From dd17c8f72993f9461e9c19250e3f155d6d99df22 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Thu, 29 Oct 2009 22:34:15 +0900 Subject: percpu: remove per_cpu__ prefix. Now that the return from alloc_percpu is compatible with the address of per-cpu vars, it makes sense to hand around the address of per-cpu variables. To make this sane, we remove the per_cpu__ prefix we used created to stop people accidentally using these vars directly. Now we have sparse, we can use that (next patch). tj: * Updated to convert stuff which were missed by or added after the original patch. * Kill per_cpu_var() macro. Signed-off-by: Rusty Russell Signed-off-by: Tejun Heo Reviewed-by: Christoph Lameter --- include/linux/percpu-defs.h | 18 ++++++------------ include/linux/percpu.h | 5 ++--- include/linux/vmstat.h | 8 ++++---- 3 files changed, 12 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h index 5a5d6ce4bd55..ee99f6c2cdcd 100644 --- a/include/linux/percpu-defs.h +++ b/include/linux/percpu-defs.h @@ -1,12 +1,6 @@ #ifndef _LINUX_PERCPU_DEFS_H #define _LINUX_PERCPU_DEFS_H -/* - * Determine the real variable name from the name visible in the - * kernel sources. - */ -#define per_cpu_var(var) per_cpu__##var - /* * Base implementations of per-CPU variable declarations and definitions, where * the section in which the variable is to be placed is provided by the @@ -56,24 +50,24 @@ */ #define DECLARE_PER_CPU_SECTION(type, name, sec) \ extern __PCPU_DUMMY_ATTRS char __pcpu_scope_##name; \ - extern __PCPU_ATTRS(sec) __typeof__(type) per_cpu__##name + extern __PCPU_ATTRS(sec) __typeof__(type) name #define DEFINE_PER_CPU_SECTION(type, name, sec) \ __PCPU_DUMMY_ATTRS char __pcpu_scope_##name; \ extern __PCPU_DUMMY_ATTRS char __pcpu_unique_##name; \ __PCPU_DUMMY_ATTRS char __pcpu_unique_##name; \ __PCPU_ATTRS(sec) PER_CPU_DEF_ATTRIBUTES __weak \ - __typeof__(type) per_cpu__##name + __typeof__(type) name #else /* * Normal declaration and definition macros. */ #define DECLARE_PER_CPU_SECTION(type, name, sec) \ - extern __PCPU_ATTRS(sec) __typeof__(type) per_cpu__##name + extern __PCPU_ATTRS(sec) __typeof__(type) name #define DEFINE_PER_CPU_SECTION(type, name, sec) \ __PCPU_ATTRS(sec) PER_CPU_DEF_ATTRIBUTES \ - __typeof__(type) per_cpu__##name + __typeof__(type) name #endif /* @@ -137,8 +131,8 @@ /* * Intermodule exports for per-CPU variables. */ -#define EXPORT_PER_CPU_SYMBOL(var) EXPORT_SYMBOL(per_cpu__##var) -#define EXPORT_PER_CPU_SYMBOL_GPL(var) EXPORT_SYMBOL_GPL(per_cpu__##var) +#define EXPORT_PER_CPU_SYMBOL(var) EXPORT_SYMBOL(var) +#define EXPORT_PER_CPU_SYMBOL_GPL(var) EXPORT_SYMBOL_GPL(var) #endif /* _LINUX_PERCPU_DEFS_H */ diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 522f421ec213..e12410e55e05 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -182,7 +182,7 @@ static inline void *pcpu_lpage_remapped(void *kaddr) #ifndef percpu_read # define percpu_read(var) \ ({ \ - typeof(per_cpu_var(var)) __tmp_var__; \ + typeof(var) __tmp_var__; \ __tmp_var__ = get_cpu_var(var); \ put_cpu_var(var); \ __tmp_var__; \ @@ -253,8 +253,7 @@ do { \ /* * Optimized manipulation for memory allocated through the per cpu - * allocator or for addresses of per cpu variables (can be determined - * using per_cpu_var(xx). + * allocator or for addresses of per cpu variables. * * These operation guarantee exclusivity of access for other operations * on the *same* processor. The assumption is that per cpu data is only diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index d85889710f9b..3e489fda11a1 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -76,22 +76,22 @@ DECLARE_PER_CPU(struct vm_event_state, vm_event_states); static inline void __count_vm_event(enum vm_event_item item) { - __this_cpu_inc(per_cpu_var(vm_event_states).event[item]); + __this_cpu_inc(vm_event_states.event[item]); } static inline void count_vm_event(enum vm_event_item item) { - this_cpu_inc(per_cpu_var(vm_event_states).event[item]); + this_cpu_inc(vm_event_states.event[item]); } static inline void __count_vm_events(enum vm_event_item item, long delta) { - __this_cpu_add(per_cpu_var(vm_event_states).event[item], delta); + __this_cpu_add(vm_event_states.event[item], delta); } static inline void count_vm_events(enum vm_event_item item, long delta) { - this_cpu_add(per_cpu_var(vm_event_states).event[item], delta); + this_cpu_add(vm_event_states.event[item], delta); } extern void all_vm_events(unsigned long *); -- cgit v1.2.3 From f7b64fe806029e0a0454df132eec3c5ab576102c Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 29 Oct 2009 22:34:15 +0900 Subject: percpu: make access macros universal Now that per_cpu__ prefix is gone, there's no distinction between static and dynamic percpu variables. Make get_cpu_var() take dynamic percpu variables and ensure that all macros have parentheses around the parameter evaluation and evaluate the variable parameter only once such that any expression which evaluates to percpu address can be used safely. Signed-off-by: Tejun Heo --- include/linux/percpu.h | 23 ++++++++++++++--------- 1 file changed, 14 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index e12410e55e05..f965f833a643 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -27,10 +27,13 @@ * we force a syntax error here if it isn't. */ #define get_cpu_var(var) (*({ \ - extern int simple_identifier_##var(void); \ preempt_disable(); \ &__get_cpu_var(var); })) -#define put_cpu_var(var) preempt_enable() + +#define put_cpu_var(var) do { \ + (void)(var); \ + preempt_enable(); \ +} while (0) #ifdef CONFIG_SMP @@ -182,17 +185,19 @@ static inline void *pcpu_lpage_remapped(void *kaddr) #ifndef percpu_read # define percpu_read(var) \ ({ \ - typeof(var) __tmp_var__; \ - __tmp_var__ = get_cpu_var(var); \ - put_cpu_var(var); \ - __tmp_var__; \ + typeof(var) *pr_ptr__ = &(var); \ + typeof(var) pr_ret__; \ + pr_ret__ = get_cpu_var(*pr_ptr__); \ + put_cpu_var(*pr_ptr__); \ + pr_ret__; \ }) #endif #define __percpu_generic_to_op(var, val, op) \ do { \ - get_cpu_var(var) op val; \ - put_cpu_var(var); \ + typeof(var) *pgto_ptr__ = &(var); \ + get_cpu_var(*pgto_ptr__) op val; \ + put_cpu_var(*pgto_ptr__); \ } while (0) #ifndef percpu_write @@ -304,7 +309,7 @@ do { \ #define _this_cpu_generic_to_op(pcp, val, op) \ do { \ preempt_disable(); \ - *__this_cpu_ptr(&pcp) op val; \ + *__this_cpu_ptr(&(pcp)) op val; \ preempt_enable(); \ } while (0) -- cgit v1.2.3 From e0fdb0e050eae331046385643618f12452aa7e73 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Thu, 29 Oct 2009 22:34:15 +0900 Subject: percpu: add __percpu for sparse. We have to make __kernel "__attribute__((address_space(0)))" so we can cast to it. tj: * put_cpu_var() update. * Annotations added to dynamic allocator interface. Signed-off-by: Rusty Russell Cc: Al Viro Signed-off-by: Tejun Heo --- include/linux/compiler.h | 4 +++- include/linux/percpu-defs.h | 2 +- include/linux/percpu.h | 18 +++++++++++------- 3 files changed, 15 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 04fb5135b4e1..abba8045c6ef 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -5,7 +5,7 @@ #ifdef __CHECKER__ # define __user __attribute__((noderef, address_space(1))) -# define __kernel /* default address space */ +# define __kernel __attribute__((address_space(0))) # define __safe __attribute__((safe)) # define __force __attribute__((force)) # define __nocast __attribute__((nocast)) @@ -15,6 +15,7 @@ # define __acquire(x) __context__(x,1) # define __release(x) __context__(x,-1) # define __cond_lock(x,c) ((c) ? ({ __acquire(x); 1; }) : 0) +# define __percpu __attribute__((noderef, address_space(3))) extern void __chk_user_ptr(const volatile void __user *); extern void __chk_io_ptr(const volatile void __iomem *); #else @@ -32,6 +33,7 @@ extern void __chk_io_ptr(const volatile void __iomem *); # define __acquire(x) (void)0 # define __release(x) (void)0 # define __cond_lock(x,c) (c) +# define __percpu #endif #ifdef __KERNEL__ diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h index ee99f6c2cdcd..0fa0cb524250 100644 --- a/include/linux/percpu-defs.h +++ b/include/linux/percpu-defs.h @@ -12,7 +12,7 @@ * that section. */ #define __PCPU_ATTRS(sec) \ - __attribute__((section(PER_CPU_BASE_SECTION sec))) \ + __percpu __attribute__((section(PER_CPU_BASE_SECTION sec))) \ PER_CPU_ATTRIBUTES #define __PCPU_DUMMY_ATTRS \ diff --git a/include/linux/percpu.h b/include/linux/percpu.h index f965f833a643..2c0d31a3f6b6 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -30,8 +30,12 @@ preempt_disable(); \ &__get_cpu_var(var); })) +/* + * The weird & is necessary because sparse considers (void)(var) to be + * a direct dereference of percpu variable (var). + */ #define put_cpu_var(var) do { \ - (void)(var); \ + (void)&(var); \ preempt_enable(); \ } while (0) @@ -130,9 +134,9 @@ extern int __init pcpu_page_first_chunk(size_t reserved_size, */ #define per_cpu_ptr(ptr, cpu) SHIFT_PERCPU_PTR((ptr), per_cpu_offset((cpu))) -extern void *__alloc_reserved_percpu(size_t size, size_t align); -extern void *__alloc_percpu(size_t size, size_t align); -extern void free_percpu(void *__pdata); +extern void __percpu *__alloc_reserved_percpu(size_t size, size_t align); +extern void __percpu *__alloc_percpu(size_t size, size_t align); +extern void free_percpu(void __percpu *__pdata); #ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA extern void __init setup_per_cpu_areas(void); @@ -142,7 +146,7 @@ extern void __init setup_per_cpu_areas(void); #define per_cpu_ptr(ptr, cpu) ({ (void)(cpu); (ptr); }) -static inline void *__alloc_percpu(size_t size, size_t align) +static inline void __percpu *__alloc_percpu(size_t size, size_t align) { /* * Can't easily make larger alignment work with kmalloc. WARN @@ -153,7 +157,7 @@ static inline void *__alloc_percpu(size_t size, size_t align) return kzalloc(size, GFP_KERNEL); } -static inline void free_percpu(void *p) +static inline void free_percpu(void __percpu *p) { kfree(p); } @@ -168,7 +172,7 @@ static inline void *pcpu_lpage_remapped(void *kaddr) #endif /* CONFIG_SMP */ #define alloc_percpu(type) \ - (typeof(type) *)__alloc_percpu(sizeof(type), __alignof__(type)) + (typeof(type) __percpu *)__alloc_percpu(sizeof(type), __alignof__(type)) /* * Optional methods for optimized non-lvalue per-cpu variable access. -- cgit v1.2.3 From 545695fb41da117928ab946067a42d9e15fd009d Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 29 Oct 2009 22:34:15 +0900 Subject: percpu: make accessors check for percpu pointer in sparse The previous patch made sparse warn about percpu variables being used directly without going through percpu accessors. This patch implements the other half - checking whether non percpu variable is passed into percpu accessors. Signed-off-by: Tejun Heo Cc: Rusty Russell Cc: Al Viro --- include/linux/percpu-defs.h | 20 ++++++++++++++++++-- include/linux/percpu.h | 2 ++ 2 files changed, 20 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h index 0fa0cb524250..1fa36eb54b6a 100644 --- a/include/linux/percpu-defs.h +++ b/include/linux/percpu-defs.h @@ -18,6 +18,16 @@ #define __PCPU_DUMMY_ATTRS \ __attribute__((section(".discard"), unused)) +/* + * Macro which verifies @ptr is a percpu pointer without evaluating + * @ptr. This is to be used in percpu accessors to verify that the + * input parameter is a percpu pointer. + */ +#define __verify_pcpu_ptr(ptr) do { \ + void __percpu *__vpp_verify = (typeof(ptr))NULL; \ + (void)__vpp_verify; \ +} while (0) + /* * s390 and alpha modules require percpu variables to be defined as * weak to force the compiler to generate GOT based external @@ -129,10 +139,16 @@ __aligned(PAGE_SIZE) /* - * Intermodule exports for per-CPU variables. + * Intermodule exports for per-CPU variables. sparse forgets about + * address space across EXPORT_SYMBOL(), change EXPORT_SYMBOL() to + * noop if __CHECKER__. */ +#ifndef __CHECKER__ #define EXPORT_PER_CPU_SYMBOL(var) EXPORT_SYMBOL(var) #define EXPORT_PER_CPU_SYMBOL_GPL(var) EXPORT_SYMBOL_GPL(var) - +#else +#define EXPORT_PER_CPU_SYMBOL(var) +#define EXPORT_PER_CPU_SYMBOL_GPL(var) +#endif #endif /* _LINUX_PERCPU_DEFS_H */ diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 2c0d31a3f6b6..42878f0cd0e2 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -237,6 +237,7 @@ extern void __bad_size_call_parameter(void); #define __pcpu_size_call_return(stem, variable) \ ({ typeof(variable) pscr_ret__; \ + __verify_pcpu_ptr(&(variable)); \ switch(sizeof(variable)) { \ case 1: pscr_ret__ = stem##1(variable);break; \ case 2: pscr_ret__ = stem##2(variable);break; \ @@ -250,6 +251,7 @@ extern void __bad_size_call_parameter(void); #define __pcpu_size_call(stem, variable, ...) \ do { \ + __verify_pcpu_ptr(&(variable)); \ switch(sizeof(variable)) { \ case 1: stem##1(variable, __VA_ARGS__);break; \ case 2: stem##2(variable, __VA_ARGS__);break; \ -- cgit v1.2.3 From 5db53f3e80dee2d9dff5e534f9e9fe1db17c9936 Mon Sep 17 00:00:00 2001 From: Joern Engel Date: Fri, 20 Nov 2009 20:13:39 +0100 Subject: [LogFS] add new flash file system This is a new flash file system. See Documentation/filesystems/logfs.txt Signed-off-by: Joern Engel --- include/linux/btree-128.h | 109 ++++++++++++++++++++ include/linux/btree-type.h | 147 +++++++++++++++++++++++++++ include/linux/btree.h | 243 +++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 499 insertions(+) create mode 100644 include/linux/btree-128.h create mode 100644 include/linux/btree-type.h create mode 100644 include/linux/btree.h (limited to 'include/linux') diff --git a/include/linux/btree-128.h b/include/linux/btree-128.h new file mode 100644 index 000000000000..0b3414c4c928 --- /dev/null +++ b/include/linux/btree-128.h @@ -0,0 +1,109 @@ +extern struct btree_geo btree_geo128; + +struct btree_head128 { struct btree_head h; }; + +static inline void btree_init_mempool128(struct btree_head128 *head, + mempool_t *mempool) +{ + btree_init_mempool(&head->h, mempool); +} + +static inline int btree_init128(struct btree_head128 *head) +{ + return btree_init(&head->h); +} + +static inline void btree_destroy128(struct btree_head128 *head) +{ + btree_destroy(&head->h); +} + +static inline void *btree_lookup128(struct btree_head128 *head, u64 k1, u64 k2) +{ + u64 key[2] = {k1, k2}; + return btree_lookup(&head->h, &btree_geo128, (unsigned long *)&key); +} + +static inline void *btree_get_prev128(struct btree_head128 *head, + u64 *k1, u64 *k2) +{ + u64 key[2] = {*k1, *k2}; + void *val; + + val = btree_get_prev(&head->h, &btree_geo128, + (unsigned long *)&key); + *k1 = key[0]; + *k2 = key[1]; + return val; +} + +static inline int btree_insert128(struct btree_head128 *head, u64 k1, u64 k2, + void *val, gfp_t gfp) +{ + u64 key[2] = {k1, k2}; + return btree_insert(&head->h, &btree_geo128, + (unsigned long *)&key, val, gfp); +} + +static inline int btree_update128(struct btree_head128 *head, u64 k1, u64 k2, + void *val) +{ + u64 key[2] = {k1, k2}; + return btree_update(&head->h, &btree_geo128, + (unsigned long *)&key, val); +} + +static inline void *btree_remove128(struct btree_head128 *head, u64 k1, u64 k2) +{ + u64 key[2] = {k1, k2}; + return btree_remove(&head->h, &btree_geo128, (unsigned long *)&key); +} + +static inline void *btree_last128(struct btree_head128 *head, u64 *k1, u64 *k2) +{ + u64 key[2]; + void *val; + + val = btree_last(&head->h, &btree_geo128, (unsigned long *)&key[0]); + if (val) { + *k1 = key[0]; + *k2 = key[1]; + } + + return val; +} + +static inline int btree_merge128(struct btree_head128 *target, + struct btree_head128 *victim, + gfp_t gfp) +{ + return btree_merge(&target->h, &victim->h, &btree_geo128, gfp); +} + +void visitor128(void *elem, unsigned long opaque, unsigned long *__key, + size_t index, void *__func); + +typedef void (*visitor128_t)(void *elem, unsigned long opaque, + u64 key1, u64 key2, size_t index); + +static inline size_t btree_visitor128(struct btree_head128 *head, + unsigned long opaque, + visitor128_t func2) +{ + return btree_visitor(&head->h, &btree_geo128, opaque, + visitor128, func2); +} + +static inline size_t btree_grim_visitor128(struct btree_head128 *head, + unsigned long opaque, + visitor128_t func2) +{ + return btree_grim_visitor(&head->h, &btree_geo128, opaque, + visitor128, func2); +} + +#define btree_for_each_safe128(head, k1, k2, val) \ + for (val = btree_last128(head, &k1, &k2); \ + val; \ + val = btree_get_prev128(head, &k1, &k2)) + diff --git a/include/linux/btree-type.h b/include/linux/btree-type.h new file mode 100644 index 000000000000..9a1147ef8563 --- /dev/null +++ b/include/linux/btree-type.h @@ -0,0 +1,147 @@ +#define __BTREE_TP(pfx, type, sfx) pfx ## type ## sfx +#define _BTREE_TP(pfx, type, sfx) __BTREE_TP(pfx, type, sfx) +#define BTREE_TP(pfx) _BTREE_TP(pfx, BTREE_TYPE_SUFFIX,) +#define BTREE_FN(name) BTREE_TP(btree_ ## name) +#define BTREE_TYPE_HEAD BTREE_TP(struct btree_head) +#define VISITOR_FN BTREE_TP(visitor) +#define VISITOR_FN_T _BTREE_TP(visitor, BTREE_TYPE_SUFFIX, _t) + +BTREE_TYPE_HEAD { + struct btree_head h; +}; + +static inline void BTREE_FN(init_mempool)(BTREE_TYPE_HEAD *head, + mempool_t *mempool) +{ + btree_init_mempool(&head->h, mempool); +} + +static inline int BTREE_FN(init)(BTREE_TYPE_HEAD *head) +{ + return btree_init(&head->h); +} + +static inline void BTREE_FN(destroy)(BTREE_TYPE_HEAD *head) +{ + btree_destroy(&head->h); +} + +static inline int BTREE_FN(merge)(BTREE_TYPE_HEAD *target, + BTREE_TYPE_HEAD *victim, + gfp_t gfp) +{ + return btree_merge(&target->h, &victim->h, BTREE_TYPE_GEO, gfp); +} + +#if (BITS_PER_LONG > BTREE_TYPE_BITS) +static inline void *BTREE_FN(lookup)(BTREE_TYPE_HEAD *head, BTREE_KEYTYPE key) +{ + unsigned long _key = key; + return btree_lookup(&head->h, BTREE_TYPE_GEO, &_key); +} + +static inline int BTREE_FN(insert)(BTREE_TYPE_HEAD *head, BTREE_KEYTYPE key, + void *val, gfp_t gfp) +{ + unsigned long _key = key; + return btree_insert(&head->h, BTREE_TYPE_GEO, &_key, val, gfp); +} + +static inline int BTREE_FN(update)(BTREE_TYPE_HEAD *head, BTREE_KEYTYPE key, + void *val) +{ + unsigned long _key = key; + return btree_update(&head->h, BTREE_TYPE_GEO, &_key, val); +} + +static inline void *BTREE_FN(remove)(BTREE_TYPE_HEAD *head, BTREE_KEYTYPE key) +{ + unsigned long _key = key; + return btree_remove(&head->h, BTREE_TYPE_GEO, &_key); +} + +static inline void *BTREE_FN(last)(BTREE_TYPE_HEAD *head, BTREE_KEYTYPE *key) +{ + unsigned long _key; + void *val = btree_last(&head->h, BTREE_TYPE_GEO, &_key); + if (val) + *key = _key; + return val; +} + +static inline void *BTREE_FN(get_prev)(BTREE_TYPE_HEAD *head, BTREE_KEYTYPE *key) +{ + unsigned long _key = *key; + void *val = btree_get_prev(&head->h, BTREE_TYPE_GEO, &_key); + if (val) + *key = _key; + return val; +} +#else +static inline void *BTREE_FN(lookup)(BTREE_TYPE_HEAD *head, BTREE_KEYTYPE key) +{ + return btree_lookup(&head->h, BTREE_TYPE_GEO, (unsigned long *)&key); +} + +static inline int BTREE_FN(insert)(BTREE_TYPE_HEAD *head, BTREE_KEYTYPE key, + void *val, gfp_t gfp) +{ + return btree_insert(&head->h, BTREE_TYPE_GEO, (unsigned long *)&key, + val, gfp); +} + +static inline int BTREE_FN(update)(BTREE_TYPE_HEAD *head, BTREE_KEYTYPE key, + void *val) +{ + return btree_update(&head->h, BTREE_TYPE_GEO, (unsigned long *)&key, val); +} + +static inline void *BTREE_FN(remove)(BTREE_TYPE_HEAD *head, BTREE_KEYTYPE key) +{ + return btree_remove(&head->h, BTREE_TYPE_GEO, (unsigned long *)&key); +} + +static inline void *BTREE_FN(last)(BTREE_TYPE_HEAD *head, BTREE_KEYTYPE *key) +{ + return btree_last(&head->h, BTREE_TYPE_GEO, (unsigned long *)key); +} + +static inline void *BTREE_FN(get_prev)(BTREE_TYPE_HEAD *head, BTREE_KEYTYPE *key) +{ + return btree_get_prev(&head->h, BTREE_TYPE_GEO, (unsigned long *)key); +} +#endif + +void VISITOR_FN(void *elem, unsigned long opaque, unsigned long *key, + size_t index, void *__func); + +typedef void (*VISITOR_FN_T)(void *elem, unsigned long opaque, + BTREE_KEYTYPE key, size_t index); + +static inline size_t BTREE_FN(visitor)(BTREE_TYPE_HEAD *head, + unsigned long opaque, + VISITOR_FN_T func2) +{ + return btree_visitor(&head->h, BTREE_TYPE_GEO, opaque, + visitorl, func2); +} + +static inline size_t BTREE_FN(grim_visitor)(BTREE_TYPE_HEAD *head, + unsigned long opaque, + VISITOR_FN_T func2) +{ + return btree_grim_visitor(&head->h, BTREE_TYPE_GEO, opaque, + visitorl, func2); +} + +#undef VISITOR_FN +#undef VISITOR_FN_T +#undef __BTREE_TP +#undef _BTREE_TP +#undef BTREE_TP +#undef BTREE_FN +#undef BTREE_TYPE_HEAD +#undef BTREE_TYPE_SUFFIX +#undef BTREE_TYPE_GEO +#undef BTREE_KEYTYPE +#undef BTREE_TYPE_BITS diff --git a/include/linux/btree.h b/include/linux/btree.h new file mode 100644 index 000000000000..65b5bb058324 --- /dev/null +++ b/include/linux/btree.h @@ -0,0 +1,243 @@ +#ifndef BTREE_H +#define BTREE_H + +#include +#include + +/** + * DOC: B+Tree basics + * + * A B+Tree is a data structure for looking up arbitrary (currently allowing + * unsigned long, u32, u64 and 2 * u64) keys into pointers. The data structure + * is described at http://en.wikipedia.org/wiki/B-tree, we currently do not + * use binary search to find the key on lookups. + * + * Each B+Tree consists of a head, that contains bookkeeping information and + * a variable number (starting with zero) nodes. Each node contains the keys + * and pointers to sub-nodes, or, for leaf nodes, the keys and values for the + * tree entries. + * + * Each node in this implementation has the following layout: + * [key1, key2, ..., keyN] [val1, val2, ..., valN] + * + * Each key here is an array of unsigned longs, geo->no_longs in total. The + * number of keys and values (N) is geo->no_pairs. + */ + +/** + * struct btree_head - btree head + * + * @node: the first node in the tree + * @mempool: mempool used for node allocations + * @height: current of the tree + */ +struct btree_head { + unsigned long *node; + mempool_t *mempool; + int height; +}; + +/* btree geometry */ +struct btree_geo; + +/** + * btree_alloc - allocate function for the mempool + * @gfp_mask: gfp mask for the allocation + * @pool_data: unused + */ +void *btree_alloc(gfp_t gfp_mask, void *pool_data); + +/** + * btree_free - free function for the mempool + * @element: the element to free + * @pool_data: unused + */ +void btree_free(void *element, void *pool_data); + +/** + * btree_init_mempool - initialise a btree with given mempool + * + * @head: the btree head to initialise + * @mempool: the mempool to use + * + * When this function is used, there is no need to destroy + * the mempool. + */ +void btree_init_mempool(struct btree_head *head, mempool_t *mempool); + +/** + * btree_init - initialise a btree + * + * @head: the btree head to initialise + * + * This function allocates the memory pool that the + * btree needs. Returns zero or a negative error code + * (-%ENOMEM) when memory allocation fails. + * + */ +int __must_check btree_init(struct btree_head *head); + +/** + * btree_destroy - destroy mempool + * + * @head: the btree head to destroy + * + * This function destroys the internal memory pool, use only + * when using btree_init(), not with btree_init_mempool(). + */ +void btree_destroy(struct btree_head *head); + +/** + * btree_lookup - look up a key in the btree + * + * @head: the btree to look in + * @geo: the btree geometry + * @key: the key to look up + * + * This function returns the value for the given key, or %NULL. + */ +void *btree_lookup(struct btree_head *head, struct btree_geo *geo, + unsigned long *key); + +/** + * btree_insert - insert an entry into the btree + * + * @head: the btree to add to + * @geo: the btree geometry + * @key: the key to add (must not already be present) + * @val: the value to add (must not be %NULL) + * @gfp: allocation flags for node allocations + * + * This function returns 0 if the item could be added, or an + * error code if it failed (may fail due to memory pressure). + */ +int __must_check btree_insert(struct btree_head *head, struct btree_geo *geo, + unsigned long *key, void *val, gfp_t gfp); +/** + * btree_update - update an entry in the btree + * + * @head: the btree to update + * @geo: the btree geometry + * @key: the key to update + * @val: the value to change it to (must not be %NULL) + * + * This function returns 0 if the update was successful, or + * -%ENOENT if the key could not be found. + */ +int btree_update(struct btree_head *head, struct btree_geo *geo, + unsigned long *key, void *val); +/** + * btree_remove - remove an entry from the btree + * + * @head: the btree to update + * @geo: the btree geometry + * @key: the key to remove + * + * This function returns the removed entry, or %NULL if the key + * could not be found. + */ +void *btree_remove(struct btree_head *head, struct btree_geo *geo, + unsigned long *key); + +/** + * btree_merge - merge two btrees + * + * @target: the tree that gets all the entries + * @victim: the tree that gets merged into @target + * @geo: the btree geometry + * @gfp: allocation flags + * + * The two trees @target and @victim may not contain the same keys, + * that is a bug and triggers a BUG(). This function returns zero + * if the trees were merged successfully, and may return a failure + * when memory allocation fails, in which case both trees might have + * been partially merged, i.e. some entries have been moved from + * @victim to @target. + */ +int btree_merge(struct btree_head *target, struct btree_head *victim, + struct btree_geo *geo, gfp_t gfp); + +/** + * btree_last - get last entry in btree + * + * @head: btree head + * @geo: btree geometry + * @key: last key + * + * Returns the last entry in the btree, and sets @key to the key + * of that entry; returns NULL if the tree is empty, in that case + * key is not changed. + */ +void *btree_last(struct btree_head *head, struct btree_geo *geo, + unsigned long *key); + +/** + * btree_get_prev - get previous entry + * + * @head: btree head + * @geo: btree geometry + * @key: pointer to key + * + * The function returns the next item right before the value pointed to by + * @key, and updates @key with its key, or returns %NULL when there is no + * entry with a key smaller than the given key. + */ +void *btree_get_prev(struct btree_head *head, struct btree_geo *geo, + unsigned long *key); + + +/* internal use, use btree_visitor{l,32,64,128} */ +size_t btree_visitor(struct btree_head *head, struct btree_geo *geo, + unsigned long opaque, + void (*func)(void *elem, unsigned long opaque, + unsigned long *key, size_t index, + void *func2), + void *func2); + +/* internal use, use btree_grim_visitor{l,32,64,128} */ +size_t btree_grim_visitor(struct btree_head *head, struct btree_geo *geo, + unsigned long opaque, + void (*func)(void *elem, unsigned long opaque, + unsigned long *key, + size_t index, void *func2), + void *func2); + + +#include + +extern struct btree_geo btree_geo32; +#define BTREE_TYPE_SUFFIX l +#define BTREE_TYPE_BITS BITS_PER_LONG +#define BTREE_TYPE_GEO &btree_geo32 +#define BTREE_KEYTYPE unsigned long +#include + +#define btree_for_each_safel(head, key, val) \ + for (val = btree_lastl(head, &key); \ + val; \ + val = btree_get_prevl(head, &key)) + +#define BTREE_TYPE_SUFFIX 32 +#define BTREE_TYPE_BITS 32 +#define BTREE_TYPE_GEO &btree_geo32 +#define BTREE_KEYTYPE u32 +#include + +#define btree_for_each_safe32(head, key, val) \ + for (val = btree_last32(head, &key); \ + val; \ + val = btree_get_prev32(head, &key)) + +extern struct btree_geo btree_geo64; +#define BTREE_TYPE_SUFFIX 64 +#define BTREE_TYPE_BITS 64 +#define BTREE_TYPE_GEO &btree_geo64 +#define BTREE_KEYTYPE u64 +#include + +#define btree_for_each_safe64(head, key, val) \ + for (val = btree_last64(head, &key); \ + val; \ + val = btree_get_prev64(head, &key)) + +#endif -- cgit v1.2.3 From e169cfbef46d62e042614ffafa8880eed1d894bb Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Mon, 23 Nov 2009 14:53:09 -0700 Subject: of/flattree: merge find_flat_dt_string and initial_boot_params Merge common code between Microblaze and PowerPC. Signed-off-by: Grant Likely Reviewed-by: Wolfram Sang Tested-by: Michal Simek --- include/linux/of_fdt.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h index 41d432b13553..d1a79f3da789 100644 --- a/include/linux/of_fdt.h +++ b/include/linux/of_fdt.h @@ -57,7 +57,11 @@ struct boot_param_header { u32 dt_struct_size; /* size of the DT structure block */ }; +/* TBD: Temporary export of fdt globals - remove when code fully merged */ +extern struct boot_param_header *initial_boot_params; + /* For scanning the flat device-tree at boot time */ +extern char *find_flat_dt_string(u32 offset); extern int __init of_scan_flat_dt(int (*it)(unsigned long node, const char *uname, int depth, void *data), -- cgit v1.2.3 From 31a6a87dfc34fbf02aef9a160adf558ec56d3ccd Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Mon, 23 Nov 2009 19:49:38 -0700 Subject: of/flattree: remove __init annotations from the header file __init annotation belongs in the .c file, not the header. Signed-off-by: Grant Likely Reviewed-by: Wolfram Sang Tested-by: Michal Simek --- include/linux/of_fdt.h | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h index d1a79f3da789..81231e04e8f3 100644 --- a/include/linux/of_fdt.h +++ b/include/linux/of_fdt.h @@ -62,15 +62,13 @@ extern struct boot_param_header *initial_boot_params; /* For scanning the flat device-tree at boot time */ extern char *find_flat_dt_string(u32 offset); -extern int __init of_scan_flat_dt(int (*it)(unsigned long node, - const char *uname, int depth, - void *data), - void *data); -extern void __init *of_get_flat_dt_prop(unsigned long node, const char *name, - unsigned long *size); -extern int __init of_flat_dt_is_compatible(unsigned long node, - const char *name); -extern unsigned long __init of_get_flat_dt_root(void); +extern int of_scan_flat_dt(int (*it)(unsigned long node, const char *uname, + int depth, void *data), + void *data); +extern void *of_get_flat_dt_prop(unsigned long node, const char *name, + unsigned long *size); +extern int of_flat_dt_is_compatible(unsigned long node, const char *name); +extern unsigned long of_get_flat_dt_root(void); /* Other Prototypes */ extern void finish_device_tree(void); -- cgit v1.2.3 From bbd33931a08362f78266a4016211a35947b91041 Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Mon, 23 Nov 2009 20:07:00 -0700 Subject: of/flattree: Merge unflatten_dt_node Merge common code between PowerPC and MicroBlaze Signed-off-by: Grant Likely Reviewed-by: Wolfram Sang Tested-by: Michal Simek --- include/linux/of_fdt.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h index 81231e04e8f3..ace9068e07e8 100644 --- a/include/linux/of_fdt.h +++ b/include/linux/of_fdt.h @@ -69,6 +69,10 @@ extern void *of_get_flat_dt_prop(unsigned long node, const char *name, unsigned long *size); extern int of_flat_dt_is_compatible(unsigned long node, const char *name); extern unsigned long of_get_flat_dt_root(void); +extern unsigned long unflatten_dt_node(unsigned long mem, unsigned long *p, + struct device_node *dad, + struct device_node ***allnextpp, + unsigned long fpsize); /* Other Prototypes */ extern void finish_device_tree(void); -- cgit v1.2.3 From 41f880091c15b039ffcc8b3d831656b81517a6d3 Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Mon, 23 Nov 2009 20:07:01 -0700 Subject: of/flattree: Merge unflatten_device_tree Merge common code between PowerPC and MicroBlaze Signed-off-by: Grant Likely Reviewed-by: Wolfram Sang Tested-by: Michal Simek --- include/linux/of.h | 3 +++ include/linux/of_fdt.h | 4 ---- 2 files changed, 3 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index e7facd8fbce8..bec215792c4f 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -63,6 +63,9 @@ struct device_node { #endif }; +/* Pointer for first entry in chain of all nodes. */ +extern struct device_node *allnodes; + static inline int of_node_check_flag(struct device_node *n, unsigned long flag) { return test_bit(flag, &n->_flags); diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h index ace9068e07e8..81231e04e8f3 100644 --- a/include/linux/of_fdt.h +++ b/include/linux/of_fdt.h @@ -69,10 +69,6 @@ extern void *of_get_flat_dt_prop(unsigned long node, const char *name, unsigned long *size); extern int of_flat_dt_is_compatible(unsigned long node, const char *name); extern unsigned long of_get_flat_dt_root(void); -extern unsigned long unflatten_dt_node(unsigned long mem, unsigned long *p, - struct device_node *dad, - struct device_node ***allnextpp, - unsigned long fpsize); /* Other Prototypes */ extern void finish_device_tree(void); -- cgit v1.2.3 From 2be09cb993826b52c9fc1d44747c20dd43a50038 Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Mon, 23 Nov 2009 20:16:46 -0700 Subject: of: remove special case definition of of_read_ulong() Special case of of_read_ulong() was defined for PPC32 to toss away all but the last 32 bits when a large number value was read, and the 'normal' version for ppc64 just #defined of_read_ulong to of_read_number which causes compiler warnings on MicroBlaze and other 32 bit architectures because it returns a u64 instead of a ulong. This patch fixes the problem by defining a common implementation of of_read_ulong() that works everywhere. Signed-off-by: Grant Likely Reviewed-by: Wolfram Sang Tested-by: Michal Simek --- include/linux/of.h | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index bec215792c4f..d4c014a35ea5 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -113,14 +113,11 @@ static inline u64 of_read_number(const u32 *cell, int size) } /* Like of_read_number, but we want an unsigned long result */ -#ifdef CONFIG_PPC32 static inline unsigned long of_read_ulong(const u32 *cell, int size) { - return cell[size-1]; + /* toss away upper bits if unsigned long is smaller than u64 */ + return of_read_number(cell, size); } -#else -#define of_read_ulong(cell, size) of_read_number(cell, size) -#endif #include -- cgit v1.2.3 From d2eecb03936878ec574ade5532fa83df7d75dde7 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Mon, 7 Dec 2009 10:36:20 -0500 Subject: ext4: Use slab allocator for sub-page sized allocations Now that the SLUB seems to be fixed so that it respects the requested alignment, use kmem_cache_alloc() to allocator if the block size of the buffer heads to be allocated is less than the page size. Previously, we were using 16k page on a Power system for each buffer, even when the file system was using 1k or 4k block size. Signed-off-by: "Theodore Ts'o" --- include/linux/jbd2.h | 11 ++--------- 1 file changed, 2 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 638ce4554c76..8ada2a129d08 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -69,15 +69,8 @@ extern u8 jbd2_journal_enable_debug; #define jbd_debug(f, a...) /**/ #endif -static inline void *jbd2_alloc(size_t size, gfp_t flags) -{ - return (void *)__get_free_pages(flags, get_order(size)); -} - -static inline void jbd2_free(void *ptr, size_t size) -{ - free_pages((unsigned long)ptr, get_order(size)); -}; +extern void *jbd2_alloc(size_t size, gfp_t flags); +extern void jbd2_free(void *ptr, size_t size); #define JBD2_MIN_JOURNAL_BLOCKS 1024 -- cgit v1.2.3 From 85438592f179c126ad4cb9a280046d4f0a501e6d Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 18 Nov 2009 17:53:21 +0900 Subject: percpu: remove compile warnings caused by __verify_pcpu_ptr() If percpu pointer is const, __verify_pcpu_ptr() triggers warnings like the following. drivers/net/loopback.c: In function 'loopback_get_stats': drivers/net/loopback.c:109: warning: initialization discards qualifiers from pointer target type Fix it by adding const to the verification target pointer used in __verify_pcpu_ptr(). Signed-off-by: Tejun Heo Reported-by: Stephen Rothwell --- include/linux/percpu-defs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h index 1fa36eb54b6a..68567c0b3a5d 100644 --- a/include/linux/percpu-defs.h +++ b/include/linux/percpu-defs.h @@ -24,7 +24,7 @@ * input parameter is a percpu pointer. */ #define __verify_pcpu_ptr(ptr) do { \ - void __percpu *__vpp_verify = (typeof(ptr))NULL; \ + const void __percpu *__vpp_verify = (typeof(ptr))NULL; \ (void)__vpp_verify; \ } while (0) -- cgit v1.2.3 From f7b3a8355ba6cad251297844a0bdd08898ea36e0 Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Tue, 24 Nov 2009 03:26:58 -0700 Subject: of/flattree: Merge early_init_dt_check_for_initrd() Merge common code between PowerPC and Microblaze Signed-off-by: Grant Likely Tested-by: Wolfram Sang Acked-by: Benjamin Herrenschmidt --- include/linux/of_fdt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h index 81231e04e8f3..ec2db8278c3f 100644 --- a/include/linux/of_fdt.h +++ b/include/linux/of_fdt.h @@ -69,6 +69,7 @@ extern void *of_get_flat_dt_prop(unsigned long node, const char *name, unsigned long *size); extern int of_flat_dt_is_compatible(unsigned long node, const char *name); extern unsigned long of_get_flat_dt_root(void); +extern void early_init_dt_check_for_initrd(unsigned long node); /* Other Prototypes */ extern void finish_device_tree(void); -- cgit v1.2.3 From f00abd94918c9780f9d2d961fc0e419c11457922 Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Tue, 24 Nov 2009 03:27:10 -0700 Subject: of/flattree: Merge earlyinit_dt_scan_root() Merge common code between PowerPC and Microblaze Signed-off-by: Grant Likely Acked-by: Benjamin Herrenschmidt Tested-by: Wolfram Sang --- include/linux/of_fdt.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h index ec2db8278c3f..828c3cdaea78 100644 --- a/include/linux/of_fdt.h +++ b/include/linux/of_fdt.h @@ -58,6 +58,8 @@ struct boot_param_header { }; /* TBD: Temporary export of fdt globals - remove when code fully merged */ +extern int __initdata dt_root_addr_cells; +extern int __initdata dt_root_size_cells; extern struct boot_param_header *initial_boot_params; /* For scanning the flat device-tree at boot time */ @@ -71,6 +73,10 @@ extern int of_flat_dt_is_compatible(unsigned long node, const char *name); extern unsigned long of_get_flat_dt_root(void); extern void early_init_dt_check_for_initrd(unsigned long node); +/* Early flat tree scan hooks */ +extern int early_init_dt_scan_root(unsigned long node, const char *uname, + int depth, void *data); + /* Other Prototypes */ extern void finish_device_tree(void); extern void unflatten_device_tree(void); -- cgit v1.2.3 From 83f7a06eb479e2aeb83536e77a2cb14cc2285e32 Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Tue, 24 Nov 2009 03:37:56 -0700 Subject: of/flattree: merge dt_mem_next_cell Merge common code between PowerPC and Microblaze Signed-off-by: Grant Likely Acked-by: Benjamin Herrenschmidt Tested-by: Wolfram Sang --- include/linux/of_fdt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h index 828c3cdaea78..d1a37e56031e 100644 --- a/include/linux/of_fdt.h +++ b/include/linux/of_fdt.h @@ -72,6 +72,7 @@ extern void *of_get_flat_dt_prop(unsigned long node, const char *name, extern int of_flat_dt_is_compatible(unsigned long node, const char *name); extern unsigned long of_get_flat_dt_root(void); extern void early_init_dt_check_for_initrd(unsigned long node); +extern u64 dt_mem_next_cell(int s, u32 **cellp); /* Early flat tree scan hooks */ extern int early_init_dt_scan_root(unsigned long node, const char *uname, -- cgit v1.2.3 From 86e032213424958b45564d0cc96b3316641a49d3 Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Thu, 10 Dec 2009 23:42:21 -0700 Subject: of/flattree: merge early_init_dt_scan_chosen() Merge common code between PowerPC and Microblaze. This patch splits the arch-specific stuff out into a new function, early_init_dt_scan_chosen_arch(). Signed-off-by: Grant Likely Tested-by: Wolfram Sang Acked-by: Benjamin Herrenschmidt --- include/linux/of_fdt.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h index d1a37e56031e..8118d4559dd5 100644 --- a/include/linux/of_fdt.h +++ b/include/linux/of_fdt.h @@ -71,6 +71,9 @@ extern void *of_get_flat_dt_prop(unsigned long node, const char *name, unsigned long *size); extern int of_flat_dt_is_compatible(unsigned long node, const char *name); extern unsigned long of_get_flat_dt_root(void); +extern void early_init_dt_scan_chosen_arch(unsigned long node); +extern int early_init_dt_scan_chosen(unsigned long node, const char *uname, + int depth, void *data); extern void early_init_dt_check_for_initrd(unsigned long node); extern u64 dt_mem_next_cell(int s, u32 **cellp); -- cgit v1.2.3 From 9dfc6e68bfe6ee452efb1a4e9ca26a9007f2b864 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Fri, 18 Dec 2009 16:26:20 -0600 Subject: SLUB: Use this_cpu operations in slub Using per cpu allocations removes the needs for the per cpu arrays in the kmem_cache struct. These could get quite big if we have to support systems with thousands of cpus. The use of this_cpu_xx operations results in: 1. The size of kmem_cache for SMP configuration shrinks since we will only need 1 pointer instead of NR_CPUS. The same pointer can be used by all processors. Reduces cache footprint of the allocator. 2. We can dynamically size kmem_cache according to the actual nodes in the system meaning less memory overhead for configurations that may potentially support up to 1k NUMA nodes / 4k cpus. 3. We can remove the diddle widdle with allocating and releasing of kmem_cache_cpu structures when bringing up and shutting down cpus. The cpu alloc logic will do it all for us. Removes some portions of the cpu hotplug functionality. 4. Fastpath performance increases since per cpu pointer lookups and address calculations are avoided. V7-V8 - Convert missed get_cpu_slab() under CONFIG_SLUB_STATS Signed-off-by: Christoph Lameter Signed-off-by: Pekka Enberg --- include/linux/slub_def.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 1e14beb23f9b..17ebe0f89bf3 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -69,6 +69,7 @@ struct kmem_cache_order_objects { * Slab cache management. */ struct kmem_cache { + struct kmem_cache_cpu *cpu_slab; /* Used for retriving partial slabs etc */ unsigned long flags; int size; /* The size of an object including meta data */ @@ -104,11 +105,6 @@ struct kmem_cache { int remote_node_defrag_ratio; struct kmem_cache_node *node[MAX_NUMNODES]; #endif -#ifdef CONFIG_SMP - struct kmem_cache_cpu *cpu_slab[NR_CPUS]; -#else - struct kmem_cache_cpu cpu_slab; -#endif }; /* -- cgit v1.2.3 From 756dee75872a2a764b478e18076360b8a4ec9045 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Fri, 18 Dec 2009 16:26:21 -0600 Subject: SLUB: Get rid of dynamic DMA kmalloc cache allocation Dynamic DMA kmalloc cache allocation is troublesome since the new percpu allocator does not support allocations in atomic contexts. Reserve some statically allocated kmalloc_cpu structures instead. Signed-off-by: Christoph Lameter Signed-off-by: Pekka Enberg --- include/linux/slub_def.h | 19 +++++++++++-------- 1 file changed, 11 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 17ebe0f89bf3..a78fb4ac2015 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -131,11 +131,21 @@ struct kmem_cache { #define SLUB_PAGE_SHIFT (PAGE_SHIFT + 2) +#ifdef CONFIG_ZONE_DMA +#define SLUB_DMA __GFP_DMA +/* Reserve extra caches for potential DMA use */ +#define KMALLOC_CACHES (2 * SLUB_PAGE_SHIFT - 6) +#else +/* Disable DMA functionality */ +#define SLUB_DMA (__force gfp_t)0 +#define KMALLOC_CACHES SLUB_PAGE_SHIFT +#endif + /* * We keep the general caches in an array of slab caches that are used for * 2^x bytes of allocations. */ -extern struct kmem_cache kmalloc_caches[SLUB_PAGE_SHIFT]; +extern struct kmem_cache kmalloc_caches[KMALLOC_CACHES]; /* * Sorry that the following has to be that ugly but some versions of GCC @@ -203,13 +213,6 @@ static __always_inline struct kmem_cache *kmalloc_slab(size_t size) return &kmalloc_caches[index]; } -#ifdef CONFIG_ZONE_DMA -#define SLUB_DMA __GFP_DMA -#else -/* Disable DMA functionality */ -#define SLUB_DMA (__force gfp_t)0 -#endif - void *kmem_cache_alloc(struct kmem_cache *, gfp_t); void *__kmalloc(size_t size, gfp_t flags); -- cgit v1.2.3 From ff12059ed14b0773d7bbef86f98218ada6c20770 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Fri, 18 Dec 2009 16:26:22 -0600 Subject: SLUB: this_cpu: Remove slub kmem_cache fields Remove the fields in struct kmem_cache_cpu that were used to cache data from struct kmem_cache when they were in different cachelines. The cacheline that holds the per cpu array pointer now also holds these values. We can cut down the struct kmem_cache_cpu size to almost half. The get_freepointer() and set_freepointer() functions that used to be only intended for the slow path now are also useful for the hot path since access to the size field does not require accessing an additional cacheline anymore. This results in consistent use of functions for setting the freepointer of objects throughout SLUB. Also we initialize all possible kmem_cache_cpu structures when a slab is created. No need to initialize them when a processor or node comes online. Signed-off-by: Christoph Lameter Signed-off-by: Pekka Enberg --- include/linux/slub_def.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index a78fb4ac2015..0249d4175bac 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -38,8 +38,6 @@ struct kmem_cache_cpu { void **freelist; /* Pointer to first free per cpu object */ struct page *page; /* The slab from which we are allocating */ int node; /* The node of the page (or -1 for debug) */ - unsigned int offset; /* Freepointer offset (in word units) */ - unsigned int objsize; /* Size of an object (from kmem_cache) */ #ifdef CONFIG_SLUB_STATS unsigned stat[NR_SLUB_STAT_ITEMS]; #endif -- cgit v1.2.3 From 0f78231bffb868a30e8533aace142213266bb811 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 1 Dec 2009 13:37:02 +0100 Subject: mac80211: enable spatial multiplexing powersave Enable spatial multiplexing in mac80211 by telling the driver what to do and, where necessary, sending action frames to the AP to update the requested SMPS mode. Also includes a trivial implementation for hwsim that just logs the requested mode. For now, the userspace interface is in debugfs only, and let you toggle the requested mode at any time. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/linux/ieee80211.h | 25 ++++++++++++++++++++++++- 1 file changed, 24 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index d9724a28c0c2..e8d43d0ff2c3 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -707,6 +707,10 @@ struct ieee80211_mgmt { u8 action; u8 trans_id[WLAN_SA_QUERY_TR_ID_LEN]; } __attribute__ ((packed)) sa_query; + struct { + u8 action; + u8 smps_control; + } __attribute__ ((packed)) ht_smps; } u; } __attribute__ ((packed)) action; } u; @@ -824,6 +828,7 @@ struct ieee80211_ht_cap { #define IEEE80211_HT_CAP_LDPC_CODING 0x0001 #define IEEE80211_HT_CAP_SUP_WIDTH_20_40 0x0002 #define IEEE80211_HT_CAP_SM_PS 0x000C +#define IEEE80211_HT_CAP_SM_PS_SHIFT 2 #define IEEE80211_HT_CAP_GRN_FLD 0x0010 #define IEEE80211_HT_CAP_SGI_20 0x0020 #define IEEE80211_HT_CAP_SGI_40 0x0040 @@ -839,6 +844,7 @@ struct ieee80211_ht_cap { /* 802.11n HT capability AMPDU settings (for ampdu_params_info) */ #define IEEE80211_HT_AMPDU_PARM_FACTOR 0x03 #define IEEE80211_HT_AMPDU_PARM_DENSITY 0x1C +#define IEEE80211_HT_AMPDU_PARM_DENSITY_SHIFT 2 /* * Maximum length of AMPDU that the STA can receive. @@ -922,12 +928,17 @@ struct ieee80211_ht_info { #define IEEE80211_MAX_AMPDU_BUF 0x40 -/* Spatial Multiplexing Power Save Modes */ +/* Spatial Multiplexing Power Save Modes (for capability) */ #define WLAN_HT_CAP_SM_PS_STATIC 0 #define WLAN_HT_CAP_SM_PS_DYNAMIC 1 #define WLAN_HT_CAP_SM_PS_INVALID 2 #define WLAN_HT_CAP_SM_PS_DISABLED 3 +/* for SM power control field lower two bits */ +#define WLAN_HT_SMPS_CONTROL_DISABLED 0 +#define WLAN_HT_SMPS_CONTROL_STATIC 1 +#define WLAN_HT_SMPS_CONTROL_DYNAMIC 3 + /* Authentication algorithms */ #define WLAN_AUTH_OPEN 0 #define WLAN_AUTH_SHARED_KEY 1 @@ -1150,6 +1161,18 @@ enum ieee80211_spectrum_mgmt_actioncode { WLAN_ACTION_SPCT_CHL_SWITCH = 4, }; +/* HT action codes */ +enum ieee80211_ht_actioncode { + WLAN_HT_ACTION_NOTIFY_CHANWIDTH = 0, + WLAN_HT_ACTION_SMPS = 1, + WLAN_HT_ACTION_PSMP = 2, + WLAN_HT_ACTION_PCO_PHASE = 3, + WLAN_HT_ACTION_CSI = 4, + WLAN_HT_ACTION_NONCOMPRESSED_BF = 5, + WLAN_HT_ACTION_COMPRESSED_BF = 6, + WLAN_HT_ACTION_ASEL_IDX_FEEDBACK = 7, +}; + /* Security key length */ enum ieee80211_key_len { WLAN_KEY_LEN_WEP40 = 5, -- cgit v1.2.3 From 9da3e068142ec7856b2f13261dcf0660fad32b61 Mon Sep 17 00:00:00 2001 From: "Luis R. Rodriguez" Date: Mon, 7 Dec 2009 15:57:50 -0500 Subject: mac80211: only bother printing highest data rate on debugfs if its set IEEE-802.11n spec says the RX highest data rate field does not specify the highest supported RX data rate if its not set. Ignore it if not set then. Refer to section 7.3.56.4 Cc: johannes@sipsolutions.net Signed-off-by: Luis R. Rodriguez Signed-off-by: John W. Linville --- include/linux/ieee80211.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index e8d43d0ff2c3..098bedcde9bb 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -775,7 +775,10 @@ struct ieee80211_bar { /** * struct ieee80211_mcs_info - MCS information * @rx_mask: RX mask - * @rx_highest: highest supported RX rate + * @rx_highest: highest supported RX rate. If set represents + * the highest supported RX data rate in units of 1 Mbps. + * If this field is 0 this value should not be used to + * consider the highest RX data rate supported. * @tx_params: TX parameters */ struct ieee80211_mcs_info { -- cgit v1.2.3 From 31d12926e37291970dd4f6e9940df3897766a81d Mon Sep 17 00:00:00 2001 From: laurent chavey Date: Tue, 15 Dec 2009 11:15:28 +0000 Subject: net: Add rtnetlink init_rcvwnd to set the TCP initial receive window Add rtnetlink init_rcvwnd to set the TCP initial receive window size advertised by passive and active TCP connections. The current Linux TCP implementation limits the advertised TCP initial receive window to the one prescribed by slow start. For short lived TCP connections used for transaction type of traffic (i.e. http requests), bounding the advertised TCP initial receive window results in increased latency to complete the transaction. Support for setting initial congestion window is already supported using rtnetlink init_cwnd, but the feature is useless without the ability to set a larger TCP initial receive window. The rtnetlink init_rcvwnd allows increasing the TCP initial receive window, allowing TCP connection to advertise larger TCP receive window than the ones bounded by slow start. Signed-off-by: Laurent Chavey Signed-off-by: David S. Miller --- include/linux/rtnetlink.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 05330fc5b436..9590364fe8b5 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -362,6 +362,8 @@ enum { #define RTAX_FEATURES RTAX_FEATURES RTAX_RTO_MIN, #define RTAX_RTO_MIN RTAX_RTO_MIN + RTAX_INITRWND, +#define RTAX_INITRWND RTAX_INITRWND __RTAX_MAX }; -- cgit v1.2.3 From e5cd6fe391aa8c93560bb7ffdfe334cf4d0a02e4 Mon Sep 17 00:00:00 2001 From: Octavian Purdila Date: Sat, 26 Dec 2009 11:51:00 +0000 Subject: llc: add support for LLC_OPT_PKTINFO Signed-off-by: Octavian Purdila Signed-off-by: David S. Miller --- include/linux/llc.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/llc.h b/include/linux/llc.h index 7733585603f1..ad7074ba81af 100644 --- a/include/linux/llc.h +++ b/include/linux/llc.h @@ -36,6 +36,7 @@ enum llc_sockopts { LLC_OPT_BUSY_TMR_EXP, /* busy state expire time (secs). */ LLC_OPT_TX_WIN, /* tx window size. */ LLC_OPT_RX_WIN, /* rx window size. */ + LLC_OPT_PKTINFO, /* ancillary packet information. */ LLC_OPT_MAX }; @@ -70,6 +71,12 @@ enum llc_sockopts { #define LLC_SAP_RM 0xD4 /* Resource Management */ #define LLC_SAP_GLOBAL 0xFF /* Global SAP. */ +struct llc_pktinfo { + int lpi_ifindex; + unsigned char lpi_sap; + unsigned char lpi_mac[IFHWADDRLEN]; +}; + #ifdef __KERNEL__ #define LLC_SAP_DYN_START 0xC0 #define LLC_SAP_DYN_STOP 0xDE -- cgit v1.2.3 From 49f474331e563a6ecf3b1e87ec27ec5482b3e4f1 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Sun, 27 Dec 2009 11:51:52 +0100 Subject: perf events: Remove arg from perf sched hooks Since we only ever schedule the local cpu, there is no need to pass the cpu number to the perf sched hooks. This micro-optimizes things a bit. Signed-off-by: Peter Zijlstra Cc: Mike Galbraith Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker LKML-Reference: Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index c66b34f75eea..a494e7501292 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -746,10 +746,10 @@ extern int perf_max_events; extern const struct pmu *hw_perf_event_init(struct perf_event *event); -extern void perf_event_task_sched_in(struct task_struct *task, int cpu); +extern void perf_event_task_sched_in(struct task_struct *task); extern void perf_event_task_sched_out(struct task_struct *task, - struct task_struct *next, int cpu); -extern void perf_event_task_tick(struct task_struct *task, int cpu); + struct task_struct *next); +extern void perf_event_task_tick(struct task_struct *task); extern int perf_event_init_task(struct task_struct *child); extern void perf_event_exit_task(struct task_struct *child); extern void perf_event_free_task(struct task_struct *task); @@ -870,12 +870,12 @@ extern void perf_event_enable(struct perf_event *event); extern void perf_event_disable(struct perf_event *event); #else static inline void -perf_event_task_sched_in(struct task_struct *task, int cpu) { } +perf_event_task_sched_in(struct task_struct *task) { } static inline void perf_event_task_sched_out(struct task_struct *task, - struct task_struct *next, int cpu) { } + struct task_struct *next) { } static inline void -perf_event_task_tick(struct task_struct *task, int cpu) { } +perf_event_task_tick(struct task_struct *task) { } static inline int perf_event_init_task(struct task_struct *child) { return 0; } static inline void perf_event_exit_task(struct task_struct *child) { } static inline void perf_event_free_task(struct task_struct *task) { } -- cgit v1.2.3 From 07b139c8c81b97bbe55c68daf0cbeca8b1c609ca Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Mon, 21 Dec 2009 14:27:35 +0800 Subject: perf events: Remove CONFIG_EVENT_PROFILE Quoted from Ingo: | This reminds me - i think we should eliminate CONFIG_EVENT_PROFILE - | it's an unnecessary Kconfig complication. If both PERF_EVENTS and | EVENT_TRACING is enabled we should expose generic tracepoints. | | Nor is it limited to event 'profiling', so it has become a misnomer as | well. Signed-off-by: Li Zefan Cc: Frederic Weisbecker Cc: Steven Rostedt Cc: Peter Zijlstra Cc: Paul Mackerras LKML-Reference: <4B2F1557.2050705@cn.fujitsu.com> Signed-off-by: Ingo Molnar --- include/linux/ftrace_event.h | 2 +- include/linux/perf_event.h | 2 +- include/linux/syscalls.h | 4 ++-- 3 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 2233c98d80df..0a09e758c7d3 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -188,7 +188,7 @@ do { \ __trace_printk(ip, fmt, ##args); \ } while (0) -#ifdef CONFIG_EVENT_PROFILE +#ifdef CONFIG_PERF_EVENTS struct perf_event; extern int ftrace_profile_enable(int event_id); extern void ftrace_profile_disable(int event_id); diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index a494e7501292..9a1d276db754 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -658,7 +658,7 @@ struct perf_event { perf_overflow_handler_t overflow_handler; -#ifdef CONFIG_EVENT_PROFILE +#ifdef CONFIG_EVENT_TRACING struct event_filter *filter; #endif diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 65793e90d6f6..b7c7fcf7790b 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -99,7 +99,7 @@ struct perf_event_attr; #define __SC_TEST5(t5, a5, ...) __SC_TEST(t5); __SC_TEST4(__VA_ARGS__) #define __SC_TEST6(t6, a6, ...) __SC_TEST(t6); __SC_TEST5(__VA_ARGS__) -#ifdef CONFIG_EVENT_PROFILE +#ifdef CONFIG_PERF_EVENTS #define TRACE_SYS_ENTER_PROFILE_INIT(sname) \ .profile_enable = prof_sysenter_enable, \ @@ -113,7 +113,7 @@ struct perf_event_attr; #define TRACE_SYS_ENTER_PROFILE_INIT(sname) #define TRACE_SYS_EXIT_PROFILE(sname) #define TRACE_SYS_EXIT_PROFILE_INIT(sname) -#endif +#endif /* CONFIG_PERF_EVENTS */ #ifdef CONFIG_FTRACE_SYSCALLS #define __SC_STR_ADECL1(t, a) #a -- cgit v1.2.3 From d894837f23f491aa7ed167aae767fc07cfe6e6e6 Mon Sep 17 00:00:00 2001 From: Simon Kagstrom Date: Wed, 23 Dec 2009 11:08:18 +0100 Subject: sched: might_sleep(): Make file parameter const char * Fixes a warning when building with g++: warning: deprecated conversion from string constant to 'char*' And the file parameter use is constant, so mark it as such. Signed-off-by: Simon Kagstrom Cc: peterz@infradead.org LKML-Reference: <20091223110818.442d848e@marrow.netinsight.se> Signed-off-by: Ingo Molnar --- include/linux/kernel.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 3fc9f5aab5f8..785d7d1099d4 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -124,7 +124,7 @@ extern int _cond_resched(void); #endif #ifdef CONFIG_DEBUG_SPINLOCK_SLEEP - void __might_sleep(char *file, int line, int preempt_offset); + void __might_sleep(const char *file, int line, int preempt_offset); /** * might_sleep - annotation for functions that can sleep * @@ -138,7 +138,8 @@ extern int _cond_resched(void); # define might_sleep() \ do { __might_sleep(__FILE__, __LINE__, 0); might_resched(); } while (0) #else - static inline void __might_sleep(char *file, int line, int preempt_offset) { } + static inline void __might_sleep(const char *file, int line, + int preempt_offset) { } # define might_sleep() do { might_resched(); } while (0) #endif -- cgit v1.2.3 From 8e664fb3fd2b04e3ac5fad7f046000ba54e0e275 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 23 Dec 2009 13:15:38 +0100 Subject: mac80211: split up and insert custom IEs correctly Currently, we insert all user-specified IEs before the HT IE for association, and after the HT IE for probe requests. For association, that's correct only if the user-specified IEs are RSN only, incorrect in all other cases including WPA. Change this to split apart the user-specified IEs in two places for association: before the HT IE (e.g. RSN), after the HT IE (generally empty right now I think?) and after WMM (all other vendor-specific IEs). For probes, split the IEs in different places to be correct according to the spec. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/linux/ieee80211.h | 39 ++++++++++++++++++++++++++++++---------