *nex { perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 1, NULL, 0); - COND_STMT(&perf_sched_events, __perf_event_task_sched_out(task, next)); + if (static_branch(&perf_sched_events)) + __perf_event_task_sched_out(task, next); } extern void perf_event_mmap(struct vm_area_struct *vma); diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 97c84a58efb..d530a4460a0 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -29,7 +29,7 @@ struct tracepoint_func { struct tracepoint { const char *name; /* Tracepoint name */ - int state; /* State. */ + struct jump_label_key key; void (*regfunc)(void); void (*unregfunc)(void); struct tracepoint_func __rcu *funcs; @@ -146,9 +146,7 @@ void tracepoint_update_probe_range(struct tracepoint * const *begin, extern struct tracepoint __tracepoint_##name; \ static inline void trace_##name(proto) \ { \ - JUMP_LABEL(&__tracepoint_##name.state, do_trace); \ - return; \ -do_trace: \ + if (static_branch(&__tracepoint_##name.key)) \ __DO_TRACE(&__tracepoint_##name, \ TP_PROTO(data_proto), \ TP_ARGS(data_args), \ @@ -176,14 +174,14 @@ do_trace: \ * structures, so we create an array of pointers that will be used for iteration * on the tracepoints. */ -#define DEFINE_TRACE_FN(name, reg, unreg) \ - static const char __tpstrtab_##name[] \ - __attribute__((section("__tracepoints_strings"))) = #name; \ - struct tracepoint __tracepoint_##name \ - __attribute__((section("__tracepoints"))) = \ - { __tpstrtab_##name, 0, reg, unreg, NULL }; \ - static struct tracepoint * const __tracepoint_ptr_##name __used \ - __attribute__((section("__tracepoints_ptrs"))) = \ +#define DEFINE_TRACE_FN(name, reg, unreg) \ + static const char __tpstrtab_##name[] \ + __attribute__((section("__tracepoints_strings"))) = #name; \ + struct tracepoint __tracepoint_##name \ + __attribute__((section("__tracepoints"))) = \ + { __tpstrtab_##name, JUMP_LABEL_INIT, reg, unreg, NULL };\ + static struct tracepoint * const __tracepoint_ptr_##name __used \ + __attribute__((section("__tracepoints_ptrs"))) = \ &__tracepoint_##name; #define DEFINE_TRACE(name) \ diff --git a/kernel/jump_label.c b/kernel/jump_label.c index 3b79bd93833..74d1c099fbd 100644 --- a/kernel/jump_label.c +++ b/kernel/jump_label.c @@ -2,43 +2,23 @@ * jump label support * * Copyright (C) 2009 Jason Baron + * Copyright (C) 2011 Peter Zijlstra * */ -#include #include #include #include #include -#include #include #include #include +#include #ifdef HAVE_JUMP_LABEL -#define JUMP_LABEL_HASH_BITS 6 -#define JUMP_LABEL_TABLE_SIZE (1 << JUMP_LABEL_HASH_BITS) -static struct hlist_head jump_label_table[JUMP_LABEL_TABLE_SIZE]; - /* mutex to protect coming/going of the the jump_label table */ static DEFINE_MUTEX(jump_label_mutex); -struct jump_label_entry { - struct hlist_node hlist; - struct jump_entry *table; - int nr_entries; - /* hang modules off here */ - struct hlist_head modules; - unsigned long key; -}; - -struct jump_label_module_entry { - struct hlist_node hlist; - struct jump_entry *table; - int nr_entries; - struct module *mod; -}; - void jump_label_lock(void) { mutex_lock(&jump_label_mutex); @@ -49,6 +29,11 @@ void jump_label_unlock(void) mutex_unlock(&jump_label_mutex); } +bool jump_label_enabled(struct jump_label_key *key) +{ + return !!atomic_read(&key->enabled); +} + static int jump_label_cmp(const void *a, const void *b) { const struct jump_entry *jea = a; @@ -64,7 +49,7 @@ static int jump_label_cmp(const void *a, const void *b) } static void -sort_jump_label_entries(struct jump_entry *start, struct jump_entry *stop) +jump_label_sort_entries(struct jump_entry *start, struct jump_entry *stop) { unsigned long size; @@ -73,118 +58,25 @@ sort_jump_label_entries(struct jump_entry *start, struct jump_entry *stop) sort(start, size, sizeof(struct jump_entry), jump_label_cmp, NULL); } -static struct jump_label_entry *get_jump_label_entry(jump_label_t key) -{ - struct hlist_head *head; - struct hlist_node *node; - struct jump_label_entry *e; - u32 hash = jhash((void *)&key, sizeof(jump_label_t), 0); - - head = &jump_label_table[hash & (JUMP_LABEL_TABLE_SIZE - 1)]; - hlist_for_each_entry(e, node, head, hlist) { - if (key == e->key) - return e; - } - return NULL; -} +static void jump_label_update(struct jump_label_key *key, int enable); -static struct jump_label_entry * -add_jump_label_entry(jump_label_t key, int nr_entries, struct jump_entry *table) +void jump_label_inc(struct jump_label_key *key) { - struct hlist_head *head; - struct jump_label_entry *e; - u32 hash; - - e = get_jump_label_entry(key); - if (e) - return ERR_PTR(-EEXIST); - - e = kmalloc(sizeof(struct jump_label_entry), GFP_KERNEL); - if (!e) - return ERR_PTR(-ENOMEM); - - hash = jhash((void *)&key, sizeof(jump_label_t), 0); - head = &jump_label_table[hash & (JUMP_LABEL_TABLE_SIZE - 1)]; - e->key = key; - e->table = table; - e->nr_entries = nr_entries; - INIT_HLIST_HEAD(&(e->modules)); - hlist_add_head(&e->hlist, head); - return e; -} + if (atomic_inc_not_zero(&key->enabled)) + return; -static int -build_jump_label_hashtable(struct jump_entry *start, struct jump_entry *stop) -{ - struct jump_entry *iter, *iter_begin; - struct jump_label_entry *entry; - int count; - - sort_jump_label_entries(start, stop); - iter = start; - while (iter < stop) { - entry = get_jump_label_entry(iter->key); - if (!entry) { - iter_begin = iter; - count = 0; - while ((iter < stop) && - (iter->key == iter_begin->key)) { - iter++; - count++; - } - entry = add_jump_label_entry(iter_begin->key, - count, iter_begin); - if (IS_ERR(entry)) - return PTR_ERR(entry); - } else { - WARN_ONCE(1, KERN_ERR "build_jump_hashtable: unexpected entry!\n"); - return -1; - } - } - return 0; + jump_label_lock(); + if (atomic_add_return(1, &key->enabled) == 1) + jump_label_update(key, JUMP_LABEL_ENABLE); + jump_label_unlock(); } -/*** - * jump_label_update - update jump label text - * @key - key value associated with a a jump label - * @type - enum set to JUMP_LABEL_ENABLE or JUMP_LABEL_DISABLE - * - * Will enable/disable the jump for jump label @key, depending on the - * value of @type. - * - */ - -void jump_label_update(unsigned long key, enum jump_label_type type) +void jump_label_dec(struct jump_label_key *key) { - struct jump_entry *iter; - struct jump_label_entry *entry; - struct hlist_node *module_node; - struct jump_label_module_entry *e_module; - int count; + if (!atomic_dec_and_mutex_lock(&key->enabled, &jump_label_mutex)) + return; - jump_label_lock(); - entry = get_jump_label_entry((jump_label_t)key); - if (entry) { - count = entry->nr_entries; - iter = entry->table; - while (count--) { - if (kernel_text_address(iter->code)) - arch_jump_label_transform(iter, type); - iter++; - } - /* eanble/disable jump labels in modules */ - hlist_for_each_entry(e_module, module_node, &(entry->modules), - hlist) { - count = e_module->nr_entries; - iter = e_module->table; - while (count--) { - if (iter->key && - kernel_text_address(iter->code)) - arch_jump_label_transform(iter, type); - iter++; - } - } - } + jump_label_update(key, JUMP_LABEL_DISABLE); jump_label_unlock(); } @@ -197,77 +89,33 @@ static int addr_conflict(struct jump_entry *entry, void *start, void *end) return 0; } -#ifdef CONFIG_MODULES - -static int module_conflict(void *start, void *end) +static int __jump_label_text_reserved(struct jump_entry *iter_start, + struct jump_entry *iter_stop, void *start, void *end) { - struct hlist_head *head; - struct hlist_node *node, *node_next, *module_node, *module_node_next; - struct jump_label_entry *e; - struct jump_label_module_entry *e_module; struct jump_entry *iter; - int i, count; - int conflict = 0; - - for (i = 0; i < JUMP_LABEL_TABLE_SIZE; i++) { - head = &jump_label_table[i]; - hlist_for_each_entry_safe(e, node, node_next, head, hlist) { - hlist_for_each_entry_safe(e_module, module_node, - module_node_next, - &(e->modules), hlist) { - count = e_module->nr_entries; - iter = e_module->table; - while (count--) { - if (addr_conflict(iter, start, end)) { - conflict = 1; - goto out; - } - iter++; - } - } - } - } -out: - return conflict; -} - -#endif - -/*** - * jump_label_text_reserved - check if addr range is reserved - * @start: start text addr - * @end: end text addr - * - * checks if the text addr located between @start and @end - * overlaps with any of the jump label patch addresses. Code - * that wants to modify kernel text should first verify that - * it does not overlap with any of the jump label addresses. - * Caller must hold jump_label_mutex. - * - * returns 1 if there is an overlap, 0 otherwise - */ -int jump_label_text_reserved(void *start, void *end) -{ - struct jump_entry *iter; - struct jump_entry *iter_start = __start___jump_table; - struct jump_entry *iter_stop = __start___jump_table; - int conflict = 0; iter = iter_start; while (iter < iter_stop) { - if (addr_conflict(iter, start, end)) { - conflict = 1; - goto out; - } + if (addr_conflict(iter, start, end)) + return 1; iter++; } - /* now check modules */ -#ifdef CONFIG_MODULES - conflict = module_conflict(start, end); -#endif -out: - return conflict; + return 0; +} + +static void __jump_label_update(struct jump_label_key *key, + struct jump_entry *entry, int enable) +{ + for (; entry->key == (jump_label_t)(unsigned long)key; entry++) { + /* + * entry->code set to 0 invalidates module init text sections + * kernel_text_address() verifies we are not in core kernel + * init code, see jump_label_invalidate_module_init(). + */ + if (entry->code && kernel_text_address(entry->code)) + arch_jump_label_transform(entry, enable); + } } /* @@ -277,142 +125,173 @@ void __weak arch_jump_label_text_poke_early(jump_label_t addr) { } -static __init int init_jump_label(void) +static __init int jump_label_init(void) { - int ret; struct jump_entry *iter_start = __start___jump_table; struct jump_entry *iter_stop = __stop___jump_table; + struct jump_label_key *key = NULL; struct jump_entry *iter; jump_label_lock(); - ret = build_jump_label_hashtable(__start___jump_table, - __stop___jump_table); - iter = iter_start; - while (iter < iter_stop) { + jump_label_sort_entries(iter_start, iter_stop); + + for (iter = iter_start; iter < iter_stop; iter++) { arch_jump_label_text_poke_early(iter->code); - iter++; + if (iter->key == (jump_label_t)(unsigned long)key) + continue; + + key = (struct jump_label_key *)(unsigned long)iter->key; + atomic_set(&key->enabled, 0); + key->entries = iter; +#ifdef CONFIG_MODULES + key->next = NULL; +#endif } jump_label_unlock(); - return ret; + + return 0; } -early_initcall(init_jump_label); +early_initcall(jump_label_init); #ifdef CONFIG_MODULES -static struct jump_label_module_entry * -add_jump_label_module_entry(struct jump_label_entry *entry, - struct jump_entry *iter_begin, - int count, struct module *mod) +struct jump_label_mod { + struct jump_label_mod *next; + struct jump_entry *entries; + struct module *mod; +}; + +static int __jump_label_mod_text_reserved(void *start, void *end) +{ + struct module *mod; + + mod = __module_text_address((unsigned long)start); + if (!mod) + return 0; + + WARN_ON_ONCE(__module_text_address((unsigned long)end) != mod); + + return __jump_label_text_reserved(mod->jump_entries, + mod->jump_entries + mod->num_jump_entries, + start, end); +} + +static void __jump_label_mod_update(struct jump_label_key *key, int enable) +{ + struct jump_label_mod *mod = key->next; + + while (mod) { + __jump_label_update(key, mod->entries, enable); + mod = mod->next; + } +} + +/*** + * apply_jump_label_nops - patch module jump labels with arch_get_jump_label_nop() + * @mod: module to patch + * + * Allow for run-time selection of the optimal nops. Before the module + * loads patch these with arch_get_jump_label_nop(), which is specified by + * the arch specific jump label code. + */ +void jump_label_apply_nops(struct module *mod) { - struct jump_label_module_entry *e; - - e = kmalloc(sizeof(struct jump_label_module_entry), GFP_KERNEL); - if (!e) - return ERR_PTR(-ENOMEM); - e->mod = mod; - e->nr_entries = count; - e->table = iter_begin; - hlist_add_head(&e->hlist, &entry->modules); - return e; + struct jump_entry *iter_start = mod->jump_entries; + struct jump_entry *iter_stop = iter_start + mod->num_jump_entries; + struct jump_entry *iter; + + /* if the module doesn't have jump label entries, just return */ + if (iter_start == iter_stop) + return; + + for (iter = iter_start; iter < iter_stop; iter++) + arch_jump_label_text_poke_early(iter->code); } -static int add_jump_label_module(struct module *mod) +static int jump_label_add_module(struct module *mod) { - struct jump_entry *iter, *iter_begin; - struct jump_label_entry *entry; - struct jump_label_module_entry *module_entry; - int count; + struct jump_entry *iter_start = mod->jump_entries; + struct jump_entry *iter_stop = iter_start + mod->num_jump_entries; + struct jump_entry *iter; + struct jump_label_key *key = NULL; + struct jump_label_mod *jlm; /* if the module doesn't have jump label entries, just return */ - if (!mod->num_jump_entries) + if (iter_start == iter_stop) return 0; - sort_jump_label_entries(mod->jump_entries, - mod->jump_entries + mod->num_jump_entries); - iter = mod->jump_entries; - while (iter < mod->jump_entries + mod->num_jump_entries) { - entry = get_jump_label_entry(iter->key); - iter_begin = iter; - count = 0; - while ((iter < mod->jump_entries + mod->num_jump_entries) && - (iter->key == iter_begin->key)) { - iter++; - count++; - } - if (!entry) { - entry = add_jump_label_entry(iter_begin->key, 0, NULL); - if (IS_ERR(entry)) - return PTR_ERR(entry); + jump_label_sort_entries(iter_start, iter_stop); + + for (iter = iter_start; iter < iter_stop; iter++) { + if (iter->key == (jump_label_t)(unsigned long)key) + continue; + + key = (struct jump_label_key *)(unsigned long)iter->key; + + if (__module_address(iter->key) == mod) { + atomic_set(&key->enabled, 0); + key->entries = iter; + key->next = NULL; + continue; } - module_entry = add_jump_label_module_entry(entry, iter_begin, - count, mod); - if (IS_ERR(module_entry)) - return PTR_ERR(module_entry); + + jlm = kzalloc(sizeof(struct jump_label_mod), GFP_KERNEL); + if (!jlm) + return -ENOMEM; + + jlm->mod = mod; + jlm->entries = iter; + jlm->next = key->next; + key->next = jlm; + + if (jump_label_enabled(key)) + __jump_label_update(key, iter, JUMP_LABEL_ENABLE); } + return 0; } -static void remove_jump_label_module(struct module *mod) +static void jump_label_del_module(struct module *mod) { - struct hlist_head *head; - struct hlist_node *node, *node_next, *module_node, *module_node_next; - struct jump_label_entry *e; - struct jump_label_module_entry *e_module; - int i; + struct jump_entry *iter_start = mod->jump_entries; + struct jump_entry *iter_stop = iter_start + mod->num_jump_entries; + struct jump_entry *iter; + struct jump_label_key *key = NULL; + struct jump_label_mod *jlm, **prev; - /* if the module doesn't have jump label entries, just return */ - if (!mod->num_jump_entries) - return; + for (iter = iter_start; iter < iter_stop; iter++) { + if (iter->key == (jump_label_t)(unsigned long)key) + continue; + + key = (struct jump_label_key *)(unsigned long)iter->key; + + if (__module_address(iter->key) == mod) + continue; + + prev = &key->next; + jlm = key->next; - for (i = 0; i < JUMP_LABEL_TABLE_SIZE; i++) { - head = &jump_label_table[i]; - hlist_for_each_entry_safe(e, node, node_next, head, hlist) { - hlist_for_each_entry_safe(e_module, module_node, - module_node_next, - &(e->modules), hlist) { - if (e_module->mod == mod) { - hlist_del(&e_module->hlist); - kfree(e_module); - } - } - if (hlist_empty(&e->modules) && (e->nr_entries == 0)) { - hlist_del(&e->hlist); - kfree(e); - } + while (jlm && jlm->mod != mod) { + prev = &jlm->next; + jlm = jlm->next; + } + + if (jlm) { + *prev = jlm->next; + kfree(jlm); } } } -static void remove_jump_label_module_init(struct module *mod) +static void jump_label_invalidate_module_init(struct module *mod) { - struct hlist_head *head; - struct hlist_node *node, *node_next, *module_node, *module_node_next; - struct jump_label_entry *e; - struct jump_label_module_entry *e_module; + struct jump_entry *iter_start = mod->jump_entries; + struct jump_entry *iter_stop = iter_start + mod->num_jump_entries; struct jump_entry *iter; - int i, count; - - /* if the module doesn't have jump label entries, just return */ - if (!mod->num_jump_entries) - return; - for (i = 0; i < JUMP_LABEL_TABLE_SIZE; i++) { - head = &jump_label_table[i]; - hlist_for_each_entry_safe(e, node, node_next, head, hlist) { - hlist_for_each_entry_safe(e_module, module_node, - module_node_next, - &(e->modules), hlist) { - if (e_module->mod != mod) - continue; - count = e_module->nr_entries; - iter = e_module->table; - while (count--) { - if (within_module_init(iter->code, mod)) - iter->key = 0; - iter++; - } - } - } + for (iter = iter_start; iter < iter_stop; iter++) { + if (within_module_init(iter->code, mod)) + iter->code = 0; } } @@ -426,59 +305,77 @@ jump_label_module_notify(struct notifier_block *self, unsigned long val, switch (val) { case MODULE_STATE_COMING: jump_label_lock(); - ret = add_jump_label_module(mod); + ret = jump_label_add_module(mod); if (ret) - remove_jump_label_module(mod); + jump_label_del_module(mod); jump_label_unlock(); break; case MODULE_STATE_GOING: jump_label_lock(); - remove_jump_label_module(mod); + jump_label_del_module(mod); jump_label_unlock(); break; case MODULE_STATE_LIVE: jump_label_lock(); - remove_jump_label_module_init(mod); + jump_label_invalidate_module_init(mod); jump_label_unlock(); break; } - return ret; -} -/*** - * apply_jump_label_nops - patch module jump labels with arch_get_jump_label_nop() - * @mod: module to patch - * - * Allow for run-time selection of the optimal nops. Before the module - * loads patch these with arch_get_jump_label_nop(), which is specified by - * the arch specific jump label code. - */ -void jump_label_apply_nops(struct module *mod) -{ - struct jump_entry *iter; - - /* if the module doesn't have jump label entries, just return */ - if (!mod->num_jump_entries) - return; - - iter = mod->jump_entries; - while (iter < mod->jump_entries + mod->num_jump_entries) { - arch_jump_label_text_poke_early(iter->code); - iter++; - } + return notifier_from_errno(ret); } struct notifier_block jump_label_module_nb = { .notifier_call = jump_label_module_notify, - .priority = 0, + .priority = 1, /* higher than tracepoints */ }; -static __init int init_jump_label_module(void) +static __init int jump_label_init_module(void) { return register_module_notifier(&jump_label_module_nb); } -early_initcall(init_jump_label_module); +early_initcall(jump_label_init_module); #endif /* CONFIG_MODULES */ +/*** + * jump_label_text_reserved - check if addr range is reserved + * @start: start text addr + * @end: end text addr + * + * checks if the text addr located between @start and @end + * overlaps with any of the jump label patch addresses. Code + * that wants to modify kernel text should first verify that + * it does not overlap with any of the jump label addresses. + * Caller must hold jump_label_mutex. + * + * returns 1 if there is an overlap, 0 otherwise + */ +int jump_label_text_reserved(void *start, void *end) +{ + int ret = __jump_label_text_reserved(__start___jump_table, + __stop___jump_table, start, end); + + if (ret) + return ret; + +#ifdef CONFIG_MODULES + ret = __jump_label_mod_text_reserved(start, end); +#endif + return ret; +} + +static void jump_label_update(struct jump_label_key *key, int enable) +{ + struct jump_entry *entry = key->entries; + + /* if there are no users, entry can be NULL */ + if (entry) + __jump_label_update(key, entry, enable); + +#ifdef CONFIG_MODULES + __jump_label_mod_update(key, enable); +#endif +} + #endif diff --git a/kernel/perf_event.c b/kernel/perf_event.c index c75925c4d1e..d665e92fbd4 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -125,7 +125,7 @@ enum event_type_t { * perf_sched_events : >0 events exist * perf_cgroup_events: >0 per-cpu cgroup events exist on this cpu */ -atomic_t perf_sched_events __read_mostly; +struct jump_label_key perf_sched_events __read_mostly; static DEFINE_PER_CPU(atomic_t, perf_cgroup_events); static atomic_t nr_mmap_events __read_mostly; @@ -5417,7 +5417,7 @@ fail: return err; } -atomic_t perf_swevent_enabled[PERF_COUNT_SW_MAX]; +struct jump_label_key perf_swevent_enabled[PERF_COUNT_SW_MAX]; static void sw_perf_event_destroy(struct perf_event *event) { diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c index 68187af4889..b219f1449c5 100644 --- a/kernel/tracepoint.c +++ b/kernel/tracepoint.c @@ -251,9 +251,9 @@ static void set_tracepoint(struct tracepoint_entry **entry, { WARN_ON(strcmp((*entry)->name, elem->name) != 0); - if (elem->regfunc && !elem->state && active) + if (elem->regfunc && !jump_label_enabled(&elem->key) && active) elem->regfunc(); - else if (elem->unregfunc && elem->state && !active) + else if (elem->unregfunc && jump_label_enabled(&elem->key) && !active) elem->unregfunc(); /* @@ -264,13 +264,10 @@ static void set_tracepoint(struct tracepoint_entry **entry, * is used. */ rcu_assign_pointer(elem->funcs, (*entry)->funcs); - if (!elem->state && active) { - jump_label_enable(&elem->state); - elem->state = active; - } else if (elem->state && !active) { - jump_label_disable(&elem->state); - elem->state = active; - } + if (active && !jump_label_enabled(&elem->key)) + jump_label_inc(&elem->key); + else if (!active && jump_label_enabled(&elem->key)) + jump_label_dec(&elem->key); } /* @@ -281,13 +278,11 @@ static void set_tracepoint(struct tracepoint_entry **entry, */ static void disable_tracepoint(struct tracepoint *elem) { - if (elem->unregfunc && elem->state) + if (elem->unregfunc && jump_label_enabled(&elem->key)) elem->unregfunc(); - if (elem->state) { - jump_label_disable(&elem->state); - elem->state = 0; - } + if (jump_label_enabled(&elem->key)) + jump_label_dec(&elem->key); rcu_assign_pointer(elem->funcs, NULL); } -- cgit v1.2.3-70-g09d2 From 5cdede2408e80f190c5595e592c24e77c1bf44b2 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 4 Apr 2011 15:55:18 +0200 Subject: PCI: Move ATS declarations in seperate header file This patch moves the relevant declarations from the local header file in drivers/pci to a more accessible locations so that it can be used by the AMD IOMMU driver too. The file is named pci-ats.h because support for the PCI PRI capability will also be added there in a later patch-set. Signed-off-by: Joerg Roedel Acked-by: Jesse Barnes --- drivers/pci/intel-iommu.c | 1 + drivers/pci/iov.c | 1 + drivers/pci/pci.h | 37 --------------------------------- include/linux/pci-ats.h | 52 +++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 54 insertions(+), 37 deletions(-) create mode 100644 include/linux/pci-ats.h (limited to 'include') diff --git a/drivers/pci/intel-iommu.c b/drivers/pci/intel-iommu.c index 7da3bef60d8..fdb2cef2b90 100644 --- a/drivers/pci/intel-iommu.c +++ b/drivers/pci/intel-iommu.c @@ -39,6 +39,7 @@ #include #include #include +#include #include #include #include "pci.h" diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c index 553d8ee55c1..42fae477651 100644 --- a/drivers/pci/iov.c +++ b/drivers/pci/iov.c @@ -13,6 +13,7 @@ #include #include #include +#include #include "pci.h" #define VIRTFN_ID_LEN 16 diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index a6ec200fe5e..4020025f854 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -250,15 +250,6 @@ struct pci_sriov { u8 __iomem *mstate; /* VF Migration State Array */ }; -/* Address Translation Service */ -struct pci_ats { - int pos; /* capability position */ - int stu; /* Smallest Translation Unit */ - int qdep; /* Invalidate Queue Depth */ - int ref_cnt; /* Physical Function reference count */ - unsigned int is_enabled:1; /* Enable bit is set */ -}; - #ifdef CONFIG_PCI_IOV extern int pci_iov_init(struct pci_dev *dev); extern void pci_iov_release(struct pci_dev *dev); @@ -269,19 +260,6 @@ extern resource_size_t pci_sriov_resource_alignment(struct pci_dev *dev, extern void pci_restore_iov_state(struct pci_dev *dev); extern int pci_iov_bus_range(struct pci_bus *bus); -extern int pci_enable_ats(struct pci_dev *dev, int ps); -extern void pci_disable_ats(struct pci_dev *dev); -extern int pci_ats_queue_depth(struct pci_dev *dev); -/** - * pci_ats_enabled - query the ATS status - * @dev: the PCI device - * - * Returns 1 if ATS capability is enabled, or 0 if not. - */ -static inline int pci_ats_enabled(struct pci_dev *dev) -{ - return dev->ats && dev->ats->is_enabled; -} #else static inline int pci_iov_init(struct pci_dev *dev) { @@ -304,21 +282,6 @@ static inline int pci_iov_bus_range(struct pci_bus *bus) return 0; } -static inline int pci_enable_ats(struct pci_dev *dev, int ps) -{ - return -ENODEV; -} -static inline void pci_disable_ats(struct pci_dev *dev) -{ -} -static inline int pci_ats_queue_depth(struct pci_dev *dev) -{ - return -ENODEV; -} -static inline int pci_ats_enabled(struct pci_dev *dev) -{ - return 0; -} #endif /* CONFIG_PCI_IOV */ static inline resource_size_t pci_resource_alignment(struct pci_dev *dev, diff --git a/include/linux/pci-ats.h b/include/linux/pci-ats.h new file mode 100644 index 00000000000..655824fa4c7 --- /dev/null +++ b/include/linux/pci-ats.h @@ -0,0 +1,52 @@ +#ifndef LINUX_PCI_ATS_H +#define LINUX_PCI_ATS_H + +/* Address Translation Service */ +struct pci_ats { + int pos; /* capability position */ + int stu; /* Smallest Translation Unit */ + int qdep; /* Invalidate Queue Depth */ + int ref_cnt; /* Physical Function reference count */ + unsigned int is_enabled:1; /* Enable bit is set */ +}; + +#ifdef CONFIG_PCI_IOV + +extern int pci_enable_ats(struct pci_dev *dev, int ps); +extern void pci_disable_ats(struct pci_dev *dev); +extern int pci_ats_queue_depth(struct pci_dev *dev); +/** + * pci_ats_enabled - query the ATS status + * @dev: the PCI device + * + * Returns 1 if ATS capability is enabled, or 0 if not. + */ +static inline int pci_ats_enabled(struct pci_dev *dev) +{ + return dev->ats && dev->ats->is_enabled; +} + +#else /* CONFIG_PCI_IOV */ + +static inline int pci_enable_ats(struct pci_dev *dev, int ps) +{ + return -ENODEV; +} + +static inline void pci_disable_ats(struct pci_dev *dev) +{ +} + +static inline int pci_ats_queue_depth(struct pci_dev *dev) +{ + return -ENODEV; +} + +static inline int pci_ats_enabled(struct pci_dev *dev) +{ + return 0; +} + +#endif /* CONFIG_PCI_IOV */ + +#endif /* LINUX_PCI_ATS_H*/ -- cgit v1.2.3-70-g09d2 From dce840a08702bd13a9a186e07e63d1ef82256b5e Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 7 Apr 2011 14:09:50 +0200 Subject: sched: Dynamically allocate sched_domain/sched_group data-structures Instead of relying on static allocations for the sched_domain and sched_group trees, dynamically allocate and RCU free them. Allocating this dynamically also allows for some build_sched_groups() simplification since we can now (like with other simplifications) rely on the sched_domain tree instead of hard-coded knowledge. One tricky to note is that detach_destroy_domains() needs to hold rcu_read_lock() over the entire tear-down, per-cpu is not sufficient since that can lead to partial sched_group existance (could possibly be solved by doing the tear-down backwards but this is much more robust). A concequence of the above is that we can no longer print the sched_domain debug stuff from cpu_attach_domain() since that might now run with preemption disabled (due to classic RCU etc.) and sched_domain_debug() does some GFP_KERNEL allocations. Another thing to note is that we now fully rely on normal RCU and not RCU-sched, this is because with the new and exiting RCU flavours we grew over the years BH doesn't necessarily hold off RCU-sched grace periods (-rt is known to break this). This would in fact already cause us grief since we do sched_domain/sched_group iterations from softirq context. This patch is somewhat larger than I would like it to be, but I didn't find any means of shrinking/splitting this. Signed-off-by: Peter Zijlstra Cc: Mike Galbraith Cc: Nick Piggin Cc: Linus Torvalds Cc: Andrew Morton Link: http://lkml.kernel.org/r/20110407122942.245307941@chello.nl Signed-off-by: Ingo Molnar --- include/linux/sched.h | 5 + kernel/sched.c | 479 ++++++++++++++++++++------------------------------ kernel/sched_fair.c | 30 +++- 3 files changed, 218 insertions(+), 296 deletions(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 4ec2c027e92..020b79d6c48 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -868,6 +868,7 @@ static inline int sd_power_saving_flags(void) struct sched_group { struct sched_group *next; /* Must be a circular list */ + atomic_t ref; /* * CPU power of this group, SCHED_LOAD_SCALE being max power for a @@ -973,6 +974,10 @@ struct sched_domain { #ifdef CONFIG_SCHED_DEBUG char *name; #endif + union { + void *private; /* used during construction */ + struct rcu_head rcu; /* used during destruction */ + }; unsigned int span_weight; /* diff --git a/kernel/sched.c b/kernel/sched.c index 1cca59ec4a4..65204845063 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -417,6 +417,7 @@ struct rt_rq { */ struct root_domain { atomic_t refcount; + struct rcu_head rcu; cpumask_var_t span; cpumask_var_t online; @@ -571,7 +572,7 @@ static inline int cpu_of(struct rq *rq) #define rcu_dereference_check_sched_domain(p) \ rcu_dereference_check((p), \ - rcu_read_lock_sched_held() || \ + rcu_read_lock_held() || \ lockdep_is_held(&sched_domains_mutex)) /* @@ -6572,12 +6573,11 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent) return 1; } -static void free_rootdomain(struct root_domain *rd) +static void free_rootdomain(struct rcu_head *rcu) { - synchronize_sched(); + struct root_domain *rd = container_of(rcu, struct root_domain, rcu); cpupri_cleanup(&rd->cpupri); - free_cpumask_var(rd->rto_mask); free_cpumask_var(rd->online); free_cpumask_var(rd->span); @@ -6618,7 +6618,7 @@ static void rq_attach_root(struct rq *rq, struct root_domain *rd) raw_spin_unlock_irqrestore(&rq->lock, flags); if (old_rd) - free_rootdomain(old_rd); + call_rcu_sched(&old_rd->rcu, free_rootdomain); } static int init_rootdomain(struct root_domain *rd) @@ -6669,6 +6669,25 @@ static struct root_domain *alloc_rootdomain(void) return rd; } +static void free_sched_domain(struct rcu_head *rcu) +{ + struct sched_domain *sd = container_of(rcu, struct sched_domain, rcu); + if (atomic_dec_and_test(&sd->groups->ref)) + kfree(sd->groups); + kfree(sd); +} + +static void destroy_sched_domain(struct sched_domain *sd, int cpu) +{ + call_rcu(&sd->rcu, free_sched_domain); +} + +static void destroy_sched_domains(struct sched_domain *sd, int cpu) +{ + for (; sd; sd = sd->parent) + destroy_sched_domain(sd, cpu); +} + /* * Attach the domain 'sd' to 'cpu' as its base domain. Callers must * hold the hotplug lock. @@ -6689,20 +6708,25 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu) tmp->parent = parent->parent; if (parent->parent) parent->parent->child = tmp; + destroy_sched_domain(parent, cpu); } else tmp = tmp->parent; } if (sd && sd_degenerate(sd)) { + tmp = sd; sd = sd->parent; + destroy_sched_domain(tmp, cpu); if (sd) sd->child = NULL; } - sched_domain_debug(sd, cpu); + /* sched_domain_debug(sd, cpu); */ rq_attach_root(rq, rd); + tmp = rq->sd; rcu_assign_pointer(rq->sd, sd); + destroy_sched_domains(tmp, cpu); } /* cpus with isolated domains */ @@ -6718,56 +6742,6 @@ static int __init isolated_cpu_setup(char *str) __setup("isolcpus=", isolated_cpu_setup); -/* - * init_sched_build_groups takes the cpumask we wish to span, and a pointer - * to a function which identifies what group(along with sched group) a CPU - * belongs to. The return value of group_fn must be a >= 0 and < nr_cpu_ids - * (due to the fact that we keep track of groups covered with a struct cpumask). - * - * init_sched_build_groups will build a circular linked list of the groups - * covered by the given span, and will set each group's ->cpumask correctly, - * and ->cpu_power to 0. - */ -static void -init_sched_build_groups(const struct cpumask *span, - const struct cpumask *cpu_map, - int (*group_fn)(int cpu, const struct cpumask *cpu_map, - struct sched_group **sg, - struct cpumask *tmpmask), - struct cpumask *covered, struct cpumask *tmpmask) -{ - struct sched_group *first = NULL, *last = NULL; - int i; - - cpumask_clear(covered); - - for_each_cpu(i, span) { - struct sched_group *sg; - int group = group_fn(i, cpu_map, &sg, tmpmask); - int j; - - if (cpumask_test_cpu(i, covered)) - continue; - - cpumask_clear(sched_group_cpus(sg)); - sg->cpu_power = 0; - - for_each_cpu(j, span) { - if (group_fn(j, cpu_map, NULL, tmpmask) != group) - continue; - - cpumask_set_cpu(j, covered); - cpumask_set_cpu(j, sched_group_cpus(sg)); - } - if (!first) - first = sg; - if (last) - last->next = sg; - last = sg; - } - last->next = first; -} - #define SD_NODES_PER_DOMAIN 16 #ifdef CONFIG_NUMA @@ -6858,154 +6832,96 @@ struct static_sched_domain { DECLARE_BITMAP(span, CONFIG_NR_CPUS); }; +struct sd_data { + struct sched_domain **__percpu sd; + struct sched_group **__percpu sg; +}; + struct s_data { #ifdef CONFIG_NUMA int sd_allnodes; #endif cpumask_var_t nodemask; cpumask_var_t send_covered; - cpumask_var_t tmpmask; struct sched_domain ** __percpu sd; + struct sd_data sdd[SD_LV_MAX]; struct root_domain *rd; }; enum s_alloc { sa_rootdomain, sa_sd, - sa_tmpmask, + sa_sd_storage, sa_send_covered, sa_nodemask, sa_none, }; /* - * SMT sched-domains: + * Assumes the sched_domain tree is fully constructed */ -#ifdef CONFIG_SCHED_SMT -static DEFINE_PER_CPU(struct static_sched_domain, cpu_domains); -static DEFINE_PER_CPU(struct static_sched_group, sched_groups); - -static int -cpu_to_cpu_group(int cpu, const struct cpumask *cpu_map, - struct sched_group **sg, struct cpumask *unused) +static int get_group(int cpu, struct sd_data *sdd, struct sched_group **sg) { - if (sg) - *sg = &per_cpu(sched_groups, cpu).sg; - return cpu; -} -#endif /* CONFIG_SCHED_SMT */ + struct sched_domain *sd = *per_cpu_ptr(sdd->sd, cpu); + struct sched_domain *child = sd->child; -/* - * multi-core sched-domains: - */ -#ifdef CONFIG_SCHED_MC -static DEFINE_PER_CPU(struct static_sched_domain, core_domains); -static DEFINE_PER_CPU(struct static_sched_group, sched_group_core); + if (child) + cpu = cpumask_first(sched_domain_span(child)); -static int -cpu_to_core_group(int cpu, const struct cpumask *cpu_map, - struct sched_group **sg, struct cpumask *mask) -{ - int group; -#ifdef CONFIG_SCHED_SMT - cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map); - group = cpumask_first(mask); -#else - group = cpu; -#endif if (sg) - *sg = &per_cpu(sched_group_core, group).sg; - return group; + *sg = *per_cpu_ptr(sdd->sg, cpu); + + return cpu; } -#endif /* CONFIG_SCHED_MC */ /* - * book sched-domains: + * build_sched_groups takes the cpumask we wish to span, and a pointer + * to a function which identifies what group(along with sched group) a CPU + * belongs to. The return value of group_fn must be a >= 0 and < nr_cpu_ids + * (due to the fact that we keep track of groups covered with a struct cpumask). + * + * build_sched_groups will build a circular linked list of the groups + * covered by the given span, and will set each group's ->cpumask correctly, + * and ->cpu_power to 0. */ -#ifdef CONFIG_SCHED_BOOK -static DEFINE_PER_CPU(struct static_sched_domain, book_domains); -static DEFINE_PER_CPU(struct static_sched_group, sched_group_book); - -static int -cpu_to_book_group(int cpu, const struct cpumask *cpu_map, - struct sched_group **sg, struct cpumask *mask) -{ - int group = cpu; -#ifdef CONFIG_SCHED_MC - cpumask_and(mask, cpu_coregroup_mask(cpu), cpu_map); - group = cpumask_first(mask); -#elif defined(CONFIG_SCHED_SMT) - cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map); - group = cpumask_first(mask); -#endif - if (sg) - *sg = &per_cpu(sched_group_book, group).sg; - return group; -} -#endif /* CONFIG_SCHED_BOOK */ - -static DEFINE_PER_CPU(struct static_sched_domain, phys_domains); -static DEFINE_PER_CPU(struct static_sched_group, sched_group_phys); - -static int -cpu_to_phys_group(int cpu, const struct cpumask *cpu_map, - struct sched_group **sg, struct cpumask *mask) +static void +build_sched_groups(struct sched_domain *sd, struct cpumask *covered) { - int group; -#ifdef CONFIG_SCHED_BOOK - cpumask_and(mask, cpu_book_mask(cpu), cpu_map); - group = cpumask_first(mask); -#elif defined(CONFIG_SCHED_MC) - cpumask_and(mask, cpu_coregroup_mask(cpu), cpu_map); - group = cpumask_first(mask); -#elif defined(CONFIG_SCHED_SMT) - cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map); - group = cpumask_first(mask); -#else - group = cpu; -#endif - if (sg) - *sg = &per_cpu(sched_group_phys, group).sg; - return group; -} - -#ifdef CONFIG_NUMA -static DEFINE_PER_CPU(struct static_sched_domain, node_domains); -static DEFINE_PER_CPU(struct static_sched_group, sched_group_node); + struct sched_group *first = NULL, *last = NULL; + struct sd_data *sdd = sd->private; + const struct cpumask *span = sched_domain_span(sd); + int i; -static int cpu_to_node_group(int cpu, const struct cpumask *cpu_map, - struct sched_group **sg, - struct cpumask *nodemask) -{ - int group; + cpumask_clear(covered); - cpumask_and(nodemask, cpumask_of_node(cpu_to_node(cpu)), cpu_map); - group = cpumask_first(nodemask); + for_each_cpu(i, span) { + struct sched_group *sg; + int group = get_group(i, sdd, &sg); + int j; - if (sg) - *sg = &per_cpu(sched_group_node, group).sg; - return group; -} + if (cpumask_test_cpu(i, covered)) + continue; -static DEFINE_PER_CPU(struct static_sched_domain, allnodes_domains); -static DEFINE_PER_CPU(struct static_sched_group, sched_group_allnodes); + cpumask_clear(sched_group_cpus(sg)); + sg->cpu_power = 0; -static int cpu_to_allnodes_group(int cpu, const struct cpumask *cpu_map, - struct sched_group **sg, - struct cpumask *nodemask) -{ - int group; + for_each_cpu(j, span) { + if (get_group(j, sdd, NULL) != group) + continue; - cpumask_and(nodemask, cpumask_of_node(cpu_to_node(cpu)), cpu_map); - group = cpumask_first(nodemask); + cpumask_set_cpu(j, covered); + cpumask_set_cpu(j, sched_group_cpus(sg)); + } - if (sg) - *sg = &per_cpu(sched_group_allnodes, group).sg; - return group; + if (!first) + first = sg; + if (last) + last->next = sg; + last = sg; + } + last->next = first; } -#endif /* CONFIG_NUMA */ - /* * Initialize sched groups cpu_power. * @@ -7039,15 +6955,15 @@ static void init_sched_groups_power(int cpu, struct sched_domain *sd) # define SD_INIT_NAME(sd, type) do { } while (0) #endif -#define SD_INIT(sd, type) sd_init_##type(sd) - -#define SD_INIT_FUNC(type) \ -static noinline void sd_init_##type(struct sched_domain *sd) \ -{ \ - memset(sd, 0, sizeof(*sd)); \ - *sd = SD_##type##_INIT; \ - sd->level = SD_LV_##type; \ - SD_INIT_NAME(sd, type); \ +#define SD_INIT_FUNC(type) \ +static noinline struct sched_domain *sd_init_##type(struct s_data *d, int cpu) \ +{ \ + struct sched_domain *sd = *per_cpu_ptr(d->sdd[SD_LV_##type].sd, cpu); \ + *sd = SD_##type##_INIT; \ + sd->level = SD_LV_##type; \ + SD_INIT_NAME(sd, type); \ + sd->private = &d->sdd[SD_LV_##type]; \ + return sd; \ } SD_INIT_FUNC(CPU) @@ -7103,13 +7019,22 @@ static void set_domain_attribute(struct sched_domain *sd, static void __free_domain_allocs(struct s_data *d, enum s_alloc what, const struct cpumask *cpu_map) { + int i, j; + switch (what) { case sa_rootdomain: - free_rootdomain(d->rd); /* fall through */ + free_rootdomain(&d->rd->rcu); /* fall through */ case sa_sd: free_percpu(d->sd); /* fall through */ - case sa_tmpmask: - free_cpumask_var(d->tmpmask); /* fall through */ + case sa_sd_storage: + for (i = 0; i < SD_LV_MAX; i++) { + for_each_cpu(j, cpu_map) { + kfree(*per_cpu_ptr(d->sdd[i].sd, j)); + kfree(*per_cpu_ptr(d->sdd[i].sg, j)); + } + free_percpu(d->sdd[i].sd); + free_percpu(d->sdd[i].sg); + } /* fall through */ case sa_send_covered: free_cpumask_var(d->send_covered); /* fall through */ case sa_nodemask: @@ -7122,25 +7047,70 @@ static void __free_domain_allocs(struct s_data *d, enum s_alloc what, static enum s_alloc __visit_domain_allocation_hell(struct s_data *d, const struct cpumask *cpu_map) { + int i, j; + + memset(d, 0, sizeof(*d)); + if (!alloc_cpumask_var(&d->nodemask, GFP_KERNEL)) return sa_none; if (!alloc_cpumask_var(&d->send_covered, GFP_KERNEL)) return sa_nodemask; - if (!alloc_cpumask_var(&d->tmpmask, GFP_KERNEL)) - return sa_send_covered; - d->sd = alloc_percpu(struct sched_domain *); - if (!d->sd) { - printk(KERN_WARNING "Cannot alloc per-cpu pointers\n"); - return sa_tmpmask; + for (i = 0; i < SD_LV_MAX; i++) { + d->sdd[i].sd = alloc_percpu(struct sched_domain *); + if (!d->sdd[i].sd) + return sa_sd_storage; + + d->sdd[i].sg = alloc_percpu(struct sched_group *); + if (!d->sdd[i].sg) + return sa_sd_storage; + + for_each_cpu(j, cpu_map) { + struct sched_domain *sd; + struct sched_group *sg; + + sd = kzalloc_node(sizeof(struct sched_domain) + cpumask_size(), + GFP_KERNEL, cpu_to_node(j)); + if (!sd) + return sa_sd_storage; + + *per_cpu_ptr(d->sdd[i].sd, j) = sd; + + sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(), + GFP_KERNEL, cpu_to_node(j)); + if (!sg) + return sa_sd_storage; + + *per_cpu_ptr(d->sdd[i].sg, j) = sg; + } } + d->sd = alloc_percpu(struct sched_domain *); + if (!d->sd) + return sa_sd_storage; d->rd = alloc_rootdomain(); - if (!d->rd) { - printk(KERN_WARNING "Cannot alloc root domain\n"); + if (!d->rd) return sa_sd; - } return sa_rootdomain; } +/* + * NULL the sd_data elements we've used to build the sched_domain and + * sched_group structure so that the subsequent __free_domain_allocs() + * will not free the data we're using. + */ +static void claim_allocations(int cpu, struct sched_domain *sd) +{ + struct sd_data *sdd = sd->private; + struct sched_group *sg = sd->groups; + + WARN_ON_ONCE(*per_cpu_ptr(sdd->sd, cpu) != sd); + *per_cpu_ptr(sdd->sd, cpu) = NULL; + + if (cpu == cpumask_first(sched_group_cpus(sg))) { + WARN_ON_ONCE(*per_cpu_ptr(sdd->sg, cpu) != sg); + *per_cpu_ptr(sdd->sg, cpu) = NULL; + } +} + static struct sched_domain *__build_numa_sched_domains(struct s_data *d, const struct cpumask *cpu_map, struct sched_domain_attr *attr, int i) { @@ -7151,24 +7121,20 @@ static struct sched_domain *__build_numa_sched_domains(struct s_data *d, d->sd_allnodes = 0; if (cpumask_weight(cpu_map) > SD_NODES_PER_DOMAIN * cpumask_weight(d->nodemask)) { - sd = &per_cpu(allnodes_domains, i).sd; - SD_INIT(sd, ALLNODES); + sd = sd_init_ALLNODES(d, i); set_domain_attribute(sd, attr); cpumask_copy(sched_domain_span(sd), cpu_map); - cpu_to_allnodes_group(i, cpu_map, &sd->groups, d->tmpmask); d->sd_allnodes = 1; } parent = sd; - sd = &per_cpu(node_domains, i).sd; - SD_INIT(sd, NODE); + sd = sd_init_NODE(d, i); set_domain_attribute(sd, attr); sched_domain_node_span(cpu_to_node(i), sched_domain_span(sd)); sd->parent = parent; if (parent) parent->child = sd; cpumask_and(sched_domain_span(sd), sched_domain_span(sd), cpu_map); - cpu_to_node_group(i, cpu_map, &sd->groups, d->tmpmask); #endif return sd; } @@ -7178,14 +7144,12 @@ static struct sched_domain *__build_cpu_sched_domain(struct s_data *d, struct sched_domain *parent, int i) { struct sched_domain *sd; - sd = &per_cpu(phys_domains, i).sd; - SD_INIT(sd, CPU); + sd = sd_init_CPU(d, i); set_domain_attribute(sd, attr); cpumask_copy(sched_domain_span(sd), d->nodemask); sd->parent = parent; if (parent) parent->child = sd; - cpu_to_phys_group(i, cpu_map, &sd->groups, d->tmpmask); return sd; } @@ -7195,13 +7159,11 @@ static struct sched_domain *__build_book_sched_domain(struct s_data *d, { struct sched_domain *sd = parent; #ifdef CONFIG_SCHED_BOOK - sd = &per_cpu(book_domains, i).sd; - SD_INIT(sd, BOOK); + sd = sd_init_BOOK(d, i); set_domain_attribute(sd, attr); cpumask_and(sched_domain_span(sd), cpu_map, cpu_book_mask(i)); sd->parent = parent; parent->child = sd; - cpu_to_book_group(i, cpu_map, &sd->groups, d->tmpmask); #endif return sd; } @@ -7212,13 +7174,11 @@ static struct sched_domain *__build_mc_sched_domain(struct s_data *d, { struct sched_domain *sd = parent; #ifdef CONFIG_SCHED_MC - sd = &per_cpu(core_domains, i).sd; - SD_INIT(sd, MC); + sd = sd_init_MC(d, i); set_domain_attribute(sd, attr); cpumask_and(sched_domain_span(sd), cpu_map, cpu_coregroup_mask(i)); sd->parent = parent; parent->child = sd; - cpu_to_core_group(i, cpu_map, &sd->groups, d->tmpmask); #endif return sd; } @@ -7229,92 +7189,32 @@ static struct sched_domain *__build_smt_sched_domain(struct s_data *d, { struct sched_domain *sd = parent; #ifdef CONFIG_SCHED_SMT - sd = &per_cpu(cpu_domains, i).sd; - SD_INIT(sd, SIBLING); + sd = sd_init_SIBLING(d, i); set_domain_attribute(sd, attr); cpumask_and(sched_domain_span(sd), cpu_map, topology_thread_cpumask(i)); sd->parent = parent; parent->child = sd; - cpu_to_cpu_group(i, cpu_map, &sd->groups, d->tmpmask); #endif return sd; } -static void build_sched_groups(struct s_data *d, struct sched_domain *sd, - const struct cpumask *cpu_map, int cpu) -{ - switch (sd->level) { -#ifdef CONFIG_SCHED_SMT - case SD_LV_SIBLING: /* set up CPU (sibling) groups */ - if (cpu == cpumask_first(sched_domain_span(sd))) - init_sched_build_groups(sched_domain_span(sd), cpu_map, - &cpu_to_cpu_group, - d->send_covered, d->tmpmask); - break; -#endif -#ifdef CONFIG_SCHED_MC - case SD_LV_MC: /* set up multi-core groups */ - if (cpu == cpumask_first(sched_domain_span(sd))) - init_sched_build_groups(sched_domain_span(sd), cpu_map, - &cpu_to_core_group, - d->send_covered, d->tmpmask); - break; -#endif -#ifdef CONFIG_SCHED_BOOK - case SD_LV_BOOK: /* set up book groups */ - if (cpu == cpumask_first(sched_domain_span(sd))) - init_sched_build_groups(sched_domain_span(sd), cpu_map, - &cpu_to_book_group, - d->send_covered, d->tmpmask); - break; -#endif - case SD_LV_CPU: /* set up physical groups */ - if (cpu == cpumask_first(sched_domain_span(sd))) - init_sched_build_groups(sched_domain_span(sd), cpu_map, - &cpu_to_phys_group, - d->send_covered, d->tmpmask); - break; -#ifdef CONFIG_NUMA - case SD_LV_NODE: - if (cpu == cpumask_first(sched_domain_span(sd))) - init_sched_build_groups(sched_domain_span(sd), cpu_map, - &cpu_to_node_group, - d->send_covered, d->tmpmask); - - case SD_LV_ALLNODES: - if (cpu == cpumask_first(cpu_map)) - init_sched_build_groups(cpu_map, cpu_map, - &cpu_to_allnodes_group, - d->send_covered, d->tmpmask); - break; -#endif - default: - break; - } -} - /* * Build sched domains for a given set of cpus and attach the sched domains * to the individual cpus */ -static int __build_sched_domains(const struct cpumask *cpu_map, - struct sched_domain_attr *attr) +static int build_sched_domains(const struct cpumask *cpu_map, + struct sched_domain_attr *attr) { enum s_alloc alloc_state = sa_none; + struct sched_domain *sd; struct s_data d; - struct sched_domain *sd, *tmp; int i; -#ifdef CONFIG_NUMA - d.sd_allnodes = 0; -#endif alloc_state = __visit_domain_allocation_hell(&d, cpu_map); if (alloc_state != sa_rootdomain) goto error; - /* - * Set up domains for cpus specified by the cpu_map. - */ + /* Set up domains for cpus specified by the cpu_map. */ for_each_cpu(i, cpu_map) { cpumask_and(d.nodemask, cpumask_of_node(cpu_to_node(i)), cpu_map); @@ -7326,10 +7226,19 @@ static int __build_sched_domains(const struct cpumask *cpu_map, sd = __build_smt_sched_domain(&d, cpu_map, attr, sd, i); *per_cpu_ptr(d.sd, i) = sd; + } + + /* Build the groups for the domains */ + for_each_cpu(i, cpu_map) { + for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) { + sd->span_weight = cpumask_weight(sched_domain_span(sd)); + get_group(i, sd->private, &sd->groups); + atomic_inc(&sd->groups->ref); - for (tmp = sd; tmp; tmp = tmp->parent) { - tmp->span_weight = cpumask_weight(sched_domain_span(tmp)); - build_sched_groups(&d, tmp, cpu_map, i); + if (i != cpumask_first(sched_domain_span(sd))) + continue; + + build_sched_groups(sd, d.send_covered); } } @@ -7338,18 +7247,21 @@ static int __build_sched_domains(const struct cpumask *cpu_map, if (!cpumask_test_cpu(i, cpu_map)) continue; - sd = *per_cpu_ptr(d.sd, i); - for (; sd; sd = sd->parent) + for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) { + claim_allocations(i, sd); init_sched_groups_power(i, sd); + } } /* Attach the domains */ + rcu_read_lock(); for_each_cpu(i, cpu_map) { sd = *per_cpu_ptr(d.sd, i); cpu_attach_domain(sd, d.rd, i); } + rcu_read_unlock(); - __free_domain_allocs(&d, sa_tmpmask, cpu_map); + __free_domain_allocs(&d, sa_sd, cpu_map); return 0; error: @@ -7357,11 +7269,6 @@ error: return -ENOMEM; } -static int build_sched_domains(const struct cpumask *cpu_map) -{ - return __build_sched_domains(cpu_map, NULL); -} - static cpumask_var_t *doms_cur; /* current sched domains */ static int ndoms_cur; /* number of sched domains in 'doms_cur' */ static struct sched_domain_attr *dattr_cur; @@ -7425,31 +7332,24 @@ static int init_sched_domains(const struct cpumask *cpu_map) doms_cur = &fallback_doms; cpumask_andnot(doms_cur[0], cpu_map, cpu_isolated_map); dattr_cur = NULL; - err = build_sched_domains(doms_cur[0]); + err = build_sched_domains(doms_cur[0], NULL); register_sched_domain_sysctl(); return err; } -static void destroy_sched_domains(const struct cpumask *cpu_map, - struct cpumask *tmpmask) -{ -} - /* * Detach sched domains from a group of cpus specified in cpu_map * These cpus will now be attached to the NULL domain */ static void detach_destroy_domains(const struct cpumask *cpu_map) { - /* Save because hotplug lock held. */ - static DECLARE_BITMAP(tmpmask, CONFIG_NR_CPUS); int i; + rcu_read_lock(); for_each_cpu(i, cpu_map) cpu_attach_domain(NULL, &def_root_domain, i); - synchronize_sched(); - destroy_sched_domains(cpu_map, to_cpumask(tmpmask)); + rcu_read_unlock(); } /* handle null as "default" */ @@ -7538,8 +7438,7 @@ match1: goto match2; } /* no match - add a new doms_new */ - __build_sched_domains(doms_new[i], - dattr_new ? dattr_new + i : NULL); + build_sched_domains(doms_new[i], dattr_new ? dattr_new + i : NULL); match2: ; } diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 4ee50f0af8d..4a8ac7c2a18 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -1622,6 +1622,7 @@ static int select_idle_sibling(struct task_struct *p, int target) /* * Otherwise, iterate the domains and find an elegible idle cpu. */ + rcu_read_lock(); for_each_domain(target, sd) { if (!(sd->flags & SD_SHARE_PKG_RESOURCES)) break; @@ -1641,6 +1642,7 @@ static int select_idle_sibling(struct task_struct *p, int target) cpumask_test_cpu(prev_cpu, sched_domain_span(sd))) break; } + rcu_read_unlock(); return target; } @@ -1673,6 +1675,7 @@ select_task_rq_fair(struct rq *rq, struct task_struct *p, int sd_flag, int wake_ new_cpu = prev_cpu; } + rcu_read_lock(); for_each_domain(cpu, tmp) { if (!(tmp->flags & SD_LOAD_BALANCE)) continue; @@ -1723,9 +1726,10 @@ select_task_rq_fair(struct rq *rq, struct task_struct *p, int sd_flag, int wake_ if (affine_sd) { if (cpu == prev_cpu || wake_affine(affine_sd, p, sync)) - return select_idle_sibling(p, cpu); - else - return select_idle_sibling(p, prev_cpu); + prev_cpu = cpu; + + new_cpu = select_idle_sibling(p, prev_cpu); + goto unlock; } while (sd) { @@ -1766,6 +1770,8 @@ select_task_rq_fair(struct rq *rq, struct task_struct *p, int sd_flag, int wake_ } /* while loop will break here if sd == NULL */ } +unlock: + rcu_read_unlock(); return new_cpu; } @@ -3462,6 +3468,7 @@ static void idle_balance(int this_cpu, struct rq *this_rq) raw_spin_unlock(&this_rq->lock); update_shares(this_cpu); + rcu_read_lock(); for_each_domain(this_cpu, sd) { unsigned long interval; int balance = 1; @@ -3483,6 +3490,7 @@ static void idle_balance(int this_cpu, struct rq *this_rq) break; } } + rcu_read_unlock(); raw_spin_lock(&this_rq->lock); @@ -3531,6 +3539,7 @@ static int active_load_balance_cpu_stop(void *data) double_lock_balance(busiest_rq, target_rq); /* Search for an sd spanning us and the target CPU. */ + rcu_read_lock(); for_each_domain(target_cpu, sd) { if ((sd->flags & SD_LOAD_BALANCE) && cpumask_test_cpu(busiest_cpu, sched_domain_span(sd))) @@ -3546,6 +3555,7 @@ static int active_load_balance_cpu_stop(void *data) else schedstat_inc(sd, alb_failed); } + rcu_read_unlock(); double_unlock_balance(busiest_rq, target_rq); out_unlock: busiest_rq->active_balance = 0; @@ -3672,6 +3682,7 @@ static int find_new_ilb(int cpu) { struct sched_domain *sd; struct sched_group *ilb_group; + int ilb = nr_cpu_ids; /* * Have idle load balancer selection from semi-idle packages only @@ -3687,20 +3698,25 @@ static int find_new_ilb(int cpu) if (cpumask_weight(nohz.idle_cpus_mask) < 2) goto out_done; + rcu_read_lock(); for_each_flag_domain(cpu, sd, SD_POWERSAVINGS_BALANCE) { ilb_group = sd->groups; do { - if (is_semi_idle_group(ilb_group)) - return cpumask_first(nohz.grp_idle_mask); + if (is_semi_idle_group(ilb_group)) { + ilb = cpumask_first(nohz.grp_idle_mask); + goto unlock; + } ilb_group = ilb_group->next; } while (ilb_group != sd->groups); } +unlock: + rcu_read_unlock(); out_done: - return nr_cpu_ids; + return ilb; } #else /* (CONFIG_SCHED_MC || CONFIG_SCHED_SMT) */ static inline int find_new_ilb(int call_cpu) @@ -3845,6 +3861,7 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle) update_shares(cpu); + rcu_read_lock(); for_each_domain(cpu, sd) { if (!(sd->flags & SD_LOAD_BALANCE)) continue; @@ -3890,6 +3907,7 @@ out: if (!balance) break; } + rcu_read_unlock(); /* * next_balance will be updated only when there is a need. -- cgit v1.2.3-70-g09d2 From 3859173d43658d51a749bc0201b943922577d39c Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 7 Apr 2011 14:09:53 +0200 Subject: sched: Reduce some allocation pressure Since we now allocate SD_LV_MAX * nr_cpu_ids sched_domain/sched_group structures when rebuilding the scheduler toplogy it might make sense to shrink that depending on the CONFIG_ options. This is only needed until we get rid of SD_LV_* alltogether and provide a full dynamic topology interface. Signed-off-by: Peter Zijlstra Cc: Mike Galbraith Cc: Nick Piggin Cc: Linus Torvalds Cc: Andrew Morton Link: http://lkml.kernel.org/r/20110407122942.406226449@chello.nl Signed-off-by: Ingo Molnar --- include/linux/sched.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 020b79d6c48..5a9168b01db 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -897,12 +897,20 @@ static inline struct cpumask *sched_group_cpus(struct sched_group *sg) enum sched_domain_level { SD_LV_NONE = 0, +#ifdef CONFIG_SCHED_SMT SD_LV_SIBLING, +#endif +#ifdef CONFIG_SCHED_MC SD_LV_MC, +#endif +#ifdef CONFIG_SCHED_BOOK SD_LV_BOOK, +#endif SD_LV_CPU, +#ifdef CONFIG_NUMA SD_LV_NODE, SD_LV_ALLNODES, +#endif SD_LV_MAX }; -- cgit v1.2.3-70-g09d2 From 7dd04b730749f957c116f363524fd622b05e5141 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 7 Apr 2011 14:09:56 +0200 Subject: sched: Remove some dead code Signed-off-by: Peter Zijlstra Cc: Mike Galbraith Cc: Nick Piggin Cc: Linus Torvalds Cc: Andrew Morton Link: http://lkml.kernel.org/r/20110407122942.553814623@chello.nl Signed-off-by: Ingo Molnar --- include/linux/sched.h | 6 ------ kernel/sched.c | 16 ---------------- 2 files changed, 22 deletions(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 5a9168b01db..09d9e02f2b6 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -883,9 +883,6 @@ struct sched_group { * NOTE: this field is variable length. (Allocated dynamically * by attaching extra space to the end of the structure, * depending on how many CPUs the kernel has booted up with) - * - * It is also be embedded into static data structures at build - * time. (See 'struct static_sched_group' in kernel/sched.c) */ unsigned long cpumask[0]; }; @@ -994,9 +991,6 @@ struct sched_domain { * NOTE: this field is variable length. (Allocated dynamically * by attaching extra space to the end of the structure, * depending on how many CPUs the kernel has booted up with) - * - * It is also be embedded into static data structures at build - * time. (See 'struct static_sched_domain' in kernel/sched.c) */ unsigned long span[0]; }; diff --git a/kernel/sched.c b/kernel/sched.c index f4d3a624c50..5ec685ce516 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -6816,22 +6816,6 @@ static void sched_domain_node_span(int node, struct cpumask *span) int sched_smt_power_savings = 0, sched_mc_power_savings = 0; -/* - * The cpus mask in sched_group and sched_domain hangs off the end. - * - * ( See the the comments in include/linux/sched.h:struct sched_group - * and struct sched_domain. ) - */ -struct static_sched_group { - struct sched_group sg; - DECLARE_BITMAP(cpus, CONFIG_NR_CPUS); -}; - -struct static_sched_domain { - struct sched_domain sd; - DECLARE_BITMAP(span, CONFIG_NR_CPUS); -}; - struct sd_data { struct sched_domain **__percpu sd; struct sched_group **__percpu sg; -- cgit v1.2.3-70-g09d2 From 60495e7760d8ee364695006af37309b0755e0e17 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 7 Apr 2011 14:10:04 +0200 Subject: sched: Dynamic sched_domain::level Remove the SD_LV_ enum and use dynamic level assignments. Signed-off-by: Peter Zijlstra Cc: Mike Galbraith Cc: Nick Piggin Cc: Linus Torvalds Cc: Andrew Morton Link: http://lkml.kernel.org/r/20110407122942.969433965@chello.nl Signed-off-by: Ingo Molnar --- include/linux/sched.h | 23 +++-------------------- kernel/cpuset.c | 2 +- kernel/sched.c | 9 ++++++--- 3 files changed, 10 insertions(+), 24 deletions(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 09d9e02f2b6..e43e5b0ab0b 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -892,25 +892,6 @@ static inline struct cpumask *sched_group_cpus(struct sched_group *sg) return to_cpumask(sg->cpumask); } -enum sched_domain_level { - SD_LV_NONE = 0, -#ifdef CONFIG_SCHED_SMT - SD_LV_SIBLING, -#endif -#ifdef CONFIG_SCHED_MC - SD_LV_MC, -#endif -#ifdef CONFIG_SCHED_BOOK - SD_LV_BOOK, -#endif - SD_LV_CPU, -#ifdef CONFIG_NUMA - SD_LV_NODE, - SD_LV_ALLNODES, -#endif - SD_LV_MAX -}; - struct sched_domain_attr { int relax_domain_level; }; @@ -919,6 +900,8 @@ struct sched_domain_attr { .relax_domain_level = -1, \ } +extern int sched_domain_level_max; + struct sched_domain { /* These fields must be setup */ struct sched_domain *parent; /* top domain must be null terminated */ @@ -936,7 +919,7 @@ struct sched_domain { unsigned int forkexec_idx; unsigned int smt_gain; int flags; /* See SD_* */ - enum sched_domain_level level; + int level; /* Runtime fields. */ unsigned long last_balance; /* init to jiffies. units in jiffies */ diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 33eee16addb..2bb8c2e98ff 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -1159,7 +1159,7 @@ int current_cpuset_is_being_rebound(void) static int update_relax_domain_level(struct cpuset *cs, s64 val) { #ifdef CONFIG_SMP - if (val < -1 || val >= SD_LV_MAX) + if (val < -1 || val >= sched_domain_level_max) return -EINVAL; #endif diff --git a/kernel/sched.c b/kernel/sched.c index 3231e199742..506cb8147c7 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -6966,7 +6966,6 @@ sd_init_##type(struct sched_domain_topology_level *tl, int cpu) \ { \ struct sched_domain *sd = *per_cpu_ptr(tl->data.sd, cpu); \ *sd = SD_##type##_INIT; \ - sd->level = SD_LV_##type; \ SD_INIT_NAME(sd, type); \ sd->private = &tl->data; \ return sd; \ @@ -6988,13 +6987,14 @@ SD_INIT_FUNC(CPU) #endif static int default_relax_domain_level = -1; +int sched_domain_level_max; static int __init setup_relax_domain_level(char *str) { unsigned long val; val = simple_strtoul(str, NULL, 0); - if (val < SD_LV_MAX) + if (val < sched_domain_level_max) default_relax_domain_level = val; return 1; @@ -7173,8 +7173,11 @@ struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl, set_domain_attribute(sd, attr); cpumask_and(sched_domain_span(sd), cpu_map, tl->mask(cpu)); - if (child) + if (child) { + sd->level = child->level + 1; + sched_domain_level_max = max(sched_domain_level_max, sd->level); child->parent = sd; + } sd->child = child; return sd; -- cgit v1.2.3-70-g09d2 From 184748cc50b2dceb8287f9fb657eda48ff8fcfe7 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 5 Apr 2011 17:23:39 +0200 Subject: sched: Provide scheduler_ipi() callback in response to smp_send_reschedule() For future rework of try_to_wake_up() we'd like to push part of that function onto the CPU the task is actually going to run on. In order to do so we need a generic callback from the existing scheduler IPI. This patch introduces such a generic callback: scheduler_ipi() and implements it as a NOP. BenH notes: PowerPC might use this IPI on offline CPUs under rare conditions! Acked-by: Russell King Acked-by: Martin Schwidefsky Acked-by: Chris Metcalf Acked-by: Jesper Nilsson Acked-by: Benjamin Herrenschmidt Signed-off-by: Ralf Baechle Reviewed-by: Frank Rowand Cc: Mike Galbraith Cc: Nick Piggin Cc: Linus Torvalds Cc: Andrew Morton Signed-off-by: Ingo Molnar Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/20110405152728.744338123@chello.nl --- arch/alpha/kernel/smp.c | 3 +-- arch/arm/kernel/smp.c | 5 +---- arch/blackfin/mach-common/smp.c | 3 +++ arch/cris/arch-v32/kernel/smp.c | 13 ++++++++----- arch/ia64/kernel/irq_ia64.c | 2 ++ arch/ia64/xen/irq_xen.c | 10 +++++++++- arch/m32r/kernel/smp.c | 4 +--- arch/mips/cavium-octeon/smp.c | 2 ++ arch/mips/kernel/smtc.c | 2 +- arch/mips/mti-malta/malta-int.c | 2 ++ arch/mips/pmc-sierra/yosemite/smp.c | 4 ++++ arch/mips/sgi-ip27/ip27-irq.c | 2 ++ arch/mips/sibyte/bcm1480/smp.c | 7 +++---- arch/mips/sibyte/sb1250/smp.c | 7 +++---- arch/mn10300/kernel/smp.c | 5 +---- arch/parisc/kernel/smp.c | 5 +---- arch/powerpc/kernel/smp.c | 4 ++-- arch/s390/kernel/smp.c | 6 +++--- arch/sh/kernel/smp.c | 2 ++ arch/sparc/kernel/smp_32.c | 4 +++- arch/sparc/kernel/smp_64.c | 1 + arch/tile/kernel/smp.c | 6 +----- arch/um/kernel/smp.c | 2 +- arch/x86/kernel/smp.c | 5 ++--- arch/x86/xen/smp.c | 5 ++--- include/linux/sched.h | 2 ++ 26 files changed, 63 insertions(+), 50 deletions(-) (limited to 'include') diff --git a/arch/alpha/kernel/smp.c b/arch/alpha/kernel/smp.c index 42aa078a5e4..5a621c6d22a 100644 --- a/arch/alpha/kernel/smp.c +++ b/arch/alpha/kernel/smp.c @@ -585,8 +585,7 @@ handle_ipi(struct pt_regs *regs) switch (which) { case IPI_RESCHEDULE: - /* Reschedule callback. Everything to be done - is done by the interrupt return path. */ + scheduler_ipi(); break; case IPI_CALL_FUNC: diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 8fe05ad932e..7a561eb731e 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -560,10 +560,7 @@ asmlinkage void __exception_irq_entry do_IPI(int ipinr, struct pt_regs *regs) break; case IPI_RESCHEDULE: - /* - * nothing more to do - eveything is - * done on the interrupt return path - */ + scheduler_ipi(); break; case IPI_CALL_FUNC: diff --git a/arch/blackfin/mach-common/smp.c b/arch/blackfin/mach-common/smp.c index 6e17a265c4d..326bb86f4d2 100644 --- a/arch/blackfin/mach-common/smp.c +++ b/arch/blackfin/mach-common/smp.c @@ -164,6 +164,9 @@ static irqreturn_t ipi_handler_int1(int irq, void *dev_instance) while (msg_queue->count) { msg = &msg_queue->ipi_message[msg_queue->head]; switch (msg->type) { + case BFIN_IPI_RESCHEDULE: + scheduler_ipi(); + break; case BFIN_IPI_CALL_FUNC: spin_unlock_irqrestore(&msg_queue->lock, flags); ipi_call_function(cpu, msg); diff --git a/arch/cris/arch-v32/kernel/smp.c b/arch/cris/arch-v32/kernel/smp.c index 4c9e3e1ba5d..66cc75657e2 100644 --- a/arch/cris/arch-v32/kernel/smp.c +++ b/arch/cris/arch-v32/kernel/smp.c @@ -342,15 +342,18 @@ irqreturn_t crisv32_ipi_interrupt(int irq, void *dev_id) ipi = REG_RD(intr_vect, irq_regs[smp_processor_id()], rw_ipi); + if (ipi.vector & IPI_SCHEDULE) { + scheduler_ipi(); + } if (ipi.vector & IPI_CALL) { - func(info); + func(info); } if (ipi.vector & IPI_FLUSH_TLB) { - if (flush_mm == FLUSH_ALL) - __flush_tlb_all(); - else if (flush_vma == FLUSH_ALL) + if (flush_mm == FLUSH_ALL) + __flush_tlb_all(); + else if (flush_vma == FLUSH_ALL) __flush_tlb_mm(flush_mm); - else + else __flush_tlb_page(flush_vma, flush_addr); } diff --git a/arch/ia64/kernel/irq_ia64.c b/arch/ia64/kernel/irq_ia64.c index 5b704740f16..782c3a357f2 100644 --- a/arch/ia64/kernel/irq_ia64.c +++ b/arch/ia64/kernel/irq_ia64.c @@ -31,6 +31,7 @@ #include #include #include +#include #include #include @@ -496,6 +497,7 @@ ia64_handle_irq (ia64_vector vector, struct pt_regs *regs) smp_local_flush_tlb(); kstat_incr_irqs_this_cpu(irq, desc); } else if (unlikely(IS_RESCHEDULE(vector))) { + scheduler_ipi(); kstat_incr_irqs_this_cpu(irq, desc); } else { ia64_setreg(_IA64_REG_CR_TPR, vector); diff --git a/arch/ia64/xen/irq_xen.c b/arch/ia64/xen/irq_xen.c index 108bb858acf..b279e142c63 100644 --- a/arch/ia64/xen/irq_xen.c +++ b/arch/ia64/xen/irq_xen.c @@ -92,6 +92,8 @@ static unsigned short saved_irq_cnt; static int xen_slab_ready; #ifdef CONFIG_SMP +#include + /* Dummy stub. Though we may check XEN_RESCHEDULE_VECTOR before __do_IRQ, * it ends up to issue several memory accesses upon percpu data and * thus adds unnecessary traffic to other paths. @@ -99,7 +101,13 @@ static int xen_slab_ready; static irqreturn_t xen_dummy_handler(int irq, void *dev_id) { + return IRQ_HANDLED; +} +static irqreturn_t +xen_resched_handler(int irq, void *dev_id) +{ + scheduler_ipi(); return IRQ_HANDLED; } @@ -110,7 +118,7 @@ static struct irqaction xen_ipi_irqaction = { }; static struct irqaction xen_resched_irqaction = { - .handler = xen_dummy_handler, + .handler = xen_resched_handler, .flags = IRQF_DISABLED, .name = "resched" }; diff --git a/arch/m32r/kernel/smp.c b/arch/m32r/kernel/smp.c index 31cef20b299..fc10b39893d 100644 --- a/arch/m32r/kernel/smp.c +++ b/arch/m32r/kernel/smp.c @@ -122,8 +122,6 @@ void smp_send_reschedule(int cpu_id) * * Description: This routine executes on CPU which received * 'RESCHEDULE_IPI'. - * Rescheduling is processed at the exit of interrupt - * operation. * * Born on Date: 2002.02.05 * @@ -138,7 +136,7 @@ void smp_send_reschedule(int cpu_id) *==========================================================================*/ void smp_reschedule_interrupt(void) { - /* nothing to do */ + scheduler_ipi(); } /*==========================================================================* diff --git a/arch/mips/cavium-octeon/smp.c b/arch/mips/cavium-octeon/smp.c index ba78b21cc8d..76923eeb58b 100644 --- a/arch/mips/cavium-octeon/smp.c +++ b/arch/mips/cavium-octeon/smp.c @@ -44,6 +44,8 @@ static irqreturn_t mailbox_interrupt(int irq, void *dev_id) if (action & SMP_CALL_FUNCTION) smp_call_function_interrupt(); + if (action & SMP_RESCHEDULE_YOURSELF) + scheduler_ipi(); /* Check if we've been told to flush the icache */ if (action & SMP_ICACHE_FLUSH) diff --git a/arch/mips/kernel/smtc.c b/arch/mips/kernel/smtc.c index 5a88cc4ccd5..cedac463374 100644 --- a/arch/mips/kernel/smtc.c +++ b/arch/mips/kernel/smtc.c @@ -929,7 +929,7 @@ static void post_direct_ipi(int cpu, struct smtc_ipi *pipi) static void ipi_resched_interrupt(void) { - /* Return from interrupt should be enough to cause scheduler check */ + scheduler_ipi(); } static void ipi_call_interrupt(void) diff --git a/arch/mips/mti-malta/malta-int.c b/arch/mips/mti-malta/malta-int.c index 9027061f0ea..7d93e6fbfa5 100644 --- a/arch/mips/mti-malta/malta-int.c +++ b/arch/mips/mti-malta/malta-int.c @@ -309,6 +309,8 @@ static void ipi_call_dispatch(void) static irqreturn_t ipi_resched_interrupt(int irq, void *dev_id) { + scheduler_ipi(); + return IRQ_HANDLED; } diff --git a/arch/mips/pmc-sierra/yosemite/smp.c b/arch/mips/pmc-sierra/yosemite/smp.c index efc9e889b34..2608752898c 100644 --- a/arch/mips/pmc-sierra/yosemite/smp.c +++ b/arch/mips/pmc-sierra/yosemite/smp.c @@ -55,6 +55,8 @@ void titan_mailbox_irq(void) if (status & 0x2) smp_call_function_interrupt(); + if (status & 0x4) + scheduler_ipi(); break; case 1: @@ -63,6 +65,8 @@ void titan_mailbox_irq(void) if (status & 0x2) smp_call_function_interrupt(); + if (status & 0x4) + scheduler_ipi(); break; } } diff --git a/arch/mips/sgi-ip27/ip27-irq.c b/arch/mips/sgi-ip27/ip27-irq.c index 0a04603d577..b18b04e4857 100644 --- a/arch/mips/sgi-ip27/ip27-irq.c +++ b/arch/mips/sgi-ip27/ip27-irq.c @@ -147,8 +147,10 @@ static void ip27_do_irq_mask0(void) #ifdef CONFIG_SMP if (pend0 & (1UL << CPU_RESCHED_A_IRQ)) { LOCAL_HUB_CLR_INTR(CPU_RESCHED_A_IRQ); + scheduler_ipi(); } else if (pend0 & (1UL << CPU_RESCHED_B_IRQ)) { LOCAL_HUB_CLR_INTR(CPU_RESCHED_B_IRQ); + scheduler_ipi(); } else if (pend0 & (1UL << CPU_CALL_A_IRQ)) { LOCAL_HUB_CLR_INTR(CPU_CALL_A_IRQ); smp_call_function_interrupt(); diff --git a/arch/mips/sibyte/bcm1480/smp.c b/arch/mips/sibyte/bcm1480/smp.c index 47b347c992e..d667875be56 100644 --- a/arch/mips/sibyte/bcm1480/smp.c +++ b/arch/mips/sibyte/bcm1480/smp.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include @@ -189,10 +190,8 @@ void bcm1480_mailbox_interrupt(void) /* Clear the mailbox to clear the interrupt */ __raw_writeq(((u64)action)<<48, mailbox_0_clear_regs[cpu]); - /* - * Nothing to do for SMP_RESCHEDULE_YOURSELF; returning from the - * interrupt will do the reschedule for us - */ + if (action & SMP_RESCHEDULE_YOURSELF) + scheduler_ipi(); if (action & SMP_CALL_FUNCTION) smp_call_function_interrupt(); diff --git a/arch/mips/sibyte/sb1250/smp.c b/arch/mips/sibyte/sb1250/smp.c index c00a5cb1128..38e7f6bd792 100644 --- a/arch/mips/sibyte/sb1250/smp.c +++ b/arch/mips/sibyte/sb1250/smp.c @@ -21,6 +21,7 @@ #include #include #include +#include #include #include @@ -177,10 +178,8 @@ void sb1250_mailbox_interrupt(void) /* Clear the mailbox to clear the interrupt */ ____raw_writeq(((u64)action) << 48, mailbox_clear_regs[cpu]); - /* - * Nothing to do for SMP_RESCHEDULE_YOURSELF; returning from the - * interrupt will do the reschedule for us - */ + if (action & SMP_RESCHEDULE_YOURSELF) + scheduler_ipi(); if (action & SMP_CALL_FUNCTION) smp_call_function_interrupt(); diff --git a/arch/mn10300/kernel/smp.c b/arch/mn10300/kernel/smp.c index 226c826a219..83fb2791223 100644 --- a/arch/mn10300/kernel/smp.c +++ b/arch/mn10300/kernel/smp.c @@ -494,14 +494,11 @@ void smp_send_stop(void) * @irq: The interrupt number. * @dev_id: The device ID. * - * We need do nothing here, since the scheduling will be effected on our way - * back through entry.S. - * * Returns IRQ_HANDLED to indicate we handled the interrupt successfully. */ static irqreturn_t smp_reschedule_interrupt(int irq, void *dev_id) { - /* do nothing */ + scheduler_ipi(); return IRQ_HANDLED; } diff --git a/arch/parisc/kernel/smp.c b/arch/parisc/kernel/smp.c index 69d63d354ef..828305f19cf 100644 --- a/arch/parisc/kernel/smp.c +++ b/arch/parisc/kernel/smp.c @@ -155,10 +155,7 @@ ipi_interrupt(int irq, void *dev_id) case IPI_RESCHEDULE: smp_debug(100, KERN_DEBUG "CPU%d IPI_RESCHEDULE\n", this_cpu); - /* - * Reschedule callback. Everything to be - * done is done by the interrupt return path. - */ + scheduler_ipi(); break; case IPI_CALL_FUNC: diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index cbdbb14be4b..9f9c204bef6 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -116,7 +116,7 @@ void smp_message_recv(int msg) generic_smp_call_function_interrupt(); break; case PPC_MSG_RESCHEDULE: - /* we notice need_resched on exit */ + scheduler_ipi(); break; case PPC_MSG_CALL_FUNC_SINGLE: generic_smp_call_function_single_interrupt(); @@ -146,7 +146,7 @@ static irqreturn_t call_function_action(int irq, void *data) static irqreturn_t reschedule_action(int irq, void *data) { - /* we just need the return path side effect of checking need_resched */ + scheduler_ipi(); return IRQ_HANDLED; } diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 63a97db83f9..63c7d9ff220 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -165,12 +165,12 @@ static void do_ext_call_interrupt(unsigned int ext_int_code, kstat_cpu(smp_processor_id()).irqs[EXTINT_IPI]++; /* * handle bit signal external calls - * - * For the ec_schedule signal we have to do nothing. All the work - * is done automatically when we return from the interrupt. */ bits = xchg(&S390_lowcore.ext_call_fast, 0); + if (test_bit(ec_schedule, &bits)) + scheduler_ipi(); + if (test_bit(ec_call_function, &bits)) generic_smp_call_function_interrupt(); diff --git a/arch/sh/kernel/smp.c b/arch/sh/kernel/smp.c index 509b36b4511..6207561ea34 100644 --- a/arch/sh/kernel/smp.c +++ b/arch/sh/kernel/smp.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include #include @@ -323,6 +324,7 @@ void smp_message_recv(unsigned int msg) generic_smp_call_function_interrupt(); break; case SMP_MSG_RESCHEDULE: + scheduler_ipi(); break; case SMP_MSG_FUNCTION_SINGLE: generic_smp_call_function_single_interrupt(); diff --git a/arch/sparc/kernel/smp_32.c b/arch/sparc/kernel/smp_32.c index 91c10fb7085..f95690c167b 100644 --- a/arch/sparc/kernel/smp_32.c +++ b/arch/sparc/kernel/smp_32.c @@ -125,7 +125,9 @@ struct linux_prom_registers smp_penguin_ctable __cpuinitdata = { 0 }; void smp_send_reschedule(int cpu) { - /* See sparc64 */ + /* + * XXX missing reschedule IPI, see scheduler_ipi() + */ } void smp_send_stop(void) diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index 3e94a8c2323..9478da7fdb3 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -1368,6 +1368,7 @@ void smp_send_reschedule(int cpu) void __irq_entry smp_receive_signal_client(int irq, struct pt_regs *regs) { clear_softint(1 << irq); + scheduler_ipi(); } /* This is a nop because we capture all other cpus diff --git a/arch/tile/kernel/smp.c b/arch/tile/kernel/smp.c index a4293102ef8..c52224d5ed4 100644 --- a/arch/tile/kernel/smp.c +++ b/arch/tile/kernel/smp.c @@ -189,12 +189,8 @@ void flush_icache_range(unsigned long start, unsigned long end) /* Called when smp_send_reschedule() triggers IRQ_RESCHEDULE. */ static irqreturn_t handle_reschedule_ipi(int irq, void *token) { - /* - * Nothing to do here; when we return from interrupt, the - * rescheduling will occur there. But do bump the interrupt - * profiler count in the meantime. - */ __get_cpu_var(irq_stat).irq_resched_count++; + scheduler_ipi(); return IRQ_HANDLED; } diff --git a/arch/um/kernel/smp.c b/arch/um/kernel/smp.c index 106bf27e2a9..eefb107d2d7 100644 --- a/arch/um/kernel/smp.c +++ b/arch/um/kernel/smp.c @@ -173,7 +173,7 @@ void IPI_handler(int cpu) break; case 'R': - set_tsk_need_resched(current); + scheduler_ipi(); break; case 'S': diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c index 513deac7228..013e7eba83b 100644 --- a/arch/x86/kernel/smp.c +++ b/arch/x86/kernel/smp.c @@ -194,14 +194,13 @@ static void native_stop_other_cpus(int wait) } /* - * Reschedule call back. Nothing to do, - * all the work is done automatically when - * we return from the interrupt. + * Reschedule call back. */ void smp_reschedule_interrupt(struct pt_regs *regs) { ack_APIC_irq(); inc_irq_stat(irq_resched_count); + scheduler_ipi(); /* * KVM uses this interrupt to force a cpu out of guest mode */ diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 30612441ed9..762b46ab14d 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -46,13 +46,12 @@ static irqreturn_t xen_call_function_interrupt(int irq, void *dev_id); static irqreturn_t xen_call_function_single_interrupt(int irq, void *dev_id); /* - * Reschedule call back. Nothing to do, - * all the work is done automatically when - * we return from the interrupt. + * Reschedule call back. */ static irqreturn_t xen_reschedule_interrupt(int irq, void *dev_id) { inc_irq_stat(irq_resched_count); + scheduler_ipi(); return IRQ_HANDLED; } diff --git a/include/linux/sched.h b/include/linux/sched.h index 4ec2c027e92..758e27afcda 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2189,8 +2189,10 @@ extern void set_task_comm(struct task_struct *tsk, char *from); extern char *get_task_comm(char *to, struct task_struct *tsk); #ifdef CONFIG_SMP +static inline void scheduler_ipi(void) { } extern unsigned long wait_task_inactive(struct task_struct *, long match_state); #else +static inline void scheduler_ipi(void) { } static inline unsigned long wait_task_inactive(struct task_struct *p, long match_state) { -- cgit v1.2.3-70-g09d2 From 3ca7a440da394808571dad32d33d3bc0389982e6 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 5 Apr 2011 17:23:40 +0200 Subject: sched: Always provide p->on_cpu Always provide p->on_cpu so that we can determine if its on a cpu without having to lock the rq. Reviewed-by: Frank Rowand Signed-off-by: Peter Zijlstra Cc: Mike Galbraith Cc: Nick Piggin Cc: Linus Torvalds Cc: Andrew Morton Link: http://lkml.kernel.org/r/20110405152728.785452014@chello.nl Signed-off-by: Ingo Molnar --- include/linux/sched.h | 4 +--- kernel/sched.c | 46 +++++++++++++++++++++++++++++----------------- 2 files changed, 30 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 758e27afcda..3435837e89f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1200,9 +1200,7 @@ struct task_struct { int lock_depth; /* BKL lock depth */ #ifdef CONFIG_SMP -#ifdef __ARCH_WANT_UNLOCKED_CTXSW - int oncpu; -#endif + int on_cpu; #endif int prio, static_prio, normal_prio; diff --git a/kernel/sched.c b/kernel/sched.c index a187c3fe027..cd2593e1a3e 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -838,18 +838,39 @@ static inline int task_current(struct rq *rq, struct task_struct *p) return rq->curr == p; } -#ifndef __ARCH_WANT_UNLOCKED_CTXSW static inline int task_running(struct rq *rq, struct task_struct *p) { +#ifdef CONFIG_SMP + return p->on_cpu; +#else return task_current(rq, p); +#endif } +#ifndef __ARCH_WANT_UNLOCKED_CTXSW static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next) { +#ifdef CONFIG_SMP + /* + * We can optimise this out completely for !SMP, because the + * SMP rebalancing from interrupt is the only thing that cares + * here. + */ + next->on_cpu = 1; +#endif } static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) { +#ifdef CONFIG_SMP + /* + * After ->on_cpu is cleared, the task can be moved to a different CPU. + * We must ensure this doesn't happen until the switch is completely + * finished. + */ + smp_wmb(); + prev->on_cpu = 0; +#endif #ifdef CONFIG_DEBUG_SPINLOCK /* this is a valid case when another task releases the spinlock */ rq->lock.owner = current; @@ -865,15 +886,6 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) } #else /* __ARCH_WANT_UNLOCKED_CTXSW */ -static inline int task_running(struct rq *rq, struct task_struct *p) -{ -#ifdef CONFIG_SMP - return p->oncpu; -#else - return task_current(rq, p); -#endif -} - static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next) { #ifdef CONFIG_SMP @@ -882,7 +894,7 @@ static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next) * SMP rebalancing from interrupt is the only thing that cares * here. */ - next->oncpu = 1; + next->on_cpu = 1; #endif #ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW raw_spin_unlock_irq(&rq->lock); @@ -895,12 +907,12 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) { #ifdef CONFIG_SMP /* - * After ->oncpu is cleared, the task can be moved to a different CPU. + * After ->on_cpu is cleared, the task can be moved to a different CPU. * We must ensure this doesn't happen until the switch is completely * finished. */ smp_wmb(); - prev->oncpu = 0; + prev->on_cpu = 0; #endif #ifndef __ARCH_WANT_INTERRUPTS_ON_CTXSW local_irq_enable(); @@ -2686,8 +2698,8 @@ void sched_fork(struct task_struct *p, int clone_flags) if (likely(sched_info_on())) memset(&p->sched_info, 0, sizeof(p->sched_info)); #endif -#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW) - p->oncpu = 0; +#if defined(CONFIG_SMP) + p->on_cpu = 0; #endif #ifdef CONFIG_PREEMPT /* Want to start with kernel preemption disabled. */ @@ -5776,8 +5788,8 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu) rcu_read_unlock(); rq->curr = rq->idle = idle; -#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW) - idle->oncpu = 1; +#if defined(CONFIG_SMP) + idle->on_cpu = 1; #endif raw_spin_unlock_irqrestore(&rq->lock, flags); -- cgit v1.2.3-70-g09d2 From c6eb3dda25892f1f974f5420f63e6721aab02f6f Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 5 Apr 2011 17:23:41 +0200 Subject: mutex: Use p->on_cpu for the adaptive spin Since we now have p->on_cpu unconditionally available, use it to re-implement mutex_spin_on_owner. Requested-by: Thomas Gleixner Reviewed-by: Frank Rowand Cc: Mike Galbraith Cc: Nick Piggin Cc: Linus Torvalds Cc: Andrew Morton Signed-off-by: Ingo Molnar Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/20110405152728.826338173@chello.nl --- include/linux/mutex.h | 2 +- include/linux/sched.h | 2 +- kernel/mutex-debug.c | 2 +- kernel/mutex-debug.h | 2 +- kernel/mutex.c | 2 +- kernel/mutex.h | 2 +- kernel/sched.c | 83 ++++++++++++++++++++------------------------------- 7 files changed, 39 insertions(+), 56 deletions(-) (limited to 'include') diff --git a/include/linux/mutex.h b/include/linux/mutex.h index 94b48bd40dd..c75471db576 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -51,7 +51,7 @@ struct mutex { spinlock_t wait_lock; struct list_head wait_list; #if defined(CONFIG_DEBUG_MUTEXES) || defined(CONFIG_SMP) - struct thread_info *owner; + struct task_struct *owner; #endif #ifdef CONFIG_DEBUG_MUTEXES const char *name; diff --git a/include/linux/sched.h b/include/linux/sched.h index 3435837e89f..173850479e2 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -360,7 +360,7 @@ extern signed long schedule_timeout_interruptible(signed long timeout); extern signed long schedule_timeout_killable(signed long timeout); extern signed long schedule_timeout_uninterruptible(signed long timeout); asmlinkage void schedule(void); -extern int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner); +extern int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner); struct nsproxy; struct user_namespace; diff --git a/kernel/mutex-debug.c b/kernel/mutex-debug.c index ec815a960b5..73da83aff41 100644 --- a/kernel/mutex-debug.c +++ b/kernel/mutex-debug.c @@ -75,7 +75,7 @@ void debug_mutex_unlock(struct mutex *lock) return; DEBUG_LOCKS_WARN_ON(lock->magic != lock); - DEBUG_LOCKS_WARN_ON(lock->owner != current_thread_info()); + DEBUG_LOCKS_WARN_ON(lock->owner != current); DEBUG_LOCKS_WARN_ON(!lock->wait_list.prev && !lock->wait_list.next); mutex_clear_owner(lock); } diff --git a/kernel/mutex-debug.h b/kernel/mutex-debug.h index 57d527a16f9..0799fd3e4cf 100644 --- a/kernel/mutex-debug.h +++ b/kernel/mutex-debug.h @@ -29,7 +29,7 @@ extern void debug_mutex_init(struct mutex *lock, const char *name, static inline void mutex_set_owner(struct mutex *lock) { - lock->owner = current_thread_info(); + lock->owner = current; } static inline void mutex_clear_owner(struct mutex *lock) diff --git a/kernel/mutex.c b/kernel/mutex.c index c4195fa9890..fe4706cb0c5 100644 --- a/kernel/mutex.c +++ b/kernel/mutex.c @@ -160,7 +160,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, */ for (;;) { - struct thread_info *owner; + struct task_struct *owner; /* * If we own the BKL, then don't spin. The owner of diff --git a/kernel/mutex.h b/kernel/mutex.h index 67578ca48f9..4115fbf83b1 100644 --- a/kernel/mutex.h +++ b/kernel/mutex.h @@ -19,7 +19,7 @@ #ifdef CONFIG_SMP static inline void mutex_set_owner(struct mutex *lock) { - lock->owner = current_thread_info(); + lock->owner = current; } static inline void mutex_clear_owner(struct mutex *lock) diff --git a/kernel/sched.c b/kernel/sched.c index cd2593e1a3e..55cc50323ce 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -4173,70 +4173,53 @@ need_resched: EXPORT_SYMBOL(schedule); #ifdef CONFIG_MUTEX_SPIN_ON_OWNER -/* - * Look out! "owner" is an entirely speculative pointer - * access and not reliable. - */ -int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner) -{ - unsigned int cpu; - struct rq *rq; - if (!sched_feat(OWNER_SPIN)) - return 0; +static inline bool owner_running(struct mutex *lock, struct task_struct *owner) +{ + bool ret = false; -#ifdef CONFIG_DEBUG_PAGEALLOC - /* - * Need to access the cpu field knowing that - * DEBUG_PAGEALLOC could have unmapped it if - * the mutex owner just released it and exited. - */ - if (probe_kernel_address(&owner->cpu, cpu)) - return 0; -#else - cpu = owner->cpu; -#endif + rcu_read_lock(); + if (lock->owner != owner) + goto fail; /* - * Even if the access succeeded (likely case), - * the cpu field may no longer be valid. + * Ensure we emit the owner->on_cpu, dereference _after_ checking + * lock->owner still matches owner, if that fails, owner might + * point to free()d memory, if it still matches, the rcu_read_lock() + * ensures the memory stays valid. */ - if (cpu >= nr_cpumask_bits) - return 0; + barrier(); - /* - * We need to validate that we can do a - * get_cpu() and that we have the percpu area. - */ - if (!cpu_online(cpu)) - return 0; + ret = owner->on_cpu; +fail: + rcu_read_unlock(); - rq = cpu_rq(cpu); + return ret; +} - for (;;) { - /* - * Owner changed, break to re-assess state. - */ - if (lock->owner != owner) { - /* - * If the lock has switched to a different owner, - * we likely have heavy contention. Return 0 to quit - * optimistic spinning and not contend further: - */ - if (lock->owner) - return 0; - break; - } +/* + * Look out! "owner" is an entirely speculative pointer + * access and not reliable. + */ +int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner) +{ + if (!sched_feat(OWNER_SPIN)) + return 0; - /* - * Is that owner really running on that cpu? - */ - if (task_thread_info(rq->curr) != owner || need_resched()) + while (owner_running(lock, owner)) { + if (need_resched()) return 0; arch_mutex_cpu_relax(); } + /* + * If the owner changed to another task there is likely + * heavy contention, stop spinning. + */ + if (lock->owner) + return 0; + return 1; } #endif -- cgit v1.2.3-70-g09d2 From fd2f4419b4cbe8fe90796df9617c355762afd6a4 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 5 Apr 2011 17:23:44 +0200 Subject: sched: Provide p->on_rq Provide a generic p->on_rq because the p->se.on_rq semantics are unfavourable for lockless wakeups but needed for sched_fair. In particular, p->on_rq is only cleared when we actually dequeue the task in schedule() and not on any random dequeue as done by things like __migrate_task() and __sched_setscheduler(). This also allows us to remove p->se usage from !sched_fair code. Reviewed-by: Frank Rowand Cc: Mike Galbraith Cc: Nick Piggin Cc: Linus Torvalds Cc: Andrew Morton Signed-off-by: Ingo Molnar Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/20110405152728.949545047@chello.nl --- include/linux/sched.h | 1 + kernel/sched.c | 38 ++++++++++++++++++++------------------ kernel/sched_debug.c | 2 +- kernel/sched_rt.c | 16 ++++++++-------- kernel/sched_stoptask.c | 2 +- 5 files changed, 31 insertions(+), 28 deletions(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 173850479e2..b33a700652d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1202,6 +1202,7 @@ struct task_struct { #ifdef CONFIG_SMP int on_cpu; #endif + int on_rq; int prio, static_prio, normal_prio; unsigned int rt_priority; diff --git a/kernel/sched.c b/kernel/sched.c index 4481638f917..dece28e505c 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -1785,7 +1785,6 @@ static void enqueue_task(struct rq *rq, struct task_struct *p, int flags) update_rq_clock(rq); sched_info_queued(p); p->sched_class->enqueue_task(rq, p, flags); - p->se.on_rq = 1; } static void dequeue_task(struct rq *rq, struct task_struct *p, int flags) @@ -1793,7 +1792,6 @@ static void dequeue_task(struct rq *rq, struct task_struct *p, int flags) update_rq_clock(rq); sched_info_dequeued(p); p->sched_class->dequeue_task(rq, p, flags); - p->se.on_rq = 0; } /* @@ -2128,7 +2126,7 @@ static void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags) * A queue event has occurred, and we're going to schedule. In * this case, we can save a useless back to back clock update. */ - if (rq->curr->se.on_rq && test_tsk_need_resched(rq->curr)) + if (rq->curr->on_rq && test_tsk_need_resched(rq->curr)) rq->skip_clock_update = 1; } @@ -2203,7 +2201,7 @@ static bool migrate_task(struct task_struct *p, struct rq *rq) * If the task is not on a runqueue (and not running), then * the next wake-up will properly place the task. */ - return p->se.on_rq || task_running(rq, p); + return p->on_rq || task_running(rq, p); } /* @@ -2263,7 +2261,7 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state) rq = task_rq_lock(p, &flags); trace_sched_wait_task(p); running = task_running(rq, p); - on_rq = p->se.on_rq; + on_rq = p->on_rq; ncsw = 0; if (!match_state || p->state == match_state) ncsw = p->nvcsw | LONG_MIN; /* sets MSB */ @@ -2444,6 +2442,7 @@ ttwu_stat(struct rq *rq, struct task_struct *p, int cpu, int wake_flags) static void ttwu_activate(struct rq *rq, struct task_struct *p, int en_flags) { activate_task(rq, p, en_flags); + p->on_rq = 1; /* if a worker is waking up, notify workqueue */ if (p->flags & PF_WQ_WORKER) @@ -2506,7 +2505,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, cpu = task_cpu(p); - if (p->se.on_rq) + if (p->on_rq) goto out_running; orig_cpu = cpu; @@ -2583,7 +2582,7 @@ static void try_to_wake_up_local(struct task_struct *p) if (!(p->state & TASK_NORMAL)) return; - if (!p->se.on_rq) + if (!p->on_rq) ttwu_activate(rq, p, ENQUEUE_WAKEUP); ttwu_post_activation(p, rq, 0); @@ -2620,19 +2619,21 @@ int wake_up_state(struct task_struct *p, unsigned int state) */ static void __sched_fork(struct task_struct *p) { + p->on_rq = 0; + + p->se.on_rq = 0; p->se.exec_start = 0; p->se.sum_exec_runtime = 0; p->se.prev_sum_exec_runtime = 0; p->se.nr_migrations = 0; p->se.vruntime = 0; + INIT_LIST_HEAD(&p->se.group_node); #ifdef CONFIG_SCHEDSTATS memset(&p->se.statistics, 0, sizeof(p->se.statistics)); #endif INIT_LIST_HEAD(&p->rt.run_list); - p->se.on_rq = 0; - INIT_LIST_HEAD(&p->se.group_node); #ifdef CONFIG_PREEMPT_NOTIFIERS INIT_HLIST_HEAD(&p->preempt_notifiers); @@ -2750,6 +2751,7 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags) rq = task_rq_lock(p, &flags); activate_task(rq, p, 0); + p->on_rq = 1; trace_sched_wakeup_new(p, true); check_preempt_curr(rq, p, WF_FORK); #ifdef CONFIG_SMP @@ -4051,7 +4053,7 @@ static inline void schedule_debug(struct task_struct *prev) static void put_prev_task(struct rq *rq, struct task_struct *prev) { - if (prev->se.on_rq) + if (prev->on_rq) update_rq_clock(rq); prev->sched_class->put_prev_task(rq, prev); } @@ -4126,7 +4128,9 @@ need_resched: if (to_wakeup) try_to_wake_up_local(to_wakeup); } + deactivate_task(rq, prev, DEQUEUE_SLEEP); + prev->on_rq = 0; /* * If we are going to sleep and we have plugged IO queued, make @@ -4695,7 +4699,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio) trace_sched_pi_setprio(p, prio); oldprio = p->prio; prev_class = p->sched_class; - on_rq = p->se.on_rq; + on_rq = p->on_rq; running = task_current(rq, p); if (on_rq) dequeue_task(rq, p, 0); @@ -4743,7 +4747,7 @@ void set_user_nice(struct task_struct *p, long nice) p->static_prio = NICE_TO_PRIO(nice); goto out_unlock; } - on_rq = p->se.on_rq; + on_rq = p->on_rq; if (on_rq) dequeue_task(rq, p, 0); @@ -4877,8 +4881,6 @@ static struct task_struct *find_process_by_pid(pid_t pid) static void __setscheduler(struct rq *rq, struct task_struct *p, int policy, int prio) { - BUG_ON(p->se.on_rq); - p->policy = policy; p->rt_priority = prio; p->normal_prio = normal_prio(p); @@ -5044,7 +5046,7 @@ recheck: raw_spin_unlock_irqrestore(&p->pi_lock, flags); goto recheck; } - on_rq = p->se.on_rq; + on_rq = p->on_rq; running = task_current(rq, p); if (on_rq) deactivate_task(rq, p, 0); @@ -5965,7 +5967,7 @@ static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu) * If we're not on a rq, the next wake-up will ensure we're * placed properly. */ - if (p->se.on_rq) { + if (p->on_rq) { deactivate_task(rq_src, p, 0); set_task_cpu(p, dest_cpu); activate_task(rq_dest, p, 0); @@ -8339,7 +8341,7 @@ static void normalize_task(struct rq *rq, struct task_struct *p) int old_prio = p->prio; int on_rq; - on_rq = p->se.on_rq; + on_rq = p->on_rq; if (on_rq) deactivate_task(rq, p, 0); __setscheduler(rq, p, SCHED_NORMAL, 0); @@ -8682,7 +8684,7 @@ void sched_move_task(struct task_struct *tsk) rq = task_rq_lock(tsk, &flags); running = task_current(rq, tsk); - on_rq = tsk->se.on_rq; + on_rq = tsk->on_rq; if (on_rq) dequeue_task(rq, tsk, 0); diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c index 7bacd83a415..3669bec6e13 100644 --- a/kernel/sched_debug.c +++ b/kernel/sched_debug.c @@ -152,7 +152,7 @@ static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu) read_lock_irqsave(&tasklist_lock, flags); do_each_thread(g, p) { - if (!p->se.on_rq || task_cpu(p) != rq_cpu) + if (!p->on_rq || task_cpu(p) != rq_cpu) continue; print_task(m, rq, p); diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index e7cebdc65f8..9ca4f5f879c 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -1136,7 +1136,7 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p) * The previous task needs to be made eligible for pushing * if it is still active */ - if (p->se.on_rq && p->rt.nr_cpus_allowed > 1) + if (on_rt_rq(&p->rt) && p->rt.nr_cpus_allowed > 1) enqueue_pushable_task(rq, p); } @@ -1287,7 +1287,7 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq) !cpumask_test_cpu(lowest_rq->cpu, &task->cpus_allowed) || task_running(rq, task) || - !task->se.on_rq)) { + !task->on_rq)) { raw_spin_unlock(&lowest_rq->lock); lowest_rq = NULL; @@ -1321,7 +1321,7 @@ static struct task_struct *pick_next_pushable_task(struct rq *rq) BUG_ON(task_current(rq, p)); BUG_ON(p->rt.nr_cpus_allowed <= 1); - BUG_ON(!p->se.on_rq); + BUG_ON(!p->on_rq); BUG_ON(!rt_task(p)); return p; @@ -1467,7 +1467,7 @@ static int pull_rt_task(struct rq *this_rq) */ if (p && (p->prio < this_rq->rt.highest_prio.curr)) { WARN_ON(p == src_rq->curr); - WARN_ON(!p->se.on_rq); + WARN_ON(!p->on_rq); /* * There's a chance that p is higher in priority @@ -1538,7 +1538,7 @@ static void set_cpus_allowed_rt(struct task_struct *p, * Update the migration status of the RQ if we have an RT task * which is running AND changing its weight value. */ - if (p->se.on_rq && (weight != p->rt.nr_cpus_allowed)) { + if (p->on_rq && (weight != p->rt.nr_cpus_allowed)) { struct rq *rq = task_rq(p); if (!task_current(rq, p)) { @@ -1608,7 +1608,7 @@ static void switched_from_rt(struct rq *rq, struct task_struct *p) * we may need to handle the pulling of RT tasks * now. */ - if (p->se.on_rq && !rq->rt.rt_nr_running) + if (p->on_rq && !rq->rt.rt_nr_running) pull_rt_task(rq); } @@ -1638,7 +1638,7 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p) * If that current running task is also an RT task * then see if we can move to another run queue. */ - if (p->se.on_rq && rq->curr != p) { + if (p->on_rq && rq->curr != p) { #ifdef CONFIG_SMP if (rq->rt.overloaded && push_rt_task(rq) && /* Don't resched if we changed runqueues */ @@ -1657,7 +1657,7 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p) static void prio_changed_rt(struct rq *rq, struct task_struct *p, int oldprio) { - if (!p->se.on_rq) + if (!p->on_rq) return; if (rq->curr == p) { diff --git a/kernel/sched_stoptask.c b/kernel/sched_stoptask.c index 1ba2bd40fda..f607de42e6f 100644 --- a/kernel/sched_stoptask.c +++ b/kernel/sched_stoptask.c @@ -26,7 +26,7 @@ static struct task_struct *pick_next_task_stop(struct rq *rq) { struct task_struct *stop = rq->stop; - if (stop && stop->se.on_rq) + if (stop && stop->on_rq) return stop; return NULL; -- cgit v1.2.3-70-g09d2 From 7608dec2ce2004c234339bef8c8074e5e601d0e9 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 5 Apr 2011 17:23:46 +0200 Subject: sched: Drop the rq argument to sched_class::select_task_rq() In preparation of calling select_task_rq() without rq->lock held, drop the dependency on the rq argument. Reviewed-by: Frank Rowand Signed-off-by: Peter Zijlstra Cc: Mike Galbraith Cc: Nick Piggin Cc: Linus Torvalds Cc: Andrew Morton Link: http://lkml.kernel.org/r/20110405152729.031077745@chello.nl Signed-off-by: Ingo Molnar --- include/linux/sched.h | 3 +-- kernel/sched.c | 20 +++++++++++--------- kernel/sched_fair.c | 2 +- kernel/sched_idletask.c | 2 +- kernel/sched_rt.c | 38 ++++++++++++++++++++++++++------------ kernel/sched_stoptask.c | 3 +-- 6 files changed, 41 insertions(+), 27 deletions(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index b33a700652d..ff4e2f9c24a 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1067,8 +1067,7 @@ struct sched_class { void (*put_prev_task) (struct rq *rq, struct task_struct *p); #ifdef CONFIG_SMP - int (*select_task_rq)(struct rq *rq, struct task_struct *p, - int sd_flag, int flags); + int (*select_task_rq)(struct task_struct *p, int sd_flag, int flags); void (*pre_schedule) (struct rq *this_rq, struct task_struct *task); void (*post_schedule) (struct rq *this_rq); diff --git a/kernel/sched.c b/kernel/sched.c index d398f2f0a3c..d4b815d345b 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2195,13 +2195,15 @@ static int migration_cpu_stop(void *data); * The task's runqueue lock must be held. * Returns true if you have to wait for migration thread. */ -static bool migrate_task(struct task_struct *p, struct rq *rq) +static bool need_migrate_task(struct task_struct *p) { /* * If the task is not on a runqueue (and not running), then * the next wake-up will properly place the task. */ - return p->on_rq || task_running(rq, p); + bool running = p->on_rq || p->on_cpu; + smp_rmb(); /* finish_lock_switch() */ + return running; } /* @@ -2376,9 +2378,9 @@ static int select_fallback_rq(int cpu, struct task_struct *p) * The caller (fork, wakeup) owns p->pi_lock, ->cpus_allowed is stable. */ static inline -int select_task_rq(struct rq *rq, struct task_struct *p, int sd_flags, int wake_flags) +int select_task_rq(struct task_struct *p, int sd_flags, int wake_flags) { - int cpu = p->sched_class->select_task_rq(rq, p, sd_flags, wake_flags); + int cpu = p->sched_class->select_task_rq(p, sd_flags, wake_flags); /* * In order not to call set_task_cpu() on a blocking task we need @@ -2533,7 +2535,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, en_flags |= ENQUEUE_WAKING; } - cpu = select_task_rq(rq, p, SD_BALANCE_WAKE, wake_flags); + cpu = select_task_rq(p, SD_BALANCE_WAKE, wake_flags); if (cpu != orig_cpu) set_task_cpu(p, cpu); __task_rq_unlock(rq); @@ -2744,7 +2746,7 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags) * We set TASK_WAKING so that select_task_rq() can drop rq->lock * without people poking at ->cpus_allowed. */ - cpu = select_task_rq(rq, p, SD_BALANCE_FORK, 0); + cpu = select_task_rq(p, SD_BALANCE_FORK, 0); set_task_cpu(p, cpu); p->state = TASK_RUNNING; @@ -3474,7 +3476,7 @@ void sched_exec(void) int dest_cpu; rq = task_rq_lock(p, &flags); - dest_cpu = p->sched_class->select_task_rq(rq, p, SD_BALANCE_EXEC, 0); + dest_cpu = p->sched_class->select_task_rq(p, SD_BALANCE_EXEC, 0); if (dest_cpu == smp_processor_id()) goto unlock; @@ -3482,7 +3484,7 @@ void sched_exec(void) * select_task_rq() can race against ->cpus_allowed */ if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed) && - likely(cpu_active(dest_cpu)) && migrate_task(p, rq)) { + likely(cpu_active(dest_cpu)) && need_migrate_task(p)) { struct migration_arg arg = { p, dest_cpu }; task_rq_unlock(rq, &flags); @@ -5911,7 +5913,7 @@ int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask) goto out; dest_cpu = cpumask_any_and(cpu_active_mask, new_mask); - if (migrate_task(p, rq)) { + if (need_migrate_task(p)) { struct migration_arg arg = { p, dest_cpu }; /* Need help from migration thread: drop lock and wait. */ __task_rq_unlock(rq); diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 4ee50f0af8d..96b2c95ac35 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -1657,7 +1657,7 @@ static int select_idle_sibling(struct task_struct *p, int target) * preempt must be disabled. */ static int -select_task_rq_fair(struct rq *rq, struct task_struct *p, int sd_flag, int wake_flags) +select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags) { struct sched_domain *tmp, *affine_sd = NULL, *sd = NULL; int cpu = smp_processor_id(); diff --git a/kernel/sched_idletask.c b/kernel/sched_idletask.c index a776a639642..0a51882534e 100644 --- a/kernel/sched_idletask.c +++ b/kernel/sched_idletask.c @@ -7,7 +7,7 @@ #ifdef CONFIG_SMP static int -select_task_rq_idle(struct rq *rq, struct task_struct *p, int sd_flag, int flags) +select_task_rq_idle(struct task_struct *p, int sd_flag, int flags) { return task_cpu(p); /* IDLE tasks as never migrated */ } diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index 9ca4f5f879c..19ecb312737 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -977,13 +977,23 @@ static void yield_task_rt(struct rq *rq) static int find_lowest_rq(struct task_struct *task); static int -select_task_rq_rt(struct rq *rq, struct task_struct *p, int sd_flag, int flags) +select_task_rq_rt(struct task_struct *p, int sd_flag, int flags) { + struct task_struct *curr; + struct rq *rq; + int cpu; + if (sd_flag != SD_BALANCE_WAKE) return smp_processor_id(); + cpu = task_cpu(p); + rq = cpu_rq(cpu); + + rcu_read_lock(); + curr = ACCESS_ONCE(rq->curr); /* unlocked access */ + /* - * If the current task is an RT task, then + * If the current task on @p's runqueue is an RT task, then * try to see if we can wake this RT task up on another * runqueue. Otherwise simply start this RT task * on its current runqueue. @@ -997,21 +1007,25 @@ select_task_rq_rt(struct rq *rq, struct task_struct *p, int sd_flag, int flags) * lock? * * For equal prio tasks, we just let the scheduler sort it out. + * + * Otherwise, just let it ride on the affined RQ and the + * post-schedule router will push the preempted task away + * + * This test is optimistic, if we get it wrong the load-balancer + * will have to sort it out. */ - if (unlikely(rt_task(rq->curr)) && - (rq->curr->rt.nr_cpus_allowed < 2 || - rq->curr->prio < p->prio) && + if (curr && unlikely(rt_task(curr)) && + (curr->rt.nr_cpus_allowed < 2 || + curr->prio < p->prio) && (p->rt.nr_cpus_allowed > 1)) { - int cpu = find_lowest_rq(p); + int target = find_lowest_rq(p); - return (cpu == -1) ? task_cpu(p) : cpu; + if (target != -1) + cpu = target; } + rcu_read_unlock(); - /* - * Otherwise, just let it ride on the affined RQ and the - * post-schedule router will push the preempted task away - */ - return task_cpu(p); + return cpu; } static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p) diff --git a/kernel/sched_stoptask.c b/kernel/sched_stoptask.c index f607de42e6f..6f437632afa 100644 --- a/kernel/sched_stoptask.c +++ b/kernel/sched_stoptask.c @@ -9,8 +9,7 @@ #ifdef CONFIG_SMP static int -select_task_rq_stop(struct rq *rq, struct task_struct *p, - int sd_flag, int flags) +select_task_rq_stop(struct task_struct *p, int sd_flag, int flags) { return task_cpu(p); /* stop tasks as never migrate */ } -- cgit v1.2.3-70-g09d2 From 74f8e4b2335de45485b8d5b31a504747f13c8070 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 5 Apr 2011 17:23:47 +0200 Subject: sched: Remove rq argument to sched_class::task_waking() In preparation of calling this without rq->lock held, remove the dependency on the rq argument. Reviewed-by: Frank Rowand Signed-off-by: Peter Zijlstra Cc: Mike Galbraith Cc: Nick Piggin Cc: Linus Torvalds Cc: Andrew Morton Link: http://lkml.kernel.org/r/20110405152729.071474242@chello.nl Signed-off-by: Ingo Molnar --- include/linux/sched.h | 10 +++++++--- kernel/sched.c | 2 +- kernel/sched_fair.c | 4 +++- 3 files changed, 11 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index ff4e2f9c24a..7f5732f8c61 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1048,8 +1048,12 @@ struct sched_domain; #define WF_FORK 0x02 /* child wakeup after fork */ #define ENQUEUE_WAKEUP 1 -#define ENQUEUE_WAKING 2 -#define ENQUEUE_HEAD 4 +#define ENQUEUE_HEAD 2 +#ifdef CONFIG_SMP +#define ENQUEUE_WAKING 4 /* sched_class::task_waking was called */ +#else +#define ENQUEUE_WAKING 0 +#endif #define DEQUEUE_SLEEP 1 @@ -1071,7 +1075,7 @@ struct sched_class { void (*pre_schedule) (struct rq *this_rq, struct task_struct *task); void (*post_schedule) (struct rq *this_rq); - void (*task_waking) (struct rq *this_rq, struct task_struct *task); + void (*task_waking) (struct task_struct *task); void (*task_woken) (struct rq *this_rq, struct task_struct *task); void (*set_cpus_allowed)(struct task_struct *p, diff --git a/kernel/sched.c b/kernel/sched.c index d4b815d345b..46f42cac4eb 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2531,7 +2531,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, p->state = TASK_WAKING; if (p->sched_class->task_waking) { - p->sched_class->task_waking(rq, p); + p->sched_class->task_waking(p); en_flags |= ENQUEUE_WAKING; } diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 96b2c95ac35..ad4c414f456 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -1372,11 +1372,13 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) #ifdef CONFIG_SMP -static void task_waking_fair(struct rq *rq, struct task_struct *p) +static void task_waking_fair(struct task_struct *p) { struct sched_entity *se = &p->se; struct cfs_rq *cfs_rq = cfs_rq_of(se); + lockdep_assert_held(&task_rq(p)->lock); + se->vruntime -= cfs_rq->min_vruntime; } -- cgit v1.2.3-70-g09d2 From a8e4f2eaecc9bfa4954adf79a04f4f22fddd829c Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 5 Apr 2011 17:23:49 +0200 Subject: sched: Delay task_contributes_to_load() In prepratation of having to call task_contributes_to_load() without holding rq->lock, we need to store the result until we do and can update the rq accounting accordingly. Reviewed-by: Frank Rowand Cc: Mike Galbraith Cc: Nick Piggin Cc: Linus Torvalds Cc: Andrew Morton Signed-off-by: Ingo Molnar Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/20110405152729.151523907@chello.nl --- include/linux/sched.h | 1 + kernel/sched.c | 16 ++++------------ 2 files changed, 5 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 7f5732f8c61..25c50317ddc 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1273,6 +1273,7 @@ struct task_struct { /* Revert to default priority/policy when forking */ unsigned sched_reset_on_fork:1; + unsigned sched_contributes_to_load:1; pid_t pid; pid_t tgid; diff --git a/kernel/sched.c b/kernel/sched.c index 7a5eb262078..fd32b78c123 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2519,18 +2519,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, if (unlikely(task_running(rq, p))) goto out_activate; - /* - * In order to handle concurrent wakeups and release the rq->lock - * we put the task in TASK_WAKING state. - * - * First fix up the nr_uninterruptible count: - */ - if (task_contributes_to_load(p)) { - if (likely(cpu_online(orig_cpu))) - rq->nr_uninterruptible--; - else - this_rq()->nr_uninterruptible--; - } + p->sched_contributes_to_load = !!task_contributes_to_load(p); p->state = TASK_WAKING; if (p->sched_class->task_waking) { @@ -2555,6 +2544,9 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, WARN_ON(task_cpu(p) != cpu); WARN_ON(p->state != TASK_WAKING); + if (p->sched_contributes_to_load) + rq->nr_uninterruptible--; + out_activate: #endif /* CONFIG_SMP */ ttwu_activate(rq, p, en_flags); -- cgit v1.2.3-70-g09d2 From 317f394160e9beb97d19a84c39b7e5eb3d7815a8 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 5 Apr 2011 17:23:58 +0200 Subject: sched: Move the second half of ttwu() to the remote cpu Now that we've removed the rq->lock requirement from the first part of ttwu() and can compute placement without holding any rq->lock, ensure we execute the second half of ttwu() on the actual cpu we want the task to run on. This avoids having to take rq->lock and doing the task enqueue remotely, saving lots on cacheline transfers. As measured using: http://oss.oracle.com/~mason/sembench.c $ for i in /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor ; do echo performance > $i; done $ echo 4096 32000 64 128 > /proc/sys/kernel/sem $ ./sembench -t 2048 -w 1900 -o 0 unpatched: run time 30 seconds 647278 worker burns per second patched: run time 30 seconds 816715 worker burns per second Reviewed-by: Frank Rowand Cc: Mike Galbraith Cc: Nick Piggin Cc: Linus Torvalds Cc: Andrew Morton Signed-off-by: Ingo Molnar Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/20110405152729.515897185@chello.nl --- include/linux/sched.h | 3 ++- init/Kconfig | 5 +++++ kernel/sched.c | 56 +++++++++++++++++++++++++++++++++++++++++++++++++ kernel/sched_features.h | 6 ++++++ 4 files changed, 69 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 25c50317ddc..e09dafa6e14 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1203,6 +1203,7 @@ struct task_struct { int lock_depth; /* BKL lock depth */ #ifdef CONFIG_SMP + struct task_struct *wake_entry; int on_cpu; #endif int on_rq; @@ -2192,7 +2193,7 @@ extern void set_task_comm(struct task_struct *tsk, char *from); extern char *get_task_comm(char *to, struct task_struct *tsk); #ifdef CONFIG_SMP -static inline void scheduler_ipi(void) { } +void scheduler_ipi(void); extern unsigned long wait_task_inactive(struct task_struct *, long match_state); #else static inline void scheduler_ipi(void) { } diff --git a/init/Kconfig b/init/Kconfig index 56240e724d9..32745bfe059 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -827,6 +827,11 @@ config SCHED_AUTOGROUP desktop applications. Task group autogeneration is currently based upon task session. +config SCHED_TTWU_QUEUE + bool + depends on !SPARC32 + default y + config MM_OWNER bool diff --git a/kernel/sched.c b/kernel/sched.c index 7d8b85fcdf0..9e3ede120e8 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -556,6 +556,10 @@ struct rq { unsigned int ttwu_count; unsigned int ttwu_local; #endif + +#ifdef CONFIG_SMP + struct task_struct *wake_list; +#endif }; static DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); @@ -2516,10 +2520,61 @@ static int ttwu_remote(struct task_struct *p, int wake_flags) return ret; } +#ifdef CONFIG_SMP +static void sched_ttwu_pending(void) +{ + struct rq *rq = this_rq(); + struct task_struct *list = xchg(&rq->wake_list, NULL); + + if (!list) + return; + + raw_spin_lock(&rq->lock); + + while (list) { + struct task_struct *p = list; + list = list->wake_entry; + ttwu_do_activate(rq, p, 0); + } + + raw_spin_unlock(&rq->lock); +} + +void scheduler_ipi(void) +{ + sched_ttwu_pending(); +} + +static void ttwu_queue_remote(struct task_struct *p, int cpu) +{ + struct rq *rq = cpu_rq(cpu); + struct task_struct *next = rq->wake_list; + + for (;;) { + struct task_struct *old = next; + + p->wake_entry = next; + next = cmpxchg(&rq->wake_list, old, p); + if (next == old) + break; + } + + if (!next) + smp_send_reschedule(cpu); +} +#endif + static void ttwu_queue(struct task_struct *p, int cpu) { struct rq *rq = cpu_rq(cpu); +#if defined(CONFIG_SMP) && defined(CONFIG_SCHED_TTWU_QUEUE) + if (sched_feat(TTWU_QUEUE) && cpu != smp_processor_id()) { + ttwu_queue_remote(p, cpu); + return; + } +#endif + raw_spin_lock(&rq->lock); ttwu_do_activate(rq, p, 0); raw_spin_unlock(&rq->lock); @@ -6331,6 +6386,7 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) #ifdef CONFIG_HOTPLUG_CPU case CPU_DYING: + sched_ttwu_pending(); /* Update our root-domain */ raw_spin_lock_irqsave(&rq->lock, flags); if (rq->rd) { diff --git a/kernel/sched_features.h b/kernel/sched_features.h index 68e69acc29b..be40f7371ee 100644 --- a/kernel/sched_features.h +++ b/kernel/sched_features.h @@ -64,3 +64,9 @@ SCHED_FEAT(OWNER_SPIN, 1) * Decrement CPU power based on irq activity */ SCHED_FEAT(NONIRQ_POWER, 1) + +/* + * Queue remote wakeups on the target CPU and process them + * using the scheduler IPI. Reduces rq->lock contention/bounces. + */ +SCHED_FEAT(TTWU_QUEUE, 1) -- cgit v1.2.3-70-g09d2 From beafbdc1df02877612dc9039c1de0639921fddec Mon Sep 17 00:00:00 2001 From: Konrad Rzeszutek Wilk Date: Thu, 14 Apr 2011 11:17:36 -0400 Subject: xen/irq: Check if the PCI device is owned by a domain different than DOMID_SELF. We check if there is a domain owner for the PCI device. In case of failure (meaning no domain has registered for this device) we make DOMID_SELF the owner. Signed-off-by: Konrad Rzeszutek Wilk [v2: deal with rebasing on v2.6.37-1] [v3: deal with rebasing on stable/irq.cleanup] [v4: deal with rebasing on stable/irq.ween_of_nr_irqs] [v5: deal with rebasing on v2.6.39-rc3] Signed-off-by: Jeremy Fitzhardinge Acked-by: Xiantao Zhang --- arch/x86/pci/xen.c | 21 ++++++++++++++++----- drivers/xen/events.c | 12 ++++++++---- include/xen/events.h | 3 ++- 3 files changed, 26 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index 6075f2d6533..393981feb12 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -108,7 +108,8 @@ static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) } irq = xen_bind_pirq_msi_to_irq(dev, msidesc, pirq, 0, (type == PCI_CAP_ID_MSIX) ? - "msi-x" : "msi"); + "msi-x" : "msi", + DOMID_SELF); if (irq < 0) goto error; dev_dbg(&dev->dev, @@ -148,7 +149,8 @@ static int xen_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) irq = xen_bind_pirq_msi_to_irq(dev, msidesc, v[i], 0, (type == PCI_CAP_ID_MSIX) ? "pcifront-msi-x" : - "pcifront-msi"); + "pcifront-msi", + DOMID_SELF); if (irq < 0) goto free; i++; @@ -190,9 +192,16 @@ static int xen_initdom_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) list_for_each_entry(msidesc, &dev->msi_list, list) { struct physdev_map_pirq map_irq; + domid_t domid; + + domid = ret = xen_find_device_domain_owner(dev); + /* N.B. Casting int's -ENODEV to uint16_t results in 0xFFED, + * hence check ret value for < 0. */ + if (ret < 0) + domid = DOMID_SELF; memset(&map_irq, 0, sizeof(map_irq)); - map_irq.domid = DOMID_SELF; + map_irq.domid = domid; map_irq.type = MAP_PIRQ_TYPE_MSI; map_irq.index = -1; map_irq.pirq = -1; @@ -215,14 +224,16 @@ static int xen_initdom_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) ret = HYPERVISOR_physdev_op(PHYSDEVOP_map_pirq, &map_irq); if (ret) { - dev_warn(&dev->dev, "xen map irq failed %d\n", ret); + dev_warn(&dev->dev, "xen map irq failed %d for %d domain\n", + ret, domid); goto out; } ret = xen_bind_pirq_msi_to_irq(dev, msidesc, map_irq.pirq, map_irq.index, (type == PCI_CAP_ID_MSIX) ? - "msi-x" : "msi"); + "msi-x" : "msi", + domid); if (ret < 0) goto out; } diff --git a/drivers/xen/events.c b/drivers/xen/events.c index 42d6c930cc8..ac0e2282635 100644 --- a/drivers/xen/events.c +++ b/drivers/xen/events.c @@ -101,6 +101,7 @@ struct irq_info unsigned short gsi; unsigned char vector; unsigned char flags; + uint16_t domid; } pirq; } u; }; @@ -184,6 +185,7 @@ static void xen_irq_info_pirq_init(unsigned irq, unsigned short pirq, unsigned short gsi, unsigned short vector, + uint16_t domid, unsigned char flags) { struct irq_info *info = info_for_irq(irq); @@ -193,6 +195,7 @@ static void xen_irq_info_pirq_init(unsigned irq, info->u.pirq.pirq = pirq; info->u.pirq.gsi = gsi; info->u.pirq.vector = vector; + info->u.pirq.domid = domid; info->u.pirq.flags = flags; } @@ -655,7 +658,7 @@ int xen_bind_pirq_gsi_to_irq(unsigned gsi, goto out; } - xen_irq_info_pirq_init(irq, 0, pirq, gsi, irq_op.vector, + xen_irq_info_pirq_init(irq, 0, pirq, gsi, irq_op.vector, DOMID_SELF, shareable ? PIRQ_SHAREABLE : 0); out: @@ -680,7 +683,8 @@ int xen_allocate_pirq_msi(struct pci_dev *dev, struct msi_desc *msidesc) } int xen_bind_pirq_msi_to_irq(struct pci_dev *dev, struct msi_desc *msidesc, - int pirq, int vector, const char *name) + int pirq, int vector, const char *name, + domid_t domid) { int irq, ret; @@ -693,7 +697,7 @@ int xen_bind_pirq_msi_to_irq(struct pci_dev *dev, struct msi_desc *msidesc, irq_set_chip_and_handler_name(irq, &xen_pirq_chip, handle_level_irq, name); - xen_irq_info_pirq_init(irq, 0, pirq, 0, vector, 0); + xen_irq_info_pirq_init(irq, 0, pirq, 0, vector, domid, 0); ret = irq_set_msi_desc(irq, msidesc); if (ret < 0) goto error_irq; @@ -722,7 +726,7 @@ int xen_destroy_irq(int irq) if (xen_initial_domain()) { unmap_irq.pirq = info->u.pirq.pirq; - unmap_irq.domid = DOMID_SELF; + unmap_irq.domid = info->u.pirq.domid; rc = HYPERVISOR_physdev_op(PHYSDEVOP_unmap_pirq, &unmap_irq); if (rc) { printk(KERN_WARNING "unmap irq failed %d\n", rc); diff --git a/include/xen/events.h b/include/xen/events.h index f1b87ad48ac..9aecc0b5a0e 100644 --- a/include/xen/events.h +++ b/include/xen/events.h @@ -85,7 +85,8 @@ int xen_bind_pirq_gsi_to_irq(unsigned gsi, int xen_allocate_pirq_msi(struct pci_dev *dev, struct msi_desc *msidesc); /* Bind an PSI pirq to an irq. */ int xen_bind_pirq_msi_to_irq(struct pci_dev *dev, struct msi_desc *msidesc, - int pirq, int vector, const char *name); + int pirq, int vector, const char *name, + domid_t domid); #endif /* De-allocates the above mentioned physical interrupt. */ -- cgit v1.2.3-70-g09d2 From c7c2c3a28657cfdcef50c02b18ccca3761209e17 Mon Sep 17 00:00:00 2001 From: Konrad Rzeszutek Wilk Date: Mon, 8 Nov 2010 14:26:36 -0500 Subject: xen/irq: Add support to check if IRQ line is shared with other domains. We do this via the PHYSDEVOP_irq_status_query support hypervisor call. We will get a positive value if another domain has binded its PIRQ to the specified GSI (IRQ line). [v2: Deal with v2.6.37-rc1 rebase fallout] [v3: Deal with stable/irq.cleanup fallout] [v4: xen_ignore_irq->xen_test_irq_shared] Signed-off-by: Konrad Rzeszutek Wilk --- drivers/xen/events.c | 12 ++++++++++++ include/xen/events.h | 3 +++ 2 files changed, 15 insertions(+) (limited to 'include') diff --git a/drivers/xen/events.c b/drivers/xen/events.c index ac0e2282635..0ac7a149e7f 100644 --- a/drivers/xen/events.c +++ b/drivers/xen/events.c @@ -1508,6 +1508,18 @@ void xen_poll_irq(int irq) xen_poll_irq_timeout(irq, 0 /* no timeout */); } +/* Check whether the IRQ line is shared with other guests. */ +int xen_test_irq_shared(int irq) +{ + struct irq_info *info = info_for_irq(irq); + struct physdev_irq_status_query irq_status = { .irq = info->u.pirq.pirq }; + + if (HYPERVISOR_physdev_op(PHYSDEVOP_irq_status_query, &irq_status)) + return 0; + return !(irq_status.flags & XENIRQSTAT_shared); +} +EXPORT_SYMBOL_GPL(xen_test_irq_shared); + void xen_irq_resume(void) { unsigned int cpu, evtchn; diff --git a/include/xen/events.h b/include/xen/events.h index 9aecc0b5a0e..932e54051d3 100644 --- a/include/xen/events.h +++ b/include/xen/events.h @@ -95,4 +95,7 @@ int xen_destroy_irq(int irq); /* Return irq from pirq */ int xen_irq_from_pirq(unsigned pirq); +/* Determine whether to ignore this IRQ if it is passed to a guest. */ +int xen_test_irq_shared(int irq); + #endif /* _XEN_EVENTS_H */ -- cgit v1.2.3-70-g09d2 From e6197acc726ab3baa60375a5891d58c2ee87e0f3 Mon Sep 17 00:00:00 2001 From: Konrad Rzeszutek Wilk Date: Thu, 24 Feb 2011 14:20:12 -0500 Subject: xen/irq: Export 'xen_pirq_from_irq' function. We need this to find the real Xen PIRQ value for a device that requests an MSI or MSI-X. In the past we used 'xen_gsi_from_irq' since that function would return an Xen PIRQ or GSI depending on the provided IRQ. Now that we have seperated that we need to use the correct function. [v2: Deal with rebase on stable/irq.cleanup] Signed-off-by: Konrad Rzeszutek Wilk --- drivers/xen/events.c | 6 ++++++ include/xen/events.h | 3 +++ 2 files changed, 9 insertions(+) (limited to 'include') diff --git a/drivers/xen/events.c b/drivers/xen/events.c index 0ac7a149e7f..e4e8e9a745b 100644 --- a/drivers/xen/events.c +++ b/drivers/xen/events.c @@ -763,6 +763,12 @@ out: return irq; } + +int xen_pirq_from_irq(unsigned irq) +{ + return pirq_from_irq(irq); +} +EXPORT_SYMBOL_GPL(xen_pirq_from_irq); int bind_evtchn_to_irq(unsigned int evtchn) { int irq; diff --git a/include/xen/events.h b/include/xen/events.h index 932e54051d3..9af21e19545 100644 --- a/include/xen/events.h +++ b/include/xen/events.h @@ -95,6 +95,9 @@ int xen_destroy_irq(int irq); /* Return irq from pirq */ int xen_irq_from_pirq(unsigned pirq); +/* Return the pirq allocated to the irq. */ +int xen_pirq_from_irq(unsigned irq); + /* Determine whether to ignore this IRQ if it is passed to a guest. */ int xen_test_irq_shared(int irq); -- cgit v1.2.3-70-g09d2 From bcdd323b893ad3c9b7ef26b5e4a0bef974238501 Mon Sep 17 00:00:00 2001 From: Felipe Balbi Date: Wed, 16 Mar 2011 15:59:35 +0200 Subject: device: add dev_WARN_ONCE it's quite useful to print the device name on the stack dump caused by WARN(), but there are other cases where we might want to use WARN_ONCE. Introduce a helper similar to dev_WARN() for that case too. Signed-off-by: Felipe Balbi Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/device.h b/include/linux/device.h index ab8dfc09570..d4840511e87 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -742,13 +742,17 @@ do { \ #endif /* - * dev_WARN() acts like dev_printk(), but with the key difference + * dev_WARN*() acts like dev_printk(), but with the key difference * of using a WARN/WARN_ON to get the message out, including the * file/line information and a backtrace. */ #define dev_WARN(dev, format, arg...) \ WARN(1, "Device: %s\n" format, dev_driver_string(dev), ## arg); +#define dev_WARN_ONCE(dev, condition, format, arg...) \ + WARN_ONCE(condition, "Device %s\n" format, \ + dev_driver_string(dev), ## arg) + /* Create alias, so I can be autoloaded. */ #define MODULE_ALIAS_CHARDEV(major,minor) \ MODULE_ALIAS("char-major-" __stringify(major) "-" __stringify(minor)) -- cgit v1.2.3-70-g09d2 From aed65af1cc2f6fc9ded5a8158f1405a02cf6d2ff Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Mon, 28 Mar 2011 09:12:52 -0700 Subject: drivers: make device_type const The device_type structure does not contain data that changes during usage and should be const. This allows devices to declare the struct const. I have patches to change all the subsystems, but need the infra structure change first. Signed-off-by: Stephen Hemminger Signed-off-by: Greg Kroah-Hartman --- drivers/base/core.c | 4 ++-- include/linux/device.h | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/base/core.c b/drivers/base/core.c index 81b78ede37c..fb8130ceea1 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -400,7 +400,7 @@ static void device_remove_groups(struct device *dev, static int device_add_attrs(struct device *dev) { struct class *class = dev->class; - struct device_type *type = dev->type; + const struct device_type *type = dev->type; int error; if (class) { @@ -440,7 +440,7 @@ static int device_add_attrs(struct device *dev) static void device_remove_attrs(struct device *dev) { struct class *class = dev->class; - struct device_type *type = dev->type; + const struct device_type *type = dev->type; device_remove_groups(dev, dev->groups); diff --git a/include/linux/device.h b/include/linux/device.h index d4840511e87..350ceda4de9 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -408,7 +408,7 @@ struct device { struct kobject kobj; const char *init_name; /* initial name of the device */ - struct device_type *type; + const struct device_type *type; struct mutex mutex; /* mutex to synchronize calls to * its driver. -- cgit v1.2.3-70-g09d2 From 764b0c4b3256ad4431cb52eaf99c0abe6df0a085 Mon Sep 17 00:00:00 2001 From: Pavan Savoy Date: Fri, 8 Apr 2011 04:57:42 -0500 Subject: drivers:misc:ti-st: handle delayed tty receive When certain technologies shutdown their interface without waiting for the acknowledgement from the chip. The receive_buf from the TTY would be invoked a while after the relevant technology is unregistered. This patch introduces a new flag "is_registered" which maintains the state of protocols BT, FM or GPS and thereby removes the need to clear the protocol data from ST when protocols gets unregistered. This fixes corner cases when HCI RESET is sent down from bluetooth stack and the receive_buf is called from tty after 250ms before which bluetooth would have unregistered from the system. OR - when FM application decides to close down the device without sending a power-off FM command resulting in some RDS data or interrupt data coming in after the driver is unregistered. Signed-off-by: Pavan Savoy Signed-off-by: Greg Kroah-Hartman --- drivers/misc/ti-st/st_core.c | 23 +++++++++++++---------- include/linux/ti_wilink_st.h | 3 ++- 2 files changed, 15 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/drivers/misc/ti-st/st_core.c b/drivers/misc/ti-st/st_core.c index 486117f72c9..f91f82eabda 100644 --- a/drivers/misc/ti-st/st_core.c +++ b/drivers/misc/ti-st/st_core.c @@ -43,13 +43,15 @@ static void add_channel_to_table(struct st_data_s *st_gdata, pr_info("%s: id %d\n", __func__, new_proto->chnl_id); /* list now has the channel id as index itself */ st_gdata->list[new_proto->chnl_id] = new_proto; + st_gdata->is_registered[new_proto->chnl_id] = true; } static void remove_channel_from_table(struct st_data_s *st_gdata, struct st_proto_s *proto) { pr_info("%s: id %d\n", __func__, proto->chnl_id); - st_gdata->list[proto->chnl_id] = NULL; +/* st_gdata->list[proto->chnl_id] = NULL; */ + st_gdata->is_registered[proto->chnl_id] = false; } /* @@ -104,7 +106,7 @@ void st_send_frame(unsigned char chnl_id, struct st_data_s *st_gdata) if (unlikely (st_gdata == NULL || st_gdata->rx_skb == NULL - || st_gdata->list[chnl_id] == NULL)) { + || st_gdata->is_registered[chnl_id] == false)) { pr_err("chnl_id %d not registered, no data to send?", chnl_id); kfree_skb(st_gdata->rx_skb); @@ -141,14 +143,15 @@ void st_reg_complete(struct st_data_s *st_gdata, char err) unsigned char i = 0; pr_info(" %s ", __func__); for (i = 0; i < ST_MAX_CHANNELS; i++) { - if (likely(st_gdata != NULL && st_gdata->list[i] != NULL && - st_gdata->list[i]->reg_complete_cb != NULL)) { + if (likely(st_gdata != NULL && + st_gdata->is_registered[i] == true && + st_gdata->list[i]->reg_complete_cb != NULL)) { st_gdata->list[i]->reg_complete_cb (st_gdata->list[i]->priv_data, err); pr_info("protocol %d's cb sent %d\n", i, err); if (err) { /* cleanup registered protocol */ st_gdata->protos_registered--; - st_gdata->list[i] = NULL; + st_gdata->is_registered[i] = false; } } } @@ -475,9 +478,9 @@ void kim_st_list_protocols(struct st_data_s *st_gdata, void *buf) { seq_printf(buf, "[%d]\nBT=%c\nFM=%c\nGPS=%c\n", st_gdata->protos_registered, - st_gdata->list[0x04] != NULL ? 'R' : 'U', - st_gdata->list[0x08] != NULL ? 'R' : 'U', - st_gdata->list[0x09] != NULL ? 'R' : 'U'); + st_gdata->is_registered[0x04] == true ? 'R' : 'U', + st_gdata->is_registered[0x08] == true ? 'R' : 'U', + st_gdata->is_registered[0x09] == true ? 'R' : 'U'); } /********************************************************************/ @@ -504,7 +507,7 @@ long st_register(struct st_proto_s *new_proto) return -EPROTONOSUPPORT; } - if (st_gdata->list[new_proto->chnl_id] != NULL) { + if (st_gdata->is_registered[new_proto->chnl_id] == true) { pr_err("chnl_id %d already registered", new_proto->chnl_id); return -EALREADY; } @@ -563,7 +566,7 @@ long st_register(struct st_proto_s *new_proto) /* check for already registered once more, * since the above check is old */ - if (st_gdata->list[new_proto->chnl_id] != NULL) { + if (st_gdata->is_registered[new_proto->chnl_id] == true) { pr_err(" proto %d already registered ", new_proto->chnl_id); return -EALREADY; diff --git a/include/linux/ti_wilink_st.h b/include/linux/ti_wilink_st.h index 7071ec5d011..b004e557caa 100644 --- a/include/linux/ti_wilink_st.h +++ b/include/linux/ti_wilink_st.h @@ -140,12 +140,12 @@ extern long st_unregister(struct st_proto_s *); */ struct st_data_s { unsigned long st_state; - struct tty_struct *tty; struct sk_buff *tx_skb; #define ST_TX_SENDING 1 #define ST_TX_WAKEUP 2 unsigned long tx_state; struct st_proto_s *list[ST_MAX_CHANNELS]; + bool is_registered[ST_MAX_CHANNELS]; unsigned long rx_state; unsigned long rx_count; struct sk_buff *rx_skb; @@ -155,6 +155,7 @@ struct st_data_s { unsigned char protos_registered; unsigned long ll_state; void *kim_data; + struct tty_struct *tty; }; /* -- cgit v1.2.3-70-g09d2 From c8705082404823a5bb3e02a32ba0764399b9e6f2 Mon Sep 17 00:00:00 2001 From: Uwe Kleine-König Date: Wed, 20 Apr 2011 09:44:46 +0200 Subject: driver core: let dev_set_drvdata return int instead of void as it can fail MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Before commit b402843 (Driver core: move dev_get/set_drvdata to drivers/base/dd.c) calling dev_set_drvdata with dev=NULL was an unchecked error. After some discussion about what to return in this case removing the check (and so producing a null pointer exception) seems fine. Signed-off-by: Uwe Kleine-König Signed-off-by: Greg Kroah-Hartman --- drivers/base/dd.c | 7 +++---- include/linux/device.h | 2 +- 2 files changed, 4 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/drivers/base/dd.c b/drivers/base/dd.c index 7e9219b0279..e3a3eff1dac 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -413,17 +413,16 @@ void *dev_get_drvdata(const struct device *dev) } EXPORT_SYMBOL(dev_get_drvdata); -void dev_set_drvdata(struct device *dev, void *data) +int dev_set_drvdata(struct device *dev, void *data) { int error; - if (!dev) - return; if (!dev->p) { error = device_private_init(dev); if (error) - return; + return error; } dev->p->driver_data = data; + return 0; } EXPORT_SYMBOL(dev_set_drvdata); diff --git a/include/linux/device.h b/include/linux/device.h index 350ceda4de9..2215d013ca9 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -557,7 +557,7 @@ extern int device_move(struct device *dev, struct device *new_parent, extern const char *device_get_devnode(struct device *dev, mode_t *mode, const char **tmp); extern void *dev_get_drvdata(const struct device *dev); -extern void dev_set_drvdata(struct device *dev, void *data); +extern int dev_set_drvdata(struct device *dev, void *data); /* * Root device objects for grouping under /sys/devices -- cgit v1.2.3-70-g09d2 From 0911f124bf55357803d53197cc1ae5479f5e37e2 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Sun, 10 Apr 2011 11:01:51 +0200 Subject: genirq: Forgotten updates/deletions after removal of compat code commit 0c6f8a8b917ad361319c8ace3e9f28e69bfdb4c1 ("genirq: Remove compat code") removed the compat code, but forgot to update some references in comments and delete some of its documentation. Signed-off-by: Geert Uytterhoeven Link: http://lkml.kernel.org/r/%3C1302426113-13808-1-git-send-email-geert%40linux-m68k.org%3E Signed-off-by: Thomas Gleixner --- include/linux/irq.h | 19 +------------------ include/linux/irqdesc.h | 2 +- 2 files changed, 2 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/include/linux/irq.h b/include/linux/irq.h index 09a308072f5..a71dd18639f 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -53,7 +53,7 @@ typedef void (*irq_preflow_handler_t)(struct irq_data *data); * Bits which can be modified via irq_set/clear/modify_status_flags() * IRQ_LEVEL - Interrupt is level type. Will be also * updated in the code when the above trigger - * bits are modified via set_irq_type() + * bits are modified via irq_set_irq_type() * IRQ_PER_CPU - Mark an interrupt PER_CPU. Will protect * it from affinity setting * IRQ_NOPROBE - Interrupt cannot be probed by autoprobing @@ -261,23 +261,6 @@ static inline void irqd_clr_chained_irq_inprogress(struct irq_data *d) * struct irq_chip - hardware interrupt chip descriptor * * @name: name for /proc/interrupts - * @startup: deprecated, replaced by irq_startup - * @shutdown: deprecated, replaced by irq_shutdown - * @enable: deprecated, replaced by irq_enable - * @disable: deprecated, replaced by irq_disable - * @ack: deprecated, replaced by irq_ack - * @mask: deprecated, replaced by irq_mask - * @mask_ack: deprecated, replaced by irq_mask_ack - * @unmask: deprecated, replaced by irq_unmask - * @eoi: deprecated, replaced by irq_eoi - * @end: deprecated, will go away with __do_IRQ() - * @set_affinity: deprecated, replaced by irq_set_affinity - * @retrigger: deprecated, replaced by irq_retrigger - * @set_type: deprecated, replaced by irq_set_type - * @set_wake: deprecated, replaced by irq_wake - * @bus_lock: deprecated, replaced by irq_bus_lock - * @bus_sync_unlock: deprecated, replaced by irq_bus_sync_unlock - * * @irq_startup: start up the interrupt (defaults to ->enable if NULL) * @irq_shutdown: shut down the interrupt (defaults to ->disable if NULL) * @irq_enable: enable the interrupt (defaults to chip->unmask if NULL) diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index a082905b5eb..8e1dc8ea547 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -21,7 +21,7 @@ struct timer_rand_state; * @status: status information * @core_internal_state__do_not_mess_with_it: core internal status information * @depth: disable-depth, for nested irq_disable() calls - * @wake_depth: enable depth, for multiple set_irq_wake() callers + * @wake_depth: enable depth, for multiple irq_set_irq_wake() callers * @irq_count: stats field to detect stalled irqs * @last_unhandled: aging timer for unhandled count * @irqs_unhandled: stats field for spurious unhandled interrupts -- cgit v1.2.3-70-g09d2 From 770767787c23040dc152e7ae230597ff55b39470 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Sun, 10 Apr 2011 11:01:52 +0200 Subject: genirq: irq_desc: Document preflow_handler and affinity_hint [ tglx: Filled in the FIXME place holders ] Signed-off-by: Geert Uytterhoeven Link: http://lkml.kernel.org/r/%3C1302426113-13808-2-git-send-email-geert%40linux-m68k.org%3E Signed-off-by: Thomas Gleixner --- include/linux/irqdesc.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index 8e1dc8ea547..c70b1aa4b93 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -16,7 +16,8 @@ struct timer_rand_state; * @irq_data: per irq and chip data passed down to chip functions * @timer_rand_state: pointer to timer rand state struct * @kstat_irqs: irq stats per cpu - * @handle_irq: highlevel irq-events handler [if NULL, __do_IRQ()] + * @handle_irq: highlevel irq-events handler + * @preflow_handler: handler called before the flow handler (currently used by sparc) * @action: the irq action chain * @status: status information * @core_internal_state__do_not_mess_with_it: core internal status information @@ -26,6 +27,7 @@ struct timer_rand_state; * @last_unhandled: aging timer for unhandled count * @irqs_unhandled: stats field for spurious unhandled interrupts * @lock: locking for SMP + * @affinity_hint: hint to user space for preferred irq affinity * @affinity_notify: context for notification of affinity changes * @pending_mask: pending rebalanced interrupts * @threads_oneshot: bitfield to handle shared oneshot threads -- cgit v1.2.3-70-g09d2 From 7f1b1244e159a8490d7fb13667c6cb7e1e75046b Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Thu, 7 Apr 2011 06:01:44 +0900 Subject: genirq: Support per-IRQ thread disabling. This adds support for disabling threading on a per-IRQ basis via the IRQ status instead of the IRQ flow, which is necessary for interrupts that don't follow the natural IRQ flow channels, such as those that are virtually created. The new APIs added are simply: irq_set_thread() irq_set_nothread() which follow the rest of the IRQ status routines. Chained handlers also have IRQ_NOTHREAD set on them automatically, making the lack of threading explicit rather than implicit. Subsequently, the nothread flag can be viewed through the standard genirq debugging facilities. [ tglx: Fixed cleanup fallout ] Signed-off-by: Paul Mundt Link: http://lkml.kernel.org/r/%3C20110406210135.GF18426%40linux-sh.org%3E Signed-off-by: Thomas Gleixner --- include/linux/irq.h | 14 +++++++++++++- kernel/irq/chip.c | 1 + kernel/irq/debug.h | 1 + kernel/irq/manage.c | 3 ++- kernel/irq/settings.h | 17 +++++++++++++++++ 5 files changed, 34 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/irq.h b/include/linux/irq.h index a71dd18639f..39c23786c1d 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -59,6 +59,7 @@ typedef void (*irq_preflow_handler_t)(struct irq_data *data); * IRQ_NOPROBE - Interrupt cannot be probed by autoprobing * IRQ_NOREQUEST - Interrupt cannot be requested via * request_irq() + * IRQ_NOTHREAD - Interrupt cannot be threaded * IRQ_NOAUTOEN - Interrupt is not automatically enabled in * request/setup_irq() * IRQ_NO_BALANCING - Interrupt cannot be balanced (affinity set) @@ -85,6 +86,7 @@ enum { IRQ_NO_BALANCING = (1 << 13), IRQ_MOVE_PCNTXT = (1 << 14), IRQ_NESTED_THREAD = (1 << 15), + IRQ_NOTHREAD = (1 << 16), }; #define IRQF_MODIFY_MASK \ @@ -422,7 +424,7 @@ irq_set_handler(unsigned int irq, irq_flow_handler_t handle) /* * Set a highlevel chained flow handler for a given IRQ. * (a chained handler is automatically enabled and set to - * IRQ_NOREQUEST and IRQ_NOPROBE) + * IRQ_NOREQUEST, IRQ_NOPROBE, and IRQ_NOTHREAD) */ static inline void irq_set_chained_handler(unsigned int irq, irq_flow_handler_t handle) @@ -452,6 +454,16 @@ static inline void irq_set_probe(unsigned int irq) irq_modify_status(irq, IRQ_NOPROBE, 0); } +static inline void irq_set_nothread(unsigned int irq) +{ + irq_modify_status(irq, 0, IRQ_NOTHREAD); +} + +static inline void irq_set_thread(unsigned int irq) +{ + irq_modify_status(irq, IRQ_NOTHREAD, 0); +} + static inline void irq_set_nested_thread(unsigned int irq, bool nest) { if (nest) diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 4af1e2b244c..52d856d513f 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -573,6 +573,7 @@ __irq_set_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained, if (handle != handle_bad_irq && is_chained) { irq_settings_set_noprobe(desc); irq_settings_set_norequest(desc); + irq_settings_set_nothread(desc); irq_startup(desc); } out: diff --git a/kernel/irq/debug.h b/kernel/irq/debug.h index 306cba37e9a..97a8bfadc88 100644 --- a/kernel/irq/debug.h +++ b/kernel/irq/debug.h @@ -27,6 +27,7 @@ static inline void print_irq_desc(unsigned int irq, struct irq_desc *desc) P(IRQ_PER_CPU); P(IRQ_NOPROBE); P(IRQ_NOREQUEST); + P(IRQ_NOTHREAD); P(IRQ_NOAUTOEN); PS(IRQS_AUTODETECT); diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 07c1611f389..f7ce0021e1c 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -900,7 +900,8 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) */ new->handler = irq_nested_primary_handler; } else { - irq_setup_forced_threading(new); + if (irq_settings_can_thread(desc)) + irq_setup_forced_threading(new); } /* diff --git a/kernel/irq/settings.h b/kernel/irq/settings.h index 0d91730b633..f1667833d44 100644 --- a/kernel/irq/settings.h +++ b/kernel/irq/settings.h @@ -8,6 +8,7 @@ enum { _IRQ_LEVEL = IRQ_LEVEL, _IRQ_NOPROBE = IRQ_NOPROBE, _IRQ_NOREQUEST = IRQ_NOREQUEST, + _IRQ_NOTHREAD = IRQ_NOTHREAD, _IRQ_NOAUTOEN = IRQ_NOAUTOEN, _IRQ_MOVE_PCNTXT = IRQ_MOVE_PCNTXT, _IRQ_NO_BALANCING = IRQ_NO_BALANCING, @@ -20,6 +21,7 @@ enum { #define IRQ_LEVEL GOT_YOU_MORON #define IRQ_NOPROBE GOT_YOU_MORON #define IRQ_NOREQUEST GOT_YOU_MORON +#define IRQ_NOTHREAD GOT_YOU_MORON #define IRQ_NOAUTOEN GOT_YOU_MORON #define IRQ_NESTED_THREAD GOT_YOU_MORON #undef IRQF_MODIFY_MASK @@ -94,6 +96,21 @@ static inline void irq_settings_set_norequest(struct irq_desc *desc) desc->status_use_accessors |= _IRQ_NOREQUEST; } +static inline bool irq_settings_can_thread(struct irq_desc *desc) +{ + return !(desc->status_use_accessors & _IRQ_NOTHREAD); +} + +static inline void irq_settings_clr_nothread(struct irq_desc *desc) +{ + desc->status_use_accessors &= ~_IRQ_NOTHREAD; +} + +static inline void irq_settings_set_nothread(struct irq_desc *desc) +{ + desc->status_use_accessors |= _IRQ_NOTHREAD; +} + static inline bool irq_settings_can_probe(struct irq_desc *desc) { return !(desc->status_use_accessors & _IRQ_NOPROBE); -- cgit v1.2.3-70-g09d2 From 7d8280624797bbe2f5170bd3c85c75a8c9c74242 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 3 Apr 2011 11:42:53 +0200 Subject: genirq: Implement a generic interrupt chip Implement a generic interrupt chip, which is configurable and is able to handle the most common irq chip implementations. Signed-off-by: Thomas Gleixner Cc: linux-arm-kernel@lists.infradead.org Tested-by: H Hartley Sweeten Tested-by: Tony Lindgren Tested-by; Kevin Hilman --- include/linux/irq.h | 135 ++++++++++++++++++++++++ kernel/irq/Makefile | 1 + kernel/irq/generic-chip.c | 261 ++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 397 insertions(+) create mode 100644 kernel/irq/generic-chip.c (limited to 'include') diff --git a/include/linux/irq.h b/include/linux/irq.h index 39c23786c1d..2ba2f121679 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -568,6 +568,141 @@ static inline int irq_reserve_irq(unsigned int irq) return irq_reserve_irqs(irq, 1); } +#ifndef irq_reg_writel +# define irq_reg_writel(val, addr) writel(val, addr) +#endif +#ifndef irq_reg_readl +# define irq_reg_readl(addr) readl(addr) +#endif + +/** + * struct irq_chip_regs - register offsets for struct irq_gci + * @enable: Enable register offset to reg_base + * @disable: Disable register offset to reg_base + * @mask: Mask register offset to reg_base + * @ack: Ack register offset to reg_base + * @eoi: Eoi register offset to reg_base + * @type: Type configuration register offset to reg_base + * @polarity: Polarity configuration register offset to reg_base + */ +struct irq_chip_regs { + unsigned long enable; + unsigned long disable; + unsigned long mask; + unsigned long ack; + unsigned long eoi; + unsigned long type; + unsigned long polarity; +}; + +/** + * struct irq_chip_type - Generic interrupt chip instance for a flow type + * @chip: The real interrupt chip which provides the callbacks + * @regs: Register offsets for this chip + * @handler: Flow handler associated with this chip + * @type: Chip can handle these flow types + * + * A irq_generic_chip can have several instances of irq_chip_type when + * it requires different functions and register offsets for different + * flow types. + */ +struct irq_chip_type { + struct irq_chip chip; + struct irq_chip_regs regs; + irq_flow_handler_t handler; + u32 type; +}; + +/** + * struct irq_chip_generic - Generic irq chip data structure + * @lock: Lock to protect register and cache data access + * @reg_base: Register base address (virtual) + * @irq_base: Interrupt base nr for this chip + * @irq_cnt: Number of interrupts handled by this chip + * @mask_cache: Cached mask register + * @type_cache: Cached type register + * @polarity_cache: Cached polarity register + * @wake_enabled: Interrupt can wakeup from suspend + * @wake_active: Interrupt is marked as an wakeup from suspend source + * @num_ct: Number of available irq_chip_type instances (usually 1) + * @private: Private data for non generic chip callbacks + * @chip_types: Array of interrupt irq_chip_types + * + * Note, that irq_chip_generic can have multiple irq_chip_type + * implementations which can be associated to a particular irq line of + * an irq_chip_generic instance. That allows to share and protect + * state in an irq_chip_generic instance when we need to implement + * different flow mechanisms (level/edge) for it. + */ +struct irq_chip_generic { + raw_spinlock_t lock; + void __iomem *reg_base; + unsigned int irq_base; + unsigned int irq_cnt; + u32 mask_cache; + u32 type_cache; + u32 polarity_cache; + u32 wake_enabled; + u32 wake_active; + unsigned int num_ct; + void *private; + struct irq_chip_type chip_types[0]; +}; + +/** + * enum irq_gc_flags - Initialization flags for generic irq chips + * @IRQ_GC_INIT_MASK_CACHE: Initialize the mask_cache by reading mask reg + * @IRQ_GC_INIT_NESTED_LOCK: Set the lock class of the irqs to nested for + * irq chips which need to call irq_set_wake() on + * the parent irq. Usually GPIO implementations + */ +enum irq_gc_flags { + IRQ_GC_INIT_MASK_CACHE = 1 << 0, + IRQ_GC_INIT_NESTED_LOCK = 1 << 1, +}; + +/* Generic chip callback functions */ +void irq_gc_noop(struct irq_data *d); +void irq_gc_mask_disable_reg(struct irq_data *d); +void irq_gc_mask_set_bit(struct irq_data *d); +void irq_gc_mask_clr_bit(struct irq_data *d); +void irq_gc_unmask_enable_reg(struct irq_data *d); +void irq_gc_ack(struct irq_data *d); +void irq_gc_mask_disable_reg_and_ack(struct irq_data *d); +void irq_gc_eoi(struct irq_data *d); +int irq_gc_set_wake(struct irq_data *d, unsigned int on); + +/* Setup functions for irq_chip_generic */ +struct irq_chip_generic * +irq_alloc_generic_chip(const char *name, int nr_ct, unsigned int irq_base, + void __iomem *reg_base, irq_flow_handler_t handler); +void irq_setup_generic_chip(struct irq_chip_generic *gc, u32 msk, + enum irq_gc_flags flags, unsigned int clr, + unsigned int set); +int irq_setup_alt_chip(struct irq_data *d, unsigned int type); + +static inline struct irq_chip_type *irq_data_get_chip_type(struct irq_data *d) +{ + return container_of(d->chip, struct irq_chip_type, chip); +} + +#define IRQ_MSK(n) (u32)((n) < 32 ? ((1 << (n)) - 1) : UINT_MAX) + +#ifdef CONFIG_SMP +static inline void irq_gc_lock(struct irq_chip_generic *gc) +{ + raw_spin_lock(&gc->lock); +} + +static inline void irq_gc_unlock(struct irq_chip_generic *gc) +{ + raw_spin_unlock(&gc->lock); +} +#else +static inline void irq_gc_lock(struct irq_chip_generic *gc) { } +static inline void irq_gc_unlock(struct irq_chip_generic *gc) { } +#endif + #endif /* CONFIG_GENERIC_HARDIRQS */ #endif /* !CONFIG_S390 */ diff --git a/kernel/irq/Makefile b/kernel/irq/Makefile index 54329cd7b3e..e7a13bd3316 100644 --- a/kernel/irq/Makefile +++ b/kernel/irq/Makefile @@ -1,5 +1,6 @@ obj-y := irqdesc.o handle.o manage.o spurious.o resend.o chip.o dummychip.o devres.o +obj-y += generic-chip.o obj-$(CONFIG_GENERIC_IRQ_PROBE) += autoprobe.o obj-$(CONFIG_PROC_FS) += proc.o obj-$(CONFIG_GENERIC_PENDING_IRQ) += migration.o diff --git a/kernel/irq/generic-chip.c b/kernel/irq/generic-chip.c new file mode 100644 index 00000000000..eb23e592426 --- /dev/null +++ b/kernel/irq/generic-chip.c @@ -0,0 +1,261 @@ +/* + * Library implementing the most common irq chip callback functions + * + * Copyright (C) 2011, Thomas Gleixner + */ +#include +#include +#include +#include +#include + +#include "internals.h" + +static inline struct irq_chip_regs *cur_regs(struct irq_data *d) +{ + return &container_of(d->chip, struct irq_chip_type, chip)->regs; +} + +/** + * irq_gc_noop - NOOP function + * @d: irq_data + */ +void irq_gc_noop(struct irq_data *d) +{ +} + +/** + * irq_gc_mask_disable_reg - Mask chip via disable register + * @d: irq_data + * + * Chip has separate enable/disable registers instead of a single mask + * register. + */ +void irq_gc_mask_disable_reg(struct irq_data *d) +{ + struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); + u32 mask = 1 << (d->irq - gc->irq_base); + + irq_gc_lock(gc); + irq_reg_writel(mask, gc->reg_base + cur_regs(d)->disable); + gc->mask_cache &= ~mask; + irq_gc_unlock(gc); +} + +/** + * irq_gc_mask_set_mask_bit - Mask chip via setting bit in mask register + * @d: irq_data + * + * Chip has a single mask register. Values of this register are cached + * and protected by gc->lock + */ +void irq_gc_mask_set_bit(struct irq_data *d) +{ + struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); + u32 mask = 1 << (d->irq - gc->irq_base); + + irq_gc_lock(gc); + gc->mask_cache |= mask; + irq_reg_writel(gc->mask_cache, gc->reg_base + cur_regs(d)->mask); + irq_gc_unlock(gc); +} + +/** + * irq_gc_mask_set_mask_bit - Mask chip via clearing bit in mask register + * @d: irq_data + * + * Chip has a single mask register. Values of this register are cached + * and protected by gc->lock + */ +void irq_gc_mask_clr_bit(struct irq_data *d) +{ + struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); + u32 mask = 1 << (d->irq - gc->irq_base); + + irq_gc_lock(gc); + gc->mask_cache &= ~mask; + irq_reg_writel(gc->mask_cache, gc->reg_base + cur_regs(d)->mask); + irq_gc_unlock(gc); +} + +/** + * irq_gc_unmask_enable_reg - Unmask chip via enable register + * @d: irq_data + * + * Chip has separate enable/disable registers instead of a single mask + * register. + */ +void irq_gc_unmask_enable_reg(struct irq_data *d) +{ + struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); + u32 mask = 1 << (d->irq - gc->irq_base); + + irq_gc_lock(gc); + irq_reg_writel(mask, gc->reg_base + cur_regs(d)->enable); + gc->mask_cache |= mask; + irq_gc_unlock(gc); +} + +/** + * irq_gc_ack - Ack pending interrupt + * @d: irq_data + */ +void irq_gc_ack(struct irq_data *d) +{ + struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); + u32 mask = 1 << (d->irq - gc->irq_base); + + irq_gc_lock(gc); + irq_reg_writel(mask, gc->reg_base + cur_regs(d)->ack); + irq_gc_unlock(gc); +} + +/** + * irq_gc_mask_disable_reg_and_ack- Mask and ack pending interrupt + * @d: irq_data + */ +void irq_gc_mask_disable_reg_and_ack(struct irq_data *d) +{ + struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); + u32 mask = 1 << (d->irq - gc->irq_base); + + irq_gc_lock(gc); + irq_reg_writel(mask, gc->reg_base + cur_regs(d)->mask); + irq_reg_writel(mask, gc->reg_base + cur_regs(d)->ack); + irq_gc_unlock(gc); +} + +/** + * irq_gc_eoi - EOI interrupt + * @d: irq_data + */ +void irq_gc_eoi(struct irq_data *d) +{ + struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); + u32 mask = 1 << (d->irq - gc->irq_base); + + irq_gc_lock(gc); + irq_reg_writel(mask, gc->reg_base + cur_regs(d)->eoi); + irq_gc_unlock(gc); +} + +/** + * irq_gc_set_wake - Set/clr wake bit for an interrupt + * @d: irq_data + * + * For chips where the wake from suspend functionality is not + * configured in a separate register and the wakeup active state is + * just stored in a bitmask. + */ +int irq_gc_set_wake(struct irq_data *d, unsigned int on) +{ + struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); + u32 mask = 1 << (d->irq - gc->irq_base); + + if (!(mask & gc->wake_enabled)) + return -EINVAL; + + irq_gc_lock(gc); + if (on) + gc->wake_active |= mask; + else + gc->wake_active &= ~mask; + irq_gc_unlock(gc); + return 0; +} + +/** + * irq_alloc_generic_chip - Allocate a generic chip and initialize it + * @name: Name of the irq chip + * @num_ct: Number of irq_chip_type instances associated with this + * @irq_base: Interrupt base nr for this chip + * @reg_base: Register base address (virtual) + * @handler: Default flow handler associated with this chip + * + * Returns an initialized irq_chip_generic structure. The chip defaults + * to the primary (index 0) irq_chip_type and @handler + */ +struct irq_chip_generic * +irq_alloc_generic_chip(const char *name, int num_ct, unsigned int irq_base, + void __iomem *reg_base, irq_flow_handler_t handler) +{ + struct irq_chip_generic *gc; + unsigned long sz = sizeof(*gc) + num_ct * sizeof(struct irq_chip_type); + + gc = kzalloc(sz, GFP_KERNEL); + if (gc) { + raw_spin_lock_init(&gc->lock); + gc->num_ct = num_ct; + gc->irq_base = irq_base; + gc->reg_base = reg_base; + gc->chip_types->chip.name = name; + gc->chip_types->handler = handler; + } + return gc; +} + +/* + * Separate lockdep class for interrupt chip which can nest irq_desc + * lock. + */ +static struct lock_class_key irq_nested_lock_class; + +/** + * irq_setup_generic_chip - Setup a range of interrupts with a generic chip + * @gc: Generic irq chip holding all data + * @msk: Bitmask holding the irqs to initialize relative to gc->irq_base + * @flags: Flags for initialization + * @clr: IRQ_* bits to clear + * @set: IRQ_* bits to set + * + * Set up max. 32 interrupts starting from gc->irq_base. Note, this + * initializes all interrupts to the primary irq_chip_type and its + * associated handler. + */ +void irq_setup_generic_chip(struct irq_chip_generic *gc, u32 msk, + enum irq_gc_flags flags, unsigned int clr, + unsigned int set) +{ + struct irq_chip_type *ct = gc->chip_types; + unsigned int i; + + /* Init mask cache ? */ + if (flags & IRQ_GC_INIT_MASK_CACHE) + gc->mask_cache = irq_reg_readl(gc->reg_base + ct->regs.mask); + + for (i = gc->irq_base; msk; msk >>= 1, i++) { + if (!msk & 0x01) + continue; + + if (flags & IRQ_GC_INIT_NESTED_LOCK) + irq_set_lockdep_class(i, &irq_nested_lock_class); + + irq_set_chip_and_handler(i, &ct->chip, ct->handler); + irq_set_chip_data(i, gc); + irq_modify_status(i, clr, set); + } + gc->irq_cnt = i - gc->irq_base; +} + +/** + * irq_setup_alt_chip - Switch to alternative chip + * @d: irq_data for this interrupt + * @type Flow type to be initialized + * + * Only to be called from chip->irq_set_type() callbacks. + */ +int irq_setup_alt_chip(struct irq_data *d, unsigned int type) +{ + struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); + struct irq_chip_type *ct = gc->chip_types; + unsigned int i; + + for (i = 0; i < gc->num_ct; i++, ct++) { + if (ct->type & type) { + d->chip = &ct->chip; + irq_data_to_desc(d)->handle_irq = ct->handler; + return 0; + } + } + return -EINVAL; +} -- cgit v1.2.3-70-g09d2 From cfefd21e693dca791bf9ecfc9dd3794facad533c Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 15 Apr 2011 22:36:08 +0200 Subject: genirq: Add chip suspend and resume callbacks These callbacks are only called in the syscore suspend/resume code on interrupt chips which have been registered via the generic irq chip mechanism. Calling those callbacks per irq would be rather icky, but with the generic irq chip mechanism we can call this per registered chip. Signed-off-by: Thomas Gleixner Cc: linux-arm-kernel@lists.infradead.org --- include/linux/irq.h | 11 ++++++ kernel/irq/generic-chip.c | 93 +++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 104 insertions(+) (limited to 'include') diff --git a/include/linux/irq.h b/include/linux/irq.h index 2ba2f121679..8b453844663 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -280,6 +280,9 @@ static inline void irqd_clr_chained_irq_inprogress(struct irq_data *d) * @irq_bus_sync_unlock:function to sync and unlock slow bus (i2c) chips * @irq_cpu_online: configure an interrupt source for a secondary CPU * @irq_cpu_offline: un-configure an interrupt source for a secondary CPU + * @irq_suspend: function called from core code on suspend once per chip + * @irq_resume: function called from core code on resume once per chip + * @irq_pm_shutdown: function called from core code on shutdown once per chip * @irq_print_chip: optional to print special chip info in show_interrupts * @flags: chip specific flags * @@ -309,6 +312,10 @@ struct irq_chip { void (*irq_cpu_online)(struct irq_data *data); void (*irq_cpu_offline)(struct irq_data *data); + void (*irq_suspend)(struct irq_data *data); + void (*irq_resume)(struct irq_data *data); + void (*irq_pm_shutdown)(struct irq_data *data); + void (*irq_print_chip)(struct irq_data *data, struct seq_file *p); unsigned long flags; @@ -626,6 +633,7 @@ struct irq_chip_type { * @wake_active: Interrupt is marked as an wakeup from suspend source * @num_ct: Number of available irq_chip_type instances (usually 1) * @private: Private data for non generic chip callbacks + * @list: List head for keeping track of instances * @chip_types: Array of interrupt irq_chip_types * * Note, that irq_chip_generic can have multiple irq_chip_type @@ -646,6 +654,7 @@ struct irq_chip_generic { u32 wake_active; unsigned int num_ct; void *private; + struct list_head list; struct irq_chip_type chip_types[0]; }; @@ -680,6 +689,8 @@ void irq_setup_generic_chip(struct irq_chip_generic *gc, u32 msk, enum irq_gc_flags flags, unsigned int clr, unsigned int set); int irq_setup_alt_chip(struct irq_data *d, unsigned int type); +void irq_remove_generic_chip(struct irq_chip_generic *gc, u32 msk, + unsigned int clr, unsigned int set); static inline struct irq_chip_type *irq_data_get_chip_type(struct irq_data *d) { diff --git a/kernel/irq/generic-chip.c b/kernel/irq/generic-chip.c index eb23e592426..31a9db71190 100644 --- a/kernel/irq/generic-chip.c +++ b/kernel/irq/generic-chip.c @@ -8,9 +8,13 @@ #include #include #include +#include #include "internals.h" +static LIST_HEAD(gc_list); +static DEFINE_RAW_SPINLOCK(gc_lock); + static inline struct irq_chip_regs *cur_regs(struct irq_data *d) { return &container_of(d->chip, struct irq_chip_type, chip)->regs; @@ -219,6 +223,10 @@ void irq_setup_generic_chip(struct irq_chip_generic *gc, u32 msk, struct irq_chip_type *ct = gc->chip_types; unsigned int i; + raw_spin_lock(&gc_lock); + list_add_tail(&gc->list, &gc_list); + raw_spin_unlock(&gc_lock); + /* Init mask cache ? */ if (flags & IRQ_GC_INIT_MASK_CACHE) gc->mask_cache = irq_reg_readl(gc->reg_base + ct->regs.mask); @@ -259,3 +267,88 @@ int irq_setup_alt_chip(struct irq_data *d, unsigned int type) } return -EINVAL; } + +/** + * irq_remove_generic_chip - Remove a chip + * @gc: Generic irq chip holding all data + * @msk: Bitmask holding the irqs to initialize relative to gc->irq_base + * @clr: IRQ_* bits to clear + * @set: IRQ_* bits to set + * + * Remove up to 32 interrupts starting from gc->irq_base. + */ +void irq_remove_generic_chip(struct irq_chip_generic *gc, u32 msk, + unsigned int clr, unsigned int set) +{ + unsigned int i = gc->irq_base; + + raw_spin_lock(&gc_lock); + list_del(&gc->list); + raw_spin_unlock(&gc_lock); + + for (; msk; msk >>= 1, i++) { + if (!msk & 0x01) + continue; + + /* Remove handler first. That will mask the irq line */ + irq_set_handler(i, NULL); + irq_set_chip(i, &no_irq_chip); + irq_set_chip_data(i, NULL); + irq_modify_status(i, clr, set); + } +} + +#ifdef CONFIG_PM +static int irq_gc_suspend(void) +{ + struct irq_chip_generic *gc; + + list_for_each_entry(gc, &gc_list, list) { + struct irq_chip_type *ct = gc->chip_types; + + if (ct->chip.irq_suspend) + ct->chip.irq_suspend(irq_get_irq_data(gc->irq_base)); + } + return 0; +} + +static void irq_gc_resume(void) +{ + struct irq_chip_generic *gc; + + list_for_each_entry(gc, &gc_list, list) { + struct irq_chip_type *ct = gc->chip_types; + + if (ct->chip.irq_resume) + ct->chip.irq_resume(irq_get_irq_data(gc->irq_base)); + } +} +#else +#define irq_gc_suspend NULL +#define irq_gc_resume NULL +#endif + +static void irq_gc_shutdown(void) +{ + struct irq_chip_generic *gc; + + list_for_each_entry(gc, &gc_list, list) { + struct irq_chip_type *ct = gc->chip_types; + + if (ct->chip.irq_pm_shutdown) + ct->chip.irq_pm_shutdown(irq_get_irq_data(gc->irq_base)); + } +} + +static struct syscore_ops irq_gc_syscore_ops = { + .suspend = irq_gc_suspend, + .resume = irq_gc_resume, + .shutdown = irq_gc_shutdown, +}; + +static int __init irq_gc_init_ops(void) +{ + register_syscore_ops(&irq_gc_syscore_ops); + return 0; +} +device_initcall(irq_gc_init_ops); -- cgit v1.2.3-70-g09d2 From 625f2a378e5a10f45fdc37932fc9f8a21676de9e Mon Sep 17 00:00:00 2001 From: Jonathan Corbet Date: Fri, 22 Apr 2011 11:19:10 -0600 Subject: sched: Get rid of lock_depth Neil Brown pointed out that lock_depth somehow escaped the BKL removal work. Let's get rid of it now. Note that the perf scripting utilities still have a bunch of code for dealing with common_lock_depth in tracepoints; I have left that in place in case anybody wants to use that code with older kernels. Suggested-by: Neil Brown Signed-off-by: Jonathan Corbet Cc: Arnd Bergmann Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Linus Torvalds Cc: Andrew Morton Link: http://lkml.kernel.org/r/20110422111910.456c0e84@bike.lwn.net Signed-off-by: Ingo Molnar --- Documentation/trace/kprobetrace.txt | 1 - include/linux/init_task.h | 1 - include/linux/sched.h | 6 ------ kernel/fork.c | 1 - kernel/mutex.c | 7 ------- kernel/sched.c | 11 +---------- kernel/sched_debug.c | 4 ---- kernel/trace/trace_kprobe.c | 1 - tools/perf/Documentation/perf-script-perl.txt | 1 - tools/perf/Documentation/perf-script-python.txt | 1 - 10 files changed, 1 insertion(+), 33 deletions(-) (limited to 'include') diff --git a/Documentation/trace/kprobetrace.txt b/Documentation/trace/kprobetrace.txt index 6d27ab8d6e9..c83bd6b4e6e 100644 --- a/Documentation/trace/kprobetrace.txt +++ b/Documentation/trace/kprobetrace.txt @@ -120,7 +120,6 @@ format: field:unsigned char common_flags; offset:2; size:1; signed:0; field:unsigned char common_preempt_count; offset:3; size:1;signed:0; field:int common_pid; offset:4; size:4; signed:1; - field:int common_lock_depth; offset:8; size:4; signed:1; field:unsigned long __probe_ip; offset:12; size:4; signed:0; field:int __probe_nargs; offset:16; size:4; signed:1; diff --git a/include/linux/init_task.h b/include/linux/init_task.h index caa151fbebb..689496bb665 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -134,7 +134,6 @@ extern struct cred init_cred; .stack = &init_thread_info, \ .usage = ATOMIC_INIT(2), \ .flags = PF_KTHREAD, \ - .lock_depth = -1, \ .prio = MAX_PRIO-20, \ .static_prio = MAX_PRIO-20, \ .normal_prio = MAX_PRIO-20, \ diff --git a/include/linux/sched.h b/include/linux/sched.h index 171ba24b08a..013314a5610 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -731,10 +731,6 @@ struct sched_info { /* timestamps */ unsigned long long last_arrival,/* when we last ran on a cpu */ last_queued; /* when we were last queued to run */ -#ifdef CONFIG_SCHEDSTATS - /* BKL stats */ - unsigned int bkl_count; -#endif }; #endif /* defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) */ @@ -1190,8 +1186,6 @@ struct task_struct { unsigned int flags; /* per process flags, defined below */ unsigned int ptrace; - int lock_depth; /* BKL lock depth */ - #ifdef CONFIG_SMP struct task_struct *wake_entry; int on_cpu; diff --git a/kernel/fork.c b/kernel/fork.c index e7548dee636..aca62871a4f 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1103,7 +1103,6 @@ static struct task_struct *copy_process(unsigned long clone_flags, posix_cpu_timers_init(p); - p->lock_depth = -1; /* -1 = no lock */ do_posix_clock_monotonic_gettime(&p->start_time); p->real_start_time = p->start_time; monotonic_to_bootbased(&p->real_start_time); diff --git a/kernel/mutex.c b/kernel/mutex.c index fe4706cb0c5..2c938e2337c 100644 --- a/kernel/mutex.c +++ b/kernel/mutex.c @@ -162,13 +162,6 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, for (;;) { struct task_struct *owner; - /* - * If we own the BKL, then don't spin. The owner of - * the mutex might be waiting on us to release the BKL. - */ - if (unlikely(current->lock_depth >= 0)) - break; - /* * If there's an owner, wait for it to either * release the lock or go to sleep. diff --git a/kernel/sched.c b/kernel/sched.c index 8cb0a5769a1..9cde2dd229c 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -4121,12 +4121,6 @@ static inline void schedule_debug(struct task_struct *prev) profile_hit(SCHED_PROFILING, __builtin_return_address(0)); schedstat_inc(this_rq(), sched_count); -#ifdef CONFIG_SCHEDSTATS - if (unlikely(prev->lock_depth >= 0)) { - schedstat_inc(this_rq(), rq_sched_info.bkl_count); - schedstat_inc(prev, sched_info.bkl_count); - } -#endif } static void put_prev_task(struct rq *rq, struct task_struct *prev) @@ -5852,11 +5846,8 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu) raw_spin_unlock_irqrestore(&rq->lock, flags); /* Set the preempt count _outside_ the spinlocks! */ -#if defined(CONFIG_PREEMPT) - task_thread_info(idle)->preempt_count = (idle->lock_depth >= 0); -#else task_thread_info(idle)->preempt_count = 0; -#endif + /* * The idle tasks have their own, simple scheduling class: */ diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c index 3669bec6e13..a6710a112b4 100644 --- a/kernel/sched_debug.c +++ b/kernel/sched_debug.c @@ -296,9 +296,6 @@ static void print_cpu(struct seq_file *m, int cpu) P(ttwu_count); P(ttwu_local); - SEQ_printf(m, " .%-30s: %d\n", "bkl_count", - rq->rq_sched_info.bkl_count); - #undef P #undef P64 #endif @@ -441,7 +438,6 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m) P(se.statistics.wait_count); PN(se.statistics.iowait_sum); P(se.statistics.iowait_count); - P(sched_info.bkl_count); P(se.nr_migrations); P(se.statistics.nr_migrations_cold); P(se.statistics.nr_failed_migrations_affine); diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 35d55a38614..f925c45f0af 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -53,7 +53,6 @@ const char *reserved_field_names[] = { "common_preempt_count", "common_pid", "common_tgid", - "common_lock_depth", FIELD_STRING_IP, FIELD_STRING_RETIP, FIELD_STRING_FUNC, diff --git a/tools/perf/Documentation/perf-script-perl.txt b/tools/perf/Documentation/perf-script-perl.txt index 5bb41e55a3a..3152cca1550 100644 --- a/tools/perf/Documentation/perf-script-perl.txt +++ b/tools/perf/Documentation/perf-script-perl.txt @@ -63,7 +63,6 @@ The format file for the sched_wakep event defines the following fields field:unsigned char common_flags; field:unsigned char common_preempt_count; field:int common_pid; - field:int common_lock_depth; field:char comm[TASK_COMM_LEN]; field:pid_t pid; diff --git a/tools/perf/Documentation/perf-script-python.txt b/tools/perf/Documentation/perf-script-python.txt index 36b38277422..47102206911 100644 --- a/tools/perf/Documentation/perf-script-python.txt +++ b/tools/perf/Documentation/perf-script-python.txt @@ -463,7 +463,6 @@ The format file for the sched_wakep event defines the following fields field:unsigned char common_flags; field:unsigned char common_preempt_count; field:int common_pid; - field:int common_lock_depth; field:char comm[TASK_COMM_LEN]; field:pid_t pid; -- cgit v1.2.3-70-g09d2 From bf26c018490c2fce7fe9b629083b96ce0e6ad019 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 7 Apr 2011 16:53:20 +0200 Subject: ptrace: Prepare to fix racy accesses on task breakpoints When a task is traced and is in a stopped state, the tracer may execute a ptrace request to examine the tracee state and get its task struct. Right after, the tracee can be killed and thus its breakpoints released. This can happen concurrently when the tracer is in the middle of reading or modifying these breakpoints, leading to dereferencing a freed pointer. Hence, to prepare the fix, create a generic breakpoint reference holding API. When a reference on the breakpoints of a task is held, the breakpoints won't be released until the last reference is dropped. After that, no more ptrace request on the task's breakpoints can be serviced for the tracer. Reported-by: Oleg Nesterov Signed-off-by: Frederic Weisbecker Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Will Deacon Cc: Prasad Cc: Paul Mundt Cc: v2.6.33.. Link: http://lkml.kernel.org/r/1302284067-7860-2-git-send-email-fweisbec@gmail.com --- include/linux/ptrace.h | 13 ++++++++++++- include/linux/sched.h | 3 +++ kernel/exit.c | 2 +- kernel/ptrace.c | 17 +++++++++++++++++ 4 files changed, 33 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index a1147e5dd24..9178d5cc0b0 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -189,6 +189,10 @@ static inline void ptrace_init_task(struct task_struct *child, bool ptrace) child->ptrace = current->ptrace; __ptrace_link(child, current->parent); } + +#ifdef CONFIG_HAVE_HW_BREAKPOINT + atomic_set(&child->ptrace_bp_refcnt, 1); +#endif } /** @@ -350,6 +354,13 @@ extern int task_current_syscall(struct task_struct *target, long *callno, unsigned long args[6], unsigned int maxargs, unsigned long *sp, unsigned long *pc); -#endif +#ifdef CONFIG_HAVE_HW_BREAKPOINT +extern int ptrace_get_breakpoints(struct task_struct *tsk); +extern void ptrace_put_breakpoints(struct task_struct *tsk); +#else +static inline void ptrace_put_breakpoints(struct task_struct *tsk) { } +#endif /* CONFIG_HAVE_HW_BREAKPOINT */ + +#endif /* __KERNEL */ #endif diff --git a/include/linux/sched.h b/include/linux/sched.h index 18d63cea284..781abd13767 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1537,6 +1537,9 @@ struct task_struct { unsigned long memsw_nr_pages; /* uncharged mem+swap usage */ } memcg_batch; #endif +#ifdef CONFIG_HAVE_HW_BREAKPOINT + atomic_t ptrace_bp_refcnt; +#endif }; /* Future-safe accessor for struct task_struct's cpus_allowed. */ diff --git a/kernel/exit.c b/kernel/exit.c index f5d2f63bae0..8dd87418154 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1016,7 +1016,7 @@ NORET_TYPE void do_exit(long code) /* * FIXME: do that only when needed, using sched_exit tracepoint */ - flush_ptrace_hw_breakpoint(tsk); + ptrace_put_breakpoints(tsk); exit_notify(tsk, group_dead); #ifdef CONFIG_NUMA diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 0fc1eed28d2..dc7ab65f3b3 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -22,6 +22,7 @@ #include #include #include +#include /* @@ -879,3 +880,19 @@ asmlinkage long compat_sys_ptrace(compat_long_t request, compat_long_t pid, return ret; } #endif /* CONFIG_COMPAT */ + +#ifdef CONFIG_HAVE_HW_BREAKPOINT +int ptrace_get_breakpoints(struct task_struct *tsk) +{ + if (atomic_inc_not_zero(&tsk->ptrace_bp_refcnt)) + return 0; + + return -1; +} + +void ptrace_put_breakpoints(struct task_struct *tsk) +{ + if (atomic_dec_and_test(&tsk->ptrace_bp_refcnt)) + flush_ptrace_hw_breakpoint(tsk); +} +#endif /* CONFIG_HAVE_HW_BREAKPOINT */ -- cgit v1.2.3-70-g09d2 From ad58671cf32c74a8d6e8f51e63e9cf4e7a73bf1e Mon Sep 17 00:00:00 2001 From: Jonathan Cameron Date: Tue, 19 Apr 2011 12:43:45 +0100 Subject: Add a strtobool function matching semantics of existing in kernel equivalents This is a rename of the usr_strtobool proposal, which was a renamed, relocated and fixed version of previous kstrtobool RFC Signed-off-by: Jonathan Cameron Signed-off-by: Greg Kroah-Hartman --- include/linux/string.h | 1 + lib/string.c | 29 +++++++++++++++++++++++++++++ 2 files changed, 30 insertions(+) (limited to 'include') diff --git a/include/linux/string.h b/include/linux/string.h index a716ee2a8ad..a176db2f2c8 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -123,6 +123,7 @@ extern char **argv_split(gfp_t gfp, const char *str, int *argcp); extern void argv_free(char **argv); extern bool sysfs_streq(const char *s1, const char *s2); +extern int strtobool(const char *s, bool *res); #ifdef CONFIG_BINARY_PRINTF int vbin_printf(u32 *bin_buf, size_t size, const char *fmt, va_list args); diff --git a/lib/string.c b/lib/string.c index f71bead1be3..01fad9b203e 100644 --- a/lib/string.c +++ b/lib/string.c @@ -535,6 +535,35 @@ bool sysfs_streq(const char *s1, const char *s2) } EXPORT_SYMBOL(sysfs_streq); +/** + * strtobool - convert common user inputs into boolean values + * @s: input string + * @res: result + * + * This routine returns 0 iff the first character is one of 'Yy1Nn0'. + * Otherwise it will return -EINVAL. Value pointed to by res is + * updated upon finding a match. + */ +int strtobool(const char *s, bool *res) +{ + switch (s[0]) { + case 'y': + case 'Y': + case '1': + *res = true; + break; + case 'n': + case 'N': + case '0': + *res = false; + break; + default: + return -EINVAL; + } + return 0; +} +EXPORT_SYMBOL(strtobool); + #ifndef __HAVE_ARCH_MEMSET /** * memset - Fill a region of memory with the given value -- cgit v1.2.3-70-g09d2 From 94403f8863d0d1d2005291b2ef0719c2534aa303 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sun, 24 Apr 2011 08:18:31 +0200 Subject: perf events: Add stalled cycles generic event - PERF_COUNT_HW_STALLED_CYCLES The new PERF_COUNT_HW_STALLED_CYCLES event tries to approximate cycles the CPU does nothing useful, because it is stalled on a cache-miss or some other condition. Acked-by: Peter Zijlstra Acked-by: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Link: http://lkml.kernel.org/n/tip-fue11vymwqsoo5to72jxxjyl@git.kernel.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event_intel.c | 3 +++ include/linux/perf_event.h | 1 + tools/perf/util/parse-events.c | 1 + tools/perf/util/python.c | 1 + 4 files changed, 6 insertions(+) (limited to 'include') diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 9ae4a2aa739..efa2704c9df 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -1413,6 +1413,9 @@ static __init int intel_pmu_init(void) x86_pmu.enable_all = intel_pmu_nhm_enable_all; x86_pmu.extra_regs = intel_nehalem_extra_regs; + /* Install the stalled-cycles event: 0xff: All reasons, 0xa2: Resource stalls */ + intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES] = 0xffa2; + if (ebx & 0x40) { /* * Erratum AAJ80 detected, we work it around by using diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index ee9f1e78280..ac636dd20a0 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -52,6 +52,7 @@ enum perf_hw_id { PERF_COUNT_HW_BRANCH_INSTRUCTIONS = 4, PERF_COUNT_HW_BRANCH_MISSES = 5, PERF_COUNT_HW_BUS_CYCLES = 6, + PERF_COUNT_HW_STALLED_CYCLES = 7, PERF_COUNT_HW_MAX, /* non-ABI */ }; diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 952b4ae3d95..1869e4c646d 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -38,6 +38,7 @@ static struct event_symbol event_symbols[] = { { CHW(BRANCH_INSTRUCTIONS), "branch-instructions", "branches" }, { CHW(BRANCH_MISSES), "branch-misses", "" }, { CHW(BUS_CYCLES), "bus-cycles", "" }, + { CHW(STALLED_CYCLES), "stalled-cycles", "" }, { CSW(CPU_CLOCK), "cpu-clock", "" }, { CSW(TASK_CLOCK), "task-clock", "" }, diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index f5e38451fdc..406f613ee61 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -798,6 +798,7 @@ static struct { { "COUNT_HW_BRANCH_INSTRUCTIONS", PERF_COUNT_HW_BRANCH_INSTRUCTIONS }, { "COUNT_HW_BRANCH_MISSES", PERF_COUNT_HW_BRANCH_MISSES }, { "COUNT_HW_BUS_CYCLES", PERF_COUNT_HW_BUS_CYCLES }, + { "COUNT_HW_STALLED_CYCLES", PERF_COUNT_HW_STALLED_CYCLES }, { "COUNT_HW_CACHE_L1D", PERF_COUNT_HW_CACHE_L1D }, { "COUNT_HW_CACHE_L1I", PERF_COUNT_HW_CACHE_L1I }, { "COUNT_HW_CACHE_LL", PERF_COUNT_HW_CACHE_LL }, -- cgit v1.2.3-70-g09d2 From 26fc8775b51484d8c0a671198639c6d5ae60533e Mon Sep 17 00:00:00 2001 From: Guennadi Liakhovetski Date: Fri, 15 Apr 2011 20:08:19 +0200 Subject: mmc: fix a race between card-detect rescan and clock-gate work instances Currently there is a race in the MMC core between a card-detect rescan work and the clock-gating work, scheduled from a command completion. Fix it by removing the dedicated clock-gating mutex and using the MMC standard locking mechanism instead. Signed-off-by: Guennadi Liakhovetski Cc: Simon Horman Cc: Magnus Damm Acked-by: Linus Walleij Cc: Signed-off-by: Chris Ball --- drivers/mmc/core/host.c | 9 ++++----- include/linux/mmc/host.h | 1 - 2 files changed, 4 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c index 461e6a17fb9..2b200c1cfbb 100644 --- a/drivers/mmc/core/host.c +++ b/drivers/mmc/core/host.c @@ -94,7 +94,7 @@ static void mmc_host_clk_gate_delayed(struct mmc_host *host) spin_unlock_irqrestore(&host->clk_lock, flags); return; } - mutex_lock(&host->clk_gate_mutex); + mmc_claim_host(host); spin_lock_irqsave(&host->clk_lock, flags); if (!host->clk_requests) { spin_unlock_irqrestore(&host->clk_lock, flags); @@ -104,7 +104,7 @@ static void mmc_host_clk_gate_delayed(struct mmc_host *host) pr_debug("%s: gated MCI clock\n", mmc_hostname(host)); } spin_unlock_irqrestore(&host->clk_lock, flags); - mutex_unlock(&host->clk_gate_mutex); + mmc_release_host(host); } /* @@ -130,7 +130,7 @@ void mmc_host_clk_ungate(struct mmc_host *host) { unsigned long flags; - mutex_lock(&host->clk_gate_mutex); + mmc_claim_host(host); spin_lock_irqsave(&host->clk_lock, flags); if (host->clk_gated) { spin_unlock_irqrestore(&host->clk_lock, flags); @@ -140,7 +140,7 @@ void mmc_host_clk_ungate(struct mmc_host *host) } host->clk_requests++; spin_unlock_irqrestore(&host->clk_lock, flags); - mutex_unlock(&host->clk_gate_mutex); + mmc_release_host(host); } /** @@ -215,7 +215,6 @@ static inline void mmc_host_clk_init(struct mmc_host *host) host->clk_gated = false; INIT_WORK(&host->clk_gate_work, mmc_host_clk_gate_work); spin_lock_init(&host->clk_lock); - mutex_init(&host->clk_gate_mutex); } /** diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index bcb793ec737..eb792cb6d74 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -183,7 +183,6 @@ struct mmc_host { struct work_struct clk_gate_work; /* delayed clock gate */ unsigned int clk_old; /* old clock value cache */ spinlock_t clk_lock; /* lock for clk fields */ - struct mutex clk_gate_mutex; /* mutex for clock gating */ #endif /* host specific block data */ -- cgit v1.2.3-70-g09d2 From acad9853b95df6a3887f52e0ec88e4a77119ee28 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Wed, 27 Apr 2011 23:08:51 -0700 Subject: Input: wm831x-ts - allow IRQ flags to be specified This allows maximum flexibility for configuring the direct GPIO based interrupts. Signed-off-by: Mark Brown Signed-off-by: Dmitry Torokhov --- drivers/input/touchscreen/wm831x-ts.c | 16 +++++++++++++--- include/linux/mfd/wm831x/pdata.h | 2 ++ 2 files changed, 15 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/input/touchscreen/wm831x-ts.c b/drivers/input/touchscreen/wm831x-ts.c index b9373012b3e..78e8705df20 100644 --- a/drivers/input/touchscreen/wm831x-ts.c +++ b/drivers/input/touchscreen/wm831x-ts.c @@ -241,7 +241,7 @@ static __devinit int wm831x_ts_probe(struct platform_device *pdev) struct wm831x_pdata *core_pdata = dev_get_platdata(pdev->dev.parent); struct wm831x_touch_pdata *pdata = NULL; struct input_dev *input_dev; - int error; + int error, irqf; if (core_pdata) pdata = core_pdata->touch; @@ -314,9 +314,14 @@ static __devinit int wm831x_ts_probe(struct platform_device *pdev) wm831x_set_bits(wm831x, WM831X_TOUCH_CONTROL_1, WM831X_TCH_RATE_MASK, 6); + if (pdata && pdata->data_irqf) + irqf = pdata->data_irqf; + else + irqf = IRQF_TRIGGER_HIGH; + error = request_threaded_irq(wm831x_ts->data_irq, NULL, wm831x_ts_data_irq, - IRQF_ONESHOT, + irqf | IRQF_ONESHOT, "Touchscreen data", wm831x_ts); if (error) { dev_err(&pdev->dev, "Failed to request data IRQ %d: %d\n", @@ -325,9 +330,14 @@ static __devinit int wm831x_ts_probe(struct platform_device *pdev) } disable_irq(wm831x_ts->data_irq); + if (pdata && pdata->pd_irqf) + irqf = pdata->pd_irqf; + else + irqf = IRQF_TRIGGER_HIGH; + error = request_threaded_irq(wm831x_ts->pd_irq, NULL, wm831x_ts_pen_down_irq, - IRQF_ONESHOT, + irqf | IRQF_ONESHOT, "Touchscreen pen down", wm831x_ts); if (error) { dev_err(&pdev->dev, "Failed to request pen down IRQ %d: %d\n", diff --git a/include/linux/mfd/wm831x/pdata.h b/include/linux/mfd/wm831x/pdata.h index 173086d42af..6b0eb130efb 100644 --- a/include/linux/mfd/wm831x/pdata.h +++ b/include/linux/mfd/wm831x/pdata.h @@ -81,7 +81,9 @@ struct wm831x_touch_pdata { int rpu; /** Pen down sensitivity resistor divider */ int pressure; /** Report pressure (boolean) */ unsigned int data_irq; /** Touch data ready IRQ */ + int data_irqf; /** IRQ flags for data ready IRQ */ unsigned int pd_irq; /** Touch pendown detect IRQ */ + int pd_irqf; /** IRQ flags for pen down IRQ */ }; enum wm831x_watchdog_action { -- cgit v1.2.3-70-g09d2 From 68972efa657040f891c7eda07c7da8c8dd576788 Mon Sep 17 00:00:00 2001 From: Paul Stewart Date: Thu, 28 Apr 2011 05:43:37 +0000 Subject: usbnet: Resubmit interrupt URB if device is open Resubmit interrupt URB if device is open. Use a flag set in usbnet_open() to determine this state. Also kill and free interrupt URB in usbnet_disconnect(). [Rebased off git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6.git] Signed-off-by: Paul Stewart Signed-off-by: David S. Miller --- drivers/net/usb/usbnet.c | 8 ++++++++ include/linux/usb/usbnet.h | 1 + 2 files changed, 9 insertions(+) (limited to 'include') diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 069c1cf0fdf..009bba3d753 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -736,6 +736,7 @@ int usbnet_open (struct net_device *net) } } + set_bit(EVENT_DEV_OPEN, &dev->flags); netif_start_queue (net); netif_info(dev, ifup, dev->net, "open: enable queueing (rx %d, tx %d) mtu %d %s framing\n", @@ -1259,6 +1260,9 @@ void usbnet_disconnect (struct usb_interface *intf) if (dev->driver_info->unbind) dev->driver_info->unbind (dev, intf); + usb_kill_urb(dev->interrupt); + usb_free_urb(dev->interrupt); + free_netdev(net); usb_put_dev (xdev); } @@ -1498,6 +1502,10 @@ int usbnet_resume (struct usb_interface *intf) int retval; if (!--dev->suspend_count) { + /* resume interrupt URBs */ + if (dev->interrupt && test_bit(EVENT_DEV_OPEN, &dev->flags)) + usb_submit_urb(dev->interrupt, GFP_NOIO); + spin_lock_irq(&dev->txq.lock); while ((res = usb_get_from_anchor(&dev->deferred))) { diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h index 0e1855079fb..605b0aa8d85 100644 --- a/include/linux/usb/usbnet.h +++ b/include/linux/usb/usbnet.h @@ -68,6 +68,7 @@ struct usbnet { # define EVENT_RX_PAUSED 5 # define EVENT_DEV_WAKING 6 # define EVENT_DEV_ASLEEP 7 +# define EVENT_DEV_OPEN 8 }; static inline struct usb_driver *driver_of(struct usb_interface *intf) -- cgit v1.2.3-70-g09d2 From 5d30b10bd68df007e7ae21e77d1e0ce184b53040 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Thu, 28 Apr 2011 15:55:52 -0400 Subject: flex_array: flex_array_prealloc takes a number of elements, not an end Change flex_array_prealloc to take the number of elements for which space should be allocated instead of the last (inclusive) element. Users and documentation are updated accordingly. flex_arrays got introduced before they had users. When folks started using it, they ended up needing a different API than was coded up originally. This swaps over to the API that folks apparently need. Based-on-patch-by: Steffen Klassert Signed-off-by: Eric Paris Tested-by: Chris Richards Acked-by: Dave Hansen Cc: stable@kernel.org [2.6.38+] --- Documentation/flexible-arrays.txt | 4 ++-- include/linux/flex_array.h | 2 +- lib/flex_array.c | 13 ++++++++----- security/selinux/ss/policydb.c | 6 +++--- 4 files changed, 14 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/Documentation/flexible-arrays.txt b/Documentation/flexible-arrays.txt index cb8a3a00cc9..df904aec990 100644 --- a/Documentation/flexible-arrays.txt +++ b/Documentation/flexible-arrays.txt @@ -66,10 +66,10 @@ trick is to ensure that any needed memory allocations are done before entering atomic context, using: int flex_array_prealloc(struct flex_array *array, unsigned int start, - unsigned int end, gfp_t flags); + unsigned int nr_elements, gfp_t flags); This function will ensure that memory for the elements indexed in the range -defined by start and end has been allocated. Thereafter, a +defined by start and nr_elements has been allocated. Thereafter, a flex_array_put() call on an element in that range is guaranteed not to block. diff --git a/include/linux/flex_array.h b/include/linux/flex_array.h index 70e4efabe0f..ebeb2f3ad06 100644 --- a/include/linux/flex_array.h +++ b/include/linux/flex_array.h @@ -61,7 +61,7 @@ struct flex_array { struct flex_array *flex_array_alloc(int element_size, unsigned int total, gfp_t flags); int flex_array_prealloc(struct flex_array *fa, unsigned int start, - unsigned int end, gfp_t flags); + unsigned int nr_elements, gfp_t flags); void flex_array_free(struct flex_array *fa); void flex_array_free_parts(struct flex_array *fa); int flex_array_put(struct flex_array *fa, unsigned int element_nr, void *src, diff --git a/lib/flex_array.c b/lib/flex_array.c index c0ea40ba208..0c33b24498b 100644 --- a/lib/flex_array.c +++ b/lib/flex_array.c @@ -232,10 +232,10 @@ EXPORT_SYMBOL(flex_array_clear); /** * flex_array_prealloc - guarantee that array space exists - * @fa: the flex array for which to preallocate parts - * @start: index of first array element for which space is allocated - * @end: index of last (inclusive) element for which space is allocated - * @flags: page allocation flags + * @fa: the flex array for which to preallocate parts + * @start: index of first array element for which space is allocated + * @nr_elements: number of elements for which space is allocated + * @flags: page allocation flags * * This will guarantee that no future calls to flex_array_put() * will allocate memory. It can be used if you are expecting to @@ -245,13 +245,16 @@ EXPORT_SYMBOL(flex_array_clear); * Locking must be provided by the caller. */ int flex_array_prealloc(struct flex_array *fa, unsigned int start, - unsigned int end, gfp_t flags) + unsigned int nr_elements, gfp_t flags) { int start_part; int end_part; int part_nr; + unsigned int end; struct flex_array_part *part; + end = start + nr_elements - 1; + if (start >= fa->total_nr_elements || end >= fa->total_nr_elements) return -ENOSPC; if (elements_fit_in_base(fa)) diff --git a/security/selinux/ss/policydb.c b/security/selinux/ss/policydb.c index e7b850ad57e..e6e7ce0d3d5 100644 --- a/security/selinux/ss/policydb.c +++ b/security/selinux/ss/policydb.c @@ -502,7 +502,7 @@ static int policydb_index(struct policydb *p) goto out; rc = flex_array_prealloc(p->type_val_to_struct_array, 0, - p->p_types.nprim - 1, GFP_KERNEL | __GFP_ZERO); + p->p_types.nprim, GFP_KERNEL | __GFP_ZERO); if (rc) goto out; @@ -519,7 +519,7 @@ static int policydb_index(struct policydb *p) goto out; rc = flex_array_prealloc(p->sym_val_to_name[i], - 0, p->symtab[i].nprim - 1, + 0, p->symtab[i].nprim, GFP_KERNEL | __GFP_ZERO); if (rc) goto out; @@ -2375,7 +2375,7 @@ int policydb_read(struct policydb *p, void *fp) goto bad; /* preallocate so we don't have to worry about the put ever failing */ - rc = flex_array_prealloc(p->type_attr_map_array, 0, p->p_types.nprim - 1, + rc = flex_array_prealloc(p->type_attr_map_array, 0, p->p_types.nprim, GFP_KERNEL | __GFP_ZERO); if (rc) goto bad; -- cgit v1.2.3-70-g09d2 From 69c9dd1ecf446ad8a830e4afc539a2a1adc85b78 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 29 Apr 2011 00:36:05 +0200 Subject: PM: Export platform bus type's default PM callbacks Export the default PM callbacks defined for the platform bus type so that they can be used by power domains for suspending and resuming platform devices in the future. Signed-off-by: Rafael J. Wysocki --- drivers/base/platform.c | 72 +++++++++++------------------------------ include/linux/platform_device.h | 60 ++++++++++++++++++++++++++++++++++ 2 files changed, 78 insertions(+), 54 deletions(-) (limited to 'include') diff --git a/drivers/base/platform.c b/drivers/base/platform.c index 9e0e4fc24c4..313556f28c9 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -667,7 +667,7 @@ static int platform_legacy_resume(struct device *dev) return ret; } -static int platform_pm_prepare(struct device *dev) +int platform_pm_prepare(struct device *dev) { struct device_driver *drv = dev->driver; int ret = 0; @@ -678,7 +678,7 @@ static int platform_pm_prepare(struct device *dev) return ret; } -static void platform_pm_complete(struct device *dev) +void platform_pm_complete(struct device *dev) { struct device_driver *drv = dev->driver; @@ -686,16 +686,11 @@ static void platform_pm_complete(struct device *dev) drv->pm->complete(dev); } -#else /* !CONFIG_PM_SLEEP */ - -#define platform_pm_prepare NULL -#define platform_pm_complete NULL - -#endif /* !CONFIG_PM_SLEEP */ +#endif /* CONFIG_PM_SLEEP */ #ifdef CONFIG_SUSPEND -int __weak platform_pm_suspend(struct device *dev) +int platform_pm_suspend(struct device *dev) { struct device_driver *drv = dev->driver; int ret = 0; @@ -713,7 +708,7 @@ int __weak platform_pm_suspend(struct device *dev) return ret; } -int __weak platform_pm_suspend_noirq(struct device *dev) +int platform_pm_suspend_noirq(struct device *dev) { struct device_driver *drv = dev->driver; int ret = 0; @@ -729,7 +724,7 @@ int __weak platform_pm_suspend_noirq(struct device *dev) return ret; } -int __weak platform_pm_resume(struct device *dev) +int platform_pm_resume(struct device *dev) { struct device_driver *drv = dev->driver; int ret = 0; @@ -747,7 +742,7 @@ int __weak platform_pm_resume(struct device *dev) return ret; } -int __weak platform_pm_resume_noirq(struct device *dev) +int platform_pm_resume_noirq(struct device *dev) { struct device_driver *drv = dev->driver; int ret = 0; @@ -763,18 +758,11 @@ int __weak platform_pm_resume_noirq(struct device *dev) return ret; } -#else /* !CONFIG_SUSPEND */ - -#define platform_pm_suspend NULL -#define platform_pm_resume NULL -#define platform_pm_suspend_noirq NULL -#define platform_pm_resume_noirq NULL - -#endif /* !CONFIG_SUSPEND */ +#endif /* CONFIG_SUSPEND */ #ifdef CONFIG_HIBERNATE_CALLBACKS -static int platform_pm_freeze(struct device *dev) +int platform_pm_freeze(struct device *dev) { struct device_driver *drv = dev->driver; int ret = 0; @@ -792,7 +780,7 @@ static int platform_pm_freeze(struct device *dev) return ret; } -static int platform_pm_freeze_noirq(struct device *dev) +int platform_pm_freeze_noirq(struct device *dev) { struct device_driver *drv = dev->driver; int ret = 0; @@ -808,7 +796,7 @@ static int platform_pm_freeze_noirq(struct device *dev) return ret; } -static int platform_pm_thaw(struct device *dev) +int platform_pm_thaw(struct device *dev) { struct device_driver *drv = dev->driver; int ret = 0; @@ -826,7 +814,7 @@ static int platform_pm_thaw(struct device *dev) return ret; } -static int platform_pm_thaw_noirq(struct device *dev) +int platform_pm_thaw_noirq(struct device *dev) { struct device_driver *drv = dev->driver; int ret = 0; @@ -842,7 +830,7 @@ static int platform_pm_thaw_noirq(struct device *dev) return ret; } -static int platform_pm_poweroff(struct device *dev) +int platform_pm_poweroff(struct device *dev) { struct device_driver *drv = dev->driver; int ret = 0; @@ -860,7 +848,7 @@ static int platform_pm_poweroff(struct device *dev) return ret; } -static int platform_pm_poweroff_noirq(struct device *dev) +int platform_pm_poweroff_noirq(struct device *dev) { struct device_driver *drv = dev->driver; int ret = 0; @@ -876,7 +864,7 @@ static int platform_pm_poweroff_noirq(struct device *dev) return ret; } -static int platform_pm_restore(struct device *dev) +int platform_pm_restore(struct device *dev) { struct device_driver *drv = dev->driver; int ret = 0; @@ -894,7 +882,7 @@ static int platform_pm_restore(struct device *dev) return ret; } -static int platform_pm_restore_noirq(struct device *dev) +int platform_pm_restore_noirq(struct device *dev) { struct device_driver *drv = dev->driver; int ret = 0; @@ -910,18 +898,7 @@ static int platform_pm_restore_noirq(struct device *dev) return ret; } -#else /* !CONFIG_HIBERNATE_CALLBACKS */ - -#define platform_pm_freeze NULL -#define platform_pm_thaw NULL -#define platform_pm_poweroff NULL -#define platform_pm_restore NULL -#define platform_pm_freeze_noirq NULL -#define platform_pm_thaw_noirq NULL -#define platform_pm_poweroff_noirq NULL -#define platform_pm_restore_noirq NULL - -#endif /* !CONFIG_HIBERNATE_CALLBACKS */ +#endif /* CONFIG_HIBERNATE_CALLBACKS */ #ifdef CONFIG_PM_RUNTIME @@ -949,23 +926,10 @@ int __weak platform_pm_runtime_idle(struct device *dev) #endif /* !CONFIG_PM_RUNTIME */ static const struct dev_pm_ops platform_dev_pm_ops = { - .prepare = platform_pm_prepare, - .complete = platform_pm_complete, - .suspend = platform_pm_suspend, - .resume = platform_pm_resume, - .freeze = platform_pm_freeze, - .thaw = platform_pm_thaw, - .poweroff = platform_pm_poweroff, - .restore = platform_pm_restore, - .suspend_noirq = platform_pm_suspend_noirq, - .resume_noirq = platform_pm_resume_noirq, - .freeze_noirq = platform_pm_freeze_noirq, - .thaw_noirq = platform_pm_thaw_noirq, - .poweroff_noirq = platform_pm_poweroff_noirq, - .restore_noirq = platform_pm_restore_noirq, .runtime_suspend = platform_pm_runtime_suspend, .runtime_resume = platform_pm_runtime_resume, .runtime_idle = platform_pm_runtime_idle, + USE_PLATFORM_PM_SLEEP_OPS }; struct bus_type platform_bus_type = { diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index 744942c95fe..e0093e061b0 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -205,4 +205,64 @@ static inline char *early_platform_driver_setup_func(void) \ } #endif /* MODULE */ +#ifdef CONFIG_PM_SLEEP +extern int platform_pm_prepare(struct device *dev); +extern void platform_pm_complete(struct device *dev); +#else +#define platform_pm_prepare NULL +#define platform_pm_complete NULL +#endif + +#ifdef CONFIG_SUSPEND +extern int platform_pm_suspend(struct device *dev); +extern int platform_pm_suspend_noirq(struct device *dev); +extern int platform_pm_resume(struct device *dev); +extern int platform_pm_resume_noirq(struct device *dev); +#else +#define platform_pm_suspend NULL +#define platform_pm_resume NULL +#define platform_pm_suspend_noirq NULL +#define platform_pm_resume_noirq NULL +#endif + +#ifdef CONFIG_HIBERNATE_CALLBACKS +extern int platform_pm_freeze(struct device *dev); +extern int platform_pm_freeze_noirq(struct device *dev); +extern int platform_pm_thaw(struct device *dev); +extern int platform_pm_thaw_noirq(struct device *dev); +extern int platform_pm_poweroff(struct device *dev); +extern int platform_pm_poweroff_noirq(struct device *dev); +extern int platform_pm_restore(struct device *dev); +extern int platform_pm_restore_noirq(struct device *dev); +#else +#define platform_pm_freeze NULL +#define platform_pm_thaw NULL +#define platform_pm_poweroff NULL +#define platform_pm_restore NULL +#define platform_pm_freeze_noirq NULL +#define platform_pm_thaw_noirq NULL +#define platform_pm_poweroff_noirq NULL +#define platform_pm_restore_noirq NULL +#endif + +#ifdef CONFIG_PM_SLEEP +#define USE_PLATFORM_PM_SLEEP_OPS \ + .prepare = platform_pm_prepare, \ + .complete = platform_pm_complete, \ + .suspend = platform_pm_suspend, \ + .resume = platform_pm_resume, \ + .freeze = platform_pm_freeze, \ + .thaw = platform_pm_thaw, \ + .poweroff = platform_pm_poweroff, \ + .restore = platform_pm_restore, \ + .suspend_noirq = platform_pm_suspend_noirq, \ + .resume_noirq = platform_pm_resume_noirq, \ + .freeze_noirq = platform_pm_freeze_noirq, \ + .thaw_noirq = platform_pm_thaw_noirq, \ + .poweroff_noirq = platform_pm_poweroff_noirq, \ + .restore_noirq = platform_pm_restore_noirq, +#else +#define USE_PLATFORM_PM_SLEEP_OPS +#endif + #endif /* _PLATFORM_DEVICE_H_ */ -- cgit v1.2.3-70-g09d2 From 1d2b71f61b6a10216274e27b717becf9ae101fc7 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 29 Apr 2011 00:36:53 +0200 Subject: PM / Runtime: Add subsystem data field to struct dev_pm_info Some subsystems need to attach PM-related data to struct device and they need to use devres for this purpose. For their convenience and to make code more straightforward, add a new field called subsys_data to struct dev_pm_info and let subsystems use it for attaching PM-related information to devices. Convert the ARM shmobile platform to using the new field. Signed-off-by: Rafael J. Wysocki --- arch/arm/mach-shmobile/pm_runtime.c | 34 +++++++++++++++++----------------- include/linux/pm.h | 1 + 2 files changed, 18 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/arch/arm/mach-shmobile/pm_runtime.c b/arch/arm/mach-shmobile/pm_runtime.c index 12bb504c7f4..30bbe9a99ae 100644 --- a/arch/arm/mach-shmobile/pm_runtime.c +++ b/arch/arm/mach-shmobile/pm_runtime.c @@ -18,6 +18,7 @@ #include #include #include +#include #ifdef CONFIG_PM_RUNTIME #define BIT_ONCE 0 @@ -29,22 +30,9 @@ struct pm_runtime_data { struct clk *clk; }; -static void __devres_release(struct device *dev, void *res) -{ - struct pm_runtime_data *prd = res; - - dev_dbg(dev, "__devres_release()\n"); - - if (test_bit(BIT_CLK_ENABLED, &prd->flags)) - clk_disable(prd->clk); - - if (test_bit(BIT_ACTIVE, &prd->flags)) - clk_put(prd->clk); -} - static struct pm_runtime_data *__to_prd(struct device *dev) { - return devres_find(dev, __devres_release, NULL, NULL); + return dev ? dev->power.subsys_data : NULL; } static void platform_pm_runtime_init(struct device *dev, @@ -121,14 +109,26 @@ static int platform_bus_notify(struct notifier_block *nb, dev_dbg(dev, "platform_bus_notify() %ld !\n", action); - if (action == BUS_NOTIFY_BIND_DRIVER) { - prd = devres_alloc(__devres_release, sizeof(*prd), GFP_KERNEL); + switch (action) { + case BUS_NOTIFY_BIND_DRIVER: + prd = kzalloc(sizeof(*prd), GFP_KERNEL); if (prd) { - devres_add(dev, prd); + dev->power.subsys_data = prd; dev->pwr_domain = &default_power_domain; } else { dev_err(dev, "unable to alloc memory for runtime pm\n"); } + break; + case BUS_NOTIFY_UNBOUND_DRIVER: + prd = __to_prd(dev); + if (prd) { + if (test_bit(BIT_CLK_ENABLED, &prd->flags)) + clk_disable(prd->clk); + + if (test_bit(BIT_ACTIVE, &prd->flags)) + clk_put(prd->clk); + } + break; } return 0; diff --git a/include/linux/pm.h b/include/linux/pm.h index 512e09177e5..f4167d0faa6 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -460,6 +460,7 @@ struct dev_pm_info { unsigned long active_jiffies; unsigned long suspended_jiffies; unsigned long accounting_timestamp; + void *subsys_data; /* Owned by the subsystem. */ #endif }; -- cgit v1.2.3-70-g09d2 From 8f62242246351b5a4bc0c1f00c0c7003edea128a Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 29 Apr 2011 13:19:47 +0200 Subject: perf events: Add generic front-end and back-end stalled cycle event definitions Add two generic hardware events: front-end and back-end stalled cycles. These events measure conditions when the CPU is executing code but its capabilities are not fully utilized. Understanding such situations and analyzing them is an important sub-task of code optimization workflows. Both events limit performance: most front end stalls tend to be caused by branch misprediction or instruction fetch cachemisses, backend stalls can be caused by various resource shortages or inefficient instruction scheduling. Front-end stalls are the more important ones: code cannot run fast if the instruction stream is not being kept up. An over-utilized back-end can cause front-end stalls and thus has to be kept an eye on as well. The exact composition is very program logic and instruction mix dependent. We use the terms 'stall', 'front-end' and 'back-end' loosely and try to use the best available events from specific CPUs that approximate these concepts. Cc: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Link: http://lkml.kernel.org/n/tip-7y40wib8n000io7hjpn1dsrm@git.kernel.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event_intel.c | 2 +- include/linux/perf_event.h | 3 ++- 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 1ea94224f62..393085b87a2 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -1414,7 +1414,7 @@ static __init int intel_pmu_init(void) x86_pmu.extra_regs = intel_nehalem_extra_regs; /* Install the stalled-cycles event: UOPS_EXECUTED.CORE_ACTIVE_CYCLES,c=1,i=1 */ - intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES] = 0x1803fb1; + intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x1803fb1; if (ebx & 0x40) { /* diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index ac636dd20a0..4e2d7ae7149 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -52,7 +52,8 @@ enum perf_hw_id { PERF_COUNT_HW_BRANCH_INSTRUCTIONS = 4, PERF_COUNT_HW_BRANCH_MISSES = 5, PERF_COUNT_HW_BUS_CYCLES = 6, - PERF_COUNT_HW_STALLED_CYCLES = 7, + PERF_COUNT_HW_STALLED_CYCLES_FRONTEND = 7, + PERF_COUNT_HW_STALLED_CYCLES_BACKEND = 8, PERF_COUNT_HW_MAX, /* non-ABI */ }; -- cgit v1.2.3-70-g09d2 From 85eb8c8d0b0900c073b0e6f89979ac9c439ade1a Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sat, 30 Apr 2011 00:25:44 +0200 Subject: PM / Runtime: Generic clock manipulation rountines for runtime PM (v6) Many different platforms and subsystems may want to disable device clocks during suspend and enable them during resume which is going to be done in a very similar way in all those cases. For this reason, provide generic routines for the manipulation of device clocks during suspend and resume. Convert the ARM shmobile platform to using the new routines. Signed-off-by: Rafael J. Wysocki --- arch/arm/mach-shmobile/pm_runtime.c | 140 +----------- drivers/base/power/Makefile | 1 + drivers/base/power/clock_ops.c | 430 ++++++++++++++++++++++++++++++++++++ include/linux/pm_runtime.h | 42 ++++ kernel/power/Kconfig | 4 + 5 files changed, 486 insertions(+), 131 deletions(-) create mode 100644 drivers/base/power/clock_ops.c (limited to 'include') diff --git a/arch/arm/mach-shmobile/pm_runtime.c b/arch/arm/mach-shmobile/pm_runtime.c index 30bbe9a99ae..2d1b67a59e4 100644 --- a/arch/arm/mach-shmobile/pm_runtime.c +++ b/arch/arm/mach-shmobile/pm_runtime.c @@ -21,70 +21,6 @@ #include #ifdef CONFIG_PM_RUNTIME -#define BIT_ONCE 0 -#define BIT_ACTIVE 1 -#define BIT_CLK_ENABLED 2 - -struct pm_runtime_data { - unsigned long flags; - struct clk *clk; -}; - -static struct pm_runtime_data *__to_prd(struct device *dev) -{ - return dev ? dev->power.subsys_data : NULL; -} - -static void platform_pm_runtime_init(struct device *dev, - struct pm_runtime_data *prd) -{ - if (prd && !test_and_set_bit(BIT_ONCE, &prd->flags)) { - prd->clk = clk_get(dev, NULL); - if (!IS_ERR(prd->clk)) { - set_bit(BIT_ACTIVE, &prd->flags); - dev_info(dev, "clocks managed by runtime pm\n"); - } - } -} - -static void platform_pm_runtime_bug(struct device *dev, - struct pm_runtime_data *prd) -{ - if (prd && !test_and_set_bit(BIT_ONCE, &prd->flags)) - dev_err(dev, "runtime pm suspend before resume\n"); -} - -static int default_platform_runtime_suspend(struct device *dev) -{ - struct pm_runtime_data *prd = __to_prd(dev); - - dev_dbg(dev, "%s()\n", __func__); - - platform_pm_runtime_bug(dev, prd); - - if (prd && test_bit(BIT_ACTIVE, &prd->flags)) { - clk_disable(prd->clk); - clear_bit(BIT_CLK_ENABLED, &prd->flags); - } - - return 0; -} - -static int default_platform_runtime_resume(struct device *dev) -{ - struct pm_runtime_data *prd = __to_prd(dev); - - dev_dbg(dev, "%s()\n", __func__); - - platform_pm_runtime_init(dev, prd); - - if (prd && test_bit(BIT_ACTIVE, &prd->flags)) { - clk_enable(prd->clk); - set_bit(BIT_CLK_ENABLED, &prd->flags); - } - - return 0; -} static int default_platform_runtime_idle(struct device *dev) { @@ -94,87 +30,29 @@ static int default_platform_runtime_idle(struct device *dev) static struct dev_power_domain default_power_domain = { .ops = { - .runtime_suspend = default_platform_runtime_suspend, - .runtime_resume = default_platform_runtime_resume, + .runtime_suspend = pm_runtime_clk_suspend, + .runtime_resume = pm_runtime_clk_resume, .runtime_idle = default_platform_runtime_idle, USE_PLATFORM_PM_SLEEP_OPS }, }; -static int platform_bus_notify(struct notifier_block *nb, - unsigned long action, void *data) -{ - struct device *dev = data; - struct pm_runtime_data *prd; - - dev_dbg(dev, "platform_bus_notify() %ld !\n", action); - - switch (action) { - case BUS_NOTIFY_BIND_DRIVER: - prd = kzalloc(sizeof(*prd), GFP_KERNEL); - if (prd) { - dev->power.subsys_data = prd; - dev->pwr_domain = &default_power_domain; - } else { - dev_err(dev, "unable to alloc memory for runtime pm\n"); - } - break; - case BUS_NOTIFY_UNBOUND_DRIVER: - prd = __to_prd(dev); - if (prd) { - if (test_bit(BIT_CLK_ENABLED, &prd->flags)) - clk_disable(prd->clk); +#define DEFAULT_PWR_DOMAIN_PTR (&default_power_domain) - if (test_bit(BIT_ACTIVE, &prd->flags)) - clk_put(prd->clk); - } - break; - } +#else - return 0; -} - -#else /* CONFIG_PM_RUNTIME */ - -static int platform_bus_notify(struct notifier_block *nb, - unsigned long action, void *data) -{ - struct device *dev = data; - struct clk *clk; - - dev_dbg(dev, "platform_bus_notify() %ld !\n", action); - - switch (action) { - case BUS_NOTIFY_BIND_DRIVER: - clk = clk_get(dev, NULL); - if (!IS_ERR(clk)) { - clk_enable(clk); - clk_put(clk); - dev_info(dev, "runtime pm disabled, clock forced on\n"); - } - break; - case BUS_NOTIFY_UNBOUND_DRIVER: - clk = clk_get(dev, NULL); - if (!IS_ERR(clk)) { - clk_disable(clk); - clk_put(clk); - dev_info(dev, "runtime pm disabled, clock forced off\n"); - } - break; - } - - return 0; -} +#define DEFAULT_PWR_DOMAIN_PTR NULL #endif /* CONFIG_PM_RUNTIME */ -static struct notifier_block platform_bus_notifier = { - .notifier_call = platform_bus_notify +static struct pm_clk_notifier_block platform_bus_notifier = { + .pwr_domain = DEFAULT_PWR_DOMAIN_PTR, + .con_ids = { NULL, }, }; static int __init sh_pm_runtime_init(void) { - bus_register_notifier(&platform_bus_type, &platform_bus_notifier); + pm_runtime_clk_add_notifier(&platform_bus_type, &platform_bus_notifier); return 0; } core_initcall(sh_pm_runtime_init); diff --git a/drivers/base/power/Makefile b/drivers/base/power/Makefile index 118c1b92a51..06a7073f902 100644 --- a/drivers/base/power/Makefile +++ b/drivers/base/power/Makefile @@ -3,6 +3,7 @@ obj-$(CONFIG_PM_SLEEP) += main.o wakeup.o obj-$(CONFIG_PM_RUNTIME) += runtime.o obj-$(CONFIG_PM_TRACE_RTC) += trace.o obj-$(CONFIG_PM_OPP) += opp.o +obj-$(CONFIG_HAVE_CLK) += clock_ops.o ccflags-$(CONFIG_DEBUG_DRIVER) := -DDEBUG ccflags-$(CONFIG_PM_VERBOSE) += -DDEBUG diff --git a/drivers/base/power/clock_ops.c b/drivers/base/power/clock_ops.c new file mode 100644 index 00000000000..d74abf33439 --- /dev/null +++ b/drivers/base/power/clock_ops.c @@ -0,0 +1,430 @@ +/* + * drivers/base/power/clock_ops.c - Generic clock manipulation PM callbacks + * + * Copyright (c) 2011 Rafael J. Wysocki , Renesas Electronics Corp. + * + * This file is released under the GPLv2. + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#ifdef CONFIG_PM_RUNTIME + +struct pm_runtime_clk_data { + struct list_head clock_list; + struct mutex lock; +}; + +enum pce_status { + PCE_STATUS_NONE = 0, + PCE_STATUS_ACQUIRED, + PCE_STATUS_ENABLED, + PCE_STATUS_ERROR, +}; + +struct pm_clock_entry { + struct list_head node; + char *con_id; + struct clk *clk; + enum pce_status status; +}; + +static struct pm_runtime_clk_data *__to_prd(struct device *dev) +{ + return dev ? dev->power.subsys_data : NULL; +} + +/** + * pm_runtime_clk_add - Start using a device clock for runtime PM. + * @dev: Device whose clock is going to be used for runtime PM. + * @con_id: Connection ID of the clock. + * + * Add the clock represented by @con_id to the list of clocks used for + * the runtime PM of @dev. + */ +int pm_runtime_clk_add(struct device *dev, const char *con_id) +{ + struct pm_runtime_clk_data *prd = __to_prd(dev); + struct pm_clock_entry *ce; + + if (!prd) + return -EINVAL; + + ce = kzalloc(sizeof(*ce), GFP_KERNEL); + if (!ce) { + dev_err(dev, "Not enough memory for clock entry.\n"); + return -ENOMEM; + } + + if (con_id) { + ce->con_id = kstrdup(con_id, GFP_KERNEL); + if (!ce->con_id) { + dev_err(dev, + "Not enough memory for clock connection ID.\n"); + kfree(ce); + return -ENOMEM; + } + } + + mutex_lock(&prd->lock); + list_add_tail(&ce->node, &prd->clock_list); + mutex_unlock(&prd->lock); + return 0; +} + +/** + * __pm_runtime_clk_remove - Destroy runtime PM clock entry. + * @ce: Runtime PM clock entry to destroy. + * + * This routine must be called under the mutex protecting the runtime PM list + * of clocks corresponding the the @ce's device. + */ +static void __pm_runtime_clk_remove(struct pm_clock_entry *ce) +{ + if (!ce) + return; + + list_del(&ce->node); + + if (ce->status < PCE_STATUS_ERROR) { + if (ce->status == PCE_STATUS_ENABLED) + clk_disable(ce->clk); + + if (ce->status >= PCE_STATUS_ACQUIRED) + clk_put(ce->clk); + } + + if (ce->con_id) + kfree(ce->con_id); + + kfree(ce); +} + +/** + * pm_runtime_clk_remove - Stop using a device clock for runtime PM. + * @dev: Device whose clock should not be used for runtime PM any more. + * @con_id: Connection ID of the clock. + * + * Remove the clock represented by @con_id from the list of clocks used for + * the runtime PM of @dev. + */ +void pm_runtime_clk_remove(struct device *dev, const char *con_id) +{ + struct pm_runtime_clk_data *prd = __to_prd(dev); + struct pm_clock_entry *ce; + + if (!prd) + return; + + mutex_lock(&prd->lock); + + list_for_each_entry(ce, &prd->clock_list, node) { + if (!con_id && !ce->con_id) { + __pm_runtime_clk_remove(ce); + break; + } else if (!con_id || !ce->con_id) { + continue; + } else if (!strcmp(con_id, ce->con_id)) { + __pm_runtime_clk_remove(ce); + break; + } + } + + mutex_unlock(&prd->lock); +} + +/** + * pm_runtime_clk_init - Initialize a device's list of runtime PM clocks. + * @dev: Device to initialize the list of runtime PM clocks for. + * + * Allocate a struct pm_runtime_clk_data object, initialize its lock member and + * make the @dev's power.subsys_data field point to it. + */ +int pm_runtime_clk_init(struct device *dev) +{ + struct pm_runtime_clk_data *prd; + + prd = kzalloc(sizeof(*prd), GFP_KERNEL); + if (!prd) { + dev_err(dev, "Not enough memory fo runtime PM data.\n"); + return -ENOMEM; + } + + INIT_LIST_HEAD(&prd->clock_list); + mutex_init(&prd->lock); + dev->power.subsys_data = prd; + return 0; +} + +/** + * pm_runtime_clk_destroy - Destroy a device's list of runtime PM clocks. + * @dev: Device to destroy the list of runtime PM clocks for. + * + * Clear the @dev's power.subsys_data field, remove the list of clock entries + * from the struct pm_runtime_clk_data object pointed to by it before and free + * that object. + */ +void pm_runtime_clk_destroy(struct device *dev) +{ + struct pm_runtime_clk_data *prd = __to_prd(dev); + struct pm_clock_entry *ce, *c; + + if (!prd) + return; + + dev->power.subsys_data = NULL; + + mutex_lock(&prd->lock); + + list_for_each_entry_safe_reverse(ce, c, &prd->clock_list, node) + __pm_runtime_clk_remove(ce); + + mutex_unlock(&prd->lock); + + kfree(prd); +} + +/** + * pm_runtime_clk_acquire - Acquire a device clock. + * @dev: Device whose clock is to be acquired. + * @con_id: Connection ID of the clock. + */ +static void pm_runtime_clk_acquire(struct device *dev, + struct pm_clock_entry *ce) +{ + ce->clk = clk_get(dev, ce->con_id); + if (IS_ERR(ce->clk)) { + ce->status = PCE_STATUS_ERROR; + } else { + ce->status = PCE_STATUS_ACQUIRED; + dev_dbg(dev, "Clock %s managed by runtime PM.\n", ce->con_id); + } +} + +/** + * pm_runtime_clk_suspend - Disable clocks in a device's runtime PM clock list. + * @dev: Device to disable the clocks for. + */ +int pm_runtime_clk_suspend(struct device *dev) +{ + struct pm_runtime_clk_data *prd = __to_prd(dev); + struct pm_clock_entry *ce; + + dev_dbg(dev, "%s()\n", __func__); + + if (!prd) + return 0; + + mutex_lock(&prd->lock); + + list_for_each_entry_reverse(ce, &prd->clock_list, node) { + if (ce->status == PCE_STATUS_NONE) + pm_runtime_clk_acquire(dev, ce); + + if (ce->status < PCE_STATUS_ERROR) { + clk_disable(ce->clk); + ce->status = PCE_STATUS_ACQUIRED; + } + } + + mutex_unlock(&prd->lock); + + return 0; +} + +/** + * pm_runtime_clk_resume - Enable clocks in a device's runtime PM clock list. + * @dev: Device to enable the clocks for. + */ +int pm_runtime_clk_resume(struct device *dev) +{ + struct pm_runtime_clk_data *prd = __to_prd(dev); + struct pm_clock_entry *ce; + + dev_dbg(dev, "%s()\n", __func__); + + if (!prd) + return 0; + + mutex_lock(&prd->lock); + + list_for_each_entry(ce, &prd->clock_list, node) { + if (ce->status == PCE_STATUS_NONE) + pm_runtime_clk_acquire(dev, ce); + + if (ce->status < PCE_STATUS_ERROR) { + clk_enable(ce->clk); + ce->status = PCE_STATUS_ENABLED; + } + } + + mutex_unlock(&prd->lock); + + return 0; +} + +/** + * pm_runtime_clk_notify - Notify routine for device addition and removal. + * @nb: Notifier block object this function is a member of. + * @action: Operation being carried out by the caller. + * @data: Device the routine is being run for. + * + * For this function to work, @nb must be a member of an object of type + * struct pm_clk_notifier_block containing all of the requisite data. + * Specifically, the pwr_domain member of that object is copied to the device's + * pwr_domain field and its con_ids member is used to populate the device's list + * of runtime PM clocks, depending on @action. + * + * If the device's pwr_domain field is already populated with a value different + * from the one stored in the struct pm_clk_notifier_block object, the function + * does nothing. + */ +static int pm_runtime_clk_notify(struct notifier_block *nb, + unsigned long action, void *data) +{ + struct pm_clk_notifier_block *clknb; + struct device *dev = data; + char *con_id; + int error; + + dev_dbg(dev, "%s() %ld\n", __func__, action); + + clknb = container_of(nb, struct pm_clk_notifier_block, nb); + + switch (action) { + case BUS_NOTIFY_ADD_DEVICE: + if (dev->pwr_domain) + break; + + error = pm_runtime_clk_init(dev); + if (error) + break; + + dev->pwr_domain = clknb->pwr_domain; + if (clknb->con_ids[0]) { + for (con_id = clknb->con_ids[0]; *con_id; con_id++) + pm_runtime_clk_add(dev, con_id); + } else { + pm_runtime_clk_add(dev, NULL); + } + + break; + case BUS_NOTIFY_DEL_DEVICE: + if (dev->pwr_domain != clknb->pwr_domain) + break; + + dev->pwr_domain = NULL; + pm_runtime_clk_destroy(dev); + break; + } + + return 0; +} + +#else /* !CONFIG_PM_RUNTIME */ + +/** + * enable_clock - Enable a device clock. + * @dev: Device whose clock is to be enabled. + * @con_id: Connection ID of the clock. + */ +static void enable_clock(struct device *dev, const char *con_id) +{ + struct clk *clk; + + clk = clk_get(dev, con_id); + if (!IS_ERR(clk)) { + clk_enable(clk); + clk_put(clk); + dev_info(dev, "Runtime PM disabled, clock forced on.\n"); + } +} + +/** + * disable_clock - Disable a device clock. + * @dev: Device whose clock is to be disabled. + * @con_id: Connection ID of the clock. + */ +static void disable_clock(struct device *dev, const char *con_id) +{ + struct clk *clk; + + clk = clk_get(dev, con_id); + if (!IS_ERR(clk)) { + clk_disable(clk); + clk_put(clk); + dev_info(dev, "Runtime PM disabled, clock forced off.\n"); + } +} + +/** + * pm_runtime_clk_notify - Notify routine for device addition and removal. + * @nb: Notifier block object this function is a member of. + * @action: Operation being carried out by the caller. + * @data: Device the routine is being run for. + * + * For this function to work, @nb must be a member of an object of type + * struct pm_clk_notifier_block containing all of the requisite data. + * Specifically, the con_ids member of that object is used to enable or disable + * the device's clocks, depending on @action. + */ +static int pm_runtime_clk_notify(struct notifier_block *nb, + unsigned long action, void *data) +{ + struct pm_clk_notifier_block *clknb; + struct device *dev = data; + + dev_dbg(dev, "%s() %ld\n", __func__, action); + + clknb = container_of(nb, struct pm_clk_notifier_block, nb); + + switch (action) { + case BUS_NOTIFY_ADD_DEVICE: + if (clknb->con_ids[0]) { + for (con_id = clknb->con_ids[0]; *con_id; con_id++) + enable_clock(dev, con_id); + } else { + enable_clock(dev, NULL); + } + break; + case BUS_NOTIFY_DEL_DEVICE: + if (clknb->con_ids[0]) { + for (con_id = clknb->con_ids[0]; *con_id; con_id++) + disable_clock(dev, con_id); + } else { + disable_clock(dev, NULL); + } + break; + } + + return 0; +} + +#endif /* !CONFIG_PM_RUNTIME */ + +/** + * pm_runtime_clk_add_notifier - Add bus type notifier for runtime PM clocks. + * @bus: Bus type to add the notifier to. + * @clknb: Notifier to be added to the given bus type. + * + * The nb member of @clknb is not expected to be initialized and its + * notifier_call member will be replaced with pm_runtime_clk_notify(). However, + * the remaining members of @clknb should be populated prior to calling this + * routine. + */ +void pm_runtime_clk_add_notifier(struct bus_type *bus, + struct pm_clk_notifier_block *clknb) +{ + if (!bus || !clknb) + return; + + clknb->nb.notifier_call = pm_runtime_clk_notify; + bus_register_notifier(bus, &clknb->nb); +} diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index 8de9aa6e7de..878cf84baeb 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -245,4 +245,46 @@ static inline void pm_runtime_dont_use_autosuspend(struct device *dev) __pm_runtime_use_autosuspend(dev, false); } +struct pm_clk_notifier_block { + struct notifier_block nb; + struct dev_power_domain *pwr_domain; + char *con_ids[]; +}; + +#ifdef CONFIG_PM_RUNTIME_CLK +extern int pm_runtime_clk_init(struct device *dev); +extern void pm_runtime_clk_destroy(struct device *dev); +extern int pm_runtime_clk_add(struct device *dev, const char *con_id); +extern void pm_runtime_clk_remove(struct device *dev, const char *con_id); +extern int pm_runtime_clk_suspend(struct device *dev); +extern int pm_runtime_clk_resume(struct device *dev); +#else +static inline int pm_runtime_clk_init(struct device *dev) +{ + return -EINVAL; +} +static inline void pm_runtime_clk_destroy(struct device *dev) +{ +} +static inline int pm_runtime_clk_add(struct device *dev, const char *con_id) +{ + return -EINVAL; +} +static inline void pm_runtime_clk_remove(struct device *dev, const char *con_id) +{ +} +#define pm_runtime_clock_suspend NULL +#define pm_runtime_clock_resume NULL +#endif + +#ifdef CONFIG_HAVE_CLK +extern void pm_runtime_clk_add_notifier(struct bus_type *bus, + struct pm_clk_notifier_block *clknb); +#else +static inline void pm_runtime_clk_add_notifier(struct bus_type *bus, + struct pm_clk_notifier_block *clknb) +{ +} +#endif + #endif diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig index 6de9a8fc341..d74ad4a9069 100644 --- a/kernel/power/Kconfig +++ b/kernel/power/Kconfig @@ -229,3 +229,7 @@ config PM_OPP representing individual voltage domains and provides SOC implementations a ready to use framework to manage OPPs. For more information, read + +config PM_RUNTIME_CLK + def_bool y + depends on PM_RUNTIME && HAVE_CLK -- cgit v1.2.3-70-g09d2 From 45a4a2372b364107cabea79f255b333236626416 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 21 Apr 2011 23:16:46 -0400 Subject: ftrace: Remove FTRACE_FL_FAILED flag Since we disable all function tracer processing if we detect that a modification of a instruction had failed, we do not need to track that the record has failed. No more ftrace processing is allowed, and the FTRACE_FL_FAILED flag is pointless. Removing this flag simplifies some of the code, but some ftrace_disabled checks needed to be added or move around a little. Signed-off-by: Steven Rostedt --- include/linux/ftrace.h | 9 +++--- kernel/trace/ftrace.c | 76 +++++++++++++++++++++++++++++++------------------- 2 files changed, 51 insertions(+), 34 deletions(-) (limited to 'include') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index ca29e03c1fa..2a195ffd426 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -147,11 +147,10 @@ extern int ftrace_text_reserved(void *start, void *end); enum { FTRACE_FL_FREE = (1 << 0), - FTRACE_FL_FAILED = (1 << 1), - FTRACE_FL_FILTER = (1 << 2), - FTRACE_FL_ENABLED = (1 << 3), - FTRACE_FL_NOTRACE = (1 << 4), - FTRACE_FL_CONVERTED = (1 << 5), + FTRACE_FL_FILTER = (1 << 1), + FTRACE_FL_ENABLED = (1 << 2), + FTRACE_FL_NOTRACE = (1 << 3), + FTRACE_FL_CONVERTED = (1 << 4), }; struct dyn_ftrace { diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 97b30f81864..eb19fae2c54 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1083,19 +1083,20 @@ static void ftrace_replace_code(int enable) struct ftrace_page *pg; int failed; + if (unlikely(ftrace_disabled)) + return; + do_for_each_ftrace_rec(pg, rec) { /* * Skip over free records, records that have * failed and not converted. */ if (rec->flags & FTRACE_FL_FREE || - rec->flags & FTRACE_FL_FAILED || !(rec->flags & FTRACE_FL_CONVERTED)) continue; failed = __ftrace_replace_code(rec, enable); if (failed) { - rec->flags |= FTRACE_FL_FAILED; ftrace_bug(failed, rec->ip); /* Stop processing */ return; @@ -1111,10 +1112,12 @@ ftrace_code_disable(struct module *mod, struct dyn_ftrace *rec) ip = rec->ip; + if (unlikely(ftrace_disabled)) + return 0; + ret = ftrace_make_nop(mod, rec, MCOUNT_ADDR); if (ret) { ftrace_bug(ret, ip); - rec->flags |= FTRACE_FL_FAILED; return 0; } return 1; @@ -1466,6 +1469,9 @@ t_next(struct seq_file *m, void *v, loff_t *pos) struct ftrace_iterator *iter = m->private; struct dyn_ftrace *rec = NULL; + if (unlikely(ftrace_disabled)) + return NULL; + if (iter->flags & FTRACE_ITER_HASH) return t_hash_next(m, pos); @@ -1518,6 +1524,10 @@ static void *t_start(struct seq_file *m, loff_t *pos) loff_t l; mutex_lock(&ftrace_lock); + + if (unlikely(ftrace_disabled)) + return NULL; + /* * If an lseek was done, then reset and start from beginning. */ @@ -1636,8 +1646,6 @@ static void ftrace_filter_reset(int enable) if (enable) ftrace_filtered = 0; do_for_each_ftrace_rec(pg, rec) { - if (rec->flags & FTRACE_FL_FAILED) - continue; rec->flags &= ~type; } while_for_each_ftrace_rec(); mutex_unlock(&ftrace_lock); @@ -1767,9 +1775,6 @@ static int ftrace_match_records(char *buff, int len, int enable) mutex_lock(&ftrace_lock); do_for_each_ftrace_rec(pg, rec) { - if (rec->flags & FTRACE_FL_FAILED) - continue; - if (ftrace_match_record(rec, search, search_len, type)) { if (not) rec->flags &= ~flag; @@ -1837,10 +1842,11 @@ static int ftrace_match_module_records(char *buff, char *mod, int enable) } mutex_lock(&ftrace_lock); - do_for_each_ftrace_rec(pg, rec) { - if (rec->flags & FTRACE_FL_FAILED) - continue; + if (unlikely(ftrace_disabled)) + goto out_unlock; + + do_for_each_ftrace_rec(pg, rec) { if (ftrace_match_module_record(rec, mod, search, search_len, type)) { @@ -1854,6 +1860,7 @@ static int ftrace_match_module_records(char *buff, char *mod, int enable) ftrace_filtered = 1; } while_for_each_ftrace_rec(); + out_unlock: mutex_unlock(&ftrace_lock); return found; @@ -2008,10 +2015,11 @@ register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, return -EINVAL; mutex_lock(&ftrace_lock); - do_for_each_ftrace_rec(pg, rec) { - if (rec->flags & FTRACE_FL_FAILED) - continue; + if (unlikely(ftrace_disabled)) + goto out_unlock; + + do_for_each_ftrace_rec(pg, rec) { if (!ftrace_match_record(rec, search, len, type)) continue; @@ -2218,6 +2226,10 @@ ftrace_regex_write(struct file *file, const char __user *ubuf, mutex_lock(&ftrace_regex_lock); + ret = -ENODEV; + if (unlikely(ftrace_disabled)) + goto out_unlock; + if (file->f_mode & FMODE_READ) { struct seq_file *m = file->private_data; iter = m->private; @@ -2545,9 +2557,6 @@ ftrace_set_func(unsigned long *array, int *idx, char *buffer) bool exists; int i; - if (ftrace_disabled) - return -ENODEV; - /* decode regex */ type = filter_parse_regex(buffer, strlen(buffer), &search, ¬); if (!not && *idx >= FTRACE_GRAPH_MAX_FUNCS) @@ -2556,9 +2565,15 @@ ftrace_set_func(unsigned long *array, int *idx, char *buffer) search_len = strlen(search); mutex_lock(&ftrace_lock); + + if (unlikely(ftrace_disabled)) { + mutex_unlock(&ftrace_lock); + return -ENODEV; + } + do_for_each_ftrace_rec(pg, rec) { - if (rec->flags & (FTRACE_FL_FAILED | FTRACE_FL_FREE)) + if (rec->flags & FTRACE_FL_FREE) continue; if (ftrace_match_record(rec, search, search_len, type)) { @@ -2700,10 +2715,11 @@ void ftrace_release_mod(struct module *mod) struct dyn_ftrace *rec; struct ftrace_page *pg; + mutex_lock(&ftrace_lock); + if (ftrace_disabled) - return; + goto out_unlock; - mutex_lock(&ftrace_lock); do_for_each_ftrace_rec(pg, rec) { if (within_module_core(rec->ip, mod)) { /* @@ -2714,6 +2730,7 @@ void ftrace_release_mod(struct module *mod) ftrace_free_rec(rec); } } while_for_each_ftrace_rec(); + out_unlock: mutex_unlock(&ftrace_lock); } @@ -3108,16 +3125,17 @@ void ftrace_kill(void) */ int register_ftrace_function(struct ftrace_ops *ops) { - int ret; - - if (unlikely(ftrace_disabled)) - return -1; + int ret = -1; mutex_lock(&ftrace_lock); + if (unlikely(ftrace_disabled)) + goto out_unlock; + ret = __register_ftrace_function(ops); ftrace_startup(0); + out_unlock: mutex_unlock(&ftrace_lock); return ret; } @@ -3145,14 +3163,14 @@ ftrace_enable_sysctl(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - int ret; - - if (unlikely(ftrace_disabled)) - return -ENODEV; + int ret = -ENODEV; mutex_lock(&ftrace_lock); - ret = proc_dointvec(table, write, buffer, lenp, ppos); + if (unlikely(ftrace_disabled)) + goto out; + + ret = proc_dointvec(table, write, buffer, lenp, ppos); if (ret || !write || (last_ftrace_enabled == !!ftrace_enabled)) goto out; -- cgit v1.2.3-70-g09d2 From d2c8c3eafbf715306ec891e7ca52d3d999acbe31 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 25 Apr 2011 14:32:42 -0400 Subject: ftrace: Remove FTRACE_FL_CONVERTED flag Since we disable all function tracer processing if we detect that a modification of a instruction had failed, we do not need to track that the record has failed. No more ftrace processing is allowed, and the FTRACE_FL_CONVERTED flag is pointless. The FTRACE_FL_CONVERTED flag was used to denote records that were successfully converted from mcount calls into nops. But if a single record fails, all of ftrace is disabled. Signed-off-by: Steven Rostedt --- include/linux/ftrace.h | 1 - kernel/trace/ftrace.c | 12 ++++-------- 2 files changed, 4 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 2a195ffd426..32047449b30 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -150,7 +150,6 @@ enum { FTRACE_FL_FILTER = (1 << 1), FTRACE_FL_ENABLED = (1 << 2), FTRACE_FL_NOTRACE = (1 << 3), - FTRACE_FL_CONVERTED = (1 << 4), }; struct dyn_ftrace { diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index eb19fae2c54..9abaaf46f21 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1087,12 +1087,8 @@ static void ftrace_replace_code(int enable) return; do_for_each_ftrace_rec(pg, rec) { - /* - * Skip over free records, records that have - * failed and not converted. - */ - if (rec->flags & FTRACE_FL_FREE || - !(rec->flags & FTRACE_FL_CONVERTED)) + /* Skip over free records */ + if (rec->flags & FTRACE_FL_FREE) continue; failed = __ftrace_replace_code(rec, enable); @@ -1280,10 +1276,10 @@ static int ftrace_update_code(struct module *mod) */ if (!ftrace_code_disable(mod, p)) { ftrace_free_rec(p); - continue; + /* Game over */ + break; } - p->flags |= FTRACE_FL_CONVERTED; ftrace_update_cnt++; /* -- cgit v1.2.3-70-g09d2 From e2c85d8e3974c9041ad7b080846b28d2243e771b Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Tue, 3 May 2011 15:15:55 -0400 Subject: drm/radeon/kms: add some new pci ids Signed-off-by: Alex Deucher Cc: stable@kernel.org Signed-off-by: Dave Airlie --- include/drm/drm_pciids.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/drm/drm_pciids.h b/include/drm/drm_pciids.h index 816e30cbd96..f04b2a3b0f4 100644 --- a/include/drm/drm_pciids.h +++ b/include/drm/drm_pciids.h @@ -155,6 +155,7 @@ {0x1002, 0x6719, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAYMAN|RADEON_NEW_MEMMAP}, \ {0x1002, 0x671c, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAYMAN|RADEON_NEW_MEMMAP}, \ {0x1002, 0x671d, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAYMAN|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x671f, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAYMAN|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6720, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BARTS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6721, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BARTS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6722, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BARTS|RADEON_NEW_MEMMAP}, \ @@ -167,6 +168,7 @@ {0x1002, 0x6729, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BARTS|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6738, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BARTS|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6739, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BARTS|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x673e, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BARTS|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6740, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6741, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6742, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ @@ -199,6 +201,7 @@ {0x1002, 0x688D, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CYPRESS|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6898, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CYPRESS|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6899, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CYPRESS|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x689b, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CYPRESS|RADEON_NEW_MEMMAP}, \ {0x1002, 0x689c, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_HEMLOCK|RADEON_NEW_MEMMAP}, \ {0x1002, 0x689d, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_HEMLOCK|RADEON_NEW_MEMMAP}, \ {0x1002, 0x689e, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CYPRESS|RADEON_NEW_MEMMAP}, \ @@ -209,7 +212,9 @@ {0x1002, 0x68b0, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_JUNIPER|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x68b8, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_JUNIPER|RADEON_NEW_MEMMAP}, \ {0x1002, 0x68b9, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_JUNIPER|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x68ba, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_JUNIPER|RADEON_NEW_MEMMAP}, \ {0x1002, 0x68be, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_JUNIPER|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x68bf, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_JUNIPER|RADEON_NEW_MEMMAP}, \ {0x1002, 0x68c0, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_REDWOOD|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x68c1, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_REDWOOD|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x68c7, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_REDWOOD|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ -- cgit v1.2.3-70-g09d2 From 8aeb96f80232e9a701b5c4715504f4c9173978bd Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Tue, 3 May 2011 19:28:02 -0400 Subject: drm/radeon/kms: fix gart setup on fusion parts (v2) Out of the entire GART/VM subsystem, the hw designers changed the location of 3 regs. v2: airlied: add parameter for userspace to work from. Signed-off-by: Alex Deucher Signed-off-by: Jerome Glisse Cc: stable@kernel.org Signed-off-by: Dave Airlie --- drivers/gpu/drm/radeon/evergreen.c | 17 +++++++++-------- drivers/gpu/drm/radeon/evergreend.h | 5 +++++ drivers/gpu/drm/radeon/radeon_kms.c | 3 +++ include/drm/radeon_drm.h | 1 + 4 files changed, 18 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c index e9bc135d918..c20eac3379e 100644 --- a/drivers/gpu/drm/radeon/evergreen.c +++ b/drivers/gpu/drm/radeon/evergreen.c @@ -862,9 +862,15 @@ int evergreen_pcie_gart_enable(struct radeon_device *rdev) SYSTEM_ACCESS_MODE_NOT_IN_SYS | SYSTEM_APERTURE_UNMAPPED_ACCESS_PASS_THRU | EFFECTIVE_L1_TLB_SIZE(5) | EFFECTIVE_L1_QUEUE_SIZE(5); - WREG32(MC_VM_MD_L1_TLB0_CNTL, tmp); - WREG32(MC_VM_MD_L1_TLB1_CNTL, tmp); - WREG32(MC_VM_MD_L1_TLB2_CNTL, tmp); + if (rdev->flags & RADEON_IS_IGP) { + WREG32(FUS_MC_VM_MD_L1_TLB0_CNTL, tmp); + WREG32(FUS_MC_VM_MD_L1_TLB1_CNTL, tmp); + WREG32(FUS_MC_VM_MD_L1_TLB2_CNTL, tmp); + } else { + WREG32(MC_VM_MD_L1_TLB0_CNTL, tmp); + WREG32(MC_VM_MD_L1_TLB1_CNTL, tmp); + WREG32(MC_VM_MD_L1_TLB2_CNTL, tmp); + } WREG32(MC_VM_MB_L1_TLB0_CNTL, tmp); WREG32(MC_VM_MB_L1_TLB1_CNTL, tmp); WREG32(MC_VM_MB_L1_TLB2_CNTL, tmp); @@ -2923,11 +2929,6 @@ static int evergreen_startup(struct radeon_device *rdev) rdev->asic->copy = NULL; dev_warn(rdev->dev, "failed blitter (%d) falling back to memcpy\n", r); } - /* XXX: ontario has problems blitting to gart at the moment */ - if (rdev->family == CHIP_PALM) { - rdev->asic->copy = NULL; - radeon_ttm_set_active_vram_size(rdev, rdev->mc.visible_vram_size); - } /* allocate wb buffer */ r = radeon_wb_init(rdev); diff --git a/drivers/gpu/drm/radeon/evergreend.h b/drivers/gpu/drm/radeon/evergreend.h index 9aaa3f0c937..94533849927 100644 --- a/drivers/gpu/drm/radeon/evergreend.h +++ b/drivers/gpu/drm/radeon/evergreend.h @@ -221,6 +221,11 @@ #define MC_VM_MD_L1_TLB0_CNTL 0x2654 #define MC_VM_MD_L1_TLB1_CNTL 0x2658 #define MC_VM_MD_L1_TLB2_CNTL 0x265C + +#define FUS_MC_VM_MD_L1_TLB0_CNTL 0x265C +#define FUS_MC_VM_MD_L1_TLB1_CNTL 0x2660 +#define FUS_MC_VM_MD_L1_TLB2_CNTL 0x2664 + #define MC_VM_SYSTEM_APERTURE_DEFAULT_ADDR 0x203C #define MC_VM_SYSTEM_APERTURE_HIGH_ADDR 0x2038 #define MC_VM_SYSTEM_APERTURE_LOW_ADDR 0x2034 diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c index 871df0376b1..bd58af65858 100644 --- a/drivers/gpu/drm/radeon/radeon_kms.c +++ b/drivers/gpu/drm/radeon/radeon_kms.c @@ -234,6 +234,9 @@ int radeon_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) return -EINVAL; } break; + case RADEON_INFO_FUSION_GART_WORKING: + value = 1; + break; default: DRM_DEBUG_KMS("Invalid request %d\n", info->request); return -EINVAL; diff --git a/include/drm/radeon_drm.h b/include/drm/radeon_drm.h index 7aa5dddb209..787f7b6fd62 100644 --- a/include/drm/radeon_drm.h +++ b/include/drm/radeon_drm.h @@ -910,6 +910,7 @@ struct drm_radeon_cs { #define RADEON_INFO_CLOCK_CRYSTAL_FREQ 0x09 /* clock crystal frequency */ #define RADEON_INFO_NUM_BACKENDS 0x0a /* DB/backends for r600+ - need for OQ */ #define RADEON_INFO_NUM_TILE_PIPES 0x0b /* tile pipes for r600+ */ +#define RADEON_INFO_FUSION_GART_WORKING 0x0c /* fusion writes to GTT were broken before this */ struct drm_radeon_info { uint32_t request; -- cgit v1.2.3-70-g09d2 From e7e7ee2eab2080248084d71fe0a115ab745eb2aa Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 4 May 2011 08:42:29 +0200 Subject: perf events: Clean up definitions and initializers, update copyrights Fix a few inconsistent style bits that were added over the past few months. Cc: Peter Zijlstra Link: http://lkml.kernel.org/n/tip-yv4hwf9yhnzoada8pcpb3a97@git.kernel.org Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 96 +++++++++++++++++++++------------------------- kernel/events/core.c | 40 +++++++++---------- 2 files changed, 64 insertions(+), 72 deletions(-) (limited to 'include') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 9eec53d9737..207c16976a1 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -2,8 +2,8 @@ * Performance events: * * Copyright (C) 2008-2009, Thomas Gleixner - * Copyright (C) 2008-2009, Red Hat, Inc., Ingo Molnar - * Copyright (C) 2008-2009, Red Hat, Inc., Peter Zijlstra + * Copyright (C) 2008-2011, Red Hat, Inc., Ingo Molnar + * Copyright (C) 2008-2011, Red Hat, Inc., Peter Zijlstra * * Data type definitions, declarations, prototypes. * @@ -468,9 +468,9 @@ enum perf_callchain_context { PERF_CONTEXT_MAX = (__u64)-4095, }; -#define PERF_FLAG_FD_NO_GROUP (1U << 0) -#define PERF_FLAG_FD_OUTPUT (1U << 1) -#define PERF_FLAG_PID_CGROUP (1U << 2) /* pid=cgroup id, per-cpu mode only */ +#define PERF_FLAG_FD_NO_GROUP (1U << 0) +#define PERF_FLAG_FD_OUTPUT (1U << 1) +#define PERF_FLAG_PID_CGROUP (1U << 2) /* pid=cgroup id, per-cpu mode only */ #ifdef __KERNEL__ /* @@ -484,9 +484,9 @@ enum perf_callchain_context { #endif struct perf_guest_info_callbacks { - int (*is_in_guest) (void); - int (*is_user_mode) (void); - unsigned long (*get_guest_ip) (void); + int (*is_in_guest)(void); + int (*is_user_mode)(void); + unsigned long (*get_guest_ip)(void); }; #ifdef CONFIG_HAVE_HW_BREAKPOINT @@ -652,19 +652,19 @@ struct pmu { * Start the transaction, after this ->add() doesn't need to * do schedulability tests. */ - void (*start_txn) (struct pmu *pmu); /* optional */ + void (*start_txn) (struct pmu *pmu); /* optional */ /* * If ->start_txn() disabled the ->add() schedulability test * then ->commit_txn() is required to perform one. On success * the transaction is closed. On error the transaction is kept * open until ->cancel_txn() is called. */ - int (*commit_txn) (struct pmu *pmu); /* optional */ + int (*commit_txn) (struct pmu *pmu); /* optional */ /* * Will cancel the transaction, assumes ->del() is called * for each successful ->add() during the transaction. */ - void (*cancel_txn) (struct pmu *pmu); /* optional */ + void (*cancel_txn) (struct pmu *pmu); /* optional */ }; /** @@ -712,15 +712,15 @@ typedef void (*perf_overflow_handler_t)(struct perf_event *, int, struct pt_regs *regs); enum perf_group_flag { - PERF_GROUP_SOFTWARE = 0x1, + PERF_GROUP_SOFTWARE = 0x1, }; -#define SWEVENT_HLIST_BITS 8 -#define SWEVENT_HLIST_SIZE (1 << SWEVENT_HLIST_BITS) +#define SWEVENT_HLIST_BITS 8 +#define SWEVENT_HLIST_SIZE (1 << SWEVENT_HLIST_BITS) struct swevent_hlist { - struct hlist_head heads[SWEVENT_HLIST_SIZE]; - struct rcu_head rcu_head; + struct hlist_head heads[SWEVENT_HLIST_SIZE]; + struct rcu_head rcu_head; }; #define PERF_ATTACH_CONTEXT 0x01 @@ -733,13 +733,13 @@ struct swevent_hlist { * This is a per-cpu dynamically allocated data structure. */ struct perf_cgroup_info { - u64 time; - u64 timestamp; + u64 time; + u64 timestamp; }; struct perf_cgroup { - struct cgroup_subsys_state css; - struct perf_cgroup_info *info; /* timing info, one per cpu */ + struct cgroup_subsys_state css; + struct perf_cgroup_info *info; /* timing info, one per cpu */ }; #endif @@ -923,7 +923,7 @@ struct perf_event_context { /* * Number of contexts where an event can trigger: - * task, softirq, hardirq, nmi. + * task, softirq, hardirq, nmi. */ #define PERF_NR_CONTEXTS 4 @@ -1001,8 +1001,7 @@ struct perf_sample_data { struct perf_raw_record *raw; }; -static inline -void perf_sample_data_init(struct perf_sample_data *data, u64 addr) +static inline void perf_sample_data_init(struct perf_sample_data *data, u64 addr) { data->addr = addr; data->raw = NULL; @@ -1039,8 +1038,7 @@ extern struct jump_label_key perf_swevent_enabled[PERF_COUNT_SW_MAX]; extern void __perf_sw_event(u32, u64, int, struct pt_regs *, u64); #ifndef perf_arch_fetch_caller_regs -static inline void -perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip) { } +static inline void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip) { } #endif /* @@ -1080,8 +1078,7 @@ static inline void perf_event_task_sched_in(struct task_struct *task) __perf_event_task_sched_in(task); } -static inline -void perf_event_task_sched_out(struct task_struct *task, struct task_struct *next) +static inline void perf_event_task_sched_out(struct task_struct *task, struct task_struct *next) { perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 1, NULL, 0); @@ -1099,14 +1096,10 @@ extern void perf_event_fork(struct task_struct *tsk); /* Callchains */ DECLARE_PER_CPU(struct perf_callchain_entry, perf_callchain_entry); -extern void perf_callchain_user(struct perf_callchain_entry *entry, - struct pt_regs *regs); -extern void perf_callchain_kernel(struct perf_callchain_entry *entry, - struct pt_regs *regs); - +extern void perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs); +extern void perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs); -static inline void -perf_callchain_store(struct perf_callchain_entry *entry, u64 ip) +static inline void perf_callchain_store(struct perf_callchain_entry *entry, u64 ip) { if (entry->nr < PERF_MAX_STACK_DEPTH) entry->ip[entry->nr++] = ip; @@ -1142,9 +1135,9 @@ extern void perf_tp_event(u64 addr, u64 count, void *record, extern void perf_bp_event(struct perf_event *event, void *data); #ifndef perf_misc_flags -#define perf_misc_flags(regs) (user_mode(regs) ? PERF_RECORD_MISC_USER : \ - PERF_RECORD_MISC_KERNEL) -#define perf_instruction_pointer(regs) instruction_pointer(regs) +# define perf_misc_flags(regs) \ + (user_mode(regs) ? PERF_RECORD_MISC_USER : PERF_RECORD_MISC_KERNEL) +# define perf_instruction_pointer(regs) instruction_pointer(regs) #endif extern int perf_output_begin(struct perf_output_handle *handle, @@ -1179,9 +1172,9 @@ static inline void perf_bp_event(struct perf_event *event, void *data) { } static inline int perf_register_guest_info_callbacks -(struct perf_guest_info_callbacks *callbacks) { return 0; } +(struct perf_guest_info_callbacks *callbacks) { return 0; } static inline int perf_unregister_guest_info_callbacks -(struct perf_guest_info_callbacks *callbacks) { return 0; } +(struct perf_guest_info_callbacks *callbacks) { return 0; } static inline void perf_event_mmap(struct vm_area_struct *vma) { } static inline void perf_event_comm(struct task_struct *tsk) { } @@ -1194,23 +1187,22 @@ static inline void perf_event_disable(struct perf_event *event) { } static inline void perf_event_task_tick(void) { } #endif -#define perf_output_put(handle, x) \ - perf_output_copy((handle), &(x), sizeof(x)) +#define perf_output_put(handle, x) perf_output_copy((handle), &(x), sizeof(x)) /* * This has to have a higher priority than migration_notifier in sched.c. */ -#define perf_cpu_notifier(fn) \ -do { \ - static struct notifier_block fn##_nb __cpuinitdata = \ - { .notifier_call = fn, .priority = CPU_PRI_PERF }; \ - fn(&fn##_nb, (unsigned long)CPU_UP_PREPARE, \ - (void *)(unsigned long)smp_processor_id()); \ - fn(&fn##_nb, (unsigned long)CPU_STARTING, \ - (void *)(unsigned long)smp_processor_id()); \ - fn(&fn##_nb, (unsigned long)CPU_ONLINE, \ - (void *)(unsigned long)smp_processor_id()); \ - register_cpu_notifier(&fn##_nb); \ +#define perf_cpu_notifier(fn) \ +do { \ + static struct notifier_block fn##_nb __cpuinitdata = \ + { .notifier_call = fn, .priority = CPU_PRI_PERF }; \ + fn(&fn##_nb, (unsigned long)CPU_UP_PREPARE, \ + (void *)(unsigned long)smp_processor_id()); \ + fn(&fn##_nb, (unsigned long)CPU_STARTING, \ + (void *)(unsigned long)smp_processor_id()); \ + fn(&fn##_nb, (unsigned long)CPU_ONLINE, \ + (void *)(unsigned long)smp_processor_id()); \ + register_cpu_notifier(&fn##_nb); \ } while (0) #endif /* __KERNEL__ */ diff --git a/kernel/events/core.c b/kernel/events/core.c index 440bc485bbf..0fc34a370ba 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -2,8 +2,8 @@ * Performance events core code: * * Copyright (C) 2008 Thomas Gleixner - * Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar - * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra + * Copyright (C) 2008-2011 Red Hat, Inc., Ingo Molnar + * Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra * Copyright © 2009 Paul Mackerras, IBM Corp. * * For licensing details see kernel-base/COPYING @@ -39,10 +39,10 @@ #include struct remote_function_call { - struct task_struct *p; - int (*func)(void *info); - void *info; - int ret; + struct task_struct *p; + int (*func)(void *info); + void *info; + int ret; }; static void remote_function(void *data) @@ -76,10 +76,10 @@ static int task_function_call(struct task_struct *p, int (*func) (void *info), void *info) { struct remote_function_call data = { - .p = p, - .func = func, - .info = info, - .ret = -ESRCH, /* No such (running) process */ + .p = p, + .func = func, + .info = info, + .ret = -ESRCH, /* No such (running) process */ }; if (task_curr(p)) @@ -100,10 +100,10 @@ task_function_call(struct task_struct *p, int (*func) (void *info), void *info) static int cpu_function_call(int cpu, int (*func) (void *info), void *info) { struct remote_function_call data = { - .p = NULL, - .func = func, - .info = info, - .ret = -ENXIO, /* No such CPU */ + .p = NULL, + .func = func, + .info = info, + .ret = -ENXIO, /* No such CPU */ }; smp_call_function_single(cpu, remote_function, &data, 1); @@ -7445,11 +7445,11 @@ static void perf_cgroup_exit(struct cgroup_subsys *ss, struct cgroup *cgrp, } struct cgroup_subsys perf_subsys = { - .name = "perf_event", - .subsys_id = perf_subsys_id, - .create = perf_cgroup_create, - .destroy = perf_cgroup_destroy, - .exit = perf_cgroup_exit, - .attach = perf_cgroup_attach, + .name = "perf_event", + .subsys_id = perf_subsys_id, + .create = perf_cgroup_create, + .destroy = perf_cgroup_destroy, + .exit = perf_cgroup_exit, + .attach = perf_cgroup_attach, }; #endif /* CONFIG_CGROUP_PERF */ -- cgit v1.2.3-70-g09d2 From 2d06d8c49afdcc9bb35a85039fa50f0fe35bd40e Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 27 Mar 2011 15:04:46 +0200 Subject: [CPUFREQ] use dynamic debug instead of custom infrastructure With dynamic debug having gained the capability to report debug messages also during the boot process, it offers a far superior interface for debug messages than the custom cpufreq infrastructure. As a first step, remove the old cpufreq_debug_printk() function and replace it with a call to the generic pr_debug() function. How can dynamic debug be used on cpufreq? You need a kernel which has CONFIG_DYNAMIC_DEBUG enabled. To enabled debugging during runtime, mount debugfs and $ echo -n 'module cpufreq +p' > /sys/kernel/debug/dynamic_debug/control for debugging the complete "cpufreq" module. To achieve the same goal during boot, append ddebug_query="module cpufreq +p" as a boot parameter to the kernel of your choice. For more detailled instructions, please see Documentation/dynamic-debug-howto.txt Signed-off-by: Dominik Brodowski Signed-off-by: Dave Jones --- arch/arm/mach-davinci/cpufreq.c | 4 +- arch/blackfin/mach-common/dpmc.c | 3 - arch/ia64/kernel/cpufreq/acpi-cpufreq.c | 44 +++--- arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c | 45 +++--- arch/x86/kernel/cpu/cpufreq/cpufreq-nforce2.c | 6 +- arch/x86/kernel/cpu/cpufreq/gx-suspmod.c | 21 ++- arch/x86/kernel/cpu/cpufreq/longhaul.c | 11 +- arch/x86/kernel/cpu/cpufreq/longrun.c | 17 +-- arch/x86/kernel/cpu/cpufreq/p4-clockmod.c | 10 +- arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c | 47 +++--- arch/x86/kernel/cpu/cpufreq/powernow-k7.c | 33 ++--- arch/x86/kernel/cpu/cpufreq/powernow-k8.c | 100 ++++++------- arch/x86/kernel/cpu/cpufreq/powernow-k8.h | 2 - arch/x86/kernel/cpu/cpufreq/sc520_freq.c | 6 +- arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c | 23 ++- arch/x86/kernel/cpu/cpufreq/speedstep-ich.c | 28 ++-- arch/x86/kernel/cpu/cpufreq/speedstep-lib.c | 43 +++--- arch/x86/kernel/cpu/cpufreq/speedstep-smi.c | 41 +++--- drivers/acpi/processor_perflib.c | 6 +- drivers/cpufreq/Kconfig | 13 -- drivers/cpufreq/cpufreq.c | 180 +++++------------------ drivers/cpufreq/cpufreq_performance.c | 5 +- drivers/cpufreq/cpufreq_powersave.c | 5 +- drivers/cpufreq/cpufreq_userspace.c | 13 +- drivers/cpufreq/freq_table.c | 19 +-- include/linux/cpufreq.h | 19 --- 26 files changed, 270 insertions(+), 474 deletions(-) (limited to 'include') diff --git a/arch/arm/mach-davinci/cpufreq.c b/arch/arm/mach-davinci/cpufreq.c index 0a95be1512b..41669ecc1f9 100644 --- a/arch/arm/mach-davinci/cpufreq.c +++ b/arch/arm/mach-davinci/cpufreq.c @@ -94,9 +94,7 @@ static int davinci_target(struct cpufreq_policy *policy, if (freqs.old == freqs.new) return ret; - cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, - dev_driver_string(cpufreq.dev), - "transition: %u --> %u\n", freqs.old, freqs.new); + dev_dbg(&cpufreq.dev, "transition: %u --> %u\n", freqs.old, freqs.new); ret = cpufreq_frequency_table_target(policy, pdata->freq_table, freqs.new, relation, &idx); diff --git a/arch/blackfin/mach-common/dpmc.c b/arch/blackfin/mach-common/dpmc.c index 382099fd556..5e4112e518a 100644 --- a/arch/blackfin/mach-common/dpmc.c +++ b/arch/blackfin/mach-common/dpmc.c @@ -19,9 +19,6 @@ #define DRIVER_NAME "bfin dpmc" -#define dprintk(msg...) \ - cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, DRIVER_NAME, msg) - struct bfin_dpmc_platform_data *pdata; /** diff --git a/arch/ia64/kernel/cpufreq/acpi-cpufreq.c b/arch/ia64/kernel/cpufreq/acpi-cpufreq.c index 22f61526a8e..f09b174244d 100644 --- a/arch/ia64/kernel/cpufreq/acpi-cpufreq.c +++ b/arch/ia64/kernel/cpufreq/acpi-cpufreq.c @@ -23,8 +23,6 @@ #include #include -#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, "acpi-cpufreq", msg) - MODULE_AUTHOR("Venkatesh Pallipadi"); MODULE_DESCRIPTION("ACPI Processor P-States Driver"); MODULE_LICENSE("GPL"); @@ -47,12 +45,12 @@ processor_set_pstate ( { s64 retval; - dprintk("processor_set_pstate\n"); + pr_debug("processor_set_pstate\n"); retval = ia64_pal_set_pstate((u64)value); if (retval) { - dprintk("Failed to set freq to 0x%x, with error 0x%lx\n", + pr_debug("Failed to set freq to 0x%x, with error 0x%lx\n", value, retval); return -ENODEV; } @@ -67,14 +65,14 @@ processor_get_pstate ( u64 pstate_index = 0; s64 retval; - dprintk("processor_get_pstate\n"); + pr_debug("processor_get_pstate\n"); retval = ia64_pal_get_pstate(&pstate_index, PAL_GET_PSTATE_TYPE_INSTANT); *value = (u32) pstate_index; if (retval) - dprintk("Failed to get current freq with " + pr_debug("Failed to get current freq with " "error 0x%lx, idx 0x%x\n", retval, *value); return (int)retval; @@ -90,7 +88,7 @@ extract_clock ( { unsigned long i; - dprintk("extract_clock\n"); + pr_debug("extract_clock\n"); for (i = 0; i < data->acpi_data.state_count; i++) { if (value == data->acpi_data.states[i].status) @@ -110,7 +108,7 @@ processor_get_freq ( cpumask_t saved_mask; unsigned long clock_freq; - dprintk("processor_get_freq\n"); + pr_debug("processor_get_freq\n"); saved_mask = current->cpus_allowed; set_cpus_allowed_ptr(current, cpumask_of(cpu)); @@ -148,7 +146,7 @@ processor_set_freq ( cpumask_t saved_mask; int retval; - dprintk("processor_set_freq\n"); + pr_debug("processor_set_freq\n"); saved_mask = current->cpus_allowed; set_cpus_allowed_ptr(current, cpumask_of(cpu)); @@ -159,16 +157,16 @@ processor_set_freq ( if (state == data->acpi_data.state) { if (unlikely(data->resume)) { - dprintk("Called after resume, resetting to P%d\n", state); + pr_debug("Called after resume, resetting to P%d\n", state); data->resume = 0; } else { - dprintk("Already at target state (P%d)\n", state); + pr_debug("Already at target state (P%d)\n", state); retval = 0; goto migrate_end; } } - dprintk("Transitioning from P%d to P%d\n", + pr_debug("Transitioning from P%d to P%d\n", data->acpi_data.state, state); /* cpufreq frequency struct */ @@ -186,7 +184,7 @@ processor_set_freq ( value = (u32) data->acpi_data.states[state].control; - dprintk("Transitioning to state: 0x%08x\n", value); + pr_debug("Transitioning to state: 0x%08x\n", value); ret = processor_set_pstate(value); if (ret) { @@ -219,7 +217,7 @@ acpi_cpufreq_get ( { struct cpufreq_acpi_io *data = acpi_io_data[cpu]; - dprintk("acpi_cpufreq_get\n"); + pr_debug("acpi_cpufreq_get\n"); return processor_get_freq(data, cpu); } @@ -235,7 +233,7 @@ acpi_cpufreq_target ( unsigned int next_state = 0; unsigned int result = 0; - dprintk("acpi_cpufreq_setpolicy\n"); + pr_debug("acpi_cpufreq_setpolicy\n"); result = cpufreq_frequency_table_target(policy, data->freq_table, target_freq, relation, &next_state); @@ -255,7 +253,7 @@ acpi_cpufreq_verify ( unsigned int result = 0; struct cpufreq_acpi_io *data = acpi_io_data[policy->cpu]; - dprintk("acpi_cpufreq_verify\n"); + pr_debug("acpi_cpufreq_verify\n"); result = cpufreq_frequency_table_verify(policy, data->freq_table); @@ -273,7 +271,7 @@ acpi_cpufreq_cpu_init ( struct cpufreq_acpi_io *data; unsigned int result = 0; - dprintk("acpi_cpufreq_cpu_init\n"); + pr_debug("acpi_cpufreq_cpu_init\n"); data = kzalloc(sizeof(struct cpufreq_acpi_io), GFP_KERNEL); if (!data) @@ -288,7 +286,7 @@ acpi_cpufreq_cpu_init ( /* capability check */ if (data->acpi_data.state_count <= 1) { - dprintk("No P-States\n"); + pr_debug("No P-States\n"); result = -ENODEV; goto err_unreg; } @@ -297,7 +295,7 @@ acpi_cpufreq_cpu_init ( ACPI_ADR_SPACE_FIXED_HARDWARE) || (data->acpi_data.status_register.space_id != ACPI_ADR_SPACE_FIXED_HARDWARE)) { - dprintk("Unsupported address space [%d, %d]\n", + pr_debug("Unsupported address space [%d, %d]\n", (u32) (data->acpi_data.control_register.space_id), (u32) (data->acpi_data.status_register.space_id)); result = -ENODEV; @@ -348,7 +346,7 @@ acpi_cpufreq_cpu_init ( "activated.\n", cpu); for (i = 0; i < data->acpi_data.state_count; i++) - dprintk(" %cP%d: %d MHz, %d mW, %d uS, %d uS, 0x%x 0x%x\n", + pr_debug(" %cP%d: %d MHz, %d mW, %d uS, %d uS, 0x%x 0x%x\n", (i == data->acpi_data.state?'*':' '), i, (u32) data->acpi_data.states[i].core_frequency, (u32) data->acpi_data.states[i].power, @@ -383,7 +381,7 @@ acpi_cpufreq_cpu_exit ( { struct cpufreq_acpi_io *data = acpi_io_data[policy->cpu]; - dprintk("acpi_cpufreq_cpu_exit\n"); + pr_debug("acpi_cpufreq_cpu_exit\n"); if (data) { cpufreq_frequency_table_put_attr(policy->cpu); @@ -418,7 +416,7 @@ static struct cpufreq_driver acpi_cpufreq_driver = { static int __init acpi_cpufreq_init (void) { - dprintk("acpi_cpufreq_init\n"); + pr_debug("acpi_cpufreq_init\n"); return cpufreq_register_driver(&acpi_cpufreq_driver); } @@ -427,7 +425,7 @@ acpi_cpufreq_init (void) static void __exit acpi_cpufreq_exit (void) { - dprintk("acpi_cpufreq_exit\n"); + pr_debug("acpi_cpufreq_exit\n"); cpufreq_unregister_driver(&acpi_cpufreq_driver); return; diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c index a2baafb2fe6..4e04e127438 100644 --- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c +++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c @@ -47,9 +47,6 @@ #include #include "mperf.h" -#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \ - "acpi-cpufreq", msg) - MODULE_AUTHOR("Paul Diefenbaugh, Dominik Brodowski"); MODULE_DESCRIPTION("ACPI Processor P-States Driver"); MODULE_LICENSE("GPL"); @@ -233,7 +230,7 @@ static u32 get_cur_val(const struct cpumask *mask) cmd.mask = mask; drv_read(&cmd); - dprintk("get_cur_val = %u\n", cmd.val); + pr_debug("get_cur_val = %u\n", cmd.val); return cmd.val; } @@ -244,7 +241,7 @@ static unsigned int get_cur_freq_on_cpu(unsigned int cpu) unsigned int freq; unsigned int cached_freq; - dprintk("get_cur_freq_on_cpu (%d)\n", cpu); + pr_debug("get_cur_freq_on_cpu (%d)\n", cpu); if (unlikely(data == NULL || data->acpi_data == NULL || data->freq_table == NULL)) { @@ -261,7 +258,7 @@ static unsigned int get_cur_freq_on_cpu(unsigned int cpu) data->resume = 1; } - dprintk("cur freq = %u\n", freq); + pr_debug("cur freq = %u\n", freq); return freq; } @@ -293,7 +290,7 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy, unsigned int i; int result = 0; - dprintk("acpi_cpufreq_target %d (%d)\n", target_freq, policy->cpu); + pr_debug("acpi_cpufreq_target %d (%d)\n", target_freq, policy->cpu); if (unlikely(data == NULL || data->acpi_data == NULL || data->freq_table == NULL)) { @@ -313,11 +310,11 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy, next_perf_state = data->freq_table[next_state].index; if (perf->state == next_perf_state) { if (unlikely(data->resume)) { - dprintk("Called after resume, resetting to P%d\n", + pr_debug("Called after resume, resetting to P%d\n", next_perf_state); data->resume = 0; } else { - dprintk("Already at target state (P%d)\n", + pr_debug("Already at target state (P%d)\n", next_perf_state); goto out; } @@ -357,7 +354,7 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy, if (acpi_pstate_strict) { if (!check_freqs(cmd.mask, freqs.new, data)) { - dprintk("acpi_cpufreq_target failed (%d)\n", + pr_debug("acpi_cpufreq_target failed (%d)\n", policy->cpu); result = -EAGAIN; goto out; @@ -378,7 +375,7 @@ static int acpi_cpufreq_verify(struct cpufreq_policy *policy) { struct acpi_cpufreq_data *data = per_cpu(acfreq_data, policy->cpu); - dprintk("acpi_cpufreq_verify\n"); + pr_debug("acpi_cpufreq_verify\n"); return cpufreq_frequency_table_verify(policy, data->freq_table); } @@ -433,11 +430,11 @@ static void free_acpi_perf_data(void) static int __init acpi_cpufreq_early_init(void) { unsigned int i; - dprintk("acpi_cpufreq_early_init\n"); + pr_debug("acpi_cpufreq_early_init\n"); acpi_perf_data = alloc_percpu(struct acpi_processor_performance); if (!acpi_perf_data) { - dprintk("Memory allocation error for acpi_perf_data.\n"); + pr_debug("Memory allocation error for acpi_perf_data.\n"); return -ENOMEM; } for_each_possible_cpu(i) { @@ -519,7 +516,7 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy) static int blacklisted; #endif - dprintk("acpi_cpufreq_cpu_init\n"); + pr_debug("acpi_cpufreq_cpu_init\n"); #ifdef CONFIG_SMP if (blacklisted) @@ -566,7 +563,7 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy) /* capability check */ if (perf->state_count <= 1) { - dprintk("No P-States\n"); + pr_debug("No P-States\n"); result = -ENODEV; goto err_unreg; } @@ -578,11 +575,11 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy) switch (perf->control_register.space_id) { case ACPI_ADR_SPACE_SYSTEM_IO: - dprintk("SYSTEM IO addr space\n"); + pr_debug("SYSTEM IO addr space\n"); data->cpu_feature = SYSTEM_IO_CAPABLE; break; case ACPI_ADR_SPACE_FIXED_HARDWARE: - dprintk("HARDWARE addr space\n"); + pr_debug("HARDWARE addr space\n"); if (!check_est_cpu(cpu)) { result = -ENODEV; goto err_unreg; @@ -590,7 +587,7 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy) data->cpu_feature = SYSTEM_INTEL_MSR_CAPABLE; break; default: - dprintk("Unknown addr space %d\n", + pr_debug("Unknown addr space %d\n", (u32) (perf->control_register.space_id)); result = -ENODEV; goto err_unreg; @@ -661,9 +658,9 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy) if (cpu_has(c, X86_FEATURE_APERFMPERF)) acpi_cpufreq_driver.getavg = cpufreq_get_measured_perf; - dprintk("CPU%u - ACPI performance management activated.\n", cpu); + pr_debug("CPU%u - ACPI performance management activated.\n", cpu); for (i = 0; i < perf->state_count; i++) - dprintk(" %cP%d: %d MHz, %d mW, %d uS\n", + pr_debug(" %cP%d: %d MHz, %d mW, %d uS\n", (i == perf->state ? '*' : ' '), i, (u32) perf->states[i].core_frequency, (u32) perf->states[i].power, @@ -694,7 +691,7 @@ static int acpi_cpufreq_cpu_exit(struct cpufreq_policy *policy) { struct acpi_cpufreq_data *data = per_cpu(acfreq_data, policy->cpu); - dprintk("acpi_cpufreq_cpu_exit\n"); + pr_debug("acpi_cpufreq_cpu_exit\n"); if (data) { cpufreq_frequency_table_put_attr(policy->cpu); @@ -712,7 +709,7 @@ static int acpi_cpufreq_resume(struct cpufreq_policy *policy) { struct acpi_cpufreq_data *data = per_cpu(acfreq_data, policy->cpu); - dprintk("acpi_cpufreq_resume\n"); + pr_debug("acpi_cpufreq_resume\n"); data->resume = 1; @@ -743,7 +740,7 @@ static int __init acpi_cpufreq_init(void) if (acpi_disabled) return 0; - dprintk("acpi_cpufreq_init\n"); + pr_debug("acpi_cpufreq_init\n"); ret = acpi_cpufreq_early_init(); if (ret) @@ -758,7 +755,7 @@ static int __init acpi_cpufreq_init(void) static void __exit acpi_cpufreq_exit(void) { - dprintk("acpi_cpufreq_exit\n"); + pr_debug("acpi_cpufreq_exit\n"); cpufreq_unregister_driver(&acpi_cpufreq_driver); diff --git a/arch/x86/kernel/cpu/cpufreq/cpufreq-nforce2.c b/arch/x86/kernel/cpu/cpufreq/cpufreq-nforce2.c index 141abebc451..7bac808804f 100644 --- a/arch/x86/kernel/cpu/cpufreq/cpufreq-nforce2.c +++ b/arch/x86/kernel/cpu/cpufreq/cpufreq-nforce2.c @@ -57,8 +57,6 @@ MODULE_PARM_DESC(min_fsb, "Minimum FSB to use, if not defined: current FSB - 50"); #define PFX "cpufreq-nforce2: " -#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \ - "cpufreq-nforce2", msg) /** * nforce2_calc_fsb - calculate FSB @@ -270,7 +268,7 @@ static int nforce2_target(struct cpufreq_policy *policy, if (freqs.old == freqs.new) return 0; - dprintk("Old CPU frequency %d kHz, new %d kHz\n", + pr_debug("Old CPU frequency %d kHz, new %d kHz\n", freqs.old, freqs.new); cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE); @@ -282,7 +280,7 @@ static int nforce2_target(struct cpufreq_policy *policy, printk(KERN_ERR PFX "Changing FSB to %d failed\n", target_fsb); else - dprintk("Changed FSB successfully to %d\n", + pr_debug("Changed FSB successfully to %d\n", target_fsb); /* Enable IRQs */ diff --git a/arch/x86/kernel/cpu/cpufreq/gx-suspmod.c b/arch/x86/kernel/cpu/cpufreq/gx-suspmod.c index 32974cf8423..ffe1f2c92ed 100644 --- a/arch/x86/kernel/cpu/cpufreq/gx-suspmod.c +++ b/arch/x86/kernel/cpu/cpufreq/gx-suspmod.c @@ -142,9 +142,6 @@ module_param(max_duration, int, 0444); #define POLICY_MIN_DIV 20 -#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \ - "gx-suspmod", msg) - /** * we can detect a core multipiler from dir0_lsb * from GX1 datasheet p.56, @@ -191,7 +188,7 @@ static __init struct pci_dev *gx_detect_chipset(void) /* check if CPU is a MediaGX or a Geode. */ if ((boot_cpu_data.x86_vendor != X86_VENDOR_NSC) && (boot_cpu_data.x86_vendor != X86_VENDOR_CYRIX)) { - dprintk("error: no MediaGX/Geode processor found!\n"); + pr_debug("error: no MediaGX/Geode processor found!\n"); return NULL; } @@ -201,7 +198,7 @@ static __init struct pci_dev *gx_detect_chipset(void) return gx_pci; } - dprintk("error: no supported chipset found!\n"); + pr_debug("error: no supported chipset found!\n"); return NULL; } @@ -305,14 +302,14 @@ static void gx_set_cpuspeed(unsigned int khz) break; default: local_irq_restore(flags); - dprintk("fatal: try to set unknown chipset.\n"); + pr_debug("fatal: try to set unknown chipset.\n"); return; } } else { suscfg = gx_params->pci_suscfg & ~(SUSMOD); gx_params->off_duration = 0; gx_params->on_duration = 0; - dprintk("suspend modulation disabled: cpu runs 100%% speed.\n"); + pr_debug("suspend modulation disabled: cpu runs 100%% speed.\n"); } gx_write_byte(PCI_MODOFF, gx_params->off_duration); @@ -327,9 +324,9 @@ static void gx_set_cpuspeed(unsigned int khz) cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE); - dprintk("suspend modulation w/ duration of ON:%d us, OFF:%d us\n", + pr_debug("suspend modulation w/ duration of ON:%d us, OFF:%d us\n", gx_params->on_duration * 32, gx_params->off_duration * 32); - dprintk("suspend modulation w/ clock speed: %d kHz.\n", freqs.new); + pr_debug("suspend modulation w/ clock speed: %d kHz.\n", freqs.new); } /**************************************************************** @@ -428,8 +425,8 @@ static int cpufreq_gx_cpu_init(struct cpufreq_policy *policy) stock_freq = maxfreq; curfreq = gx_get_cpuspeed(0); - dprintk("cpu max frequency is %d.\n", maxfreq); - dprintk("cpu current frequency is %dkHz.\n", curfreq); + pr_debug("cpu max frequency is %d.\n", maxfreq); + pr_debug("cpu current frequency is %dkHz.\n", curfreq); /* setup basic struct for cpufreq API */ policy->cpu = 0; @@ -475,7 +472,7 @@ static int __init cpufreq_gx_init(void) if (max_duration > 0xff) max_duration = 0xff; - dprintk("geode suspend modulation available.\n"); + pr_debug("geode suspend modulation available.\n"); params = kzalloc(sizeof(struct gxfreq_params), GFP_KERNEL); if (params == NULL) diff --git a/arch/x86/kernel/cpu/cpufreq/longhaul.c b/arch/x86/kernel/cpu/cpufreq/longhaul.c index cf48cdd6907..f47d26e2a13 100644 --- a/arch/x86/kernel/cpu/cpufreq/longhaul.c +++ b/arch/x86/kernel/cpu/cpufreq/longhaul.c @@ -77,9 +77,6 @@ static int scale_voltage; static int disable_acpi_c3; static int revid_errata; -#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \ - "longhaul", msg) - /* Clock ratios multiplied by 10 */ static int mults[32]; @@ -87,7 +84,6 @@ static int eblcr[32]; static int longhaul_version; static struct cpufreq_frequency_table *longhaul_table; -#ifdef CONFIG_CPU_FREQ_DEBUG static char speedbuffer[8]; static char *print_speed(int speed) @@ -106,7 +102,6 @@ static char *print_speed(int speed) return speedbuffer; } -#endif static unsigned int calc_speed(int mult) @@ -275,7 +270,7 @@ static void longhaul_setstate(unsigned int table_index) cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE); - dprintk("Setting to FSB:%dMHz Mult:%d.%dx (%s)\n", + pr_debug("Setting to FSB:%dMHz Mult:%d.%dx (%s)\n", fsb, mult/10, mult%10, print_speed(speed/1000)); retry_loop: preempt_disable(); @@ -460,12 +455,12 @@ static int __cpuinit longhaul_get_ranges(void) break; } - dprintk("MinMult:%d.%dx MaxMult:%d.%dx\n", + pr_debug("MinMult:%d.%dx MaxMult:%d.%dx\n", minmult/10, minmult%10, maxmult/10, maxmult%10); highest_speed = calc_speed(maxmult); lowest_speed = calc_speed(minmult); - dprintk("FSB:%dMHz Lowest speed: %s Highest speed:%s\n", fsb, + pr_debug("FSB:%dMHz Lowest speed: %s Highest speed:%s\n", fsb, print_speed(lowest_speed/1000), print_speed(highest_speed/1000)); diff --git a/arch/x86/kernel/cpu/cpufreq/longrun.c b/arch/x86/kernel/cpu/cpufreq/longrun.c index d9f51367666..34ea359b370 100644 --- a/arch/x86/kernel/cpu/cpufreq/longrun.c +++ b/arch/x86/kernel/cpu/cpufreq/longrun.c @@ -15,9 +15,6 @@ #include #include -#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \ - "longrun", msg) - static struct cpufreq_driver longrun_driver; /** @@ -40,14 +37,14 @@ static void __cpuinit longrun_get_policy(struct cpufreq_policy *policy) u32 msr_lo, msr_hi; rdmsr(MSR_TMTA_LONGRUN_FLAGS, msr_lo, msr_hi); - dprintk("longrun flags are %x - %x\n", msr_lo, msr_hi); + pr_debug("longrun flags are %x - %x\n", msr_lo, msr_hi); if (msr_lo & 0x01) policy->policy = CPUFREQ_POLICY_PERFORMANCE; else policy->policy = CPUFREQ_POLICY_POWERSAVE; rdmsr(MSR_TMTA_LONGRUN_CTRL, msr_lo, msr_hi); - dprintk("longrun ctrl is %x - %x\n", msr_lo, msr_hi); + pr_debug("longrun ctrl is %x - %x\n", msr_lo, msr_hi); msr_lo &= 0x0000007F; msr_hi &= 0x0000007F; @@ -150,7 +147,7 @@ static unsigned int longrun_get(unsigned int cpu) return 0; cpuid(0x80860007, &eax, &ebx, &ecx, &edx); - dprintk("cpuid eax is %u\n", eax); + pr_debug("cpuid eax is %u\n", eax); return eax * 1000; } @@ -196,7 +193,7 @@ static int __cpuinit longrun_determine_freqs(unsigned int *low_freq, rdmsr(MSR_TMTA_LRTI_VOLT_MHZ, msr_lo, msr_hi); *high_freq = msr_lo * 1000; /* to kHz */ - dprintk("longrun table interface told %u - %u kHz\n", + pr_debug("longrun table interface told %u - %u kHz\n", *low_freq, *high_freq); if (*low_freq > *high_freq) @@ -207,7 +204,7 @@ static int __cpuinit longrun_determine_freqs(unsigned int *low_freq, /* set the upper border to the value determined during TSC init */ *high_freq = (cpu_khz / 1000); *high_freq = *high_freq * 1000; - dprintk("high frequency is %u kHz\n", *high_freq); + pr_debug("high frequency is %u kHz\n", *high_freq); /* get current borders */ rdmsr(MSR_TMTA_LONGRUN_CTRL, msr_lo, msr_hi); @@ -233,7 +230,7 @@ static int __cpuinit longrun_determine_freqs(unsigned int *low_freq, /* restore values */ wrmsr(MSR_TMTA_LONGRUN_CTRL, save_lo, save_hi); } - dprintk("percentage is %u %%, freq is %u MHz\n", ecx, eax); + pr_debug("percentage is %u %%, freq is %u MHz\n", ecx, eax); /* performance_pctg = (current_freq - low_freq)/(high_freq - low_freq) * eqals @@ -249,7 +246,7 @@ static int __cpuinit longrun_determine_freqs(unsigned int *low_freq, edx = ((eax - ebx) * 100) / (100 - ecx); *low_freq = edx * 1000; /* back to kHz */ - dprintk("low frequency is %u kHz\n", *low_freq); + pr_debug("low frequency is %u kHz\n", *low_freq); if (*low_freq > *high_freq) *low_freq = *high_freq; diff --git a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c index 52c93648e49..6be3e0760c2 100644 --- a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c +++ b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c @@ -35,8 +35,6 @@ #include "speedstep-lib.h" #define PFX "p4-clockmod: " -#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \ - "p4-clockmod", msg) /* * Duty Cycle (3bits), note DC_DISABLE is not specified in @@ -66,7 +64,7 @@ static int cpufreq_p4_setdc(unsigned int cpu, unsigned int newstate) rdmsr_on_cpu(cpu, MSR_IA32_THERM_STATUS, &l, &h); if (l & 0x01) - dprintk("CPU#%d currently thermal throttled\n", cpu); + pr_debug("CPU#%d currently thermal throttled\n", cpu); if (has_N44_O17_errata[cpu] && (newstate == DC_25PT || newstate == DC_DFLT)) @@ -74,10 +72,10 @@ static int cpufreq_p4_setdc(unsigned int cpu, unsigned int newstate) rdmsr_on_cpu(cpu, MSR_IA32_THERM_CONTROL, &l, &h); if (newstate == DC_DISABLE) { - dprintk("CPU#%d disabling modulation\n", cpu); + pr_debug("CPU#%d disabling modulation\n", cpu); wrmsr_on_cpu(cpu, MSR_IA32_THERM_CONTROL, l & ~(1<<4), h); } else { - dprintk("CPU#%d setting duty cycle to %d%%\n", + pr_debug("CPU#%d setting duty cycle to %d%%\n", cpu, ((125 * newstate) / 10)); /* bits 63 - 5 : reserved * bit 4 : enable/disable @@ -217,7 +215,7 @@ static int cpufreq_p4_cpu_init(struct cpufreq_policy *policy) case 0x0f11: case 0x0f12: has_N44_O17_errata[policy->cpu] = 1; - dprintk("has errata -- disabling low frequencies\n"); + pr_debug("has errata -- disabling low frequencies\n"); } if (speedstep_detect_processor() == SPEEDSTEP_CPU_P4D && diff --git a/arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c index 907c8e637ef..7b0603eb012 100644 --- a/arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c +++ b/arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c @@ -48,9 +48,6 @@ #define BUF_SZ 4 -#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \ - "pcc-cpufreq", msg) - struct pcc_register_resource { u8 descriptor; u16 length; @@ -152,7 +149,7 @@ static unsigned int pcc_get_freq(unsigned int cpu) spin_lock(&pcc_lock); - dprintk("get: get_freq for CPU %d\n", cpu); + pr_debug("get: get_freq for CPU %d\n", cpu); pcc_cpu_data = per_cpu_ptr(pcc_cpu_info, cpu); input_buffer = 0x1; @@ -170,7 +167,7 @@ static unsigned int pcc_get_freq(unsigned int cpu) status = ioread16(&pcch_hdr->status); if (status != CMD_COMPLETE) { - dprintk("get: FAILED: for CPU %d, status is %d\n", + pr_debug("get: FAILED: for CPU %d, status is %d\n", cpu, status); goto cmd_incomplete; } @@ -178,14 +175,14 @@ static unsigned int pcc_get_freq(unsigned int cpu) curr_freq = (((ioread32(&pcch_hdr->nominal) * (output_buffer & 0xff)) / 100) * 1000); - dprintk("get: SUCCESS: (virtual) output_offset for cpu %d is " - "0x%x, contains a value of: 0x%x. Speed is: %d MHz\n", + pr_debug("get: SUCCESS: (virtual) output_offset for cpu %d is " + "0x%p, contains a value of: 0x%x. Speed is: %d MHz\n", cpu, (pcch_virt_addr + pcc_cpu_data->output_offset), output_buffer, curr_freq); freq_limit = (output_buffer >> 8) & 0xff; if (freq_limit != 0xff) { - dprintk("get: frequency for cpu %d is being temporarily" + pr_debug("get: frequency for cpu %d is being temporarily" " capped at %d\n", cpu, curr_freq); } @@ -212,8 +209,8 @@ static int pcc_cpufreq_target(struct cpufreq_policy *policy, cpu = policy->cpu; pcc_cpu_data = per_cpu_ptr(pcc_cpu_info, cpu); - dprintk("target: CPU %d should go to target freq: %d " - "(virtual) input_offset is 0x%x\n", + pr_debug("target: CPU %d should go to target freq: %d " + "(virtual) input_offset is 0x%p\n", cpu, target_freq, (pcch_virt_addr + pcc_cpu_data->input_offset)); @@ -234,14 +231,14 @@ static int pcc_cpufreq_target(struct cpufreq_policy *policy, status = ioread16(&pcch_hdr->status); if (status != CMD_COMPLETE) { - dprintk("target: FAILED for cpu %d, with status: 0x%x\n", + pr_debug("target: FAILED for cpu %d, with status: 0x%x\n", cpu, status); goto cmd_incomplete; } iowrite16(0, &pcch_hdr->status); cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE); - dprintk("target: was SUCCESSFUL for cpu %d\n", cpu); + pr_debug("target: was SUCCESSFUL for cpu %d\n", cpu); spin_unlock(&pcc_lock); return 0; @@ -293,7 +290,7 @@ static int pcc_get_offset(int cpu) memset_io((pcch_virt_addr + pcc_cpu_data->input_offset), 0, BUF_SZ); memset_io((pcch_virt_addr + pcc_cpu_data->output_offset), 0, BUF_SZ); - dprintk("pcc_get_offset: for CPU %d: pcc_cpu_data " + pr_debug("pcc_get_offset: for CPU %d: pcc_cpu_data " "input_offset: 0x%x, pcc_cpu_data output_offset: 0x%x\n", cpu, pcc_cpu_data->input_offset, pcc_cpu_data->output_offset); out_free: @@ -410,7 +407,7 @@ static int __init pcc_cpufreq_probe(void) if (ACPI_SUCCESS(status)) { ret = pcc_cpufreq_do_osc(&osc_handle); if (ret) - dprintk("probe: _OSC evaluation did not succeed\n"); + pr_debug("probe: _OSC evaluation did not succeed\n"); /* Firmware's use of _OSC is optional */ ret = 0; } @@ -433,7 +430,7 @@ static int __init pcc_cpufreq_probe(void) mem_resource = (struct pcc_memory_resource *)member->buffer.pointer; - dprintk("probe: mem_resource descriptor: 0x%x," + pr_debug("probe: mem_resource descriptor: 0x%x," " length: %d, space_id: %d, resource_usage: %d," " type_specific: %d, granularity: 0x%llx," " minimum: 0x%llx, maximum: 0x%llx," @@ -453,13 +450,13 @@ static int __init pcc_cpufreq_probe(void) pcch_virt_addr = ioremap_nocache(mem_resource->minimum, mem_resource->address_length); if (pcch_virt_addr == NULL) { - dprintk("probe: could not map shared mem region\n"); + pr_debug("probe: could not map shared mem region\n"); goto out_free; } pcch_hdr = pcch_virt_addr; - dprintk("probe: PCCH header (virtual) addr: 0x%p\n", pcch_hdr); - dprintk("probe: PCCH header is at physical address: 0x%llx," + pr_debug("probe: PCCH header (virtual) addr: 0x%p\n", pcch_hdr); + pr_debug("probe: PCCH header is at physical address: 0x%llx," " signature: 0x%x, length: %d bytes, major: %d, minor: %d," " supported features: 0x%x, command field: 0x%x," " status field: 0x%x, nominal latency: %d us\n", @@ -469,7 +466,7 @@ static int __init pcc_cpufreq_probe(void) ioread16(&pcch_hdr->command), ioread16(&pcch_hdr->status), ioread32(&pcch_hdr->latency)); - dprintk("probe: min time between commands: %d us," + pr_debug("probe: min time between commands: %d us," " max time between commands: %d us," " nominal CPU frequency: %d MHz," " minimum CPU frequency: %d MHz," @@ -494,7 +491,7 @@ static int __init pcc_cpufreq_probe(void) doorbell.access_width = 64; doorbell.address = reg_resource->address; - dprintk("probe: doorbell: space_id is %d, bit_width is %d, " + pr_debug("probe: doorbell: space_id is %d, bit_width is %d, " "bit_offset is %d, access_width is %d, address is 0x%llx\n", doorbell.space_id, doorbell.bit_width, doorbell.bit_offset, doorbell.access_width, reg_resource->address); @@ -515,7 +512,7 @@ static int __init pcc_cpufreq_probe(void) doorbell_write = member->integer.value; - dprintk("probe: doorbell_preserve: 0x%llx," + pr_debug("probe: doorbell_preserve: 0x%llx," " doorbell_write: 0x%llx\n", doorbell_preserve, doorbell_write); @@ -550,7 +547,7 @@ static int pcc_cpufreq_cpu_init(struct cpufreq_policy *policy) result = pcc_get_offset(cpu); if (result) { - dprintk("init: PCCP evaluation failed\n"); + pr_debug("init: PCCP evaluation failed\n"); goto out; } @@ -561,12 +558,12 @@ static int pcc_cpufreq_cpu_init(struct cpufreq_policy *policy) policy->cur = pcc_get_freq(cpu); if (!policy->cur) { - dprintk("init: Unable to get current CPU frequency\n"); + pr_debug("init: Unable to get current CPU frequency\n"); result = -EINVAL; goto out; } - dprintk("init: policy->max is %d, policy->min is %d\n", + pr_debug("init: policy->max is %d, policy->min is %d\n", policy->max, policy->min); out: return result; @@ -597,7 +594,7 @@ static int __init pcc_cpufreq_init(void) ret = pcc_cpufreq_probe(); if (ret) { - dprintk("pcc_cpufreq_init: PCCH evaluation failed\n"); + pr_debug("pcc_cpufreq_init: PCCH evaluation failed\n"); return ret; } diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k7.c b/arch/x86/kernel/cpu/cpufreq/powernow-k7.c index 4a45fd6e41b..d71d9f37235 100644 --- a/arch/x86/kernel/cpu/cpufreq/powernow-k7.c +++ b/arch/x86/kernel/cpu/cpufreq/powernow-k7.c @@ -68,7 +68,6 @@ union powernow_acpi_control_t { }; #endif -#ifdef CONFIG_CPU_FREQ_DEBUG /* divide by 1000 to get VCore voltage in V. */ static const int mobile_vid_table[32] = { 2000, 1950, 1900, 1850, 1800, 1750, 1700, 1650, @@ -76,7 +75,6 @@ static const int mobile_vid_table[32] = { 1275, 1250, 1225, 1200, 1175, 1150, 1125, 1100, 1075, 1050, 1025, 1000, 975, 950, 925, 0, }; -#endif /* divide by 10 to get FID. */ static const int fid_codes[32] = { @@ -103,9 +101,6 @@ static unsigned int fsb; static unsigned int latency; static char have_a0; -#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \ - "powernow-k7", msg) - static int check_fsb(unsigned int fsbspeed) { int delta; @@ -209,7 +204,7 @@ static int get_ranges(unsigned char *pst) vid = *pst++; powernow_table[j].index |= (vid << 8); /* upper 8 bits */ - dprintk(" FID: 0x%x (%d.%dx [%dMHz]) " + pr_debug(" FID: 0x%x (%d.%dx [%dMHz]) " "VID: 0x%x (%d.%03dV)\n", fid, fid_codes[fid] / 10, fid_codes[fid] % 10, speed/1000, vid, mobile_vid_table[vid]/1000, @@ -367,7 +362,7 @@ static int powernow_acpi_init(void) unsigned int speed, speed_mhz; pc.val = (unsigned long) state->control; - dprintk("acpi: P%d: %d MHz %d mW %d uS control %08x SGTC %d\n", + pr_debug("acpi: P%d: %d MHz %d mW %d uS control %08x SGTC %d\n", i, (u32) state->core_frequency, (u32) state->power, @@ -401,7 +396,7 @@ static int powernow_acpi_init(void) invalidate_entry(i); } - dprintk(" FID: 0x%x (%d.%dx [%dMHz]) " + pr_debug(" FID: 0x%x (%d.%dx [%dMHz]) " "VID: 0x%x (%d.%03dV)\n", fid, fid_codes[fid] / 10, fid_codes[fid] % 10, speed_mhz, vid, mobile_vid_table[vid]/1000, @@ -409,7 +404,7 @@ static int powernow_acpi_init(void) if (state->core_frequency != speed_mhz) { state->core_frequency = speed_mhz; - dprintk(" Corrected ACPI frequency to %d\n", + pr_debug(" Corrected ACPI frequency to %d\n", speed_mhz); } @@ -453,8 +448,8 @@ static int powernow_acpi_init(void) static void print_pst_entry(struct pst_s *pst, unsigned int j) { - dprintk("PST:%d (@%p)\n", j, pst); - dprintk(" cpuid: 0x%x fsb: %d maxFID: 0x%x startvid: 0x%x\n", + pr_debug("PST:%d (@%p)\n", j, pst); + pr_debug(" cpuid: 0x%x fsb: %d maxFID: 0x%x startvid: 0x%x\n", pst->cpuid, pst->fsbspeed, pst->maxfid, pst->startvid); } @@ -474,20 +469,20 @@ static int powernow_decode_bios(int maxfid, int startvid) p = phys_to_virt(i); if (memcmp(p, "AMDK7PNOW!", 10) == 0) { - dprintk("Found PSB header at %p\n", p); + pr_debug("Found PSB header at %p\n", p); psb = (struct psb_s *) p; - dprintk("Table version: 0x%x\n", psb->tableversion); + pr_debug("Table version: 0x%x\n", psb->tableversion); if (psb->tableversion != 0x12) { printk(KERN_INFO PFX "Sorry, only v1.2 tables" " supported right now\n"); return -ENODEV; } - dprintk("Flags: 0x%x\n", psb->flags); + pr_debug("Flags: 0x%x\n", psb->flags); if ((psb->flags & 1) == 0) - dprintk("Mobile voltage regulator\n"); + pr_debug("Mobile voltage regulator\n"); else - dprintk("Desktop voltage regulator\n"); + pr_debug("Desktop voltage regulator\n"); latency = psb->settlingtime; if (latency < 100) { @@ -497,9 +492,9 @@ static int powernow_decode_bios(int maxfid, int startvid) "Correcting.\n", latency); latency = 100; } - dprintk("Settling Time: %d microseconds.\n", + pr_debug("Settling Time: %d microseconds.\n", psb->settlingtime); - dprintk("Has %d PST tables. (Only dumping ones " + pr_debug("Has %d PST tables. (Only dumping ones " "relevant to this CPU).\n", psb->numpst); @@ -650,7 +645,7 @@ static int __cpuinit powernow_cpu_init(struct cpufreq_policy *policy) printk(KERN_WARNING PFX "can not determine bus frequency\n"); return -EINVAL; } - dprintk("FSB: %3dMHz\n", fsb/1000); + pr_debug("FSB: %3dMHz\n", fsb/1000); if (dmi_check_system(powernow_dmi_table) || acpi_force) { printk(KERN_INFO PFX "PSB/PST known to be broken. " diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c index 2368e38327b..83479b6fb9a 100644 --- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c +++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c @@ -139,7 +139,7 @@ static int query_current_values_with_pending_wait(struct powernow_k8_data *data) } do { if (i++ > 10000) { - dprintk("detected change pending stuck\n"); + pr_debug("detected change pending stuck\n"); return 1; } rdmsr(MSR_FIDVID_STATUS, lo, hi); @@ -176,7 +176,7 @@ static void fidvid_msr_init(void) fid = lo & MSR_S_LO_CURRENT_FID; lo = fid | (vid << MSR_C_LO_VID_SHIFT); hi = MSR_C_HI_STP_GNT_BENIGN; - dprintk("cpu%d, init lo 0x%x, hi 0x%x\n", smp_processor_id(), lo, hi); + pr_debug("cpu%d, init lo 0x%x, hi 0x%x\n", smp_processor_id(), lo, hi); wrmsr(MSR_FIDVID_CTL, lo, hi); } @@ -196,7 +196,7 @@ static int write_new_fid(struct powernow_k8_data *data, u32 fid) lo |= (data->currvid << MSR_C_LO_VID_SHIFT); lo |= MSR_C_LO_INIT_FID_VID; - dprintk("writing fid 0x%x, lo 0x%x, hi 0x%x\n", + pr_debug("writing fid 0x%x, lo 0x%x, hi 0x%x\n", fid, lo, data->plllock * PLL_LOCK_CONVERSION); do { @@ -244,7 +244,7 @@ static int write_new_vid(struct powernow_k8_data *data, u32 vid) lo |= (vid << MSR_C_LO_VID_SHIFT); lo |= MSR_C_LO_INIT_FID_VID; - dprintk("writing vid 0x%x, lo 0x%x, hi 0x%x\n", + pr_debug("writing vid 0x%x, lo 0x%x, hi 0x%x\n", vid, lo, STOP_GRANT_5NS); do { @@ -325,7 +325,7 @@ static int transition_fid_vid(struct powernow_k8_data *data, return 1; } - dprintk("transitioned (cpu%d): new fid 0x%x, vid 0x%x\n", + pr_debug("transitioned (cpu%d): new fid 0x%x, vid 0x%x\n", smp_processor_id(), data->currfid, data->currvid); return 0; @@ -339,7 +339,7 @@ static int core_voltage_pre_transition(struct powernow_k8_data *data, u32 savefid = data->currfid; u32 maxvid, lo, rvomult = 1; - dprintk("ph1 (cpu%d): start, currfid 0x%x, currvid 0x%x, " + pr_debug("ph1 (cpu%d): start, currfid 0x%x, currvid 0x%x, " "reqvid 0x%x, rvo 0x%x\n", smp_processor_id(), data->currfid, data->currvid, reqvid, data->rvo); @@ -349,12 +349,12 @@ static int core_voltage_pre_transition(struct powernow_k8_data *data, rvosteps *= rvomult; rdmsr(MSR_FIDVID_STATUS, lo, maxvid); maxvid = 0x1f & (maxvid >> 16); - dprintk("ph1 maxvid=0x%x\n", maxvid); + pr_debug("ph1 maxvid=0x%x\n", maxvid); if (reqvid < maxvid) /* lower numbers are higher voltages */ reqvid = maxvid; while (data->currvid > reqvid) { - dprintk("ph1: curr 0x%x, req vid 0x%x\n", + pr_debug("ph1: curr 0x%x, req vid 0x%x\n", data->currvid, reqvid); if (decrease_vid_code_by_step(data, reqvid, data->vidmvs)) return 1; @@ -365,7 +365,7 @@ static int core_voltage_pre_transition(struct powernow_k8_data *data, if (data->currvid == maxvid) { rvosteps = 0; } else { - dprintk("ph1: changing vid for rvo, req 0x%x\n", + pr_debug("ph1: changing vid for rvo, req 0x%x\n", data->currvid - 1); if (decrease_vid_code_by_step(data, data->currvid-1, 1)) return 1; @@ -382,7 +382,7 @@ static int core_voltage_pre_transition(struct powernow_k8_data *data, return 1; } - dprintk("ph1 complete, currfid 0x%x, currvid 0x%x\n", + pr_debug("ph1 complete, currfid 0x%x, currvid 0x%x\n", data->currfid, data->currvid); return 0; @@ -400,7 +400,7 @@ static int core_frequency_transition(struct powernow_k8_data *data, u32 reqfid) return 0; } - dprintk("ph2 (cpu%d): starting, currfid 0x%x, currvid 0x%x, " + pr_debug("ph2 (cpu%d): starting, currfid 0x%x, currvid 0x%x, " "reqfid 0x%x\n", smp_processor_id(), data->currfid, data->currvid, reqfid); @@ -457,7 +457,7 @@ static int core_frequency_transition(struct powernow_k8_data *data, u32 reqfid) return 1; } - dprintk("ph2 complete, currfid 0x%x, currvid 0x%x\n", + pr_debug("ph2 complete, currfid 0x%x, currvid 0x%x\n", data->currfid, data->currvid); return 0; @@ -470,7 +470,7 @@ static int core_voltage_post_transition(struct powernow_k8_data *data, u32 savefid = data->currfid; u32 savereqvid = reqvid; - dprintk("ph3 (cpu%d): starting, currfid 0x%x, currvid 0x%x\n", + pr_debug("ph3 (cpu%d): starting, currfid 0x%x, currvid 0x%x\n", smp_processor_id(), data->currfid, data->currvid); @@ -498,17 +498,17 @@ static int core_voltage_post_transition(struct powernow_k8_data *data, return 1; if (savereqvid != data->currvid) { - dprintk("ph3 failed, currvid 0x%x\n", data->currvid); + pr_debug("ph3 failed, currvid 0x%x\n", data->currvid); return 1; } if (savefid != data->currfid) { - dprintk("ph3 failed, currfid changed 0x%x\n", + pr_debug("ph3 failed, currfid changed 0x%x\n", data->currfid); return 1; } - dprintk("ph3 complete, currfid 0x%x, currvid 0x%x\n", + pr_debug("ph3 complete, currfid 0x%x, currvid 0x%x\n", data->currfid, data->currvid); return 0; @@ -707,7 +707,7 @@ static int fill_powernow_table(struct powernow_k8_data *data, return -EIO; } - dprintk("cfid 0x%x, cvid 0x%x\n", data->currfid, data->currvid); + pr_debug("cfid 0x%x, cvid 0x%x\n", data->currfid, data->currvid); data->powernow_table = powernow_table; if (cpumask_first(cpu_core_mask(data->cpu)) == data->cpu) print_basics(data); @@ -717,7 +717,7 @@ static int fill_powernow_table(struct powernow_k8_data *data, (pst[j].vid == data->currvid)) return 0; - dprintk("currfid/vid do not match PST, ignoring\n"); + pr_debug("currfid/vid do not match PST, ignoring\n"); return 0; } @@ -739,36 +739,36 @@ static int find_psb_table(struct powernow_k8_data *data) if (memcmp(psb, PSB_ID_STRING, PSB_ID_STRING_LEN) != 0) continue; - dprintk("found PSB header at 0x%p\n", psb); + pr_debug("found PSB header at 0x%p\n", psb); - dprintk("table vers: 0x%x\n", psb->tableversion); + pr_debug("table vers: 0x%x\n", psb->tableversion); if (psb->tableversion != PSB_VERSION_1_4) { printk(KERN_ERR FW_BUG PFX "PSB table is not v1.4\n"); return -ENODEV; } - dprintk("flags: 0x%x\n", psb->flags1); + pr_debug("flags: 0x%x\n", psb->flags1); if (psb->flags1) { printk(KERN_ERR FW_BUG PFX "unknown flags\n"); return -ENODEV; } data->vstable = psb->vstable; - dprintk("voltage stabilization time: %d(*20us)\n", + pr_debug("voltage stabilization time: %d(*20us)\n", data->vstable); - dprintk("flags2: 0x%x\n", psb->flags2); + pr_debug("flags2: 0x%x\n", psb->flags2); data->rvo = psb->flags2 & 3; data->irt = ((psb->flags2) >> 2) & 3; mvs = ((psb->flags2) >> 4) & 3; data->vidmvs = 1 << mvs; data->batps = ((psb->flags2) >> 6) & 3; - dprintk("ramp voltage offset: %d\n", data->rvo); - dprintk("isochronous relief time: %d\n", data->irt); - dprintk("maximum voltage step: %d - 0x%x\n", mvs, data->vidmvs); + pr_debug("ramp voltage offset: %d\n", data->rvo); + pr_debug("isochronous relief time: %d\n", data->irt); + pr_debug("maximum voltage step: %d - 0x%x\n", mvs, data->vidmvs); - dprintk("numpst: 0x%x\n", psb->num_tables); + pr_debug("numpst: 0x%x\n", psb->num_tables); cpst = psb->num_tables; if ((psb->cpuid == 0x00000fc0) || (psb->cpuid == 0x00000fe0)) { @@ -783,13 +783,13 @@ static int find_psb_table(struct powernow_k8_data *data) } data->plllock = psb->plllocktime; - dprintk("plllocktime: 0x%x (units 1us)\n", psb->plllocktime); - dprintk("maxfid: 0x%x\n", psb->maxfid); - dprintk("maxvid: 0x%x\n", psb->maxvid); + pr_debug("plllocktime: 0x%x (units 1us)\n", psb->plllocktime); + pr_debug("maxfid: 0x%x\n", psb->maxfid); + pr_debug("maxvid: 0x%x\n", psb->maxvid); maxvid = psb->maxvid; data->numps = psb->numps; - dprintk("numpstates: 0x%x\n", data->numps); + pr_debug("numpstates: 0x%x\n", data->numps); return fill_powernow_table(data, (struct pst_s *)(psb+1), maxvid); } @@ -834,13 +834,13 @@ static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data) u64 control, status; if (acpi_processor_register_performance(&data->acpi_data, data->cpu)) { - dprintk("register performance failed: bad ACPI data\n"); + pr_debug("register performance failed: bad ACPI data\n"); return -EIO; } /* verify the data contained in the ACPI structures */ if (data->acpi_data.state_count <= 1) { - dprintk("No ACPI P-States\n"); + pr_debug("No ACPI P-States\n"); goto err_out; } @@ -849,7 +849,7 @@ static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data) if ((control != ACPI_ADR_SPACE_FIXED_HARDWARE) || (status != ACPI_ADR_SPACE_FIXED_HARDWARE)) { - dprintk("Invalid control/status registers (%x - %x)\n", + pr_debug("Invalid control/status registers (%llx - %llx)\n", control, status); goto err_out; } @@ -858,7 +858,7 @@ static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data) powernow_table = kmalloc((sizeof(struct cpufreq_frequency_table) * (data->acpi_data.state_count + 1)), GFP_KERNEL); if (!powernow_table) { - dprintk("powernow_table memory alloc failure\n"); + pr_debug("powernow_table memory alloc failure\n"); goto err_out; } @@ -928,7 +928,7 @@ static int fill_powernow_table_pstate(struct powernow_k8_data *data, } rdmsr(MSR_PSTATE_DEF_BASE + index, lo, hi); if (!(hi & HW_PSTATE_VALID_MASK)) { - dprintk("invalid pstate %d, ignoring\n", index); + pr_debug("invalid pstate %d, ignoring\n", index); invalidate_entry(powernow_table, i); continue; } @@ -968,7 +968,7 @@ static int fill_powernow_table_fidvid(struct powernow_k8_data *data, vid = (control >> VID_SHIFT) & VID_MASK; } - dprintk(" %d : fid 0x%x, vid 0x%x\n", i, fid, vid); + pr_debug(" %d : fid 0x%x, vid 0x%x\n", i, fid, vid); index = fid | (vid<<8); powernow_table[i].index = index; @@ -978,7 +978,7 @@ static int fill_powernow_table_fidvid(struct powernow_k8_data *data, /* verify frequency is OK */ if ((freq > (MAX_FREQ * 1000)) || (freq < (MIN_FREQ * 1000))) { - dprintk("invalid freq %u kHz, ignoring\n", freq); + pr_debug("invalid freq %u kHz, ignoring\n", freq); invalidate_entry(powernow_table, i); continue; } @@ -986,7 +986,7 @@ static int fill_powernow_table_fidvid(struct powernow_k8_data *data, /* verify voltage is OK - * BIOSs are using "off" to indicate invalid */ if (vid == VID_OFF) { - dprintk("invalid vid %u, ignoring\n", vid); + pr_debug("invalid vid %u, ignoring\n", vid); invalidate_entry(powernow_table, i); continue; } @@ -1047,7 +1047,7 @@ static int transition_frequency_fidvid(struct powernow_k8_data *data, int res, i; struct cpufreq_freqs freqs; - dprintk("cpu %d transition to index %u\n", smp_processor_id(), index); + pr_debug("cpu %d transition to index %u\n", smp_processor_id(), index); /* fid/vid correctness check for k8 */ /* fid are the lower 8 bits of the index we stored into @@ -1057,18 +1057,18 @@ static int transition_frequency_fidvid(struct powernow_k8_data *data, fid = data->powernow_table[index].index & 0xFF; vid = (data->powernow_table[index].index & 0xFF00) >> 8; - dprintk("table matched fid 0x%x, giving vid 0x%x\n", fid, vid); + pr_debug("table matched fid 0x%x, giving vid 0x%x\n", fid, vid); if (query_current_values_with_pending_wait(data)) return 1; if ((data->currvid == vid) && (data->currfid == fid)) { - dprintk("target matches current values (fid 0x%x, vid 0x%x)\n", + pr_debug("target matches current values (fid 0x%x, vid 0x%x)\n", fid, vid); return 0; } - dprintk("cpu %d, changing to fid 0x%x, vid 0x%x\n", + pr_debug("cpu %d, changing to fid 0x%x, vid 0x%x\n", smp_processor_id(), fid, vid); freqs.old = find_khz_freq_from_fid(data->currfid); freqs.new = find_khz_freq_from_fid(fid); @@ -1096,7 +1096,7 @@ static int transition_frequency_pstate(struct powernow_k8_data *data, int res, i; struct cpufreq_freqs freqs; - dprintk("cpu %d transition to index %u\n", smp_processor_id(), index); + pr_debug("cpu %d transition to index %u\n", smp_processor_id(), index); /* get MSR index for hardware pstate transition */ pstate = index & HW_PSTATE_MASK; @@ -1156,14 +1156,14 @@ static int powernowk8_target(struct cpufreq_policy *pol, goto err_out; } - dprintk("targ: cpu %d, %d kHz, min %d, max %d, relation %d\n", + pr_debug("targ: cpu %d, %d kHz, min %d, max %d, relation %d\n", pol->cpu, targfreq, pol->min, pol->max, relation); if (query_current_values_with_pending_wait(data)) goto err_out; if (cpu_family != CPU_HW_PSTATE) { - dprintk("targ: curr fid 0x%x, vid 0x%x\n", + pr_debug("targ: curr fid 0x%x, vid 0x%x\n", data->currfid, data->currvid); if ((checkvid != data->currvid) || @@ -1319,7 +1319,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol) data->currpstate); else pol->cur = find_khz_freq_from_fid(data->currfid); - dprintk("policy current frequency %d kHz\n", pol->cur); + pr_debug("policy current frequency %d kHz\n", pol->cur); /* min/max the cpu is capable of */ if (cpufreq_frequency_table_cpuinfo(pol, data->powernow_table)) { @@ -1337,10 +1337,10 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol) cpufreq_frequency_table_get_attr(data->powernow_table, pol->cpu); if (cpu_family == CPU_HW_PSTATE) - dprintk("cpu_init done, current pstate 0x%x\n", + pr_debug("cpu_init done, current pstate 0x%x\n", data->currpstate); else - dprintk("cpu_init done, current fid 0x%x, vid 0x%x\n", + pr_debug("cpu_init done, current fid 0x%x, vid 0x%x\n", data->currfid, data->currvid); per_cpu(powernow_data, pol->cpu) = data; @@ -1586,7 +1586,7 @@ static int __cpuinit powernowk8_init(void) /* driver entry point for term */ static void __exit powernowk8_exit(void) { - dprintk("exit\n"); + pr_debug("exit\n"); if (boot_cpu_has(X86_FEATURE_CPB)) { msrs_free(msrs); diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.h b/arch/x86/kernel/cpu/cpufreq/powernow-k8.h index df3529b1c02..3744d26cdc2 100644 --- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.h +++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.h @@ -211,8 +211,6 @@ struct pst_s { u8 vid; }; -#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, "powernow-k8", msg) - static int core_voltage_pre_transition(struct powernow_k8_data *data, u32 reqvid, u32 regfid); static int core_voltage_post_transition(struct powernow_k8_data *data, u32 reqvid); diff --git a/arch/x86/kernel/cpu/cpufreq/sc520_freq.c b/arch/x86/kernel/cpu/cpufreq/sc520_freq.c index 435a996a613..1e205e6b172 100644 --- a/arch/x86/kernel/cpu/cpufreq/sc520_freq.c +++ b/arch/x86/kernel/cpu/cpufreq/sc520_freq.c @@ -29,8 +29,6 @@ static __u8 __iomem *cpuctl; -#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \ - "sc520_freq", msg) #define PFX "sc520_freq: " static struct cpufreq_frequency_table sc520_freq_table[] = { @@ -66,7 +64,7 @@ static void sc520_freq_set_cpu_state(unsigned int state) cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE); - dprintk("attempting to set frequency to %i kHz\n", + pr_debug("attempting to set frequency to %i kHz\n", sc520_freq_table[state].frequency); local_irq_disable(); @@ -161,7 +159,7 @@ static int __init sc520_freq_init(void) /* Test if we have the right hardware */ if (c->x86_vendor != X86_VENDOR_AMD || c->x86 != 4 || c->x86_model != 9) { - dprintk("no Elan SC520 processor found!\n"); + pr_debug("no Elan SC520 processor found!\n"); return -ENODEV; } cpuctl = ioremap((unsigned long)(MMCR_BASE + OFFS_CPUCTL), 1); diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c b/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c index 9b1ff37de46..6ea3455def2 100644 --- a/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c +++ b/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c @@ -29,9 +29,6 @@ #define PFX "speedstep-centrino: " #define MAINTAINER "cpufreq@vger.kernel.org" -#define dprintk(msg...) \ - cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, "speedstep-centrino", msg) - #define INTEL_MSR_RANGE (0xffff) struct cpu_id @@ -244,7 +241,7 @@ static int centrino_cpu_init_table(struct cpufreq_policy *policy) if (model->cpu_id == NULL) { /* No match at all */ - dprintk("no support for CPU model \"%s\": " + pr_debug("no support for CPU model \"%s\": " "send /proc/cpuinfo to " MAINTAINER "\n", cpu->x86_model_id); return -ENOENT; @@ -252,15 +249,15 @@ static int centrino_cpu_init_table(struct cpufreq_policy *policy) if (model->op_points == NULL) { /* Matched a non-match */ - dprintk("no table support for CPU model \"%s\"\n", + pr_debug("no table support for CPU model \"%s\"\n", cpu->x86_model_id); - dprintk("try using the acpi-cpufreq driver\n"); + pr_debug("try using the acpi-cpufreq driver\n"); return -ENOENT; } per_cpu(centrino_model, policy->cpu) = model; - dprintk("found \"%s\": max frequency: %dkHz\n", + pr_debug("found \"%s\": max frequency: %dkHz\n", model->model_name, model->max_freq); return 0; @@ -369,7 +366,7 @@ static int centrino_cpu_init(struct cpufreq_policy *policy) per_cpu(centrino_cpu, policy->cpu) = &cpu_ids[i]; if (!per_cpu(centrino_cpu, policy->cpu)) { - dprintk("found unsupported CPU with " + pr_debug("found unsupported CPU with " "Enhanced SpeedStep: send /proc/cpuinfo to " MAINTAINER "\n"); return -ENODEV; @@ -385,7 +382,7 @@ static int centrino_cpu_init(struct cpufreq_policy *policy) if (!(l & MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP)) { l |= MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP; - dprintk("trying to enable Enhanced SpeedStep (%x)\n", l); + pr_debug("trying to enable Enhanced SpeedStep (%x)\n", l); wrmsr(MSR_IA32_MISC_ENABLE, l, h); /* check to see if it stuck */ @@ -402,7 +399,7 @@ static int centrino_cpu_init(struct cpufreq_policy *policy) /* 10uS transition latency */ policy->cur = freq; - dprintk("centrino_cpu_init: cur=%dkHz\n", policy->cur); + pr_debug("centrino_cpu_init: cur=%dkHz\n", policy->cur); ret = cpufreq_frequency_table_cpuinfo(policy, per_cpu(centrino_model, policy->cpu)->op_points); @@ -498,7 +495,7 @@ static int centrino_target (struct cpufreq_policy *policy, good_cpu = j; if (good_cpu >= nr_cpu_ids) { - dprintk("couldn't limit to CPUs in this domain\n"); + pr_debug("couldn't limit to CPUs in this domain\n"); retval = -EAGAIN; if (first_cpu) { /* We haven't started the transition yet. */ @@ -512,7 +509,7 @@ static int centrino_target (struct cpufreq_policy *policy, if (first_cpu) { rdmsr_on_cpu(good_cpu, MSR_IA32_PERF_CTL, &oldmsr, &h); if (msr == (oldmsr & 0xffff)) { - dprintk("no change needed - msr was and needs " + pr_debug("no change needed - msr was and needs " "to be %x\n", oldmsr); retval = 0; goto out; @@ -521,7 +518,7 @@ static int centrino_target (struct cpufreq_policy *policy, freqs.old = extract_clock(oldmsr, cpu, 0); freqs.new = extract_clock(msr, cpu, 0); - dprintk("target=%dkHz old=%d new=%d msr=%04x\n", + pr_debug("target=%dkHz old=%d new=%d msr=%04x\n", target_freq, freqs.old, freqs.new, msr); for_each_cpu(k, policy->cpus) { diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c b/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c index 561758e9518..a748ce782fe 100644 --- a/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c +++ b/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c @@ -53,10 +53,6 @@ static struct cpufreq_frequency_table speedstep_freqs[] = { }; -#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \ - "speedstep-ich", msg) - - /** * speedstep_find_register - read the PMBASE address * @@ -80,7 +76,7 @@ static int speedstep_find_register(void) return -ENODEV; } - dprintk("pmbase is 0x%x\n", pmbase); + pr_debug("pmbase is 0x%x\n", pmbase); return 0; } @@ -106,13 +102,13 @@ static void speedstep_set_state(unsigned int state) /* read state */ value = inb(pmbase + 0x50); - dprintk("read at pmbase 0x%x + 0x50 returned 0x%x\n", pmbase, value); + pr_debug("read at pmbase 0x%x + 0x50 returned 0x%x\n", pmbase, value); /* write new state */ value &= 0xFE; value |= state; - dprintk("writing 0x%x to pmbase 0x%x + 0x50\n", value, pmbase); + pr_debug("writing 0x%x to pmbase 0x%x + 0x50\n", value, pmbase); /* Disable bus master arbitration */ pm2_blk = inb(pmbase + 0x20); @@ -132,10 +128,10 @@ static void speedstep_set_state(unsigned int state) /* Enable IRQs */ local_irq_restore(flags); - dprintk("read at pmbase 0x%x + 0x50 returned 0x%x\n", pmbase, value); + pr_debug("read at pmbase 0x%x + 0x50 returned 0x%x\n", pmbase, value); if (state == (value & 0x1)) - dprintk("change to %u MHz succeeded\n", + pr_debug("change to %u MHz succeeded\n", speedstep_get_frequency(speedstep_processor) / 1000); else printk(KERN_ERR "cpufreq: change failed - I/O error\n"); @@ -165,7 +161,7 @@ static int speedstep_activate(void) pci_read_config_word(speedstep_chipset_dev, 0x00A0, &value); if (!(value & 0x08)) { value |= 0x08; - dprintk("activating SpeedStep (TM) registers\n"); + pr_debug("activating SpeedStep (TM) registers\n"); pci_write_config_word(speedstep_chipset_dev, 0x00A0, value); } @@ -218,7 +214,7 @@ static unsigned int speedstep_detect_chipset(void) return 2; /* 2-M */ if (hostbridge->revision < 5) { - dprintk("hostbridge does not support speedstep\n"); + pr_debug("hostbridge does not support speedstep\n"); speedstep_chipset_dev = NULL; pci_dev_put(hostbridge); return 0; @@ -246,7 +242,7 @@ static unsigned int speedstep_get(unsigned int cpu) if (smp_call_function_single(cpu, get_freq_data, &speed, 1) != 0) BUG(); - dprintk("detected %u kHz as current frequency\n", speed); + pr_debug("detected %u kHz as current frequency\n", speed); return speed; } @@ -276,7 +272,7 @@ static int speedstep_target(struct cpufreq_policy *policy, freqs.new = speedstep_freqs[newstate].frequency; freqs.cpu = policy->cpu; - dprintk("transiting from %u to %u kHz\n", freqs.old, freqs.new); + pr_debug("transiting from %u to %u kHz\n", freqs.old, freqs.new); /* no transition necessary */ if (freqs.old == freqs.new) @@ -351,7 +347,7 @@ static int speedstep_cpu_init(struct cpufreq_policy *policy) if (!speed) return -EIO; - dprintk("currently at %s speed setting - %i MHz\n", + pr_debug("currently at %s speed setting - %i MHz\n", (speed == speedstep_freqs[SPEEDSTEP_LOW].frequency) ? "low" : "high", (speed / 1000)); @@ -405,14 +401,14 @@ static int __init speedstep_init(void) /* detect processor */ speedstep_processor = speedstep_detect_processor(); if (!speedstep_processor) { - dprintk("Intel(R) SpeedStep(TM) capable processor " + pr_debug("Intel(R) SpeedStep(TM) capable processor " "not found\n"); return -ENODEV; } /* detect chipset */ if (!speedstep_detect_chipset()) { - dprintk("Intel(R) SpeedStep(TM) for this chipset not " + pr_debug("Intel(R) SpeedStep(TM) for this chipset not " "(yet) available.\n"); return -ENODEV; } diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-lib.c b/arch/x86/kernel/cpu/cpufreq/speedstep-lib.c index a94ec6be69f..8af2d2fd9d5 100644 --- a/arch/x86/kernel/cpu/cpufreq/speedstep-lib.c +++ b/arch/x86/kernel/cpu/cpufreq/speedstep-lib.c @@ -18,9 +18,6 @@ #include #include "speedstep-lib.h" -#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \ - "speedstep-lib", msg) - #define PFX "speedstep-lib: " #ifdef CONFIG_X86_SPEEDSTEP_RELAXED_CAP_CHECK @@ -75,7 +72,7 @@ static unsigned int pentium3_get_frequency(enum speedstep_processor processor) /* read MSR 0x2a - we only need the low 32 bits */ rdmsr(MSR_IA32_EBL_CR_POWERON, msr_lo, msr_tmp); - dprintk("P3 - MSR_IA32_EBL_CR_POWERON: 0x%x 0x%x\n", msr_lo, msr_tmp); + pr_debug("P3 - MSR_IA32_EBL_CR_POWERON: 0x%x 0x%x\n", msr_lo, msr_tmp); msr_tmp = msr_lo; /* decode the FSB */ @@ -89,7 +86,7 @@ static unsigned int pentium3_get_frequency(enum speedstep_processor processor) /* decode the multiplier */ if (processor == SPEEDSTEP_CPU_PIII_C_EARLY) { - dprintk("workaround for early PIIIs\n"); + pr_debug("workaround for early PIIIs\n"); msr_lo &= 0x03c00000; } else msr_lo &= 0x0bc00000; @@ -100,7 +97,7 @@ static unsigned int pentium3_get_frequency(enum speedstep_processor processor) j++; } - dprintk("speed is %u\n", + pr_debug("speed is %u\n", (msr_decode_mult[j].ratio * msr_decode_fsb[i].value * 100)); return msr_decode_mult[j].ratio * msr_decode_fsb[i].value * 100; @@ -112,7 +109,7 @@ static unsigned int pentiumM_get_frequency(void) u32 msr_lo, msr_tmp; rdmsr(MSR_IA32_EBL_CR_POWERON, msr_lo, msr_tmp); - dprintk("PM - MSR_IA32_EBL_CR_POWERON: 0x%x 0x%x\n", msr_lo, msr_tmp); + pr_debug("PM - MSR_IA32_EBL_CR_POWERON: 0x%x 0x%x\n", msr_lo, msr_tmp); /* see table B-2 of 24547212.pdf */ if (msr_lo & 0x00040000) { @@ -122,7 +119,7 @@ static unsigned int pentiumM_get_frequency(void) } msr_tmp = (msr_lo >> 22) & 0x1f; - dprintk("bits 22-26 are 0x%x, speed is %u\n", + pr_debug("bits 22-26 are 0x%x, speed is %u\n", msr_tmp, (msr_tmp * 100 * 1000)); return msr_tmp * 100 * 1000; @@ -160,11 +157,11 @@ static unsigned int pentium_core_get_frequency(void) } rdmsr(MSR_IA32_EBL_CR_POWERON, msr_lo, msr_tmp); - dprintk("PCORE - MSR_IA32_EBL_CR_POWERON: 0x%x 0x%x\n", + pr_debug("PCORE - MSR_IA32_EBL_CR_POWERON: 0x%x 0x%x\n", msr_lo, msr_tmp); msr_tmp = (msr_lo >> 22) & 0x1f; - dprintk("bits 22-26 are 0x%x, speed is %u\n", + pr_debug("bits 22-26 are 0x%x, speed is %u\n", msr_tmp, (msr_tmp * fsb)); ret = (msr_tmp * fsb); @@ -190,7 +187,7 @@ static unsigned int pentium4_get_frequency(void) rdmsr(0x2c, msr_lo, msr_hi); - dprintk("P4 - MSR_EBC_FREQUENCY_ID: 0x%x 0x%x\n", msr_lo, msr_hi); + pr_debug("P4 - MSR_EBC_FREQUENCY_ID: 0x%x 0x%x\n", msr_lo, msr_hi); /* decode the FSB: see IA-32 Intel (C) Architecture Software * Developer's Manual, Volume 3: System Prgramming Guide, @@ -217,7 +214,7 @@ static unsigned int pentium4_get_frequency(void) /* Multiplier. */ mult = msr_lo >> 24; - dprintk("P4 - FSB %u kHz; Multiplier %u; Speed %u kHz\n", + pr_debug("P4 - FSB %u kHz; Multiplier %u; Speed %u kHz\n", fsb, mult, (fsb * mult)); ret = (fsb * mult); @@ -257,7 +254,7 @@ unsigned int speedstep_detect_processor(void) struct cpuinfo_x86 *c = &cpu_data(0); u32 ebx, msr_lo, msr_hi; - dprintk("x86: %x, model: %x\n", c->x86, c->x86_model); + pr_debug("x86: %x, model: %x\n", c->x86, c->x86_model); if ((c->x86_vendor != X86_VENDOR_INTEL) || ((c->x86 != 6) && (c->x86 != 0xF))) @@ -272,7 +269,7 @@ unsigned int speedstep_detect_processor(void) ebx = cpuid_ebx(0x00000001); ebx &= 0x000000FF; - dprintk("ebx value is %x, x86_mask is %x\n", ebx, c->x86_mask); + pr_debug("ebx value is %x, x86_mask is %x\n", ebx, c->x86_mask); switch (c->x86_mask) { case 4: @@ -327,7 +324,7 @@ unsigned int speedstep_detect_processor(void) /* cpuid_ebx(1) is 0x04 for desktop PIII, * 0x06 for mobile PIII-M */ ebx = cpuid_ebx(0x00000001); - dprintk("ebx is %x\n", ebx); + pr_debug("ebx is %x\n", ebx); ebx &= 0x000000FF; @@ -344,7 +341,7 @@ unsigned int speedstep_detect_processor(void) /* all mobile PIII Coppermines have FSB 100 MHz * ==> sort out a few desktop PIIIs. */ rdmsr(MSR_IA32_EBL_CR_POWERON, msr_lo, msr_hi); - dprintk("Coppermine: MSR_IA32_EBL_CR_POWERON is 0x%x, 0x%x\n", + pr_debug("Coppermine: MSR_IA32_EBL_CR_POWERON is 0x%x, 0x%x\n", msr_lo, msr_hi); msr_lo &= 0x00c0000; if (msr_lo != 0x0080000) @@ -357,12 +354,12 @@ unsigned int speedstep_detect_processor(void) * bit 56 or 57 is set */ rdmsr(MSR_IA32_PLATFORM_ID, msr_lo, msr_hi); - dprintk("Coppermine: MSR_IA32_PLATFORM ID is 0x%x, 0x%x\n", + pr_debug("Coppermine: MSR_IA32_PLATFORM ID is 0x%x, 0x%x\n", msr_lo, msr_hi); if ((msr_hi & (1<<18)) && (relaxed_check ? 1 : (msr_hi & (3<<24)))) { if (c->x86_mask == 0x01) { - dprintk("early PIII version\n"); + pr_debug("early PIII version\n"); return SPEEDSTEP_CPU_PIII_C_EARLY; } else return SPEEDSTEP_CPU_PIII_C; @@ -393,14 +390,14 @@ unsigned int speedstep_get_freqs(enum speedstep_processor processor, if ((!processor) || (!low_speed) || (!high_speed) || (!set_state)) return -EINVAL; - dprintk("trying to determine both speeds\n"); + pr_debug("trying to determine both speeds\n"); /* get current speed */ prev_speed = speedstep_get_frequency(processor); if (!prev_speed) return -EIO; - dprintk("previous speed is %u\n", prev_speed); + pr_debug("previous speed is %u\n", prev_speed); local_irq_save(flags); @@ -412,7 +409,7 @@ unsigned int speedstep_get_freqs(enum speedstep_processor processor, goto out; } - dprintk("low speed is %u\n", *low_speed); + pr_debug("low speed is %u\n", *low_speed); /* start latency measurement */ if (transition_latency) @@ -431,7 +428,7 @@ unsigned int speedstep_get_freqs(enum speedstep_processor processor, goto out; } - dprintk("high speed is %u\n", *high_speed); + pr_debug("high speed is %u\n", *high_speed); if (*low_speed == *high_speed) { ret = -ENODEV; @@ -445,7 +442,7 @@ unsigned int speedstep_get_freqs(enum speedstep_processor processor, if (transition_latency) { *transition_latency = (tv2.tv_sec - tv1.tv_sec) * USEC_PER_SEC + tv2.tv_usec - tv1.tv_usec; - dprintk("transition latency is %u uSec\n", *transition_latency); + pr_debug("transition latency is %u uSec\n", *transition_latency); /* convert uSec to nSec and add 20% for safety reasons */ *transition_latency *= 1200; diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c b/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c index 91bc25b67bc..c76ead3490b 100644 --- a/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c +++ b/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c @@ -55,9 +55,6 @@ static struct cpufreq_frequency_table speedstep_freqs[] = { * of DMA activity going on? */ #define SMI_TRIES 5 -#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \ - "speedstep-smi", msg) - /** * speedstep_smi_ownership */ @@ -70,7 +67,7 @@ static int speedstep_smi_ownership(void) command = (smi_sig & 0xffffff00) | (smi_cmd & 0xff); magic = virt_to_phys(magic_data); - dprintk("trying to obtain ownership with command %x at port %x\n", + pr_debug("trying to obtain ownership with command %x at port %x\n", command, smi_port); __asm__ __volatile__( @@ -85,7 +82,7 @@ static int speedstep_smi_ownership(void) : "memory" ); - dprintk("result is %x\n", result); + pr_debug("result is %x\n", result); return result; } @@ -106,13 +103,13 @@ static int speedstep_smi_get_freqs(unsigned int *low, unsigned int *high) u32 function = GET_SPEEDSTEP_FREQS; if (!(ist_info.event & 0xFFFF)) { - dprintk("bug #1422 -- can't read freqs from BIOS\n"); + pr_debug("bug #1422 -- can't read freqs from BIOS\n"); return -ENODEV; } command = (smi_sig & 0xffffff00) | (smi_cmd & 0xff); - dprintk("trying to determine frequencies with command %x at port %x\n", + pr_debug("trying to determine frequencies with command %x at port %x\n", command, smi_port); __asm__ __volatile__( @@ -129,7 +126,7 @@ static int speedstep_smi_get_freqs(unsigned int *low, unsigned int *high) "d" (smi_port), "S" (0), "D" (0) ); - dprintk("result %x, low_freq %u, high_freq %u\n", + pr_debug("result %x, low_freq %u, high_freq %u\n", result, low_mhz, high_mhz); /* abort if results are obviously incorrect... */ @@ -154,7 +151,7 @@ static int speedstep_get_state(void) command = (smi_sig & 0xffffff00) | (smi_cmd & 0xff); - dprintk("trying to determine current setting with command %x " + pr_debug("trying to determine current setting with command %x " "at port %x\n", command, smi_port); __asm__ __volatile__( @@ -168,7 +165,7 @@ static int speedstep_get_state(void) "d" (smi_port), "S" (0), "D" (0) ); - dprintk("state is %x, result is %x\n", state, result); + pr_debug("state is %x, result is %x\n", state, result); return state & 1; } @@ -194,13 +191,13 @@ static void speedstep_set_state(unsigned int state) command = (smi_sig & 0xffffff00) | (smi_cmd & 0xff); - dprintk("trying to set frequency to state %u " + pr_debug("trying to set frequency to state %u " "with command %x at port %x\n", state, command, smi_port); do { if (retry) { - dprintk("retry %u, previous result %u, waiting...\n", + pr_debug("retry %u, previous result %u, waiting...\n", retry, result); mdelay(retry * 50); } @@ -221,7 +218,7 @@ static void speedstep_set_state(unsigned int state) local_irq_restore(flags); if (new_state == state) - dprintk("change to %u MHz succeeded after %u tries " + pr_debug("change to %u MHz succeeded after %u tries " "with result %u\n", (speedstep_freqs[new_state].frequency / 1000), retry, result); @@ -292,7 +289,7 @@ static int speedstep_cpu_init(struct cpufreq_policy *policy) result = speedstep_smi_ownership(); if (result) { - dprintk("fails in acquiring ownership of a SMI interface.\n"); + pr_debug("fails in acquiring ownership of a SMI interface.\n"); return -EINVAL; } @@ -304,7 +301,7 @@ static int speedstep_cpu_init(struct cpufreq_policy *policy) if (result) { /* fall back to speedstep_lib.c dection mechanism: * try both states out */ - dprintk("could not detect low and high frequencies " + pr_debug("could not detect low and high frequencies " "by SMI call.\n"); result = speedstep_get_freqs(speedstep_processor, low, high, @@ -312,18 +309,18 @@ static int speedstep_cpu_init(struct cpufreq_policy *policy) &speedstep_set_state); if (result) { - dprintk("could not detect two different speeds" + pr_debug("could not detect two different speeds" " -- aborting.\n"); return result; } else - dprintk("workaround worked.\n"); + pr_debug("workaround worked.\n"); } /* get current speed setting */ state = speedstep_get_state(); speed = speedstep_freqs[state].frequency; - dprintk("currently at %s speed setting - %i MHz\n", + pr_debug("currently at %s speed setting - %i MHz\n", (speed == speedstep_freqs[SPEEDSTEP_LOW].frequency) ? "low" : "high", (speed / 1000)); @@ -360,7 +357,7 @@ static int speedstep_resume(struct cpufreq_policy *policy) int result = speedstep_smi_ownership(); if (result) - dprintk("fails in re-acquiring ownership of a SMI interface.\n"); + pr_debug("fails in re-acquiring ownership of a SMI interface.\n"); return result; } @@ -403,12 +400,12 @@ static int __init speedstep_init(void) } if (!speedstep_processor) { - dprintk("No supported Intel CPU detected.\n"); + pr_debug("No supported Intel CPU detected.\n"); return -ENODEV; } - dprintk("signature:0x%.8lx, command:0x%.8lx, " - "event:0x%.8lx, perf_level:0x%.8lx.\n", + pr_debug("signature:0x%.8ulx, command:0x%.8ulx, " + "event:0x%.8ulx, perf_level:0x%.8ulx.\n", ist_info.signature, ist_info.command, ist_info.event, ist_info.perf_level); diff --git a/drivers/acpi/processor_perflib.c b/drivers/acpi/processor_perflib.c index 3a73a93596e..85b32376dad 100644 --- a/drivers/acpi/processor_perflib.c +++ b/drivers/acpi/processor_perflib.c @@ -49,10 +49,6 @@ ACPI_MODULE_NAME("processor_perflib"); static DEFINE_MUTEX(performance_mutex); -/* Use cpufreq debug layer for _PPC changes. */ -#define cpufreq_printk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_CORE, \ - "cpufreq-core", msg) - /* * _PPC support is implemented as a CPUfreq policy notifier: * This means each time a CPUfreq driver registered also with @@ -145,7 +141,7 @@ static int acpi_processor_get_platform_limit(struct acpi_processor *pr) return -ENODEV; } - cpufreq_printk("CPU %d: _PPC is %d - frequency %s limited\n", pr->id, + pr_debug("CPU %d: _PPC is %d - frequency %s limited\n", pr->id, (int)ppc, ppc ? "" : "not"); pr->performance_platform_limit = (int)ppc; diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig index ca8ee8093d6..b78baa547ef 100644 --- a/drivers/cpufreq/Kconfig +++ b/drivers/cpufreq/Kconfig @@ -18,19 +18,6 @@ if CPU_FREQ config CPU_FREQ_TABLE tristate -config CPU_FREQ_DEBUG - bool "Enable CPUfreq debugging" - help - Say Y here to enable CPUfreq subsystem (including drivers) - debugging. You will need to activate it via the kernel - command line by passing - cpufreq.debug= - - To get , add - 1 to activate CPUfreq core debugging, - 2 to activate CPUfreq drivers debugging, and - 4 to activate CPUfreq governor debugging - config CPU_FREQ_STAT tristate "CPU frequency translation statistics" select CPU_FREQ_TABLE diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 7c10f96c5ae..1e08af43ae7 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -32,9 +32,6 @@ #include -#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_CORE, \ - "cpufreq-core", msg) - /** * The "cpufreq driver" - the arch- or hardware-dependent low * level driver of CPUFreq support, and its spinlock. This lock @@ -180,93 +177,6 @@ void cpufreq_cpu_put(struct cpufreq_policy *data) EXPORT_SYMBOL_GPL(cpufreq_cpu_put); -/********************************************************************* - * UNIFIED DEBUG HELPERS * - *********************************************************************/ -#ifdef CONFIG_CPU_FREQ_DEBUG - -/* what part(s) of the CPUfreq subsystem are debugged? */ -static unsigned int debug; - -/* is the debug output ratelimit'ed using printk_ratelimit? User can - * set or modify this value. - */ -static unsigned int debug_ratelimit = 1; - -/* is the printk_ratelimit'ing enabled? It's enabled after a successful - * loading of a cpufreq driver, temporarily disabled when a new policy - * is set, and disabled upon cpufreq driver removal - */ -static unsigned int disable_ratelimit = 1; -static DEFINE_SPINLOCK(disable_ratelimit_lock); - -static void cpufreq_debug_enable_ratelimit(void) -{ - unsigned long flags; - - spin_lock_irqsave(&disable_ratelimit_lock, flags); - if (disable_ratelimit) - disable_ratelimit--; - spin_unlock_irqrestore(&disable_ratelimit_lock, flags); -} - -static void cpufreq_debug_disable_ratelimit(void) -{ - unsigned long flags; - - spin_lock_irqsave(&disable_ratelimit_lock, flags); - disable_ratelimit++; - spin_unlock_irqrestore(&disable_ratelimit_lock, flags); -} - -void cpufreq_debug_printk(unsigned int type, const char *prefix, - const char *fmt, ...) -{ - char s[256]; - va_list args; - unsigned int len; - unsigned long flags; - - WARN_ON(!prefix); - if (type & debug) { - spin_lock_irqsave(&disable_ratelimit_lock, flags); - if (!disable_ratelimit && debug_ratelimit - && !printk_ratelimit()) { - spin_unlock_irqrestore(&disable_ratelimit_lock, flags); - return; - } - spin_unlock_irqrestore(&disable_ratelimit_lock, flags); - - len = snprintf(s, 256, KERN_DEBUG "%s: ", prefix); - - va_start(args, fmt); - len += vsnprintf(&s[len], (256 - len), fmt, args); - va_end(args); - - printk(s); - - WARN_ON(len < 5); - } -} -EXPORT_SYMBOL(cpufreq_debug_printk); - - -module_param(debug, uint, 0644); -MODULE_PARM_DESC(debug, "CPUfreq debugging: add 1 to debug core," - " 2 to debug drivers, and 4 to debug governors."); - -module_param(debug_ratelimit, uint, 0644); -MODULE_PARM_DESC(debug_ratelimit, "CPUfreq debugging:" - " set to 0 to disable ratelimiting."); - -#else /* !CONFIG_CPU_FREQ_DEBUG */ - -static inline void cpufreq_debug_enable_ratelimit(void) { return; } -static inline void cpufreq_debug_disable_ratelimit(void) { return; } - -#endif /* CONFIG_CPU_FREQ_DEBUG */ - - /********************************************************************* * EXTERNALLY AFFECTING FREQUENCY CHANGES * *********************************************************************/ @@ -291,7 +201,7 @@ static void adjust_jiffies(unsigned long val, struct cpufreq_freqs *ci) if (!l_p_j_ref_freq) { l_p_j_ref = loops_per_jiffy; l_p_j_ref_freq = ci->old; - dprintk("saving %lu as reference value for loops_per_jiffy; " + pr_debug("saving %lu as reference value for loops_per_jiffy; " "freq is %u kHz\n", l_p_j_ref, l_p_j_ref_freq); } if ((val == CPUFREQ_PRECHANGE && ci->old < ci->new) || @@ -299,7 +209,7 @@ static void adjust_jiffies(unsigned long val, struct cpufreq_freqs *ci) (val == CPUFREQ_RESUMECHANGE || val == CPUFREQ_SUSPENDCHANGE)) { loops_per_jiffy = cpufreq_scale(l_p_j_ref, l_p_j_ref_freq, ci->new); - dprintk("scaling loops_per_jiffy to %lu " + pr_debug("scaling loops_per_jiffy to %lu " "for frequency %u kHz\n", loops_per_jiffy, ci->new); } } @@ -326,7 +236,7 @@ void cpufreq_notify_transition(struct cpufreq_freqs *freqs, unsigned int state) BUG_ON(irqs_disabled()); freqs->flags = cpufreq_driver->flags; - dprintk("notification %u of frequency transition to %u kHz\n", + pr_debug("notification %u of frequency transition to %u kHz\n", state, freqs->new); policy = per_cpu(cpufreq_cpu_data, freqs->cpu); @@ -340,7 +250,7 @@ void cpufreq_notify_transition(struct cpufreq_freqs *freqs, unsigned int state) if (!(cpufreq_driver->flags & CPUFREQ_CONST_LOOPS)) { if ((policy) && (policy->cpu == freqs->cpu) && (policy->cur) && (policy->cur != freqs->old)) { - dprintk("Warning: CPU frequency is" + pr_debug("Warning: CPU frequency is" " %u, cpufreq assumed %u kHz.\n", freqs->old, policy->cur); freqs->old = policy->cur; @@ -353,7 +263,7 @@ void cpufreq_notify_transition(struct cpufreq_freqs *freqs, unsigned int state) case CPUFREQ_POSTCHANGE: adjust_jiffies(CPUFREQ_POSTCHANGE, freqs); - dprintk("FREQ: %lu - CPU: %lu", (unsigned long)freqs->new, + pr_debug("FREQ: %lu - CPU: %lu", (unsigned long)freqs->new, (unsigned long)freqs->cpu); trace_power_frequency(POWER_PSTATE, freqs->new, freqs->cpu); trace_cpu_frequency(freqs->new, freqs->cpu); @@ -753,7 +663,7 @@ no_policy: static void cpufreq_sysfs_release(struct kobject *kobj) { struct cpufreq_policy *policy = to_policy(kobj); - dprintk("last reference is dropped\n"); + pr_debug("last reference is dropped\n"); complete(&policy->kobj_unregister); } @@ -788,7 +698,7 @@ static int cpufreq_add_dev_policy(unsigned int cpu, gov = __find_governor(per_cpu(cpufreq_cpu_governor, cpu)); if (gov) { policy->governor = gov; - dprintk("Restoring governor %s for cpu %d\n", + pr_debug("Restoring governor %s for cpu %d\n", policy->governor->name, cpu); } #endif @@ -824,7 +734,7 @@ static int cpufreq_add_dev_policy(unsigned int cpu, per_cpu(cpufreq_cpu_data, cpu) = managed_policy; spin_unlock_irqrestore(&cpufreq_driver_lock, flags); - dprintk("CPU already managed, adding link\n"); + pr_debug("CPU already managed, adding link\n"); ret = sysfs_create_link(&sys_dev->kobj, &managed_policy->kobj, "cpufreq"); @@ -865,7 +775,7 @@ static int cpufreq_add_dev_symlink(unsigned int cpu, if (!cpu_online(j)) continue; - dprintk("CPU %u already managed, adding link\n", j); + pr_debug("CPU %u already managed, adding link\n", j); managed_policy = cpufreq_cpu_get(cpu); cpu_sys_dev = get_cpu_sysdev(j); ret = sysfs_create_link(&cpu_sys_dev->kobj, &policy->kobj, @@ -941,7 +851,7 @@ static int cpufreq_add_dev_interface(unsigned int cpu, policy->user_policy.governor = policy->governor; if (ret) { - dprintk("setting policy failed\n"); + pr_debug("setting policy failed\n"); if (cpufreq_driver->exit) cpufreq_driver->exit(policy); } @@ -977,8 +887,7 @@ static int cpufreq_add_dev(struct sys_device *sys_dev) if (cpu_is_offline(cpu)) return 0; - cpufreq_debug_disable_ratelimit(); - dprintk("adding CPU %u\n", cpu); + pr_debug("adding CPU %u\n", cpu); #ifdef CONFIG_SMP /* check whether a different CPU already registered this @@ -986,7 +895,6 @@ static int cpufreq_add_dev(struct sys_device *sys_dev) policy = cpufreq_cpu_get(cpu); if (unlikely(policy)) { cpufreq_cpu_put(policy); - cpufreq_debug_enable_ratelimit(); return 0; } #endif @@ -1037,7 +945,7 @@ static int cpufreq_add_dev(struct sys_device *sys_dev) */ ret = cpufreq_driver->init(policy); if (ret) { - dprintk("initialization failed\n"); + pr_debug("initialization failed\n"); goto err_unlock_policy; } policy->user_policy.min = policy->min; @@ -1063,8 +971,7 @@ static int cpufreq_add_dev(struct sys_device *sys_dev) kobject_uevent(&policy->kobj, KOBJ_ADD); module_put(cpufreq_driver->owner); - dprintk("initialization complete\n"); - cpufreq_debug_enable_ratelimit(); + pr_debug("initialization complete\n"); return 0; @@ -1088,7 +995,6 @@ err_free_policy: nomem_out: module_put(cpufreq_driver->owner); module_out: - cpufreq_debug_enable_ratelimit(); return ret; } @@ -1112,15 +1018,13 @@ static int __cpufreq_remove_dev(struct sys_device *sys_dev) unsigned int j; #endif - cpufreq_debug_disable_ratelimit(); - dprintk("unregistering CPU %u\n", cpu); + pr_debug("unregistering CPU %u\n", cpu); spin_lock_irqsave(&cpufreq_driver_lock, flags); data = per_cpu(cpufreq_cpu_data, cpu); if (!data) { spin_unlock_irqrestore(&cpufreq_driver_lock, flags); - cpufreq_debug_enable_ratelimit(); unlock_policy_rwsem_write(cpu); return -EINVAL; } @@ -1132,12 +1036,11 @@ static int __cpufreq_remove_dev(struct sys_device *sys_dev) * only need to unlink, put and exit */ if (unlikely(cpu != data->cpu)) { - dprintk("removing link\n"); + pr_debug("removing link\n"); cpumask_clear_cpu(cpu, data->cpus); spin_unlock_irqrestore(&cpufreq_driver_lock, flags); kobj = &sys_dev->kobj; cpufreq_cpu_put(data); - cpufreq_debug_enable_ratelimit(); unlock_policy_rwsem_write(cpu); sysfs_remove_link(kobj, "cpufreq"); return 0; @@ -1170,7 +1073,7 @@ static int __cpufreq_remove_dev(struct sys_device *sys_dev) for_each_cpu(j, data->cpus) { if (j == cpu) continue; - dprintk("removing link for cpu %u\n", j); + pr_debug("removing link for cpu %u\n", j); #ifdef CONFIG_HOTPLUG_CPU strncpy(per_cpu(cpufreq_cpu_governor, j), data->governor->name, CPUFREQ_NAME_LEN); @@ -1199,17 +1102,15 @@ static int __cpufreq_remove_dev(struct sys_device *sys_dev) * not referenced anymore by anybody before we proceed with * unloading. */ - dprintk("waiting for dropping of refcount\n"); + pr_debug("waiting for dropping of refcount\n"); wait_for_completion(cmp); - dprintk("wait complete\n"); + pr_debug("wait complete\n"); lock_policy_rwsem_write(cpu); if (cpufreq_driver->exit) cpufreq_driver->exit(data); unlock_policy_rwsem_write(cpu); - cpufreq_debug_enable_ratelimit(); - #ifdef CONFIG_HOTPLUG_CPU /* when the CPU which is the parent of the kobj is hotplugged * offline, check for siblings, and create cpufreq sysfs interface @@ -1255,7 +1156,7 @@ static void handle_update(struct work_struct *work) struct cpufreq_policy *policy = container_of(work, struct cpufreq_policy, update); unsigned int cpu = policy->cpu; - dprintk("handle_update for cpu %u called\n", cpu); + pr_debug("handle_update for cpu %u called\n", cpu); cpufreq_update_policy(cpu); } @@ -1273,7 +1174,7 @@ static void cpufreq_out_of_sync(unsigned int cpu, unsigned int old_freq, { struct cpufreq_freqs freqs; - dprintk("Warning: CPU frequency out of sync: cpufreq and timing " + pr_debug("Warning: CPU frequency out of sync: cpufreq and timing " "core thinks of %u, is %u kHz.\n", old_freq, new_freq); freqs.cpu = cpu; @@ -1376,7 +1277,7 @@ static int cpufreq_bp_suspend(void) int cpu = smp_processor_id(); struct cpufreq_policy *cpu_policy; - dprintk("suspending cpu %u\n", cpu); + pr_debug("suspending cpu %u\n", cpu); /* If there's no policy for the boot CPU, we have nothing to do. */ cpu_policy = cpufreq_cpu_get(cpu); @@ -1414,7 +1315,7 @@ static void cpufreq_bp_resume(void) int cpu = smp_processor_id(); struct cpufreq_policy *cpu_policy; - dprintk("resuming cpu %u\n", cpu); + pr_debug("resuming cpu %u\n", cpu); /* If there's no policy for the boot CPU, we have nothing to do. */ cpu_policy = cpufreq_cpu_get(cpu); @@ -1526,7 +1427,7 @@ int __cpufreq_driver_target(struct cpufreq_policy *policy, { int retval = -EINVAL; - dprintk("target for CPU %u: %u kHz, relation %u\n", policy->cpu, + pr_debug("target for CPU %u: %u kHz, relation %u\n", policy->cpu, target_freq, relation); if (cpu_online(policy->cpu) && cpufreq_driver->target) retval = cpufreq_driver->target(policy, target_freq, relation); @@ -1612,7 +1513,7 @@ static int __cpufreq_governor(struct cpufreq_policy *policy, if (!try_module_get(policy->governor->owner)) return -EINVAL; - dprintk("__cpufreq_governor for CPU %u, event %u\n", + pr_debug("__cpufreq_governor for CPU %u, event %u\n", policy->cpu, event); ret = policy->governor->governor(policy, event); @@ -1713,8 +1614,7 @@ static int __cpufreq_set_policy(struct cpufreq_policy *data, { int ret = 0; - cpufreq_debug_disable_ratelimit(); - dprintk("setting new policy for CPU %u: %u - %u kHz\n", policy->cpu, + pr_debug("setting new policy for CPU %u: %u - %u kHz\n", policy->cpu, policy->min, policy->max); memcpy(&policy->cpuinfo, &data->cpuinfo, @@ -1751,19 +1651,19 @@ static int __cpufreq_set_policy(struct cpufreq_policy *data, data->min = policy->min; data->max = policy->max; - dprintk("new min and max freqs are %u - %u kHz\n", + pr_debug("new min and max freqs are %u - %u kHz\n", data->min, data->max); if (cpufreq_driver->setpolicy) { data->policy = policy->policy; - dprintk("setting range\n"); + pr_debug("setting range\n"); ret = cpufreq_driver->setpolicy(policy); } else { if (policy->governor != data->governor) { /* save old, working values */ struct cpufreq_governor *old_gov = data->governor; - dprintk("governor switch\n"); + pr_debug("governor switch\n"); /* end old governor */ if (data->governor) @@ -1773,7 +1673,7 @@ static int __cpufreq_set_policy(struct cpufreq_policy *data, data->governor = policy->governor; if (__cpufreq_governor(data, CPUFREQ_GOV_START)) { /* new governor failed, so re-start old one */ - dprintk("starting governor %s failed\n", + pr_debug("starting governor %s failed\n", data->governor->name); if (old_gov) { data->governor = old_gov; @@ -1785,12 +1685,11 @@ static int __cpufreq_set_policy(struct cpufreq_policy *data, } /* might be a policy change, too, so fall through */ } - dprintk("governor: change or update limits\n"); + pr_debug("governor: change or update limits\n"); __cpufreq_governor(data, CPUFREQ_GOV_LIMITS); } error_out: - cpufreq_debug_enable_ratelimit(); return ret; } @@ -1817,7 +1716,7 @@ int cpufreq_update_policy(unsigned int cpu) goto fail; } - dprintk("updating policy for CPU %u\n", cpu); + pr_debug("updating policy for CPU %u\n", cpu); memcpy(&policy, data, sizeof(struct cpufreq_policy)); policy.min = data->user_policy.min; policy.max = data->user_policy.max; @@ -1829,7 +1728,7 @@ int cpufreq_update_policy(unsigned int cpu) if (cpufreq_driver->get) { policy.cur = cpufreq_driver->get(cpu); if (!data->cur) { - dprintk("Driver did not initialize current freq"); + pr_debug("Driver did not initialize current freq"); data->cur = policy.cur; } else { if (data->cur != policy.cur) @@ -1905,7 +1804,7 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data) ((!driver_data->setpolicy) && (!driver_data->target))) return -EINVAL; - dprintk("trying to register driver %s\n", driver_data->name); + pr_debug("trying to register driver %s\n", driver_data->name); if (driver_data->setpolicy) driver_data->flags |= CPUFREQ_CONST_LOOPS; @@ -1936,15 +1835,14 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data) /* if all ->init() calls failed, unregister */ if (ret) { - dprintk("no CPU initialized for driver %s\n", + pr_debug("no CPU initialized for driver %s\n", driver_data->name); goto err_sysdev_unreg; } } register_hotcpu_notifier(&cpufreq_cpu_notifier); - dprintk("driver %s up and running\n", driver_data->name); - cpufreq_debug_enable_ratelimit(); + pr_debug("driver %s up and running\n", driver_data->name); return 0; err_sysdev_unreg: @@ -1971,14 +1869,10 @@ int cpufreq_unregister_driver(struct cpufreq_driver *driver) { unsigned long flags; - cpufreq_debug_disable_ratelimit(); - - if (!cpufreq_driver || (driver != cpufreq_driver)) { - cpufreq_debug_enable_ratelimit(); + if (!cpufreq_driver || (driver != cpufreq_driver)) return -EINVAL; - } - dprintk("unregistering driver %s\n", driver->name); + pr_debug("unregistering driver %s\n", driver->name); sysdev_driver_unregister(&cpu_sysdev_class, &cpufreq_sysdev_driver); unregister_hotcpu_notifier(&cpufreq_cpu_notifier); diff --git a/drivers/cpufreq/cpufreq_performance.c b/drivers/cpufreq/cpufreq_performance.c index 7e2e515087f..f13a8a9af6a 100644 --- a/drivers/cpufreq/cpufreq_performance.c +++ b/drivers/cpufreq/cpufreq_performance.c @@ -15,9 +15,6 @@ #include #include -#define dprintk(msg...) \ - cpufreq_debug_printk(CPUFREQ_DEBUG_GOVERNOR, "performance", msg) - static int cpufreq_governor_performance(struct cpufreq_policy *policy, unsigned int event) @@ -25,7 +22,7 @@ static int cpufreq_governor_performance(struct cpufreq_policy *policy, switch (event) { case CPUFREQ_GOV_START: case CPUFREQ_GOV_LIMITS: - dprintk("setting to %u kHz because of event %u\n", + pr_debug("setting to %u kHz because of event %u\n", policy->max, event); __cpufreq_driver_target(policy, policy->max, CPUFREQ_RELATION_H); diff --git a/drivers/cpufreq/cpufreq_powersave.c b/drivers/cpufreq/cpufreq_powersave.c index e6db5faf3eb..4c2eb512f2b 100644 --- a/drivers/cpufreq/cpufreq_powersave.c +++ b/drivers/cpufreq/cpufreq_powersave.c @@ -15,16 +15,13 @@ #include #include -#define dprintk(msg...) \ - cpufreq_debug_printk(CPUFREQ_DEBUG_GOVERNOR, "powersave", msg) - static int cpufreq_governor_powersave(struct cpufreq_policy *policy, unsigned int event) { switch (event) { case CPUFREQ_GOV_START: case CPUFREQ_GOV_LIMITS: - dprintk("setting to %u kHz because of event %u\n", + pr_debug("setting to %u kHz because of event %u\n", policy->min, event); __cpufreq_driver_target(policy, policy->min, CPUFREQ_RELATION_L); diff --git a/drivers/cpufreq/cpufreq_userspace.c b/drivers/cpufreq/cpufreq_userspace.c index 66d2d1d6c80..f231015904c 100644 --- a/drivers/cpufreq/cpufreq_userspace.c +++ b/drivers/cpufreq/cpufreq_userspace.c @@ -37,9 +37,6 @@ static DEFINE_PER_CPU(unsigned int, cpu_is_managed); static DEFINE_MUTEX(userspace_mutex); static int cpus_using_userspace_governor; -#define dprintk(msg...) \ - cpufreq_debug_printk(CPUFREQ_DEBUG_GOVERNOR, "userspace", msg) - /* keep track of frequency transitions */ static int userspace_cpufreq_notifier(struct notifier_block *nb, unsigned long val, @@ -50,7 +47,7 @@ userspace_cpufreq_notifier(struct notifier_block *nb, unsigned long val, if (!per_cpu(cpu_is_managed, freq->cpu)) return 0; - dprintk("saving cpu_cur_freq of cpu %u to be %u kHz\n", + pr_debug("saving cpu_cur_freq of cpu %u to be %u kHz\n", freq->cpu, freq->new); per_cpu(cpu_cur_freq, freq->cpu) = freq->new; @@ -73,7 +70,7 @@ static int cpufreq_set(struct cpufreq_policy *policy, unsigned int freq) { int ret = -EINVAL; - dprintk("cpufreq_set for cpu %u, freq %u kHz\n", policy->cpu, freq); + pr_debug("cpufreq_set for cpu %u, freq %u kHz\n", policy->cpu, freq); mutex_lock(&userspace_mutex); if (!per_cpu(cpu_is_managed, policy->cpu)) @@ -134,7 +131,7 @@ static int cpufreq_governor_userspace(struct cpufreq_policy *policy, per_cpu(cpu_max_freq, cpu) = policy->max; per_cpu(cpu_cur_freq, cpu) = policy->cur; per_cpu(cpu_set_freq, cpu) = policy->cur; - dprintk("managing cpu %u started " + pr_debug("managing cpu %u started " "(%u - %u kHz, currently %u kHz)\n", cpu, per_cpu(cpu_min_freq, cpu), @@ -156,12 +153,12 @@ static int cpufreq_governor_userspace(struct cpufreq_policy *policy, per_cpu(cpu_min_freq, cpu) = 0; per_cpu(cpu_max_freq, cpu) = 0; per_cpu(cpu_set_freq, cpu) = 0; - dprintk("managing cpu %u stopped\n", cpu); + pr_debug("managing cpu %u stopped\n", cpu); mutex_unlock(&userspace_mutex); break; case CPUFREQ_GOV_LIMITS: mutex_lock(&userspace_mutex); - dprintk("limit event for cpu %u: %u - %u kHz, " + pr_debug("limit event for cpu %u: %u - %u kHz, " "currently %u kHz, last set to %u kHz\n", cpu, policy->min, policy->max, per_cpu(cpu_cur_freq, cpu), diff --git a/drivers/cpufreq/freq_table.c b/drivers/cpufreq/freq_table.c index 05432216e22..90431cb9280 100644 --- a/drivers/cpufreq/freq_table.c +++ b/drivers/cpufreq/freq_table.c @@ -14,9 +14,6 @@ #include #include -#define dprintk(msg...) \ - cpufreq_debug_printk(CPUFREQ_DEBUG_CORE, "freq-table", msg) - /********************************************************************* * FREQUENCY TABLE HELPERS * *********************************************************************/ @@ -31,11 +28,11 @@ int cpufreq_frequency_table_cpuinfo(struct cpufreq_policy *policy, for (i = 0; (table[i].frequency != CPUFREQ_TABLE_END); i++) { unsigned int freq = table[i].frequency; if (freq == CPUFREQ_ENTRY_INVALID) { - dprintk("table entry %u is invalid, skipping\n", i); + pr_debug("table entry %u is invalid, skipping\n", i); continue; } - dprintk("table entry %u: %u kHz, %u index\n", + pr_debug("table entry %u: %u kHz, %u index\n", i, freq, table[i].index); if (freq < min_freq) min_freq = freq; @@ -61,7 +58,7 @@ int cpufreq_frequency_table_verify(struct cpufreq_policy *policy, unsigned int i; unsigned int count = 0; - dprintk("request for verification of policy (%u - %u kHz) for cpu %u\n", + pr_debug("request for verification of policy (%u - %u kHz) for cpu %u\n", policy->min, policy->max, policy->cpu); if (!cpu_online(policy->cpu)) @@ -86,7 +83,7 @@ int cpufreq_frequency_table_verify(struct cpufreq_policy *policy, cpufreq_verify_within_limits(policy, policy->cpuinfo.min_freq, policy->cpuinfo.max_freq); - dprintk("verification lead to (%u - %u kHz) for cpu %u\n", + pr_debug("verification lead to (%u - %u kHz) for cpu %u\n", policy->min, policy->max, policy->cpu); return 0; @@ -110,7 +107,7 @@ int cpufreq_frequency_table_target(struct cpufreq_policy *policy, }; unsigned int i; - dprintk("request for target %u kHz (relation: %u) for cpu %u\n", + pr_debug("request for target %u kHz (relation: %u) for cpu %u\n", target_freq, relation, policy->cpu); switch (relation) { @@ -167,7 +164,7 @@ int cpufreq_frequency_table_target(struct cpufreq_policy *policy, } else *index = optimal.index; - dprintk("target is %u (%u kHz, %u)\n", *index, table[*index].frequency, + pr_debug("target is %u (%u kHz, %u)\n", *index, table[*index].frequency, table[*index].index); return 0; @@ -216,14 +213,14 @@ EXPORT_SYMBOL_GPL(cpufreq_freq_attr_scaling_available_freqs); void cpufreq_frequency_table_get_attr(struct cpufreq_frequency_table *table, unsigned int cpu) { - dprintk("setting show_table for cpu %u to %p\n", cpu, table); + pr_debug("setting show_table for cpu %u to %p\n", cpu, table); per_cpu(cpufreq_show_table, cpu) = table; } EXPORT_SYMBOL_GPL(cpufreq_frequency_table_get_attr); void cpufreq_frequency_table_put_attr(unsigned int cpu) { - dprintk("clearing show_table for cpu %u\n", cpu); + pr_debug("clearing show_table for cpu %u\n", cpu); per_cpu(cpufreq_show_table, cpu) = NULL; } EXPORT_SYMBOL_GPL(cpufreq_frequency_table_put_attr); diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 9343dd3de85..2845f6e6722 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -397,23 +397,4 @@ void cpufreq_frequency_table_get_attr(struct cpufreq_frequency_table *table, void cpufreq_frequency_table_put_attr(unsigned int cpu); -/********************************************************************* - * UNIFIED DEBUG HELPERS * - *********************************************************************/ - -#define CPUFREQ_DEBUG_CORE 1 -#define CPUFREQ_DEBUG_DRIVER 2 -#define CPUFREQ_DEBUG_GOVERNOR 4 - -#ifdef CONFIG_CPU_FREQ_DEBUG - -extern void cpufreq_debug_printk(unsigned int type, const char *prefix, - const char *fmt, ...); - -#else - -#define cpufreq_debug_printk(msg...) do { } while(0) - -#endif /* CONFIG_CPU_FREQ_DEBUG */ - #endif /* _LINUX_CPUFREQ_H */ -- cgit v1.2.3-70-g09d2 From 335dc3335ff692173bc766b248f7a97f3a23b30a Mon Sep 17 00:00:00 2001 From: Thiago Farina Date: Thu, 28 Apr 2011 20:42:53 -0300 Subject: [CPUFREQ] cpufreq.h: Fix some checkpatch.pl coding style issues. Before: $ scripts/checkpatch.pl --file --terse include/linux/cpufreq.h total: 14 errors, 11 warnings, 419 lines checked After: $ scripts/checkpatch.pl --file --terse include/linux/cpufreq.h total: 2 errors, 4 warnings, 422 lines checked Signed-off-by: Thiago Farina Signed-off-by: Dave Jones --- include/linux/cpufreq.h | 33 ++++++++++++++++++--------------- 1 file changed, 18 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 2845f6e6722..11be48e0d16 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -3,7 +3,7 @@ * * Copyright (C) 2001 Russell King * (C) 2002 - 2003 Dominik Brodowski - * + * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. @@ -56,9 +56,9 @@ static inline int cpufreq_unregister_notifier(struct notifier_block *nb, #define CPUFREQ_POLICY_POWERSAVE (1) #define CPUFREQ_POLICY_PERFORMANCE (2) -/* Frequency values here are CPU kHz so that hardware which doesn't run - * with some frequencies can complain without having to guess what per - * cent / per mille means. +/* Frequency values here are CPU kHz so that hardware which doesn't run + * with some frequencies can complain without having to guess what per + * cent / per mille means. * Maximum transition latency is in nanoseconds - if it's unknown, * CPUFREQ_ETERNAL shall be used. */ @@ -72,13 +72,15 @@ extern struct kobject *cpufreq_global_kobject; struct cpufreq_cpuinfo { unsigned int max_freq; unsigned int min_freq; - unsigned int transition_latency; /* in 10^(-9) s = nanoseconds */ + + /* in 10^(-9) s = nanoseconds */ + unsigned int transition_latency; }; struct cpufreq_real_policy { unsigned int min; /* in kHz */ unsigned int max; /* in kHz */ - unsigned int policy; /* see above */ + unsigned int policy; /* see above */ struct cpufreq_governor *governor; /* see below */ }; @@ -94,7 +96,7 @@ struct cpufreq_policy { unsigned int max; /* in kHz */ unsigned int cur; /* in kHz, only needed if cpufreq * governors are used */ - unsigned int policy; /* see above */ + unsigned int policy; /* see above */ struct cpufreq_governor *governor; /* see below */ struct work_struct update; /* if update_policy() needs to be @@ -167,11 +169,11 @@ static inline unsigned long cpufreq_scale(unsigned long old, u_int div, u_int mu struct cpufreq_governor { char name[CPUFREQ_NAME_LEN]; - int (*governor) (struct cpufreq_policy *policy, + int (*governor) (struct cpufreq_policy *policy, unsigned int event); ssize_t (*show_setspeed) (struct cpufreq_policy *policy, char *buf); - int (*store_setspeed) (struct cpufreq_policy *policy, + int (*store_setspeed) (struct cpufreq_policy *policy, unsigned int freq); unsigned int max_transition_latency; /* HW must be able to switch to next freq faster than this value in nano secs or we @@ -180,7 +182,8 @@ struct cpufreq_governor { struct module *owner; }; -/* pass a target to the cpufreq driver +/* + * Pass a target to the cpufreq driver. */ extern int cpufreq_driver_target(struct cpufreq_policy *policy, unsigned int target_freq, @@ -237,9 +240,9 @@ struct cpufreq_driver { /* flags */ -#define CPUFREQ_STICKY 0x01 /* the driver isn't removed even if +#define CPUFREQ_STICKY 0x01 /* the driver isn't removed even if * all ->init() calls failed */ -#define CPUFREQ_CONST_LOOPS 0x02 /* loops_per_jiffy or other kernel +#define CPUFREQ_CONST_LOOPS 0x02 /* loops_per_jiffy or other kernel * "constants" aren't affected by * frequency transitions */ #define CPUFREQ_PM_NO_WARN 0x04 /* don't warn on suspend/resume speed @@ -252,7 +255,7 @@ int cpufreq_unregister_driver(struct cpufreq_driver *driver_data); void cpufreq_notify_transition(struct cpufreq_freqs *freqs, unsigned int state); -static inline void cpufreq_verify_within_limits(struct cpufreq_policy *policy, unsigned int min, unsigned int max) +static inline void cpufreq_verify_within_limits(struct cpufreq_policy *policy, unsigned int min, unsigned int max) { if (policy->min < min) policy->min = min; @@ -386,12 +389,12 @@ int cpufreq_frequency_table_target(struct cpufreq_policy *policy, /* the following 3 funtions are for cpufreq core use only */ struct cpufreq_frequency_table *cpufreq_frequency_get_table(unsigned int cpu); struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu); -void cpufreq_cpu_put (struct cpufreq_policy *data); +void cpufreq_cpu_put(struct cpufreq_policy *data); /* the following are really really optional */ extern struct freq_attr cpufreq_freq_attr_scaling_available_freqs; -void cpufreq_frequency_table_get_attr(struct cpufreq_frequency_table *table, +void cpufreq_frequency_table_get_attr(struct cpufreq_frequency_table *table, unsigned int cpu); void cpufreq_frequency_table_put_attr(unsigned int cpu); -- cgit v1.2.3-70-g09d2 From 30106b8ce2cc2243514116d6f29086e6deecc754 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 4 May 2011 15:38:19 +0200 Subject: slub: Fix the lockless code on 32-bit platforms with no 64-bit cmpxchg The SLUB allocator use of the cmpxchg_double logic was wrong: it actually needs the irq-safe one. That happens automatically when we use the native unlocked 'cmpxchg8b' instruction, but when compiling the kernel for older x86 CPUs that do not support that instruction, we fall back to the generic emulation code. And if you don't specify that you want the irq-safe version, the generic code ends up just open-coding the cmpxchg8b equivalent without any protection against interrupts or preemption. Which definitely doesn't work for SLUB. This was reported by Werner Landgraf , who saw instability with his distro-kernel that was compiled to support pretty much everything under the sun. Most big Linux distributions tend to compile for PPro and later, and would never have noticed this problem. This also fixes the prototypes for the irqsafe cmpxchg_double functions to use 'bool' like they should. [ Btw, that whole "generic code defaults to no protection" design just sounds stupid - if the code needs no protection, there is no reason to use "cmpxchg_double" to begin with. So we should probably just remove the unprotected version entirely as pointless. - Linus ] Signed-off-by: Thomas Gleixner Reported-and-tested-by: werner Acked-and-tested-by: Ingo Molnar Acked-by: Christoph Lameter Cc: Pekka Enberg Cc: Jens Axboe Cc: Tejun Heo Link: http://lkml.kernel.org/r/alpine.LFD.2.02.1105041539050.3005@ionos Signed-off-by: Ingo Molnar Signed-off-by: Linus Torvalds --- include/linux/percpu.h | 2 +- mm/slub.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 3a5c4449fd3..8b97308e65d 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -948,7 +948,7 @@ do { \ irqsafe_generic_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2) # endif # define irqsafe_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2) \ - __pcpu_double_call_return_int(irqsafe_cpu_cmpxchg_double_, (pcp1), (pcp2), (oval1), (oval2), (nval1), (nval2)) + __pcpu_double_call_return_bool(irqsafe_cpu_cmpxchg_double_, (pcp1), (pcp2), (oval1), (oval2), (nval1), (nval2)) #endif #endif /* __LINUX_PERCPU_H */ diff --git a/mm/slub.c b/mm/slub.c index 94d2a33a866..9d2e5e46bf0 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1940,7 +1940,7 @@ redo: * Since this is without lock semantics the protection is only against * code executing on this cpu *not* from access by other cpus. */ - if (unlikely(!this_cpu_cmpxchg_double( + if (unlikely(!irqsafe_cpu_cmpxchg_double( s->cpu_slab->freelist, s->cpu_slab->tid, object, tid, get_freepointer(s, object), next_tid(tid)))) { @@ -2145,7 +2145,7 @@ redo: set_freepointer(s, object, c->freelist); #ifdef CONFIG_CMPXCHG_LOCAL - if (unlikely(!this_cpu_cmpxchg_double( + if (unlikely(!irqsafe_cpu_cmpxchg_double( s->cpu_slab->freelist, s->cpu_slab->tid, c->freelist, tid, object, next_tid(tid)))) { -- cgit v1.2.3-70-g09d2 From a26ac2455ffcf3be5c6ef92bc6df7182700f2114 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 12 Jan 2011 14:10:23 -0800 Subject: rcu: move TREE_RCU from softirq to kthread If RCU priority boosting is to be meaningful, callback invocation must be boosted in addition to preempted RCU readers. Otherwise, in presence of CPU real-time threads, the grace period ends, but the callbacks don't get invoked. If the callbacks don't get invoked, the associated memory doesn't get freed, so the system is still subject to OOM. But it is not reasonable to priority-boost RCU_SOFTIRQ, so this commit moves the callback invocations to a kthread, which can be boosted easily. Also add comments and properly synchronized all accesses to rcu_cpu_kthread_task, as suggested by Lai Jiangshan. Signed-off-by: Paul E. McKenney Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- Documentation/filesystems/proc.txt | 1 - include/linux/interrupt.h | 1 - include/trace/events/irq.h | 3 +- kernel/rcutree.c | 340 +++++++++++++++++++++++++++++++++++- kernel/rcutree.h | 8 + kernel/rcutree_plugin.h | 4 +- kernel/softirq.c | 2 +- tools/perf/util/trace-event-parse.c | 1 - 8 files changed, 348 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index b0b814d75ca..60740e8ecb3 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -836,7 +836,6 @@ Provides counts of softirq handlers serviced since boot time, for each cpu. TASKLET: 0 0 0 290 SCHED: 27035 26983 26971 26746 HRTIMER: 0 0 0 0 - RCU: 1678 1769 2178 2250 1.3 IDE devices in /proc/ide diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index bea0ac75071..6c12989839d 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -414,7 +414,6 @@ enum TASKLET_SOFTIRQ, SCHED_SOFTIRQ, HRTIMER_SOFTIRQ, - RCU_SOFTIRQ, /* Preferable RCU should always be the last softirq */ NR_SOFTIRQS }; diff --git a/include/trace/events/irq.h b/include/trace/events/irq.h index 1c09820df58..ae045ca7d35 100644 --- a/include/trace/events/irq.h +++ b/include/trace/events/irq.h @@ -20,8 +20,7 @@ struct softirq_action; softirq_name(BLOCK_IOPOLL), \ softirq_name(TASKLET), \ softirq_name(SCHED), \ - softirq_name(HRTIMER), \ - softirq_name(RCU)) + softirq_name(HRTIMER)) /** * irq_handler_entry - called immediately before the irq action handler diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 0ac1cc03f93..18e33313873 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -47,6 +47,8 @@ #include #include #include +#include +#include #include "rcutree.h" @@ -82,6 +84,20 @@ DEFINE_PER_CPU(struct rcu_data, rcu_bh_data); int rcu_scheduler_active __read_mostly; EXPORT_SYMBOL_GPL(rcu_scheduler_active); +/* + * Control variables for per-CPU and per-rcu_node kthreads. These + * handle all flavors of RCU. + */ +static DEFINE_PER_CPU(struct task_struct *, rcu_cpu_kthread_task); +static DEFINE_PER_CPU(wait_queue_head_t, rcu_cpu_wq); +static DEFINE_PER_CPU(char, rcu_cpu_has_work); +static char rcu_kthreads_spawnable; + +static void rcu_node_kthread_setaffinity(struct rcu_node *rnp); +static void invoke_rcu_kthread(void); + +#define RCU_KTHREAD_PRIO 1 /* RT priority for per-CPU kthreads. */ + /* * Return true if an RCU grace period is in progress. The ACCESS_ONCE()s * permit this function to be invoked without holding the root rcu_node @@ -1009,6 +1025,8 @@ static void rcu_send_cbs_to_online(struct rcu_state *rsp) /* * Remove the outgoing CPU from the bitmasks in the rcu_node hierarchy * and move all callbacks from the outgoing CPU to the current one. + * There can only be one CPU hotplug operation at a time, so no other + * CPU can be attempting to update rcu_cpu_kthread_task. */ static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp) { @@ -1017,6 +1035,14 @@ static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp) int need_report = 0; struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); struct rcu_node *rnp; + struct task_struct *t; + + /* Stop the CPU's kthread. */ + t = per_cpu(rcu_cpu_kthread_task, cpu); + if (t != NULL) { + per_cpu(rcu_cpu_kthread_task, cpu) = NULL; + kthread_stop(t); + } /* Exclude any attempts to start a new grace period. */ raw_spin_lock_irqsave(&rsp->onofflock, flags); @@ -1054,6 +1080,19 @@ static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp) raw_spin_unlock_irqrestore(&rnp->lock, flags); if (need_report & RCU_OFL_TASKS_EXP_GP) rcu_report_exp_rnp(rsp, rnp); + + /* + * If there are no more online CPUs for this rcu_node structure, + * kill the rcu_node structure's kthread. Otherwise, adjust its + * affinity. + */ + t = rnp->node_kthread_task; + if (t != NULL && + rnp->qsmaskinit == 0) { + kthread_stop(t); + rnp->node_kthread_task = NULL; + } else + rcu_node_kthread_setaffinity(rnp); } /* @@ -1151,7 +1190,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp) /* Re-raise the RCU softirq if there are callbacks remaining. */ if (cpu_has_callbacks_ready_to_invoke(rdp)) - raise_softirq(RCU_SOFTIRQ); + invoke_rcu_kthread(); } /* @@ -1197,7 +1236,7 @@ void rcu_check_callbacks(int cpu, int user) } rcu_preempt_check_callbacks(cpu); if (rcu_pending(cpu)) - raise_softirq(RCU_SOFTIRQ); + invoke_rcu_kthread(); } #ifdef CONFIG_SMP @@ -1361,7 +1400,7 @@ __rcu_process_callbacks(struct rcu_state *rsp, struct rcu_data *rdp) /* * Do softirq processing for the current CPU. */ -static void rcu_process_callbacks(struct softirq_action *unused) +static void rcu_process_callbacks(void) { __rcu_process_callbacks(&rcu_sched_state, &__get_cpu_var(rcu_sched_data)); @@ -1372,6 +1411,281 @@ static void rcu_process_callbacks(struct softirq_action *unused) rcu_needs_cpu_flush(); } +/* + * Wake up the current CPU's kthread. This replaces raise_softirq() + * in earlier versions of RCU. Note that because we are running on + * the current CPU with interrupts disabled, the rcu_cpu_kthread_task + * cannot disappear out from under us. + */ +static void invoke_rcu_kthread(void) +{ + unsigned long flags; + wait_queue_head_t *q; + int cpu; + + local_irq_save(flags); + cpu = smp_processor_id(); + per_cpu(rcu_cpu_has_work, cpu) = 1; + if (per_cpu(rcu_cpu_kthread_task, cpu) == NULL) { + local_irq_restore(flags); + return; + } + q = &per_cpu(rcu_cpu_wq, cpu); + wake_up(q); + local_irq_restore(flags); +} + +/* + * Timer handler to initiate the waking up of per-CPU kthreads that + * have yielded the CPU due to excess numbers of RCU callbacks. + */ +static void rcu_cpu_kthread_timer(unsigned long arg) +{ + unsigned long flags; + struct rcu_data *rdp = (struct rcu_data *)arg; + struct rcu_node *rnp = rdp->mynode; + struct task_struct *t; + + raw_spin_lock_irqsave(&rnp->lock, flags); + rnp->wakemask |= rdp->grpmask; + t = rnp->node_kthread_task; + if (t == NULL) { + raw_spin_unlock_irqrestore(&rnp->lock, flags); + return; + } + wake_up_process(t); + raw_spin_unlock_irqrestore(&rnp->lock, flags); +} + +/* + * Drop to non-real-time priority and yield, but only after posting a + * timer that will cause us to regain our real-time priority if we + * remain preempted. Either way, we restore our real-time priority + * before returning. + */ +static void rcu_yield(int cpu) +{ + struct rcu_data *rdp = per_cpu_ptr(rcu_sched_state.rda, cpu); + struct sched_param sp; + struct timer_list yield_timer; + + setup_timer_on_stack(&yield_timer, rcu_cpu_kthread_timer, (unsigned long)rdp); + mod_timer(&yield_timer, jiffies + 2); + sp.sched_priority = 0; + sched_setscheduler_nocheck(current, SCHED_NORMAL, &sp); + schedule(); + sp.sched_priority = RCU_KTHREAD_PRIO; + sched_setscheduler_nocheck(current, SCHED_FIFO, &sp); + del_timer(&yield_timer); +} + +/* + * Handle cases where the rcu_cpu_kthread() ends up on the wrong CPU. + * This can happen while the corresponding CPU is either coming online + * or going offline. We cannot wait until the CPU is fully online + * before starting the kthread, because the various notifier functions + * can wait for RCU grace periods. So we park rcu_cpu_kthread() until + * the corresponding CPU is online. + * + * Return 1 if the kthread needs to stop, 0 otherwise. + * + * Caller must disable bh. This function can momentarily enable it. + */ +static int rcu_cpu_kthread_should_stop(int cpu) +{ + while (cpu_is_offline(cpu) || + !cpumask_equal(¤t->cpus_allowed, cpumask_of(cpu)) || + smp_processor_id() != cpu) { + if (kthread_should_stop()) + return 1; + local_bh_enable(); + schedule_timeout_uninterruptible(1); + if (!cpumask_equal(¤t->cpus_allowed, cpumask_of(cpu))) + set_cpus_allowed_ptr(current, cpumask_of(cpu)); + local_bh_disable(); + } + return 0; +} + +/* + * Per-CPU kernel thread that invokes RCU callbacks. This replaces the + * earlier RCU softirq. + */ +static int rcu_cpu_kthread(void *arg) +{ + int cpu = (int)(long)arg; + unsigned long flags; + int spincnt = 0; + wait_queue_head_t *wqp = &per_cpu(rcu_cpu_wq, cpu); + char work; + char *workp = &per_cpu(rcu_cpu_has_work, cpu); + + for (;;) { + wait_event_interruptible(*wqp, + *workp != 0 || kthread_should_stop()); + local_bh_disable(); + if (rcu_cpu_kthread_should_stop(cpu)) { + local_bh_enable(); + break; + } + local_irq_save(flags); + work = *workp; + *workp = 0; + local_irq_restore(flags); + if (work) + rcu_process_callbacks(); + local_bh_enable(); + if (*workp != 0) + spincnt++; + else + spincnt = 0; + if (spincnt > 10) { + rcu_yield(cpu); + spincnt = 0; + } + } + return 0; +} + +/* + * Spawn a per-CPU kthread, setting up affinity and priority. + * Because the CPU hotplug lock is held, no other CPU will be attempting + * to manipulate rcu_cpu_kthread_task. There might be another CPU + * attempting to access it during boot, but the locking in kthread_bind() + * will enforce sufficient ordering. + */ +static int __cpuinit rcu_spawn_one_cpu_kthread(int cpu) +{ + struct sched_param sp; + struct task_struct *t; + + if (!rcu_kthreads_spawnable || + per_cpu(rcu_cpu_kthread_task, cpu) != NULL) + return 0; + t = kthread_create(rcu_cpu_kthread, (void *)(long)cpu, "rcuc%d", cpu); + if (IS_ERR(t)) + return PTR_ERR(t); + kthread_bind(t, cpu); + WARN_ON_ONCE(per_cpu(rcu_cpu_kthread_task, cpu) != NULL); + per_cpu(rcu_cpu_kthread_task, cpu) = t; + wake_up_process(t); + sp.sched_priority = RCU_KTHREAD_PRIO; + sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); + return 0; +} + +/* + * Per-rcu_node kthread, which is in charge of waking up the per-CPU + * kthreads when needed. We ignore requests to wake up kthreads + * for offline CPUs, which is OK because force_quiescent_state() + * takes care of this case. + */ +static int rcu_node_kthread(void *arg) +{ + int cpu; + unsigned long flags; + unsigned long mask; + struct rcu_node *rnp = (struct rcu_node *)arg; + struct sched_param sp; + struct task_struct *t; + + for (;;) { + wait_event_interruptible(rnp->node_wq, rnp->wakemask != 0 || + kthread_should_stop()); + if (kthread_should_stop()) + break; + raw_spin_lock_irqsave(&rnp->lock, flags); + mask = rnp->wakemask; + rnp->wakemask = 0; + raw_spin_unlock_irqrestore(&rnp->lock, flags); + for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask >>= 1) { + if ((mask & 0x1) == 0) + continue; + preempt_disable(); + t = per_cpu(rcu_cpu_kthread_task, cpu); + if (!cpu_online(cpu) || t == NULL) { + preempt_enable(); + continue; + } + per_cpu(rcu_cpu_has_work, cpu) = 1; + sp.sched_priority = RCU_KTHREAD_PRIO; + sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); + preempt_enable(); + } + } + return 0; +} + +/* + * Set the per-rcu_node kthread's affinity to cover all CPUs that are + * served by the rcu_node in question. + */ +static void rcu_node_kthread_setaffinity(struct rcu_node *rnp) +{ + cpumask_var_t cm; + int cpu; + unsigned long mask = rnp->qsmaskinit; + + if (rnp->node_kthread_task == NULL || + rnp->qsmaskinit == 0) + return; + if (!alloc_cpumask_var(&cm, GFP_KERNEL)) + return; + cpumask_clear(cm); + for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask >>= 1) + if (mask & 0x1) + cpumask_set_cpu(cpu, cm); + set_cpus_allowed_ptr(rnp->node_kthread_task, cm); + free_cpumask_var(cm); +} + +/* + * Spawn a per-rcu_node kthread, setting priority and affinity. + */ +static int __cpuinit rcu_spawn_one_node_kthread(struct rcu_state *rsp, + struct rcu_node *rnp) +{ + int rnp_index = rnp - &rsp->node[0]; + struct sched_param sp; + struct task_struct *t; + + if (!rcu_kthreads_spawnable || + rnp->qsmaskinit == 0 || + rnp->node_kthread_task != NULL) + return 0; + t = kthread_create(rcu_node_kthread, (void *)rnp, "rcun%d", rnp_index); + if (IS_ERR(t)) + return PTR_ERR(t); + rnp->node_kthread_task = t; + wake_up_process(t); + sp.sched_priority = 99; + sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); + return 0; +} + +/* + * Spawn all kthreads -- called as soon as the scheduler is running. + */ +static int __init rcu_spawn_kthreads(void) +{ + int cpu; + struct rcu_node *rnp; + + rcu_kthreads_spawnable = 1; + for_each_possible_cpu(cpu) { + init_waitqueue_head(&per_cpu(rcu_cpu_wq, cpu)); + per_cpu(rcu_cpu_has_work, cpu) = 0; + if (cpu_online(cpu)) + (void)rcu_spawn_one_cpu_kthread(cpu); + } + rcu_for_each_leaf_node(&rcu_sched_state, rnp) { + init_waitqueue_head(&rnp->node_wq); + (void)rcu_spawn_one_node_kthread(&rcu_sched_state, rnp); + } + return 0; +} +early_initcall(rcu_spawn_kthreads); + static void __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), struct rcu_state *rsp) @@ -1771,6 +2085,19 @@ static void __cpuinit rcu_online_cpu(int cpu) rcu_preempt_init_percpu_data(cpu); } +static void __cpuinit rcu_online_kthreads(int cpu) +{ + struct rcu_data *rdp = per_cpu_ptr(rcu_sched_state.rda, cpu); + struct rcu_node *rnp = rdp->mynode; + + /* Fire up the incoming CPU's kthread and leaf rcu_node kthread. */ + if (rcu_kthreads_spawnable) { + (void)rcu_spawn_one_cpu_kthread(cpu); + if (rnp->node_kthread_task == NULL) + (void)rcu_spawn_one_node_kthread(&rcu_sched_state, rnp); + } +} + /* * Handle CPU online/offline notification events. */ @@ -1778,11 +2105,17 @@ static int __cpuinit rcu_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) { long cpu = (long)hcpu; + struct rcu_data *rdp = per_cpu_ptr(rcu_sched_state.rda, cpu); + struct rcu_node *rnp = rdp->mynode; switch (action) { case CPU_UP_PREPARE: case CPU_UP_PREPARE_FROZEN: rcu_online_cpu(cpu); + rcu_online_kthreads(cpu); + break; + case CPU_ONLINE: + rcu_node_kthread_setaffinity(rnp); break; case CPU_DYING: case CPU_DYING_FROZEN: @@ -1923,7 +2256,6 @@ void __init rcu_init(void) rcu_init_one(&rcu_sched_state, &rcu_sched_data); rcu_init_one(&rcu_bh_state, &rcu_bh_data); __rcu_init_preempt(); - open_softirq(RCU_SOFTIRQ, rcu_process_callbacks); /* * We don't need protection against CPU-hotplug here because diff --git a/kernel/rcutree.h b/kernel/rcutree.h index 5a439c180e6..c0213802d16 100644 --- a/kernel/rcutree.h +++ b/kernel/rcutree.h @@ -111,6 +111,7 @@ struct rcu_node { /* elements that need to drain to allow the */ /* current expedited grace period to */ /* complete (only for TREE_PREEMPT_RCU). */ + unsigned long wakemask; /* CPUs whose kthread needs to be awakened. */ unsigned long qsmaskinit; /* Per-GP initial value for qsmask & expmask. */ unsigned long grpmask; /* Mask to apply to parent qsmask. */ @@ -134,6 +135,13 @@ struct rcu_node { /* if there is no such task. If there */ /* is no current expedited grace period, */ /* then there can cannot be any such task. */ + struct task_struct *node_kthread_task; + /* kthread that takes care of this rcu_node */ + /* structure, for example, awakening the */ + /* per-CPU kthreads as needed. */ + wait_queue_head_t node_wq; + /* Wait queue on which to park the per-node */ + /* kthread. */ } ____cacheline_internodealigned_in_smp; /* diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index 774f010a461..b9bd69a5a4f 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -1206,7 +1206,7 @@ static DEFINE_PER_CPU(unsigned long, rcu_dyntick_holdoff); * * Because it is not legal to invoke rcu_process_callbacks() with irqs * disabled, we do one pass of force_quiescent_state(), then do a - * raise_softirq() to cause rcu_process_callbacks() to be invoked later. + * invoke_rcu_kthread() to cause rcu_process_callbacks() to be invoked later. * The per-cpu rcu_dyntick_drain variable controls the sequencing. */ int rcu_needs_cpu(int cpu) @@ -1257,7 +1257,7 @@ int rcu_needs_cpu(int cpu) /* If RCU callbacks are still pending, RCU still needs this CPU. */ if (c) - raise_softirq(RCU_SOFTIRQ); + invoke_rcu_kthread(); return c; } diff --git a/kernel/softirq.c b/kernel/softirq.c index 174f976c287..13960170cad 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -58,7 +58,7 @@ DEFINE_PER_CPU(struct task_struct *, ksoftirqd); char *softirq_to_name[NR_SOFTIRQS] = { "HI", "TIMER", "NET_TX", "NET_RX", "BLOCK", "BLOCK_IOPOLL", - "TASKLET", "SCHED", "HRTIMER", "RCU" + "TASKLET", "SCHED", "HRTIMER" }; /* diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c index 0a7ed5b5e28..1e88485c16a 100644 --- a/tools/perf/util/trace-event-parse.c +++ b/tools/perf/util/trace-event-parse.c @@ -2187,7 +2187,6 @@ static const struct flag flags[] = { { "TASKLET_SOFTIRQ", 6 }, { "SCHED_SOFTIRQ", 7 }, { "HRTIMER_SOFTIRQ", 8 }, - { "RCU_SOFTIRQ", 9 }, { "HRTIMER_NORESTART", 0 }, { "HRTIMER_RESTART", 1 }, -- cgit v1.2.3-70-g09d2 From 4a29865689dbb87a02e3b0fff4a4ae5041273173 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sun, 3 Apr 2011 21:33:51 -0700 Subject: rcu: make rcutorture version numbers available through debugfs It is not possible to accurately correlate rcutorture output with that of debugfs. This patch therefore adds a debugfs file that prints out the rcutorture version number, permitting easy correlation. Signed-off-by: Paul E. McKenney Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- include/linux/rcupdate.h | 13 ++++++++++++- include/linux/rcutree.h | 3 +++ kernel/rcutorture.c | 8 +++++--- kernel/rcutree.c | 37 +++++++++++++++++++++++++++++++++++++ kernel/rcutree_trace.c | 28 ++++++++++++++++++++++++++++ 5 files changed, 85 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index ff422d2b7f9..9e169c2ba91 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -47,6 +47,18 @@ extern int rcutorture_runnable; /* for sysctl */ #endif /* #ifdef CONFIG_RCU_TORTURE_TEST */ +#if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU) +extern void rcutorture_record_test_transition(void); +extern void rcutorture_record_progress(unsigned long vernum); +#else +static inline void rcutorture_record_test_transition(void) +{ +} +static inline void rcutorture_record_progress(unsigned long vernum) +{ +} +#endif + #define UINT_CMP_GE(a, b) (UINT_MAX / 2 >= (a) - (b)) #define UINT_CMP_LT(a, b) (UINT_MAX / 2 < (a) - (b)) #define ULONG_CMP_GE(a, b) (ULONG_MAX / 2 >= (a) - (b)) @@ -68,7 +80,6 @@ extern void call_rcu_sched(struct rcu_head *head, extern void synchronize_sched(void); extern void rcu_barrier_bh(void); extern void rcu_barrier_sched(void); -extern int sched_expedited_torture_stats(char *page); static inline void __rcu_read_lock_bh(void) { diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 3a933482734..284dad10c55 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -58,9 +58,12 @@ static inline void synchronize_rcu_bh_expedited(void) extern void rcu_barrier(void); +extern unsigned long rcutorture_testseq; +extern unsigned long rcutorture_vernum; extern long rcu_batches_completed(void); extern long rcu_batches_completed_bh(void); extern long rcu_batches_completed_sched(void); + extern void rcu_force_quiescent_state(void); extern void rcu_bh_force_quiescent_state(void); extern void rcu_sched_force_quiescent_state(void); diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c index 22b0e74e7d9..c2f58ec2475 100644 --- a/kernel/rcutorture.c +++ b/kernel/rcutorture.c @@ -131,7 +131,7 @@ struct rcu_torture { static LIST_HEAD(rcu_torture_freelist); static struct rcu_torture __rcu *rcu_torture_current; -static long rcu_torture_current_version; +static unsigned long rcu_torture_current_version; static struct rcu_torture rcu_tortures[10 * RCU_TORTURE_PIPE_LEN]; static DEFINE_SPINLOCK(rcu_torture_lock); static DEFINE_PER_CPU(long [RCU_TORTURE_PIPE_LEN + 1], rcu_torture_count) = @@ -884,7 +884,7 @@ rcu_torture_writer(void *arg) old_rp->rtort_pipe_count++; cur_ops->deferred_free(old_rp); } - rcu_torture_current_version++; + rcutorture_record_progress(++rcu_torture_current_version); oldbatch = cur_ops->completed(); rcu_stutter_wait("rcu_torture_writer"); } while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP); @@ -1064,7 +1064,7 @@ rcu_torture_printk(char *page) } cnt += sprintf(&page[cnt], "%s%s ", torture_type, TORTURE_FLAG); cnt += sprintf(&page[cnt], - "rtc: %p ver: %ld tfle: %d rta: %d rtaf: %d rtf: %d " + "rtc: %p ver: %lu tfle: %d rta: %d rtaf: %d rtf: %d " "rtmbe: %d rtbke: %ld rtbre: %ld " "rtbf: %ld rtb: %ld nt: %ld", rcu_torture_current, @@ -1325,6 +1325,7 @@ rcu_torture_cleanup(void) int i; mutex_lock(&fullstop_mutex); + rcutorture_record_test_transition(); if (fullstop == FULLSTOP_SHUTDOWN) { printk(KERN_WARNING /* but going down anyway, so... */ "Concurrent 'rmmod rcutorture' and shutdown illegal!\n"); @@ -1616,6 +1617,7 @@ rcu_torture_init(void) } } register_reboot_notifier(&rcutorture_shutdown_nb); + rcutorture_record_test_transition(); mutex_unlock(&fullstop_mutex); return 0; diff --git a/kernel/rcutree.c b/kernel/rcutree.c index d8917401cbb..bb84deca331 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -101,6 +101,18 @@ static void invoke_rcu_cpu_kthread(void); #define RCU_KTHREAD_PRIO 1 /* RT priority for per-CPU kthreads. */ +/* + * Track the rcutorture test sequence number and the update version + * number within a given test. The rcutorture_testseq is incremented + * on every rcutorture module load and unload, so has an odd value + * when a test is running. The rcutorture_vernum is set to zero + * when rcutorture starts and is incremented on each rcutorture update. + * These variables enable correlating rcutorture output with the + * RCU tracing information. + */ +unsigned long rcutorture_testseq; +unsigned long rcutorture_vernum; + /* * Return true if an RCU grace period is in progress. The ACCESS_ONCE()s * permit this function to be invoked without holding the root rcu_node @@ -192,6 +204,31 @@ void rcu_bh_force_quiescent_state(void) } EXPORT_SYMBOL_GPL(rcu_bh_force_quiescent_state); +/* + * Record the number of times rcutorture tests have been initiated and + * terminated. This information allows the debugfs tracing stats to be + * correlated to the rcutorture messages, even when the rcutorture module + * is being repeatedly loaded and unloaded. In other words, we cannot + * store this state in rcutorture itself. + */ +void rcutorture_record_test_transition(void) +{ + rcutorture_testseq++; + rcutorture_vernum = 0; +} +EXPORT_SYMBOL_GPL(rcutorture_record_test_transition); + +/* + * Record the number of writer passes through the current rcutorture test. + * This is also used to correlate debugfs tracing stats with the rcutorture + * messages. + */ +void rcutorture_record_progress(unsigned long vernum) +{ + rcutorture_vernum++; +} +EXPORT_SYMBOL_GPL(rcutorture_record_progress); + /* * Force a quiescent state for RCU-sched. */ diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c index fc40e89a028..3baa235786b 100644 --- a/kernel/rcutree_trace.c +++ b/kernel/rcutree_trace.c @@ -394,6 +394,29 @@ static const struct file_operations rcu_pending_fops = { .release = single_release, }; +static int show_rcutorture(struct seq_file *m, void *unused) +{ + seq_printf(m, "rcutorture test sequence: %lu %s\n", + rcutorture_testseq >> 1, + (rcutorture_testseq & 0x1) ? "(test in progress)" : ""); + seq_printf(m, "rcutorture update version number: %lu\n", + rcutorture_vernum); + return 0; +} + +static int rcutorture_open(struct inode *inode, struct file *file) +{ + return single_open(file, show_rcutorture, NULL); +} + +static const struct file_operations rcutorture_fops = { + .owner = THIS_MODULE, + .open = rcutorture_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + static struct dentry *rcudir; static int __init rcutree_trace_init(void) @@ -430,6 +453,11 @@ static int __init rcutree_trace_init(void) NULL, &rcu_pending_fops); if (!retval) goto free_out; + + retval = debugfs_create_file("rcutorture", 0444, rcudir, + NULL, &rcutorture_fops); + if (!retval) + goto free_out; return 0; free_out: debugfs_remove_recursive(rcudir); -- cgit v1.2.3-70-g09d2 From b0c9d7ff2793502650ad987c3f237d5fe5587a1e Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 29 Mar 2011 12:56:56 -0700 Subject: rcu: add DEBUG_OBJECTS_RCU_HEAD check for alignment Verify that rcu_head structures are aligned to a four-byte boundary. This check is enabled by CONFIG_DEBUG_OBJECTS_RCU_HEAD. Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- include/linux/rcupdate.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 9e169c2ba91..c7aeacf7fc9 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -785,6 +785,7 @@ extern struct debug_obj_descr rcuhead_debug_descr; static inline void debug_rcu_head_queue(struct rcu_head *head) { + WARN_ON_ONCE((unsigned long)head & 0x3); debug_object_activate(head, &rcuhead_debug_descr); debug_object_active_state(head, &rcuhead_debug_descr, STATE_RCU_HEAD_READY, -- cgit v1.2.3-70-g09d2 From 9ab1544eb4196ca8d05c433b2eb56f74496b1ee3 Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Fri, 18 Mar 2011 11:15:47 +0800 Subject: rcu: introduce kfree_rcu() Many rcu callbacks functions just call kfree() on the base structure. These functions are trivial, but their size adds up, and furthermore when they are used in a kernel module, that module must invoke the high-latency rcu_barrier() function at module-unload time. The kfree_rcu() function introduced by this commit addresses this issue. Rather than encoding a function address in the embedded rcu_head structure, kfree_rcu() instead encodes the offset of the rcu_head structure within the base structure. Because the functions are not allowed in the low-order 4096 bytes of kernel virtual memory, offsets up to 4095 bytes can be accommodated. If the offset is larger than 4095 bytes, a compile-time error will be generated in __kfree_rcu(). If this error is triggered, you can either fall back to use of call_rcu() or rearrange the structure to position the rcu_head structure into the first 4096 bytes. Note that the allowable offset might decrease in the future, for example, to allow something like kmem_cache_free_rcu(). The new kfree_rcu() function can replace code as follows: call_rcu(&p->rcu, simple_kfree_callback); where "simple_kfree_callback()" might be defined as follows: void simple_kfree_callback(struct rcu_head *p) { struct foo *q = container_of(p, struct foo, rcu); kfree(q); } with the following: kfree_rcu(&p->rcu, rcu); Note that the "rcu" is the name of a field in the structure being freed. The reason for using this rather than passing in a pointer to the base structure is that the above approach allows better type checking. This commit is based on earlier work by Lai Jiangshan and Manfred Spraul: Lai's V1 patch: http://lkml.org/lkml/2008/9/18/1 Manfred's patch: http://lkml.org/lkml/2009/1/2/115 Signed-off-by: Lai Jiangshan Signed-off-by: Manfred Spraul Signed-off-by: Paul E. McKenney Reviewed-by: David Howells Reviewed-by: Josh Triplett --- include/linux/rcupdate.h | 56 ++++++++++++++++++++++++++++++++++++++++++++++++ kernel/rcutiny.c | 2 +- kernel/rcutree.c | 2 +- 3 files changed, 58 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index c7aeacf7fc9..99f9aa7c280 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -809,4 +809,60 @@ static inline void debug_rcu_head_unqueue(struct rcu_head *head) } #endif /* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ +static __always_inline bool __is_kfree_rcu_offset(unsigned long offset) +{ + return offset < 4096; +} + +static __always_inline +void __kfree_rcu(struct rcu_head *head, unsigned long offset) +{ + typedef void (*rcu_callback)(struct rcu_head *); + + BUILD_BUG_ON(!__builtin_constant_p(offset)); + + /* See the kfree_rcu() header comment. */ + BUILD_BUG_ON(!__is_kfree_rcu_offset(offset)); + + call_rcu(head, (rcu_callback)offset); +} + +extern void kfree(const void *); + +static inline void __rcu_reclaim(struct rcu_head *head) +{ + unsigned long offset = (unsigned long)head->func; + + if (__is_kfree_rcu_offset(offset)) + kfree((void *)head - offset); + else + head->func(head); +} + +/** + * kfree_rcu() - kfree an object after a grace period. + * @ptr: pointer to kfree + * @rcu_head: the name of the struct rcu_head within the type of @ptr. + * + * Many rcu callbacks functions just call kfree() on the base structure. + * These functions are trivial, but their size adds up, and furthermore + * when they are used in a kernel module, that module must invoke the + * high-latency rcu_barrier() function at module-unload time. + * + * The kfree_rcu() function handles this issue. Rather than encoding a + * function address in the embedded rcu_head structure, kfree_rcu() instead + * encodes the offset of the rcu_head structure within the base structure. + * Because the functions are not allowed in the low-order 4096 bytes of + * kernel virtual memory, offsets up to 4095 bytes can be accommodated. + * If the offset is larger than 4095 bytes, a compile-time error will + * be generated in __kfree_rcu(). If this error is triggered, you can + * either fall back to use of call_rcu() or rearrange the structure to + * position the rcu_head structure into the first 4096 bytes. + * + * Note that the allowable offset might decrease in the future, for example, + * to allow something like kmem_cache_free_rcu(). + */ +#define kfree_rcu(ptr, rcu_head) \ + __kfree_rcu(&((ptr)->rcu_head), offsetof(typeof(*(ptr)), rcu_head)) + #endif /* __LINUX_RCUPDATE_H */ diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c index 0c343b9a46d..4d60fbc9c64 100644 --- a/kernel/rcutiny.c +++ b/kernel/rcutiny.c @@ -167,7 +167,7 @@ static void rcu_process_callbacks(struct rcu_ctrlblk *rcp) prefetch(next); debug_rcu_head_unqueue(list); local_bh_disable(); - list->func(list); + __rcu_reclaim(list); local_bh_enable(); list = next; RCU_TRACE(cb_count++); diff --git a/kernel/rcutree.c b/kernel/rcutree.c index b579e4f9721..2c07adb9708 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -1206,7 +1206,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp) next = list->next; prefetch(next); debug_rcu_head_unqueue(list); - list->func(list); + __rcu_reclaim(list); list = next; if (++count >= rdp->blimit) break; -- cgit v1.2.3-70-g09d2 From 29ce831000081dd757d3116bf774aafffc4b6b20 Mon Sep 17 00:00:00 2001 From: Gleb Natapov Date: Wed, 4 May 2011 16:31:03 +0300 Subject: rcu: provide rcu_virt_note_context_switch() function. Provide rcu_virt_note_context_switch() for vitalization use to note quiescent state during guest entry. Signed-off-by: Gleb Natapov Signed-off-by: Paul E. McKenney --- include/linux/rcutiny.h | 8 ++++++++ include/linux/rcutree.h | 10 ++++++++++ kernel/rcutree.c | 1 + 3 files changed, 19 insertions(+) (limited to 'include') diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 30ebd7c8d87..52b3e0281fd 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -99,6 +99,14 @@ static inline void rcu_note_context_switch(int cpu) rcu_preempt_note_context_switch(); } +/* + * Take advantage of the fact that there is only one CPU, which + * allows us to ignore virtualization-based context switches. + */ +static inline void rcu_virt_note_context_switch(int cpu) +{ +} + /* * Return the number of grace periods. */ diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 284dad10c55..e65d06634dd 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -35,6 +35,16 @@ extern void rcu_note_context_switch(int cpu); extern int rcu_needs_cpu(int cpu); extern void rcu_cpu_stall_reset(void); +/* + * Note a virtualization-based context switch. This is simply a + * wrapper around rcu_note_context_switch(), which allows TINY_RCU + * to save a few bytes. + */ +static inline void rcu_virt_note_context_switch(int cpu) +{ + rcu_note_context_switch(cpu); +} + #ifdef CONFIG_TREE_PREEMPT_RCU extern void exit_rcu(void); diff --git a/kernel/rcutree.c b/kernel/rcutree.c index b2fe2a273df..54ff7eb9281 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -157,6 +157,7 @@ void rcu_note_context_switch(int cpu) rcu_sched_qs(cpu); rcu_preempt_note_context_switch(cpu); } +EXPORT_SYMBOL_GPL(rcu_note_context_switch); #ifdef CONFIG_NO_HZ DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = { -- cgit v1.2.3-70-g09d2 From a3a4a5acd3bd2f6f1e102e1f1b9d2e2bb320a7fd Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Thu, 5 May 2011 23:55:18 -0400 Subject: Regression: partial revert "tracing: Remove lock_depth from event entry" This partially reverts commit e6e1e2593592a8f6f6380496655d8c6f67431266. That commit changed the structure layout of the trace structure, which in turn broke PowerTOP (1.9x generation) quite badly. I appreciate not wanting to expose the variable in question, and PowerTOP was not using it, so I've replaced the variable with just a padding field - that way if in the future a new field is needed it can just use this padding field. Signed-off-by: Arjan van de Ven Signed-off-by: Linus Torvalds --- include/linux/ftrace_event.h | 1 + kernel/trace/trace.c | 1 + kernel/trace/trace_events.c | 1 + 3 files changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 22b32af1b5e..b5a550a39a7 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -37,6 +37,7 @@ struct trace_entry { unsigned char flags; unsigned char preempt_count; int pid; + int padding; }; #define FTRACE_MAX_EVENT \ diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index d38c16a06a6..1cb49be7c7f 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1110,6 +1110,7 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags, entry->preempt_count = pc & 0xff; entry->pid = (tsk) ? tsk->pid : 0; + entry->padding = 0; entry->flags = #ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT (irqs_disabled_flags(flags) ? TRACE_FLAG_IRQS_OFF : 0) | diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index e88f74fe1d4..2fe11034135 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -116,6 +116,7 @@ static int trace_define_common_fields(void) __common_field(unsigned char, flags); __common_field(unsigned char, preempt_count); __common_field(int, pid); + __common_field(int, padding); return ret; } -- cgit v1.2.3-70-g09d2 From 880ffb5c6c5c8c8c6efd9efe9355317322b4603b Mon Sep 17 00:00:00 2001 From: Wanlong Gao Date: Thu, 5 May 2011 07:55:36 +0800 Subject: driver core: Add the device driver-model structures to kerneldoc Add the comments to the structure bus_type, device_driver, device, class to device.h for generating the driver-model kerneldoc. With another patch these all removed from the files in Documentation/driver-model/ since they are out of date. That will keep things up to date and provide a better way to document this stuff. Signed-off-by: Wanlong Gao Acked-by: Harry Wei Signed-off-by: Greg Kroah-Hartman --- Documentation/DocBook/device-drivers.tmpl | 6 +- include/linux/device.h | 154 +++++++++++++++++++++++++++++- 2 files changed, 154 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/Documentation/DocBook/device-drivers.tmpl b/Documentation/DocBook/device-drivers.tmpl index 36f63d4a0a0..b638e50cf8f 100644 --- a/Documentation/DocBook/device-drivers.tmpl +++ b/Documentation/DocBook/device-drivers.tmpl @@ -96,10 +96,10 @@ X!Iinclude/linux/kobject.h Device drivers infrastructure + The Basic Device Driver-Model Structures +!Iinclude/linux/device.h + Device Drivers Base - !Edrivers/base/driver.c !Edrivers/base/core.c !Edrivers/base/class.c diff --git a/include/linux/device.h b/include/linux/device.h index 2215d013ca9..42365067a83 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -47,6 +47,38 @@ extern int __must_check bus_create_file(struct bus_type *, struct bus_attribute *); extern void bus_remove_file(struct bus_type *, struct bus_attribute *); +/** + * struct bus_type - The bus type of the device + * + * @name: The name of the bus. + * @bus_attrs: Default attributes of the bus. + * @dev_attrs: Default attributes of the devices on the bus. + * @drv_attrs: Default attributes of the device drivers on the bus. + * @match: Called, perhaps multiple times, whenever a new device or driver + * is added for this bus. It should return a nonzero value if the + * given device can be handled by the given driver. + * @uevent: Called when a device is added, removed, or a few other things + * that generate uevents to add the environment variables. + * @probe: Called when a new device or driver add to this bus, and callback + * the specific driver's probe to initial the matched device. + * @remove: Called when a device removed from this bus. + * @shutdown: Called at shut-down time to quiesce the device. + * @suspend: Called when a device on this bus wants to go to sleep mode. + * @resume: Called to bring a device on this bus out of sleep mode. + * @pm: Power management operations of this bus, callback the specific + * device driver's pm-ops. + * @p: The private data of the driver core, only the driver core can + * touch this. + * + * A bus is a channel between the processor and one or more devices. For the + * purposes of the device model, all devices are connected via a bus, even if + * it is an internal, virtual, "platform" bus. Buses can plug into each other. + * A USB controller is usually a PCI device, for example. The device model + * represents the actual connections between buses and the devices they control. + * A bus is represented by the bus_type structure. It contains the name, the + * default attributes, the bus' methods, PM operations, and the driver core's + * private data. + */ struct bus_type { const char *name; struct bus_attribute *bus_attrs; @@ -119,6 +151,37 @@ extern int bus_unregister_notifier(struct bus_type *bus, extern struct kset *bus_get_kset(struct bus_type *bus); extern struct klist *bus_get_device_klist(struct bus_type *bus); +/** + * struct device_driver - The basic device driver structure + * @name: Name of the device driver. + * @bus: The bus which the device of this driver belongs to. + * @owner: The module owner. + * @mod_name: Used for built-in modules. + * @suppress_bind_attrs: Disables bind/unbind via sysfs. + * @of_match_table: The open firmware table. + * @probe: Called to query the existence of a specific device, + * whether this driver can work with it, and bind the driver + * to a specific device. + * @remove: Called when the device is removed from the system to + * unbind a device from this driver. + * @shutdown: Called at shut-down time to quiesce the device. + * @suspend: Called to put the device to sleep mode. Usually to a + * low power state. + * @resume: Called to bring a device from sleep mode. + * @groups: Default attributes that get created by the driver core + * automatically. + * @pm: Power management operations of the device which matched + * this driver. + * @p: Driver core's private data, no one other than the driver + * core can touch this. + * + * The device driver-model tracks all of the drivers known to the system. + * The main reason for this tracking is to enable the driver core to match + * up drivers with new devices. Once drivers are known objects within the + * system, however, a number of other things become possible. Device drivers + * can export information and configuration variables that are independent + * of any specific device. + */ struct device_driver { const char *name; struct bus_type *bus; @@ -185,8 +248,34 @@ struct device *driver_find_device(struct device_driver *drv, struct device *start, void *data, int (*match)(struct device *dev, void *data)); -/* - * device classes +/** + * struct class - device classes + * @name: Name of the class. + * @owner: The module owner. + * @class_attrs: Default attributes of this class. + * @dev_attrs: Default attributes of the devices belong to the class. + * @dev_bin_attrs: Default binary attributes of the devices belong to the class. + * @dev_kobj: The kobject that represents this class and links it into the hierarchy. + * @dev_uevent: Called when a device is added, removed from this class, or a + * few other things that generate uevents to add the environment + * variables. + * @devnode: Callback to provide the devtmpfs. + * @class_release: Called to release this class. + * @dev_release: Called to release the device. + * @suspend: Used to put the device to sleep mode, usually to a low power + * state. + * @resume: Used to bring the device from the sleep mode. + * @ns_type: Callbacks so sysfs can detemine namespaces. + * @namespace: Namespace of the device belongs to this class. + * @pm: The default device power management operations of this class. + * @p: The private data of the driver core, no one other than the + * driver core can touch this. + * + * A class is a higher-level view of a device that abstracts out low-level + * implementation details. Drivers may see a SCSI disk or an ATA disk, but, + * at the class level, they are all simply disks. Classes allow user space + * to work with devices based on what they do, rather than how they are + * connected or how they work. */ struct class { const char *name; @@ -401,6 +490,65 @@ struct device_dma_parameters { unsigned long segment_boundary_mask; }; +/** + * struct device - The basic device structure + * @parent: The device's "parent" device, the device to which it is attached. + * In most cases, a parent device is some sort of bus or host + * controller. If parent is NULL, the device, is a top-level device, + * which is not usually what you want. + * @p: Holds the private data of the driver core portions of the device. + * See the comment of the struct device_private for detail. + * @kobj: A top-level, abstract class from which other classes are derived. + * @init_name: Initial name of the device. + * @type: The type of device. + * This identifies the device type and carries type-specific + * information. + * @mutex: Mutex to synchronize calls to its driver. + * @bus: Type of bus device is on. + * @driver: Which driver has allocated this + * @platform_data: Platform data specific to the device. + * Example: For devices on custom boards, as typical of embedded + * and SOC based hardware, Linux often uses platform_data to point + * to board-specific structures describing devices and how they + * are wired. That can include what ports are available, chip + * variants, which GPIO pins act in what additional roles, and so + * on. This shrinks the "Board Support Packages" (BSPs) and + * minimizes board-specific #ifdefs in drivers. + * @power: For device power management. + * See Documentation/power/devices.txt for details. + * @pwr_domain: Provide callbacks that are executed during system suspend, + * hibernation, system resume and during runtime PM transitions + * along with subsystem-level and driver-level callbacks. + * @numa_node: NUMA node this device is close to. + * @dma_mask: Dma mask (if dma'ble device). + * @coherent_dma_mask: Like dma_mask, but for alloc_coherent mapping as not all + * hardware supports 64-bit addresses for consistent allocations + * such descriptors. + * @dma_parms: A low level driver may set these to teach IOMMU code about + * segment limitations. + * @dma_pools: Dma pools (if dma'ble device). + * @dma_mem: Internal for coherent mem override. + * @archdata: For arch-specific additions. + * @of_node: Associated device tree node. + * @of_match: Matching of_device_id from driver. + * @devt: For creating the sysfs "dev". + * @devres_lock: Spinlock to protect the resource of the device. + * @devres_head: The resources list of the device. + * @knode_class: The node used to add the device to the class list. + * @class: The class of the device. + * @groups: Optional attribute groups. + * @release: Callback to free the device after all references have + * gone away. This should be set by the allocator of the + * device (i.e. the bus driver that discovered the device). + * + * At the lowest level, every device in a Linux system is represented by an + * instance of struct device. The device structure contains the information + * that the device model core needs to model the system. Most subsystems, + * however, track additional information about the devices they host. As a + * result, it is rare for devices to be represented by bare device structures; + * instead, that structure, like kobject structures, is usually embedded within + * a higher-level representation of the device. + */ struct device { struct device *parent; @@ -611,7 +759,7 @@ extern int (*platform_notify)(struct device *dev); extern int (*platform_notify_remove)(struct device *dev); -/** +/* * get_device - atomically increment the reference count for the device. * */ -- cgit v1.2.3-70-g09d2 From 1231f0baa547a541a7481119323b7f964dda4788 Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Tue, 15 Mar 2011 18:05:02 +0800 Subject: net,rcu: convert call_rcu(sctp_local_addr_free) to kfree_rcu() The rcu callback sctp_local_addr_free() just calls a kfree(), so we use kfree_rcu() instead of the call_rcu(sctp_local_addr_free). Signed-off-by: Lai Jiangshan Acked-by: David S. Miller Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- include/net/sctp/sctp.h | 1 - net/sctp/bind_addr.c | 2 +- net/sctp/ipv6.c | 2 +- net/sctp/protocol.c | 9 +-------- 4 files changed, 3 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index 505845ddb0b..01e094c6d0a 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -115,7 +115,6 @@ * sctp/protocol.c */ extern struct sock *sctp_get_ctl_sock(void); -extern void sctp_local_addr_free(struct rcu_head *head); extern int sctp_copy_local_addr_list(struct sctp_bind_addr *, sctp_scope_t, gfp_t gfp, int flags); diff --git a/net/sctp/bind_addr.c b/net/sctp/bind_addr.c index faf71d179e4..3c06c87cd28 100644 --- a/net/sctp/bind_addr.c +++ b/net/sctp/bind_addr.c @@ -219,7 +219,7 @@ int sctp_del_bind_addr(struct sctp_bind_addr *bp, union sctp_addr *del_addr) } if (found) { - call_rcu(&addr->rcu, sctp_local_addr_free); + kfree_rcu(addr, rcu); SCTP_DBG_OBJCNT_DEC(addr); return 0; } diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 865ce7ba4e1..185fe058db1 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -123,7 +123,7 @@ static int sctp_inet6addr_event(struct notifier_block *this, unsigned long ev, } spin_unlock_bh(&sctp_local_addr_lock); if (found) - call_rcu(&addr->rcu, sctp_local_addr_free); + kfree_rcu(addr, rcu); break; } diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index d5bf91d04f6..065d99958ce 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -230,13 +230,6 @@ static void sctp_free_local_addr_list(void) } } -void sctp_local_addr_free(struct rcu_head *head) -{ - struct sctp_sockaddr_entry *e = container_of(head, - struct sctp_sockaddr_entry, rcu); - kfree(e); -} - /* Copy the local addresses which are valid for 'scope' into 'bp'. */ int sctp_copy_local_addr_list(struct sctp_bind_addr *bp, sctp_scope_t scope, gfp_t gfp, int copy_flags) @@ -681,7 +674,7 @@ static int sctp_inetaddr_event(struct notifier_block *this, unsigned long ev, } spin_unlock_bh(&sctp_local_addr_lock); if (found) - call_rcu(&addr->rcu, sctp_local_addr_free); + kfree_rcu(addr, rcu); break; } -- cgit v1.2.3-70-g09d2 From 2bbd4492552867053b5a618a2474297e2b1c355d Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Fri, 6 May 2011 23:47:53 +0200 Subject: drm: mm: fix debug output The looping helper didn't do anything due to a superficial semicolon. Furthermore one of the two dump functions suffered from copy&paste fail. While staring at the code I've also noticed that the replace helper (currently unused) is a bit broken. Signed-off-by: Daniel Vetter Signed-off-by: Dave Airlie --- drivers/gpu/drm/drm_mm.c | 6 +++--- include/drm/drm_mm.h | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_mm.c b/drivers/gpu/drm/drm_mm.c index 5d00b0fc0d9..959186cbf32 100644 --- a/drivers/gpu/drm/drm_mm.c +++ b/drivers/gpu/drm/drm_mm.c @@ -431,7 +431,7 @@ EXPORT_SYMBOL(drm_mm_search_free_in_range); void drm_mm_replace_node(struct drm_mm_node *old, struct drm_mm_node *new) { list_replace(&old->node_list, &new->node_list); - list_replace(&old->node_list, &new->hole_stack); + list_replace(&old->hole_stack, &new->hole_stack); new->hole_follows = old->hole_follows; new->mm = old->mm; new->start = old->start; @@ -699,8 +699,8 @@ int drm_mm_dump_table(struct seq_file *m, struct drm_mm *mm) entry->size); total_used += entry->size; if (entry->hole_follows) { - hole_start = drm_mm_hole_node_start(&mm->head_node); - hole_end = drm_mm_hole_node_end(&mm->head_node); + hole_start = drm_mm_hole_node_start(entry); + hole_end = drm_mm_hole_node_end(entry); hole_size = hole_end - hole_start; seq_printf(m, "0x%08lx-0x%08lx: 0x%08lx: free\n", hole_start, hole_end, hole_size); diff --git a/include/drm/drm_mm.h b/include/drm/drm_mm.h index c2f93a8ae2e..564b14aa7e1 100644 --- a/include/drm/drm_mm.h +++ b/include/drm/drm_mm.h @@ -86,7 +86,7 @@ static inline bool drm_mm_initialized(struct drm_mm *mm) } #define drm_mm_for_each_node(entry, mm) list_for_each_entry(entry, \ &(mm)->head_node.node_list, \ - node_list); + node_list) #define drm_mm_for_each_scanned_node_reverse(entry, n, mm) \ for (entry = (mm)->prev_scanned_node, \ next = entry ? list_entry(entry->node_list.next, \ -- cgit v1.2.3-70-g09d2 From a09a79f66874c905af35d5bb5e5f2fdc7b6b894d Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Mon, 9 May 2011 13:01:09 +0200 Subject: Don't lock guardpage if the stack is growing up Linux kernel excludes guard page when performing mlock on a VMA with down-growing stack. However, some architectures have up-growing stack and locking the guard page should be excluded in this case too. This patch fixes lvm2 on PA-RISC (and possibly other architectures with up-growing stack). lvm2 calculates number of used pages when locking and when unlocking and reports an internal error if the numbers mismatch. [ Patch changed fairly extensively to also fix /proc//maps for the grows-up case, and to move things around a bit to clean it all up and share the infrstructure with the /proc bits. Tested on ia64 that has both grow-up and grow-down segments - Linus ] Signed-off-by: Mikulas Patocka Tested-by: Tony Luck Cc: stable@kernel.org Signed-off-by: Linus Torvalds --- fs/proc/task_mmu.c | 12 +++++++----- include/linux/mm.h | 24 +++++++++++++++++++++++- mm/memory.c | 16 +++++++--------- 3 files changed, 37 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 2e7addfd980..318d8654989 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -214,7 +214,7 @@ static void show_map_vma(struct seq_file *m, struct vm_area_struct *vma) int flags = vma->vm_flags; unsigned long ino = 0; unsigned long long pgoff = 0; - unsigned long start; + unsigned long start, end; dev_t dev = 0; int len; @@ -227,13 +227,15 @@ static void show_map_vma(struct seq_file *m, struct vm_area_struct *vma) /* We don't show the stack guard page in /proc/maps */ start = vma->vm_start; - if (vma->vm_flags & VM_GROWSDOWN) - if (!vma_stack_continue(vma->vm_prev, vma->vm_start)) - start += PAGE_SIZE; + if (stack_guard_page_start(vma, start)) + start += PAGE_SIZE; + end = vma->vm_end; + if (stack_guard_page_end(vma, end)) + end -= PAGE_SIZE; seq_printf(m, "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu %n", start, - vma->vm_end, + end, flags & VM_READ ? 'r' : '-', flags & VM_WRITE ? 'w' : '-', flags & VM_EXEC ? 'x' : '-', diff --git a/include/linux/mm.h b/include/linux/mm.h index 2348db26bc3..6507dde38b1 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1011,11 +1011,33 @@ int set_page_dirty_lock(struct page *page); int clear_page_dirty_for_io(struct page *page); /* Is the vma a continuation of the stack vma above it? */ -static inline int vma_stack_continue(struct vm_area_struct *vma, unsigned long addr) +static inline int vma_growsdown(struct vm_area_struct *vma, unsigned long addr) { return vma && (vma->vm_end == addr) && (vma->vm_flags & VM_GROWSDOWN); } +static inline int stack_guard_page_start(struct vm_area_struct *vma, + unsigned long addr) +{ + return (vma->vm_flags & VM_GROWSDOWN) && + (vma->vm_start == addr) && + !vma_growsdown(vma->vm_prev, addr); +} + +/* Is the vma a continuation of the stack vma below it? */ +static inline int vma_growsup(struct vm_area_struct *vma, unsigned long addr) +{ + return vma && (vma->vm_start == addr) && (vma->vm_flags & VM_GROWSUP); +} + +static inline int stack_guard_page_end(struct vm_area_struct *vma, + unsigned long addr) +{ + return (vma->vm_flags & VM_GROWSUP) && + (vma->vm_end == addr) && + !vma_growsup(vma->vm_next, addr); +} + extern unsigned long move_page_tables(struct vm_area_struct *vma, unsigned long old_addr, struct vm_area_struct *new_vma, unsigned long new_addr, unsigned long len); diff --git a/mm/memory.c b/mm/memory.c index 27f42537811..61e66f02656 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1412,9 +1412,8 @@ no_page_table: static inline int stack_guard_page(struct vm_area_struct *vma, unsigned long addr) { - return (vma->vm_flags & VM_GROWSDOWN) && - (vma->vm_start == addr) && - !vma_stack_continue(vma->vm_prev, addr); + return stack_guard_page_start(vma, addr) || + stack_guard_page_end(vma, addr+PAGE_SIZE); } /** @@ -1551,12 +1550,6 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, continue; } - /* - * For mlock, just skip the stack guard page. - */ - if ((gup_flags & FOLL_MLOCK) && stack_guard_page(vma, start)) - goto next_page; - do { struct page *page; unsigned int foll_flags = gup_flags; @@ -1573,6 +1566,11 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, int ret; unsigned int fault_flags = 0; + /* For mlock, just skip the stack guard page. */ + if (foll_flags & FOLL_MLOCK) { + if (stack_guard_page(vma, start)) + goto next_page; + } if (foll_flags & FOLL_WRITE) fault_flags |= FAULT_FLAG_WRITE; if (nonblocking) -- cgit v1.2.3-70-g09d2 From a9bb79128aa659f97b774b97c9bb1bdc74444595 Mon Sep 17 00:00:00 2001 From: "Hefty, Sean" Date: Mon, 9 May 2011 22:06:10 -0700 Subject: RDMA/cma: Add an ID_REUSEADDR option Lustre requires that clients bind to a privileged port number before connecting to a remote server. On larger clusters (typically more than about 1000 nodes), the number of privileged ports is exhausted, resulting in lustre being unusable. To handle this, we add support for reusable addresses to the rdma_cm. This mimics the behavior of the socket option SO_REUSEADDR. A user may set an rdma_cm_id to reuse an address before calling rdma_bind_addr() (explicitly or implicitly). If set, other rdma_cm_id's may be bound to the same address, provided that they all have reuse enabled, and there are no active listens. If rdma_listen() is called on an rdma_cm_id that has reuse enabled, it will only succeed if there are no other id's bound to that same address. The reuse option is exported to user space. The behavior of the kernel reuse implementation was verified against that given by sockets. This patch is derived from a path by Ira Weiny Signed-off-by: Sean Hefty Signed-off-by: Roland Dreier --- drivers/infiniband/core/cma.c | 190 ++++++++++++++++++++++++++--------------- drivers/infiniband/core/ucma.c | 7 ++ include/rdma/rdma_cm.h | 10 +++ include/rdma/rdma_user_cm.h | 5 +- 4 files changed, 143 insertions(+), 69 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index eff5e46f005..99dde874fbb 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -148,6 +148,7 @@ struct rdma_id_private { u32 qp_num; u8 srq; u8 tos; + u8 reuseaddr; }; struct cma_multicast { @@ -1579,50 +1580,6 @@ static void cma_listen_on_all(struct rdma_id_private *id_priv) mutex_unlock(&lock); } -int rdma_listen(struct rdma_cm_id *id, int backlog) -{ - struct rdma_id_private *id_priv; - int ret; - - id_priv = container_of(id, struct rdma_id_private, id); - if (id_priv->state == CMA_IDLE) { - ((struct sockaddr *) &id->route.addr.src_addr)->sa_family = AF_INET; - ret = rdma_bind_addr(id, (struct sockaddr *) &id->route.addr.src_addr); - if (ret) - return ret; - } - - if (!cma_comp_exch(id_priv, CMA_ADDR_BOUND, CMA_LISTEN)) - return -EINVAL; - - id_priv->backlog = backlog; - if (id->device) { - switch (rdma_node_get_transport(id->device->node_type)) { - case RDMA_TRANSPORT_IB: - ret = cma_ib_listen(id_priv); - if (ret) - goto err; - break; - case RDMA_TRANSPORT_IWARP: - ret = cma_iw_listen(id_priv, backlog); - if (ret) - goto err; - break; - default: - ret = -ENOSYS; - goto err; - } - } else - cma_listen_on_all(id_priv); - - return 0; -err: - id_priv->backlog = 0; - cma_comp_exch(id_priv, CMA_LISTEN, CMA_ADDR_BOUND); - return ret; -} -EXPORT_SYMBOL(rdma_listen); - void rdma_set_service_type(struct rdma_cm_id *id, int tos) { struct rdma_id_private *id_priv; @@ -2105,6 +2062,25 @@ err: } EXPORT_SYMBOL(rdma_resolve_addr); +int rdma_set_reuseaddr(struct rdma_cm_id *id, int reuse) +{ + struct rdma_id_private *id_priv; + unsigned long flags; + int ret; + + id_priv = container_of(id, struct rdma_id_private, id); + spin_lock_irqsave(&id_priv->lock, flags); + if (id_priv->state == CMA_IDLE) { + id_priv->reuseaddr = reuse; + ret = 0; + } else { + ret = -EINVAL; + } + spin_unlock_irqrestore(&id_priv->lock, flags); + return ret; +} +EXPORT_SYMBOL(rdma_set_reuseaddr); + static void cma_bind_port(struct rdma_bind_list *bind_list, struct rdma_id_private *id_priv) { @@ -2180,43 +2156,73 @@ retry: return -EADDRNOTAVAIL; } -static int cma_use_port(struct idr *ps, struct rdma_id_private *id_priv) +/* + * Check that the requested port is available. This is called when trying to + * bind to a specific port, or when trying to listen on a bound port. In + * the latter case, the provided id_priv may already be on the bind_list, but + * we still need to check that it's okay to start listening. + */ +static int cma_check_port(struct rdma_bind_list *bind_list, + struct rdma_id_private *id_priv, uint8_t reuseaddr) { struct rdma_id_private *cur_id; struct sockaddr *addr, *cur_addr; - struct rdma_bind_list *bind_list; struct hlist_node *node; - unsigned short snum; addr = (struct sockaddr *) &id_priv->id.route.addr.src_addr; - snum = ntohs(cma_port(addr)); - if (snum < PROT_SOCK && !capable(CAP_NET_BIND_SERVICE)) - return -EACCES; - - bind_list = idr_find(ps, snum); - if (!bind_list) - return cma_alloc_port(ps, id_priv, snum); - - /* - * We don't support binding to any address if anyone is bound to - * a specific address on the same port. - */ - if (cma_any_addr(addr)) + if (cma_any_addr(addr) && !reuseaddr) return -EADDRNOTAVAIL; hlist_for_each_entry(cur_id, node, &bind_list->owners, node) { - cur_addr = (struct sockaddr *) &cur_id->id.route.addr.src_addr; - if (cma_any_addr(cur_addr)) - return -EADDRNOTAVAIL; + if (id_priv == cur_id) + continue; - if (!cma_addr_cmp(addr, cur_addr)) - return -EADDRINUSE; - } + if ((cur_id->state == CMA_LISTEN) || + !reuseaddr || !cur_id->reuseaddr) { + cur_addr = (struct sockaddr *) &cur_id->id.route.addr.src_addr; + if (cma_any_addr(cur_addr)) + return -EADDRNOTAVAIL; - cma_bind_port(bind_list, id_priv); + if (!cma_addr_cmp(addr, cur_addr)) + return -EADDRINUSE; + } + } return 0; } +static int cma_use_port(struct idr *ps, struct rdma_id_private *id_priv) +{ + struct rdma_bind_list *bind_list; + unsigned short snum; + int ret; + + snum = ntohs(cma_port((struct sockaddr *) &id_priv->id.route.addr.src_addr)); + if (snum < PROT_SOCK && !capable(CAP_NET_BIND_SERVICE)) + return -EACCES; + + bind_list = idr_find(ps, snum); + if (!bind_list) { + ret = cma_alloc_port(ps, id_priv, snum); + } else { + ret = cma_check_port(bind_list, id_priv, id_priv->reuseaddr); + if (!ret) + cma_bind_port(bind_list, id_priv); + } + return ret; +} + +static int cma_bind_listen(struct rdma_id_private *id_priv) +{ + struct rdma_bind_list *bind_list = id_priv->bind_list; + int ret = 0; + + mutex_lock(&lock); + if (bind_list->owners.first->next) + ret = cma_check_port(bind_list, id_priv, 0); + mutex_unlock(&lock); + return ret; +} + static int cma_get_port(struct rdma_id_private *id_priv) { struct idr *ps; @@ -2268,6 +2274,56 @@ static int cma_check_linklocal(struct rdma_dev_addr *dev_addr, return 0; } +int rdma_listen(struct rdma_cm_id *id, int backlog) +{ + struct rdma_id_private *id_priv; + int ret; + + id_priv = container_of(id, struct rdma_id_private, id); + if (id_priv->state == CMA_IDLE) { + ((struct sockaddr *) &id->route.addr.src_addr)->sa_family = AF_INET; + ret = rdma_bind_addr(id, (struct sockaddr *) &id->route.addr.src_addr); + if (ret) + return ret; + } + + if (!cma_comp_exch(id_priv, CMA_ADDR_BOUND, CMA_LISTEN)) + return -EINVAL; + + if (id_priv->reuseaddr) { + ret = cma_bind_listen(id_priv); + if (ret) + goto err; + } + + id_priv->backlog = backlog; + if (id->device) { + switch (rdma_node_get_transport(id->device->node_type)) { + case RDMA_TRANSPORT_IB: + ret = cma_ib_listen(id_priv); + if (ret) + goto err; + break; + case RDMA_TRANSPORT_IWARP: + ret = cma_iw_listen(id_priv, backlog); + if (ret) + goto err; + break; + default: + ret = -ENOSYS; + goto err; + } + } else + cma_listen_on_all(id_priv); + + return 0; +err: + id_priv->backlog = 0; + cma_comp_exch(id_priv, CMA_LISTEN, CMA_ADDR_BOUND); + return ret; +} +EXPORT_SYMBOL(rdma_listen); + int rdma_bind_addr(struct rdma_cm_id *id, struct sockaddr *addr) { struct rdma_id_private *id_priv; diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c index ec1e9da1488..b3fa798525b 100644 --- a/drivers/infiniband/core/ucma.c +++ b/drivers/infiniband/core/ucma.c @@ -883,6 +883,13 @@ static int ucma_set_option_id(struct ucma_context *ctx, int optname, } rdma_set_service_type(ctx->cm_id, *((u8 *) optval)); break; + case RDMA_OPTION_ID_REUSEADDR: + if (optlen != sizeof(int)) { + ret = -EINVAL; + break; + } + ret = rdma_set_reuseaddr(ctx->cm_id, *((int *) optval) ? 1 : 0); + break; default: ret = -ENOSYS; } diff --git a/include/rdma/rdma_cm.h b/include/rdma/rdma_cm.h index 4fae9030464..169f7a53fb0 100644 --- a/include/rdma/rdma_cm.h +++ b/include/rdma/rdma_cm.h @@ -329,4 +329,14 @@ void rdma_leave_multicast(struct rdma_cm_id *id, struct sockaddr *addr); */ void rdma_set_service_type(struct rdma_cm_id *id, int tos); +/** + * rdma_set_reuseaddr - Allow the reuse of local addresses when binding + * the rdma_cm_id. + * @id: Communication identifier to configure. + * @reuse: Value indicating if the bound address is reusable. + * + * Reuse must be set before an address is bound to the id. + */ +int rdma_set_reuseaddr(struct rdma_cm_id *id, int reuse); + #endif /* RDMA_CM_H */ diff --git a/include/rdma/rdma_user_cm.h b/include/rdma/rdma_user_cm.h index 1d165022c02..fc82c1896f7 100644 --- a/include/rdma/rdma_user_cm.h +++ b/include/rdma/rdma_user_cm.h @@ -221,8 +221,9 @@ enum { /* Option details */ enum { - RDMA_OPTION_ID_TOS = 0, - RDMA_OPTION_IB_PATH = 1 + RDMA_OPTION_ID_TOS = 0, + RDMA_OPTION_ID_REUSEADDR = 1, + RDMA_OPTION_IB_PATH = 1 }; struct rdma_ucm_set_option { -- cgit v1.2.3-70-g09d2 From d0c49bf391b2e230a8f3ae4486da7df440f1216d Mon Sep 17 00:00:00 2001 From: Roland Dreier Date: Mon, 9 May 2011 22:23:57 -0700 Subject: RDMA/iwcm: Get rid of enum iw_cm_event_status The IW_CM_EVENT_STATUS_xxx values were used in only a couple of places; cma.c uses -Exxx values instead, and so do the amso1100, cxgb3 and cxgb4 drivers -- only nes was using the enum values (with the mild consequence that all nes connection failures were treated as generic errors rather than reported as timeouts or rejections). We can fix this confusion by getting rid of enum iw_cm_event_status and using a plain int for struct iw_cm_event.status, and converting nes to use -Exxx as the other iWARP drivers do. This also gets rid of the warning drivers/infiniband/core/cma.c: In function 'cma_iw_handler': drivers/infiniband/core/cma.c:1333:3: warning: case value '4294967185' not in enumerated type 'enum iw_cm_event_status' drivers/infiniband/core/cma.c:1336:3: warning: case value '4294967186' not in enumerated type 'enum iw_cm_event_status' drivers/infiniband/core/cma.c:1332:3: warning: case value '4294967192' not in enumerated type 'enum iw_cm_event_status' Signed-off-by: Roland Dreier Reviewed-by: Steve Wise Reviewed-by: Sean Hefty Reviewed-by: Faisal Latif --- drivers/infiniband/core/iwcm.c | 2 +- drivers/infiniband/hw/nes/nes_cm.c | 16 ++++++++-------- drivers/infiniband/hw/nes/nes_verbs.c | 2 +- include/rdma/iw_cm.h | 11 +---------- 4 files changed, 11 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/core/iwcm.c b/drivers/infiniband/core/iwcm.c index 2a1e9ae134b..a9c042345c6 100644 --- a/drivers/infiniband/core/iwcm.c +++ b/drivers/infiniband/core/iwcm.c @@ -725,7 +725,7 @@ static int cm_conn_rep_handler(struct iwcm_id_private *cm_id_priv, */ clear_bit(IWCM_F_CONNECT_WAIT, &cm_id_priv->flags); BUG_ON(cm_id_priv->state != IW_CM_STATE_CONN_SENT); - if (iw_event->status == IW_CM_EVENT_STATUS_ACCEPTED) { + if (iw_event->status == 0) { cm_id_priv->id.local_addr = iw_event->local_addr; cm_id_priv->id.remote_addr = iw_event->remote_addr; cm_id_priv->state = IW_CM_STATE_ESTABLISHED; diff --git a/drivers/infiniband/hw/nes/nes_cm.c b/drivers/infiniband/hw/nes/nes_cm.c index 33c7eedaba6..e74cdf9ef47 100644 --- a/drivers/infiniband/hw/nes/nes_cm.c +++ b/drivers/infiniband/hw/nes/nes_cm.c @@ -2563,7 +2563,7 @@ static int nes_cm_disconn_true(struct nes_qp *nesqp) u16 last_ae; u8 original_hw_tcp_state; u8 original_ibqp_state; - enum iw_cm_event_status disconn_status = IW_CM_EVENT_STATUS_OK; + int disconn_status = 0; int issue_disconn = 0; int issue_close = 0; int issue_flush = 0; @@ -2605,7 +2605,7 @@ static int nes_cm_disconn_true(struct nes_qp *nesqp) (last_ae == NES_AEQE_AEID_LLP_CONNECTION_RESET))) { issue_disconn = 1; if (last_ae == NES_AEQE_AEID_LLP_CONNECTION_RESET) - disconn_status = IW_CM_EVENT_STATUS_RESET; + disconn_status = -ECONNRESET; } if (((original_hw_tcp_state == NES_AEQE_TCP_STATE_CLOSED) || @@ -2666,7 +2666,7 @@ static int nes_cm_disconn_true(struct nes_qp *nesqp) cm_id->provider_data = nesqp; /* Send up the close complete event */ cm_event.event = IW_CM_EVENT_CLOSE; - cm_event.status = IW_CM_EVENT_STATUS_OK; + cm_event.status = 0; cm_event.provider_data = cm_id->provider_data; cm_event.local_addr = cm_id->local_addr; cm_event.remote_addr = cm_id->remote_addr; @@ -2966,7 +2966,7 @@ int nes_accept(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) nes_add_ref(&nesqp->ibqp); cm_event.event = IW_CM_EVENT_ESTABLISHED; - cm_event.status = IW_CM_EVENT_STATUS_ACCEPTED; + cm_event.status = 0; cm_event.provider_data = (void *)nesqp; cm_event.local_addr = cm_id->local_addr; cm_event.remote_addr = cm_id->remote_addr; @@ -3377,7 +3377,7 @@ static void cm_event_connected(struct nes_cm_event *event) /* notify OF layer we successfully created the requested connection */ cm_event.event = IW_CM_EVENT_CONNECT_REPLY; - cm_event.status = IW_CM_EVENT_STATUS_ACCEPTED; + cm_event.status = 0; cm_event.provider_data = cm_id->provider_data; cm_event.local_addr.sin_family = AF_INET; cm_event.local_addr.sin_port = cm_id->local_addr.sin_port; @@ -3484,7 +3484,7 @@ static void cm_event_reset(struct nes_cm_event *event) nesqp->cm_id = NULL; /* cm_id->provider_data = NULL; */ cm_event.event = IW_CM_EVENT_DISCONNECT; - cm_event.status = IW_CM_EVENT_STATUS_RESET; + cm_event.status = -ECONNRESET; cm_event.provider_data = cm_id->provider_data; cm_event.local_addr = cm_id->local_addr; cm_event.remote_addr = cm_id->remote_addr; @@ -3495,7 +3495,7 @@ static void cm_event_reset(struct nes_cm_event *event) ret = cm_id->event_handler(cm_id, &cm_event); atomic_inc(&cm_closes); cm_event.event = IW_CM_EVENT_CLOSE; - cm_event.status = IW_CM_EVENT_STATUS_OK; + cm_event.status = 0; cm_event.provider_data = cm_id->provider_data; cm_event.local_addr = cm_id->local_addr; cm_event.remote_addr = cm_id->remote_addr; @@ -3534,7 +3534,7 @@ static void cm_event_mpa_req(struct nes_cm_event *event) cm_node, cm_id, jiffies); cm_event.event = IW_CM_EVENT_CONNECT_REQUEST; - cm_event.status = IW_CM_EVENT_STATUS_OK; + cm_event.status = 0; cm_event.provider_data = (void *)cm_node; cm_event.local_addr.sin_family = AF_INET; diff --git a/drivers/infiniband/hw/nes/nes_verbs.c b/drivers/infiniband/hw/nes/nes_verbs.c index 26d8018c0a7..95ca93ceeda 100644 --- a/drivers/infiniband/hw/nes/nes_verbs.c +++ b/drivers/infiniband/hw/nes/nes_verbs.c @@ -1484,7 +1484,7 @@ static int nes_destroy_qp(struct ib_qp *ibqp) (nesqp->ibqp_state == IB_QPS_RTR)) && (nesqp->cm_id)) { cm_id = nesqp->cm_id; cm_event.event = IW_CM_EVENT_CONNECT_REPLY; - cm_event.status = IW_CM_EVENT_STATUS_TIMEOUT; + cm_event.status = -ETIMEDOUT; cm_event.local_addr = cm_id->local_addr; cm_event.remote_addr = cm_id->remote_addr; cm_event.private_data = NULL; diff --git a/include/rdma/iw_cm.h b/include/rdma/iw_cm.h index cbb822e8d79..2d0191c90f9 100644 --- a/include/rdma/iw_cm.h +++ b/include/rdma/iw_cm.h @@ -46,18 +46,9 @@ enum iw_cm_event_type { IW_CM_EVENT_CLOSE /* close complete */ }; -enum iw_cm_event_status { - IW_CM_EVENT_STATUS_OK = 0, /* request successful */ - IW_CM_EVENT_STATUS_ACCEPTED = 0, /* connect request accepted */ - IW_CM_EVENT_STATUS_REJECTED, /* connect request rejected */ - IW_CM_EVENT_STATUS_TIMEOUT, /* the operation timed out */ - IW_CM_EVENT_STATUS_RESET, /* reset from remote peer */ - IW_CM_EVENT_STATUS_EINVAL, /* asynchronous failure for bad parm */ -}; - struct iw_cm_event { enum iw_cm_event_type event; - enum iw_cm_event_status status; + int status; struct sockaddr_in local_addr; struct sockaddr_in remote_addr; void *private_data; -- cgit v1.2.3-70-g09d2 From 7a4f0761fce32ff4918a7c23b08db564ad33092d Mon Sep 17 00:00:00 2001 From: Hans Schillstrom Date: Tue, 3 May 2011 22:09:31 +0200 Subject: IPVS: init and cleanup restructuring DESCRIPTION This patch tries to restore the initial init and cleanup sequences that was before namspace patch. Netns also requires action when net devices unregister which has never been implemented. I.e this patch also covers when a device moves into a network namespace, and has to be released. IMPLEMENTATION The number of calls to register_pernet_device have been reduced to one for the ip_vs.ko Schedulers still have their own calls. This patch adds a function __ip_vs_service_cleanup() and an enable flag for the netfilter hooks. The nf hooks will be enabled when the first service is loaded and never disabled again, except when a namespace exit starts. Signed-off-by: Hans Schillstrom Acked-by: Julian Anastasov [horms@verge.net.au: minor edit to changelog] Signed-off-by: Simon Horman --- include/net/ip_vs.h | 17 ++++++ net/netfilter/ipvs/ip_vs_app.c | 15 +---- net/netfilter/ipvs/ip_vs_conn.c | 12 +--- net/netfilter/ipvs/ip_vs_core.c | 101 +++++++++++++++++++++++++++++--- net/netfilter/ipvs/ip_vs_ctl.c | 120 ++++++++++++++++++++++++++++++++------- net/netfilter/ipvs/ip_vs_est.c | 14 +---- net/netfilter/ipvs/ip_vs_proto.c | 11 +--- net/netfilter/ipvs/ip_vs_sync.c | 13 +---- 8 files changed, 223 insertions(+), 80 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index d516f00c8e0..86aefed6140 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -791,6 +791,7 @@ struct ip_vs_app { /* IPVS in network namespace */ struct netns_ipvs { int gen; /* Generation */ + int enable; /* enable like nf_hooks do */ /* * Hash table: for real service lookups */ @@ -1089,6 +1090,22 @@ ip_vs_control_add(struct ip_vs_conn *cp, struct ip_vs_conn *ctl_cp) atomic_inc(&ctl_cp->n_control); } +/* + * IPVS netns init & cleanup functions + */ +extern int __ip_vs_estimator_init(struct net *net); +extern int __ip_vs_control_init(struct net *net); +extern int __ip_vs_protocol_init(struct net *net); +extern int __ip_vs_app_init(struct net *net); +extern int __ip_vs_conn_init(struct net *net); +extern int __ip_vs_sync_init(struct net *net); +extern void __ip_vs_conn_cleanup(struct net *net); +extern void __ip_vs_app_cleanup(struct net *net); +extern void __ip_vs_protocol_cleanup(struct net *net); +extern void __ip_vs_control_cleanup(struct net *net); +extern void __ip_vs_estimator_cleanup(struct net *net); +extern void __ip_vs_sync_cleanup(struct net *net); +extern void __ip_vs_service_cleanup(struct net *net); /* * IPVS application functions diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c index 2dc6de13ac1..51f3af7c474 100644 --- a/net/netfilter/ipvs/ip_vs_app.c +++ b/net/netfilter/ipvs/ip_vs_app.c @@ -576,7 +576,7 @@ static const struct file_operations ip_vs_app_fops = { }; #endif -static int __net_init __ip_vs_app_init(struct net *net) +int __net_init __ip_vs_app_init(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); @@ -585,26 +585,17 @@ static int __net_init __ip_vs_app_init(struct net *net) return 0; } -static void __net_exit __ip_vs_app_cleanup(struct net *net) +void __net_exit __ip_vs_app_cleanup(struct net *net) { proc_net_remove(net, "ip_vs_app"); } -static struct pernet_operations ip_vs_app_ops = { - .init = __ip_vs_app_init, - .exit = __ip_vs_app_cleanup, -}; - int __init ip_vs_app_init(void) { - int rv; - - rv = register_pernet_subsys(&ip_vs_app_ops); - return rv; + return 0; } void ip_vs_app_cleanup(void) { - unregister_pernet_subsys(&ip_vs_app_ops); } diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index c97bd45975b..d3fd91bbba4 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -1258,22 +1258,17 @@ int __net_init __ip_vs_conn_init(struct net *net) return 0; } -static void __net_exit __ip_vs_conn_cleanup(struct net *net) +void __net_exit __ip_vs_conn_cleanup(struct net *net) { /* flush all the connection entries first */ ip_vs_conn_flush(net); proc_net_remove(net, "ip_vs_conn"); proc_net_remove(net, "ip_vs_conn_sync"); } -static struct pernet_operations ipvs_conn_ops = { - .init = __ip_vs_conn_init, - .exit = __ip_vs_conn_cleanup, -}; int __init ip_vs_conn_init(void) { int idx; - int retc; /* Compute size and mask */ ip_vs_conn_tab_size = 1 << ip_vs_conn_tab_bits; @@ -1309,17 +1304,14 @@ int __init ip_vs_conn_init(void) rwlock_init(&__ip_vs_conntbl_lock_array[idx].l); } - retc = register_pernet_subsys(&ipvs_conn_ops); - /* calculate the random value for connection hash */ get_random_bytes(&ip_vs_conn_rnd, sizeof(ip_vs_conn_rnd)); - return retc; + return 0; } void ip_vs_conn_cleanup(void) { - unregister_pernet_subsys(&ipvs_conn_ops); /* Release the empty cache */ kmem_cache_destroy(ip_vs_conn_cachep); vfree(ip_vs_conn_tab); diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index a0791dc05a2..a74dae6c5db 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1113,6 +1113,9 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af) return NF_ACCEPT; net = skb_net(skb); + if (!net_ipvs(net)->enable) + return NF_ACCEPT; + ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { @@ -1343,6 +1346,7 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum) return NF_ACCEPT; /* The packet looks wrong, ignore */ net = skb_net(skb); + pd = ip_vs_proto_data_get(net, cih->protocol); if (!pd) return NF_ACCEPT; @@ -1529,6 +1533,11 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) IP_VS_DBG_ADDR(af, &iph.daddr), hooknum); return NF_ACCEPT; } + /* ipvs enabled in this netns ? */ + net = skb_net(skb); + if (!net_ipvs(net)->enable) + return NF_ACCEPT; + ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); /* Bad... Do not break raw sockets */ @@ -1562,7 +1571,6 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); } - net = skb_net(skb); /* Protocol supported? */ pd = ip_vs_proto_data_get(net, iph.protocol); if (unlikely(!pd)) @@ -1588,7 +1596,6 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) } IP_VS_DBG_PKT(11, af, pp, skb, 0, "Incoming packet"); - net = skb_net(skb); ipvs = net_ipvs(net); /* Check the server status */ if (cp->dest && !(cp->dest->flags & IP_VS_DEST_F_AVAILABLE)) { @@ -1743,10 +1750,16 @@ ip_vs_forward_icmp(unsigned int hooknum, struct sk_buff *skb, int (*okfn)(struct sk_buff *)) { int r; + struct net *net; if (ip_hdr(skb)->protocol != IPPROTO_ICMP) return NF_ACCEPT; + /* ipvs enabled in this netns ? */ + net = skb_net(skb); + if (!net_ipvs(net)->enable) + return NF_ACCEPT; + return ip_vs_in_icmp(skb, &r, hooknum); } @@ -1757,10 +1770,16 @@ ip_vs_forward_icmp_v6(unsigned int hooknum, struct sk_buff *skb, int (*okfn)(struct sk_buff *)) { int r; + struct net *net; if (ipv6_hdr(skb)->nexthdr != IPPROTO_ICMPV6) return NF_ACCEPT; + /* ipvs enabled in this netns ? */ + net = skb_net(skb); + if (!net_ipvs(net)->enable) + return NF_ACCEPT; + return ip_vs_in_icmp_v6(skb, &r, hooknum); } #endif @@ -1884,21 +1903,72 @@ static int __net_init __ip_vs_init(struct net *net) pr_err("%s(): no memory.\n", __func__); return -ENOMEM; } + /* Hold the beast until a service is registerd */ + ipvs->enable = 0; ipvs->net = net; /* Counters used for creating unique names */ ipvs->gen = atomic_read(&ipvs_netns_cnt); atomic_inc(&ipvs_netns_cnt); net->ipvs = ipvs; + + if (__ip_vs_estimator_init(net) < 0) + goto estimator_fail; + + if (__ip_vs_control_init(net) < 0) + goto control_fail; + + if (__ip_vs_protocol_init(net) < 0) + goto protocol_fail; + + if (__ip_vs_app_init(net) < 0) + goto app_fail; + + if (__ip_vs_conn_init(net) < 0) + goto conn_fail; + + if (__ip_vs_sync_init(net) < 0) + goto sync_fail; + printk(KERN_INFO "IPVS: Creating netns size=%zu id=%d\n", sizeof(struct netns_ipvs), ipvs->gen); return 0; +/* + * Error handling + */ + +sync_fail: + __ip_vs_conn_cleanup(net); +conn_fail: + __ip_vs_app_cleanup(net); +app_fail: + __ip_vs_protocol_cleanup(net); +protocol_fail: + __ip_vs_control_cleanup(net); +control_fail: + __ip_vs_estimator_cleanup(net); +estimator_fail: + return -ENOMEM; } static void __net_exit __ip_vs_cleanup(struct net *net) { + __ip_vs_service_cleanup(net); /* ip_vs_flush() with locks */ + __ip_vs_conn_cleanup(net); + __ip_vs_app_cleanup(net); + __ip_vs_protocol_cleanup(net); + __ip_vs_control_cleanup(net); + __ip_vs_estimator_cleanup(net); IP_VS_DBG(2, "ipvs netns %d released\n", net_ipvs(net)->gen); } +static void __net_exit __ip_vs_dev_cleanup(struct net *net) +{ + EnterFunction(2); + net_ipvs(net)->enable = 0; /* Disable packet reception */ + __ip_vs_sync_cleanup(net); + LeaveFunction(2); +} + static struct pernet_operations ipvs_core_ops = { .init = __ip_vs_init, .exit = __ip_vs_cleanup, @@ -1906,6 +1976,10 @@ static struct pernet_operations ipvs_core_ops = { .size = sizeof(struct netns_ipvs), }; +static struct pernet_operations ipvs_core_dev_ops = { + .exit = __ip_vs_dev_cleanup, +}; + /* * Initialize IP Virtual Server */ @@ -1913,10 +1987,6 @@ static int __init ip_vs_init(void) { int ret; - ret = register_pernet_subsys(&ipvs_core_ops); /* Alloc ip_vs struct */ - if (ret < 0) - return ret; - ip_vs_estimator_init(); ret = ip_vs_control_init(); if (ret < 0) { @@ -1944,15 +2014,28 @@ static int __init ip_vs_init(void) goto cleanup_conn; } + ret = register_pernet_subsys(&ipvs_core_ops); /* Alloc ip_vs struct */ + if (ret < 0) + goto cleanup_sync; + + ret = register_pernet_device(&ipvs_core_dev_ops); + if (ret < 0) + goto cleanup_sub; + ret = nf_register_hooks(ip_vs_ops, ARRAY_SIZE(ip_vs_ops)); if (ret < 0) { pr_err("can't register hooks.\n"); - goto cleanup_sync; + goto cleanup_dev; } pr_info("ipvs loaded.\n"); + return ret; +cleanup_dev: + unregister_pernet_device(&ipvs_core_dev_ops); +cleanup_sub: + unregister_pernet_subsys(&ipvs_core_ops); cleanup_sync: ip_vs_sync_cleanup(); cleanup_conn: @@ -1964,20 +2047,20 @@ cleanup_sync: ip_vs_control_cleanup(); cleanup_estimator: ip_vs_estimator_cleanup(); - unregister_pernet_subsys(&ipvs_core_ops); /* free ip_vs struct */ return ret; } static void __exit ip_vs_cleanup(void) { nf_unregister_hooks(ip_vs_ops, ARRAY_SIZE(ip_vs_ops)); + unregister_pernet_device(&ipvs_core_dev_ops); + unregister_pernet_subsys(&ipvs_core_ops); /* free ip_vs struct */ ip_vs_sync_cleanup(); ip_vs_conn_cleanup(); ip_vs_app_cleanup(); ip_vs_protocol_cleanup(); ip_vs_control_cleanup(); ip_vs_estimator_cleanup(); - unregister_pernet_subsys(&ipvs_core_ops); /* free ip_vs struct */ pr_info("ipvs unloaded.\n"); } diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index ae47090bf45..ea722810faf 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -69,6 +69,11 @@ int ip_vs_get_debug_level(void) } #endif + +/* Protos */ +static void __ip_vs_del_service(struct ip_vs_service *svc); + + #ifdef CONFIG_IP_VS_IPV6 /* Taken from rt6_fill_node() in net/ipv6/route.c, is there a better way? */ static int __ip_vs_addr_is_local_v6(struct net *net, @@ -1214,6 +1219,8 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u, write_unlock_bh(&__ip_vs_svc_lock); *svc_p = svc; + /* Now there is a service - full throttle */ + ipvs->enable = 1; return 0; @@ -1472,6 +1479,84 @@ static int ip_vs_flush(struct net *net) return 0; } +/* + * Delete service by {netns} in the service table. + * Called by __ip_vs_cleanup() + */ +void __ip_vs_service_cleanup(struct net *net) +{ + EnterFunction(2); + /* Check for "full" addressed entries */ + mutex_lock(&__ip_vs_mutex); + ip_vs_flush(net); + mutex_unlock(&__ip_vs_mutex); + LeaveFunction(2); +} +/* + * Release dst hold by dst_cache + */ +static inline void +__ip_vs_dev_reset(struct ip_vs_dest *dest, struct net_device *dev) +{ + spin_lock_bh(&dest->dst_lock); + if (dest->dst_cache && dest->dst_cache->dev == dev) { + IP_VS_DBG_BUF(3, "Reset dev:%s dest %s:%u ,dest->refcnt=%d\n", + dev->name, + IP_VS_DBG_ADDR(dest->af, &dest->addr), + ntohs(dest->port), + atomic_read(&dest->refcnt)); + ip_vs_dst_reset(dest); + } + spin_unlock_bh(&dest->dst_lock); + +} +/* + * Netdev event receiver + * Currently only NETDEV_UNREGISTER is handled, i.e. if we hold a reference to + * a device that is "unregister" it must be released. + */ +static int ip_vs_dst_event(struct notifier_block *this, unsigned long event, + void *ptr) +{ + struct net_device *dev = ptr; + struct net *net = dev_net(dev); + struct ip_vs_service *svc; + struct ip_vs_dest *dest; + unsigned int idx; + + if (event != NETDEV_UNREGISTER) + return NOTIFY_DONE; + IP_VS_DBG(3, "%s() dev=%s\n", __func__, dev->name); + EnterFunction(2); + mutex_lock(&__ip_vs_mutex); + for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { + list_for_each_entry(svc, &ip_vs_svc_table[idx], s_list) { + if (net_eq(svc->net, net)) { + list_for_each_entry(dest, &svc->destinations, + n_list) { + __ip_vs_dev_reset(dest, dev); + } + } + } + + list_for_each_entry(svc, &ip_vs_svc_fwm_table[idx], f_list) { + if (net_eq(svc->net, net)) { + list_for_each_entry(dest, &svc->destinations, + n_list) { + __ip_vs_dev_reset(dest, dev); + } + } + + } + } + + list_for_each_entry(dest, &net_ipvs(net)->dest_trash, n_list) { + __ip_vs_dev_reset(dest, dev); + } + mutex_unlock(&__ip_vs_mutex); + LeaveFunction(2); + return NOTIFY_DONE; +} /* * Zero counters in a service or all services @@ -3588,6 +3673,10 @@ void __net_init __ip_vs_control_cleanup_sysctl(struct net *net) { } #endif +static struct notifier_block ip_vs_dst_notifier = { + .notifier_call = ip_vs_dst_event, +}; + int __net_init __ip_vs_control_init(struct net *net) { int idx; @@ -3626,7 +3715,7 @@ err: return -ENOMEM; } -static void __net_exit __ip_vs_control_cleanup(struct net *net) +void __net_exit __ip_vs_control_cleanup(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); @@ -3639,11 +3728,6 @@ static void __net_exit __ip_vs_control_cleanup(struct net *net) free_percpu(ipvs->tot_stats.cpustats); } -static struct pernet_operations ipvs_control_ops = { - .init = __ip_vs_control_init, - .exit = __ip_vs_control_cleanup, -}; - int __init ip_vs_control_init(void) { int idx; @@ -3657,33 +3741,32 @@ int __init ip_vs_control_init(void) INIT_LIST_HEAD(&ip_vs_svc_fwm_table[idx]); } - ret = register_pernet_subsys(&ipvs_control_ops); - if (ret) { - pr_err("cannot register namespace.\n"); - goto err; - } - smp_wmb(); /* Do we really need it now ? */ ret = nf_register_sockopt(&ip_vs_sockopts); if (ret) { pr_err("cannot register sockopt.\n"); - goto err_net; + goto err_sock; } ret = ip_vs_genl_register(); if (ret) { pr_err("cannot register Generic Netlink interface.\n"); - nf_unregister_sockopt(&ip_vs_sockopts); - goto err_net; + goto err_genl; } + ret = register_netdevice_notifier(&ip_vs_dst_notifier); + if (ret < 0) + goto err_notf; + LeaveFunction(2); return 0; -err_net: - unregister_pernet_subsys(&ipvs_control_ops); -err: +err_notf: + ip_vs_genl_unregister(); +err_genl: + nf_unregister_sockopt(&ip_vs_sockopts); +err_sock: return ret; } @@ -3691,7 +3774,6 @@ err: void ip_vs_control_cleanup(void) { EnterFunction(2); - unregister_pernet_subsys(&ipvs_control_ops); ip_vs_genl_unregister(); nf_unregister_sockopt(&ip_vs_sockopts); LeaveFunction(2); diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c index 8c8766ca56a..508cce98777 100644 --- a/net/netfilter/ipvs/ip_vs_est.c +++ b/net/netfilter/ipvs/ip_vs_est.c @@ -192,7 +192,7 @@ void ip_vs_read_estimator(struct ip_vs_stats_user *dst, dst->outbps = (e->outbps + 0xF) >> 5; } -static int __net_init __ip_vs_estimator_init(struct net *net) +int __net_init __ip_vs_estimator_init(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); @@ -203,24 +203,16 @@ static int __net_init __ip_vs_estimator_init(struct net *net) return 0; } -static void __net_exit __ip_vs_estimator_exit(struct net *net) +void __net_exit __ip_vs_estimator_cleanup(struct net *net) { del_timer_sync(&net_ipvs(net)->est_timer); } -static struct pernet_operations ip_vs_app_ops = { - .init = __ip_vs_estimator_init, - .exit = __ip_vs_estimator_exit, -}; int __init ip_vs_estimator_init(void) { - int rv; - - rv = register_pernet_subsys(&ip_vs_app_ops); - return rv; + return 0; } void ip_vs_estimator_cleanup(void) { - unregister_pernet_subsys(&ip_vs_app_ops); } diff --git a/net/netfilter/ipvs/ip_vs_proto.c b/net/netfilter/ipvs/ip_vs_proto.c index 17484a4416e..eb86028536f 100644 --- a/net/netfilter/ipvs/ip_vs_proto.c +++ b/net/netfilter/ipvs/ip_vs_proto.c @@ -316,7 +316,7 @@ ip_vs_tcpudp_debug_packet(int af, struct ip_vs_protocol *pp, /* * per network name-space init */ -static int __net_init __ip_vs_protocol_init(struct net *net) +int __net_init __ip_vs_protocol_init(struct net *net) { #ifdef CONFIG_IP_VS_PROTO_TCP register_ip_vs_proto_netns(net, &ip_vs_protocol_tcp); @@ -336,7 +336,7 @@ static int __net_init __ip_vs_protocol_init(struct net *net) return 0; } -static void __net_exit __ip_vs_protocol_cleanup(struct net *net) +void __net_exit __ip_vs_protocol_cleanup(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); struct ip_vs_proto_data *pd; @@ -349,11 +349,6 @@ static void __net_exit __ip_vs_protocol_cleanup(struct net *net) } } -static struct pernet_operations ipvs_proto_ops = { - .init = __ip_vs_protocol_init, - .exit = __ip_vs_protocol_cleanup, -}; - int __init ip_vs_protocol_init(void) { char protocols[64]; @@ -382,7 +377,6 @@ int __init ip_vs_protocol_init(void) REGISTER_PROTOCOL(&ip_vs_protocol_esp); #endif pr_info("Registered protocols (%s)\n", &protocols[2]); - return register_pernet_subsys(&ipvs_proto_ops); return 0; } @@ -393,7 +387,6 @@ void ip_vs_protocol_cleanup(void) struct ip_vs_protocol *pp; int i; - unregister_pernet_subsys(&ipvs_proto_ops); /* unregister all the ipvs protocols */ for (i = 0; i < IP_VS_PROTO_TAB_SIZE; i++) { while ((pp = ip_vs_proto_table[i]) != NULL) diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index 0cce9531082..e292e5bddc7 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -1663,7 +1663,7 @@ int stop_sync_thread(struct net *net, int state) /* * Initialize data struct for each netns */ -static int __net_init __ip_vs_sync_init(struct net *net) +int __net_init __ip_vs_sync_init(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); @@ -1677,7 +1677,7 @@ static int __net_init __ip_vs_sync_init(struct net *net) return 0; } -static void __ip_vs_sync_cleanup(struct net *net) +void __ip_vs_sync_cleanup(struct net *net) { int retc; @@ -1690,18 +1690,11 @@ static void __ip_vs_sync_cleanup(struct net *net) pr_err("Failed to stop Backup Daemon\n"); } -static struct pernet_operations ipvs_sync_ops = { - .init = __ip_vs_sync_init, - .exit = __ip_vs_sync_cleanup, -}; - - int __init ip_vs_sync_init(void) { - return register_pernet_device(&ipvs_sync_ops); + return 0; } void ip_vs_sync_cleanup(void) { - unregister_pernet_device(&ipvs_sync_ops); } -- cgit v1.2.3-70-g09d2 From 43a4dea4c9d44baae38ddc14b9b6d86fde4c8b88 Mon Sep 17 00:00:00 2001 From: Steffen Klassert Date: Mon, 9 May 2011 19:36:38 +0000 Subject: xfrm: Assign the inner mode output function to the dst entry As it is, we assign the outer modes output function to the dst entry when we create the xfrm bundle. This leads to two problems on interfamily scenarios. We might insert ipv4 packets into ip6_fragment when called from xfrm6_output. The system crashes if we try to fragment an ipv4 packet with ip6_fragment. This issue was introduced with git commit ad0081e4 (ipv6: Fragment locally generated tunnel-mode IPSec6 packets as needed). The second issue is, that we might insert ipv4 packets in netfilter6 and vice versa on interfamily scenarios. With this patch we assign the inner mode output function to the dst entry when we create the xfrm bundle. So xfrm4_output/xfrm6_output from the inner mode is used and the right fragmentation and netfilter functions are called. We switch then to outer mode with the output_finish functions. Signed-off-by: Steffen Klassert Signed-off-by: David S. Miller --- include/net/xfrm.h | 3 +++ net/ipv4/xfrm4_output.c | 8 ++++++-- net/ipv4/xfrm4_state.c | 1 + net/ipv6/xfrm6_output.c | 6 +++--- net/ipv6/xfrm6_state.c | 1 + net/xfrm/xfrm_policy.c | 14 +++++++++++++- 6 files changed, 27 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 6ae4bc5ce8a..20afeaa3939 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -324,6 +324,7 @@ struct xfrm_state_afinfo { int (*tmpl_sort)(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n); int (*state_sort)(struct xfrm_state **dst, struct xfrm_state **src, int n); int (*output)(struct sk_buff *skb); + int (*output_finish)(struct sk_buff *skb); int (*extract_input)(struct xfrm_state *x, struct sk_buff *skb); int (*extract_output)(struct xfrm_state *x, @@ -1454,6 +1455,7 @@ static inline int xfrm4_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi) extern int xfrm4_extract_output(struct xfrm_state *x, struct sk_buff *skb); extern int xfrm4_prepare_output(struct xfrm_state *x, struct sk_buff *skb); extern int xfrm4_output(struct sk_buff *skb); +extern int xfrm4_output_finish(struct sk_buff *skb); extern int xfrm4_tunnel_register(struct xfrm_tunnel *handler, unsigned short family); extern int xfrm4_tunnel_deregister(struct xfrm_tunnel *handler, unsigned short family); extern int xfrm6_extract_header(struct sk_buff *skb); @@ -1470,6 +1472,7 @@ extern __be32 xfrm6_tunnel_spi_lookup(struct net *net, xfrm_address_t *saddr); extern int xfrm6_extract_output(struct xfrm_state *x, struct sk_buff *skb); extern int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb); extern int xfrm6_output(struct sk_buff *skb); +extern int xfrm6_output_finish(struct sk_buff *skb); extern int xfrm6_find_1stfragopt(struct xfrm_state *x, struct sk_buff *skb, u8 **prevhdr); diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c index 571aa96a175..2d51840e53a 100644 --- a/net/ipv4/xfrm4_output.c +++ b/net/ipv4/xfrm4_output.c @@ -69,7 +69,7 @@ int xfrm4_prepare_output(struct xfrm_state *x, struct sk_buff *skb) } EXPORT_SYMBOL(xfrm4_prepare_output); -static int xfrm4_output_finish(struct sk_buff *skb) +int xfrm4_output_finish(struct sk_buff *skb) { #ifdef CONFIG_NETFILTER if (!skb_dst(skb)->xfrm) { @@ -86,7 +86,11 @@ static int xfrm4_output_finish(struct sk_buff *skb) int xfrm4_output(struct sk_buff *skb) { + struct dst_entry *dst = skb_dst(skb); + struct xfrm_state *x = dst->xfrm; + return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, skb, - NULL, skb_dst(skb)->dev, xfrm4_output_finish, + NULL, dst->dev, + x->outer_mode->afinfo->output_finish, !(IPCB(skb)->flags & IPSKB_REROUTED)); } diff --git a/net/ipv4/xfrm4_state.c b/net/ipv4/xfrm4_state.c index 1717c64628d..805d63ef434 100644 --- a/net/ipv4/xfrm4_state.c +++ b/net/ipv4/xfrm4_state.c @@ -78,6 +78,7 @@ static struct xfrm_state_afinfo xfrm4_state_afinfo = { .init_tempsel = __xfrm4_init_tempsel, .init_temprop = xfrm4_init_temprop, .output = xfrm4_output, + .output_finish = xfrm4_output_finish, .extract_input = xfrm4_extract_input, .extract_output = xfrm4_extract_output, .transport_finish = xfrm4_transport_finish, diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index 8e688b3de9a..49a91c5f562 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -79,7 +79,7 @@ int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb) } EXPORT_SYMBOL(xfrm6_prepare_output); -static int xfrm6_output_finish(struct sk_buff *skb) +int xfrm6_output_finish(struct sk_buff *skb) { #ifdef CONFIG_NETFILTER IP6CB(skb)->flags |= IP6SKB_XFRM_TRANSFORMED; @@ -97,9 +97,9 @@ static int __xfrm6_output(struct sk_buff *skb) if ((x && x->props.mode == XFRM_MODE_TUNNEL) && ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) || dst_allfrag(skb_dst(skb)))) { - return ip6_fragment(skb, xfrm6_output_finish); + return ip6_fragment(skb, x->outer_mode->afinfo->output_finish); } - return xfrm6_output_finish(skb); + return x->outer_mode->afinfo->output_finish(skb); } int xfrm6_output(struct sk_buff *skb) diff --git a/net/ipv6/xfrm6_state.c b/net/ipv6/xfrm6_state.c index afe941e9415..248f0b2a7ee 100644 --- a/net/ipv6/xfrm6_state.c +++ b/net/ipv6/xfrm6_state.c @@ -178,6 +178,7 @@ static struct xfrm_state_afinfo xfrm6_state_afinfo = { .tmpl_sort = __xfrm6_tmpl_sort, .state_sort = __xfrm6_state_sort, .output = xfrm6_output, + .output_finish = xfrm6_output_finish, .extract_input = xfrm6_extract_input, .extract_output = xfrm6_extract_output, .transport_finish = xfrm6_transport_finish, diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 15792d8b627..b4d745ea8ee 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1406,6 +1406,7 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, struct net *net = xp_net(policy); unsigned long now = jiffies; struct net_device *dev; + struct xfrm_mode *inner_mode; struct dst_entry *dst_prev = NULL; struct dst_entry *dst0 = NULL; int i = 0; @@ -1436,6 +1437,17 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, goto put_states; } + if (xfrm[i]->sel.family == AF_UNSPEC) { + inner_mode = xfrm_ip2inner_mode(xfrm[i], + xfrm_af2proto(family)); + if (!inner_mode) { + err = -EAFNOSUPPORT; + dst_release(dst); + goto put_states; + } + } else + inner_mode = xfrm[i]->inner_mode; + if (!dst_prev) dst0 = dst1; else { @@ -1464,7 +1476,7 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, dst1->lastuse = now; dst1->input = dst_discard; - dst1->output = xfrm[i]->outer_mode->afinfo->output; + dst1->output = inner_mode->afinfo->output; dst1->next = dst_prev; dst_prev = dst1; -- cgit v1.2.3-70-g09d2 From 2e711c04dbbf7a7732a3f7073b1fc285d12b369d Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 26 Apr 2011 19:15:07 +0200 Subject: PM: Remove sysdev suspend, resume and shutdown operations Since suspend, resume and shutdown operations in struct sysdev_class and struct sysdev_driver are not used any more, remove them. Also drop sysdev_suspend(), sysdev_resume() and sysdev_shutdown() used for executing those operations and modify all of their users accordingly. This reduces kernel code size quite a bit and reduces its complexity. Signed-off-by: Rafael J. Wysocki Acked-by: Greg Kroah-Hartman --- arch/sh/Kconfig | 1 - arch/x86/Kconfig | 1 - arch/x86/kernel/apm_32.c | 4 - drivers/base/Kconfig | 7 -- drivers/base/base.h | 2 - drivers/base/sys.c | 202 +---------------------------------------------- drivers/xen/manage.c | 8 +- include/linux/device.h | 7 -- include/linux/pm.h | 8 -- include/linux/sysdev.h | 11 --- kernel/kexec.c | 9 +-- kernel/power/hibernate.c | 18 +---- kernel/power/suspend.c | 8 +- kernel/sys.c | 3 - 14 files changed, 7 insertions(+), 282 deletions(-) (limited to 'include') diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index 4b89da248d1..bc439de48cd 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -24,7 +24,6 @@ config SUPERH select RTC_LIB select GENERIC_ATOMIC64 select GENERIC_IRQ_SHOW - select ARCH_NO_SYSDEV_OPS help The SuperH is a RISC processor targeted for use in embedded systems and consumer electronics; it was also used in the Sega Dreamcast diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index cc6c53a95bf..140e254fe54 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -71,7 +71,6 @@ config X86 select GENERIC_IRQ_SHOW select IRQ_FORCED_THREADING select USE_GENERIC_SMP_HELPERS if SMP - select ARCH_NO_SYSDEV_OPS config INSTRUCTION_DECODER def_bool (KPROBES || PERF_EVENTS) diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index adee12e0da1..3bfa0223596 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -1238,7 +1238,6 @@ static int suspend(int vetoable) dpm_suspend_noirq(PMSG_SUSPEND); local_irq_disable(); - sysdev_suspend(PMSG_SUSPEND); syscore_suspend(); local_irq_enable(); @@ -1258,7 +1257,6 @@ static int suspend(int vetoable) err = (err == APM_SUCCESS) ? 0 : -EIO; syscore_resume(); - sysdev_resume(); local_irq_enable(); dpm_resume_noirq(PMSG_RESUME); @@ -1282,7 +1280,6 @@ static void standby(void) dpm_suspend_noirq(PMSG_SUSPEND); local_irq_disable(); - sysdev_suspend(PMSG_SUSPEND); syscore_suspend(); local_irq_enable(); @@ -1292,7 +1289,6 @@ static void standby(void) local_irq_disable(); syscore_resume(); - sysdev_resume(); local_irq_enable(); dpm_resume_noirq(PMSG_RESUME); diff --git a/drivers/base/Kconfig b/drivers/base/Kconfig index e9e5238f310..d57e8d0fb82 100644 --- a/drivers/base/Kconfig +++ b/drivers/base/Kconfig @@ -168,11 +168,4 @@ config SYS_HYPERVISOR bool default n -config ARCH_NO_SYSDEV_OPS - bool - ---help--- - To be selected by architectures that don't use sysdev class or - sysdev driver power management (suspend/resume) and shutdown - operations. - endmenu diff --git a/drivers/base/base.h b/drivers/base/base.h index 19f49e41ce5..a34dca0ad04 100644 --- a/drivers/base/base.h +++ b/drivers/base/base.h @@ -111,8 +111,6 @@ static inline int driver_match_device(struct device_driver *drv, return drv->bus->match ? drv->bus->match(dev, drv) : 1; } -extern void sysdev_shutdown(void); - extern char *make_class_name(const char *name, struct kobject *kobj); extern int devres_release_all(struct device *dev); diff --git a/drivers/base/sys.c b/drivers/base/sys.c index acde9b5ee13..9dff77bfe1e 100644 --- a/drivers/base/sys.c +++ b/drivers/base/sys.c @@ -328,203 +328,8 @@ void sysdev_unregister(struct sys_device *sysdev) kobject_put(&sysdev->kobj); } - -#ifndef CONFIG_ARCH_NO_SYSDEV_OPS -/** - * sysdev_shutdown - Shut down all system devices. - * - * Loop over each class of system devices, and the devices in each - * of those classes. For each device, we call the shutdown method for - * each driver registered for the device - the auxiliaries, - * and the class driver. - * - * Note: The list is iterated in reverse order, so that we shut down - * child devices before we shut down their parents. The list ordering - * is guaranteed by virtue of the fact that child devices are registered - * after their parents. - */ -void sysdev_shutdown(void) -{ - struct sysdev_class *cls; - - pr_debug("Shutting Down System Devices\n"); - - mutex_lock(&sysdev_drivers_lock); - list_for_each_entry_reverse(cls, &system_kset->list, kset.kobj.entry) { - struct sys_device *sysdev; - - pr_debug("Shutting down type '%s':\n", - kobject_name(&cls->kset.kobj)); - - list_for_each_entry(sysdev, &cls->kset.list, kobj.entry) { - struct sysdev_driver *drv; - pr_debug(" %s\n", kobject_name(&sysdev->kobj)); - - /* Call auxiliary drivers first */ - list_for_each_entry(drv, &cls->drivers, entry) { - if (drv->shutdown) - drv->shutdown(sysdev); - } - - /* Now call the generic one */ - if (cls->shutdown) - cls->shutdown(sysdev); - } - } - mutex_unlock(&sysdev_drivers_lock); -} - -static void __sysdev_resume(struct sys_device *dev) -{ - struct sysdev_class *cls = dev->cls; - struct sysdev_driver *drv; - - /* First, call the class-specific one */ - if (cls->resume) - cls->resume(dev); - WARN_ONCE(!irqs_disabled(), - "Interrupts enabled after %pF\n", cls->resume); - - /* Call auxiliary drivers next. */ - list_for_each_entry(drv, &cls->drivers, entry) { - if (drv->resume) - drv->resume(dev); - WARN_ONCE(!irqs_disabled(), - "Interrupts enabled after %pF\n", drv->resume); - } -} - -/** - * sysdev_suspend - Suspend all system devices. - * @state: Power state to enter. - * - * We perform an almost identical operation as sysdev_shutdown() - * above, though calling ->suspend() instead. Interrupts are disabled - * when this called. Devices are responsible for both saving state and - * quiescing or powering down the device. - * - * This is only called by the device PM core, so we let them handle - * all synchronization. - */ -int sysdev_suspend(pm_message_t state) -{ - struct sysdev_class *cls; - struct sys_device *sysdev, *err_dev; - struct sysdev_driver *drv, *err_drv; - int ret; - - pr_debug("Checking wake-up interrupts\n"); - - /* Return error code if there are any wake-up interrupts pending */ - ret = check_wakeup_irqs(); - if (ret) - return ret; - - WARN_ONCE(!irqs_disabled(), - "Interrupts enabled while suspending system devices\n"); - - pr_debug("Suspending System Devices\n"); - - list_for_each_entry_reverse(cls, &system_kset->list, kset.kobj.entry) { - pr_debug("Suspending type '%s':\n", - kobject_name(&cls->kset.kobj)); - - list_for_each_entry(sysdev, &cls->kset.list, kobj.entry) { - pr_debug(" %s\n", kobject_name(&sysdev->kobj)); - - /* Call auxiliary drivers first */ - list_for_each_entry(drv, &cls->drivers, entry) { - if (drv->suspend) { - ret = drv->suspend(sysdev, state); - if (ret) - goto aux_driver; - } - WARN_ONCE(!irqs_disabled(), - "Interrupts enabled after %pF\n", - drv->suspend); - } - - /* Now call the generic one */ - if (cls->suspend) { - ret = cls->suspend(sysdev, state); - if (ret) - goto cls_driver; - WARN_ONCE(!irqs_disabled(), - "Interrupts enabled after %pF\n", - cls->suspend); - } - } - } - return 0; - /* resume current sysdev */ -cls_driver: - drv = NULL; - printk(KERN_ERR "Class suspend failed for %s: %d\n", - kobject_name(&sysdev->kobj), ret); - -aux_driver: - if (drv) - printk(KERN_ERR "Class driver suspend failed for %s: %d\n", - kobject_name(&sysdev->kobj), ret); - list_for_each_entry(err_drv, &cls->drivers, entry) { - if (err_drv == drv) - break; - if (err_drv->resume) - err_drv->resume(sysdev); - } - - /* resume other sysdevs in current class */ - list_for_each_entry(err_dev, &cls->kset.list, kobj.entry) { - if (err_dev == sysdev) - break; - pr_debug(" %s\n", kobject_name(&err_dev->kobj)); - __sysdev_resume(err_dev); - } - - /* resume other classes */ - list_for_each_entry_continue(cls, &system_kset->list, kset.kobj.entry) { - list_for_each_entry(err_dev, &cls->kset.list, kobj.entry) { - pr_debug(" %s\n", kobject_name(&err_dev->kobj)); - __sysdev_resume(err_dev); - } - } - return ret; -} -EXPORT_SYMBOL_GPL(sysdev_suspend); - -/** - * sysdev_resume - Bring system devices back to life. - * - * Similar to sysdev_suspend(), but we iterate the list forwards - * to guarantee that parent devices are resumed before their children. - * - * Note: Interrupts are disabled when called. - */ -int sysdev_resume(void) -{ - struct sysdev_class *cls; - - WARN_ONCE(!irqs_disabled(), - "Interrupts enabled while resuming system devices\n"); - - pr_debug("Resuming System Devices\n"); - - list_for_each_entry(cls, &system_kset->list, kset.kobj.entry) { - struct sys_device *sysdev; - - pr_debug("Resuming type '%s':\n", - kobject_name(&cls->kset.kobj)); - - list_for_each_entry(sysdev, &cls->kset.list, kobj.entry) { - pr_debug(" %s\n", kobject_name(&sysdev->kobj)); - - __sysdev_resume(sysdev); - } - } - return 0; -} -EXPORT_SYMBOL_GPL(sysdev_resume); -#endif /* CONFIG_ARCH_NO_SYSDEV_OPS */ +EXPORT_SYMBOL_GPL(sysdev_register); +EXPORT_SYMBOL_GPL(sysdev_unregister); int __init system_bus_init(void) { @@ -534,9 +339,6 @@ int __init system_bus_init(void) return 0; } -EXPORT_SYMBOL_GPL(sysdev_register); -EXPORT_SYMBOL_GPL(sysdev_unregister); - #define to_ext_attr(x) container_of(x, struct sysdev_ext_attribute, attr) ssize_t sysdev_store_ulong(struct sys_device *sysdev, diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c index a2eee574784..0b5366b5be2 100644 --- a/drivers/xen/manage.c +++ b/drivers/xen/manage.c @@ -70,12 +70,7 @@ static int xen_suspend(void *data) BUG_ON(!irqs_disabled()); - err = sysdev_suspend(PMSG_FREEZE); - if (!err) { - err = syscore_suspend(); - if (err) - sysdev_resume(); - } + err = syscore_suspend(); if (err) { printk(KERN_ERR "xen_suspend: system core suspend failed: %d\n", err); @@ -102,7 +97,6 @@ static int xen_suspend(void *data) } syscore_resume(); - sysdev_resume(); return 0; } diff --git a/include/linux/device.h b/include/linux/device.h index ab8dfc09570..ea9db9b0f24 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -633,13 +633,6 @@ static inline int devtmpfs_mount(const char *mountpoint) { return 0; } /* drivers/base/power/shutdown.c */ extern void device_shutdown(void); -#ifndef CONFIG_ARCH_NO_SYSDEV_OPS -/* drivers/base/sys.c */ -extern void sysdev_shutdown(void); -#else -static inline void sysdev_shutdown(void) { } -#endif - /* debugging and troubleshooting/diagnostic helpers. */ extern const char *dev_driver_string(const struct device *dev); diff --git a/include/linux/pm.h b/include/linux/pm.h index 512e09177e5..3c053e2beb8 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -529,14 +529,6 @@ struct dev_power_domain { */ #ifdef CONFIG_PM_SLEEP -#ifndef CONFIG_ARCH_NO_SYSDEV_OPS -extern int sysdev_suspend(pm_message_t state); -extern int sysdev_resume(void); -#else -static inline int sysdev_suspend(pm_message_t state) { return 0; } -static inline int sysdev_resume(void) { return 0; } -#endif - extern void device_pm_lock(void); extern void dpm_resume_noirq(pm_message_t state); extern void dpm_resume_end(pm_message_t state); diff --git a/include/linux/sysdev.h b/include/linux/sysdev.h index dfb078db8eb..d35e783a598 100644 --- a/include/linux/sysdev.h +++ b/include/linux/sysdev.h @@ -34,12 +34,6 @@ struct sysdev_class { struct list_head drivers; struct sysdev_class_attribute **attrs; struct kset kset; -#ifndef CONFIG_ARCH_NO_SYSDEV_OPS - /* Default operations for these types of devices */ - int (*shutdown)(struct sys_device *); - int (*suspend)(struct sys_device *, pm_message_t state); - int (*resume)(struct sys_device *); -#endif }; struct sysdev_class_attribute { @@ -77,11 +71,6 @@ struct sysdev_driver { struct list_head entry; int (*add)(struct sys_device *); int (*remove)(struct sys_device *); -#ifndef CONFIG_ARCH_NO_SYSDEV_OPS - int (*shutdown)(struct sys_device *); - int (*suspend)(struct sys_device *, pm_message_t state); - int (*resume)(struct sys_device *); -#endif }; diff --git a/kernel/kexec.c b/kernel/kexec.c index 87b77de03dd..8d814cbc810 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -1531,13 +1531,7 @@ int kernel_kexec(void) if (error) goto Enable_cpus; local_irq_disable(); - /* Suspend system devices */ - error = sysdev_suspend(PMSG_FREEZE); - if (!error) { - error = syscore_suspend(); - if (error) - sysdev_resume(); - } + error = syscore_suspend(); if (error) goto Enable_irqs; } else @@ -1553,7 +1547,6 @@ int kernel_kexec(void) #ifdef CONFIG_KEXEC_JUMP if (kexec_image->preserve_context) { syscore_resume(); - sysdev_resume(); Enable_irqs: local_irq_enable(); Enable_cpus: diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index 50aae660174..554d3b049f3 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -272,12 +272,7 @@ static int create_image(int platform_mode) local_irq_disable(); - error = sysdev_suspend(PMSG_FREEZE); - if (!error) { - error = syscore_suspend(); - if (error) - sysdev_resume(); - } + error = syscore_suspend(); if (error) { printk(KERN_ERR "PM: Some system devices failed to power down, " "aborting hibernation\n"); @@ -302,7 +297,6 @@ static int create_image(int platform_mode) Power_up: syscore_resume(); - sysdev_resume(); /* NOTE: dpm_resume_noirq() is just a resume() for devices * that suspended with irqs off ... no overall powerup. */ @@ -409,12 +403,7 @@ static int resume_target_kernel(bool platform_mode) local_irq_disable(); - error = sysdev_suspend(PMSG_QUIESCE); - if (!error) { - error = syscore_suspend(); - if (error) - sysdev_resume(); - } + error = syscore_suspend(); if (error) goto Enable_irqs; @@ -442,7 +431,6 @@ static int resume_target_kernel(bool platform_mode) touch_softlockup_watchdog(); syscore_resume(); - sysdev_resume(); Enable_irqs: local_irq_enable(); @@ -528,7 +516,6 @@ int hibernation_platform_enter(void) goto Platform_finish; local_irq_disable(); - sysdev_suspend(PMSG_HIBERNATE); syscore_suspend(); if (pm_wakeup_pending()) { error = -EAGAIN; @@ -541,7 +528,6 @@ int hibernation_platform_enter(void) Power_up: syscore_resume(); - sysdev_resume(); local_irq_enable(); enable_nonboot_cpus(); diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 8935369d503..732d77a957e 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -163,19 +163,13 @@ static int suspend_enter(suspend_state_t state) arch_suspend_disable_irqs(); BUG_ON(!irqs_disabled()); - error = sysdev_suspend(PMSG_SUSPEND); - if (!error) { - error = syscore_suspend(); - if (error) - sysdev_resume(); - } + error = syscore_suspend(); if (!error) { if (!(suspend_test(TEST_CORE) || pm_wakeup_pending())) { error = suspend_ops->enter(state); events_check_enabled = false; } syscore_resume(); - sysdev_resume(); } arch_suspend_enable_irqs(); diff --git a/kernel/sys.c b/kernel/sys.c index af468edf096..f0c10385f30 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -315,7 +315,6 @@ void kernel_restart_prepare(char *cmd) blocking_notifier_call_chain(&reboot_notifier_list, SYS_RESTART, cmd); system_state = SYSTEM_RESTART; device_shutdown(); - sysdev_shutdown(); syscore_shutdown(); } @@ -354,7 +353,6 @@ static void kernel_shutdown_prepare(enum system_states state) void kernel_halt(void) { kernel_shutdown_prepare(SYSTEM_HALT); - sysdev_shutdown(); syscore_shutdown(); printk(KERN_EMERG "System halted.\n"); kmsg_dump(KMSG_DUMP_HALT); @@ -374,7 +372,6 @@ void kernel_power_off(void) if (pm_power_off_prepare) pm_power_off_prepare(); disable_nonboot_cpus(); - sysdev_shutdown(); syscore_shutdown(); printk(KERN_EMERG "Power down.\n"); kmsg_dump(KMSG_DUMP_POWEROFF); -- cgit v1.2.3-70-g09d2 From 8f389a99b652aab5b42297280bd94d95933ad12f Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Wed, 11 May 2011 15:13:32 -0700 Subject: mm: use alloc_bootmem_node_nopanic() on really needed path Stefan found nobootmem does not work on his system that has only 8M of RAM. This causes an early panic: BIOS-provided physical RAM map: BIOS-88: 0000000000000000 - 000000000009f000 (usable) BIOS-88: 0000000000100000 - 0000000000840000 (usable) bootconsole [earlyser0] enabled Notice: NX (Execute Disable) protection missing in CPU or disabled in BIOS! DMI not present or invalid. last_pfn = 0x840 max_arch_pfn = 0x100000 init_memory_mapping: 0000000000000000-0000000000840000 8MB LOWMEM available. mapped low ram: 0 - 00840000 low ram: 0 - 00840000 Zone PFN ranges: DMA 0x00000001 -> 0x00001000 Normal empty Movable zone start PFN for each node early_node_map[2] active PFN ranges 0: 0x00000001 -> 0x0000009f 0: 0x00000100 -> 0x00000840 BUG: Int 6: CR2 (null) EDI c034663c ESI (null) EBP c0329f38 ESP c0329ef4 EBX c0346380 EDX 00000006 ECX ffffffff EAX fffffff4 err (null) EIP c0353191 CS c0320060 flg 00010082 Stack: (null) c030c533 000007cd (null) c030c533 00000001 (null) (null) 00000003 0000083f 00000018 00000002 00000002 c0329f6c c03534d6 (null) (null) 00000100 00000840 (null) c0329f64 00000001 00001000 (null) Pid: 0, comm: swapper Not tainted 2.6.36 #5 Call Trace: [] ? 0xc02e3707 [] 0xc035e6e5 [] ? 0xc0353191 [] 0xc03534d6 [] 0xc034f1cd [] 0xc034a824 [] ? 0xc03513cb [] 0xc0349432 [] 0xc0349066 It turns out that we should ignore the low limit of 16M. Use alloc_bootmem_node_nopanic() in this case. [akpm@linux-foundation.org: less mess] Signed-off-by: Yinghai LU Reported-by: Stefan Hellermann Tested-by: Stefan Hellermann Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Thomas Gleixner Cc: [2.6.34+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootmem.h | 2 ++ mm/page_alloc.c | 7 ++++--- 2 files changed, 6 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index b8613e806aa..01eca1794e1 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -111,6 +111,8 @@ extern void *__alloc_bootmem_low_node(pg_data_t *pgdat, __alloc_bootmem_nopanic(x, PAGE_SIZE, __pa(MAX_DMA_ADDRESS)) #define alloc_bootmem_node(pgdat, x) \ __alloc_bootmem_node(pgdat, x, SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS)) +#define alloc_bootmem_node_nopanic(pgdat, x) \ + __alloc_bootmem_node_nopanic(pgdat, x, SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS)) #define alloc_bootmem_pages_node(pgdat, x) \ __alloc_bootmem_node(pgdat, x, PAGE_SIZE, __pa(MAX_DMA_ADDRESS)) #define alloc_bootmem_pages_node_nopanic(pgdat, x) \ diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 9f8a97b9a35..454191a2517 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3564,7 +3564,7 @@ int zone_wait_table_init(struct zone *zone, unsigned long zone_size_pages) if (!slab_is_available()) { zone->wait_table = (wait_queue_head_t *) - alloc_bootmem_node(pgdat, alloc_size); + alloc_bootmem_node_nopanic(pgdat, alloc_size); } else { /* * This case means that a zone whose size was 0 gets new memory @@ -4141,7 +4141,8 @@ static void __init setup_usemap(struct pglist_data *pgdat, unsigned long usemapsize = usemap_size(zonesize); zone->pageblock_flags = NULL; if (usemapsize) - zone->pageblock_flags = alloc_bootmem_node(pgdat, usemapsize); + zone->pageblock_flags = alloc_bootmem_node_nopanic(pgdat, + usemapsize); } #else static inline void setup_usemap(struct pglist_data *pgdat, @@ -4307,7 +4308,7 @@ static void __init_refok alloc_node_mem_map(struct pglist_data *pgdat) size = (end - start) * sizeof(struct page); map = alloc_remap(pgdat->node_id, size); if (!map) - map = alloc_bootmem_node(pgdat, size); + map = alloc_bootmem_node_nopanic(pgdat, size); pgdat->node_mem_map = map + (pgdat->node_start_pfn - start); } #ifndef CONFIG_NEED_MULTIPLE_NODES -- cgit v1.2.3-70-g09d2 From ee85c2e1454603ebb9f8d87223ac79dcdc87fa32 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Wed, 11 May 2011 15:13:34 -0700 Subject: mm: add alloc_pages_exact_nid() Add a alloc_pages_exact_nid() that allocates on a specific node. The naming is quite broken, but fixing that would need a larger renaming action. [akpm@linux-foundation.org: coding-style fixes] [akpm@linux-foundation.org: tweak comment] Signed-off-by: Andi Kleen Cc: Michal Hocko Cc: Balbir Singh Cc: KOSAKI Motohiro Cc: Dave Hansen Cc: David Rientjes Acked-by: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 2 ++ mm/page_alloc.c | 49 +++++++++++++++++++++++++++++++++++++------------ 2 files changed, 39 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index bfb8f934521..56d8fc87fbb 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -353,6 +353,8 @@ extern unsigned long get_zeroed_page(gfp_t gfp_mask); void *alloc_pages_exact(size_t size, gfp_t gfp_mask); void free_pages_exact(void *virt, size_t size); +/* This is different from alloc_pages_exact_node !!! */ +void *alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask); #define __get_free_page(gfp_mask) \ __get_free_pages((gfp_mask), 0) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 454191a2517..570d944daeb 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2317,6 +2317,21 @@ void free_pages(unsigned long addr, unsigned int order) EXPORT_SYMBOL(free_pages); +static void *make_alloc_exact(unsigned long addr, unsigned order, size_t size) +{ + if (addr) { + unsigned long alloc_end = addr + (PAGE_SIZE << order); + unsigned long used = addr + PAGE_ALIGN(size); + + split_page(virt_to_page((void *)addr), order); + while (used < alloc_end) { + free_page(used); + used += PAGE_SIZE; + } + } + return (void *)addr; +} + /** * alloc_pages_exact - allocate an exact number physically-contiguous pages. * @size: the number of bytes to allocate @@ -2336,21 +2351,31 @@ void *alloc_pages_exact(size_t size, gfp_t gfp_mask) unsigned long addr; addr = __get_free_pages(gfp_mask, order); - if (addr) { - unsigned long alloc_end = addr + (PAGE_SIZE << order); - unsigned long used = addr + PAGE_ALIGN(size); - - split_page(virt_to_page((void *)addr), order); - while (used < alloc_end) { - free_page(used); - used += PAGE_SIZE; - } - } - - return (void *)addr; + return make_alloc_exact(addr, order, size); } EXPORT_SYMBOL(alloc_pages_exact); +/** + * alloc_pages_exact_nid - allocate an exact number of physically-contiguous + * pages on a node. + * @size: the number of bytes to allocate + * @gfp_mask: GFP flags for the allocation + * + * Like alloc_pages_exact(), but try to allocate on node nid first before falling + * back. + * Note this is not alloc_pages_exact_node() which allocates on a specific node, + * but is not exact. + */ +void *alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask) +{ + unsigned order = get_order(size); + struct page *p = alloc_pages_node(nid, gfp_mask, order); + if (!p) + return NULL; + return make_alloc_exact((unsigned long)page_address(p), order, size); +} +EXPORT_SYMBOL(alloc_pages_exact_nid); + /** * free_pages_exact - release memory allocated via alloc_pages_exact() * @virt: the value returned by alloc_pages_exact. -- cgit v1.2.3-70-g09d2 From 1d929b7a84438ad9012c5826f5617d79a3efcef1 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 11 May 2011 15:13:39 -0700 Subject: mm: tracing: add missing GFP flags to tracing include/linux/gfp.h and include/trace/events/gfpflags.h are out of sync. When tracing is enabled, certain flags are not recognised and the text output is less useful as a result. Add the missing flags. Signed-off-by: Mel Gorman Cc: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/trace/events/gfpflags.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/trace/events/gfpflags.h b/include/trace/events/gfpflags.h index e3615c09374..9fe3a36646e 100644 --- a/include/trace/events/gfpflags.h +++ b/include/trace/events/gfpflags.h @@ -10,6 +10,7 @@ */ #define show_gfp_flags(flags) \ (flags) ? __print_flags(flags, "|", \ + {(unsigned long)GFP_TRANSHUGE, "GFP_TRANSHUGE"}, \ {(unsigned long)GFP_HIGHUSER_MOVABLE, "GFP_HIGHUSER_MOVABLE"}, \ {(unsigned long)GFP_HIGHUSER, "GFP_HIGHUSER"}, \ {(unsigned long)GFP_USER, "GFP_USER"}, \ @@ -32,6 +33,9 @@ {(unsigned long)__GFP_HARDWALL, "GFP_HARDWALL"}, \ {(unsigned long)__GFP_THISNODE, "GFP_THISNODE"}, \ {(unsigned long)__GFP_RECLAIMABLE, "GFP_RECLAIMABLE"}, \ - {(unsigned long)__GFP_MOVABLE, "GFP_MOVABLE"} \ + {(unsigned long)__GFP_MOVABLE, "GFP_MOVABLE"}, \ + {(unsigned long)__GFP_NOTRACK, "GFP_NOTRACK"}, \ + {(unsigned long)__GFP_NO_KSWAPD, "GFP_NO_KSWAPD"}, \ + {(unsigned long)__GFP_OTHER_NODE, "GFP_OTHER_NODE"} \ ) : "GFP_NOWAIT" -- cgit v1.2.3-70-g09d2 From a75b9df9d3bfc3cd1083974c045ae31ce5f3434f Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 11 May 2011 18:00:51 -0400 Subject: NFSv4.1: Ensure that layoutget uses the correct gfp modes Currently, writebacks may end up recursing back into the filesystem due to GFP_KERNEL direct reclaims in the pnfs subsystem. Signed-off-by: Trond Myklebust --- fs/nfs/nfs4filelayout.c | 25 ++++++++++++++----------- fs/nfs/nfs4filelayout.h | 2 +- fs/nfs/nfs4filelayoutdev.c | 34 +++++++++++++++++----------------- fs/nfs/pnfs.c | 33 +++++++++++++++++++-------------- fs/nfs/pnfs.h | 6 +++--- fs/nfs/read.c | 4 ++-- fs/nfs/write.c | 4 ++-- include/linux/nfs_xdr.h | 1 + 8 files changed, 59 insertions(+), 50 deletions(-) (limited to 'include') diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c index 7841ea603c9..be79dc9f386 100644 --- a/fs/nfs/nfs4filelayout.c +++ b/fs/nfs/nfs4filelayout.c @@ -418,7 +418,8 @@ static int filelayout_check_layout(struct pnfs_layout_hdr *lo, struct nfs4_filelayout_segment *fl, struct nfs4_layoutget_res *lgr, - struct nfs4_deviceid *id) + struct nfs4_deviceid *id, + gfp_t gfp_flags) { struct nfs4_file_layout_dsaddr *dsaddr; int status = -EINVAL; @@ -441,7 +442,7 @@ filelayout_check_layout(struct pnfs_layout_hdr *lo, /* find and reference the deviceid */ dsaddr = nfs4_fl_find_get_deviceid(id); if (dsaddr == NULL) { - dsaddr = get_device_info(lo->plh_inode, id); + dsaddr = get_device_info(lo->plh_inode, id, gfp_flags); if (dsaddr == NULL) goto out; } @@ -502,7 +503,8 @@ static int filelayout_decode_layout(struct pnfs_layout_hdr *flo, struct nfs4_filelayout_segment *fl, struct nfs4_layoutget_res *lgr, - struct nfs4_deviceid *id) + struct nfs4_deviceid *id, + gfp_t gfp_flags) { struct xdr_stream stream; struct xdr_buf buf = { @@ -518,7 +520,7 @@ filelayout_decode_layout(struct pnfs_layout_hdr *flo, dprintk("%s: set_layout_map Begin\n", __func__); - scratch = alloc_page(GFP_KERNEL); + scratch = alloc_page(gfp_flags); if (!scratch) return -ENOMEM; @@ -556,13 +558,13 @@ filelayout_decode_layout(struct pnfs_layout_hdr *flo, goto out_err; fl->fh_array = kzalloc(fl->num_fh * sizeof(struct nfs_fh *), - GFP_KERNEL); + gfp_flags); if (!fl->fh_array) goto out_err; for (i = 0; i < fl->num_fh; i++) { /* Do we want to use a mempool here? */ - fl->fh_array[i] = kmalloc(sizeof(struct nfs_fh), GFP_KERNEL); + fl->fh_array[i] = kmalloc(sizeof(struct nfs_fh), gfp_flags); if (!fl->fh_array[i]) goto out_err_free; @@ -607,19 +609,20 @@ filelayout_free_lseg(struct pnfs_layout_segment *lseg) static struct pnfs_layout_segment * filelayout_alloc_lseg(struct pnfs_layout_hdr *layoutid, - struct nfs4_layoutget_res *lgr) + struct nfs4_layoutget_res *lgr, + gfp_t gfp_flags) { struct nfs4_filelayout_segment *fl; int rc; struct nfs4_deviceid id; dprintk("--> %s\n", __func__); - fl = kzalloc(sizeof(*fl), GFP_KERNEL); + fl = kzalloc(sizeof(*fl), gfp_flags); if (!fl) return NULL; - rc = filelayout_decode_layout(layoutid, fl, lgr, &id); - if (rc != 0 || filelayout_check_layout(layoutid, fl, lgr, &id)) { + rc = filelayout_decode_layout(layoutid, fl, lgr, &id, gfp_flags); + if (rc != 0 || filelayout_check_layout(layoutid, fl, lgr, &id, gfp_flags)) { _filelayout_free_lseg(fl); return NULL; } @@ -635,7 +638,7 @@ filelayout_alloc_lseg(struct pnfs_layout_hdr *layoutid, int size = (fl->stripe_type == STRIPE_SPARSE) ? fl->dsaddr->ds_num : fl->dsaddr->stripe_count; - fl->commit_buckets = kcalloc(size, sizeof(struct list_head), GFP_KERNEL); + fl->commit_buckets = kcalloc(size, sizeof(struct list_head), gfp_flags); if (!fl->commit_buckets) { filelayout_free_lseg(&fl->generic_hdr); return NULL; diff --git a/fs/nfs/nfs4filelayout.h b/fs/nfs/nfs4filelayout.h index 7c44579f583..2b461d77b43 100644 --- a/fs/nfs/nfs4filelayout.h +++ b/fs/nfs/nfs4filelayout.h @@ -104,6 +104,6 @@ extern struct nfs4_file_layout_dsaddr * nfs4_fl_find_get_deviceid(struct nfs4_deviceid *dev_id); extern void nfs4_fl_put_deviceid(struct nfs4_file_layout_dsaddr *dsaddr); struct nfs4_file_layout_dsaddr * -get_device_info(struct inode *inode, struct nfs4_deviceid *dev_id); +get_device_info(struct inode *inode, struct nfs4_deviceid *dev_id, gfp_t gfp_flags); #endif /* FS_NFS_NFS4FILELAYOUT_H */ diff --git a/fs/nfs/nfs4filelayoutdev.c b/fs/nfs/nfs4filelayoutdev.c index de5350f2b24..db07c7af139 100644 --- a/fs/nfs/nfs4filelayoutdev.c +++ b/fs/nfs/nfs4filelayoutdev.c @@ -225,11 +225,11 @@ nfs4_fl_free_deviceid(struct nfs4_file_layout_dsaddr *dsaddr) } static struct nfs4_pnfs_ds * -nfs4_pnfs_ds_add(struct inode *inode, u32 ip_addr, u32 port) +nfs4_pnfs_ds_add(struct inode *inode, u32 ip_addr, u32 port, gfp_t gfp_flags) { struct nfs4_pnfs_ds *tmp_ds, *ds; - ds = kzalloc(sizeof(*tmp_ds), GFP_KERNEL); + ds = kzalloc(sizeof(*tmp_ds), gfp_flags); if (!ds) goto out; @@ -261,7 +261,7 @@ out: * Currently only support ipv4, and one multi-path address. */ static struct nfs4_pnfs_ds * -decode_and_add_ds(struct xdr_stream *streamp, struct inode *inode) +decode_and_add_ds(struct xdr_stream *streamp, struct inode *inode, gfp_t gfp_flags) { struct nfs4_pnfs_ds *ds = NULL; char *buf; @@ -303,7 +303,7 @@ decode_and_add_ds(struct xdr_stream *streamp, struct inode *inode) rlen); goto out_err; } - buf = kmalloc(rlen + 1, GFP_KERNEL); + buf = kmalloc(rlen + 1, gfp_flags); if (!buf) { dprintk("%s: Not enough memory\n", __func__); goto out_err; @@ -333,7 +333,7 @@ decode_and_add_ds(struct xdr_stream *streamp, struct inode *inode) sscanf(pstr, "-%d-%d", &tmp[0], &tmp[1]); port = htons((tmp[0] << 8) | (tmp[1])); - ds = nfs4_pnfs_ds_add(inode, ip_addr, port); + ds = nfs4_pnfs_ds_add(inode, ip_addr, port, gfp_flags); dprintk("%s: Decoded address and port %s\n", __func__, buf); out_free: kfree(buf); @@ -343,7 +343,7 @@ out_err: /* Decode opaque device data and return the result */ static struct nfs4_file_layout_dsaddr* -decode_device(struct inode *ino, struct pnfs_device *pdev) +decode_device(struct inode *ino, struct pnfs_device *pdev, gfp_t gfp_flags) { int i; u32 cnt, num; @@ -362,7 +362,7 @@ decode_device(struct inode *ino, struct pnfs_device *pdev) struct page *scratch; /* set up xdr stream */ - scratch = alloc_page(GFP_KERNEL); + scratch = alloc_page(gfp_flags); if (!scratch) goto out_err; @@ -384,7 +384,7 @@ decode_device(struct inode *ino, struct pnfs_device *pdev) } /* read stripe indices */ - stripe_indices = kcalloc(cnt, sizeof(u8), GFP_KERNEL); + stripe_indices = kcalloc(cnt, sizeof(u8), gfp_flags); if (!stripe_indices) goto out_err_free_scratch; @@ -423,7 +423,7 @@ decode_device(struct inode *ino, struct pnfs_device *pdev) dsaddr = kzalloc(sizeof(*dsaddr) + (sizeof(struct nfs4_pnfs_ds *) * (num - 1)), - GFP_KERNEL); + gfp_flags); if (!dsaddr) goto out_err_free_stripe_indices; @@ -452,7 +452,7 @@ decode_device(struct inode *ino, struct pnfs_device *pdev) for (j = 0; j < mp_count; j++) { if (j == 0) { dsaddr->ds_list[i] = decode_and_add_ds(&stream, - ino); + ino, gfp_flags); if (dsaddr->ds_list[i] == NULL) goto out_err_free_deviceid; } else { @@ -503,12 +503,12 @@ out_err: * available devices. */ static struct nfs4_file_layout_dsaddr * -decode_and_add_device(struct inode *inode, struct pnfs_device *dev) +decode_and_add_device(struct inode *inode, struct pnfs_device *dev, gfp_t gfp_flags) { struct nfs4_file_layout_dsaddr *d, *new; long hash; - new = decode_device(inode, dev); + new = decode_device(inode, dev, gfp_flags); if (!new) { printk(KERN_WARNING "%s: Could not decode or add device\n", __func__); @@ -537,7 +537,7 @@ decode_and_add_device(struct inode *inode, struct pnfs_device *dev) * of available devices, and return it. */ struct nfs4_file_layout_dsaddr * -get_device_info(struct inode *inode, struct nfs4_deviceid *dev_id) +get_device_info(struct inode *inode, struct nfs4_deviceid *dev_id, gfp_t gfp_flags) { struct pnfs_device *pdev = NULL; u32 max_resp_sz; @@ -556,17 +556,17 @@ get_device_info(struct inode *inode, struct nfs4_deviceid *dev_id) dprintk("%s inode %p max_resp_sz %u max_pages %d\n", __func__, inode, max_resp_sz, max_pages); - pdev = kzalloc(sizeof(struct pnfs_device), GFP_KERNEL); + pdev = kzalloc(sizeof(struct pnfs_device), gfp_flags); if (pdev == NULL) return NULL; - pages = kzalloc(max_pages * sizeof(struct page *), GFP_KERNEL); + pages = kzalloc(max_pages * sizeof(struct page *), gfp_flags); if (pages == NULL) { kfree(pdev); return NULL; } for (i = 0; i < max_pages; i++) { - pages[i] = alloc_page(GFP_KERNEL); + pages[i] = alloc_page(gfp_flags); if (!pages[i]) goto out_free; } @@ -587,7 +587,7 @@ get_device_info(struct inode *inode, struct nfs4_deviceid *dev_id) * Found new device, need to decode it and then add it to the * list of known devices for this mountpoint. */ - dsaddr = decode_and_add_device(inode, pdev); + dsaddr = decode_and_add_device(inode, pdev, gfp_flags); out_free: for (i = 0; i < max_pages; i++) __free_page(pages[i]); diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 65455f58b10..f57f5281a52 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -467,7 +467,8 @@ pnfs_choose_layoutget_stateid(nfs4_stateid *dst, struct pnfs_layout_hdr *lo, static struct pnfs_layout_segment * send_layoutget(struct pnfs_layout_hdr *lo, struct nfs_open_context *ctx, - u32 iomode) + u32 iomode, + gfp_t gfp_flags) { struct inode *ino = lo->plh_inode; struct nfs_server *server = NFS_SERVER(ino); @@ -480,7 +481,7 @@ send_layoutget(struct pnfs_layout_hdr *lo, dprintk("--> %s\n", __func__); BUG_ON(ctx == NULL); - lgp = kzalloc(sizeof(*lgp), GFP_KERNEL); + lgp = kzalloc(sizeof(*lgp), gfp_flags); if (lgp == NULL) return NULL; @@ -488,12 +489,12 @@ send_layoutget(struct pnfs_layout_hdr *lo, max_resp_sz = server->nfs_client->cl_session->fc_attrs.max_resp_sz; max_pages = max_resp_sz >> PAGE_SHIFT; - pages = kzalloc(max_pages * sizeof(struct page *), GFP_KERNEL); + pages = kzalloc(max_pages * sizeof(struct page *), gfp_flags); if (!pages) goto out_err_free; for (i = 0; i < max_pages; i++) { - pages[i] = alloc_page(GFP_KERNEL); + pages[i] = alloc_page(gfp_flags); if (!pages[i]) goto out_err_free; } @@ -509,6 +510,7 @@ send_layoutget(struct pnfs_layout_hdr *lo, lgp->args.layout.pages = pages; lgp->args.layout.pglen = max_pages * PAGE_SIZE; lgp->lsegpp = &lseg; + lgp->gfp_flags = gfp_flags; /* Synchronously retrieve layout information from server and * store in lseg. @@ -666,11 +668,11 @@ pnfs_insert_layout(struct pnfs_layout_hdr *lo, } static struct pnfs_layout_hdr * -alloc_init_layout_hdr(struct inode *ino) +alloc_init_layout_hdr(struct inode *ino, gfp_t gfp_flags) { struct pnfs_layout_hdr *lo; - lo = kzalloc(sizeof(struct pnfs_layout_hdr), GFP_KERNEL); + lo = kzalloc(sizeof(struct pnfs_layout_hdr), gfp_flags); if (!lo) return NULL; atomic_set(&lo->plh_refcount, 1); @@ -682,7 +684,7 @@ alloc_init_layout_hdr(struct inode *ino) } static struct pnfs_layout_hdr * -pnfs_find_alloc_layout(struct inode *ino) +pnfs_find_alloc_layout(struct inode *ino, gfp_t gfp_flags) { struct nfs_inode *nfsi = NFS_I(ino); struct pnfs_layout_hdr *new = NULL; @@ -697,7 +699,7 @@ pnfs_find_alloc_layout(struct inode *ino) return nfsi->layout; } spin_unlock(&ino->i_lock); - new = alloc_init_layout_hdr(ino); + new = alloc_init_layout_hdr(ino, gfp_flags); spin_lock(&ino->i_lock); if (likely(nfsi->layout == NULL)) /* Won the race? */ @@ -757,7 +759,8 @@ pnfs_find_lseg(struct pnfs_layout_hdr *lo, u32 iomode) struct pnfs_layout_segment * pnfs_update_layout(struct inode *ino, struct nfs_open_context *ctx, - enum pnfs_iomode iomode) + enum pnfs_iomode iomode, + gfp_t gfp_flags) { struct nfs_inode *nfsi = NFS_I(ino); struct nfs_client *clp = NFS_SERVER(ino)->nfs_client; @@ -768,7 +771,7 @@ pnfs_update_layout(struct inode *ino, if (!pnfs_enabled_sb(NFS_SERVER(ino))) return NULL; spin_lock(&ino->i_lock); - lo = pnfs_find_alloc_layout(ino); + lo = pnfs_find_alloc_layout(ino, gfp_flags); if (lo == NULL) { dprintk("%s ERROR: can't get pnfs_layout_hdr\n", __func__); goto out_unlock; @@ -808,7 +811,7 @@ pnfs_update_layout(struct inode *ino, spin_unlock(&clp->cl_lock); } - lseg = send_layoutget(lo, ctx, iomode); + lseg = send_layoutget(lo, ctx, iomode, gfp_flags); if (!lseg && first) { spin_lock(&clp->cl_lock); list_del_init(&lo->plh_layouts); @@ -847,7 +850,7 @@ pnfs_layout_process(struct nfs4_layoutget *lgp) goto out; } /* Inject layout blob into I/O device driver */ - lseg = NFS_SERVER(ino)->pnfs_curr_ld->alloc_lseg(lo, res); + lseg = NFS_SERVER(ino)->pnfs_curr_ld->alloc_lseg(lo, res, lgp->gfp_flags); if (!lseg || IS_ERR(lseg)) { if (!lseg) status = -ENOMEM; @@ -900,7 +903,8 @@ static int pnfs_read_pg_test(struct nfs_pageio_descriptor *pgio, /* This is first coelesce call for a series of nfs_pages */ pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, prev->wb_context, - IOMODE_READ); + IOMODE_READ, + GFP_KERNEL); } return NFS_SERVER(pgio->pg_inode)->pnfs_curr_ld->pg_test(pgio, prev, req); } @@ -922,7 +926,8 @@ static int pnfs_write_pg_test(struct nfs_pageio_descriptor *pgio, /* This is first coelesce call for a series of nfs_pages */ pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, prev->wb_context, - IOMODE_RW); + IOMODE_RW, + GFP_NOFS); } return NFS_SERVER(pgio->pg_inode)->pnfs_curr_ld->pg_test(pgio, prev, req); } diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index bc4827202e7..0c015bad9e7 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -70,7 +70,7 @@ struct pnfs_layoutdriver_type { const u32 id; const char *name; struct module *owner; - struct pnfs_layout_segment * (*alloc_lseg) (struct pnfs_layout_hdr *layoutid, struct nfs4_layoutget_res *lgr); + struct pnfs_layout_segment * (*alloc_lseg) (struct pnfs_layout_hdr *layoutid, struct nfs4_layoutget_res *lgr, gfp_t gfp_flags); void (*free_lseg) (struct pnfs_layout_segment *lseg); /* test for nfs page cache coalescing */ @@ -126,7 +126,7 @@ void get_layout_hdr(struct pnfs_layout_hdr *lo); void put_lseg(struct pnfs_layout_segment *lseg); struct pnfs_layout_segment * pnfs_update_layout(struct inode *ino, struct nfs_open_context *ctx, - enum pnfs_iomode access_type); + enum pnfs_iomode access_type, gfp_t gfp_flags); void set_pnfs_layoutdriver(struct nfs_server *, u32 id); void unset_pnfs_layoutdriver(struct nfs_server *); enum pnfs_try_status pnfs_try_to_write_data(struct nfs_write_data *, @@ -245,7 +245,7 @@ static inline void put_lseg(struct pnfs_layout_segment *lseg) static inline struct pnfs_layout_segment * pnfs_update_layout(struct inode *ino, struct nfs_open_context *ctx, - enum pnfs_iomode access_type) + enum pnfs_iomode access_type, gfp_t gfp_flags) { return NULL; } diff --git a/fs/nfs/read.c b/fs/nfs/read.c index 7cded2b12a0..2bcf0dc306a 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -288,7 +288,7 @@ static int nfs_pagein_multi(struct nfs_pageio_descriptor *desc) atomic_set(&req->wb_complete, requests); BUG_ON(desc->pg_lseg != NULL); - lseg = pnfs_update_layout(desc->pg_inode, req->wb_context, IOMODE_READ); + lseg = pnfs_update_layout(desc->pg_inode, req->wb_context, IOMODE_READ, GFP_KERNEL); ClearPageError(page); offset = 0; nbytes = desc->pg_count; @@ -351,7 +351,7 @@ static int nfs_pagein_one(struct nfs_pageio_descriptor *desc) } req = nfs_list_entry(data->pages.next); if ((!lseg) && list_is_singular(&data->pages)) - lseg = pnfs_update_layout(desc->pg_inode, req->wb_context, IOMODE_READ); + lseg = pnfs_update_layout(desc->pg_inode, req->wb_context, IOMODE_READ, GFP_KERNEL); ret = nfs_read_rpcsetup(req, data, &nfs_read_full_ops, desc->pg_count, 0, lseg); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 3bd5d7e80f6..49c715b4ac9 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -939,7 +939,7 @@ static int nfs_flush_multi(struct nfs_pageio_descriptor *desc) atomic_set(&req->wb_complete, requests); BUG_ON(desc->pg_lseg); - lseg = pnfs_update_layout(desc->pg_inode, req->wb_context, IOMODE_RW); + lseg = pnfs_update_layout(desc->pg_inode, req->wb_context, IOMODE_RW, GFP_NOFS); ClearPageError(page); offset = 0; nbytes = desc->pg_count; @@ -1013,7 +1013,7 @@ static int nfs_flush_one(struct nfs_pageio_descriptor *desc) } req = nfs_list_entry(data->pages.next); if ((!lseg) && list_is_singular(&data->pages)) - lseg = pnfs_update_layout(desc->pg_inode, req->wb_context, IOMODE_RW); + lseg = pnfs_update_layout(desc->pg_inode, req->wb_context, IOMODE_RW, GFP_NOFS); if ((desc->pg_ioflags & FLUSH_COND_STABLE) && (desc->pg_moreio || NFS_I(desc->pg_inode)->ncommit)) diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 890dce24263..7e371f7df9c 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -233,6 +233,7 @@ struct nfs4_layoutget { struct nfs4_layoutget_args args; struct nfs4_layoutget_res res; struct pnfs_layout_segment **lsegpp; + gfp_t gfp_flags; }; struct nfs4_getdeviceinfo_args { -- cgit v1.2.3-70-g09d2 From 3e51e3edfd81bfd9853ad7de91167e4ce33d0fe7 Mon Sep 17 00:00:00 2001 From: Samir Bellabes Date: Wed, 11 May 2011 18:18:05 +0200 Subject: sched: Remove unused parameters from sched_fork() and wake_up_new_task() sched_fork() and wake_up_new_task() are defined with a parameter 'unsigned long clone_flags', which is unused. This patch removes the parameters. Signed-off-by: Samir Bellabes Acked-by: Peter Zijlstra Link: http://lkml.kernel.org/r/1305130685-1047-1-git-send-email-sam@synack.fr Signed-off-by: Ingo Molnar --- include/linux/sched.h | 5 ++--- kernel/fork.c | 4 ++-- kernel/sched.c | 4 ++-- 3 files changed, 6 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 6b4280b23ee..12211e1666e 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2051,14 +2051,13 @@ extern void xtime_update(unsigned long ticks); extern int wake_up_state(struct task_struct *tsk, unsigned int state); extern int wake_up_process(struct task_struct *tsk); -extern void wake_up_new_task(struct task_struct *tsk, - unsigned long clone_flags); +extern void wake_up_new_task(struct task_struct *tsk); #ifdef CONFIG_SMP extern void kick_process(struct task_struct *tsk); #else static inline void kick_process(struct task_struct *tsk) { } #endif -extern void sched_fork(struct task_struct *p, int clone_flags); +extern void sched_fork(struct task_struct *p); extern void sched_dead(struct task_struct *p); extern void proc_caches_init(void); diff --git a/kernel/fork.c b/kernel/fork.c index aca62871a4f..2b44d82b823 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1152,7 +1152,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, #endif /* Perform scheduler related setup. Assign this task to a CPU. */ - sched_fork(p, clone_flags); + sched_fork(p); retval = perf_event_init_task(p); if (retval) @@ -1463,7 +1463,7 @@ long do_fork(unsigned long clone_flags, */ p->flags &= ~PF_STARTING; - wake_up_new_task(p, clone_flags); + wake_up_new_task(p); tracehook_report_clone_complete(trace, regs, clone_flags, nr, p); diff --git a/kernel/sched.c b/kernel/sched.c index da933815048..f9778c0d91e 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2741,7 +2741,7 @@ static void __sched_fork(struct task_struct *p) /* * fork()/clone()-time setup: */ -void sched_fork(struct task_struct *p, int clone_flags) +void sched_fork(struct task_struct *p) { unsigned long flags; int cpu = get_cpu(); @@ -2823,7 +2823,7 @@ void sched_fork(struct task_struct *p, int clone_flags) * that must be done for every newly created context, then puts the task * on the runqueue and wakes it. */ -void wake_up_new_task(struct task_struct *p, unsigned long clone_flags) +void wake_up_new_task(struct task_struct *p) { unsigned long flags; struct rq *rq; -- cgit v1.2.3-70-g09d2 From 5db1256a5131d3b133946fa02ac9770a784e6eb2 Mon Sep 17 00:00:00 2001 From: Milton Miller Date: Thu, 12 May 2011 04:13:54 -0500 Subject: seqlock: Don't smp_rmb in seqlock reader spin loop Move the smp_rmb after cpu_relax loop in read_seqlock and add ACCESS_ONCE to make sure the test and return are consistent. A multi-threaded core in the lab didn't like the update from 2.6.35 to 2.6.36, to the point it would hang during boot when multiple threads were active. Bisection showed af5ab277ded04bd9bc6b048c5a2f0e7d70ef0867 (clockevents: Remove the per cpu tick skew) as the culprit and it is supported with stack traces showing xtime_lock waits including tick_do_update_jiffies64 and/or update_vsyscall. Experimentation showed the combination of cpu_relax and smp_rmb was significantly slowing the progress of other threads sharing the core, and this patch is effective in avoiding the hang. A theory is the rmb is affecting the whole core while the cpu_relax is causing a resource rebalance flush, together they cause an interfernce cadance that is unbroken when the seqlock reader has interrupts disabled. At first I was confused why the refactor in 3c22cd5709e8143444a6d08682a87f4c57902df3 (kernel: optimise seqlock) didn't affect this patch application, but after some study that affected seqcount not seqlock. The new seqcount was not factored back into the seqlock. I defer that the future. While the removal of the timer interrupt offset created contention for the xtime lock while a cpu does the additonal work to update the system clock, the seqlock implementation with the tight rmb spin loop goes back much further, and is just waiting for the right trigger. Cc: Signed-off-by: Milton Miller Cc: Cc: Linus Torvalds Cc: Andi Kleen Cc: Nick Piggin Cc: Benjamin Herrenschmidt Cc: Anton Blanchard Cc: Paul McKenney Acked-by: Eric Dumazet Link: http://lkml.kernel.org/r/%3Cseqlock-rmb%40mdm.bga.com%3E Signed-off-by: Thomas Gleixner --- include/linux/seqlock.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index e98cd2e5719..06d69648fc8 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -88,12 +88,12 @@ static __always_inline unsigned read_seqbegin(const seqlock_t *sl) unsigned ret; repeat: - ret = sl->sequence; - smp_rmb(); + ret = ACCESS_ONCE(sl->sequence); if (unlikely(ret & 1)) { cpu_relax(); goto repeat; } + smp_rmb(); return ret; } -- cgit v1.2.3-70-g09d2 From 698b368275c3fa98261159253cfc79653f9dffc6 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 11 May 2011 14:49:36 -0700 Subject: fbcon: add lifetime refcount to opened frame buffers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This just adds the refcount and the new registration lock logic. It does not (for example) actually change the read/write/ioctl routines to actually use the frame buffer that was opened: those function still end up alway susing whatever the current frame buffer is at the time of the call. Without this, if something holds the frame buffer open over a framebuffer switch, the close() operation after the switch will access a fb_info that has been free'd by the unregistering of the old frame buffer. (The read/write/ioctl operations will normally not cause problems, because they will - illogically - pick up the new fbcon instead. But a switch that happens just as one of those is going on might see problems too, the window is just much smaller: one individual op rather than the whole open-close sequence.) This use-after-free is apparently fairly easily triggered by the Ubuntu 11.04 boot sequence. Acked-by: Tim Gardner Tested-by: Daniel J Blueman Tested-by: Anca Emanuel Cc: Bruno PrĂ©mont Cc: Alan Cox Cc: Paul Mundt Cc: Dave Airlie Cc: Andy Whitcroft Signed-off-by: Linus Torvalds --- drivers/video/fbmem.c | 56 ++++++++++++++++++++++++++++++++++++++++++--------- include/linux/fb.h | 1 + 2 files changed, 47 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/drivers/video/fbmem.c b/drivers/video/fbmem.c index e0c2284924b..eec14d2ca1c 100644 --- a/drivers/video/fbmem.c +++ b/drivers/video/fbmem.c @@ -42,9 +42,34 @@ #define FBPIXMAPSIZE (1024 * 8) +static DEFINE_MUTEX(registration_lock); struct fb_info *registered_fb[FB_MAX] __read_mostly; int num_registered_fb __read_mostly; +static struct fb_info *get_fb_info(unsigned int idx) +{ + struct fb_info *fb_info; + + if (idx >= FB_MAX) + return ERR_PTR(-ENODEV); + + mutex_lock(®istration_lock); + fb_info = registered_fb[idx]; + if (fb_info) + atomic_inc(&fb_info->count); + mutex_unlock(®istration_lock); + + return fb_info; +} + +static void put_fb_info(struct fb_info *fb_info) +{ + if (!atomic_dec_and_test(&fb_info->count)) + return; + if (fb_info->fbops->fb_destroy) + fb_info->fbops->fb_destroy(fb_info); +} + int lock_fb_info(struct fb_info *info) { mutex_lock(&info->lock); @@ -647,6 +672,7 @@ int fb_show_logo(struct fb_info *info, int rotate) { return 0; } static void *fb_seq_start(struct seq_file *m, loff_t *pos) { + mutex_lock(®istration_lock); return (*pos < FB_MAX) ? pos : NULL; } @@ -658,6 +684,7 @@ static void *fb_seq_next(struct seq_file *m, void *v, loff_t *pos) static void fb_seq_stop(struct seq_file *m, void *v) { + mutex_unlock(®istration_lock); } static int fb_seq_show(struct seq_file *m, void *v) @@ -1361,14 +1388,16 @@ __releases(&info->lock) struct fb_info *info; int res = 0; - if (fbidx >= FB_MAX) - return -ENODEV; - info = registered_fb[fbidx]; - if (!info) + info = get_fb_info(fbidx); + if (!info) { request_module("fb%d", fbidx); - info = registered_fb[fbidx]; - if (!info) - return -ENODEV; + info = get_fb_info(fbidx); + if (!info) + return -ENODEV; + } + if (IS_ERR(info)) + return PTR_ERR(info); + mutex_lock(&info->lock); if (!try_module_get(info->fbops->owner)) { res = -ENODEV; @@ -1386,6 +1415,8 @@ __releases(&info->lock) #endif out: mutex_unlock(&info->lock); + if (res) + put_fb_info(info); return res; } @@ -1401,6 +1432,7 @@ __releases(&info->lock) info->fbops->fb_release(info,1); module_put(info->fbops->owner); mutex_unlock(&info->lock); + put_fb_info(info); return 0; } @@ -1542,11 +1574,13 @@ register_framebuffer(struct fb_info *fb_info) remove_conflicting_framebuffers(fb_info->apertures, fb_info->fix.id, fb_is_primary_device(fb_info)); + mutex_lock(®istration_lock); num_registered_fb++; for (i = 0 ; i < FB_MAX; i++) if (!registered_fb[i]) break; fb_info->node = i; + atomic_set(&fb_info->count, 1); mutex_init(&fb_info->lock); mutex_init(&fb_info->mm_lock); @@ -1583,6 +1617,7 @@ register_framebuffer(struct fb_info *fb_info) fb_var_to_videomode(&mode, &fb_info->var); fb_add_videomode(&mode, &fb_info->modelist); registered_fb[i] = fb_info; + mutex_unlock(®istration_lock); event.info = fb_info; if (!lock_fb_info(fb_info)) @@ -1616,6 +1651,7 @@ unregister_framebuffer(struct fb_info *fb_info) struct fb_event event; int i, ret = 0; + mutex_lock(®istration_lock); i = fb_info->node; if (!registered_fb[i]) { ret = -EINVAL; @@ -1638,7 +1674,7 @@ unregister_framebuffer(struct fb_info *fb_info) (fb_info->pixmap.flags & FB_PIXMAP_DEFAULT)) kfree(fb_info->pixmap.addr); fb_destroy_modelist(&fb_info->modelist); - registered_fb[i]=NULL; + registered_fb[i] = NULL; num_registered_fb--; fb_cleanup_device(fb_info); device_destroy(fb_class, MKDEV(FB_MAJOR, i)); @@ -1646,9 +1682,9 @@ unregister_framebuffer(struct fb_info *fb_info) fb_notifier_call_chain(FB_EVENT_FB_UNREGISTERED, &event); /* this may free fb info */ - if (fb_info->fbops->fb_destroy) - fb_info->fbops->fb_destroy(fb_info); + put_fb_info(fb_info); done: + mutex_unlock(®istration_lock); return ret; } diff --git a/include/linux/fb.h b/include/linux/fb.h index df728c1c29e..6a827487717 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -832,6 +832,7 @@ struct fb_tile_ops { #define FBINFO_CAN_FORCE_OUTPUT 0x200000 struct fb_info { + atomic_t count; int node; int flags; struct mutex lock; /* Lock for open/release/ioctl funcs */ -- cgit v1.2.3-70-g09d2 From ca06707022d6ba4744198a8ebbe4994786b0c613 Mon Sep 17 00:00:00 2001 From: "Steinar H. Gunderson" Date: Fri, 6 May 2011 23:44:46 +0000 Subject: ipv6: restore correct ECN handling on TCP xmit Since commit e9df2e8fd8fbc9 (Use appropriate sock tclass setting for routing lookup) we lost ability to properly add ECN codemarks to ipv6 TCP frames. It seems like TCP_ECN_send() calls INET_ECN_xmit(), which only sets the ECN bit in the IPv4 ToS field (inet_sk(sk)->tos), but after the patch, what's checked is inet6_sk(sk)->tclass, which is a completely different field. Close bug https://bugzilla.kernel.org/show_bug.cgi?id=34322 [Eric Dumazet] : added the INET_ECN_dontxmit() fix and replace macros by inline functions for clarity. Signed-off-by: Steinar H. Gunderson Signed-off-by: Eric Dumazet Cc: YOSHIFUJI Hideaki Cc: Andrew Morton Signed-off-by: David S. Miller --- include/net/inet_ecn.h | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/inet_ecn.h b/include/net/inet_ecn.h index 88bdd010d65..2fa8d1341a0 100644 --- a/include/net/inet_ecn.h +++ b/include/net/inet_ecn.h @@ -38,9 +38,19 @@ static inline __u8 INET_ECN_encapsulate(__u8 outer, __u8 inner) return outer; } -#define INET_ECN_xmit(sk) do { inet_sk(sk)->tos |= INET_ECN_ECT_0; } while (0) -#define INET_ECN_dontxmit(sk) \ - do { inet_sk(sk)->tos &= ~INET_ECN_MASK; } while (0) +static inline void INET_ECN_xmit(struct sock *sk) +{ + inet_sk(sk)->tos |= INET_ECN_ECT_0; + if (inet6_sk(sk) != NULL) + inet6_sk(sk)->tclass |= INET_ECN_ECT_0; +} + +static inline void INET_ECN_dontxmit(struct sock *sk) +{ + inet_sk(sk)->tos &= ~INET_ECN_MASK; + if (inet6_sk(sk) != NULL) + inet6_sk(sk)->tclass &= ~INET_ECN_MASK; +} #define IP6_ECN_flow_init(label) do { \ (label) &= ~htonl(INET_ECN_MASK << 20); \ -- cgit v1.2.3-70-g09d2 From 47a150edc2ae734c0f4bf50aa19499e23b9a46f8 Mon Sep 17 00:00:00 2001 From: "Serge E. Hallyn" Date: Fri, 13 May 2011 04:27:54 +0100 Subject: Cache user_ns in struct cred If !CONFIG_USERNS, have current_user_ns() defined to (&init_user_ns). Get rid of _current_user_ns. This requires nsown_capable() to be defined in capability.c rather than as static inline in capability.h, so do that. Request_key needs init_user_ns defined at current_user_ns if !CONFIG_USERNS, so forward-declare that in cred.h if !CONFIG_USERNS at current_user_ns() define. Compile-tested with and without CONFIG_USERNS. Signed-off-by: Serge E. Hallyn [ This makes a huge performance difference for acl_permission_check(), up to 30%. And that is one of the hottest kernel functions for loads that are pathname-lookup heavy. ] Signed-off-by: Linus Torvalds --- include/linux/capability.h | 13 +------------ include/linux/cred.h | 10 ++++++++-- kernel/capability.c | 12 ++++++++++++ kernel/cred.c | 12 ++++++------ 4 files changed, 27 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/include/linux/capability.h b/include/linux/capability.h index 16ee8b49a20..d4675af963f 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -546,18 +546,7 @@ extern bool has_capability_noaudit(struct task_struct *t, int cap); extern bool capable(int cap); extern bool ns_capable(struct user_namespace *ns, int cap); extern bool task_ns_capable(struct task_struct *t, int cap); - -/** - * nsown_capable - Check superior capability to one's own user_ns - * @cap: The capability in question - * - * Return true if the current task has the given superior capability - * targeted at its own user namespace. - */ -static inline bool nsown_capable(int cap) -{ - return ns_capable(current_user_ns(), cap); -} +extern bool nsown_capable(int cap); /* audit system wants to get cap info from files as well */ extern int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps); diff --git a/include/linux/cred.h b/include/linux/cred.h index 9aeeb0ba200..be16b61283c 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -146,6 +146,7 @@ struct cred { void *security; /* subjective LSM security */ #endif struct user_struct *user; /* real user ID subscription */ + struct user_namespace *user_ns; /* cached user->user_ns */ struct group_info *group_info; /* supplementary groups for euid/fsgid */ struct rcu_head rcu; /* RCU deletion hook */ }; @@ -354,10 +355,15 @@ static inline void put_cred(const struct cred *_cred) #define current_fsgid() (current_cred_xxx(fsgid)) #define current_cap() (current_cred_xxx(cap_effective)) #define current_user() (current_cred_xxx(user)) -#define _current_user_ns() (current_cred_xxx(user)->user_ns) #define current_security() (current_cred_xxx(security)) -extern struct user_namespace *current_user_ns(void); +#ifdef CONFIG_USER_NS +#define current_user_ns() (current_cred_xxx(user_ns)) +#else +extern struct user_namespace init_user_ns; +#define current_user_ns() (&init_user_ns) +#endif + #define current_uid_gid(_uid, _gid) \ do { \ diff --git a/kernel/capability.c b/kernel/capability.c index bf0c734d0c1..32a80e08ff4 100644 --- a/kernel/capability.c +++ b/kernel/capability.c @@ -399,3 +399,15 @@ bool task_ns_capable(struct task_struct *t, int cap) return ns_capable(task_cred_xxx(t, user)->user_ns, cap); } EXPORT_SYMBOL(task_ns_capable); + +/** + * nsown_capable - Check superior capability to one's own user_ns + * @cap: The capability in question + * + * Return true if the current task has the given superior capability + * targeted at its own user namespace. + */ +bool nsown_capable(int cap) +{ + return ns_capable(current_user_ns(), cap); +} diff --git a/kernel/cred.c b/kernel/cred.c index 5557b55048d..8093c16b84b 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -54,6 +54,7 @@ struct cred init_cred = { .cap_effective = CAP_INIT_EFF_SET, .cap_bset = CAP_INIT_BSET, .user = INIT_USER, + .user_ns = &init_user_ns, .group_info = &init_groups, #ifdef CONFIG_KEYS .tgcred = &init_tgcred, @@ -410,6 +411,11 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags) goto error_put; } + /* cache user_ns in cred. Doesn't need a refcount because it will + * stay pinned by cred->user + */ + new->user_ns = new->user->user_ns; + #ifdef CONFIG_KEYS /* new threads get their own thread keyrings if their parent already * had one */ @@ -741,12 +747,6 @@ int set_create_files_as(struct cred *new, struct inode *inode) } EXPORT_SYMBOL(set_create_files_as); -struct user_namespace *current_user_ns(void) -{ - return _current_user_ns(); -} -EXPORT_SYMBOL(current_user_ns); - #ifdef CONFIG_DEBUG_CREDENTIALS bool creds_are_invalid(const struct cred *cred) -- cgit v1.2.3-70-g09d2 From a10e14667635dde504ed9e7ee851494c2cf2ae8e Mon Sep 17 00:00:00 2001 From: Vitalii Demianets Date: Thu, 12 May 2011 23:04:29 +0000 Subject: bonding,llc: Fix structure sizeof incompatibility for some PDUs With some combinations of arch/compiler (e.g. arm-linux-gcc) the sizeof operator on structure returns value greater than expected. In cases when the structure is used for mapping PDU fields it may lead to unexpected results (such as holes and alignment problems in skb data). __packed prevents this undesired behavior. Signed-off-by: Vitalii Demianets Signed-off-by: David S. Miller --- drivers/net/bonding/bond_3ad.h | 10 +++++----- include/net/llc_pdu.h | 8 ++++---- 2 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/drivers/net/bonding/bond_3ad.h b/drivers/net/bonding/bond_3ad.h index b28baff7086..01b8a6af275 100644 --- a/drivers/net/bonding/bond_3ad.h +++ b/drivers/net/bonding/bond_3ad.h @@ -39,7 +39,7 @@ typedef struct mac_addr { u8 mac_addr_value[ETH_ALEN]; -} mac_addr_t; +} __packed mac_addr_t; enum { BOND_AD_STABLE = 0, @@ -134,12 +134,12 @@ typedef struct lacpdu { u8 tlv_type_terminator; // = terminator u8 terminator_length; // = 0 u8 reserved_50[50]; // = 0 -} lacpdu_t; +} __packed lacpdu_t; typedef struct lacpdu_header { struct ethhdr hdr; struct lacpdu lacpdu; -} lacpdu_header_t; +} __packed lacpdu_header_t; // Marker Protocol Data Unit(PDU) structure(43.5.3.2 in the 802.3ad standard) typedef struct bond_marker { @@ -155,12 +155,12 @@ typedef struct bond_marker { u8 tlv_type_terminator; // = 0x00 u8 terminator_length; // = 0x00 u8 reserved_90[90]; // = 0 -} bond_marker_t; +} __packed bond_marker_t; typedef struct bond_marker_header { struct ethhdr hdr; struct bond_marker marker; -} bond_marker_header_t; +} __packed bond_marker_header_t; #pragma pack() diff --git a/include/net/llc_pdu.h b/include/net/llc_pdu.h index 75b8e2968c9..f57e7d46a45 100644 --- a/include/net/llc_pdu.h +++ b/include/net/llc_pdu.h @@ -199,7 +199,7 @@ struct llc_pdu_sn { u8 ssap; u8 ctrl_1; u8 ctrl_2; -}; +} __packed; static inline struct llc_pdu_sn *llc_pdu_sn_hdr(struct sk_buff *skb) { @@ -211,7 +211,7 @@ struct llc_pdu_un { u8 dsap; u8 ssap; u8 ctrl_1; -}; +} __packed; static inline struct llc_pdu_un *llc_pdu_un_hdr(struct sk_buff *skb) { @@ -359,7 +359,7 @@ struct llc_xid_info { u8 fmt_id; /* always 0x81 for LLC */ u8 type; /* different if NULL/non-NULL LSAP */ u8 rw; /* sender receive window */ -}; +} __packed; /** * llc_pdu_init_as_xid_cmd - sets bytes 3, 4 & 5 of LLC header as XID @@ -415,7 +415,7 @@ struct llc_frmr_info { u8 curr_ssv; /* current send state variable val */ u8 curr_rsv; /* current receive state variable */ u8 ind_bits; /* indicator bits set with macro */ -}; +} __packed; extern void llc_pdu_set_cmd_rsp(struct sk_buff *skb, u8 type); extern void llc_pdu_set_pf_bit(struct sk_buff *skb, u8 bit_value); -- cgit v1.2.3-70-g09d2 From 82a3242e11d9e63c8195be46c954efaefee35e22 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 12 May 2011 16:01:02 -0700 Subject: sysfs: remove "last sysfs file:" line from the oops messages On some arches (x86, sh, arm, unicore, powerpc) the oops message would print out the last sysfs file accessed. This was very useful in finding a number of sysfs and driver core bugs in the 2.5 and early 2.6 development days, but it has been a number of years since this file has actually helped in debugging anything that couldn't also be trivially determined from the stack traceback. So it's time to delete the line. This is good as we need all the space we can get for oops messages at times on consoles. Acked-by: Phil Carmody Acked-by: Ingo Molnar Cc: Andrew Morton Cc: Thomas Gleixner Signed-off-by: Greg Kroah-Hartman --- arch/arm/kernel/traps.c | 1 - arch/powerpc/kernel/traps.c | 1 - arch/sh/kernel/traps_32.c | 1 - arch/unicore32/kernel/traps.c | 1 - arch/x86/kernel/dumpstack.c | 1 - fs/sysfs/file.c | 12 ------------ include/linux/sysfs.h | 5 ----- 7 files changed, 22 deletions(-) (limited to 'include') diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c index 3b54ad19d48..d52eec268b4 100644 --- a/arch/arm/kernel/traps.c +++ b/arch/arm/kernel/traps.c @@ -234,7 +234,6 @@ static int __die(const char *str, int err, struct thread_info *thread, struct pt printk(KERN_EMERG "Internal error: %s: %x [#%d]" S_PREEMPT S_SMP "\n", str, err, ++die_counter); - sysfs_printk_last_file(); /* trap and error numbers are mostly meaningless on ARM */ ret = notify_die(DIE_OOPS, str, regs, err, tsk->thread.trap_no, SIGSEGV); diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 5ddb801bc15..d782cd71c07 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -143,7 +143,6 @@ int die(const char *str, struct pt_regs *regs, long err) #endif printk("%s\n", ppc_md.name ? ppc_md.name : ""); - sysfs_printk_last_file(); if (notify_die(DIE_OOPS, str, regs, err, 255, SIGSEGV) == NOTIFY_STOP) return 1; diff --git a/arch/sh/kernel/traps_32.c b/arch/sh/kernel/traps_32.c index 3484c2f65ab..b51a17104b5 100644 --- a/arch/sh/kernel/traps_32.c +++ b/arch/sh/kernel/traps_32.c @@ -87,7 +87,6 @@ void die(const char * str, struct pt_regs * regs, long err) bust_spinlocks(1); printk("%s: %04lx [#%d]\n", str, err & 0xffff, ++die_counter); - sysfs_printk_last_file(); print_modules(); show_regs(regs); diff --git a/arch/unicore32/kernel/traps.c b/arch/unicore32/kernel/traps.c index 254e36fa951..b9a26465e72 100644 --- a/arch/unicore32/kernel/traps.c +++ b/arch/unicore32/kernel/traps.c @@ -192,7 +192,6 @@ static int __die(const char *str, int err, struct thread_info *thread, printk(KERN_EMERG "Internal error: %s: %x [#%d]\n", str, err, ++die_counter); - sysfs_printk_last_file(); /* trap and error numbers are mostly meaningless on UniCore */ ret = notify_die(DIE_OOPS, str, regs, err, tsk->thread.trap_no, \ diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index e2a3f0606da..f72e7193acc 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -279,7 +279,6 @@ int __kprobes __die(const char *str, struct pt_regs *regs, long err) printk("DEBUG_PAGEALLOC"); #endif printk("\n"); - sysfs_printk_last_file(); if (notify_die(DIE_OOPS, str, regs, err, current->thread.trap_no, SIGSEGV) == NOTIFY_STOP) return 1; diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index da3fefe91a8..1ad8c93c1b8 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -24,13 +24,6 @@ #include "sysfs.h" -/* used in crash dumps to help with debugging */ -static char last_sysfs_file[PATH_MAX]; -void sysfs_printk_last_file(void) -{ - printk(KERN_EMERG "last sysfs file: %s\n", last_sysfs_file); -} - /* * There's one sysfs_buffer for each open file and one * sysfs_open_dirent for each sysfs_dirent with one or more open @@ -337,11 +330,6 @@ static int sysfs_open_file(struct inode *inode, struct file *file) struct sysfs_buffer *buffer; const struct sysfs_ops *ops; int error = -EACCES; - char *p; - - p = d_path(&file->f_path, last_sysfs_file, sizeof(last_sysfs_file)); - if (!IS_ERR(p)) - memmove(last_sysfs_file, p, strlen(p) + 1); /* need attr_sd for attr and ops, its parent for kobj */ if (!sysfs_get_active(attr_sd)) diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index 30b881555fa..c3acda60eee 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -176,7 +176,6 @@ struct sysfs_dirent *sysfs_get_dirent(struct sysfs_dirent *parent_sd, const unsigned char *name); struct sysfs_dirent *sysfs_get(struct sysfs_dirent *sd); void sysfs_put(struct sysfs_dirent *sd); -void sysfs_printk_last_file(void); /* Called to clear a ns tag when it is no longer valid */ void sysfs_exit_ns(enum kobj_ns_type type, const void *tag); @@ -348,10 +347,6 @@ static inline int __must_check sysfs_init(void) return 0; } -static inline void sysfs_printk_last_file(void) -{ -} - #endif /* CONFIG_SYSFS */ #endif /* _SYSFS_H_ */ -- cgit v1.2.3-70-g09d2 From 8c414ff3f4dcdde228c6a668385218290d73a265 Mon Sep 17 00:00:00 2001 From: Russell King Date: Sun, 8 May 2011 18:50:20 +0100 Subject: clocksource: convert footbridge to generic i8253 clocksource Convert the footbridge isa-timer code to use generic i8253 clocksource. Acked-by: John Stultz Acked-by: Thomas Gleixner Signed-off-by: Russell King --- arch/arm/include/asm/i8253.h | 15 ++++++++++++ arch/arm/mach-footbridge/Kconfig | 2 ++ arch/arm/mach-footbridge/isa-timer.c | 45 ++++-------------------------------- include/linux/clocksource.h | 2 ++ 4 files changed, 23 insertions(+), 41 deletions(-) create mode 100644 arch/arm/include/asm/i8253.h (limited to 'include') diff --git a/arch/arm/include/asm/i8253.h b/arch/arm/include/asm/i8253.h new file mode 100644 index 00000000000..70656b69d5c --- /dev/null +++ b/arch/arm/include/asm/i8253.h @@ -0,0 +1,15 @@ +#ifndef __ASMARM_I8253_H +#define __ASMARM_I8253_H + +/* i8253A PIT registers */ +#define PIT_MODE 0x43 +#define PIT_CH0 0x40 + +#define PIT_LATCH ((PIT_TICK_RATE + HZ / 2) / HZ) + +extern raw_spinlock_t i8253_lock; + +#define outb_pit outb_p +#define inb_pit inb_p + +#endif diff --git a/arch/arm/mach-footbridge/Kconfig b/arch/arm/mach-footbridge/Kconfig index bdd257921cf..46adca068f2 100644 --- a/arch/arm/mach-footbridge/Kconfig +++ b/arch/arm/mach-footbridge/Kconfig @@ -4,6 +4,7 @@ menu "Footbridge Implementations" config ARCH_CATS bool "CATS" + select CLKSRC_I8253 select FOOTBRIDGE_HOST select ISA select ISA_DMA @@ -59,6 +60,7 @@ config ARCH_EBSA285_HOST config ARCH_NETWINDER bool "NetWinder" + select CLKSRC_I8253 select FOOTBRIDGE_HOST select ISA select ISA_DMA diff --git a/arch/arm/mach-footbridge/isa-timer.c b/arch/arm/mach-footbridge/isa-timer.c index 441c6ce0d55..7020f1a3fec 100644 --- a/arch/arm/mach-footbridge/isa-timer.c +++ b/arch/arm/mach-footbridge/isa-timer.c @@ -10,53 +10,16 @@ #include #include #include +#include #include #include - +#include #include #include "common.h" -#define PIT_MODE 0x43 -#define PIT_CH0 0x40 - -#define PIT_LATCH ((PIT_TICK_RATE + HZ / 2) / HZ) - -static cycle_t pit_read(struct clocksource *cs) -{ - unsigned long flags; - static int old_count; - static u32 old_jifs; - int count; - u32 jifs; - - raw_local_irq_save(flags); - - jifs = jiffies; - outb_p(0x00, PIT_MODE); /* latch the count */ - count = inb_p(PIT_CH0); /* read the latched count */ - count |= inb_p(PIT_CH0) << 8; - - if (count > old_count && jifs == old_jifs) - count = old_count; - - old_count = count; - old_jifs = jifs; - - raw_local_irq_restore(flags); - - count = (PIT_LATCH - 1) - count; - - return (cycle_t)(jifs * PIT_LATCH) + count; -} - -static struct clocksource pit_cs = { - .name = "pit", - .rating = 110, - .read = pit_read, - .mask = CLOCKSOURCE_MASK(32), -}; +DEFINE_RAW_SPINLOCK(i8253_lock); static void pit_set_mode(enum clock_event_mode mode, struct clock_event_device *evt) @@ -121,7 +84,7 @@ static void __init isa_timer_init(void) pit_ce.max_delta_ns = clockevent_delta2ns(0x7fff, &pit_ce); pit_ce.min_delta_ns = clockevent_delta2ns(0x000f, &pit_ce); - clocksource_register_hz(&pit_cs, PIT_TICK_RATE); + clocksource_i8253_init(); setup_irq(pit_ce.irq, &pit_timer_irq); clockevents_register_device(&pit_ce); diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index c37b21ad5a3..f13469b3df8 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -341,4 +341,6 @@ static inline void update_vsyscall_tz(void) extern void timekeeping_notify(struct clocksource *clock); +extern int clocksource_i8253_init(void); + #endif /* _LINUX_CLOCKSOURCE_H */ -- cgit v1.2.3-70-g09d2 From e1e8fb6a1ff3f9487e03a4cbf85b81d1316068ce Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Fri, 15 Apr 2011 03:02:49 +0000 Subject: fs: remove FS_COW_FL FS_COW_FL and FS_NOCOW_FL were newly introduced to control per file COW in btrfs, but FS_NOCOW_FL is sufficient. The fact is we don't have corresponding BTRFS_INODE_COW flag. COW is default, and FS_NOCOW_FL can be used to switch off COW for a single file. If we mount btrfs with nodatacow, a newly created file will be set with the FS_NOCOW_FL flag. So to turn on COW for it, we can just clear the FS_NOCOW_FL flag. Signed-off-by: Li Zefan Signed-off-by: Chris Mason --- fs/btrfs/ioctl.c | 15 ++++++--------- include/linux/fs.h | 1 - 2 files changed, 6 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index f580a3a5d2f..3240dd90da4 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -144,16 +144,13 @@ static int check_flags(unsigned int flags) if (flags & ~(FS_IMMUTABLE_FL | FS_APPEND_FL | \ FS_NOATIME_FL | FS_NODUMP_FL | \ FS_SYNC_FL | FS_DIRSYNC_FL | \ - FS_NOCOMP_FL | FS_COMPR_FL | \ - FS_NOCOW_FL | FS_COW_FL)) + FS_NOCOMP_FL | FS_COMPR_FL | + FS_NOCOW_FL)) return -EOPNOTSUPP; if ((flags & FS_NOCOMP_FL) && (flags & FS_COMPR_FL)) return -EINVAL; - if ((flags & FS_NOCOW_FL) && (flags & FS_COW_FL)) - return -EINVAL; - return 0; } @@ -218,6 +215,10 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg) ip->flags |= BTRFS_INODE_DIRSYNC; else ip->flags &= ~BTRFS_INODE_DIRSYNC; + if (flags & FS_NOCOW_FL) + ip->flags |= BTRFS_INODE_NODATACOW; + else + ip->flags &= ~BTRFS_INODE_NODATACOW; /* * The COMPRESS flag can only be changed by users, while the NOCOMPRESS @@ -231,10 +232,6 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg) ip->flags |= BTRFS_INODE_COMPRESS; ip->flags &= ~BTRFS_INODE_NOCOMPRESS; } - if (flags & FS_NOCOW_FL) - ip->flags |= BTRFS_INODE_NODATACOW; - else if (flags & FS_COW_FL) - ip->flags &= ~BTRFS_INODE_NODATACOW; trans = btrfs_join_transaction(root, 1); BUG_ON(IS_ERR(trans)); diff --git a/include/linux/fs.h b/include/linux/fs.h index de9dd8119b7..56a41412903 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -365,7 +365,6 @@ struct inodes_stat_t { #define FS_EXTENT_FL 0x00080000 /* Extents */ #define FS_DIRECTIO_FL 0x00100000 /* Use direct i/o */ #define FS_NOCOW_FL 0x00800000 /* Do not cow file */ -#define FS_COW_FL 0x02000000 /* Cow file */ #define FS_RESERVED_FL 0x80000000 /* reserved for ext2 lib */ #define FS_FL_USER_VISIBLE 0x0003DFFF /* User visible flags */ -- cgit v1.2.3-70-g09d2 From 752d2635ebb12b6122ba05775f7d1ccfef14b275 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Fri, 22 Apr 2011 11:03:57 +0100 Subject: drm: Take lock around probes for drm_fb_helper_hotplug_event We need to hold the dev->mode_config.mutex whilst detecting the output status. But we also need to drop it for the call into drm_fb_helper_single_fb_probe(), which indirectly acquires the lock when attaching the fbcon. Failure to do so exposes a race with normal output probing. Detected by adding some warnings that the mutex is held to the backend detect routines: [ 17.772456] WARNING: at drivers/gpu/drm/i915/intel_crt.c:471 intel_crt_detect+0x3e/0x373 [i915]() [ 17.772458] Hardware name: Latitude E6400 [ 17.772460] Modules linked in: .... [ 17.772582] Pid: 11, comm: kworker/0:1 Tainted: G W 2.6.38.4-custom.2 #8 [ 17.772584] Call Trace: [ 17.772591] [] ? warn_slowpath_common+0x78/0x8c [ 17.772603] [] ? intel_crt_detect+0x3e/0x373 [i915] [ 17.772612] [] ? drm_helper_probe_single_connector_modes+0xbf/0x2af [drm_kms_helper] [ 17.772619] [] ? drm_fb_helper_probe_connector_modes+0x39/0x4d [drm_kms_helper] [ 17.772625] [] ? drm_fb_helper_hotplug_event+0xa5/0xc3 [drm_kms_helper] [ 17.772633] [] ? output_poll_execute+0x146/0x17c [drm_kms_helper] [ 17.772638] [] ? cfq_init_queue+0x247/0x345 [ 17.772644] [] ? output_poll_execute+0x0/0x17c [drm_kms_helper] [ 17.772648] [] ? process_one_work+0x193/0x28e [ 17.772652] [] ? worker_thread+0xef/0x172 [ 17.772655] [] ? worker_thread+0x0/0x172 [ 17.772658] [] ? worker_thread+0x0/0x172 [ 17.772663] [] ? kthread+0x7a/0x82 [ 17.772668] [] ? kernel_thread_helper+0x4/0x10 [ 17.772671] [] ? kthread+0x0/0x82 [ 17.772674] [] ? kernel_thread_helper+0x0/0x10 Reported-by: Frederik Himpe References: https://bugs.freedesktop.org/show_bug.cgi?id=36394 Signed-off-by: Chris Wilson Signed-off-by: Dave Airlie --- drivers/gpu/drm/drm_fb_helper.c | 26 ++++++++++++++++++++++---- include/drm/drm_fb_helper.h | 2 +- 2 files changed, 23 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index 11d7a72c22d..140b9525b48 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -1516,17 +1516,33 @@ bool drm_fb_helper_initial_config(struct drm_fb_helper *fb_helper, int bpp_sel) } EXPORT_SYMBOL(drm_fb_helper_initial_config); -bool drm_fb_helper_hotplug_event(struct drm_fb_helper *fb_helper) +/** + * drm_fb_helper_hotplug_event - respond to a hotplug notification by + * probing all the outputs attached to the fb. + * @fb_helper: the drm_fb_helper + * + * LOCKING: + * Called at runtime, must take mode config lock. + * + * Scan the connectors attached to the fb_helper and try to put together a + * setup after *notification of a change in output configuration. + * + * RETURNS: + * 0 on success and a non-zero error code otherwise. + */ +int drm_fb_helper_hotplug_event(struct drm_fb_helper *fb_helper) { + struct drm_device *dev = fb_helper->dev; int count = 0; u32 max_width, max_height, bpp_sel; bool bound = false, crtcs_bound = false; struct drm_crtc *crtc; if (!fb_helper->fb) - return false; + return 0; - list_for_each_entry(crtc, &fb_helper->dev->mode_config.crtc_list, head) { + mutex_lock(&dev->mode_config.mutex); + list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { if (crtc->fb) crtcs_bound = true; if (crtc->fb == fb_helper->fb) @@ -1535,7 +1551,8 @@ bool drm_fb_helper_hotplug_event(struct drm_fb_helper *fb_helper) if (!bound && crtcs_bound) { fb_helper->delayed_hotplug = true; - return false; + mutex_unlock(&dev->mode_config.mutex); + return 0; } DRM_DEBUG_KMS("\n"); @@ -1546,6 +1563,7 @@ bool drm_fb_helper_hotplug_event(struct drm_fb_helper *fb_helper) count = drm_fb_helper_probe_connector_modes(fb_helper, max_width, max_height); drm_setup_crtcs(fb_helper); + mutex_unlock(&dev->mode_config.mutex); return drm_fb_helper_single_fb_probe(fb_helper, bpp_sel); } diff --git a/include/drm/drm_fb_helper.h b/include/drm/drm_fb_helper.h index ade09d7b427..c99c3d3e781 100644 --- a/include/drm/drm_fb_helper.h +++ b/include/drm/drm_fb_helper.h @@ -127,7 +127,7 @@ void drm_fb_helper_fill_fix(struct fb_info *info, uint32_t pitch, int drm_fb_helper_setcmap(struct fb_cmap *cmap, struct fb_info *info); -bool drm_fb_helper_hotplug_event(struct drm_fb_helper *fb_helper); +int drm_fb_helper_hotplug_event(struct drm_fb_helper *fb_helper); bool drm_fb_helper_initial_config(struct drm_fb_helper *fb_helper, int bpp_sel); int drm_fb_helper_single_add_all_connectors(struct drm_fb_helper *fb_helper); int drm_fb_helper_debug_enter(struct fb_info *info); -- cgit v1.2.3-70-g09d2 From 86f315bbb2374f1f077500ad131dd9b71856e697 Mon Sep 17 00:00:00 2001 From: Chris Ball Date: Mon, 16 May 2011 11:32:26 -0400 Subject: Revert "mmc: fix a race between card-detect rescan and clock-gate work instances" This reverts commit 26fc8775b51484d8c0a671198639c6d5ae60533e, which has been reported to cause boot/resume-time crashes for some users: https://bbs.archlinux.org/viewtopic.php?id=118751. Signed-off-by: Chris Ball Cc: --- drivers/mmc/core/host.c | 9 +++++---- include/linux/mmc/host.h | 1 + 2 files changed, 6 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c index 2b200c1cfbb..461e6a17fb9 100644 --- a/drivers/mmc/core/host.c +++ b/drivers/mmc/core/host.c @@ -94,7 +94,7 @@ static void mmc_host_clk_gate_delayed(struct mmc_host *host) spin_unlock_irqrestore(&host->clk_lock, flags); return; } - mmc_claim_host(host); + mutex_lock(&host->clk_gate_mutex); spin_lock_irqsave(&host->clk_lock, flags); if (!host->clk_requests) { spin_unlock_irqrestore(&host->clk_lock, flags); @@ -104,7 +104,7 @@ static void mmc_host_clk_gate_delayed(struct mmc_host *host) pr_debug("%s: gated MCI clock\n", mmc_hostname(host)); } spin_unlock_irqrestore(&host->clk_lock, flags); - mmc_release_host(host); + mutex_unlock(&host->clk_gate_mutex); } /* @@ -130,7 +130,7 @@ void mmc_host_clk_ungate(struct mmc_host *host) { unsigned long flags; - mmc_claim_host(host); + mutex_lock(&host->clk_gate_mutex); spin_lock_irqsave(&host->clk_lock, flags); if (host->clk_gated) { spin_unlock_irqrestore(&host->clk_lock, flags); @@ -140,7 +140,7 @@ void mmc_host_clk_ungate(struct mmc_host *host) } host->clk_requests++; spin_unlock_irqrestore(&host->clk_lock, flags); - mmc_release_host(host); + mutex_unlock(&host->clk_gate_mutex); } /** @@ -215,6 +215,7 @@ static inline void mmc_host_clk_init(struct mmc_host *host) host->clk_gated = false; INIT_WORK(&host->clk_gate_work, mmc_host_clk_gate_work); spin_lock_init(&host->clk_lock); + mutex_init(&host->clk_gate_mutex); } /** diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index eb792cb6d74..bcb793ec737 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -183,6 +183,7 @@ struct mmc_host { struct work_struct clk_gate_work; /* delayed clock gate */ unsigned int clk_old; /* old clock value cache */ spinlock_t clk_lock; /* lock for clk fields */ + struct mutex clk_gate_mutex; /* mutex for clock gating */ #endif /* host specific block data */ -- cgit v1.2.3-70-g09d2 From 2064af917b3ba7589070064ca4ed12cecd99a63c Mon Sep 17 00:00:00 2001 From: Kevin Hilman Date: Fri, 29 Apr 2011 00:37:26 +0200 Subject: PM: Revert "driver core: platform_bus: allow runtime override of dev_pm_ops" The platform_bus_set_pm_ops() operation is deprecated in favor of the new device power domain infrastructre implemented in commit 7538e3db6e015e890825fbd9f8659952896ddd5b (PM: add support for device power domains) Signed-off-by: Kevin Hilman Signed-off-by: Rafael J. Wysocki --- drivers/base/platform.c | 35 ----------------------------------- include/linux/platform_device.h | 3 --- 2 files changed, 38 deletions(-) (limited to 'include') diff --git a/drivers/base/platform.c b/drivers/base/platform.c index 079c18a5e47..48425f18302 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -916,41 +916,6 @@ struct bus_type platform_bus_type = { }; EXPORT_SYMBOL_GPL(platform_bus_type); -/** - * platform_bus_get_pm_ops() - return pointer to busses dev_pm_ops - * - * This function can be used by platform code to get the current - * set of dev_pm_ops functions used by the platform_bus_type. - */ -const struct dev_pm_ops * __init platform_bus_get_pm_ops(void) -{ - return platform_bus_type.pm; -} - -/** - * platform_bus_set_pm_ops() - update dev_pm_ops for the platform_bus_type - * - * @pm: pointer to new dev_pm_ops struct to be used for platform_bus_type - * - * Platform code can override the dev_pm_ops methods of - * platform_bus_type by using this function. It is expected that - * platform code will first do a platform_bus_get_pm_ops(), then - * kmemdup it, then customize selected methods and pass a pointer to - * the new struct dev_pm_ops to this function. - * - * Since platform-specific code is customizing methods for *all* - * devices (not just platform-specific devices) it is expected that - * any custom overrides of these functions will keep existing behavior - * and simply extend it. For example, any customization of the - * runtime PM methods should continue to call the pm_generic_* - * functions as the default ones do in addition to the - * platform-specific behavior. - */ -void __init platform_bus_set_pm_ops(const struct dev_pm_ops *pm) -{ - platform_bus_type.pm = pm; -} - int __init platform_bus_init(void) { int error; diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index e0093e061b0..ede1a80e335 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -150,9 +150,6 @@ extern struct platform_device *platform_create_bundle(struct platform_driver *dr struct resource *res, unsigned int n_res, const void *data, size_t size); -extern const struct dev_pm_ops * platform_bus_get_pm_ops(void); -extern void platform_bus_set_pm_ops(const struct dev_pm_ops *pm); - /* early platform driver interface */ struct early_platform_driver { const char *class_str; -- cgit v1.2.3-70-g09d2 From f0201738b61b1adcf6b2c4719c5c415745014c1c Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 12 Apr 2011 19:06:39 -0400 Subject: ftrace: Avoid recording mcount on .init sections directly The init and exit sections should not be traced and adding a call to mcount to them is a waste of text and instruction cache. Have the macro section attributes include notrace to ignore these functions for tracing from the build. Link: http://lkml.kernel.org/r/20110421023738.953028219@goodmis.org Signed-off-by: Steven Rostedt --- include/linux/init.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/init.h b/include/linux/init.h index 577671c5515..9146f39cddd 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -79,29 +79,29 @@ #define __exitused __used #endif -#define __exit __section(.exit.text) __exitused __cold +#define __exit __section(.exit.text) __exitused __cold notrace /* Used for HOTPLUG */ -#define __devinit __section(.devinit.text) __cold +#define __devinit __section(.devinit.text) __cold notrace #define __devinitdata __section(.devinit.data) #define __devinitconst __section(.devinit.rodata) -#define __devexit __section(.devexit.text) __exitused __cold +#define __devexit __section(.devexit.text) __exitused __cold notrace #define __devexitdata __section(.devexit.data) #define __devexitconst __section(.devexit.rodata) /* Used for HOTPLUG_CPU */ -#define __cpuinit __section(.cpuinit.text) __cold +#define __cpuinit __section(.cpuinit.text) __cold notrace #define __cpuinitdata __section(.cpuinit.data) #define __cpuinitconst __section(.cpuinit.rodata) -#define __cpuexit __section(.cpuexit.text) __exitused __cold +#define __cpuexit __section(.cpuexit.text) __exitused __cold notrace #define __cpuexitdata __section(.cpuexit.data) #define __cpuexitconst __section(.cpuexit.rodata) /* Used for MEMORY_HOTPLUG */ -#define __meminit __section(.meminit.text) __cold +#define __meminit __section(.meminit.text) __cold notrace #define __meminitdata __section(.meminit.data) #define __meminitconst __section(.meminit.rodata) -#define __memexit __section(.memexit.text) __exitused __cold +#define __memexit __section(.memexit.text) __exitused __cold notrace #define __memexitdata __section(.memexit.data) #define __memexitconst __section(.memexit.rodata) -- cgit v1.2.3-70-g09d2 From 9937a5e2f32892db0dbeefc2b3bc74b3ae3ea9c7 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 17 May 2011 11:04:44 +0200 Subject: scsi: remove performance regression due to async queue run Commit c21e6beb removed our queue request_fn re-enter protection, and defaulted to always running the queues from kblockd to be safe. This was a known potential slow down, but should be safe. Unfortunately this is causing big performance regressions for some, so we need to improve this logic. Looking into the details of the re-enter, the real issue is on requeue of requests. Requeue of requests upon seeing a BUSY condition from the device ends up re-running the queue, causing traces like this: scsi_request_fn() scsi_dispatch_cmd() scsi_queue_insert() __scsi_queue_insert() scsi_run_queue() scsi_request_fn() ... potentially causing the issue we want to avoid. So special case the requeue re-run of the queue, but improve it to offload the entire run of local queue and starved queue from a single workqueue callback. This is a lot better than potentially kicking off a workqueue run for each device seen. This also fixes the issue of the local device going into recursion, since the above mentioned commit never moved that queue run out of line. Signed-off-by: Jens Axboe --- drivers/scsi/scsi_lib.c | 20 ++++++++++++++++---- drivers/scsi/scsi_scan.c | 2 ++ include/scsi/scsi_device.h | 1 + 3 files changed, 19 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index e9901b8f844..01e4e51c4b6 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -74,8 +74,6 @@ struct kmem_cache *scsi_sdb_cache; */ #define SCSI_QUEUE_DELAY 3 -static void scsi_run_queue(struct request_queue *q); - /* * Function: scsi_unprep_request() * @@ -161,7 +159,7 @@ static int __scsi_queue_insert(struct scsi_cmnd *cmd, int reason, int unbusy) blk_requeue_request(q, cmd->request); spin_unlock_irqrestore(q->queue_lock, flags); - scsi_run_queue(q); + kblockd_schedule_work(q, &device->requeue_work); return 0; } @@ -433,7 +431,11 @@ static void scsi_run_queue(struct request_queue *q) continue; } - blk_run_queue_async(sdev->request_queue); + spin_unlock(shost->host_lock); + spin_lock(sdev->request_queue->queue_lock); + __blk_run_queue(sdev->request_queue); + spin_unlock(sdev->request_queue->queue_lock); + spin_lock(shost->host_lock); } /* put any unprocessed entries back */ list_splice(&starved_list, &shost->starved_list); @@ -442,6 +444,16 @@ static void scsi_run_queue(struct request_queue *q) blk_run_queue(q); } +void scsi_requeue_run_queue(struct work_struct *work) +{ + struct scsi_device *sdev; + struct request_queue *q; + + sdev = container_of(work, struct scsi_device, requeue_work); + q = sdev->request_queue; + scsi_run_queue(q); +} + /* * Function: scsi_requeue_command() * diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c index 087821fac8f..58584dc0724 100644 --- a/drivers/scsi/scsi_scan.c +++ b/drivers/scsi/scsi_scan.c @@ -242,6 +242,7 @@ static struct scsi_device *scsi_alloc_sdev(struct scsi_target *starget, int display_failure_msg = 1, ret; struct Scsi_Host *shost = dev_to_shost(starget->dev.parent); extern void scsi_evt_thread(struct work_struct *work); + extern void scsi_requeue_run_queue(struct work_struct *work); sdev = kzalloc(sizeof(*sdev) + shost->transportt->device_size, GFP_ATOMIC); @@ -264,6 +265,7 @@ static struct scsi_device *scsi_alloc_sdev(struct scsi_target *starget, INIT_LIST_HEAD(&sdev->event_list); spin_lock_init(&sdev->list_lock); INIT_WORK(&sdev->event_work, scsi_evt_thread); + INIT_WORK(&sdev->requeue_work, scsi_requeue_run_queue); sdev->sdev_gendev.parent = get_device(&starget->dev); sdev->sdev_target = starget; diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index 2d3ec509468..dd82e02ddde 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -169,6 +169,7 @@ struct scsi_device { sdev_dev; struct execute_work ew; /* used to get process context on put */ + struct work_struct requeue_work; struct scsi_dh_data *scsi_dh_data; enum scsi_device_state sdev_state; -- cgit v1.2.3-70-g09d2 From a144c6a6c924aa1da04dd77fb84b89927354fdff Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 6 May 2011 20:09:42 +0200 Subject: PM: Print a warning if firmware is requested when tasks are frozen Some drivers erroneously use request_firmware() from their ->resume() (or ->thaw(), or ->restore()) callbacks, which is not going to work unless the firmware has been built in. This causes system resume to stall until the firmware-loading timeout expires, which makes users think that the resume has failed and reboot their machines unnecessarily. For this reason, make _request_firmware() print a warning and return immediately with error code if it has been called when tasks are frozen and it's impossible to start any new usermode helpers. Signed-off-by: Rafael J. Wysocki Acked-by: Greg Kroah-Hartman Reviewed-by: Valdis Kletnieks --- drivers/base/firmware_class.c | 5 +++++ include/linux/kmod.h | 5 +++++ kernel/kmod.c | 9 +++++++++ 3 files changed, 19 insertions(+) (limited to 'include') diff --git a/drivers/base/firmware_class.c b/drivers/base/firmware_class.c index 8c798ef7f13..bbb03e6f725 100644 --- a/drivers/base/firmware_class.c +++ b/drivers/base/firmware_class.c @@ -521,6 +521,11 @@ static int _request_firmware(const struct firmware **firmware_p, if (!firmware_p) return -EINVAL; + if (WARN_ON(usermodehelper_is_disabled())) { + dev_err(device, "firmware: %s will not be loaded\n", name); + return -EBUSY; + } + *firmware_p = firmware = kzalloc(sizeof(*firmware), GFP_KERNEL); if (!firmware) { dev_err(device, "%s: kmalloc(struct firmware) failed\n", diff --git a/include/linux/kmod.h b/include/linux/kmod.h index 6efd7a78de6..7f3dbcb7811 100644 --- a/include/linux/kmod.h +++ b/include/linux/kmod.h @@ -111,7 +111,12 @@ call_usermodehelper(char *path, char **argv, char **envp, enum umh_wait wait) extern void usermodehelper_init(void); +#ifdef CONFIG_PM_SLEEP extern int usermodehelper_disable(void); extern void usermodehelper_enable(void); +extern bool usermodehelper_is_disabled(void); +#else +static inline bool usermodehelper_is_disabled(void) { return false; } +#endif #endif /* __LINUX_KMOD_H__ */ diff --git a/kernel/kmod.c b/kernel/kmod.c index 9cd0591c96a..9ab513bd0c3 100644 --- a/kernel/kmod.c +++ b/kernel/kmod.c @@ -301,6 +301,15 @@ void usermodehelper_enable(void) usermodehelper_disabled = 0; } +/** + * usermodehelper_is_disabled - check if new helpers are allowed to be started + */ +bool usermodehelper_is_disabled(void) +{ + return usermodehelper_disabled; +} +EXPORT_SYMBOL_GPL(usermodehelper_is_disabled); + static void helper_lock(void) { atomic_inc(&running_helpers); -- cgit v1.2.3-70-g09d2 From 13d53f8775c6a00b070a3eef6833795412eb7fcd Mon Sep 17 00:00:00 2001 From: Kay Sievers Date: Tue, 10 May 2011 21:27:34 +0200 Subject: kmod: always provide usermodehelper_disable() We need to prevent kernel-forked processes during system poweroff. Such processes try to access the filesystem whose disks we are trying to shutdown at the same time. This causes delays and exceptions in the storage drivers. A follow-up patch will add these calls and need usermodehelper_disable() also on systems without suspend support. Signed-off-by: Kay Sievers Signed-off-by: Rafael J. Wysocki --- include/linux/kmod.h | 4 ---- kernel/kmod.c | 7 ------- 2 files changed, 11 deletions(-) (limited to 'include') diff --git a/include/linux/kmod.h b/include/linux/kmod.h index 7f3dbcb7811..31023182385 100644 --- a/include/linux/kmod.h +++ b/include/linux/kmod.h @@ -111,12 +111,8 @@ call_usermodehelper(char *path, char **argv, char **envp, enum umh_wait wait) extern void usermodehelper_init(void); -#ifdef CONFIG_PM_SLEEP extern int usermodehelper_disable(void); extern void usermodehelper_enable(void); extern bool usermodehelper_is_disabled(void); -#else -static inline bool usermodehelper_is_disabled(void) { return false; } -#endif #endif /* __LINUX_KMOD_H__ */ diff --git a/kernel/kmod.c b/kernel/kmod.c index 9ab513bd0c3..5ae0ff38425 100644 --- a/kernel/kmod.c +++ b/kernel/kmod.c @@ -245,7 +245,6 @@ static void __call_usermodehelper(struct work_struct *work) } } -#ifdef CONFIG_PM_SLEEP /* * If set, call_usermodehelper_exec() will exit immediately returning -EBUSY * (used for preventing user land processes from being created after the user @@ -321,12 +320,6 @@ static void helper_unlock(void) if (atomic_dec_and_test(&running_helpers)) wake_up(&running_helpers_waitq); } -#else /* CONFIG_PM_SLEEP */ -#define usermodehelper_disabled 0 - -static inline void helper_lock(void) {} -static inline void helper_unlock(void) {} -#endif /* CONFIG_PM_SLEEP */ /** * call_usermodehelper_setup - prepare to call a usermode helper -- cgit v1.2.3-70-g09d2 From 91e7c75ba93c48a82670d630b9daac92ff70095d Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 17 May 2011 23:26:00 +0200 Subject: PM: Allow drivers to allocate memory from .prepare() callbacks safely If device drivers allocate substantial amounts of memory (above 1 MB) in their hibernate .freeze() callbacks (or in their legacy suspend callbcks during hibernation), the subsequent creation of hibernate image may fail due to the lack of memory. This is the case, because the drivers' .freeze() callbacks are executed after the hibernate memory preallocation has been carried out and the preallocated amount of memory may be too small to cover the new driver allocations. Unfortunately, the drivers' .prepare() callbacks also are executed after the hibernate memory preallocation has completed, so they are not suitable for allocating additional memory either. Thus the only way a driver can safely allocate memory during hibernation is to use a hibernate/suspend notifier. However, the notifiers are called before the freezing of user space and the drivers wanting to use them for allocating additional memory may not know how much memory needs to be allocated at that point. To let device drivers overcome this difficulty rework the hibernation sequence so that the memory preallocation is carried out after the drivers' .prepare() callbacks have been executed, so that the .prepare() callbacks can be used for allocating additional memory to be used by the drivers' .freeze() callbacks. Update documentation to match the new behavior of the code. Signed-off-by: Rafael J. Wysocki --- Documentation/power/devices.txt | 14 +++++++---- Documentation/power/notifiers.txt | 51 ++++++++++++++++++--------------------- drivers/base/power/main.c | 18 +++++++++----- include/linux/pm.h | 4 +++ kernel/power/hibernate.c | 17 ++++++++++--- 5 files changed, 61 insertions(+), 43 deletions(-) (limited to 'include') diff --git a/Documentation/power/devices.txt b/Documentation/power/devices.txt index 1971bcf48a6..88880839ece 100644 --- a/Documentation/power/devices.txt +++ b/Documentation/power/devices.txt @@ -279,11 +279,15 @@ When the system goes into the standby or memory sleep state, the phases are: time.) Unlike the other suspend-related phases, during the prepare phase the device tree is traversed top-down. - The prepare phase uses only a bus callback. After the callback method - returns, no new children may be registered below the device. The method - may also prepare the device or driver in some way for the upcoming - system power transition, but it should not put the device into a - low-power state. + In addition to that, if device drivers need to allocate additional + memory to be able to hadle device suspend correctly, that should be + done in the prepare phase. + + After the prepare callback method returns, no new children may be + registered below the device. The method may also prepare the device or + driver in some way for the upcoming system power transition (for + example, by allocating additional memory required for this purpose), but + it should not put the device into a low-power state. 2. The suspend methods should quiesce the device to stop it from performing I/O. They also may save the device registers and put it into the diff --git a/Documentation/power/notifiers.txt b/Documentation/power/notifiers.txt index cf980709122..c2a4a346c0d 100644 --- a/Documentation/power/notifiers.txt +++ b/Documentation/power/notifiers.txt @@ -1,46 +1,41 @@ Suspend notifiers - (C) 2007 Rafael J. Wysocki , GPL - -There are some operations that device drivers may want to carry out in their -.suspend() routines, but shouldn't, because they can cause the hibernation or -suspend to fail. For example, a driver may want to allocate a substantial amount -of memory (like 50 MB) in .suspend(), but that shouldn't be done after the -swsusp's memory shrinker has run. - -Also, there may be some operations, that subsystems want to carry out before a -hibernation/suspend or after a restore/resume, requiring the system to be fully -functional, so the drivers' .suspend() and .resume() routines are not suitable -for this purpose. For example, device drivers may want to upload firmware to -their devices after a restore from a hibernation image, but they cannot do it by -calling request_firmware() from their .resume() routines (user land processes -are frozen at this point). The solution may be to load the firmware into -memory before processes are frozen and upload it from there in the .resume() -routine. Of course, a hibernation notifier may be used for this purpose. - -The subsystems that have such needs can register suspend notifiers that will be -called upon the following events by the suspend core: + (C) 2007-2011 Rafael J. Wysocki , GPL + +There are some operations that subsystems or drivers may want to carry out +before hibernation/suspend or after restore/resume, but they require the system +to be fully functional, so the drivers' and subsystems' .suspend() and .resume() +or even .prepare() and .complete() callbacks are not suitable for this purpose. +For example, device drivers may want to upload firmware to their devices after +resume/restore, but they cannot do it by calling request_firmware() from their +.resume() or .complete() routines (user land processes are frozen at these +points). The solution may be to load the firmware into memory before processes +are frozen and upload it from there in the .resume() routine. +A suspend/hibernation notifier may be used for this purpose. + +The subsystems or drivers having such needs can register suspend notifiers that +will be called upon the following events by the PM core: PM_HIBERNATION_PREPARE The system is going to hibernate or suspend, tasks will be frozen immediately. PM_POST_HIBERNATION The system memory state has been restored from a - hibernation image or an error occurred during the - hibernation. Device drivers' .resume() callbacks have + hibernation image or an error occurred during + hibernation. Device drivers' restore callbacks have been executed and tasks have been thawed. PM_RESTORE_PREPARE The system is going to restore a hibernation image. - If all goes well the restored kernel will issue a + If all goes well, the restored kernel will issue a PM_POST_HIBERNATION notification. -PM_POST_RESTORE An error occurred during the hibernation restore. - Device drivers' .resume() callbacks have been executed +PM_POST_RESTORE An error occurred during restore from hibernation. + Device drivers' restore callbacks have been executed and tasks have been thawed. -PM_SUSPEND_PREPARE The system is preparing for a suspend. +PM_SUSPEND_PREPARE The system is preparing for suspend. PM_POST_SUSPEND The system has just resumed or an error occurred during - the suspend. Device drivers' .resume() callbacks have - been executed and tasks have been thawed. + suspend. Device drivers' resume callbacks have been + executed and tasks have been thawed. It is generally assumed that whatever the notifiers do for PM_HIBERNATION_PREPARE, should be undone for PM_POST_HIBERNATION. Analogously, diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index 3b354560f30..aa632020774 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -579,11 +579,13 @@ static bool is_async(struct device *dev) * Execute the appropriate "resume" callback for all devices whose status * indicates that they are suspended. */ -static void dpm_resume(pm_message_t state) +void dpm_resume(pm_message_t state) { struct device *dev; ktime_t starttime = ktime_get(); + might_sleep(); + mutex_lock(&dpm_list_mtx); pm_transition = state; async_error = 0; @@ -656,10 +658,12 @@ static void device_complete(struct device *dev, pm_message_t state) * Execute the ->complete() callbacks for all devices whose PM status is not * DPM_ON (this allows new devices to be registered). */ -static void dpm_complete(pm_message_t state) +void dpm_complete(pm_message_t state) { struct list_head list; + might_sleep(); + INIT_LIST_HEAD(&list); mutex_lock(&dpm_list_mtx); while (!list_empty(&dpm_prepared_list)) { @@ -688,7 +692,6 @@ static void dpm_complete(pm_message_t state) */ void dpm_resume_end(pm_message_t state) { - might_sleep(); dpm_resume(state); dpm_complete(state); } @@ -912,11 +915,13 @@ static int device_suspend(struct device *dev) * dpm_suspend - Execute "suspend" callbacks for all non-sysdev devices. * @state: PM transition of the system being carried out. */ -static int dpm_suspend(pm_message_t state) +int dpm_suspend(pm_message_t state) { ktime_t starttime = ktime_get(); int error = 0; + might_sleep(); + mutex_lock(&dpm_list_mtx); pm_transition = state; async_error = 0; @@ -1003,10 +1008,12 @@ static int device_prepare(struct device *dev, pm_message_t state) * * Execute the ->prepare() callback(s) for all devices. */ -static int dpm_prepare(pm_message_t state) +int dpm_prepare(pm_message_t state) { int error = 0; + might_sleep(); + mutex_lock(&dpm_list_mtx); while (!list_empty(&dpm_list)) { struct device *dev = to_device(dpm_list.next); @@ -1055,7 +1062,6 @@ int dpm_suspend_start(pm_message_t state) { int error; - might_sleep(); error = dpm_prepare(state); if (!error) error = dpm_suspend(state); diff --git a/include/linux/pm.h b/include/linux/pm.h index 3cc3e7e589f..dce7c714877 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -533,10 +533,14 @@ struct dev_power_domain { extern void device_pm_lock(void); extern void dpm_resume_noirq(pm_message_t state); extern void dpm_resume_end(pm_message_t state); +extern void dpm_resume(pm_message_t state); +extern void dpm_complete(pm_message_t state); extern void device_pm_unlock(void); extern int dpm_suspend_noirq(pm_message_t state); extern int dpm_suspend_start(pm_message_t state); +extern int dpm_suspend(pm_message_t state); +extern int dpm_prepare(pm_message_t state); extern void __suspend_report_result(const char *function, void *fn, int ret); diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index 95a2ac40f48..f9bec56d882 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -327,20 +327,25 @@ static int create_image(int platform_mode) int hibernation_snapshot(int platform_mode) { + pm_message_t msg = PMSG_RECOVER; int error; error = platform_begin(platform_mode); if (error) goto Close; + error = dpm_prepare(PMSG_FREEZE); + if (error) + goto Complete_devices; + /* Preallocate image memory before shutting down devices. */ error = hibernate_preallocate_memory(); if (error) - goto Close; + goto Complete_devices; suspend_console(); pm_restrict_gfp_mask(); - error = dpm_suspend_start(PMSG_FREEZE); + error = dpm_suspend(PMSG_FREEZE); if (error) goto Recover_platform; @@ -358,13 +363,17 @@ int hibernation_snapshot(int platform_mode) if (error || !in_suspend) swsusp_free(); - dpm_resume_end(in_suspend ? - (error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE); + msg = in_suspend ? (error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE; + dpm_resume(msg); if (error || !in_suspend) pm_restore_gfp_mask(); resume_console(); + + Complete_devices: + dpm_complete(msg); + Close: platform_end(platform_mode); return error; -- cgit v1.2.3-70-g09d2 From 6538df80194e305f1b78cafb556f4bb442f808b3 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 17 May 2011 23:26:21 +0200 Subject: PM: Introduce generic prepare and complete callbacks for subsystems Introduce generic .prepare() and .complete() power management callbacks, currently missing, that can be used by subsystems and power domains and export them. Provide NULL definitions of all the generic system sleep callbacks for CONFIG_PM_SLEEP unset. Signed-off-by: Rafael J. Wysocki --- drivers/base/power/generic_ops.c | 39 +++++++++++++++++++++++++++++++++++++++ include/linux/pm.h | 26 +++++++++++++++++++------- 2 files changed, 58 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/drivers/base/power/generic_ops.c b/drivers/base/power/generic_ops.c index 42f97f92562..cb3bb368681 100644 --- a/drivers/base/power/generic_ops.c +++ b/drivers/base/power/generic_ops.c @@ -73,6 +73,23 @@ EXPORT_SYMBOL_GPL(pm_generic_runtime_resume); #endif /* CONFIG_PM_RUNTIME */ #ifdef CONFIG_PM_SLEEP +/** + * pm_generic_prepare - Generic routine preparing a device for power transition. + * @dev: Device to prepare. + * + * Prepare a device for a system-wide power transition. + */ +int pm_generic_prepare(struct device *dev) +{ + struct device_driver *drv = dev->driver; + int ret = 0; + + if (drv && drv->pm && drv->pm->prepare) + ret = drv->pm->prepare(dev); + + return ret; +} + /** * __pm_generic_call - Generic suspend/freeze/poweroff/thaw subsystem callback. * @dev: Device to handle. @@ -213,16 +230,38 @@ int pm_generic_restore(struct device *dev) return __pm_generic_resume(dev, PM_EVENT_RESTORE); } EXPORT_SYMBOL_GPL(pm_generic_restore); + +/** + * pm_generic_complete - Generic routine competing a device power transition. + * @dev: Device to handle. + * + * Complete a device power transition during a system-wide power transition. + */ +void pm_generic_complete(struct device *dev) +{ + struct device_driver *drv = dev->driver; + + if (drv && drv->pm && drv->pm->complete) + drv->pm->complete(dev); + + /* + * Let runtime PM try to suspend devices that haven't been in use before + * going into the system-wide sleep state we're resuming from. + */ + pm_runtime_idle(dev); +} #endif /* CONFIG_PM_SLEEP */ struct dev_pm_ops generic_subsys_pm_ops = { #ifdef CONFIG_PM_SLEEP + .prepare = pm_generic_prepare, .suspend = pm_generic_suspend, .resume = pm_generic_resume, .freeze = pm_generic_freeze, .thaw = pm_generic_thaw, .poweroff = pm_generic_poweroff, .restore = pm_generic_restore, + .complete = pm_generic_complete, #endif #ifdef CONFIG_PM_RUNTIME .runtime_suspend = pm_generic_runtime_suspend, diff --git a/include/linux/pm.h b/include/linux/pm.h index dce7c714877..3160648ccdd 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -550,6 +550,16 @@ extern void __suspend_report_result(const char *function, void *fn, int ret); } while (0) extern int device_pm_wait_for_dev(struct device *sub, struct device *dev); + +extern int pm_generic_prepare(struct device *dev); +extern int pm_generic_suspend(struct device *dev); +extern int pm_generic_resume(struct device *dev); +extern int pm_generic_freeze(struct device *dev); +extern int pm_generic_thaw(struct device *dev); +extern int pm_generic_restore(struct device *dev); +extern int pm_generic_poweroff(struct device *dev); +extern void pm_generic_complete(struct device *dev); + #else /* !CONFIG_PM_SLEEP */ #define device_pm_lock() do {} while (0) @@ -566,6 +576,15 @@ static inline int device_pm_wait_for_dev(struct device *a, struct device *b) { return 0; } + +#define pm_generic_prepare NULL +#define pm_generic_suspend NULL +#define pm_generic_resume NULL +#define pm_generic_freeze NULL +#define pm_generic_thaw NULL +#define pm_generic_restore NULL +#define pm_generic_poweroff NULL +#define pm_generic_complete NULL #endif /* !CONFIG_PM_SLEEP */ /* How to reorder dpm_list after device_move() */ @@ -576,11 +595,4 @@ enum dpm_order { DPM_ORDER_DEV_LAST, }; -extern int pm_generic_suspend(struct device *dev); -extern int pm_generic_resume(struct device *dev); -extern int pm_generic_freeze(struct device *dev); -extern int pm_generic_thaw(struct device *dev); -extern int pm_generic_restore(struct device *dev); -extern int pm_generic_poweroff(struct device *dev); - #endif /* _LINUX_PM_H */ -- cgit v1.2.3-70-g09d2 From f12a20fc9bfba4218ecbc4e40c8e08dc2a85dc99 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 17 May 2011 15:44:12 -0700 Subject: procfs: add stub for proc_mkdir_mode() Provide a stub for proc_mkdir_mode() when CONFIG_PROC_FS is not enabled, just like the stub for proc_mkdir(). Fixes this linux-next build error: drivers/net/wireless/airo.c:4504: error: implicit declaration of function 'proc_mkdir_mode' Signed-off-by: Randy Dunlap Cc: Stephen Rothwell Cc: Alexey Dobriyan Cc: "John W. Linville" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/proc_fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 838c1149251..eaf4350c0f9 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -208,6 +208,8 @@ static inline struct proc_dir_entry *proc_symlink(const char *name, struct proc_dir_entry *parent,const char *dest) {return NULL;} static inline struct proc_dir_entry *proc_mkdir(const char *name, struct proc_dir_entry *parent) {return NULL;} +static inline struct proc_dir_entry *proc_mkdir_mode(const char *name, + mode_t mode, struct proc_dir_entry *parent) { return NULL; } static inline struct proc_dir_entry *create_proc_read_entry(const char *name, mode_t mode, struct proc_dir_entry *base, -- cgit v1.2.3-70-g09d2 From fe12bc2c996d3e492b2920e32ac79f7bbae3e15d Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 18 May 2011 12:48:00 +0200 Subject: genirq: Uninline and sanity check generic_handle_irq() generic_handle_irq() is missing a NULL pointer check for the result of irq_to_desc. This was a not a big problem, but we want to expose it to drivers, so we better have sanity checks in place. Add a return value as well, which indicates that the irq number was valid and the handler was invoked. Based on the pure code move from Jonathan Cameron. Signed-off-by: Thomas Gleixner Cc: Jonathan Cameron --- include/linux/irqdesc.h | 5 +---- kernel/irq/irqdesc.c | 15 +++++++++++++++ 2 files changed, 16 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index c70b1aa4b93..2d921b35212 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -111,10 +111,7 @@ static inline void generic_handle_irq_desc(unsigned int irq, struct irq_desc *de desc->handle_irq(irq, desc); } -static inline void generic_handle_irq(unsigned int irq) -{ - generic_handle_irq_desc(irq, irq_to_desc(irq)); -} +int generic_handle_irq(unsigned int irq); /* Test to see if a driver has successfully requested an irq */ static inline int irq_has_action(unsigned int irq) diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index e07b975fdc5..9f65b0225d6 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -290,6 +290,21 @@ static int irq_expand_nr_irqs(unsigned int nr) #endif /* !CONFIG_SPARSE_IRQ */ +/** + * generic_handle_irq - Invoke the handler for a particular irq + * @irq: The irq number to handle + * + */ +int generic_handle_irq(unsigned int irq) +{ + struct irq_desc *desc = irq_to_desc(irq); + + if (!desc) + return -EINVAL; + generic_handle_irq_desc(irq, desc); + return 0; +} + /* Dynamic interrupt handling */ /** -- cgit v1.2.3-70-g09d2 From 01294d82622d6d9d64bde8e4530c7e2c6dbb6ee6 Mon Sep 17 00:00:00 2001 From: Milton Miller Date: Wed, 18 May 2011 10:27:39 -0500 Subject: of: fix race when matching drivers If two drivers are probing devices at the same time, both will write their match table result to the dev->of_match cache at the same time. Only write the result if the device matches. In a thread titled "SBus devices sometimes detected, sometimes not", Meelis reported his SBus hme was not detected about 50% of the time. From the debug suggested by Grant it was obvious another driver matched some devices between the call to match the hme and the hme discovery failling. Reported-by: Meelis Roos Signed-off-by: Milton Miller [grant.likely: modified to only call of_match_device() once] Signed-off-by: Grant Likely --- include/linux/of_device.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/of_device.h b/include/linux/of_device.h index 8bfe6c1d436..b33d68814a7 100644 --- a/include/linux/of_device.h +++ b/include/linux/of_device.h @@ -21,8 +21,12 @@ extern void of_device_make_bus_id(struct device *dev); static inline int of_driver_match_device(struct device *dev, const struct device_driver *drv) { - dev->of_match = of_match_device(drv->of_match_table, dev); - return dev->of_match != NULL; + const struct of_device_id *match; + + match = of_match_device(drv->of_match_table, dev); + if (match) + dev->of_match = match; + return match != NULL; } extern struct platform_device *of_dev_get(struct platform_device *dev); -- cgit v1.2.3-70-g09d2 From b1608d69cb804e414d0887140ba08a9398e4e638 Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Wed, 18 May 2011 11:19:24 -0600 Subject: drivercore: revert addition of of_match to struct device Commit b826291c, "drivercore/dt: add a match table pointer to struct device" added an of_match pointer to struct device to cache the of_match_table entry discovered at driver match time. This was unsafe because matching is not an atomic operation with probing a driver. If two or more drivers are attempted to be matched to a driver at the same time, then the cached matching entry pointer could get overwritten. This patch reverts the of_match cache pointer and reworks all users to call of_match_device() directly instead. Signed-off-by: Grant Likely --- arch/powerpc/platforms/83xx/suspend.c | 7 +++++-- arch/powerpc/sysdev/fsl_msi.c | 7 +++++-- arch/sparc/kernel/pci_sabre.c | 5 ++++- arch/sparc/kernel/pci_schizo.c | 8 ++++++-- drivers/atm/fore200e.c | 7 +++++-- drivers/char/hw_random/n2-drv.c | 7 +++++-- drivers/char/ipmi/ipmi_si_intf.c | 7 +++++-- drivers/char/xilinx_hwicap/xilinx_hwicap.c | 14 +++++++++----- drivers/edac/ppc4xx_edac.c | 2 +- drivers/i2c/busses/i2c-mpc.c | 9 ++++++--- drivers/mmc/host/sdhci-of-core.c | 7 +++++-- drivers/mtd/maps/physmap_of.c | 7 +++++-- drivers/net/can/mscan/mpc5xxx_can.c | 7 +++++-- drivers/net/fs_enet/fs_enet-main.c | 9 ++++++--- drivers/net/fs_enet/mii-fec.c | 7 +++++-- drivers/net/sunhme.c | 7 +++++-- drivers/scsi/qlogicpti.c | 7 +++++-- drivers/tty/serial/of_serial.c | 7 +++++-- drivers/usb/gadget/fsl_qe_udc.c | 7 +++++-- drivers/watchdog/mpc8xxx_wdt.c | 7 +++++-- include/linux/device.h | 1 - include/linux/of_device.h | 12 ++++++------ 22 files changed, 108 insertions(+), 50 deletions(-) (limited to 'include') diff --git a/arch/powerpc/platforms/83xx/suspend.c b/arch/powerpc/platforms/83xx/suspend.c index 188272934cf..104faa8aa23 100644 --- a/arch/powerpc/platforms/83xx/suspend.c +++ b/arch/powerpc/platforms/83xx/suspend.c @@ -318,17 +318,20 @@ static const struct platform_suspend_ops mpc83xx_suspend_ops = { .end = mpc83xx_suspend_end, }; +static struct of_device_id pmc_match[]; static int pmc_probe(struct platform_device *ofdev) { + const struct of_device_id *match; struct device_node *np = ofdev->dev.of_node; struct resource res; struct pmc_type *type; int ret = 0; - if (!ofdev->dev.of_match) + match = of_match_device(pmc_match, &ofdev->dev); + if (!match) return -EINVAL; - type = ofdev->dev.of_match->data; + type = match->data; if (!of_device_is_available(np)) return -ENODEV; diff --git a/arch/powerpc/sysdev/fsl_msi.c b/arch/powerpc/sysdev/fsl_msi.c index d5679dc1e20..01cd2f08951 100644 --- a/arch/powerpc/sysdev/fsl_msi.c +++ b/arch/powerpc/sysdev/fsl_msi.c @@ -304,8 +304,10 @@ static int __devinit fsl_msi_setup_hwirq(struct fsl_msi *msi, return 0; } +static const struct of_device_id fsl_of_msi_ids[]; static int __devinit fsl_of_msi_probe(struct platform_device *dev) { + const struct of_device_id *match; struct fsl_msi *msi; struct resource res; int err, i, j, irq_index, count; @@ -316,9 +318,10 @@ static int __devinit fsl_of_msi_probe(struct platform_device *dev) u32 offset; static const u32 all_avail[] = { 0, NR_MSI_IRQS }; - if (!dev->dev.of_match) + match = of_match_device(fsl_of_msi_ids, &dev->dev); + if (!match) return -EINVAL; - features = dev->dev.of_match->data; + features = match->data; printk(KERN_DEBUG "Setting up Freescale MSI support\n"); diff --git a/arch/sparc/kernel/pci_sabre.c b/arch/sparc/kernel/pci_sabre.c index 948068a083f..d1840dbdaa2 100644 --- a/arch/sparc/kernel/pci_sabre.c +++ b/arch/sparc/kernel/pci_sabre.c @@ -452,8 +452,10 @@ static void __devinit sabre_pbm_init(struct pci_pbm_info *pbm, sabre_scan_bus(pbm, &op->dev); } +static const struct of_device_id sabre_match[]; static int __devinit sabre_probe(struct platform_device *op) { + const struct of_device_id *match; const struct linux_prom64_registers *pr_regs; struct device_node *dp = op->dev.of_node; struct pci_pbm_info *pbm; @@ -463,7 +465,8 @@ static int __devinit sabre_probe(struct platform_device *op) const u32 *vdma; u64 clear_irq; - hummingbird_p = op->dev.of_match && (op->dev.of_match->data != NULL); + match = of_match_device(sabre_match, &op->dev); + hummingbird_p = match && (match->data != NULL); if (!hummingbird_p) { struct device_node *cpu_dp; diff --git a/arch/sparc/kernel/pci_schizo.c b/arch/sparc/kernel/pci_schizo.c index fecfcb2063c..283fbc329a4 100644 --- a/arch/sparc/kernel/pci_schizo.c +++ b/arch/sparc/kernel/pci_schizo.c @@ -1458,11 +1458,15 @@ out_err: return err; } +static const struct of_device_id schizo_match[]; static int __devinit schizo_probe(struct platform_device *op) { - if (!op->dev.of_match) + const struct of_device_id *match; + + match = of_match_device(schizo_match, &op->dev); + if (!match) return -EINVAL; - return __schizo_init(op, (unsigned long) op->dev.of_match->data); + return __schizo_init(op, (unsigned long)match->data); } /* The ordering of this table is very important. Some Tomatillo diff --git a/drivers/atm/fore200e.c b/drivers/atm/fore200e.c index bdd2719f3f6..bc9e702186d 100644 --- a/drivers/atm/fore200e.c +++ b/drivers/atm/fore200e.c @@ -2643,16 +2643,19 @@ fore200e_init(struct fore200e* fore200e, struct device *parent) } #ifdef CONFIG_SBUS +static const struct of_device_id fore200e_sba_match[]; static int __devinit fore200e_sba_probe(struct platform_device *op) { + const struct of_device_id *match; const struct fore200e_bus *bus; struct fore200e *fore200e; static int index = 0; int err; - if (!op->dev.of_match) + match = of_match_device(fore200e_sba_match, &op->dev); + if (!match) return -EINVAL; - bus = op->dev.of_match->data; + bus = match->data; fore200e = kzalloc(sizeof(struct fore200e), GFP_KERNEL); if (!fore200e) diff --git a/drivers/char/hw_random/n2-drv.c b/drivers/char/hw_random/n2-drv.c index 43ac61978d8..ac6739e085e 100644 --- a/drivers/char/hw_random/n2-drv.c +++ b/drivers/char/hw_random/n2-drv.c @@ -619,15 +619,18 @@ static void __devinit n2rng_driver_version(void) pr_info("%s", version); } +static const struct of_device_id n2rng_match[]; static int __devinit n2rng_probe(struct platform_device *op) { + const struct of_device_id *match; int victoria_falls; int err = -ENOMEM; struct n2rng *np; - if (!op->dev.of_match) + match = of_match_device(n2rng_match, &op->dev); + if (!match) return -EINVAL; - victoria_falls = (op->dev.of_match->data != NULL); + victoria_falls = (match->data != NULL); n2rng_driver_version(); np = kzalloc(sizeof(*np), GFP_KERNEL); diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c index cc6c9b2546a..64c6b853061 100644 --- a/drivers/char/ipmi/ipmi_si_intf.c +++ b/drivers/char/ipmi/ipmi_si_intf.c @@ -2554,9 +2554,11 @@ static struct pci_driver ipmi_pci_driver = { }; #endif /* CONFIG_PCI */ +static struct of_device_id ipmi_match[]; static int __devinit ipmi_probe(struct platform_device *dev) { #ifdef CONFIG_OF + const struct of_device_id *match; struct smi_info *info; struct resource resource; const __be32 *regsize, *regspacing, *regshift; @@ -2566,7 +2568,8 @@ static int __devinit ipmi_probe(struct platform_device *dev) dev_info(&dev->dev, "probing via device tree\n"); - if (!dev->dev.of_match) + match = of_match_device(ipmi_match, &dev->dev); + if (!match) return -EINVAL; ret = of_address_to_resource(np, 0, &resource); @@ -2601,7 +2604,7 @@ static int __devinit ipmi_probe(struct platform_device *dev) return -ENOMEM; } - info->si_type = (enum si_type) dev->dev.of_match->data; + info->si_type = (enum si_type) match->data; info->addr_source = SI_DEVICETREE; info->irq_setup = std_irq_setup; diff --git a/drivers/char/xilinx_hwicap/xilinx_hwicap.c b/drivers/char/xilinx_hwicap/xilinx_hwicap.c index d6412c16385..39ccdeada79 100644 --- a/drivers/char/xilinx_hwicap/xilinx_hwicap.c +++ b/drivers/char/xilinx_hwicap/xilinx_hwicap.c @@ -715,13 +715,13 @@ static int __devexit hwicap_remove(struct device *dev) } #ifdef CONFIG_OF -static int __devinit hwicap_of_probe(struct platform_device *op) +static int __devinit hwicap_of_probe(struct platform_device *op, + const struct hwicap_driver_config *config) { struct resource res; const unsigned int *id; const char *family; int rc; - const struct hwicap_driver_config *config = op->dev.of_match->data; const struct config_registers *regs; @@ -751,20 +751,24 @@ static int __devinit hwicap_of_probe(struct platform_device *op) regs); } #else -static inline int hwicap_of_probe(struct platform_device *op) +static inline int hwicap_of_probe(struct platform_device *op, + const struct hwicap_driver_config *config) { return -EINVAL; } #endif /* CONFIG_OF */ +static const struct of_device_id __devinitconst hwicap_of_match[]; static int __devinit hwicap_drv_probe(struct platform_device *pdev) { + const struct of_device_id *match; struct resource *res; const struct config_registers *regs; const char *family; - if (pdev->dev.of_match) - return hwicap_of_probe(pdev); + match = of_match_device(hwicap_of_match, &pdev->dev); + if (match) + return hwicap_of_probe(pdev, match->data); res = platform_get_resource(pdev, IORESOURCE_MEM, 0); if (!res) diff --git a/drivers/edac/ppc4xx_edac.c b/drivers/edac/ppc4xx_edac.c index c1f0045ceb8..af8e7b1aa29 100644 --- a/drivers/edac/ppc4xx_edac.c +++ b/drivers/edac/ppc4xx_edac.c @@ -1019,7 +1019,7 @@ ppc4xx_edac_mc_init(struct mem_ctl_info *mci, struct ppc4xx_edac_pdata *pdata = NULL; const struct device_node *np = op->dev.of_node; - if (op->dev.of_match == NULL) + if (of_match_device(ppc4xx_edac_match, &op->dev) == NULL) return -EINVAL; /* Initial driver pointers and private data */ diff --git a/drivers/i2c/busses/i2c-mpc.c b/drivers/i2c/busses/i2c-mpc.c index 75b984c519a..107397a606b 100644 --- a/drivers/i2c/busses/i2c-mpc.c +++ b/drivers/i2c/busses/i2c-mpc.c @@ -560,15 +560,18 @@ static struct i2c_adapter mpc_ops = { .timeout = HZ, }; +static const struct of_device_id mpc_i2c_of_match[]; static int __devinit fsl_i2c_probe(struct platform_device *op) { + const struct of_device_id *match; struct mpc_i2c *i2c; const u32 *prop; u32 clock = MPC_I2C_CLOCK_LEGACY; int result = 0; int plen; - if (!op->dev.of_match) + match = of_match_device(mpc_i2c_of_match, &op->dev); + if (!match) return -EINVAL; i2c = kzalloc(sizeof(*i2c), GFP_KERNEL); @@ -605,8 +608,8 @@ static int __devinit fsl_i2c_probe(struct platform_device *op) clock = *prop; } - if (op->dev.of_match->data) { - struct mpc_i2c_data *data = op->dev.of_match->data; + if (match->data) { + struct mpc_i2c_data *data = match->data; data->setup(op->dev.of_node, i2c, clock, data->prescaler); } else { /* Backwards compatibility */ diff --git a/drivers/mmc/host/sdhci-of-core.c b/drivers/mmc/host/sdhci-of-core.c index f9b611fc773..60e4186a434 100644 --- a/drivers/mmc/host/sdhci-of-core.c +++ b/drivers/mmc/host/sdhci-of-core.c @@ -124,8 +124,10 @@ static bool __devinit sdhci_of_wp_inverted(struct device_node *np) #endif } +static const struct of_device_id sdhci_of_match[]; static int __devinit sdhci_of_probe(struct platform_device *ofdev) { + const struct of_device_id *match; struct device_node *np = ofdev->dev.of_node; struct sdhci_of_data *sdhci_of_data; struct sdhci_host *host; @@ -134,9 +136,10 @@ static int __devinit sdhci_of_probe(struct platform_device *ofdev) int size; int ret; - if (!ofdev->dev.of_match) + match = of_match_device(sdhci_of_match, &ofdev->dev); + if (!match) return -EINVAL; - sdhci_of_data = ofdev->dev.of_match->data; + sdhci_of_data = match->data; if (!of_device_is_available(np)) return -ENODEV; diff --git a/drivers/mtd/maps/physmap_of.c b/drivers/mtd/maps/physmap_of.c index bd483f0c57e..c1d33464aee 100644 --- a/drivers/mtd/maps/physmap_of.c +++ b/drivers/mtd/maps/physmap_of.c @@ -214,11 +214,13 @@ static void __devinit of_free_probes(const char **probes) } #endif +static struct of_device_id of_flash_match[]; static int __devinit of_flash_probe(struct platform_device *dev) { #ifdef CONFIG_MTD_PARTITIONS const char **part_probe_types; #endif + const struct of_device_id *match; struct device_node *dp = dev->dev.of_node; struct resource res; struct of_flash *info; @@ -232,9 +234,10 @@ static int __devinit of_flash_probe(struct platform_device *dev) struct mtd_info **mtd_list = NULL; resource_size_t res_size; - if (!dev->dev.of_match) + match = of_match_device(of_flash_match, &dev->dev); + if (!match) return -EINVAL; - probe_type = dev->dev.of_match->data; + probe_type = match->data; reg_tuple_size = (of_n_addr_cells(dp) + of_n_size_cells(dp)) * sizeof(u32); diff --git a/drivers/net/can/mscan/mpc5xxx_can.c b/drivers/net/can/mscan/mpc5xxx_can.c index bd1d811c204..5fedc337556 100644 --- a/drivers/net/can/mscan/mpc5xxx_can.c +++ b/drivers/net/can/mscan/mpc5xxx_can.c @@ -247,8 +247,10 @@ static u32 __devinit mpc512x_can_get_clock(struct platform_device *ofdev, } #endif /* CONFIG_PPC_MPC512x */ +static struct of_device_id mpc5xxx_can_table[]; static int __devinit mpc5xxx_can_probe(struct platform_device *ofdev) { + const struct of_device_id *match; struct mpc5xxx_can_data *data; struct device_node *np = ofdev->dev.of_node; struct net_device *dev; @@ -258,9 +260,10 @@ static int __devinit mpc5xxx_can_probe(struct platform_device *ofdev) int irq, mscan_clksrc = 0; int err = -ENOMEM; - if (!ofdev->dev.of_match) + match = of_match_device(mpc5xxx_can_table, &ofdev->dev); + if (!match) return -EINVAL; - data = (struct mpc5xxx_can_data *)ofdev->dev.of_match->data; + data = match->data; base = of_iomap(np, 0); if (!base) { diff --git a/drivers/net/fs_enet/fs_enet-main.c b/drivers/net/fs_enet/fs_enet-main.c index 24cb953900d..5131e61c358 100644 --- a/drivers/net/fs_enet/fs_enet-main.c +++ b/drivers/net/fs_enet/fs_enet-main.c @@ -998,8 +998,10 @@ static const struct net_device_ops fs_enet_netdev_ops = { #endif }; +static struct of_device_id fs_enet_match[]; static int __devinit fs_enet_probe(struct platform_device *ofdev) { + const struct of_device_id *match; struct net_device *ndev; struct fs_enet_private *fep; struct fs_platform_info *fpi; @@ -1007,14 +1009,15 @@ static int __devinit fs_enet_probe(struct platform_device *ofdev) const u8 *mac_addr; int privsize, len, ret = -ENODEV; - if (!ofdev->dev.of_match) + match = of_match_device(fs_enet_match, &ofdev->dev); + if (!match) return -EINVAL; fpi = kzalloc(sizeof(*fpi), GFP_KERNEL); if (!fpi) return -ENOMEM; - if (!IS_FEC(ofdev->dev.of_match)) { + if (!IS_FEC(match)) { data = of_get_property(ofdev->dev.of_node, "fsl,cpm-command", &len); if (!data || len != 4) goto out_free_fpi; @@ -1049,7 +1052,7 @@ static int __devinit fs_enet_probe(struct platform_device *ofdev) fep->dev = &ofdev->dev; fep->ndev = ndev; fep->fpi = fpi; - fep->ops = ofdev->dev.of_match->data; + fep->ops = match->data; ret = fep->ops->setup_data(ndev); if (ret) diff --git a/drivers/net/fs_enet/mii-fec.c b/drivers/net/fs_enet/mii-fec.c index 7e840d373ab..6a2e150e75b 100644 --- a/drivers/net/fs_enet/mii-fec.c +++ b/drivers/net/fs_enet/mii-fec.c @@ -101,17 +101,20 @@ static int fs_enet_fec_mii_reset(struct mii_bus *bus) return 0; } +static struct of_device_id fs_enet_mdio_fec_match[]; static int __devinit fs_enet_mdio_probe(struct platform_device *ofdev) { + const struct of_device_id *match; struct resource res; struct mii_bus *new_bus; struct fec_info *fec; int (*get_bus_freq)(struct device_node *); int ret = -ENOMEM, clock, speed; - if (!ofdev->dev.of_match) + match = of_match_device(fs_enet_mdio_fec_match, &ofdev->dev); + if (!match) return -EINVAL; - get_bus_freq = ofdev->dev.of_match->data; + get_bus_freq = match->data; new_bus = mdiobus_alloc(); if (!new_bus) diff --git a/drivers/net/sunhme.c b/drivers/net/sunhme.c index eb4f59fb01e..bff2f7999ff 100644 --- a/drivers/net/sunhme.c +++ b/drivers/net/sunhme.c @@ -3237,15 +3237,18 @@ static void happy_meal_pci_exit(void) #endif #ifdef CONFIG_SBUS +static const struct of_device_id hme_sbus_match[]; static int __devinit hme_sbus_probe(struct platform_device *op) { + const struct of_device_id *match; struct device_node *dp = op->dev.of_node; const char *model = of_get_property(dp, "model", NULL); int is_qfe; - if (!op->dev.of_match) + match = of_match_device(hme_sbus_match, &op->dev); + if (!match) return -EINVAL; - is_qfe = (op->dev.of_match->data != NULL); + is_qfe = (match->data != NULL); if (!is_qfe && model && !strcmp(model, "SUNW,sbus-qfe")) is_qfe = 1; diff --git a/drivers/scsi/qlogicpti.c b/drivers/scsi/qlogicpti.c index e2d45c91b8e..9689d41c788 100644 --- a/drivers/scsi/qlogicpti.c +++ b/drivers/scsi/qlogicpti.c @@ -1292,8 +1292,10 @@ static struct scsi_host_template qpti_template = { .use_clustering = ENABLE_CLUSTERING, }; +static const struct of_device_id qpti_match[]; static int __devinit qpti_sbus_probe(struct platform_device *op) { + const struct of_device_id *match; struct scsi_host_template *tpnt; struct device_node *dp = op->dev.of_node; struct Scsi_Host *host; @@ -1301,9 +1303,10 @@ static int __devinit qpti_sbus_probe(struct platform_device *op) static int nqptis; const char *fcode; - if (!op->dev.of_match) + match = of_match_device(qpti_match, &op->dev); + if (!match) return -EINVAL; - tpnt = op->dev.of_match->data; + tpnt = match->data; /* Sometimes Antares cards come up not completely * setup, and we get a report of a zero IRQ. diff --git a/drivers/tty/serial/of_serial.c b/drivers/tty/serial/of_serial.c index 0e8eec516df..c911b2419ab 100644 --- a/drivers/tty/serial/of_serial.c +++ b/drivers/tty/serial/of_serial.c @@ -80,14 +80,17 @@ static int __devinit of_platform_serial_setup(struct platform_device *ofdev, /* * Try to register a serial port */ +static struct of_device_id of_platform_serial_table[]; static int __devinit of_platform_serial_probe(struct platform_device *ofdev) { + const struct of_device_id *match; struct of_serial_info *info; struct uart_port port; int port_type; int ret; - if (!ofdev->dev.of_match) + match = of_match_device(of_platform_serial_table, &ofdev->dev); + if (!match) return -EINVAL; if (of_find_property(ofdev->dev.of_node, "used-by-rtas", NULL)) @@ -97,7 +100,7 @@ static int __devinit of_platform_serial_probe(struct platform_device *ofdev) if (info == NULL) return -ENOMEM; - port_type = (unsigned long)ofdev->dev.of_match->data; + port_type = (unsigned long)match->data; ret = of_platform_serial_setup(ofdev, port_type, &port); if (ret) goto out; diff --git a/drivers/usb/gadget/fsl_qe_udc.c b/drivers/usb/gadget/fsl_qe_udc.c index 36613b37c50..3a68e09309f 100644 --- a/drivers/usb/gadget/fsl_qe_udc.c +++ b/drivers/usb/gadget/fsl_qe_udc.c @@ -2539,15 +2539,18 @@ static void qe_udc_release(struct device *dev) } /* Driver probe functions */ +static const struct of_device_id qe_udc_match[]; static int __devinit qe_udc_probe(struct platform_device *ofdev) { + const struct of_device_id *match; struct device_node *np = ofdev->dev.of_node; struct qe_ep *ep; unsigned int ret = 0; unsigned int i; const void *prop; - if (!ofdev->dev.of_match) + match = of_match_device(qe_udc_match, &ofdev->dev); + if (!match) return -EINVAL; prop = of_get_property(np, "mode", NULL); @@ -2561,7 +2564,7 @@ static int __devinit qe_udc_probe(struct platform_device *ofdev) return -ENOMEM; } - udc_controller->soc_type = (unsigned long)ofdev->dev.of_match->data; + udc_controller->soc_type = (unsigned long)match->data; udc_controller->usb_regs = of_iomap(np, 0); if (!udc_controller->usb_regs) { ret = -ENOMEM; diff --git a/drivers/watchdog/mpc8xxx_wdt.c b/drivers/watchdog/mpc8xxx_wdt.c index 528bceb220f..eed5436ffb5 100644 --- a/drivers/watchdog/mpc8xxx_wdt.c +++ b/drivers/watchdog/mpc8xxx_wdt.c @@ -185,17 +185,20 @@ static struct miscdevice mpc8xxx_wdt_miscdev = { .fops = &mpc8xxx_wdt_fops, }; +static const struct of_device_id mpc8xxx_wdt_match[]; static int __devinit mpc8xxx_wdt_probe(struct platform_device *ofdev) { int ret; + const struct of_device_id *match; struct device_node *np = ofdev->dev.of_node; struct mpc8xxx_wdt_type *wdt_type; u32 freq = fsl_get_sys_freq(); bool enabled; - if (!ofdev->dev.of_match) + match = of_match_device(mpc8xxx_wdt_match, &ofdev->dev); + if (!match) return -EINVAL; - wdt_type = ofdev->dev.of_match->data; + wdt_type = match->data; if (!freq || freq == -1) return -EINVAL; diff --git a/include/linux/device.h b/include/linux/device.h index ab8dfc09570..d08399db6e2 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -442,7 +442,6 @@ struct device { struct dev_archdata archdata; struct device_node *of_node; /* associated device tree node */ - const struct of_device_id *of_match; /* matching of_device_id from driver */ dev_t devt; /* dev_t, creates the sysfs "dev" */ diff --git a/include/linux/of_device.h b/include/linux/of_device.h index b33d68814a7..ae5638480ef 100644 --- a/include/linux/of_device.h +++ b/include/linux/of_device.h @@ -21,12 +21,7 @@ extern void of_device_make_bus_id(struct device *dev); static inline int of_driver_match_device(struct device *dev, const struct device_driver *drv) { - const struct of_device_id *match; - - match = of_match_device(drv->of_match_table, dev); - if (match) - dev->of_match = match; - return match != NULL; + return of_match_device(drv->of_match_table, dev) != NULL; } extern struct platform_device *of_dev_get(struct platform_device *dev); @@ -62,6 +57,11 @@ static inline int of_device_uevent(struct device *dev, static inline void of_device_node_put(struct device *dev) { } +static inline const struct of_device_id *of_match_device( + const struct of_device_id *matches, const struct device *dev) +{ + return NULL; +} #endif /* CONFIG_OF_DEVICE */ #endif /* _LINUX_OF_DEVICE_H */ -- cgit v1.2.3-70-g09d2 From b448c4e3ae6d20108dba1d7833f2c0d3dbad87ce Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 29 Apr 2011 15:12:32 -0400 Subject: ftrace: Replace FTRACE_FL_NOTRACE flag with a hash of ignored functions To prepare for the accounting system that will allow multiple users of the function tracer, having the FTRACE_FL_NOTRACE as a flag in the dyn_trace record does not make sense. All ftrace_ops will soon have a hash of functions they should trace and not trace. By making a global hash of functions not to trace makes this easier for the transition. Signed-off-by: Steven Rostedt --- include/linux/ftrace.h | 1 - kernel/trace/ftrace.c | 176 +++++++++++++++++++++++++++++++++++++++++-------- 2 files changed, 150 insertions(+), 27 deletions(-) (limited to 'include') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 32047449b30..fe0a90a0924 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -149,7 +149,6 @@ enum { FTRACE_FL_FREE = (1 << 0), FTRACE_FL_FILTER = (1 << 1), FTRACE_FL_ENABLED = (1 << 2), - FTRACE_FL_NOTRACE = (1 << 3), }; struct dyn_ftrace { diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index d3406346ced..04c002a491f 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -57,6 +57,7 @@ /* hash bits for specific function selection */ #define FTRACE_HASH_BITS 7 #define FTRACE_FUNC_HASHSIZE (1 << FTRACE_HASH_BITS) +#define FTRACE_HASH_MAX_BITS 10 /* ftrace_enabled is a method to turn ftrace on or off */ int ftrace_enabled __read_mostly; @@ -865,6 +866,22 @@ enum { FTRACE_START_FUNC_RET = (1 << 3), FTRACE_STOP_FUNC_RET = (1 << 4), }; +struct ftrace_func_entry { + struct hlist_node hlist; + unsigned long ip; +}; + +struct ftrace_hash { + unsigned long size_bits; + struct hlist_head *buckets; + unsigned long count; +}; + +static struct hlist_head notrace_buckets[1 << FTRACE_HASH_MAX_BITS]; +static struct ftrace_hash notrace_hash = { + .size_bits = FTRACE_HASH_MAX_BITS, + .buckets = notrace_buckets, +}; static int ftrace_filtered; @@ -889,6 +906,79 @@ static struct ftrace_page *ftrace_pages; static struct dyn_ftrace *ftrace_free_records; +static struct ftrace_func_entry * +ftrace_lookup_ip(struct ftrace_hash *hash, unsigned long ip) +{ + unsigned long key; + struct ftrace_func_entry *entry; + struct hlist_head *hhd; + struct hlist_node *n; + + if (!hash->count) + return NULL; + + if (hash->size_bits > 0) + key = hash_long(ip, hash->size_bits); + else + key = 0; + + hhd = &hash->buckets[key]; + + hlist_for_each_entry_rcu(entry, n, hhd, hlist) { + if (entry->ip == ip) + return entry; + } + return NULL; +} + +static int add_hash_entry(struct ftrace_hash *hash, unsigned long ip) +{ + struct ftrace_func_entry *entry; + struct hlist_head *hhd; + unsigned long key; + + entry = kmalloc(sizeof(*entry), GFP_KERNEL); + if (!entry) + return -ENOMEM; + + if (hash->size_bits) + key = hash_long(ip, hash->size_bits); + else + key = 0; + + entry->ip = ip; + hhd = &hash->buckets[key]; + hlist_add_head(&entry->hlist, hhd); + hash->count++; + + return 0; +} + +static void +remove_hash_entry(struct ftrace_hash *hash, + struct ftrace_func_entry *entry) +{ + hlist_del(&entry->hlist); + kfree(entry); + hash->count--; +} + +static void ftrace_hash_clear(struct ftrace_hash *hash) +{ + struct hlist_head *hhd; + struct hlist_node *tp, *tn; + struct ftrace_func_entry *entry; + int size = 1 << hash->size_bits; + int i; + + for (i = 0; i < size; i++) { + hhd = &hash->buckets[i]; + hlist_for_each_entry_safe(entry, tp, tn, hhd, hlist) + remove_hash_entry(hash, entry); + } + FTRACE_WARN_ON(hash->count); +} + /* * This is a double for. Do not use 'break' to break out of the loop, * you must use a goto. @@ -1032,7 +1122,7 @@ __ftrace_replace_code(struct dyn_ftrace *rec, int enable) * If we want to enable it and filtering is on, enable it only if * it's filtered */ - if (enable && !(rec->flags & FTRACE_FL_NOTRACE)) { + if (enable && !ftrace_lookup_ip(¬race_hash, rec->ip)) { if (!ftrace_filtered || (rec->flags & FTRACE_FL_FILTER)) flag = FTRACE_FL_ENABLED; } @@ -1465,7 +1555,7 @@ t_next(struct seq_file *m, void *v, loff_t *pos) !(rec->flags & FTRACE_FL_FILTER)) || ((iter->flags & FTRACE_ITER_NOTRACE) && - !(rec->flags & FTRACE_FL_NOTRACE))) { + !ftrace_lookup_ip(¬race_hash, rec->ip))) { rec = NULL; goto retry; } @@ -1609,14 +1699,15 @@ static void ftrace_filter_reset(int enable) { struct ftrace_page *pg; struct dyn_ftrace *rec; - unsigned long type = enable ? FTRACE_FL_FILTER : FTRACE_FL_NOTRACE; mutex_lock(&ftrace_lock); - if (enable) + if (enable) { ftrace_filtered = 0; - do_for_each_ftrace_rec(pg, rec) { - rec->flags &= ~type; - } while_for_each_ftrace_rec(); + do_for_each_ftrace_rec(pg, rec) { + rec->flags &= ~FTRACE_FL_FILTER; + } while_for_each_ftrace_rec(); + } else + ftrace_hash_clear(¬race_hash); mutex_unlock(&ftrace_lock); } @@ -1716,13 +1807,36 @@ static int ftrace_match(char *str, char *regex, int len, int type) return matched; } -static void -update_record(struct dyn_ftrace *rec, unsigned long flag, int not) +static int +update_record(struct dyn_ftrace *rec, int enable, int not) { - if (not) - rec->flags &= ~flag; - else - rec->flags |= flag; + struct ftrace_func_entry *entry; + struct ftrace_hash *hash = ¬race_hash; + int ret = 0; + + if (enable) { + if (not) + rec->flags &= ~FTRACE_FL_FILTER; + else + rec->flags |= FTRACE_FL_FILTER; + } else { + if (not) { + /* Do nothing if it doesn't exist */ + entry = ftrace_lookup_ip(hash, rec->ip); + if (!entry) + return 0; + + remove_hash_entry(hash, entry); + } else { + /* Do nothing if it exists */ + entry = ftrace_lookup_ip(hash, rec->ip); + if (entry) + return 0; + + ret = add_hash_entry(hash, rec->ip); + } + } + return ret; } static int @@ -1754,16 +1868,14 @@ static int match_records(char *buff, int len, char *mod, int enable, int not) struct dyn_ftrace *rec; int type = MATCH_FULL; char *search = buff; - unsigned long flag; int found = 0; + int ret; if (len) { type = filter_parse_regex(buff, len, &search, ¬); search_len = strlen(search); } - flag = enable ? FTRACE_FL_FILTER : FTRACE_FL_NOTRACE; - mutex_lock(&ftrace_lock); if (unlikely(ftrace_disabled)) @@ -1772,7 +1884,11 @@ static int match_records(char *buff, int len, char *mod, int enable, int not) do_for_each_ftrace_rec(pg, rec) { if (ftrace_match_record(rec, mod, search, search_len, type)) { - update_record(rec, flag, not); + ret = update_record(rec, enable, not); + if (ret < 0) { + found = ret; + goto out_unlock; + } found = 1; } /* @@ -1821,6 +1937,7 @@ static int ftrace_mod_callback(char *func, char *cmd, char *param, int enable) { char *mod; + int ret = -EINVAL; /* * cmd == 'mod' because we only registered this func @@ -1832,15 +1949,19 @@ ftrace_mod_callback(char *func, char *cmd, char *param, int enable) /* we must have a module name */ if (!param) - return -EINVAL; + return ret; mod = strsep(¶m, ":"); if (!strlen(mod)) - return -EINVAL; + return ret; - if (ftrace_match_module_records(func, mod, enable)) - return 0; - return -EINVAL; + ret = ftrace_match_module_records(func, mod, enable); + if (!ret) + ret = -EINVAL; + if (ret < 0) + return ret; + + return 0; } static struct ftrace_func_command ftrace_mod_cmd = { @@ -2132,14 +2253,17 @@ static int ftrace_process_regex(char *buff, int len, int enable) { char *func, *command, *next = buff; struct ftrace_func_command *p; - int ret = -EINVAL; + int ret; func = strsep(&next, ":"); if (!next) { - if (ftrace_match_records(func, len, enable)) - return 0; - return ret; + ret = ftrace_match_records(func, len, enable); + if (!ret) + ret = -EINVAL; + if (ret < 0) + return ret; + return 0; } /* command found */ -- cgit v1.2.3-70-g09d2 From 1cf41dd79993389b012e4542ab502ce36ae7343f Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 29 Apr 2011 20:59:51 -0400 Subject: ftrace: Use hash instead for FTRACE_FL_FILTER When multiple users are allowed to have their own set of functions to trace, having the FTRACE_FL_FILTER flag will not be enough to handle the accounting of those users. Each user will need their own set of functions. Replace the FTRACE_FL_FILTER with a filter_hash instead. This is temporary until the rest of the function filtering accounting gets in. Signed-off-by: Steven Rostedt --- include/linux/ftrace.h | 3 +- kernel/trace/ftrace.c | 151 ++++++++++++++++++++++--------------------------- 2 files changed, 70 insertions(+), 84 deletions(-) (limited to 'include') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index fe0a90a0924..52fc5d4e6ed 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -147,8 +147,7 @@ extern int ftrace_text_reserved(void *start, void *end); enum { FTRACE_FL_FREE = (1 << 0), - FTRACE_FL_FILTER = (1 << 1), - FTRACE_FL_ENABLED = (1 << 2), + FTRACE_FL_ENABLED = (1 << 1), }; struct dyn_ftrace { diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 04c002a491f..222eca4c302 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -883,7 +883,11 @@ static struct ftrace_hash notrace_hash = { .buckets = notrace_buckets, }; -static int ftrace_filtered; +static struct hlist_head filter_buckets[1 << FTRACE_HASH_MAX_BITS]; +static struct ftrace_hash filter_hash = { + .size_bits = FTRACE_HASH_MAX_BITS, + .buckets = filter_buckets, +}; static struct dyn_ftrace *ftrace_new_addrs; @@ -1123,7 +1127,7 @@ __ftrace_replace_code(struct dyn_ftrace *rec, int enable) * it's filtered */ if (enable && !ftrace_lookup_ip(¬race_hash, rec->ip)) { - if (!ftrace_filtered || (rec->flags & FTRACE_FL_FILTER)) + if (!filter_hash.count || ftrace_lookup_ip(&filter_hash, rec->ip)) flag = FTRACE_FL_ENABLED; } @@ -1430,6 +1434,7 @@ struct ftrace_iterator { struct dyn_ftrace *func; struct ftrace_func_probe *probe; struct trace_parser parser; + struct ftrace_hash *hash; int hidx; int idx; unsigned flags; @@ -1552,7 +1557,7 @@ t_next(struct seq_file *m, void *v, loff_t *pos) if ((rec->flags & FTRACE_FL_FREE) || ((iter->flags & FTRACE_ITER_FILTER) && - !(rec->flags & FTRACE_FL_FILTER)) || + !(ftrace_lookup_ip(&filter_hash, rec->ip))) || ((iter->flags & FTRACE_ITER_NOTRACE) && !ftrace_lookup_ip(¬race_hash, rec->ip))) { @@ -1598,7 +1603,7 @@ static void *t_start(struct seq_file *m, loff_t *pos) * off, we can short cut and just print out that all * functions are enabled. */ - if (iter->flags & FTRACE_ITER_FILTER && !ftrace_filtered) { + if (iter->flags & FTRACE_ITER_FILTER && !filter_hash.count) { if (*pos > 0) return t_hash_start(m, pos); iter->flags |= FTRACE_ITER_PRINTALL; @@ -1695,24 +1700,16 @@ ftrace_avail_open(struct inode *inode, struct file *file) return ret; } -static void ftrace_filter_reset(int enable) +static void ftrace_filter_reset(struct ftrace_hash *hash) { - struct ftrace_page *pg; - struct dyn_ftrace *rec; - mutex_lock(&ftrace_lock); - if (enable) { - ftrace_filtered = 0; - do_for_each_ftrace_rec(pg, rec) { - rec->flags &= ~FTRACE_FL_FILTER; - } while_for_each_ftrace_rec(); - } else - ftrace_hash_clear(¬race_hash); + ftrace_hash_clear(hash); mutex_unlock(&ftrace_lock); } static int -ftrace_regex_open(struct inode *inode, struct file *file, int enable) +ftrace_regex_open(struct ftrace_hash *hash, int flag, + struct inode *inode, struct file *file) { struct ftrace_iterator *iter; int ret = 0; @@ -1729,15 +1726,16 @@ ftrace_regex_open(struct inode *inode, struct file *file, int enable) return -ENOMEM; } + iter->hash = hash; + mutex_lock(&ftrace_regex_lock); if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) - ftrace_filter_reset(enable); + ftrace_filter_reset(hash); if (file->f_mode & FMODE_READ) { iter->pg = ftrace_pages_start; - iter->flags = enable ? FTRACE_ITER_FILTER : - FTRACE_ITER_NOTRACE; + iter->flags = flag; ret = seq_open(file, &show_ftrace_seq_ops); if (!ret) { @@ -1757,13 +1755,15 @@ ftrace_regex_open(struct inode *inode, struct file *file, int enable) static int ftrace_filter_open(struct inode *inode, struct file *file) { - return ftrace_regex_open(inode, file, 1); + return ftrace_regex_open(&filter_hash, FTRACE_ITER_FILTER, + inode, file); } static int ftrace_notrace_open(struct inode *inode, struct file *file) { - return ftrace_regex_open(inode, file, 0); + return ftrace_regex_open(¬race_hash, FTRACE_ITER_NOTRACE, + inode, file); } static loff_t @@ -1808,33 +1808,24 @@ static int ftrace_match(char *str, char *regex, int len, int type) } static int -update_record(struct dyn_ftrace *rec, int enable, int not) +enter_record(struct ftrace_hash *hash, struct dyn_ftrace *rec, int not) { struct ftrace_func_entry *entry; - struct ftrace_hash *hash = ¬race_hash; int ret = 0; - if (enable) { - if (not) - rec->flags &= ~FTRACE_FL_FILTER; - else - rec->flags |= FTRACE_FL_FILTER; - } else { - if (not) { - /* Do nothing if it doesn't exist */ - entry = ftrace_lookup_ip(hash, rec->ip); - if (!entry) - return 0; + entry = ftrace_lookup_ip(hash, rec->ip); + if (not) { + /* Do nothing if it doesn't exist */ + if (!entry) + return 0; - remove_hash_entry(hash, entry); - } else { - /* Do nothing if it exists */ - entry = ftrace_lookup_ip(hash, rec->ip); - if (entry) - return 0; + remove_hash_entry(hash, entry); + } else { + /* Do nothing if it exists */ + if (entry) + return 0; - ret = add_hash_entry(hash, rec->ip); - } + ret = add_hash_entry(hash, rec->ip); } return ret; } @@ -1861,7 +1852,9 @@ ftrace_match_record(struct dyn_ftrace *rec, char *mod, return ftrace_match(str, regex, len, type); } -static int match_records(char *buff, int len, char *mod, int enable, int not) +static int +match_records(struct ftrace_hash *hash, char *buff, + int len, char *mod, int not) { unsigned search_len = 0; struct ftrace_page *pg; @@ -1884,20 +1877,13 @@ static int match_records(char *buff, int len, char *mod, int enable, int not) do_for_each_ftrace_rec(pg, rec) { if (ftrace_match_record(rec, mod, search, search_len, type)) { - ret = update_record(rec, enable, not); + ret = enter_record(hash, rec, not); if (ret < 0) { found = ret; goto out_unlock; } found = 1; } - /* - * Only enable filtering if we have a function that - * is filtered on. - */ - if (enable && (rec->flags & FTRACE_FL_FILTER)) - ftrace_filtered = 1; - } while_for_each_ftrace_rec(); out_unlock: mutex_unlock(&ftrace_lock); @@ -1906,12 +1892,13 @@ static int match_records(char *buff, int len, char *mod, int enable, int not) } static int -ftrace_match_records(char *buff, int len, int enable) +ftrace_match_records(struct ftrace_hash *hash, char *buff, int len) { - return match_records(buff, len, NULL, enable, 0); + return match_records(hash, buff, len, NULL, 0); } -static int ftrace_match_module_records(char *buff, char *mod, int enable) +static int +ftrace_match_module_records(struct ftrace_hash *hash, char *buff, char *mod) { int not = 0; @@ -1925,7 +1912,7 @@ static int ftrace_match_module_records(char *buff, char *mod, int enable) not = 1; } - return match_records(buff, strlen(buff), mod, enable, not); + return match_records(hash, buff, strlen(buff), mod, not); } /* @@ -1936,6 +1923,7 @@ static int ftrace_match_module_records(char *buff, char *mod, int enable) static int ftrace_mod_callback(char *func, char *cmd, char *param, int enable) { + struct ftrace_hash *hash; char *mod; int ret = -EINVAL; @@ -1955,7 +1943,12 @@ ftrace_mod_callback(char *func, char *cmd, char *param, int enable) if (!strlen(mod)) return ret; - ret = ftrace_match_module_records(func, mod, enable); + if (enable) + hash = &filter_hash; + else + hash = ¬race_hash; + + ret = ftrace_match_module_records(hash, func, mod); if (!ret) ret = -EINVAL; if (ret < 0) @@ -2253,12 +2246,18 @@ static int ftrace_process_regex(char *buff, int len, int enable) { char *func, *command, *next = buff; struct ftrace_func_command *p; + struct ftrace_hash *hash; int ret; + if (enable) + hash = &filter_hash; + else + hash = ¬race_hash; + func = strsep(&next, ":"); if (!next) { - ret = ftrace_match_records(func, len, enable); + ret = ftrace_match_records(hash, func, len); if (!ret) ret = -EINVAL; if (ret < 0) @@ -2340,16 +2339,16 @@ ftrace_notrace_write(struct file *file, const char __user *ubuf, } static void -ftrace_set_regex(unsigned char *buf, int len, int reset, int enable) +ftrace_set_regex(struct ftrace_hash *hash, unsigned char *buf, int len, int reset) { if (unlikely(ftrace_disabled)) return; mutex_lock(&ftrace_regex_lock); if (reset) - ftrace_filter_reset(enable); + ftrace_filter_reset(hash); if (buf) - ftrace_match_records(buf, len, enable); + ftrace_match_records(hash, buf, len); mutex_unlock(&ftrace_regex_lock); } @@ -2364,7 +2363,7 @@ ftrace_set_regex(unsigned char *buf, int len, int reset, int enable) */ void ftrace_set_filter(unsigned char *buf, int len, int reset) { - ftrace_set_regex(buf, len, reset, 1); + ftrace_set_regex(&filter_hash, buf, len, reset); } /** @@ -2379,7 +2378,7 @@ void ftrace_set_filter(unsigned char *buf, int len, int reset) */ void ftrace_set_notrace(unsigned char *buf, int len, int reset) { - ftrace_set_regex(buf, len, reset, 0); + ftrace_set_regex(¬race_hash, buf, len, reset); } /* @@ -2431,22 +2430,22 @@ static void __init set_ftrace_early_graph(char *buf) } #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ -static void __init set_ftrace_early_filter(char *buf, int enable) +static void __init set_ftrace_early_filter(struct ftrace_hash *hash, char *buf) { char *func; while (buf) { func = strsep(&buf, ","); - ftrace_set_regex(func, strlen(func), 0, enable); + ftrace_set_regex(hash, func, strlen(func), 0); } } static void __init set_ftrace_early_filters(void) { if (ftrace_filter_buf[0]) - set_ftrace_early_filter(ftrace_filter_buf, 1); + set_ftrace_early_filter(&filter_hash, ftrace_filter_buf); if (ftrace_notrace_buf[0]) - set_ftrace_early_filter(ftrace_notrace_buf, 0); + set_ftrace_early_filter(¬race_hash, ftrace_notrace_buf); #ifdef CONFIG_FUNCTION_GRAPH_TRACER if (ftrace_graph_buf[0]) set_ftrace_early_graph(ftrace_graph_buf); @@ -2454,7 +2453,7 @@ static void __init set_ftrace_early_filters(void) } static int -ftrace_regex_release(struct inode *inode, struct file *file, int enable) +ftrace_regex_release(struct inode *inode, struct file *file) { struct seq_file *m = (struct seq_file *)file->private_data; struct ftrace_iterator *iter; @@ -2471,7 +2470,7 @@ ftrace_regex_release(struct inode *inode, struct file *file, int enable) parser = &iter->parser; if (trace_parser_loaded(parser)) { parser->buffer[parser->idx] = 0; - ftrace_match_records(parser->buffer, parser->idx, enable); + ftrace_match_records(iter->hash, parser->buffer, parser->idx); } trace_parser_put(parser); @@ -2488,18 +2487,6 @@ ftrace_regex_release(struct inode *inode, struct file *file, int enable) return 0; } -static int -ftrace_filter_release(struct inode *inode, struct file *file) -{ - return ftrace_regex_release(inode, file, 1); -} - -static int -ftrace_notrace_release(struct inode *inode, struct file *file) -{ - return ftrace_regex_release(inode, file, 0); -} - static const struct file_operations ftrace_avail_fops = { .open = ftrace_avail_open, .read = seq_read, @@ -2512,7 +2499,7 @@ static const struct file_operations ftrace_filter_fops = { .read = seq_read, .write = ftrace_filter_write, .llseek = ftrace_regex_lseek, - .release = ftrace_filter_release, + .release = ftrace_regex_release, }; static const struct file_operations ftrace_notrace_fops = { @@ -2520,7 +2507,7 @@ static const struct file_operations ftrace_notrace_fops = { .read = seq_read, .write = ftrace_notrace_write, .llseek = ftrace_regex_lseek, - .release = ftrace_notrace_release, + .release = ftrace_regex_release, }; #ifdef CONFIG_FUNCTION_GRAPH_TRACER -- cgit v1.2.3-70-g09d2 From f45948e898e7bc76a73a468796d2ce80dd040058 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 2 May 2011 12:29:25 -0400 Subject: ftrace: Create a global_ops to hold the filter and notrace hashes Combine the filter and notrace hashes to be accessed by a single entity, the global_ops. The global_ops is a ftrace_ops structure that is passed to different functions that can read or modify the filtering of the function tracer. The ftrace_ops structure was modified to hold a filter and notrace hashes so that later patches may allow each ftrace_ops to have its own set of rules to what functions may be filtered. Signed-off-by: Steven Rostedt --- include/linux/ftrace.h | 10 ++++++-- kernel/trace/ftrace.c | 65 +++++++++++++++++++++++++++++++++++--------------- 2 files changed, 54 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 52fc5d4e6ed..6658a51390f 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -29,9 +29,15 @@ ftrace_enable_sysctl(struct ctl_table *table, int write, typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip); +struct ftrace_hash; + struct ftrace_ops { - ftrace_func_t func; - struct ftrace_ops *next; + ftrace_func_t func; + struct ftrace_ops *next; +#ifdef CONFIG_DYNAMIC_FTRACE + struct ftrace_hash *notrace_hash; + struct ftrace_hash *filter_hash; +#endif }; extern int function_trace_stop; diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 222eca4c302..a517a6c4064 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -889,6 +889,12 @@ static struct ftrace_hash filter_hash = { .buckets = filter_buckets, }; +struct ftrace_ops global_ops = { + .func = ftrace_stub, + .notrace_hash = ¬race_hash, + .filter_hash = &filter_hash, +}; + static struct dyn_ftrace *ftrace_new_addrs; static DEFINE_MUTEX(ftrace_regex_lock); @@ -1112,6 +1118,7 @@ int ftrace_text_reserved(void *start, void *end) static int __ftrace_replace_code(struct dyn_ftrace *rec, int enable) { + struct ftrace_ops *ops = &global_ops; unsigned long ftrace_addr; unsigned long flag = 0UL; @@ -1126,8 +1133,9 @@ __ftrace_replace_code(struct dyn_ftrace *rec, int enable) * If we want to enable it and filtering is on, enable it only if * it's filtered */ - if (enable && !ftrace_lookup_ip(¬race_hash, rec->ip)) { - if (!filter_hash.count || ftrace_lookup_ip(&filter_hash, rec->ip)) + if (enable && !ftrace_lookup_ip(ops->notrace_hash, rec->ip)) { + if (!ops->filter_hash->count || + ftrace_lookup_ip(ops->filter_hash, rec->ip)) flag = FTRACE_FL_ENABLED; } @@ -1531,6 +1539,7 @@ static void * t_next(struct seq_file *m, void *v, loff_t *pos) { struct ftrace_iterator *iter = m->private; + struct ftrace_ops *ops = &global_ops; struct dyn_ftrace *rec = NULL; if (unlikely(ftrace_disabled)) @@ -1557,10 +1566,10 @@ t_next(struct seq_file *m, void *v, loff_t *pos) if ((rec->flags & FTRACE_FL_FREE) || ((iter->flags & FTRACE_ITER_FILTER) && - !(ftrace_lookup_ip(&filter_hash, rec->ip))) || + !(ftrace_lookup_ip(ops->filter_hash, rec->ip))) || ((iter->flags & FTRACE_ITER_NOTRACE) && - !ftrace_lookup_ip(¬race_hash, rec->ip))) { + !ftrace_lookup_ip(ops->notrace_hash, rec->ip))) { rec = NULL; goto retry; } @@ -1584,6 +1593,7 @@ static void reset_iter_read(struct ftrace_iterator *iter) static void *t_start(struct seq_file *m, loff_t *pos) { struct ftrace_iterator *iter = m->private; + struct ftrace_ops *ops = &global_ops; void *p = NULL; loff_t l; @@ -1603,7 +1613,7 @@ static void *t_start(struct seq_file *m, loff_t *pos) * off, we can short cut and just print out that all * functions are enabled. */ - if (iter->flags & FTRACE_ITER_FILTER && !filter_hash.count) { + if (iter->flags & FTRACE_ITER_FILTER && !ops->filter_hash->count) { if (*pos > 0) return t_hash_start(m, pos); iter->flags |= FTRACE_ITER_PRINTALL; @@ -1708,10 +1718,11 @@ static void ftrace_filter_reset(struct ftrace_hash *hash) } static int -ftrace_regex_open(struct ftrace_hash *hash, int flag, +ftrace_regex_open(struct ftrace_ops *ops, int flag, struct inode *inode, struct file *file) { struct ftrace_iterator *iter; + struct ftrace_hash *hash; int ret = 0; if (unlikely(ftrace_disabled)) @@ -1726,6 +1737,11 @@ ftrace_regex_open(struct ftrace_hash *hash, int flag, return -ENOMEM; } + if (flag & FTRACE_ITER_NOTRACE) + hash = ops->notrace_hash; + else + hash = ops->filter_hash; + iter->hash = hash; mutex_lock(&ftrace_regex_lock); @@ -1755,14 +1771,14 @@ ftrace_regex_open(struct ftrace_hash *hash, int flag, static int ftrace_filter_open(struct inode *inode, struct file *file) { - return ftrace_regex_open(&filter_hash, FTRACE_ITER_FILTER, + return ftrace_regex_open(&global_ops, FTRACE_ITER_FILTER, inode, file); } static int ftrace_notrace_open(struct inode *inode, struct file *file) { - return ftrace_regex_open(¬race_hash, FTRACE_ITER_NOTRACE, + return ftrace_regex_open(&global_ops, FTRACE_ITER_NOTRACE, inode, file); } @@ -1923,6 +1939,7 @@ ftrace_match_module_records(struct ftrace_hash *hash, char *buff, char *mod) static int ftrace_mod_callback(char *func, char *cmd, char *param, int enable) { + struct ftrace_ops *ops = &global_ops; struct ftrace_hash *hash; char *mod; int ret = -EINVAL; @@ -1944,9 +1961,9 @@ ftrace_mod_callback(char *func, char *cmd, char *param, int enable) return ret; if (enable) - hash = &filter_hash; + hash = ops->filter_hash; else - hash = ¬race_hash; + hash = ops->notrace_hash; ret = ftrace_match_module_records(hash, func, mod); if (!ret) @@ -2245,14 +2262,15 @@ int unregister_ftrace_command(struct ftrace_func_command *cmd) static int ftrace_process_regex(char *buff, int len, int enable) { char *func, *command, *next = buff; + struct ftrace_ops *ops = &global_ops; struct ftrace_func_command *p; struct ftrace_hash *hash; int ret; if (enable) - hash = &filter_hash; + hash = ops->filter_hash; else - hash = ¬race_hash; + hash = ops->notrace_hash; func = strsep(&next, ":"); @@ -2339,11 +2357,19 @@ ftrace_notrace_write(struct file *file, const char __user *ubuf, } static void -ftrace_set_regex(struct ftrace_hash *hash, unsigned char *buf, int len, int reset) +ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len, + int reset, int enable) { + struct ftrace_hash *hash; + if (unlikely(ftrace_disabled)) return; + if (enable) + hash = ops->filter_hash; + else + hash = ops->notrace_hash; + mutex_lock(&ftrace_regex_lock); if (reset) ftrace_filter_reset(hash); @@ -2363,7 +2389,7 @@ ftrace_set_regex(struct ftrace_hash *hash, unsigned char *buf, int len, int rese */ void ftrace_set_filter(unsigned char *buf, int len, int reset) { - ftrace_set_regex(&filter_hash, buf, len, reset); + ftrace_set_regex(&global_ops, buf, len, reset, 1); } /** @@ -2378,7 +2404,7 @@ void ftrace_set_filter(unsigned char *buf, int len, int reset) */ void ftrace_set_notrace(unsigned char *buf, int len, int reset) { - ftrace_set_regex(¬race_hash, buf, len, reset); + ftrace_set_regex(&global_ops, buf, len, reset, 0); } /* @@ -2430,22 +2456,23 @@ static void __init set_ftrace_early_graph(char *buf) } #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ -static void __init set_ftrace_early_filter(struct ftrace_hash *hash, char *buf) +static void __init +set_ftrace_early_filter(struct ftrace_ops *ops, char *buf, int enable) { char *func; while (buf) { func = strsep(&buf, ","); - ftrace_set_regex(hash, func, strlen(func), 0); + ftrace_set_regex(ops, func, strlen(func), 0, enable); } } static void __init set_ftrace_early_filters(void) { if (ftrace_filter_buf[0]) - set_ftrace_early_filter(&filter_hash, ftrace_filter_buf); + set_ftrace_early_filter(&global_ops, ftrace_filter_buf, 1); if (ftrace_notrace_buf[0]) - set_ftrace_early_filter(¬race_hash, ftrace_notrace_buf); + set_ftrace_early_filter(&global_ops, ftrace_notrace_buf, 0); #ifdef CONFIG_FUNCTION_GRAPH_TRACER if (ftrace_graph_buf[0]) set_ftrace_early_graph(ftrace_graph_buf); -- cgit v1.2.3-70-g09d2 From ed926f9b35cda0988234c356e16a7cb30f4e5338 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 3 May 2011 13:25:24 -0400 Subject: ftrace: Use counters to enable functions to trace Every function has its own record that stores the instruction pointer and flags for the function to be traced. There are only two flags: enabled and free. The enabled flag states that tracing for the function has been enabled (actively traced), and the free flag states that the record no longer points to a function and can be used by new functions (loaded modules). These flags are now moved to the MSB of the flags (actually just the top 32bits). The rest of the bits (30 bits) are now used as a ref counter. Everytime a tracer register functions to trace, those functions will have its counter incremented. When tracing is enabled, to determine if a function should be traced, the counter is examined, and if it is non-zero it is set to trace. When a ftrace_ops is registered to trace functions, its hashes are examined. If the ftrace_ops filter_hash count is zero, then all functions are set to be traced, otherwise only the functions in the hash are to be traced. The exception to this is if a function is also in the ftrace_ops notrace_hash. Then that function's counter is not incremented for this ftrace_ops. Signed-off-by: Steven Rostedt --- include/linux/ftrace.h | 8 ++- kernel/trace/ftrace.c | 158 ++++++++++++++++++++++++++++++++++++++++++++----- 2 files changed, 148 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 6658a51390f..ab1c46e70bb 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -37,6 +37,7 @@ struct ftrace_ops { #ifdef CONFIG_DYNAMIC_FTRACE struct ftrace_hash *notrace_hash; struct ftrace_hash *filter_hash; + unsigned long flags; #endif }; @@ -152,10 +153,13 @@ extern void unregister_ftrace_function_probe_all(char *glob); extern int ftrace_text_reserved(void *start, void *end); enum { - FTRACE_FL_FREE = (1 << 0), - FTRACE_FL_ENABLED = (1 << 1), + FTRACE_FL_ENABLED = (1 << 30), + FTRACE_FL_FREE = (1 << 31), }; +#define FTRACE_FL_MASK (0x3UL << 30) +#define FTRACE_REF_MAX ((1 << 30) - 1) + struct dyn_ftrace { union { unsigned long ip; /* address of mcount call-site */ diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 46f08264980..5dd332cc5aa 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -890,6 +890,10 @@ static const struct ftrace_hash empty_hash = { }; #define EMPTY_HASH ((struct ftrace_hash *)&empty_hash) +enum { + FTRACE_OPS_FL_ENABLED = 1, +}; + struct ftrace_ops global_ops = { .func = ftrace_stub, .notrace_hash = EMPTY_HASH, @@ -1161,6 +1165,105 @@ ftrace_hash_move(struct ftrace_hash **dst, struct ftrace_hash *src) } \ } +static void __ftrace_hash_rec_update(struct ftrace_ops *ops, + int filter_hash, + bool inc) +{ + struct ftrace_hash *hash; + struct ftrace_hash *other_hash; + struct ftrace_page *pg; + struct dyn_ftrace *rec; + int count = 0; + int all = 0; + + /* Only update if the ops has been registered */ + if (!(ops->flags & FTRACE_OPS_FL_ENABLED)) + return; + + /* + * In the filter_hash case: + * If the count is zero, we update all records. + * Otherwise we just update the items in the hash. + * + * In the notrace_hash case: + * We enable the update in the hash. + * As disabling notrace means enabling the tracing, + * and enabling notrace means disabling, the inc variable + * gets inversed. + */ + if (filter_hash) { + hash = ops->filter_hash; + other_hash = ops->notrace_hash; + if (!hash->count) + all = 1; + } else { + inc = !inc; + hash = ops->notrace_hash; + other_hash = ops->filter_hash; + /* + * If the notrace hash has no items, + * then there's nothing to do. + */ + if (!hash->count) + return; + } + + do_for_each_ftrace_rec(pg, rec) { + int in_other_hash = 0; + int in_hash = 0; + int match = 0; + + if (all) { + /* + * Only the filter_hash affects all records. + * Update if the record is not in the notrace hash. + */ + if (!ftrace_lookup_ip(other_hash, rec->ip)) + match = 1; + } else { + in_hash = !!ftrace_lookup_ip(hash, rec->ip); + in_other_hash = !!ftrace_lookup_ip(other_hash, rec->ip); + + /* + * + */ + if (filter_hash && in_hash && !in_other_hash) + match = 1; + else if (!filter_hash && in_hash && + (in_other_hash || !other_hash->count)) + match = 1; + } + if (!match) + continue; + + if (inc) { + rec->flags++; + if (FTRACE_WARN_ON((rec->flags & ~FTRACE_FL_MASK) == FTRACE_REF_MAX)) + return; + } else { + if (FTRACE_WARN_ON((rec->flags & ~FTRACE_FL_MASK) == 0)) + return; + rec->flags--; + } + count++; + /* Shortcut, if we handled all records, we are done. */ + if (!all && count == hash->count) + return; + } while_for_each_ftrace_rec(); +} + +static void ftrace_hash_rec_disable(struct ftrace_ops *ops, + int filter_hash) +{ + __ftrace_hash_rec_update(ops, filter_hash, 0); +} + +static void ftrace_hash_rec_enable(struct ftrace_ops *ops, + int filter_hash) +{ + __ftrace_hash_rec_update(ops, filter_hash, 1); +} + static void ftrace_free_rec(struct dyn_ftrace *rec) { rec->freelist = ftrace_free_records; @@ -1276,26 +1379,24 @@ int ftrace_text_reserved(void *start, void *end) static int __ftrace_replace_code(struct dyn_ftrace *rec, int enable) { - struct ftrace_ops *ops = &global_ops; unsigned long ftrace_addr; unsigned long flag = 0UL; ftrace_addr = (unsigned long)FTRACE_ADDR; /* - * If this record is not to be traced or we want to disable it, - * then disable it. + * If we are enabling tracing: * - * If we want to enable it and filtering is off, then enable it. + * If the record has a ref count, then we need to enable it + * because someone is using it. * - * If we want to enable it and filtering is on, enable it only if - * it's filtered + * Otherwise we make sure its disabled. + * + * If we are disabling tracing, then disable all records that + * are enabled. */ - if (enable && !ftrace_lookup_ip(ops->notrace_hash, rec->ip)) { - if (!ops->filter_hash->count || - ftrace_lookup_ip(ops->filter_hash, rec->ip)) - flag = FTRACE_FL_ENABLED; - } + if (enable && (rec->flags & ~FTRACE_FL_MASK)) + flag = FTRACE_FL_ENABLED; /* If the state of this record hasn't changed, then do nothing */ if ((rec->flags & FTRACE_FL_ENABLED) == flag) @@ -1423,17 +1524,25 @@ static void ftrace_startup_enable(int command) static void ftrace_startup(int command) { + struct ftrace_ops *ops = &global_ops; + if (unlikely(ftrace_disabled)) return; ftrace_start_up++; command |= FTRACE_ENABLE_CALLS; + ops->flags |= FTRACE_OPS_FL_ENABLED; + if (ftrace_start_up == 1) + ftrace_hash_rec_enable(ops, 1); + ftrace_startup_enable(command); } static void ftrace_shutdown(int command) { + struct ftrace_ops *ops = &global_ops; + if (unlikely(ftrace_disabled)) return; @@ -1446,7 +1555,12 @@ static void ftrace_shutdown(int command) WARN_ON_ONCE(ftrace_start_up < 0); if (!ftrace_start_up) + ftrace_hash_rec_disable(ops, 1); + + if (!ftrace_start_up) { command |= FTRACE_DISABLE_CALLS; + ops->flags &= ~FTRACE_OPS_FL_ENABLED; + } if (saved_ftrace_func != ftrace_trace_function) { saved_ftrace_func = ftrace_trace_function; @@ -2668,6 +2782,7 @@ ftrace_regex_release(struct inode *inode, struct file *file) struct ftrace_iterator *iter; struct ftrace_hash **orig_hash; struct trace_parser *parser; + int filter_hash; int ret; mutex_lock(&ftrace_regex_lock); @@ -2687,15 +2802,26 @@ ftrace_regex_release(struct inode *inode, struct file *file) trace_parser_put(parser); if (file->f_mode & FMODE_WRITE) { - if (iter->flags & FTRACE_ITER_NOTRACE) - orig_hash = &iter->ops->notrace_hash; - else + filter_hash = !!(iter->flags & FTRACE_ITER_FILTER); + + if (filter_hash) orig_hash = &iter->ops->filter_hash; + else + orig_hash = &iter->ops->notrace_hash; mutex_lock(&ftrace_lock); + /* + * Remove the current set, update the hash and add + * them back. + */ + ftrace_hash_rec_disable(iter->ops, filter_hash); ret = ftrace_hash_move(orig_hash, iter->hash); - if (!ret && ftrace_start_up && ftrace_enabled) - ftrace_run_update_code(FTRACE_ENABLE_CALLS); + if (!ret) { + ftrace_hash_rec_enable(iter->ops, filter_hash); + if (iter->ops->flags & FTRACE_OPS_FL_ENABLED + && ftrace_enabled) + ftrace_run_update_code(FTRACE_ENABLE_CALLS); + } mutex_unlock(&ftrace_lock); } free_ftrace_hash(iter->hash); -- cgit v1.2.3-70-g09d2 From b848914ce39589d89ee0078a6d1ef452b464729e Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Wed, 4 May 2011 09:27:52 -0400 Subject: ftrace: Implement separate user function filtering ftrace_ops that are registered to trace functions can now be agnostic to each other in respect to what functions they trace. Each ops has their own hash of the functions they want to trace and a hash to what they do not want to trace. A empty hash for the functions they want to trace denotes all functions should be traced that are not in the notrace hash. Cc: Paul E. McKenney Signed-off-by: Steven Rostedt --- include/linux/ftrace.h | 7 +- kernel/trace/ftrace.c | 193 ++++++++++++++++++++++++++++++-------- kernel/trace/trace_functions.c | 2 + kernel/trace/trace_irqsoff.c | 1 + kernel/trace/trace_sched_wakeup.c | 1 + kernel/trace/trace_stack.c | 1 + 6 files changed, 166 insertions(+), 39 deletions(-) (limited to 'include') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index ab1c46e70bb..4609c0ece79 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -31,13 +31,18 @@ typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip); struct ftrace_hash; +enum { + FTRACE_OPS_FL_ENABLED = 1 << 0, + FTRACE_OPS_FL_GLOBAL = 1 << 1, +}; + struct ftrace_ops { ftrace_func_t func; struct ftrace_ops *next; + unsigned long flags; #ifdef CONFIG_DYNAMIC_FTRACE struct ftrace_hash *notrace_hash; struct ftrace_hash *filter_hash; - unsigned long flags; #endif }; diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 92b6fdf49ae..6c7e1df39b5 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -87,24 +87,29 @@ static struct ftrace_ops ftrace_list_end __read_mostly = .func = ftrace_stub, }; -static struct ftrace_ops *ftrace_list __read_mostly = &ftrace_list_end; +static struct ftrace_ops *ftrace_global_list __read_mostly = &ftrace_list_end; +static struct ftrace_ops *ftrace_ops_list __read_mostly = &ftrace_list_end; ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub; ftrace_func_t __ftrace_trace_function __read_mostly = ftrace_stub; ftrace_func_t ftrace_pid_function __read_mostly = ftrace_stub; static struct ftrace_ops global_ops; +static void +ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip); + /* - * Traverse the ftrace_list, invoking all entries. The reason that we + * Traverse the ftrace_global_list, invoking all entries. The reason that we * can use rcu_dereference_raw() is that elements removed from this list * are simply leaked, so there is no need to interact with a grace-period * mechanism. The rcu_dereference_raw() calls are needed to handle - * concurrent insertions into the ftrace_list. + * concurrent insertions into the ftrace_global_list. * * Silly Alpha and silly pointer-speculation compiler optimizations! */ -static void ftrace_list_func(unsigned long ip, unsigned long parent_ip) +static void ftrace_global_list_func(unsigned long ip, + unsigned long parent_ip) { - struct ftrace_ops *op = rcu_dereference_raw(ftrace_list); /*see above*/ + struct ftrace_ops *op = rcu_dereference_raw(ftrace_global_list); /*see above*/ while (op != &ftrace_list_end) { op->func(ip, parent_ip); @@ -163,11 +168,11 @@ static void update_global_ops(void) * function directly. Otherwise, we need to iterate over the * registered callers. */ - if (ftrace_list == &ftrace_list_end || - ftrace_list->next == &ftrace_list_end) - func = ftrace_list->func; + if (ftrace_global_list == &ftrace_list_end || + ftrace_global_list->next == &ftrace_list_end) + func = ftrace_global_list->func; else - func = ftrace_list_func; + func = ftrace_global_list_func; /* If we filter on pids, update to use the pid function */ if (!list_empty(&ftrace_pids)) { @@ -184,7 +189,11 @@ static void update_ftrace_function(void) update_global_ops(); - func = global_ops.func; + if (ftrace_ops_list == &ftrace_list_end || + ftrace_ops_list->next == &ftrace_list_end) + func = ftrace_ops_list->func; + else + func = ftrace_ops_list_func; #ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST ftrace_trace_function = func; @@ -198,10 +207,10 @@ static void add_ftrace_ops(struct ftrace_ops **list, struct ftrace_ops *ops) { ops->next = *list; /* - * We are entering ops into the ftrace_list but another + * We are entering ops into the list but another * CPU might be walking that list. We need to make sure * the ops->next pointer is valid before another CPU sees - * the ops pointer included into the ftrace_list. + * the ops pointer included into the list. */ rcu_assign_pointer(*list, ops); } @@ -238,7 +247,18 @@ static int __register_ftrace_function(struct ftrace_ops *ops) if (FTRACE_WARN_ON(ops == &global_ops)) return -EINVAL; - add_ftrace_ops(&ftrace_list, ops); + if (WARN_ON(ops->flags & FTRACE_OPS_FL_ENABLED)) + return -EBUSY; + + if (ops->flags & FTRACE_OPS_FL_GLOBAL) { + int first = ftrace_global_list == &ftrace_list_end; + add_ftrace_ops(&ftrace_global_list, ops); + ops->flags |= FTRACE_OPS_FL_ENABLED; + if (first) + add_ftrace_ops(&ftrace_ops_list, &global_ops); + } else + add_ftrace_ops(&ftrace_ops_list, ops); + if (ftrace_enabled) update_ftrace_function(); @@ -252,12 +272,24 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops) if (ftrace_disabled) return -ENODEV; + if (WARN_ON(!(ops->flags & FTRACE_OPS_FL_ENABLED))) + return -EBUSY; + if (FTRACE_WARN_ON(ops == &global_ops)) return -EINVAL; - ret = remove_ftrace_ops(&ftrace_list, ops); + if (ops->flags & FTRACE_OPS_FL_GLOBAL) { + ret = remove_ftrace_ops(&ftrace_global_list, ops); + if (!ret && ftrace_global_list == &ftrace_list_end) + ret = remove_ftrace_ops(&ftrace_ops_list, &global_ops); + if (!ret) + ops->flags &= ~FTRACE_OPS_FL_ENABLED; + } else + ret = remove_ftrace_ops(&ftrace_ops_list, ops); + if (ret < 0) return ret; + if (ftrace_enabled) update_ftrace_function(); @@ -928,10 +960,6 @@ static const struct ftrace_hash empty_hash = { }; #define EMPTY_HASH ((struct ftrace_hash *)&empty_hash) -enum { - FTRACE_OPS_FL_ENABLED = 1, -}; - static struct ftrace_ops global_ops = { .func = ftrace_stub, .notrace_hash = EMPTY_HASH, @@ -1189,6 +1217,40 @@ ftrace_hash_move(struct ftrace_hash **dst, struct ftrace_hash *src) return 0; } +/* + * Test the hashes for this ops to see if we want to call + * the ops->func or not. + * + * It's a match if the ip is in the ops->filter_hash or + * the filter_hash does not exist or is empty, + * AND + * the ip is not in the ops->notrace_hash. + */ +static int +ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip) +{ + struct ftrace_hash *filter_hash; + struct ftrace_hash *notrace_hash; + int ret; + + /* The hashes are freed with call_rcu_sched() */ + preempt_disable_notrace(); + + filter_hash = rcu_dereference_raw(ops->filter_hash); + notrace_hash = rcu_dereference_raw(ops->notrace_hash); + + if ((!filter_hash || !filter_hash->count || + ftrace_lookup_ip(filter_hash, ip)) && + (!notrace_hash || !notrace_hash->count || + !ftrace_lookup_ip(notrace_hash, ip))) + ret = 1; + else + ret = 0; + preempt_enable_notrace(); + + return ret; +} + /* * This is a double for. Do not use 'break' to break out of the loop, * you must use a goto. @@ -1232,7 +1294,7 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops, if (filter_hash) { hash = ops->filter_hash; other_hash = ops->notrace_hash; - if (!hash->count) + if (!hash || !hash->count) all = 1; } else { inc = !inc; @@ -1242,7 +1304,7 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops, * If the notrace hash has no items, * then there's nothing to do. */ - if (!hash->count) + if (hash && !hash->count) return; } @@ -1256,11 +1318,11 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops, * Only the filter_hash affects all records. * Update if the record is not in the notrace hash. */ - if (!ftrace_lookup_ip(other_hash, rec->ip)) + if (!other_hash || !ftrace_lookup_ip(other_hash, rec->ip)) match = 1; } else { - in_hash = !!ftrace_lookup_ip(hash, rec->ip); - in_other_hash = !!ftrace_lookup_ip(other_hash, rec->ip); + in_hash = hash && !!ftrace_lookup_ip(hash, rec->ip); + in_other_hash = other_hash && !!ftrace_lookup_ip(other_hash, rec->ip); /* * @@ -1546,6 +1608,7 @@ static void ftrace_run_update_code(int command) static ftrace_func_t saved_ftrace_func; static int ftrace_start_up; +static int global_start_up; static void ftrace_startup_enable(int command) { @@ -1562,14 +1625,25 @@ static void ftrace_startup_enable(int command) static void ftrace_startup(struct ftrace_ops *ops, int command) { + bool hash_enable = true; + if (unlikely(ftrace_disabled)) return; ftrace_start_up++; command |= FTRACE_ENABLE_CALLS; + /* ops marked global share the filter hashes */ + if (ops->flags & FTRACE_OPS_FL_GLOBAL) { + ops = &global_ops; + /* Don't update hash if global is already set */ + if (global_start_up) + hash_enable = false; + global_start_up++; + } + ops->flags |= FTRACE_OPS_FL_ENABLED; - if (ftrace_start_up == 1) + if (hash_enable) ftrace_hash_rec_enable(ops, 1); ftrace_startup_enable(command); @@ -1577,6 +1651,8 @@ static void ftrace_startup(struct ftrace_ops *ops, int command) static void ftrace_shutdown(struct ftrace_ops *ops, int command) { + bool hash_disable = true; + if (unlikely(ftrace_disabled)) return; @@ -1588,13 +1664,25 @@ static void ftrace_shutdown(struct ftrace_ops *ops, int command) */ WARN_ON_ONCE(ftrace_start_up < 0); - if (!ftrace_start_up) + if (ops->flags & FTRACE_OPS_FL_GLOBAL) { + ops = &global_ops; + global_start_up--; + WARN_ON_ONCE(global_start_up < 0); + /* Don't update hash if global still has users */ + if (global_start_up) { + WARN_ON_ONCE(!ftrace_start_up); + hash_disable = false; + } + } + + if (hash_disable) ftrace_hash_rec_disable(ops, 1); - if (!ftrace_start_up) { - command |= FTRACE_DISABLE_CALLS; + if (ops != &global_ops || !global_start_up) ops->flags &= ~FTRACE_OPS_FL_ENABLED; - } + + if (!ftrace_start_up) + command |= FTRACE_DISABLE_CALLS; if (saved_ftrace_func != ftrace_trace_function) { saved_ftrace_func = ftrace_trace_function; @@ -2381,6 +2469,7 @@ static int ftrace_probe_registered; static void __enable_ftrace_function_probe(void) { + int ret; int i; if (ftrace_probe_registered) @@ -2395,13 +2484,16 @@ static void __enable_ftrace_function_probe(void) if (i == FTRACE_FUNC_HASHSIZE) return; - __register_ftrace_function(&trace_probe_ops); - ftrace_startup(&global_ops, 0); + ret = __register_ftrace_function(&trace_probe_ops); + if (!ret) + ftrace_startup(&trace_probe_ops, 0); + ftrace_probe_registered = 1; } static void __disable_ftrace_function_probe(void) { + int ret; int i; if (!ftrace_probe_registered) @@ -2414,8 +2506,10 @@ static void __disable_ftrace_function_probe(void) } /* no more funcs left */ - __unregister_ftrace_function(&trace_probe_ops); - ftrace_shutdown(&global_ops, 0); + ret = __unregister_ftrace_function(&trace_probe_ops); + if (!ret) + ftrace_shutdown(&trace_probe_ops, 0); + ftrace_probe_registered = 0; } @@ -3319,8 +3413,28 @@ static inline void ftrace_startup_enable(int command) { } # define ftrace_shutdown(ops, command) do { } while (0) # define ftrace_startup_sysctl() do { } while (0) # define ftrace_shutdown_sysctl() do { } while (0) + +static inline int +ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip) +{ + return 1; +} + #endif /* CONFIG_DYNAMIC_FTRACE */ +static void +ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip) +{ + /* see comment above ftrace_global_list_func */ + struct ftrace_ops *op = rcu_dereference_raw(ftrace_ops_list); + + while (op != &ftrace_list_end) { + if (ftrace_ops_test(op, ip)) + op->func(ip, parent_ip); + op = rcu_dereference_raw(op->next); + }; +} + static void clear_ftrace_swapper(void) { struct task_struct *p; @@ -3621,7 +3735,9 @@ int register_ftrace_function(struct ftrace_ops *ops) goto out_unlock; ret = __register_ftrace_function(ops); - ftrace_startup(&global_ops, 0); + if (!ret) + ftrace_startup(ops, 0); + out_unlock: mutex_unlock(&ftrace_lock); @@ -3640,7 +3756,8 @@ int unregister_ftrace_function(struct ftrace_ops *ops) mutex_lock(&ftrace_lock); ret = __unregister_ftrace_function(ops); - ftrace_shutdown(&global_ops, 0); + if (!ret) + ftrace_shutdown(ops, 0); mutex_unlock(&ftrace_lock); return ret; @@ -3670,11 +3787,11 @@ ftrace_enable_sysctl(struct ctl_table *table, int write, ftrace_startup_sysctl(); /* we are starting ftrace again */ - if (ftrace_list != &ftrace_list_end) { - if (ftrace_list->next == &ftrace_list_end) - ftrace_trace_function = ftrace_list->func; + if (ftrace_ops_list != &ftrace_list_end) { + if (ftrace_ops_list->next == &ftrace_list_end) + ftrace_trace_function = ftrace_ops_list->func; else - ftrace_trace_function = ftrace_list_func; + ftrace_trace_function = ftrace_ops_list_func; } } else { diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index 16aee4d44e8..8d0e1cc4e97 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -149,11 +149,13 @@ function_stack_trace_call(unsigned long ip, unsigned long parent_ip) static struct ftrace_ops trace_ops __read_mostly = { .func = function_trace_call, + .flags = FTRACE_OPS_FL_GLOBAL, }; static struct ftrace_ops trace_stack_ops __read_mostly = { .func = function_stack_trace_call, + .flags = FTRACE_OPS_FL_GLOBAL, }; /* Our two options */ diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index a4969b47afc..c77424be284 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -153,6 +153,7 @@ irqsoff_tracer_call(unsigned long ip, unsigned long parent_ip) static struct ftrace_ops trace_ops __read_mostly = { .func = irqsoff_tracer_call, + .flags = FTRACE_OPS_FL_GLOBAL, }; #endif /* CONFIG_FUNCTION_TRACER */ diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index 7319559ed59..f029dd4fd2c 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -129,6 +129,7 @@ wakeup_tracer_call(unsigned long ip, unsigned long parent_ip) static struct ftrace_ops trace_ops __read_mostly = { .func = wakeup_tracer_call, + .flags = FTRACE_OPS_FL_GLOBAL, }; #endif /* CONFIG_FUNCTION_TRACER */ diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index 4c5dead0c23..b0b53b8e4c2 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -133,6 +133,7 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip) static struct ftrace_ops trace_ops __read_mostly = { .func = stack_trace_call, + .flags = FTRACE_OPS_FL_GLOBAL, }; static ssize_t -- cgit v1.2.3-70-g09d2 From cdbe61bfe70440939e457fb4a8d0995eaaed17de Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 5 May 2011 21:14:55 -0400 Subject: ftrace: Allow dynamically allocated function tracers Now that functions may be selected individually, it only makes sense that we should allow dynamically allocated trace structures to be traced. This will allow perf to allocate a ftrace_ops structure at runtime and use it to pick and choose which functions that structure will trace. Note, a dynamically allocated ftrace_ops will always be called indirectly instead of being called directly from the mcount in entry.S. This is because there's no safe way to prevent mcount from being preempted before calling the function, unless we modify every entry.S to do so (not likely). Thus, dynamically allocated functions will now be called by the ftrace_ops_list_func() that loops through the ops that are allocated if there are more than one op allocated at a time. This loop is protected with a preempt_disable. To determine if an ftrace_ops structure is allocated or not, a new util function was added to the kernel/extable.c called core_kernel_data(), which returns 1 if the address is between _sdata and _edata. Cc: Paul E. McKenney Signed-off-by: Steven Rostedt --- include/linux/ftrace.h | 1 + include/linux/kernel.h | 1 + kernel/extable.c | 8 ++++++++ kernel/trace/ftrace.c | 37 ++++++++++++++++++++++++++++++------- 4 files changed, 40 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 4609c0ece79..caba694a62b 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -34,6 +34,7 @@ struct ftrace_hash; enum { FTRACE_OPS_FL_ENABLED = 1 << 0, FTRACE_OPS_FL_GLOBAL = 1 << 1, + FTRACE_OPS_FL_DYNAMIC = 1 << 2, }; struct ftrace_ops { diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 00cec4dc0ae..f37ba716ef8 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -283,6 +283,7 @@ extern char *get_options(const char *str, int nints, int *ints); extern unsigned long long memparse(const char *ptr, char **retptr); extern int core_kernel_text(unsigned long addr); +extern int core_kernel_data(unsigned long addr); extern int __kernel_text_address(unsigned long addr); extern int kernel_text_address(unsigned long addr); extern int func_ptr_is_kernel_text(void *ptr); diff --git a/kernel/extable.c b/kernel/extable.c index 7f8f263f852..c2d625fcda7 100644 --- a/kernel/extable.c +++ b/kernel/extable.c @@ -72,6 +72,14 @@ int core_kernel_text(unsigned long addr) return 0; } +int core_kernel_data(unsigned long addr) +{ + if (addr >= (unsigned long)_sdata && + addr < (unsigned long)_edata) + return 1; + return 0; +} + int __kernel_text_address(unsigned long addr) { if (core_kernel_text(addr)) diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 6c7e1df39b5..5b3ee04e39d 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -189,8 +189,14 @@ static void update_ftrace_function(void) update_global_ops(); + /* + * If we are at the end of the list and this ops is + * not dynamic, then have the mcount trampoline call + * the function directly + */ if (ftrace_ops_list == &ftrace_list_end || - ftrace_ops_list->next == &ftrace_list_end) + (ftrace_ops_list->next == &ftrace_list_end && + !(ftrace_ops_list->flags & FTRACE_OPS_FL_DYNAMIC))) func = ftrace_ops_list->func; else func = ftrace_ops_list_func; @@ -250,6 +256,9 @@ static int __register_ftrace_function(struct ftrace_ops *ops) if (WARN_ON(ops->flags & FTRACE_OPS_FL_ENABLED)) return -EBUSY; + if (!core_kernel_data((unsigned long)ops)) + ops->flags |= FTRACE_OPS_FL_DYNAMIC; + if (ops->flags & FTRACE_OPS_FL_GLOBAL) { int first = ftrace_global_list == &ftrace_list_end; add_ftrace_ops(&ftrace_global_list, ops); @@ -293,6 +302,13 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops) if (ftrace_enabled) update_ftrace_function(); + /* + * Dynamic ops may be freed, we must make sure that all + * callers are done before leaving this function. + */ + if (ops->flags & FTRACE_OPS_FL_DYNAMIC) + synchronize_sched(); + return 0; } @@ -1225,6 +1241,9 @@ ftrace_hash_move(struct ftrace_hash **dst, struct ftrace_hash *src) * the filter_hash does not exist or is empty, * AND * the ip is not in the ops->notrace_hash. + * + * This needs to be called with preemption disabled as + * the hashes are freed with call_rcu_sched(). */ static int ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip) @@ -1233,9 +1252,6 @@ ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip) struct ftrace_hash *notrace_hash; int ret; - /* The hashes are freed with call_rcu_sched() */ - preempt_disable_notrace(); - filter_hash = rcu_dereference_raw(ops->filter_hash); notrace_hash = rcu_dereference_raw(ops->notrace_hash); @@ -1246,7 +1262,6 @@ ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip) ret = 1; else ret = 0; - preempt_enable_notrace(); return ret; } @@ -3425,14 +3440,20 @@ ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip) static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip) { - /* see comment above ftrace_global_list_func */ - struct ftrace_ops *op = rcu_dereference_raw(ftrace_ops_list); + struct ftrace_ops *op; + /* + * Some of the ops may be dynamically allocated, + * they must be freed after a synchronize_sched(). + */ + preempt_disable_notrace(); + op = rcu_dereference_raw(ftrace_ops_list); while (op != &ftrace_list_end) { if (ftrace_ops_test(op, ip)) op->func(ip, parent_ip); op = rcu_dereference_raw(op->next); }; + preempt_enable_notrace(); } static void clear_ftrace_swapper(void) @@ -3743,6 +3764,7 @@ int register_ftrace_function(struct ftrace_ops *ops) mutex_unlock(&ftrace_lock); return ret; } +EXPORT_SYMBOL_GPL(register_ftrace_function); /** * unregister_ftrace_function - unregister a function for profiling. @@ -3762,6 +3784,7 @@ int unregister_ftrace_function(struct ftrace_ops *ops) return ret; } +EXPORT_SYMBOL_GPL(unregister_ftrace_function); int ftrace_enable_sysctl(struct ctl_table *table, int write, -- cgit v1.2.3-70-g09d2 From 936e074b286ae779f134312178dbab139ee7ea52 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 5 May 2011 22:54:01 -0400 Subject: ftrace: Modify ftrace_set_filter/notrace to take ops Since users of the function tracer can now pick and choose which functions they want to trace agnostically from other users of the function tracer, we need to pass the ops struct to the ftrace_set_filter() functions. The functions ftrace_set_global_filter() and ftrace_set_global_notrace() is added to keep the old filter functions which are used to modify the generic function tracers. Signed-off-by: Steven Rostedt --- include/linux/ftrace.h | 7 ++++++- kernel/trace/ftrace.c | 46 +++++++++++++++++++++++++++++++++++++++++-- kernel/trace/trace_selftest.c | 4 ++-- 3 files changed, 52 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index caba694a62b..9d88e1cb5db 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -179,7 +179,12 @@ struct dyn_ftrace { }; int ftrace_force_update(void); -void ftrace_set_filter(unsigned char *buf, int len, int reset); +void ftrace_set_filter(struct ftrace_ops *ops, unsigned char *buf, + int len, int reset); +void ftrace_set_notrace(struct ftrace_ops *ops, unsigned char *buf, + int len, int reset); +void ftrace_set_global_filter(unsigned char *buf, int len, int reset); +void ftrace_set_global_notrace(unsigned char *buf, int len, int reset); int register_ftrace_command(struct ftrace_func_command *cmd); int unregister_ftrace_command(struct ftrace_func_command *cmd); diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 5b3ee04e39d..d017c2c82c4 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -2826,6 +2826,10 @@ ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len, struct ftrace_hash *hash; int ret; + /* All global ops uses the global ops filters */ + if (ops->flags & FTRACE_OPS_FL_GLOBAL) + ops = &global_ops; + if (unlikely(ftrace_disabled)) return -ENODEV; @@ -2856,6 +2860,41 @@ ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len, /** * ftrace_set_filter - set a function to filter on in ftrace + * @ops - the ops to set the filter with + * @buf - the string that holds the function filter text. + * @len - the length of the string. + * @reset - non zero to reset all filters before applying this filter. + * + * Filters denote which functions should be enabled when tracing is enabled. + * If @buf is NULL and reset is set, all functions will be enabled for tracing. + */ +void ftrace_set_filter(struct ftrace_ops *ops, unsigned char *buf, + int len, int reset) +{ + ftrace_set_regex(ops, buf, len, reset, 1); +} +EXPORT_SYMBOL_GPL(ftrace_set_filter); + +/** + * ftrace_set_notrace - set a function to not trace in ftrace + * @ops - the ops to set the notrace filter with + * @buf - the string that holds the function notrace text. + * @len - the length of the string. + * @reset - non zero to reset all filters before applying this filter. + * + * Notrace Filters denote which functions should not be enabled when tracing + * is enabled. If @buf is NULL and reset is set, all functions will be enabled + * for tracing. + */ +void ftrace_set_notrace(struct ftrace_ops *ops, unsigned char *buf, + int len, int reset) +{ + ftrace_set_regex(ops, buf, len, reset, 0); +} +EXPORT_SYMBOL_GPL(ftrace_set_notrace); +/** + * ftrace_set_filter - set a function to filter on in ftrace + * @ops - the ops to set the filter with * @buf - the string that holds the function filter text. * @len - the length of the string. * @reset - non zero to reset all filters before applying this filter. @@ -2863,13 +2902,15 @@ ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len, * Filters denote which functions should be enabled when tracing is enabled. * If @buf is NULL and reset is set, all functions will be enabled for tracing. */ -void ftrace_set_filter(unsigned char *buf, int len, int reset) +void ftrace_set_global_filter(unsigned char *buf, int len, int reset) { ftrace_set_regex(&global_ops, buf, len, reset, 1); } +EXPORT_SYMBOL_GPL(ftrace_set_global_filter); /** * ftrace_set_notrace - set a function to not trace in ftrace + * @ops - the ops to set the notrace filter with * @buf - the string that holds the function notrace text. * @len - the length of the string. * @reset - non zero to reset all filters before applying this filter. @@ -2878,10 +2919,11 @@ void ftrace_set_filter(unsigned char *buf, int len, int reset) * is enabled. If @buf is NULL and reset is set, all functions will be enabled * for tracing. */ -void ftrace_set_notrace(unsigned char *buf, int len, int reset) +void ftrace_set_global_notrace(unsigned char *buf, int len, int reset) { ftrace_set_regex(&global_ops, buf, len, reset, 0); } +EXPORT_SYMBOL_GPL(ftrace_set_global_notrace); /* * command line interface to allow users to set filters on boot up. diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index 659732eba07..0fa2db305b7 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -131,7 +131,7 @@ int trace_selftest_startup_dynamic_tracing(struct tracer *trace, func_name = "*" __stringify(DYN_FTRACE_TEST_NAME); /* filter only on our function */ - ftrace_set_filter(func_name, strlen(func_name), 1); + ftrace_set_global_filter(func_name, strlen(func_name), 1); /* enable tracing */ ret = tracer_init(trace, tr); @@ -181,7 +181,7 @@ int trace_selftest_startup_dynamic_tracing(struct tracer *trace, tracer_enabled = save_tracer_enabled; /* Enable tracing on all functions again */ - ftrace_set_filter(NULL, 0, 1); + ftrace_set_global_filter(NULL, 0, 1); return ret; } -- cgit v1.2.3-70-g09d2 From b4bc842802db3314f9a657094da0450a903ea619 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Mon, 7 Feb 2011 16:02:25 -0800 Subject: module: deal with alignment issues in built-in module versions On m68k natural alignment is 2-byte boundary but we are trying to align structures in __modver section on sizeof(void *) boundary. This causes trouble when we try to access elements in this section in array-like fashion when create "version" attributes for built-in modules. Moreover, as DaveM said, we can't reliably put structures into independent objects, put them into a special section, and then expect array access over them (via the section boundaries) after linking the objects together to just "work" due to variable alignment choices in different situations. The only solution that seems to work reliably is to make an array of plain pointers to the objects in question and put those pointers in the special section. Reported-by: Geert Uytterhoeven Signed-off-by: Dmitry Torokhov Signed-off-by: Rusty Russell --- include/linux/module.h | 10 +++++----- kernel/params.c | 9 ++++++--- 2 files changed, 11 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/module.h b/include/linux/module.h index 5de42043dff..4cfebc21169 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -174,10 +174,7 @@ extern struct module __this_module; #define MODULE_VERSION(_version) \ extern ssize_t __modver_version_show(struct module_attribute *, \ struct module *, char *); \ - static struct module_version_attribute __modver_version_attr \ - __used \ - __attribute__ ((__section__ ("__modver"),aligned(sizeof(void *)))) \ - = { \ + static struct module_version_attribute ___modver_attr = { \ .mattr = { \ .attr = { \ .name = "version", \ @@ -187,7 +184,10 @@ extern struct module __this_module; }, \ .module_name = KBUILD_MODNAME, \ .version = _version, \ - } + }; \ + static const struct module_version_attribute \ + __used __attribute__ ((__section__ ("__modver"))) \ + * __moduleparam_const __modver_attr = &___modver_attr #endif /* Optional firmware file (or files) needed by the module diff --git a/kernel/params.c b/kernel/params.c index 7ab388a48a2..28c5d5c83f6 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -821,15 +821,18 @@ ssize_t __modver_version_show(struct module_attribute *mattr, return sprintf(buf, "%s\n", vattr->version); } -extern struct module_version_attribute __start___modver[], __stop___modver[]; +extern const struct module_version_attribute *__start___modver[]; +extern const struct module_version_attribute *__stop___modver[]; static void __init version_sysfs_builtin(void) { - const struct module_version_attribute *vattr; + const struct module_version_attribute **p; struct module_kobject *mk; int err; - for (vattr = __start___modver; vattr < __stop___modver; vattr++) { + for (p = __start___modver; p < __stop___modver; p++) { + const struct module_version_attribute *vattr = *p; + mk = locate_module_kobject(vattr->module_name); if (mk) { err = sysfs_create_file(&mk->kobj, &vattr->mattr.attr); -- cgit v1.2.3-70-g09d2 From 9b73a5840c7d5f77e5766626716df13787cb258c Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Mon, 7 Feb 2011 16:02:27 -0800 Subject: module: do not hide __modver_version_show declaration behind ifdef Doing so prevents the following warning from sparse: CHECK kernel/params.c kernel/params.c:817:9: warning: symbol '__modver_version_show' was not declared. Should it be static? since kernel/params.c is never compiled with MODULE being set. Signed-off-by: Dmitry Torokhov Signed-off-by: Rusty Russell --- include/linux/module.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/module.h b/include/linux/module.h index 4cfebc21169..23996ad147e 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -64,6 +64,9 @@ struct module_version_attribute { const char *version; } __attribute__ ((__aligned__(sizeof(void *)))); +extern ssize_t __modver_version_show(struct module_attribute *, + struct module *, char *); + struct module_kobject { struct kobject kobj; @@ -172,8 +175,6 @@ extern struct module __this_module; #define MODULE_VERSION(_version) MODULE_INFO(version, _version) #else #define MODULE_VERSION(_version) \ - extern ssize_t __modver_version_show(struct module_attribute *, \ - struct module *, char *); \ static struct module_version_attribute ___modver_attr = { \ .mattr = { \ .attr = { \ -- cgit v1.2.3-70-g09d2 From a288bd651f4180c224cfddf837a0416157a36661 Mon Sep 17 00:00:00 2001 From: Richard Kennedy Date: Thu, 19 May 2011 16:55:25 -0600 Subject: module: remove 64 bit alignment padding from struct module with CONFIG_TRACE* Reorder struct module to remove 24 bytes of alignment padding on 64 bit builds when the CONFIG_TRACE options are selected. This allows the structure to fit into one fewer cache lines, and its size drops from 592 to 568 on x86_64. Signed-off-by: Richard Kennedy Signed-off-by: Rusty Russell --- include/linux/module.h | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/module.h b/include/linux/module.h index 23996ad147e..65cc6cc73ca 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -368,34 +368,35 @@ struct module struct module_notes_attrs *notes_attrs; #endif + /* The command line arguments (may be mangled). People like + keeping pointers to this stuff */ + char *args; + #ifdef CONFIG_SMP /* Per-cpu data. */ void __percpu *percpu; unsigned int percpu_size; #endif - /* The command line arguments (may be mangled). People like - keeping pointers to this stuff */ - char *args; #ifdef CONFIG_TRACEPOINTS - struct tracepoint * const *tracepoints_ptrs; unsigned int num_tracepoints; + struct tracepoint * const *tracepoints_ptrs; #endif #ifdef HAVE_JUMP_LABEL struct jump_entry *jump_entries; unsigned int num_jump_entries; #endif #ifdef CONFIG_TRACING - const char **trace_bprintk_fmt_start; unsigned int num_trace_bprintk_fmt; + const char **trace_bprintk_fmt_start; #endif #ifdef CONFIG_EVENT_TRACING struct ftrace_event_call **trace_events; unsigned int num_trace_events; #endif #ifdef CONFIG_FTRACE_MCOUNT_RECORD - unsigned long *ftrace_callsites; unsigned int num_ftrace_callsites; + unsigned long *ftrace_callsites; #endif #ifdef CONFIG_MODULE_UNLOAD -- cgit v1.2.3-70-g09d2 From c5be0b2eb1ca05e0cd747f9c0ba552c6ee8827a0 Mon Sep 17 00:00:00 2001 From: Richard Kennedy Date: Thu, 19 May 2011 16:55:25 -0600 Subject: module: reorder kparam_array to remove alignment padding on 64 bit builds Reorder structure kparam_array to remove 8 bytes of alignment padding on 64 bit builds, dropping its size from 40 to 32 bytes. Also update the macro module_param_array_named to initialise the structure using its member names to allow it to be changed without touching all its call sites. 'git grep' finds module_param_array in 1037 places so this patch will save a small amount of data space across many modules. Signed-off-by: Richard Kennedy Signed-off-by: Rusty Russell --- include/linux/moduleparam.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h index 07b41951e3f..ddaae98c53f 100644 --- a/include/linux/moduleparam.h +++ b/include/linux/moduleparam.h @@ -67,9 +67,9 @@ struct kparam_string { struct kparam_array { unsigned int max; + unsigned int elemsize; unsigned int *num; const struct kernel_param_ops *ops; - unsigned int elemsize; void *elem; }; @@ -371,8 +371,9 @@ extern int param_get_invbool(char *buffer, const struct kernel_param *kp); */ #define module_param_array_named(name, array, type, nump, perm) \ static const struct kparam_array __param_arr_##name \ - = { ARRAY_SIZE(array), nump, ¶m_ops_##type, \ - sizeof(array[0]), array }; \ + = { .max = ARRAY_SIZE(array), .num = nump, \ + .ops = ¶m_ops_##type, \ + .elemsize = sizeof(array[0]), .elem = array }; \ __module_param_call(MODULE_PARAM_PREFIX, name, \ ¶m_array_ops, \ .arr = &__param_arr_##name, \ -- cgit v1.2.3-70-g09d2 From de4d8d53465483168d6a627d409ee2d09d8e3308 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Tue, 19 Apr 2011 21:49:58 +0200 Subject: module: each_symbol_section instead of each_symbol Instead of having a callback function for each symbol in the kernel, have a callback for each array of symbols. This eases the logic when we move to sorted symbols and binary search. Signed-off-by: Rusty Russell Signed-off-by: Alessio Igor Bogani --- include/linux/module.h | 5 +++-- kernel/module.c | 42 +++++++++++++++++++++++++++--------------- 2 files changed, 30 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/include/linux/module.h b/include/linux/module.h index 65cc6cc73ca..49f4ad0ddec 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -477,8 +477,9 @@ const struct kernel_symbol *find_symbol(const char *name, bool warn); /* Walk the exported symbol table */ -bool each_symbol(bool (*fn)(const struct symsearch *arr, struct module *owner, - unsigned int symnum, void *data), void *data); +bool each_symbol_section(bool (*fn)(const struct symsearch *arr, + struct module *owner, + void *data), void *data); /* Returns 0 and fills in value, defined and namebuf, or -ERANGE if symnum out of range. */ diff --git a/kernel/module.c b/kernel/module.c index 0e6f97f43c8..e8aa462301e 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -240,23 +240,24 @@ static bool each_symbol_in_section(const struct symsearch *arr, struct module *owner, bool (*fn)(const struct symsearch *syms, struct module *owner, - unsigned int symnum, void *data), + void *data), void *data) { - unsigned int i, j; + unsigned int j; for (j = 0; j < arrsize; j++) { - for (i = 0; i < arr[j].stop - arr[j].start; i++) - if (fn(&arr[j], owner, i, data)) - return true; + if (fn(&arr[j], owner, data)) + return true; } return false; } /* Returns true as soon as fn returns true, otherwise false. */ -bool each_symbol(bool (*fn)(const struct symsearch *arr, struct module *owner, - unsigned int symnum, void *data), void *data) +bool each_symbol_section(bool (*fn)(const struct symsearch *arr, + struct module *owner, + void *data), + void *data) { struct module *mod; static const struct symsearch arr[] = { @@ -309,7 +310,7 @@ bool each_symbol(bool (*fn)(const struct symsearch *arr, struct module *owner, } return false; } -EXPORT_SYMBOL_GPL(each_symbol); +EXPORT_SYMBOL_GPL(each_symbol_section); struct find_symbol_arg { /* Input */ @@ -323,15 +324,12 @@ struct find_symbol_arg { const struct kernel_symbol *sym; }; -static bool find_symbol_in_section(const struct symsearch *syms, - struct module *owner, - unsigned int symnum, void *data) +static bool check_symbol(const struct symsearch *syms, + struct module *owner, + unsigned int symnum, void *data) { struct find_symbol_arg *fsa = data; - if (strcmp(syms->start[symnum].name, fsa->name) != 0) - return false; - if (!fsa->gplok) { if (syms->licence == GPL_ONLY) return false; @@ -365,6 +363,20 @@ static bool find_symbol_in_section(const struct symsearch *syms, return true; } +static bool find_symbol_in_section(const struct symsearch *syms, + struct module *owner, + void *data) +{ + struct find_symbol_arg *fsa = data; + unsigned int i; + + for (i = 0; i < syms->stop - syms->start; i++) { + if (strcmp(syms->start[i].name, fsa->name) == 0) + return check_symbol(syms, owner, i, data); + } + return false; +} + /* Find a symbol and return it, along with, (optional) crc and * (optional) module which owns it. Needs preempt disabled or module_mutex. */ const struct kernel_symbol *find_symbol(const char *name, @@ -379,7 +391,7 @@ const struct kernel_symbol *find_symbol(const char *name, fsa.gplok = gplok; fsa.warn = warn; - if (each_symbol(find_symbol_in_section, &fsa)) { + if (each_symbol_section(find_symbol_in_section, &fsa)) { if (owner) *owner = fsa.owner; if (crc) -- cgit v1.2.3-70-g09d2 From f02e8a6596b7dc9b2171f7ff5654039ef0950cdc Mon Sep 17 00:00:00 2001 From: Alessio Igor Bogani Date: Thu, 14 Apr 2011 14:59:39 +0200 Subject: module: Sort exported symbols This patch places every exported symbol in its own section (i.e. "___ksymtab+printk"). Thus the linker will use its SORT() directive to sort and finally merge all symbol in the right and final section (i.e. "__ksymtab"). The symbol prefixed archs use an underscore as prefix for symbols. To avoid collision we use a different character to create the temporary section names. This work was supported by a hardware donation from the CE Linux Forum. Signed-off-by: Alessio Igor Bogani Signed-off-by: Rusty Russell (folded in '+' fixup) Tested-by: Dirk Behme --- include/asm-generic/vmlinux.lds.h | 20 ++++++++++---------- include/linux/module.h | 4 ++-- scripts/module-common.lds | 11 +++++++++++ 3 files changed, 23 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index bd297a20ab9..b27445e00b6 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -274,70 +274,70 @@ /* Kernel symbol table: Normal symbols */ \ __ksymtab : AT(ADDR(__ksymtab) - LOAD_OFFSET) { \ VMLINUX_SYMBOL(__start___ksymtab) = .; \ - *(__ksymtab) \ + *(SORT(___ksymtab+*)) \ VMLINUX_SYMBOL(__stop___ksymtab) = .; \ } \ \ /* Kernel symbol table: GPL-only symbols */ \ __ksymtab_gpl : AT(ADDR(__ksymtab_gpl) - LOAD_OFFSET) { \ VMLINUX_SYMBOL(__start___ksymtab_gpl) = .; \ - *(__ksymtab_gpl) \ + *(SORT(___ksymtab_gpl+*)) \ VMLINUX_SYMBOL(__stop___ksymtab_gpl) = .; \ } \ \ /* Kernel symbol table: Normal unused symbols */ \ __ksymtab_unused : AT(ADDR(__ksymtab_unused) - LOAD_OFFSET) { \ VMLINUX_SYMBOL(__start___ksymtab_unused) = .; \ - *(__ksymtab_unused) \ + *(SORT(___ksymtab_unused+*)) \ VMLINUX_SYMBOL(__stop___ksymtab_unused) = .; \ } \ \ /* Kernel symbol table: GPL-only unused symbols */ \ __ksymtab_unused_gpl : AT(ADDR(__ksymtab_unused_gpl) - LOAD_OFFSET) { \ VMLINUX_SYMBOL(__start___ksymtab_unused_gpl) = .; \ - *(__ksymtab_unused_gpl) \ + *(SORT(___ksymtab_unused_gpl+*)) \ VMLINUX_SYMBOL(__stop___ksymtab_unused_gpl) = .; \ } \ \ /* Kernel symbol table: GPL-future-only symbols */ \ __ksymtab_gpl_future : AT(ADDR(__ksymtab_gpl_future) - LOAD_OFFSET) { \ VMLINUX_SYMBOL(__start___ksymtab_gpl_future) = .; \ - *(__ksymtab_gpl_future) \ + *(SORT(___ksymtab_gpl_future+*)) \ VMLINUX_SYMBOL(__stop___ksymtab_gpl_future) = .; \ } \ \ /* Kernel symbol table: Normal symbols */ \ __kcrctab : AT(ADDR(__kcrctab) - LOAD_OFFSET) { \ VMLINUX_SYMBOL(__start___kcrctab) = .; \ - *(__kcrctab) \ + *(SORT(___kcrctab+*)) \ VMLINUX_SYMBOL(__stop___kcrctab) = .; \ } \ \ /* Kernel symbol table: GPL-only symbols */ \ __kcrctab_gpl : AT(ADDR(__kcrctab_gpl) - LOAD_OFFSET) { \ VMLINUX_SYMBOL(__start___kcrctab_gpl) = .; \ - *(__kcrctab_gpl) \ + *(SORT(___kcrctab_gpl+*)) \ VMLINUX_SYMBOL(__stop___kcrctab_gpl) = .; \ } \ \ /* Kernel symbol table: Normal unused symbols */ \ __kcrctab_unused : AT(ADDR(__kcrctab_unused) - LOAD_OFFSET) { \ VMLINUX_SYMBOL(__start___kcrctab_unused) = .; \ - *(__kcrctab_unused) \ + *(SORT(___kcrctab_unused+*)) \ VMLINUX_SYMBOL(__stop___kcrctab_unused) = .; \ } \ \ /* Kernel symbol table: GPL-only unused symbols */ \ __kcrctab_unused_gpl : AT(ADDR(__kcrctab_unused_gpl) - LOAD_OFFSET) { \ VMLINUX_SYMBOL(__start___kcrctab_unused_gpl) = .; \ - *(__kcrctab_unused_gpl) \ + *(SORT(___kcrctab_unused_gpl+*)) \ VMLINUX_SYMBOL(__stop___kcrctab_unused_gpl) = .; \ } \ \ /* Kernel symbol table: GPL-future-only symbols */ \ __kcrctab_gpl_future : AT(ADDR(__kcrctab_gpl_future) - LOAD_OFFSET) { \ VMLINUX_SYMBOL(__start___kcrctab_gpl_future) = .; \ - *(__kcrctab_gpl_future) \ + *(SORT(___kcrctab_gpl_future+*)) \ VMLINUX_SYMBOL(__stop___kcrctab_gpl_future) = .; \ } \ \ diff --git a/include/linux/module.h b/include/linux/module.h index 49f4ad0ddec..d9ca2d5dc6d 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -224,7 +224,7 @@ struct module_use { extern void *__crc_##sym __attribute__((weak)); \ static const unsigned long __kcrctab_##sym \ __used \ - __attribute__((section("__kcrctab" sec), unused)) \ + __attribute__((section("___kcrctab" sec "+" #sym), unused)) \ = (unsigned long) &__crc_##sym; #else #define __CRC_SYMBOL(sym, sec) @@ -239,7 +239,7 @@ struct module_use { = MODULE_SYMBOL_PREFIX #sym; \ static const struct kernel_symbol __ksymtab_##sym \ __used \ - __attribute__((section("__ksymtab" sec), unused)) \ + __attribute__((section("___ksymtab" sec "+" #sym), unused)) \ = { (unsigned long)&sym, __kstrtab_##sym } #define EXPORT_SYMBOL(sym) \ diff --git a/scripts/module-common.lds b/scripts/module-common.lds index 47a1f9ae0ed..0865b3e752b 100644 --- a/scripts/module-common.lds +++ b/scripts/module-common.lds @@ -5,4 +5,15 @@ */ SECTIONS { /DISCARD/ : { *(.discard) } + + __ksymtab : { *(SORT(___ksymtab+*)) } + __ksymtab_gpl : { *(SORT(___ksymtab_gpl+*)) } + __ksymtab_unused : { *(SORT(___ksymtab_unused+*)) } + __ksymtab_unused_gpl : { *(SORT(___ksymtab_unused_gpl+*)) } + __ksymtab_gpl_future : { *(SORT(___ksymtab_gpl_future+*)) } + __kcrctab : { *(SORT(___kcrctab+*)) } + __kcrctab_gpl : { *(SORT(___kcrctab_gpl+*)) } + __kcrctab_unused : { *(SORT(___kcrctab_unused+*)) } + __kcrctab_unused_gpl : { *(SORT(___kcrctab_unused_gpl+*)) } + __kcrctab_gpl_future : { *(SORT(___kcrctab_gpl_future+*)) } } -- cgit v1.2.3-70-g09d2 From 1a94dc35bc5c166d89913dc01a49d27a3c21a455 Mon Sep 17 00:00:00 2001 From: Tim Abbott Date: Thu, 14 Apr 2011 20:00:19 +0200 Subject: lib: Add generic binary search function to the kernel. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There a large number hand-coded binary searches in the kernel (run "git grep search | grep binary" to find many of them). Since in my experience, hand-coding binary searches can be error-prone, it seems worth cleaning this up by providing a generic binary search function. This generic binary search implementation comes from Ksplice. It has the same basic API as the C library bsearch() function. Ksplice uses it in half a dozen places with 4 different comparison functions, and I think our code is substantially cleaner because of this. Signed-off-by: Tim Abbott Extra-bikeshedding-by: Alan Jenkins Extra-bikeshedding-by: AndrĂ© Goddard Rosa Extra-bikeshedding-by: Rusty Russell Signed-off-by: Rusty Russell Signed-off-by: Alessio Igor Bogani Signed-off-by: Rusty Russell --- include/linux/bsearch.h | 9 +++++++++ lib/Makefile | 3 ++- lib/bsearch.c | 53 +++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 64 insertions(+), 1 deletion(-) create mode 100644 include/linux/bsearch.h create mode 100644 lib/bsearch.c (limited to 'include') diff --git a/include/linux/bsearch.h b/include/linux/bsearch.h new file mode 100644 index 00000000000..90b1aa86722 --- /dev/null +++ b/include/linux/bsearch.h @@ -0,0 +1,9 @@ +#ifndef _LINUX_BSEARCH_H +#define _LINUX_BSEARCH_H + +#include + +void *bsearch(const void *key, const void *base, size_t num, size_t size, + int (*cmp)(const void *key, const void *elt)); + +#endif /* _LINUX_BSEARCH_H */ diff --git a/lib/Makefile b/lib/Makefile index ef0f2857115..4b49a249064 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -21,7 +21,8 @@ lib-y += kobject.o kref.o klist.o obj-y += bcd.o div64.o sort.o parser.o halfmd4.o debug_locks.o random32.o \ bust_spinlocks.o hexdump.o kasprintf.o bitmap.o scatterlist.o \ - string_helpers.o gcd.o lcm.o list_sort.o uuid.o flex_array.o + string_helpers.o gcd.o lcm.o list_sort.o uuid.o flex_array.o \ + bsearch.o obj-y += kstrtox.o obj-$(CONFIG_TEST_KSTRTOX) += test-kstrtox.o diff --git a/lib/bsearch.c b/lib/bsearch.c new file mode 100644 index 00000000000..5b54758e2af --- /dev/null +++ b/lib/bsearch.c @@ -0,0 +1,53 @@ +/* + * A generic implementation of binary search for the Linux kernel + * + * Copyright (C) 2008-2009 Ksplice, Inc. + * Author: Tim Abbott + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation; version 2. + */ + +#include +#include + +/* + * bsearch - binary search an array of elements + * @key: pointer to item being searched for + * @base: pointer to first element to search + * @num: number of elements + * @size: size of each element + * @cmp: pointer to comparison function + * + * This function does a binary search on the given array. The + * contents of the array should already be in ascending sorted order + * under the provided comparison function. + * + * Note that the key need not have the same type as the elements in + * the array, e.g. key could be a string and the comparison function + * could compare the string with the struct's name field. However, if + * the key and elements in the array are of the same type, you can use + * the same comparison function for both sort() and bsearch(). + */ +void *bsearch(const void *key, const void *base, size_t num, size_t size, + int (*cmp)(const void *key, const void *elt)) +{ + size_t start = 0, end = num; + int result; + + while (start < end) { + size_t mid = start + (end - start) / 2; + + result = cmp(key, base + mid * size); + if (result < 0) + end = mid; + else if (result > 0) + start = mid + 1; + else + return (void *)base + mid * size; + } + + return NULL; +} +EXPORT_SYMBOL(bsearch); -- cgit v1.2.3-70-g09d2 From d0f1fed29e6e73d9d17f4c91a5896a4ce3938d45 Mon Sep 17 00:00:00 2001 From: Jonathan Cameron Date: Tue, 19 Apr 2011 12:43:45 +0100 Subject: Add a strtobool function matching semantics of existing in kernel equivalents This is a rename of the usr_strtobool proposal, which was a renamed, relocated and fixed version of previous kstrtobool RFC Signed-off-by: Jonathan Cameron Signed-off-by: Rusty Russell --- include/linux/string.h | 1 + lib/string.c | 29 +++++++++++++++++++++++++++++ 2 files changed, 30 insertions(+) (limited to 'include') diff --git a/include/linux/string.h b/include/linux/string.h index a716ee2a8ad..a176db2f2c8 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -123,6 +123,7 @@ extern char **argv_split(gfp_t gfp, const char *str, int *argcp); extern void argv_free(char **argv); extern bool sysfs_streq(const char *s1, const char *s2); +extern int strtobool(const char *s, bool *res); #ifdef CONFIG_BINARY_PRINTF int vbin_printf(u32 *bin_buf, size_t size, const char *fmt, va_list args); diff --git a/lib/string.c b/lib/string.c index f71bead1be3..01fad9b203e 100644 --- a/lib/string.c +++ b/lib/string.c @@ -535,6 +535,35 @@ bool sysfs_streq(const char *s1, const char *s2) } EXPORT_SYMBOL(sysfs_streq); +/** + * strtobool - convert common user inputs into boolean values + * @s: input string + * @res: result + * + * This routine returns 0 iff the first character is one of 'Yy1Nn0'. + * Otherwise it will return -EINVAL. Value pointed to by res is + * updated upon finding a match. + */ +int strtobool(const char *s, bool *res) +{ + switch (s[0]) { + case 'y': + case 'Y': + case '1': + *res = true; + break; + case 'n': + case 'N': + case '0': + *res = false; + break; + default: + return -EINVAL; + } + return 0; +} +EXPORT_SYMBOL(strtobool); + #ifndef __HAVE_ARCH_MEMSET /** * memset - Fill a region of memory with the given value -- cgit v1.2.3-70-g09d2 From b3ae52b6b0335eba547221aad2cb3c50902e3d2d Mon Sep 17 00:00:00 2001 From: Hauke Mehrtens Date: Tue, 10 May 2011 23:31:30 +0200 Subject: SSB: Change fallback sprom to callback mechanism. Some embedded devices like the Netgear WNDR3300 have two SSB based cards without an own sprom on the pci bus. We have to provide two different fallback sproms for these and this was not possible with the old solution. In the bcm47xx architecture the sprom data is stored in the nvram in the main flash storage. The architecture code will be able to fill the sprom with the stored data based on the bus where the device was found. The bcm63xx code should do the same thing as before, just using the new API. Acked-by: Michael Buesch Cc: netdev@vger.kernel.org Cc: linux-wireless@vger.kernel.org Cc: Florian Fainelli Signed-off-by: Hauke Mehrtens Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/2362/ Signed-off-by: Ralf Baechle --- arch/mips/bcm63xx/boards/board_bcm963xx.c | 16 ++++++++++-- drivers/ssb/pci.c | 16 ++++++++---- drivers/ssb/sprom.c | 43 ++++++++++++++++++------------- drivers/ssb/ssb_private.h | 3 ++- include/linux/ssb/ssb.h | 4 ++- 5 files changed, 55 insertions(+), 27 deletions(-) (limited to 'include') diff --git a/arch/mips/bcm63xx/boards/board_bcm963xx.c b/arch/mips/bcm63xx/boards/board_bcm963xx.c index 8dba8cfb752..40b223b603b 100644 --- a/arch/mips/bcm63xx/boards/board_bcm963xx.c +++ b/arch/mips/bcm63xx/boards/board_bcm963xx.c @@ -643,6 +643,17 @@ static struct ssb_sprom bcm63xx_sprom = { .boardflags_lo = 0x2848, .boardflags_hi = 0x0000, }; + +int bcm63xx_get_fallback_sprom(struct ssb_bus *bus, struct ssb_sprom *out) +{ + if (bus->bustype == SSB_BUSTYPE_PCI) { + memcpy(out, &bcm63xx_sprom, sizeof(struct ssb_sprom)); + return 0; + } else { + printk(KERN_ERR PFX "unable to fill SPROM for given bustype.\n"); + return -EINVAL; + } +} #endif /* @@ -793,8 +804,9 @@ void __init board_prom_init(void) if (!board_get_mac_address(bcm63xx_sprom.il0mac)) { memcpy(bcm63xx_sprom.et0mac, bcm63xx_sprom.il0mac, ETH_ALEN); memcpy(bcm63xx_sprom.et1mac, bcm63xx_sprom.il0mac, ETH_ALEN); - if (ssb_arch_set_fallback_sprom(&bcm63xx_sprom) < 0) - printk(KERN_ERR "failed to register fallback SPROM\n"); + if (ssb_arch_register_fallback_sprom( + &bcm63xx_get_fallback_sprom) < 0) + printk(KERN_ERR PFX "failed to register fallback SPROM\n"); } #endif } diff --git a/drivers/ssb/pci.c b/drivers/ssb/pci.c index 6f34963b3c6..7ad48585c5e 100644 --- a/drivers/ssb/pci.c +++ b/drivers/ssb/pci.c @@ -662,7 +662,6 @@ static int sprom_extract(struct ssb_bus *bus, struct ssb_sprom *out, static int ssb_pci_sprom_get(struct ssb_bus *bus, struct ssb_sprom *sprom) { - const struct ssb_sprom *fallback; int err; u16 *buf; @@ -707,10 +706,17 @@ static int ssb_pci_sprom_get(struct ssb_bus *bus, if (err) { /* All CRC attempts failed. * Maybe there is no SPROM on the device? - * If we have a fallback, use that. */ - fallback = ssb_get_fallback_sprom(); - if (fallback) { - memcpy(sprom, fallback, sizeof(*sprom)); + * Now we ask the arch code if there is some sprom + * available for this device in some other storage */ + err = ssb_fill_sprom_with_fallback(bus, sprom); + if (err) { + ssb_printk(KERN_WARNING PFX "WARNING: Using" + " fallback SPROM failed (err %d)\n", + err); + } else { + ssb_dprintk(KERN_DEBUG PFX "Using SPROM" + " revision %d provided by" + " platform.\n", sprom->revision); err = 0; goto out_free; } diff --git a/drivers/ssb/sprom.c b/drivers/ssb/sprom.c index 5f34d7a3e3a..45ff0e3a382 100644 --- a/drivers/ssb/sprom.c +++ b/drivers/ssb/sprom.c @@ -17,7 +17,7 @@ #include -static const struct ssb_sprom *fallback_sprom; +static int(*get_fallback_sprom)(struct ssb_bus *dev, struct ssb_sprom *out); static int sprom2hex(const u16 *sprom, char *buf, size_t buf_len, @@ -145,36 +145,43 @@ out: } /** - * ssb_arch_set_fallback_sprom - Set a fallback SPROM for use if no SPROM is found. + * ssb_arch_register_fallback_sprom - Registers a method providing a + * fallback SPROM if no SPROM is found. * - * @sprom: The SPROM data structure to register. + * @sprom_callback: The callback function. * - * With this function the architecture implementation may register a fallback - * SPROM data structure. The fallback is only used for PCI based SSB devices, - * where no valid SPROM can be found in the shadow registers. + * With this function the architecture implementation may register a + * callback handler which fills the SPROM data structure. The fallback is + * only used for PCI based SSB devices, where no valid SPROM can be found + * in the shadow registers. * - * This function is useful for weird architectures that have a half-assed SSB device - * hardwired to their PCI bus. + * This function is useful for weird architectures that have a half-assed + * SSB device hardwired to their PCI bus. * - * Note that it does only work with PCI attached SSB devices. PCMCIA devices currently - * don't use this fallback. - * Architectures must provide the SPROM for native SSB devices anyway, - * so the fallback also isn't used for native devices. + * Note that it does only work with PCI attached SSB devices. PCMCIA + * devices currently don't use this fallback. + * Architectures must provide the SPROM for native SSB devices anyway, so + * the fallback also isn't used for native devices. * - * This function is available for architecture code, only. So it is not exported. + * This function is available for architecture code, only. So it is not + * exported. */ -int ssb_arch_set_fallback_sprom(const struct ssb_sprom *sprom) +int ssb_arch_register_fallback_sprom(int (*sprom_callback)(struct ssb_bus *bus, + struct ssb_sprom *out)) { - if (fallback_sprom) + if (get_fallback_sprom) return -EEXIST; - fallback_sprom = sprom; + get_fallback_sprom = sprom_callback; return 0; } -const struct ssb_sprom *ssb_get_fallback_sprom(void) +int ssb_fill_sprom_with_fallback(struct ssb_bus *bus, struct ssb_sprom *out) { - return fallback_sprom; + if (!get_fallback_sprom) + return -ENOENT; + + return get_fallback_sprom(bus, out); } /* http://bcm-v4.sipsolutions.net/802.11/IsSpromAvailable */ diff --git a/drivers/ssb/ssb_private.h b/drivers/ssb/ssb_private.h index 0331139a726..77653014db0 100644 --- a/drivers/ssb/ssb_private.h +++ b/drivers/ssb/ssb_private.h @@ -171,7 +171,8 @@ ssize_t ssb_attr_sprom_store(struct ssb_bus *bus, const char *buf, size_t count, int (*sprom_check_crc)(const u16 *sprom, size_t size), int (*sprom_write)(struct ssb_bus *bus, const u16 *sprom)); -extern const struct ssb_sprom *ssb_get_fallback_sprom(void); +extern int ssb_fill_sprom_with_fallback(struct ssb_bus *bus, + struct ssb_sprom *out); /* core.c */ diff --git a/include/linux/ssb/ssb.h b/include/linux/ssb/ssb.h index 9659eff52ca..045f72ab5df 100644 --- a/include/linux/ssb/ssb.h +++ b/include/linux/ssb/ssb.h @@ -404,7 +404,9 @@ extern bool ssb_is_sprom_available(struct ssb_bus *bus); /* Set a fallback SPROM. * See kdoc at the function definition for complete documentation. */ -extern int ssb_arch_set_fallback_sprom(const struct ssb_sprom *sprom); +extern int ssb_arch_register_fallback_sprom( + int (*sprom_callback)(struct ssb_bus *bus, + struct ssb_sprom *out)); /* Suspend a SSB bus. * Call this from the parent bus suspend routine. */ -- cgit v1.2.3-70-g09d2 From 369db4c9524b7487faf1ff89646eee396c1363e1 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 18 May 2011 21:33:40 +0000 Subject: clocksource: Restructure clocksource struct members Group the hot path members of struct clocksource together so we have a better cache line footprint. Make it cacheline aligned. Signed-off-by: Thomas Gleixner Cc: John Stultz Cc: Eric Dumazet Reviewed-by: Ingo Molnar Link: http://lkml.kernel.org/r/%3C20110518210136.003081882%40linutronix.de%3E --- include/linux/clocksource.h | 32 ++++++++++++++------------------ 1 file changed, 14 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 0fb0b7e7939..c918fbd33ee 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -159,42 +159,38 @@ extern u64 timecounter_cyc2time(struct timecounter *tc, */ struct clocksource { /* - * First part of structure is read mostly + * Hotpath data, fits in a single cache line when the + * clocksource itself is cacheline aligned. */ - const char *name; - struct list_head list; - int rating; cycle_t (*read)(struct clocksource *cs); - int (*enable)(struct clocksource *cs); - void (*disable)(struct clocksource *cs); + cycle_t cycle_last; cycle_t mask; u32 mult; u32 shift; u64 max_idle_ns; - unsigned long flags; - cycle_t (*vread)(void); - void (*suspend)(struct clocksource *cs); - void (*resume)(struct clocksource *cs); + #ifdef CONFIG_IA64 void *fsys_mmio; /* used by fsyscall asm code */ #define CLKSRC_FSYS_MMIO_SET(mmio, addr) ((mmio) = (addr)) #else #define CLKSRC_FSYS_MMIO_SET(mmio, addr) do { } while (0) #endif - - /* - * Second part is written at each timer interrupt - * Keep it in a different cache line to dirty no - * more than one cache line. - */ - cycle_t cycle_last ____cacheline_aligned_in_smp; + const char *name; + struct list_head list; + int rating; + cycle_t (*vread)(void); + int (*enable)(struct clocksource *cs); + void (*disable)(struct clocksource *cs); + unsigned long flags; + void (*suspend)(struct clocksource *cs); + void (*resume)(struct clocksource *cs); #ifdef CONFIG_CLOCKSOURCE_WATCHDOG /* Watchdog related data, used by the framework */ struct list_head wd_list; cycle_t wd_last; #endif -}; +} ____cacheline_aligned; /* * Clock source flags bits:: -- cgit v1.2.3-70-g09d2 From 847b2f42be203f3cff7f243fdd3ee50c1e06c882 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 18 May 2011 21:33:41 +0000 Subject: clockevents: Restructure clock_event_device members Group the hot path members of struct clock_event_device together so we have a better cache line footprint. Make it cacheline aligned. Signed-off-by: Thomas Gleixner Cc: John Stultz Reviewed-by: Ingo Molnar Link: http://lkml.kernel.org/r/%3C20110518210136.223607682%40linutronix.de%3E --- include/linux/clockchips.h | 45 +++++++++++++++++++++++---------------------- 1 file changed, 23 insertions(+), 22 deletions(-) (limited to 'include') diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h index fc53492b6ad..9466eebc8e1 100644 --- a/include/linux/clockchips.h +++ b/include/linux/clockchips.h @@ -56,46 +56,47 @@ enum clock_event_nofitiers { /** * struct clock_event_device - clock event device descriptor - * @name: ptr to clock event name - * @features: features + * @event_handler: Assigned by the framework to be called by the low + * level handler of the event source + * @set_next_event: set next event function + * @next_event: local storage for the next event in oneshot mode * @max_delta_ns: maximum delta value in ns * @min_delta_ns: minimum delta value in ns * @mult: nanosecond to cycles multiplier * @shift: nanoseconds to cycles divisor (power of two) + * @mode: operating mode assigned by the management code + * @features: features + * @retries: number of forced programming retries + * @set_mode: set mode function + * @broadcast: function to broadcast events + * @name: ptr to clock event name * @rating: variable to rate clock event devices * @irq: IRQ number (only for non CPU local devices) * @cpumask: cpumask to indicate for which CPUs this device works - * @set_next_event: set next event function - * @set_mode: set mode function - * @event_handler: Assigned by the framework to be called by the low - * level handler of the event source - * @broadcast: function to broadcast events * @list: list head for the management code - * @mode: operating mode assigned by the management code - * @next_event: local storage for the next event in oneshot mode - * @retries: number of forced programming retries */ struct clock_event_device { - const char *name; - unsigned int features; + void (*event_handler)(struct clock_event_device *); + int (*set_next_event)(unsigned long evt, + struct clock_event_device *); + ktime_t next_event; u64 max_delta_ns; u64 min_delta_ns; u32 mult; u32 shift; + enum clock_event_mode mode; + unsigned int features; + unsigned long retries; + + void (*broadcast)(const struct cpumask *mask); + void (*set_mode)(enum clock_event_mode mode, + struct clock_event_device *); + const char *name; int rating; int irq; const struct cpumask *cpumask; - int (*set_next_event)(unsigned long evt, - struct clock_event_device *); - void (*set_mode)(enum clock_event_mode mode, - struct clock_event_device *); - void (*event_handler)(struct clock_event_device *); - void (*broadcast)(const struct cpumask *mask); struct list_head list; - enum clock_event_mode mode; - ktime_t next_event; - unsigned long retries; -}; +} ____cacheline_aligned; /* * Calculate a multiplication factor for scaled math, which is used to convert -- cgit v1.2.3-70-g09d2 From 57f0fcbe1dea8a36c9d1673086326059991c5f81 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 18 May 2011 21:33:41 +0000 Subject: clockevents: Provide combined configure and register function All clockevent devices have the same open coded initialization functions. Provide an interface which does all necessary initialization in the core code. Signed-off-by: Thomas Gleixner Cc: John Stultz Reviewed-by: Ingo Molnar Link: http://lkml.kernel.org/r/%3C20110518210136.331975870%40linutronix.de%3E --- include/linux/clockchips.h | 9 +++++++++ kernel/time/clockevents.c | 44 ++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 53 insertions(+) (limited to 'include') diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h index 9466eebc8e1..80acc79e0dc 100644 --- a/include/linux/clockchips.h +++ b/include/linux/clockchips.h @@ -69,6 +69,8 @@ enum clock_event_nofitiers { * @retries: number of forced programming retries * @set_mode: set mode function * @broadcast: function to broadcast events + * @min_delta_ticks: minimum delta value in ticks stored for reconfiguration + * @max_delta_ticks: maximum delta value in ticks stored for reconfiguration * @name: ptr to clock event name * @rating: variable to rate clock event devices * @irq: IRQ number (only for non CPU local devices) @@ -91,6 +93,9 @@ struct clock_event_device { void (*broadcast)(const struct cpumask *mask); void (*set_mode)(enum clock_event_mode mode, struct clock_event_device *); + unsigned long min_delta_ticks; + unsigned long max_delta_ticks; + const char *name; int rating; int irq; @@ -123,6 +128,10 @@ extern u64 clockevent_delta2ns(unsigned long latch, struct clock_event_device *evt); extern void clockevents_register_device(struct clock_event_device *dev); +extern void clockevents_config_and_register(struct clock_event_device *dev, + u32 freq, unsigned long min_delta, + unsigned long max_delta); + extern void clockevents_exchange_device(struct clock_event_device *old, struct clock_event_device *new); extern void clockevents_set_mode(struct clock_event_device *dev, diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index 0d74b9ba90c..c69e88c9444 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -194,6 +194,50 @@ void clockevents_register_device(struct clock_event_device *dev) } EXPORT_SYMBOL_GPL(clockevents_register_device); +static void clockevents_config(struct clock_event_device *dev, + u32 freq) +{ + unsigned long sec; + + if (!(dev->features & CLOCK_EVT_FEAT_ONESHOT)) + return; + + /* + * Calculate the maximum number of seconds we can sleep. Limit + * to 10 minutes for hardware which can program more than + * 32bit ticks so we still get reasonable conversion values. + */ + sec = dev->max_delta_ticks; + do_div(sec, freq); + if (!sec) + sec = 1; + else if (sec > 600 && dev->max_delta_ticks > UINT_MAX) + sec = 600; + + clockevents_calc_mult_shift(dev, freq, sec); + dev->min_delta_ns = clockevent_delta2ns(dev->min_delta_ticks, dev); + dev->max_delta_ns = clockevent_delta2ns(dev->max_delta_ticks, dev); +} + +/** + * clockevents_config_and_register - Configure and register a clock event device + * @dev: device to register + * @freq: The clock frequency + * @min_delta: The minimum clock ticks to program in oneshot mode + * @max_delta: The maximum clock ticks to program in oneshot mode + * + * min/max_delta can be 0 for devices which do not support oneshot mode. + */ +void clockevents_config_and_register(struct clock_event_device *dev, + u32 freq, unsigned long min_delta, + unsigned long max_delta) +{ + dev->min_delta_ticks = min_delta; + dev->max_delta_ticks = max_delta; + clockevents_config(dev, freq); + clockevents_register_device(dev); +} + /* * Noop handler when we shut down an event device */ -- cgit v1.2.3-70-g09d2 From 80b816b736cfa5b9582279127099b20a479ab7d9 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 18 May 2011 21:33:42 +0000 Subject: clockevents: Provide interface to reconfigure an active clock event device Some ARM SoCs have clock event devices which have their frequency modified due to frequency scaling. Provide an interface which allows to reconfigure an active device. After reconfiguration reprogram the current pending event. Signed-off-by: Thomas Gleixner Cc: LAK Cc: John Stultz Acked-by: Linus Walleij Reviewed-by: Ingo Molnar Link: http://lkml.kernel.org/r/%3C20110518210136.437459958%40linutronix.de%3E --- include/linux/clockchips.h | 2 ++ kernel/time/clockevents.c | 20 ++++++++++++++++++++ 2 files changed, 22 insertions(+) (limited to 'include') diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h index 80acc79e0dc..d6733e27af3 100644 --- a/include/linux/clockchips.h +++ b/include/linux/clockchips.h @@ -132,6 +132,8 @@ extern void clockevents_config_and_register(struct clock_event_device *dev, u32 freq, unsigned long min_delta, unsigned long max_delta); +extern int clockevents_update_freq(struct clock_event_device *ce, u32 freq); + extern void clockevents_exchange_device(struct clock_event_device *old, struct clock_event_device *new); extern void clockevents_set_mode(struct clock_event_device *dev, diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index c69e88c9444..22a9da9a9c9 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -238,6 +238,26 @@ void clockevents_config_and_register(struct clock_event_device *dev, clockevents_register_device(dev); } +/** + * clockevents_update_freq - Update frequency and reprogram a clock event device. + * @dev: device to modify + * @freq: new device frequency + * + * Reconfigure and reprogram a clock event device in oneshot + * mode. Must be called on the cpu for which the device delivers per + * cpu timer events with interrupts disabled! Returns 0 on success, + * -ETIME when the event is in the past. + */ +int clockevents_update_freq(struct clock_event_device *dev, u32 freq) +{ + clockevents_config(dev, freq); + + if (dev->mode != CLOCK_EVT_MODE_ONESHOT) + return 0; + + return clockevents_program_event(dev, dev->next_event, ktime_get()); +} + /* * Noop handler when we shut down an event device */ -- cgit v1.2.3-70-g09d2 From 75d65a425c0163d3ec476ddc12b51087217a070c Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 19 May 2011 13:50:07 -0700 Subject: hlist: remove software prefetching in hlist iterators They not only increase the code footprint, they actually make things slower rather than faster. On internationally acclaimed benchmarks ("make -j16" on an already fully built kernel source tree) the hlist prefetching slows down the build by up to 1%. (Almost all of it comes from hlist_for_each_entry_rcu() as used by avc_has_perm_noaudit(), which is very hot due to all the pathname lookups to see if there is anything to do). The cause seems to be two-fold: - on at least some Intel cores, prefetch(NULL) ends up with some microarchitectural stall due to the TLB miss that it incurs. The hlist case triggers this very commonly, since the NULL pointer is the last entry in the list. - the prefetch appears to cause more D$ activity, probably because it prefetches hash list entries that are never actually used (because we ended the search early due to a hit). Regardless, the numbers clearly say that the implicit prefetching is simply a bad idea. If some _particular_ user of the hlist iterators wants to prefetch the next list entry, they can do so themselves explicitly, rather than depend on all list iterators doing so implicitly. Acked-by: Ingo Molnar Acked-by: David S. Miller Cc: linux-arch@vger.kernel.org Signed-off-by: Linus Torvalds --- include/linux/list.h | 9 ++++----- include/linux/rculist.h | 10 +++++----- 2 files changed, 9 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/list.h b/include/linux/list.h index 3a54266a1e8..9ac11148e03 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -664,8 +664,7 @@ static inline void hlist_move_list(struct hlist_head *old, #define hlist_entry(ptr, type, member) container_of(ptr,type,member) #define hlist_for_each(pos, head) \ - for (pos = (head)->first; pos && ({ prefetch(pos->next); 1; }); \ - pos = pos->next) + for (pos = (head)->first; pos ; pos = pos->next) #define hlist_for_each_safe(pos, n, head) \ for (pos = (head)->first; pos && ({ n = pos->next; 1; }); \ @@ -680,7 +679,7 @@ static inline void hlist_move_list(struct hlist_head *old, */ #define hlist_for_each_entry(tpos, pos, head, member) \ for (pos = (head)->first; \ - pos && ({ prefetch(pos->next); 1;}) && \ + pos && \ ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1;}); \ pos = pos->next) @@ -692,7 +691,7 @@ static inline void hlist_move_list(struct hlist_head *old, */ #define hlist_for_each_entry_continue(tpos, pos, member) \ for (pos = (pos)->next; \ - pos && ({ prefetch(pos->next); 1;}) && \ + pos && \ ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1;}); \ pos = pos->next) @@ -703,7 +702,7 @@ static inline void hlist_move_list(struct hlist_head *old, * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_from(tpos, pos, member) \ - for (; pos && ({ prefetch(pos->next); 1;}) && \ + for (; pos && \ ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1;}); \ pos = pos->next) diff --git a/include/linux/rculist.h b/include/linux/rculist.h index 2dea94fc440..900a97a4476 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -427,7 +427,7 @@ static inline void hlist_add_after_rcu(struct hlist_node *prev, #define __hlist_for_each_rcu(pos, head) \ for (pos = rcu_dereference(hlist_first_rcu(head)); \ - pos && ({ prefetch(pos->next); 1; }); \ + pos; \ pos = rcu_dereference(hlist_next_rcu(pos))) /** @@ -443,7 +443,7 @@ static inline void hlist_add_after_rcu(struct hlist_node *prev, */ #define hlist_for_each_entry_rcu(tpos, pos, head, member) \ for (pos = rcu_dereference_raw(hlist_first_rcu(head)); \ - pos && ({ prefetch(pos->next); 1; }) && \ + pos && \ ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1; }); \ pos = rcu_dereference_raw(hlist_next_rcu(pos))) @@ -460,7 +460,7 @@ static inline void hlist_add_after_rcu(struct hlist_node *prev, */ #define hlist_for_each_entry_rcu_bh(tpos, pos, head, member) \ for (pos = rcu_dereference_bh((head)->first); \ - pos && ({ prefetch(pos->next); 1; }) && \ + pos && \ ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1; }); \ pos = rcu_dereference_bh(pos->next)) @@ -472,7 +472,7 @@ static inline void hlist_add_after_rcu(struct hlist_node *prev, */ #define hlist_for_each_entry_continue_rcu(tpos, pos, member) \ for (pos = rcu_dereference((pos)->next); \ - pos && ({ prefetch(pos->next); 1; }) && \ + pos && \ ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1; }); \ pos = rcu_dereference(pos->next)) @@ -484,7 +484,7 @@ static inline void hlist_add_after_rcu(struct hlist_node *prev, */ #define hlist_for_each_entry_continue_rcu_bh(tpos, pos, member) \ for (pos = rcu_dereference_bh((pos)->next); \ - pos && ({ prefetch(pos->next); 1; }) && \ + pos && \ ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1; }); \ pos = rcu_dereference_bh(pos->next)) -- cgit v1.2.3-70-g09d2 From e66eed651fd18a961f11cda62f3b5286c8cc4f9f Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 19 May 2011 14:15:29 -0700 Subject: list: remove prefetching from regular list iterators This is removes the use of software prefetching from the regular list iterators. We don't want it. If you do want to prefetch in some iterator of yours, go right ahead. Just don't expect the iterator to do it, since normally the downsides are bigger than the upsides. It also replaces with , because the use of LIST_POISON ends up needing it. is sadly not self-contained, and including prefetch.h just happened to hide that. Suggested by David Miller (networking has a lot of regular lists that are often empty or a single entry, and prefetching is not going to do anything but add useless instructions). Acked-by: Ingo Molnar Acked-by: David S. Miller Cc: linux-arch@vger.kernel.org Signed-off-by: Linus Torvalds --- include/linux/list.h | 26 +++++++++++--------------- include/linux/rculist.h | 6 +++--- 2 files changed, 14 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/linux/list.h b/include/linux/list.h index 9ac11148e03..cc6d2aa6b41 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -4,7 +4,7 @@ #include #include #include -#include +#include /* * Simple doubly linked list implementation. @@ -367,18 +367,15 @@ static inline void list_splice_tail_init(struct list_head *list, * @head: the head for your list. */ #define list_for_each(pos, head) \ - for (pos = (head)->next; prefetch(pos->next), pos != (head); \ - pos = pos->next) + for (pos = (head)->next; pos != (head); pos = pos->next) /** * __list_for_each - iterate over a list * @pos: the &struct list_head to use as a loop cursor. * @head: the head for your list. * - * This variant differs from list_for_each() in that it's the - * simplest possible list iteration code, no prefetching is done. - * Use this for code that knows the list to be very short (empty - * or 1 entry) most of the time. + * This variant doesn't differ from list_for_each() any more. + * We don't do prefetching in either case. */ #define __list_for_each(pos, head) \ for (pos = (head)->next; pos != (head); pos = pos->next) @@ -389,8 +386,7 @@ static inline void list_splice_tail_init(struct list_head *list, * @head: the head for your list. */ #define list_for_each_prev(pos, head) \ - for (pos = (head)->prev; prefetch(pos->prev), pos != (head); \ - pos = pos->prev) + for (pos = (head)->prev; pos != (head); pos = pos->prev) /** * list_for_each_safe - iterate over a list safe against removal of list entry @@ -410,7 +406,7 @@ static inline void list_splice_tail_init(struct list_head *list, */ #define list_for_each_prev_safe(pos, n, head) \ for (pos = (head)->prev, n = pos->prev; \ - prefetch(pos->prev), pos != (head); \ + pos != (head); \ pos = n, n = pos->prev) /** @@ -421,7 +417,7 @@ static inline void list_splice_tail_init(struct list_head *list, */ #define list_for_each_entry(pos, head, member) \ for (pos = list_entry((head)->next, typeof(*pos), member); \ - prefetch(pos->member.next), &pos->member != (head); \ + &pos->member != (head); \ pos = list_entry(pos->member.next, typeof(*pos), member)) /** @@ -432,7 +428,7 @@ static inline void list_splice_tail_init(struct list_head *list, */ #define list_for_each_entry_reverse(pos, head, member) \ for (pos = list_entry((head)->prev, typeof(*pos), member); \ - prefetch(pos->member.prev), &pos->member != (head); \ + &pos->member != (head); \ pos = list_entry(pos->member.prev, typeof(*pos), member)) /** @@ -457,7 +453,7 @@ static inline void list_splice_tail_init(struct list_head *list, */ #define list_for_each_entry_continue(pos, head, member) \ for (pos = list_entry(pos->member.next, typeof(*pos), member); \ - prefetch(pos->member.next), &pos->member != (head); \ + &pos->member != (head); \ pos = list_entry(pos->member.next, typeof(*pos), member)) /** @@ -471,7 +467,7 @@ static inline void list_splice_tail_init(struct list_head *list, */ #define list_for_each_entry_continue_reverse(pos, head, member) \ for (pos = list_entry(pos->member.prev, typeof(*pos), member); \ - prefetch(pos->member.prev), &pos->member != (head); \ + &pos->member != (head); \ pos = list_entry(pos->member.prev, typeof(*pos), member)) /** @@ -483,7 +479,7 @@ static inline void list_splice_tail_init(struct list_head *list, * Iterate over list of given type, continuing from current position. */ #define list_for_each_entry_from(pos, head, member) \ - for (; prefetch(pos->member.next), &pos->member != (head); \ + for (; &pos->member != (head); \ pos = list_entry(pos->member.next, typeof(*pos), member)) /** diff --git a/include/linux/rculist.h b/include/linux/rculist.h index 900a97a4476..e3beb315517 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -253,7 +253,7 @@ static inline void list_splice_init_rcu(struct list_head *list, */ #define list_for_each_entry_rcu(pos, head, member) \ for (pos = list_entry_rcu((head)->next, typeof(*pos), member); \ - prefetch(pos->member.next), &pos->member != (head); \ + &pos->member != (head); \ pos = list_entry_rcu(pos->member.next, typeof(*pos), member)) @@ -270,7 +270,7 @@ static inline void list_splice_init_rcu(struct list_head *list, */ #define list_for_each_continue_rcu(pos, head) \ for ((pos) = rcu_dereference_raw(list_next_rcu(pos)); \ - prefetch((pos)->next), (pos) != (head); \ + (pos) != (head); \ (pos) = rcu_dereference_raw(list_next_rcu(pos))) /** @@ -284,7 +284,7 @@ static inline void list_splice_init_rcu(struct list_head *list, */ #define list_for_each_entry_continue_rcu(pos, head, member) \ for (pos = list_entry_rcu(pos->member.next, typeof(*pos), member); \ - prefetch(pos->member.next), &pos->member != (head); \ + &pos->member != (head); \ pos = list_entry_rcu(pos->member.next, typeof(*pos), member)) /** -- cgit v1.2.3-70-g09d2 From 1477fcc290b3d5c2614bde98bf3b1154c538860d Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Fri, 20 May 2011 11:11:53 +1000 Subject: signal.h need a definition of struct task_struct This fixes these build errors on powerpc: In file included from arch/powerpc/mm/fault.c:18: include/linux/signal.h:239: error: 'struct task_struct' declared inside parameter list include/linux/signal.h:239: error: its scope is only this definition or declaration, which is probably not what you want include/linux/signal.h:240: error: 'struct task_struct' declared inside parameter list .. Exposed by commit e66eed651fd1 ("list: remove prefetching from regular list iterators"), which removed the include of from . Without that, linux/signal.h no longer accidentally got the declaration of 'struct task_struct'. Fix by properly declaring the struct, rather than introducing any new header file dependency. Signed-off-by: Stephen Rothwell Signed-off-by: Linus Torvalds --- include/linux/signal.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/signal.h b/include/linux/signal.h index fcd2b14b193..29a68ac7af8 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -7,6 +7,8 @@ #ifdef __KERNEL__ #include +struct task_struct; + /* for sysctl */ extern int print_fatal_signals; /* -- cgit v1.2.3-70-g09d2