From 23fb064bb96f001ecb8682129f7ee1bc1ca691bc Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 21 Jul 2009 21:18:35 +0900 Subject: percpu: kill legacy percpu allocator With ia64 converted, there's no arch left which still uses legacy percpu allocator. Kill it. Signed-off-by: Tejun Heo Delightedly-acked-by: Rusty Russell Cc: Ingo Molnar Cc: Christoph Lameter --- mm/Makefile | 4 -- mm/allocpercpu.c | 177 ------------------------------------------------------- mm/percpu.c | 2 - 3 files changed, 183 deletions(-) delete mode 100644 mm/allocpercpu.c (limited to 'mm') diff --git a/mm/Makefile b/mm/Makefile index ebf849042ed..82131d0f8d8 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -34,11 +34,7 @@ obj-$(CONFIG_FAILSLAB) += failslab.o obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o obj-$(CONFIG_FS_XIP) += filemap_xip.o obj-$(CONFIG_MIGRATION) += migrate.o -ifndef CONFIG_HAVE_LEGACY_PER_CPU_AREA obj-$(CONFIG_SMP) += percpu.o -else -obj-$(CONFIG_SMP) += allocpercpu.o -endif obj-$(CONFIG_QUICKLIST) += quicklist.o obj-$(CONFIG_CGROUP_MEM_RES_CTLR) += memcontrol.o page_cgroup.o obj-$(CONFIG_MEMORY_FAILURE) += memory-failure.o diff --git a/mm/allocpercpu.c b/mm/allocpercpu.c deleted file mode 100644 index df34ceae0c6..00000000000 --- a/mm/allocpercpu.c +++ /dev/null @@ -1,177 +0,0 @@ -/* - * linux/mm/allocpercpu.c - * - * Separated from slab.c August 11, 2006 Christoph Lameter - */ -#include -#include -#include -#include - -#ifndef cache_line_size -#define cache_line_size() L1_CACHE_BYTES -#endif - -/** - * percpu_depopulate - depopulate per-cpu data for given cpu - * @__pdata: per-cpu data to depopulate - * @cpu: depopulate per-cpu data for this cpu - * - * Depopulating per-cpu data for a cpu going offline would be a typical - * use case. You need to register a cpu hotplug handler for that purpose. - */ -static void percpu_depopulate(void *__pdata, int cpu) -{ - struct percpu_data *pdata = __percpu_disguise(__pdata); - - kfree(pdata->ptrs[cpu]); - pdata->ptrs[cpu] = NULL; -} - -/** - * percpu_depopulate_mask - depopulate per-cpu data for some cpu's - * @__pdata: per-cpu data to depopulate - * @mask: depopulate per-cpu data for cpu's selected through mask bits - */ -static void __percpu_depopulate_mask(void *__pdata, const cpumask_t *mask) -{ - int cpu; - for_each_cpu_mask_nr(cpu, *mask) - percpu_depopulate(__pdata, cpu); -} - -#define percpu_depopulate_mask(__pdata, mask) \ - __percpu_depopulate_mask((__pdata), &(mask)) - -/** - * percpu_populate - populate per-cpu data for given cpu - * @__pdata: per-cpu data to populate further - * @size: size of per-cpu object - * @gfp: may sleep or not etc. - * @cpu: populate per-data for this cpu - * - * Populating per-cpu data for a cpu coming online would be a typical - * use case. You need to register a cpu hotplug handler for that purpose. - * Per-cpu object is populated with zeroed buffer. - */ -static void *percpu_populate(void *__pdata, size_t size, gfp_t gfp, int cpu) -{ - struct percpu_data *pdata = __percpu_disguise(__pdata); - int node = cpu_to_node(cpu); - - /* - * We should make sure each CPU gets private memory. - */ - size = roundup(size, cache_line_size()); - - BUG_ON(pdata->ptrs[cpu]); - if (node_online(node)) - pdata->ptrs[cpu] = kmalloc_node(size, gfp|__GFP_ZERO, node); - else - pdata->ptrs[cpu] = kzalloc(size, gfp); - return pdata->ptrs[cpu]; -} - -/** - * percpu_populate_mask - populate per-cpu data for more cpu's - * @__pdata: per-cpu data to populate further - * @size: size of per-cpu object - * @gfp: may sleep or not etc. - * @mask: populate per-cpu data for cpu's selected through mask bits - * - * Per-cpu objects are populated with zeroed buffers. - */ -static int __percpu_populate_mask(void *__pdata, size_t size, gfp_t gfp, - cpumask_t *mask) -{ - cpumask_t populated; - int cpu; - - cpus_clear(populated); - for_each_cpu_mask_nr(cpu, *mask) - if (unlikely(!percpu_populate(__pdata, size, gfp, cpu))) { - __percpu_depopulate_mask(__pdata, &populated); - return -ENOMEM; - } else - cpu_set(cpu, populated); - return 0; -} - -#define percpu_populate_mask(__pdata, size, gfp, mask) \ - __percpu_populate_mask((__pdata), (size), (gfp), &(mask)) - -/** - * alloc_percpu - initial setup of per-cpu data - * @size: size of per-cpu object - * @align: alignment - * - * Allocate dynamic percpu area. Percpu objects are populated with - * zeroed buffers. - */ -void *__alloc_percpu(size_t size, size_t align) -{ - /* - * We allocate whole cache lines to avoid false sharing - */ - size_t sz = roundup(nr_cpu_ids * sizeof(void *), cache_line_size()); - void *pdata = kzalloc(sz, GFP_KERNEL); - void *__pdata = __percpu_disguise(pdata); - - /* - * Can't easily make larger alignment work with kmalloc. WARN - * on it. Larger alignment should only be used for module - * percpu sections on SMP for which this path isn't used. - */ - WARN_ON_ONCE(align > SMP_CACHE_BYTES); - - if (unlikely(!pdata)) - return NULL; - if (likely(!__percpu_populate_mask(__pdata, size, GFP_KERNEL, - &cpu_possible_map))) - return __pdata; - kfree(pdata); - return NULL; -} -EXPORT_SYMBOL_GPL(__alloc_percpu); - -/** - * free_percpu - final cleanup of per-cpu data - * @__pdata: object to clean up - * - * We simply clean up any per-cpu object left. No need for the client to - * track and specify through a bis mask which per-cpu objects are to free. - */ -void free_percpu(void *__pdata) -{ - if (unlikely(!__pdata)) - return; - __percpu_depopulate_mask(__pdata, cpu_possible_mask); - kfree(__percpu_disguise(__pdata)); -} -EXPORT_SYMBOL_GPL(free_percpu); - -/* - * Generic percpu area setup. - */ -#ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA -unsigned long __per_cpu_offset[NR_CPUS] __read_mostly; - -EXPORT_SYMBOL(__per_cpu_offset); - -void __init setup_per_cpu_areas(void) -{ - unsigned long size, i; - char *ptr; - unsigned long nr_possible_cpus = num_possible_cpus(); - - /* Copy section for each CPU (we discard the original) */ - size = ALIGN(PERCPU_ENOUGH_ROOM, PAGE_SIZE); - ptr = alloc_bootmem_pages(size * nr_possible_cpus); - - for_each_possible_cpu(i) { - __per_cpu_offset[i] = ptr - __per_cpu_start; - memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start); - ptr += size; - } -} -#endif /* CONFIG_HAVE_SETUP_PER_CPU_AREA */ diff --git a/mm/percpu.c b/mm/percpu.c index 4a048abad04..e4e08b87b77 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -46,8 +46,6 @@ * * To use this allocator, arch code should do the followings. * - * - drop CONFIG_HAVE_LEGACY_PER_CPU_AREA - * * - define __addr_to_pcpu_ptr() and __pcpu_ptr_to_addr() to translate * regular address to percpu pointer and back if they need to be * different from the default -- cgit v1.2.3-70-g09d2 From 3f04ba859597412afbfb31f2fcbe289f2461f9a1 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 29 Oct 2009 22:34:12 +0900 Subject: vmalloc: fix use of non-existent percpu variable in put_cpu_var() vmalloc used non-existent percpu variable vmap_cpu_blocks instead of the intended vmap_block_queue. This went unnoticed because put_cpu_var() didn't evaluate the parameter. Fix it. Signed-off-by: Tejun Heo Cc: Nick Piggin --- mm/vmalloc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'mm') diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 69511e66323..b65cfe44a56 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -760,7 +760,7 @@ static struct vmap_block *new_vmap_block(gfp_t gfp_mask) spin_lock(&vbq->lock); list_add(&vb->free_list, &vbq->free); spin_unlock(&vbq->lock); - put_cpu_var(vmap_cpu_blocks); + put_cpu_var(vmap_block_queue); return vb; } @@ -825,7 +825,7 @@ again: } spin_unlock(&vb->lock); } - put_cpu_var(vmap_cpu_blocks); + put_cpu_var(vmap_block_queue); rcu_read_unlock(); if (!addr) { -- cgit v1.2.3-70-g09d2 From 0f5e4816dbf38ce9488e611ca2296925c1e90d5e Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 29 Oct 2009 22:34:12 +0900 Subject: percpu: remove some sparse warnings Make the following changes to remove some sparse warnings. * Make DEFINE_PER_CPU_SECTION() declare __pcpu_unique_* before defining it. * Annotate pcpu_extend_area_map() that it is entered with pcpu_lock held, releases it and then reacquires it. * Make percpu related macros use unique nested variable names. * While at it, add pcpu prefix to __size_call[_return]() macros as to-be-implemented sparse annotations will add percpu specific stuff to these macros. Signed-off-by: Tejun Heo Reviewed-by: Christoph Lameter Cc: Rusty Russell --- arch/x86/include/asm/percpu.h | 26 +++++++++++------------ include/linux/percpu-defs.h | 1 + include/linux/percpu.h | 48 +++++++++++++++++++++---------------------- mm/percpu.c | 1 + 4 files changed, 39 insertions(+), 37 deletions(-) (limited to 'mm') diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index 8b5ec19bdef..0c44196b78a 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -74,31 +74,31 @@ extern void __bad_percpu_size(void); #define percpu_to_op(op, var, val) \ do { \ - typedef typeof(var) T__; \ + typedef typeof(var) pto_T__; \ if (0) { \ - T__ tmp__; \ - tmp__ = (val); \ + pto_T__ pto_tmp__; \ + pto_tmp__ = (val); \ } \ switch (sizeof(var)) { \ case 1: \ asm(op "b %1,"__percpu_arg(0) \ : "+m" (var) \ - : "qi" ((T__)(val))); \ + : "qi" ((pto_T__)(val))); \ break; \ case 2: \ asm(op "w %1,"__percpu_arg(0) \ : "+m" (var) \ - : "ri" ((T__)(val))); \ + : "ri" ((pto_T__)(val))); \ break; \ case 4: \ asm(op "l %1,"__percpu_arg(0) \ : "+m" (var) \ - : "ri" ((T__)(val))); \ + : "ri" ((pto_T__)(val))); \ break; \ case 8: \ asm(op "q %1,"__percpu_arg(0) \ : "+m" (var) \ - : "re" ((T__)(val))); \ + : "re" ((pto_T__)(val))); \ break; \ default: __bad_percpu_size(); \ } \ @@ -106,31 +106,31 @@ do { \ #define percpu_from_op(op, var, constraint) \ ({ \ - typeof(var) ret__; \ + typeof(var) pfo_ret__; \ switch (sizeof(var)) { \ case 1: \ asm(op "b "__percpu_arg(1)",%0" \ - : "=q" (ret__) \ + : "=q" (pfo_ret__) \ : constraint); \ break; \ case 2: \ asm(op "w "__percpu_arg(1)",%0" \ - : "=r" (ret__) \ + : "=r" (pfo_ret__) \ : constraint); \ break; \ case 4: \ asm(op "l "__percpu_arg(1)",%0" \ - : "=r" (ret__) \ + : "=r" (pfo_ret__) \ : constraint); \ break; \ case 8: \ asm(op "q "__percpu_arg(1)",%0" \ - : "=r" (ret__) \ + : "=r" (pfo_ret__) \ : constraint); \ break; \ default: __bad_percpu_size(); \ } \ - ret__; \ + pfo_ret__; \ }) /* diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h index 9bd03193ecd..5a5d6ce4bd5 100644 --- a/include/linux/percpu-defs.h +++ b/include/linux/percpu-defs.h @@ -60,6 +60,7 @@ #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 diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 519d6876590..522f421ec21 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -226,20 +226,20 @@ do { \ extern void __bad_size_call_parameter(void); -#define __size_call_return(stem, variable) \ -({ typeof(variable) ret__; \ +#define __pcpu_size_call_return(stem, variable) \ +({ typeof(variable) pscr_ret__; \ switch(sizeof(variable)) { \ - case 1: ret__ = stem##1(variable);break; \ - case 2: ret__ = stem##2(variable);break; \ - case 4: ret__ = stem##4(variable);break; \ - case 8: ret__ = stem##8(variable);break; \ + case 1: pscr_ret__ = stem##1(variable);break; \ + case 2: pscr_ret__ = stem##2(variable);break; \ + case 4: pscr_ret__ = stem##4(variable);break; \ + case 8: pscr_ret__ = stem##8(variable);break; \ default: \ __bad_size_call_parameter();break; \ } \ - ret__; \ + pscr_ret__; \ }) -#define __size_call(stem, variable, ...) \ +#define __pcpu_size_call(stem, variable, ...) \ do { \ switch(sizeof(variable)) { \ case 1: stem##1(variable, __VA_ARGS__);break; \ @@ -299,7 +299,7 @@ do { \ # ifndef this_cpu_read_8 # define this_cpu_read_8(pcp) _this_cpu_generic_read(pcp) # endif -# define this_cpu_read(pcp) __size_call_return(this_cpu_read_, (pcp)) +# define this_cpu_read(pcp) __pcpu_size_call_return(this_cpu_read_, (pcp)) #endif #define _this_cpu_generic_to_op(pcp, val, op) \ @@ -322,7 +322,7 @@ do { \ # ifndef this_cpu_write_8 # define this_cpu_write_8(pcp, val) _this_cpu_generic_to_op((pcp), (val), =) # endif -# define this_cpu_write(pcp, val) __size_call(this_cpu_write_, (pcp), (val)) +# define this_cpu_write(pcp, val) __pcpu_size_call(this_cpu_write_, (pcp), (val)) #endif #ifndef this_cpu_add @@ -338,7 +338,7 @@ do { \ # ifndef this_cpu_add_8 # define this_cpu_add_8(pcp, val) _this_cpu_generic_to_op((pcp), (val), +=) # endif -# define this_cpu_add(pcp, val) __size_call(this_cpu_add_, (pcp), (val)) +# define this_cpu_add(pcp, val) __pcpu_size_call(this_cpu_add_, (pcp), (val)) #endif #ifndef this_cpu_sub @@ -366,7 +366,7 @@ do { \ # ifndef this_cpu_and_8 # define this_cpu_and_8(pcp, val) _this_cpu_generic_to_op((pcp), (val), &=) # endif -# define this_cpu_and(pcp, val) __size_call(this_cpu_and_, (pcp), (val)) +# define this_cpu_and(pcp, val) __pcpu_size_call(this_cpu_and_, (pcp), (val)) #endif #ifndef this_cpu_or @@ -382,7 +382,7 @@ do { \ # ifndef this_cpu_or_8 # define this_cpu_or_8(pcp, val) _this_cpu_generic_to_op((pcp), (val), |=) # endif -# define this_cpu_or(pcp, val) __size_call(this_cpu_or_, (pcp), (val)) +# define this_cpu_or(pcp, val) __pcpu_size_call(this_cpu_or_, (pcp), (val)) #endif #ifndef this_cpu_xor @@ -398,7 +398,7 @@ do { \ # ifndef this_cpu_xor_8 # define this_cpu_xor_8(pcp, val) _this_cpu_generic_to_op((pcp), (val), ^=) # endif -# define this_cpu_xor(pcp, val) __size_call(this_cpu_or_, (pcp), (val)) +# define this_cpu_xor(pcp, val) __pcpu_size_call(this_cpu_or_, (pcp), (val)) #endif /* @@ -428,7 +428,7 @@ do { \ # ifndef __this_cpu_read_8 # define __this_cpu_read_8(pcp) (*__this_cpu_ptr(&(pcp))) # endif -# define __this_cpu_read(pcp) __size_call_return(__this_cpu_read_, (pcp)) +# define __this_cpu_read(pcp) __pcpu_size_call_return(__this_cpu_read_, (pcp)) #endif #define __this_cpu_generic_to_op(pcp, val, op) \ @@ -449,7 +449,7 @@ do { \ # ifndef __this_cpu_write_8 # define __this_cpu_write_8(pcp, val) __this_cpu_generic_to_op((pcp), (val), =) # endif -# define __this_cpu_write(pcp, val) __size_call(__this_cpu_write_, (pcp), (val)) +# define __this_cpu_write(pcp, val) __pcpu_size_call(__this_cpu_write_, (pcp), (val)) #endif #ifndef __this_cpu_add @@ -465,7 +465,7 @@ do { \ # ifndef __this_cpu_add_8 # define __this_cpu_add_8(pcp, val) __this_cpu_generic_to_op((pcp), (val), +=) # endif -# define __this_cpu_add(pcp, val) __size_call(__this_cpu_add_, (pcp), (val)) +# define __this_cpu_add(pcp, val) __pcpu_size_call(__this_cpu_add_, (pcp), (val)) #endif #ifndef __this_cpu_sub @@ -493,7 +493,7 @@ do { \ # ifndef __this_cpu_and_8 # define __this_cpu_and_8(pcp, val) __this_cpu_generic_to_op((pcp), (val), &=) # endif -# define __this_cpu_and(pcp, val) __size_call(__this_cpu_and_, (pcp), (val)) +# define __this_cpu_and(pcp, val) __pcpu_size_call(__this_cpu_and_, (pcp), (val)) #endif #ifndef __this_cpu_or @@ -509,7 +509,7 @@ do { \ # ifndef __this_cpu_or_8 # define __this_cpu_or_8(pcp, val) __this_cpu_generic_to_op((pcp), (val), |=) # endif -# define __this_cpu_or(pcp, val) __size_call(__this_cpu_or_, (pcp), (val)) +# define __this_cpu_or(pcp, val) __pcpu_size_call(__this_cpu_or_, (pcp), (val)) #endif #ifndef __this_cpu_xor @@ -525,7 +525,7 @@ do { \ # ifndef __this_cpu_xor_8 # define __this_cpu_xor_8(pcp, val) __this_cpu_generic_to_op((pcp), (val), ^=) # endif -# define __this_cpu_xor(pcp, val) __size_call(__this_cpu_xor_, (pcp), (val)) +# define __this_cpu_xor(pcp, val) __pcpu_size_call(__this_cpu_xor_, (pcp), (val)) #endif /* @@ -556,7 +556,7 @@ do { \ # ifndef irqsafe_cpu_add_8 # define irqsafe_cpu_add_8(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), +=) # endif -# define irqsafe_cpu_add(pcp, val) __size_call(irqsafe_cpu_add_, (pcp), (val)) +# define irqsafe_cpu_add(pcp, val) __pcpu_size_call(irqsafe_cpu_add_, (pcp), (val)) #endif #ifndef irqsafe_cpu_sub @@ -584,7 +584,7 @@ do { \ # ifndef irqsafe_cpu_and_8 # define irqsafe_cpu_and_8(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), &=) # endif -# define irqsafe_cpu_and(pcp, val) __size_call(irqsafe_cpu_and_, (val)) +# define irqsafe_cpu_and(pcp, val) __pcpu_size_call(irqsafe_cpu_and_, (val)) #endif #ifndef irqsafe_cpu_or @@ -600,7 +600,7 @@ do { \ # ifndef irqsafe_cpu_or_8 # define irqsafe_cpu_or_8(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), |=) # endif -# define irqsafe_cpu_or(pcp, val) __size_call(irqsafe_cpu_or_, (val)) +# define irqsafe_cpu_or(pcp, val) __pcpu_size_call(irqsafe_cpu_or_, (val)) #endif #ifndef irqsafe_cpu_xor @@ -616,7 +616,7 @@ do { \ # ifndef irqsafe_cpu_xor_8 # define irqsafe_cpu_xor_8(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), ^=) # endif -# define irqsafe_cpu_xor(pcp, val) __size_call(irqsafe_cpu_xor_, (val)) +# define irqsafe_cpu_xor(pcp, val) __pcpu_size_call(irqsafe_cpu_xor_, (val)) #endif #endif /* __LINUX_PERCPU_H */ diff --git a/mm/percpu.c b/mm/percpu.c index ec158bb5f86..e2e80fc7860 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -365,6 +365,7 @@ static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr) * 0 if noop, 1 if successfully extended, -errno on failure. */ static int pcpu_extend_area_map(struct pcpu_chunk *chunk) + __releases(lock) __acquires(lock) { int new_alloc; int *new; -- cgit v1.2.3-70-g09d2 From 1871e52c76dd95895caeb772f845a1718dcbcd75 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 29 Oct 2009 22:34:13 +0900 Subject: percpu: make percpu symbols under kernel/ and mm/ unique This patch updates percpu related symbols under kernel/ and mm/ such that percpu symbols are unique and don't clash with local symbols. This serves two purposes of decreasing the possibility of global percpu symbol collision and allowing dropping per_cpu__ prefix from percpu symbols. * kernel/lockdep.c: s/lock_stats/cpu_lock_stats/ * kernel/sched.c: s/init_rq_rt/init_rt_rq_var/ (any better idea?) s/sched_group_cpus/sched_groups/ * kernel/softirq.c: s/ksoftirqd/run_ksoftirqd/a * kernel/softlockup.c: s/(*)_timestamp/softlockup_\1_ts/ s/watchdog_task/softlockup_watchdog/ s/timestamp/ts/ for local variables * kernel/time/timer_stats: s/lookup_lock/tstats_lookup_lock/ * mm/slab.c: s/reap_work/slab_reap_work/ s/reap_node/slab_reap_node/ * mm/vmstat.c: local variable changed to avoid collision with vmstat_work Partly based on Rusty Russell's "alloc_percpu: rename percpu vars which cause name clashes" patch. Signed-off-by: Tejun Heo Acked-by: (slab/vmstat) Christoph Lameter Reviewed-by: Christoph Lameter Cc: Rusty Russell Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Andrew Morton Cc: Nick Piggin --- kernel/lockdep.c | 11 +++++----- kernel/sched.c | 8 +++---- kernel/softirq.c | 4 ++-- kernel/softlockup.c | 54 +++++++++++++++++++++++------------------------ kernel/time/timer_stats.c | 11 +++++----- mm/slab.c | 18 ++++++++-------- mm/vmstat.c | 7 +++--- 7 files changed, 57 insertions(+), 56 deletions(-) (limited to 'mm') diff --git a/kernel/lockdep.c b/kernel/lockdep.c index 3815ac1d58b..8631320a50d 100644 --- a/kernel/lockdep.c +++ b/kernel/lockdep.c @@ -140,7 +140,8 @@ static inline struct lock_class *hlock_class(struct held_lock *hlock) } #ifdef CONFIG_LOCK_STAT -static DEFINE_PER_CPU(struct lock_class_stats[MAX_LOCKDEP_KEYS], lock_stats); +static DEFINE_PER_CPU(struct lock_class_stats[MAX_LOCKDEP_KEYS], + cpu_lock_stats); static int lock_point(unsigned long points[], unsigned long ip) { @@ -186,7 +187,7 @@ struct lock_class_stats lock_stats(struct lock_class *class) memset(&stats, 0, sizeof(struct lock_class_stats)); for_each_possible_cpu(cpu) { struct lock_class_stats *pcs = - &per_cpu(lock_stats, cpu)[class - lock_classes]; + &per_cpu(cpu_lock_stats, cpu)[class - lock_classes]; for (i = 0; i < ARRAY_SIZE(stats.contention_point); i++) stats.contention_point[i] += pcs->contention_point[i]; @@ -213,7 +214,7 @@ void clear_lock_stats(struct lock_class *class) for_each_possible_cpu(cpu) { struct lock_class_stats *cpu_stats = - &per_cpu(lock_stats, cpu)[class - lock_classes]; + &per_cpu(cpu_lock_stats, cpu)[class - lock_classes]; memset(cpu_stats, 0, sizeof(struct lock_class_stats)); } @@ -223,12 +224,12 @@ void clear_lock_stats(struct lock_class *class) static struct lock_class_stats *get_lock_stats(struct lock_class *class) { - return &get_cpu_var(lock_stats)[class - lock_classes]; + return &get_cpu_var(cpu_lock_stats)[class - lock_classes]; } static void put_lock_stats(struct lock_class_stats *stats) { - put_cpu_var(lock_stats); + put_cpu_var(cpu_lock_stats); } static void lock_release_holdtime(struct held_lock *hlock) diff --git a/kernel/sched.c b/kernel/sched.c index 1535f3884b8..854ab418fd4 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -298,7 +298,7 @@ static DEFINE_PER_CPU_SHARED_ALIGNED(struct cfs_rq, init_tg_cfs_rq); #ifdef CONFIG_RT_GROUP_SCHED static DEFINE_PER_CPU(struct sched_rt_entity, init_sched_rt_entity); -static DEFINE_PER_CPU_SHARED_ALIGNED(struct rt_rq, init_rt_rq); +static DEFINE_PER_CPU_SHARED_ALIGNED(struct rt_rq, init_rt_rq_var); #endif /* CONFIG_RT_GROUP_SCHED */ #else /* !CONFIG_USER_SCHED */ #define root_task_group init_task_group @@ -8199,14 +8199,14 @@ enum s_alloc { */ #ifdef CONFIG_SCHED_SMT static DEFINE_PER_CPU(struct static_sched_domain, cpu_domains); -static DEFINE_PER_CPU(struct static_sched_group, sched_group_cpus); +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) { if (sg) - *sg = &per_cpu(sched_group_cpus, cpu).sg; + *sg = &per_cpu(sched_groups, cpu).sg; return cpu; } #endif /* CONFIG_SCHED_SMT */ @@ -9470,7 +9470,7 @@ void __init sched_init(void) #elif defined CONFIG_USER_SCHED init_tg_rt_entry(&root_task_group, &rq->rt, NULL, i, 0, NULL); init_tg_rt_entry(&init_task_group, - &per_cpu(init_rt_rq, i), + &per_cpu(init_rt_rq_var, i), &per_cpu(init_sched_rt_entity, i), i, 1, root_task_group.rt_se[i]); #endif diff --git a/kernel/softirq.c b/kernel/softirq.c index f8749e5216e..0740dfd55c5 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -697,7 +697,7 @@ void __init softirq_init(void) open_softirq(HI_SOFTIRQ, tasklet_hi_action); } -static int ksoftirqd(void * __bind_cpu) +static int run_ksoftirqd(void * __bind_cpu) { set_current_state(TASK_INTERRUPTIBLE); @@ -810,7 +810,7 @@ static int __cpuinit cpu_callback(struct notifier_block *nfb, switch (action) { case CPU_UP_PREPARE: case CPU_UP_PREPARE_FROZEN: - p = kthread_create(ksoftirqd, hcpu, "ksoftirqd/%d", hotcpu); + p = kthread_create(run_ksoftirqd, hcpu, "ksoftirqd/%d", hotcpu); if (IS_ERR(p)) { printk("ksoftirqd for %i failed\n", hotcpu); return NOTIFY_BAD; diff --git a/kernel/softlockup.c b/kernel/softlockup.c index 81324d12eb3..d22579087e2 100644 --- a/kernel/softlockup.c +++ b/kernel/softlockup.c @@ -22,9 +22,9 @@ static DEFINE_SPINLOCK(print_lock); -static DEFINE_PER_CPU(unsigned long, touch_timestamp); -static DEFINE_PER_CPU(unsigned long, print_timestamp); -static DEFINE_PER_CPU(struct task_struct *, watchdog_task); +static DEFINE_PER_CPU(unsigned long, softlockup_touch_ts); /* touch timestamp */ +static DEFINE_PER_CPU(unsigned long, softlockup_print_ts); /* print timestamp */ +static DEFINE_PER_CPU(struct task_struct *, softlockup_watchdog); static int __read_mostly did_panic; int __read_mostly softlockup_thresh = 60; @@ -70,12 +70,12 @@ static void __touch_softlockup_watchdog(void) { int this_cpu = raw_smp_processor_id(); - __raw_get_cpu_var(touch_timestamp) = get_timestamp(this_cpu); + __raw_get_cpu_var(softlockup_touch_ts) = get_timestamp(this_cpu); } void touch_softlockup_watchdog(void) { - __raw_get_cpu_var(touch_timestamp) = 0; + __raw_get_cpu_var(softlockup_touch_ts) = 0; } EXPORT_SYMBOL(touch_softlockup_watchdog); @@ -85,7 +85,7 @@ void touch_all_softlockup_watchdogs(void) /* Cause each CPU to re-update its timestamp rather than complain */ for_each_online_cpu(cpu) - per_cpu(touch_timestamp, cpu) = 0; + per_cpu(softlockup_touch_ts, cpu) = 0; } EXPORT_SYMBOL(touch_all_softlockup_watchdogs); @@ -104,28 +104,28 @@ int proc_dosoftlockup_thresh(struct ctl_table *table, int write, void softlockup_tick(void) { int this_cpu = smp_processor_id(); - unsigned long touch_timestamp = per_cpu(touch_timestamp, this_cpu); - unsigned long print_timestamp; + unsigned long touch_ts = per_cpu(softlockup_touch_ts, this_cpu); + unsigned long print_ts; struct pt_regs *regs = get_irq_regs(); unsigned long now; /* Is detection switched off? */ - if (!per_cpu(watchdog_task, this_cpu) || softlockup_thresh <= 0) { + if (!per_cpu(softlockup_watchdog, this_cpu) || softlockup_thresh <= 0) { /* Be sure we don't false trigger if switched back on */ - if (touch_timestamp) - per_cpu(touch_timestamp, this_cpu) = 0; + if (touch_ts) + per_cpu(softlockup_touch_ts, this_cpu) = 0; return; } - if (touch_timestamp == 0) { + if (touch_ts == 0) { __touch_softlockup_watchdog(); return; } - print_timestamp = per_cpu(print_timestamp, this_cpu); + print_ts = per_cpu(softlockup_print_ts, this_cpu); /* report at most once a second */ - if (print_timestamp == touch_timestamp || did_panic) + if (print_ts == touch_ts || did_panic) return; /* do not print during early bootup: */ @@ -140,18 +140,18 @@ void softlockup_tick(void) * Wake up the high-prio watchdog task twice per * threshold timespan. */ - if (now > touch_timestamp + softlockup_thresh/2) - wake_up_process(per_cpu(watchdog_task, this_cpu)); + if (now > touch_ts + softlockup_thresh/2) + wake_up_process(per_cpu(softlockup_watchdog, this_cpu)); /* Warn about unreasonable delays: */ - if (now <= (touch_timestamp + softlockup_thresh)) + if (now <= (touch_ts + softlockup_thresh)) return; - per_cpu(print_timestamp, this_cpu) = touch_timestamp; + per_cpu(softlockup_print_ts, this_cpu) = touch_ts; spin_lock(&print_lock); printk(KERN_ERR "BUG: soft lockup - CPU#%d stuck for %lus! [%s:%d]\n", - this_cpu, now - touch_timestamp, + this_cpu, now - touch_ts, current->comm, task_pid_nr(current)); print_modules(); print_irqtrace_events(current); @@ -209,32 +209,32 @@ cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) switch (action) { case CPU_UP_PREPARE: case CPU_UP_PREPARE_FROZEN: - BUG_ON(per_cpu(watchdog_task, hotcpu)); + BUG_ON(per_cpu(softlockup_watchdog, hotcpu)); p = kthread_create(watchdog, hcpu, "watchdog/%d", hotcpu); if (IS_ERR(p)) { printk(KERN_ERR "watchdog for %i failed\n", hotcpu); return NOTIFY_BAD; } - per_cpu(touch_timestamp, hotcpu) = 0; - per_cpu(watchdog_task, hotcpu) = p; + per_cpu(softlockup_touch_ts, hotcpu) = 0; + per_cpu(softlockup_watchdog, hotcpu) = p; kthread_bind(p, hotcpu); break; case CPU_ONLINE: case CPU_ONLINE_FROZEN: - wake_up_process(per_cpu(watchdog_task, hotcpu)); + wake_up_process(per_cpu(softlockup_watchdog, hotcpu)); break; #ifdef CONFIG_HOTPLUG_CPU case CPU_UP_CANCELED: case CPU_UP_CANCELED_FROZEN: - if (!per_cpu(watchdog_task, hotcpu)) + if (!per_cpu(softlockup_watchdog, hotcpu)) break; /* Unbind so it can run. Fall thru. */ - kthread_bind(per_cpu(watchdog_task, hotcpu), + kthread_bind(per_cpu(softlockup_watchdog, hotcpu), cpumask_any(cpu_online_mask)); case CPU_DEAD: case CPU_DEAD_FROZEN: - p = per_cpu(watchdog_task, hotcpu); - per_cpu(watchdog_task, hotcpu) = NULL; + p = per_cpu(softlockup_watchdog, hotcpu); + per_cpu(softlockup_watchdog, hotcpu) = NULL; kthread_stop(p); break; #endif /* CONFIG_HOTPLUG_CPU */ diff --git a/kernel/time/timer_stats.c b/kernel/time/timer_stats.c index ee5681f8d7e..63b117e9eba 100644 --- a/kernel/time/timer_stats.c +++ b/kernel/time/timer_stats.c @@ -86,7 +86,7 @@ static DEFINE_SPINLOCK(table_lock); /* * Per-CPU lookup locks for fast hash lookup: */ -static DEFINE_PER_CPU(spinlock_t, lookup_lock); +static DEFINE_PER_CPU(spinlock_t, tstats_lookup_lock); /* * Mutex to serialize state changes with show-stats activities: @@ -245,7 +245,7 @@ void timer_stats_update_stats(void *timer, pid_t pid, void *startf, if (likely(!timer_stats_active)) return; - lock = &per_cpu(lookup_lock, raw_smp_processor_id()); + lock = &per_cpu(tstats_lookup_lock, raw_smp_processor_id()); input.timer = timer; input.start_func = startf; @@ -348,9 +348,10 @@ static void sync_access(void) int cpu; for_each_online_cpu(cpu) { - spin_lock_irqsave(&per_cpu(lookup_lock, cpu), flags); + spinlock_t *lock = &per_cpu(tstats_lookup_lock, cpu); + spin_lock_irqsave(lock, flags); /* nothing */ - spin_unlock_irqrestore(&per_cpu(lookup_lock, cpu), flags); + spin_unlock_irqrestore(lock, flags); } } @@ -408,7 +409,7 @@ void __init init_timer_stats(void) int cpu; for_each_possible_cpu(cpu) - spin_lock_init(&per_cpu(lookup_lock, cpu)); + spin_lock_init(&per_cpu(tstats_lookup_lock, cpu)); } static int __init init_tstats_procfs(void) diff --git a/mm/slab.c b/mm/slab.c index 7dfa481c96b..211b1746c63 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -685,7 +685,7 @@ int slab_is_available(void) return g_cpucache_up >= EARLY; } -static DEFINE_PER_CPU(struct delayed_work, reap_work); +static DEFINE_PER_CPU(struct delayed_work, slab_reap_work); static inline struct array_cache *cpu_cache_get(struct kmem_cache *cachep) { @@ -826,7 +826,7 @@ __setup("noaliencache", noaliencache_setup); * objects freed on different nodes from which they were allocated) and the * flushing of remote pcps by calling drain_node_pages. */ -static DEFINE_PER_CPU(unsigned long, reap_node); +static DEFINE_PER_CPU(unsigned long, slab_reap_node); static void init_reap_node(int cpu) { @@ -836,17 +836,17 @@ static void init_reap_node(int cpu) if (node == MAX_NUMNODES) node = first_node(node_online_map); - per_cpu(reap_node, cpu) = node; + per_cpu(slab_reap_node, cpu) = node; } static void next_reap_node(void) { - int node = __get_cpu_var(reap_node); + int node = __get_cpu_var(slab_reap_node); node = next_node(node, node_online_map); if (unlikely(node >= MAX_NUMNODES)) node = first_node(node_online_map); - __get_cpu_var(reap_node) = node; + __get_cpu_var(slab_reap_node) = node; } #else @@ -863,7 +863,7 @@ static void next_reap_node(void) */ static void __cpuinit start_cpu_timer(int cpu) { - struct delayed_work *reap_work = &per_cpu(reap_work, cpu); + struct delayed_work *reap_work = &per_cpu(slab_reap_work, cpu); /* * When this gets called from do_initcalls via cpucache_init(), @@ -1027,7 +1027,7 @@ static void __drain_alien_cache(struct kmem_cache *cachep, */ static void reap_alien(struct kmem_cache *cachep, struct kmem_list3 *l3) { - int node = __get_cpu_var(reap_node); + int node = __get_cpu_var(slab_reap_node); if (l3->alien) { struct array_cache *ac = l3->alien[node]; @@ -1286,9 +1286,9 @@ static int __cpuinit cpuup_callback(struct notifier_block *nfb, * anything expensive but will only modify reap_work * and reschedule the timer. */ - cancel_rearming_delayed_work(&per_cpu(reap_work, cpu)); + cancel_rearming_delayed_work(&per_cpu(slab_reap_work, cpu)); /* Now the cache_reaper is guaranteed to be not running. */ - per_cpu(reap_work, cpu).work.func = NULL; + per_cpu(slab_reap_work, cpu).work.func = NULL; break; case CPU_DOWN_FAILED: case CPU_DOWN_FAILED_FROZEN: diff --git a/mm/vmstat.c b/mm/vmstat.c index c81321f9fee..dad2327e458 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -883,11 +883,10 @@ static void vmstat_update(struct work_struct *w) static void __cpuinit start_cpu_timer(int cpu) { - struct delayed_work *vmstat_work = &per_cpu(vmstat_work, cpu); + struct delayed_work *work = &per_cpu(vmstat_work, cpu); - INIT_DELAYED_WORK_DEFERRABLE(vmstat_work, vmstat_update); - schedule_delayed_work_on(cpu, vmstat_work, - __round_jiffies_relative(HZ, cpu)); + INIT_DELAYED_WORK_DEFERRABLE(work, vmstat_update); + schedule_delayed_work_on(cpu, work, __round_jiffies_relative(HZ, cpu)); } /* -- cgit v1.2.3-70-g09d2 From 3b034b0d084221596bf35c8d893e1d4d5477b9cc Mon Sep 17 00:00:00 2001 From: Vivek Goyal Date: Tue, 24 Nov 2009 15:50:03 +0900 Subject: percpu: Fix kdump failure if booted with percpu_alloc=page o kdump functionality reserves a per cpu area at boot time and exports the physical address of that area to user space through sys interface. This area stores some dump related information like cpu register states etc at the time of crash. o We were assuming that per cpu area always come from linearly mapped meory region and using __pa() to determine physical address. With percpu_alloc=page, per cpu area can come from vmalloc region also and __pa() breaks. o This patch implments a new function to convert per cpu address to physical address. Before the patch, crash_notes addresses looked as follows. cpu0 60fffff49800 cpu1 60fffff60800 cpu2 60fffff77800 These are bogus phsyical addresses. After the patch, address are following. cpu0 13eb44000 cpu1 13eb43000 cpu2 13eb42000 cpu3 13eb41000 These look fine. I got 4G of memory and /proc/iomem tell me following. 100000000-13fffffff : System RAM tj: * added missing asm/io.h include reported by Stephen Rothwell * repositioned per_cpu_ptr_phys() in percpu.c and added comment. Signed-off-by: Vivek Goyal Signed-off-by: Tejun Heo Cc: Stephen Rothwell --- drivers/base/cpu.c | 2 +- include/linux/percpu.h | 1 + mm/percpu.c | 22 ++++++++++++++++++++++ 3 files changed, 24 insertions(+), 1 deletion(-) (limited to 'mm') diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index e62a4ccea54..69ee5b7517e 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -97,7 +97,7 @@ static ssize_t show_crash_notes(struct sys_device *dev, struct sysdev_attribute * boot up and this data does not change there after. Hence this * operation should be safe. No locking required. */ - addr = __pa(per_cpu_ptr(crash_notes, cpunum)); + addr = per_cpu_ptr_to_phys(per_cpu_ptr(crash_notes, cpunum)); rc = sprintf(buf, "%Lx\n", addr); return rc; } diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 878836ca999..6ac984fa34f 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -154,6 +154,7 @@ struct percpu_data { extern void *__alloc_percpu(size_t size, size_t align); extern void free_percpu(void *__pdata); +extern phys_addr_t per_cpu_ptr_to_phys(void *addr); #ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA extern void __init setup_per_cpu_areas(void); diff --git a/mm/percpu.c b/mm/percpu.c index 5adfc268b40..008fbd9e6fa 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -74,6 +74,7 @@ #include #include #include +#include #define PCPU_SLOT_BASE_SHIFT 5 /* 1-31 shares the same slot */ #define PCPU_DFL_MAP_ALLOC 16 /* start a map with 16 ents */ @@ -1302,6 +1303,27 @@ void free_percpu(void *ptr) } EXPORT_SYMBOL_GPL(free_percpu); +/** + * per_cpu_ptr_to_phys - convert translated percpu address to physical address + * @addr: the address to be converted to physical address + * + * Given @addr which is dereferenceable address obtained via one of + * percpu access macros, this function translates it into its physical + * address. The caller is responsible for ensuring @addr stays valid + * until this function finishes. + * + * RETURNS: + * The physical address for @addr. + */ +phys_addr_t per_cpu_ptr_to_phys(void *addr) +{ + if ((unsigned long)addr < VMALLOC_START || + (unsigned long)addr >= VMALLOC_END) + return __pa(addr); + else + return page_to_phys(vmalloc_to_page(addr)); +} + static inline size_t pcpu_calc_fc_sizes(size_t static_size, size_t reserved_size, ssize_t *dyn_sizep) -- cgit v1.2.3-70-g09d2