From 0bd74fa8e29dcad98f7e8ffe01ec05fb3326abaf Mon Sep 17 00:00:00 2001 From: Brian Gerst Date: Mon, 19 Jan 2009 12:21:27 +0900 Subject: percpu: refactor percpu.h Impact: cleanup Refactor the DEFINE_PER_CPU_* macros and add .data.percpu.first section. Signed-off-by: Brian Gerst Signed-off-by: Tejun Heo --- include/linux/percpu.h | 41 +++++++++++++++++++++++------------------ 1 file changed, 23 insertions(+), 18 deletions(-) (limited to 'include/linux/percpu.h') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 9f2a3751873..0e24202b5a4 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -9,34 +9,39 @@ #include #ifdef CONFIG_SMP -#define DEFINE_PER_CPU(type, name) \ - __attribute__((__section__(".data.percpu"))) \ - PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name +#define PER_CPU_BASE_SECTION ".data.percpu" #ifdef MODULE -#define SHARED_ALIGNED_SECTION ".data.percpu" +#define PER_CPU_SHARED_ALIGNED_SECTION "" #else -#define SHARED_ALIGNED_SECTION ".data.percpu.shared_aligned" +#define PER_CPU_SHARED_ALIGNED_SECTION ".shared_aligned" #endif +#define PER_CPU_FIRST_SECTION ".first" -#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name) \ - __attribute__((__section__(SHARED_ALIGNED_SECTION))) \ - PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name \ - ____cacheline_aligned_in_smp +#else + +#define PER_CPU_BASE_SECTION ".data" +#define PER_CPU_SHARED_ALIGNED_SECTION "" +#define PER_CPU_FIRST_SECTION "" + +#endif -#define DEFINE_PER_CPU_PAGE_ALIGNED(type, name) \ - __attribute__((__section__(".data.percpu.page_aligned"))) \ +#define DEFINE_PER_CPU_SECTION(type, name, section) \ + __attribute__((__section__(PER_CPU_BASE_SECTION section))) \ PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name -#else + #define DEFINE_PER_CPU(type, name) \ - PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name + DEFINE_PER_CPU_SECTION(type, name, "") -#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name) \ - DEFINE_PER_CPU(type, name) +#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name) \ + DEFINE_PER_CPU_SECTION(type, name, PER_CPU_SHARED_ALIGNED_SECTION) \ + ____cacheline_aligned_in_smp -#define DEFINE_PER_CPU_PAGE_ALIGNED(type, name) \ - DEFINE_PER_CPU(type, name) -#endif +#define DEFINE_PER_CPU_PAGE_ALIGNED(type, name) \ + DEFINE_PER_CPU_SECTION(type, name, ".page_aligned") + +#define DEFINE_PER_CPU_FIRST(type, name) \ + DEFINE_PER_CPU_SECTION(type, name, PER_CPU_FIRST_SECTION) #define EXPORT_PER_CPU_SYMBOL(var) EXPORT_SYMBOL(per_cpu__##var) #define EXPORT_PER_CPU_SYMBOL_GPL(var) EXPORT_SYMBOL_GPL(per_cpu__##var) -- cgit v1.2.3-70-g09d2 From d3770449d3cb058b94ca1d050d5ced4a66c75ce4 Mon Sep 17 00:00:00 2001 From: Brian Gerst Date: Sun, 8 Feb 2009 09:58:38 -0500 Subject: percpu: make PER_CPU_BASE_SECTION overridable by arches Impact: bug fix IA-64 needs to put percpu data in the seperate section even on UP. Fixes regression caused by "percpu: refactor percpu.h" Signed-off-by: Brian Gerst Acked-by: Tony Luck Signed-off-by: Ingo Molnar --- arch/ia64/include/asm/percpu.h | 4 ++-- include/linux/percpu.h | 8 +++++++- 2 files changed, 9 insertions(+), 3 deletions(-) (limited to 'include/linux/percpu.h') diff --git a/arch/ia64/include/asm/percpu.h b/arch/ia64/include/asm/percpu.h index 77f30b664b4..30cf46534dd 100644 --- a/arch/ia64/include/asm/percpu.h +++ b/arch/ia64/include/asm/percpu.h @@ -27,12 +27,12 @@ extern void *per_cpu_init(void); #else /* ! SMP */ -#define PER_CPU_ATTRIBUTES __attribute__((__section__(".data.percpu"))) - #define per_cpu_init() (__phys_per_cpu_start) #endif /* SMP */ +#define PER_CPU_BASE_SECTION ".data.percpu" + /* * Be extremely careful when taking the address of this variable! Due to virtual * remapping, it is different from the canonical address returned by __get_cpu_var(var)! diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 0e24202b5a4..3577ffd90d4 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -8,8 +8,15 @@ #include +#ifndef PER_CPU_BASE_SECTION #ifdef CONFIG_SMP #define PER_CPU_BASE_SECTION ".data.percpu" +#else +#define PER_CPU_BASE_SECTION ".data" +#endif +#endif + +#ifdef CONFIG_SMP #ifdef MODULE #define PER_CPU_SHARED_ALIGNED_SECTION "" @@ -20,7 +27,6 @@ #else -#define PER_CPU_BASE_SECTION ".data" #define PER_CPU_SHARED_ALIGNED_SECTION "" #define PER_CPU_FIRST_SECTION "" -- cgit v1.2.3-70-g09d2 From b36128c830a8f5bd7d4981f5b0b69950f5928ee6 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Fri, 20 Feb 2009 16:29:08 +0900 Subject: alloc_percpu: change percpu_ptr to per_cpu_ptr Impact: cleanup There are two allocated per-cpu accessor macros with almost identical spelling. The original and far more popular is per_cpu_ptr (44 files), so change over the other 4 files. tj: kill percpu_ptr() and update UP too Signed-off-by: Rusty Russell Cc: mingo@redhat.com Cc: lenb@kernel.org Cc: cpufreq@vger.kernel.org Signed-off-by: Tejun Heo --- arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c | 2 +- drivers/acpi/processor_perflib.c | 4 ++-- include/linux/percpu.h | 23 +++++++++++------------ kernel/sched.c | 6 +++--- kernel/stop_machine.c | 2 +- 5 files changed, 18 insertions(+), 19 deletions(-) (limited to 'include/linux/percpu.h') diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c index 4b1c319d30c..22590cf688a 100644 --- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c +++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c @@ -601,7 +601,7 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy) if (!data) return -ENOMEM; - data->acpi_data = percpu_ptr(acpi_perf_data, cpu); + data->acpi_data = per_cpu_ptr(acpi_perf_data, cpu); per_cpu(drv_data, cpu) = data; if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) diff --git a/drivers/acpi/processor_perflib.c b/drivers/acpi/processor_perflib.c index 9cc769b587f..68fd3d29279 100644 --- a/drivers/acpi/processor_perflib.c +++ b/drivers/acpi/processor_perflib.c @@ -516,12 +516,12 @@ int acpi_processor_preregister_performance( continue; } - if (!performance || !percpu_ptr(performance, i)) { + if (!performance || !per_cpu_ptr(performance, i)) { retval = -EINVAL; continue; } - pr->performance = percpu_ptr(performance, i); + pr->performance = per_cpu_ptr(performance, i); cpumask_set_cpu(i, pr->performance->shared_cpu_map); if (acpi_processor_get_psd(pr)) { retval = -EINVAL; diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 3577ffd90d4..c80cfe1260e 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -81,23 +81,13 @@ struct percpu_data { }; #define __percpu_disguise(pdata) (struct percpu_data *)~(unsigned long)(pdata) -/* - * Use this to get to a cpu's version of the per-cpu object dynamically - * allocated. Non-atomic access to the current CPU's version should - * probably be combined with get_cpu()/put_cpu(). - */ -#define percpu_ptr(ptr, cpu) \ -({ \ - struct percpu_data *__p = __percpu_disguise(ptr); \ - (__typeof__(ptr))__p->ptrs[(cpu)]; \ -}) extern void *__percpu_alloc_mask(size_t size, gfp_t gfp, cpumask_t *mask); extern void percpu_free(void *__pdata); #else /* CONFIG_SMP */ -#define percpu_ptr(ptr, cpu) ({ (void)(cpu); (ptr); }) +#define per_cpu_ptr(ptr, cpu) ({ (void)(cpu); (ptr); }) static __always_inline void *__percpu_alloc_mask(size_t size, gfp_t gfp, cpumask_t *mask) { @@ -122,6 +112,15 @@ static inline void percpu_free(void *__pdata) cpu_possible_map) #define alloc_percpu(type) (type *)__alloc_percpu(sizeof(type)) #define free_percpu(ptr) percpu_free((ptr)) -#define per_cpu_ptr(ptr, cpu) percpu_ptr((ptr), (cpu)) +/* + * Use this to get to a cpu's version of the per-cpu object dynamically + * allocated. Non-atomic access to the current CPU's version should + * probably be combined with get_cpu()/put_cpu(). + */ +#define per_cpu_ptr(ptr, cpu) \ +({ \ + struct percpu_data *__p = __percpu_disguise(ptr); \ + (__typeof__(ptr))__p->ptrs[(cpu)]; \ +}) #endif /* __LINUX_PERCPU_H */ diff --git a/kernel/sched.c b/kernel/sched.c index fc17fd91ab5..9d30ac95632 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -9472,7 +9472,7 @@ cpuacct_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp) static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu) { - u64 *cpuusage = percpu_ptr(ca->cpuusage, cpu); + u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu); u64 data; #ifndef CONFIG_64BIT @@ -9491,7 +9491,7 @@ static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu) static void cpuacct_cpuusage_write(struct cpuacct *ca, int cpu, u64 val) { - u64 *cpuusage = percpu_ptr(ca->cpuusage, cpu); + u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu); #ifndef CONFIG_64BIT /* @@ -9587,7 +9587,7 @@ static void cpuacct_charge(struct task_struct *tsk, u64 cputime) ca = task_ca(tsk); for (; ca; ca = ca->parent) { - u64 *cpuusage = percpu_ptr(ca->cpuusage, cpu); + u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu); *cpuusage += cputime; } } diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index 0cd415ee62a..74541ca4953 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -170,7 +170,7 @@ int __stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus) * doesn't hit this CPU until we're ready. */ get_cpu(); for_each_online_cpu(i) { - sm_work = percpu_ptr(stop_machine_work, i); + sm_work = per_cpu_ptr(stop_machine_work, i); INIT_WORK(sm_work, stop_cpu); queue_work_on(i, stop_machine_wq, sm_work); } -- cgit v1.2.3-70-g09d2 From 313e458f81ec3852106c5a83830fe0d4f405a71a Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Fri, 20 Feb 2009 16:29:08 +0900 Subject: alloc_percpu: add align argument to __alloc_percpu. This prepares for a real __alloc_percpu, by adding an alignment argument. Only one place uses __alloc_percpu directly, and that's for a string. tj: af_inet also uses __alloc_percpu(), update it. Signed-off-by: Rusty Russell Cc: Christoph Lameter Cc: Jens Axboe --- block/blktrace.c | 2 +- include/linux/percpu.h | 5 +++-- net/ipv4/af_inet.c | 4 ++-- 3 files changed, 6 insertions(+), 5 deletions(-) (limited to 'include/linux/percpu.h') diff --git a/block/blktrace.c b/block/blktrace.c index 39cc3bfe56e..487766237d2 100644 --- a/block/blktrace.c +++ b/block/blktrace.c @@ -363,7 +363,7 @@ int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev, if (!bt->sequence) goto err; - bt->msg_data = __alloc_percpu(BLK_TN_MAX_MSG); + bt->msg_data = __alloc_percpu(BLK_TN_MAX_MSG, __alignof__(char)); if (!bt->msg_data) goto err; diff --git a/include/linux/percpu.h b/include/linux/percpu.h index c80cfe1260e..1fdaee93c04 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -108,9 +108,10 @@ static inline void percpu_free(void *__pdata) /* (legacy) interface for use without CPU hotplug handling */ -#define __alloc_percpu(size) percpu_alloc_mask((size), GFP_KERNEL, \ +#define __alloc_percpu(size, align) percpu_alloc_mask((size), GFP_KERNEL, \ cpu_possible_map) -#define alloc_percpu(type) (type *)__alloc_percpu(sizeof(type)) +#define alloc_percpu(type) (type *)__alloc_percpu(sizeof(type), \ + __alignof__(type)) #define free_percpu(ptr) percpu_free((ptr)) /* * Use this to get to a cpu's version of the per-cpu object dynamically diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 743f5542d65..3a3dad80135 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1375,10 +1375,10 @@ EXPORT_SYMBOL_GPL(snmp_fold_field); int snmp_mib_init(void *ptr[2], size_t mibsize) { BUG_ON(ptr == NULL); - ptr[0] = __alloc_percpu(mibsize); + ptr[0] = __alloc_percpu(mibsize, __alignof__(unsigned long long)); if (!ptr[0]) goto err0; - ptr[1] = __alloc_percpu(mibsize); + ptr[1] = __alloc_percpu(mibsize, __alignof__(unsigned long long)); if (!ptr[1]) goto err1; return 0; -- cgit v1.2.3-70-g09d2 From f2a8205c4ef1af917d175c36a4097ae5587791c8 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 20 Feb 2009 16:29:08 +0900 Subject: percpu: kill percpu_alloc() and friends Impact: kill unused functions percpu_alloc() and its friends never saw much action. It was supposed to replace the cpu-mask unaware __alloc_percpu() but it never happened and in fact __percpu_alloc_mask() itself never really grew proper up/down handling interface either (no exported interface for populate/depopulate). percpu allocation is about to go through major reimplementation and there's no reason to carry this unused interface around. Replace it with __alloc_percpu() and free_percpu(). Signed-off-by: Tejun Heo --- include/linux/percpu.h | 47 ++++++++++++++++++++++------------------------- mm/allocpercpu.c | 32 +++++++++++++++++++------------- 2 files changed, 41 insertions(+), 38 deletions(-) (limited to 'include/linux/percpu.h') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 1fdaee93c04..d99e24ae181 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -82,46 +82,43 @@ struct percpu_data { #define __percpu_disguise(pdata) (struct percpu_data *)~(unsigned long)(pdata) -extern void *__percpu_alloc_mask(size_t size, gfp_t gfp, cpumask_t *mask); -extern void percpu_free(void *__pdata); +/* + * Use this to get to a cpu's version of the per-cpu object + * dynamically allocated. Non-atomic access to the current CPU's + * version should probably be combined with get_cpu()/put_cpu(). + */ +#define per_cpu_ptr(ptr, cpu) \ +({ \ + struct percpu_data *__p = __percpu_disguise(ptr); \ + (__typeof__(ptr))__p->ptrs[(cpu)]; \ +}) + +extern void *__alloc_percpu(size_t size, size_t align); +extern void free_percpu(void *__pdata); #else /* CONFIG_SMP */ #define per_cpu_ptr(ptr, cpu) ({ (void)(cpu); (ptr); }) -static __always_inline void *__percpu_alloc_mask(size_t size, gfp_t gfp, cpumask_t *mask) +static inline void *__alloc_percpu(size_t size, size_t align) { + /* + * 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 > __alignof__(unsigned long long)); return kzalloc(size, gfp); } -static inline void percpu_free(void *__pdata) +static inline void free_percpu(void *p) { - kfree(__pdata); + kfree(p); } #endif /* CONFIG_SMP */ -#define percpu_alloc_mask(size, gfp, mask) \ - __percpu_alloc_mask((size), (gfp), &(mask)) - -#define percpu_alloc(size, gfp) percpu_alloc_mask((size), (gfp), cpu_online_map) - -/* (legacy) interface for use without CPU hotplug handling */ - -#define __alloc_percpu(size, align) percpu_alloc_mask((size), GFP_KERNEL, \ - cpu_possible_map) #define alloc_percpu(type) (type *)__alloc_percpu(sizeof(type), \ __alignof__(type)) -#define free_percpu(ptr) percpu_free((ptr)) -/* - * Use this to get to a cpu's version of the per-cpu object dynamically - * allocated. Non-atomic access to the current CPU's version should - * probably be combined with get_cpu()/put_cpu(). - */ -#define per_cpu_ptr(ptr, cpu) \ -({ \ - struct percpu_data *__p = __percpu_disguise(ptr); \ - (__typeof__(ptr))__p->ptrs[(cpu)]; \ -}) #endif /* __LINUX_PERCPU_H */ diff --git a/mm/allocpercpu.c b/mm/allocpercpu.c index 4297bc41bfd..3653c570232 100644 --- a/mm/allocpercpu.c +++ b/mm/allocpercpu.c @@ -99,45 +99,51 @@ static int __percpu_populate_mask(void *__pdata, size_t size, gfp_t gfp, __percpu_populate_mask((__pdata), (size), (gfp), &(mask)) /** - * percpu_alloc_mask - initial setup of per-cpu data + * alloc_percpu - initial setup of per-cpu data * @size: size of per-cpu object - * @gfp: may sleep or not etc. - * @mask: populate per-data for cpu's selected through mask bits + * @align: alignment * - * Populating per-cpu data for all online cpu's would be a typical use case, - * which is simplified by the percpu_alloc() wrapper. - * Per-cpu objects are populated with zeroed buffers. + * Allocate dynamic percpu area. Percpu objects are populated with + * zeroed buffers. */ -void *__percpu_alloc_mask(size_t size, gfp_t gfp, cpumask_t *mask) +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); + 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 > __alignof__(unsigned long long)); + if (unlikely(!pdata)) return NULL; - if (likely(!__percpu_populate_mask(__pdata, size, gfp, mask))) + if (likely(!__percpu_populate_mask(__pdata, size, GFP_KERNEL, + &cpu_possible_map))) return __pdata; kfree(pdata); return NULL; } -EXPORT_SYMBOL_GPL(__percpu_alloc_mask); +EXPORT_SYMBOL_GPL(__alloc_percpu); /** - * percpu_free - final cleanup of per-cpu data + * 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 percpu_free(void *__pdata) +void free_percpu(void *__pdata) { if (unlikely(!__pdata)) return; __percpu_depopulate_mask(__pdata, &cpu_possible_map); kfree(__percpu_disguise(__pdata)); } -EXPORT_SYMBOL_GPL(percpu_free); +EXPORT_SYMBOL_GPL(free_percpu); -- cgit v1.2.3-70-g09d2 From fbf59bc9d74d1fb30b8e0630743aff2806eafcea Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 20 Feb 2009 16:29:08 +0900 Subject: percpu: implement new dynamic percpu allocator Impact: new scalable dynamic percpu allocator which allows dynamic percpu areas to be accessed the same way as static ones Implement scalable dynamic percpu allocator which can be used for both static and dynamic percpu areas. This will allow static and dynamic areas to share faster direct access methods. This feature is optional and enabled only when CONFIG_HAVE_DYNAMIC_PER_CPU_AREA is defined by arch. Please read comment on top of mm/percpu.c for details. Signed-off-by: Tejun Heo Cc: Andrew Morton --- include/linux/percpu.h | 22 +- kernel/module.c | 31 ++ mm/Makefile | 4 + mm/percpu.c | 890 +++++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 943 insertions(+), 4 deletions(-) create mode 100644 mm/percpu.c (limited to 'include/linux/percpu.h') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index d99e24ae181..18080995ff3 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -76,23 +76,37 @@ #ifdef CONFIG_SMP -struct percpu_data { - void *ptrs[1]; -}; +#ifdef CONFIG_HAVE_DYNAMIC_PER_CPU_AREA -#define __percpu_disguise(pdata) (struct percpu_data *)~(unsigned long)(pdata) +extern void *pcpu_base_addr; +typedef void (*pcpu_populate_pte_fn_t)(unsigned long addr); + +extern size_t __init pcpu_setup_static(pcpu_populate_pte_fn_t populate_pte_fn, + struct page **pages, size_t cpu_size); /* * Use this to get to a cpu's version of the per-cpu object * dynamically allocated. Non-atomic access to the current CPU's * version should probably be combined with get_cpu()/put_cpu(). */ +#define per_cpu_ptr(ptr, cpu) SHIFT_PERCPU_PTR((ptr), per_cpu_offset((cpu))) + +#else /* CONFIG_HAVE_DYNAMIC_PER_CPU_AREA */ + +struct percpu_data { + void *ptrs[1]; +}; + +#define __percpu_disguise(pdata) (struct percpu_data *)~(unsigned long)(pdata) + #define per_cpu_ptr(ptr, cpu) \ ({ \ struct percpu_data *__p = __percpu_disguise(ptr); \ (__typeof__(ptr))__p->ptrs[(cpu)]; \ }) +#endif /* CONFIG_HAVE_DYNAMIC_PER_CPU_AREA */ + extern void *__alloc_percpu(size_t size, size_t align); extern void free_percpu(void *__pdata); diff --git a/kernel/module.c b/kernel/module.c index 52b3497b874..1f0657ae555 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -51,6 +51,7 @@ #include #include #include +#include #if 0 #define DEBUGP printk @@ -366,6 +367,34 @@ static struct module *find_module(const char *name) } #ifdef CONFIG_SMP + +#ifdef CONFIG_HAVE_DYNAMIC_PER_CPU_AREA + +static void *percpu_modalloc(unsigned long size, unsigned long align, + const char *name) +{ + void *ptr; + + if (align > PAGE_SIZE) { + printk(KERN_WARNING "%s: per-cpu alignment %li > %li\n", + name, align, PAGE_SIZE); + align = PAGE_SIZE; + } + + ptr = __alloc_percpu(size, align); + if (!ptr) + printk(KERN_WARNING + "Could not allocate %lu bytes percpu data\n", size); + return ptr; +} + +static void percpu_modfree(void *freeme) +{ + free_percpu(freeme); +} + +#else /* ... !CONFIG_HAVE_DYNAMIC_PER_CPU_AREA */ + /* Number of blocks used and allocated. */ static unsigned int pcpu_num_used, pcpu_num_allocated; /* Size of each block. -ve means used. */ @@ -499,6 +528,8 @@ static int percpu_modinit(void) } __initcall(percpu_modinit); +#endif /* CONFIG_HAVE_DYNAMIC_PER_CPU_AREA */ + static unsigned int find_pcpusec(Elf_Ehdr *hdr, Elf_Shdr *sechdrs, const char *secstrings) diff --git a/mm/Makefile b/mm/Makefile index 72255be57f8..818569b68f4 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -30,6 +30,10 @@ obj-$(CONFIG_FAILSLAB) += failslab.o obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o obj-$(CONFIG_FS_XIP) += filemap_xip.o obj-$(CONFIG_MIGRATION) += migrate.o +ifdef CONFIG_HAVE_DYNAMIC_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 diff --git a/mm/percpu.c b/mm/percpu.c new file mode 100644 index 00000000000..4617d97e877 --- /dev/null +++ b/mm/percpu.c @@ -0,0 +1,890 @@ +/* + * linux/mm/percpu.c - percpu memory allocator + * + * Copyright (C) 2009 SUSE Linux Products GmbH + * Copyright (C) 2009 Tejun Heo + * + * This file is released under the GPLv2. + * + * This is percpu allocator which can handle both static and dynamic + * areas. Percpu areas are allocated in chunks in vmalloc area. Each + * chunk is consisted of num_possible_cpus() units and the first chunk + * is used for static percpu variables in the kernel image (special + * boot time alloc/init handling necessary as these areas need to be + * brought up before allocation services are running). Unit grows as + * necessary and all units grow or shrink in unison. When a chunk is + * filled up, another chunk is allocated. ie. in vmalloc area + * + * c0 c1 c2 + * ------------------- ------------------- ------------ + * | u0 | u1 | u2 | u3 | | u0 | u1 | u2 | u3 | | u0 | u1 | u + * ------------------- ...... ------------------- .... ------------ + * + * Allocation is done in offset-size areas of single unit space. Ie, + * an area of 512 bytes at 6k in c1 occupies 512 bytes at 6k of c1:u0, + * c1:u1, c1:u2 and c1:u3. Percpu access can be done by configuring + * percpu base registers UNIT_SIZE apart. + * + * There are usually many small percpu allocations many of them as + * small as 4 bytes. The allocator organizes chunks into lists + * according to free size and tries to allocate from the fullest one. + * Each chunk keeps the maximum contiguous area size hint which is + * guaranteed to be eqaul to or larger than the maximum contiguous + * area in the chunk. This helps the allocator not to iterate the + * chunk maps unnecessarily. + * + * Allocation state in each chunk is kept using an array of integers + * on chunk->map. A positive value in the map represents a free + * region and negative allocated. Allocation inside a chunk is done + * by scanning this map sequentially and serving the first matching + * entry. This is mostly copied from the percpu_modalloc() allocator. + * Chunks are also linked into a rb tree to ease address to chunk + * mapping during free. + * + * To use this allocator, arch code should do the followings. + * + * - define CONFIG_HAVE_DYNAMIC_PER_CPU_AREA + * + * - define __addr_to_pcpu_ptr() and __pcpu_ptr_to_addr() to translate + * regular address to percpu pointer and back + * + * - use pcpu_setup_static() during percpu area initialization to + * setup kernel static percpu area + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +#define PCPU_MIN_UNIT_PAGES_SHIFT 4 /* also max alloc size */ +#define PCPU_SLOT_BASE_SHIFT 5 /* 1-31 shares the same slot */ +#define PCPU_DFL_MAP_ALLOC 16 /* start a map with 16 ents */ + +struct pcpu_chunk { + struct list_head list; /* linked to pcpu_slot lists */ + struct rb_node rb_node; /* key is chunk->vm->addr */ + int free_size; /* free bytes in the chunk */ + int contig_hint; /* max contiguous size hint */ + struct vm_struct *vm; /* mapped vmalloc region */ + int map_used; /* # of map entries used */ + int map_alloc; /* # of map entries allocated */ + int *map; /* allocation map */ + struct page *page[]; /* #cpus * UNIT_PAGES */ +}; + +static int pcpu_unit_pages_shift; +static int pcpu_unit_pages; +static int pcpu_unit_shift; +static int pcpu_unit_size; +static int pcpu_chunk_size; +static int pcpu_nr_slots; +static size_t pcpu_chunk_struct_size; + +/* the address of the first chunk which starts with the kernel static area */ +void *pcpu_base_addr; +EXPORT_SYMBOL_GPL(pcpu_base_addr); + +/* the size of kernel static area */ +static int pcpu_static_size; + +/* + * One mutex to rule them all. + * + * The following mutex is grabbed in the outermost public alloc/free + * interface functions and released only when the operation is + * complete. As such, every function in this file other than the + * outermost functions are called under pcpu_mutex. + * + * It can easily be switched to use spinlock such that only the area + * allocation and page population commit are protected with it doing + * actual [de]allocation without holding any lock. However, given + * what this allocator does, I think it's better to let them run + * sequentially. + */ +static DEFINE_MUTEX(pcpu_mutex); + +static struct list_head *pcpu_slot; /* chunk list slots */ +static struct rb_root pcpu_addr_root = RB_ROOT; /* chunks by address */ + +static int pcpu_size_to_slot(int size) +{ + int highbit = fls(size); + return max(highbit - PCPU_SLOT_BASE_SHIFT + 2, 1); +} + +static int pcpu_chunk_slot(const struct pcpu_chunk *chunk) +{ + if (chunk->free_size < sizeof(int) || chunk->contig_hint < sizeof(int)) + return 0; + + return pcpu_size_to_slot(chunk->free_size); +} + +static int pcpu_page_idx(unsigned int cpu, int page_idx) +{ + return (cpu << pcpu_unit_pages_shift) + page_idx; +} + +static struct page **pcpu_chunk_pagep(struct pcpu_chunk *chunk, + unsigned int cpu, int page_idx) +{ + return &chunk->page[pcpu_page_idx(cpu, page_idx)]; +} + +static unsigned long pcpu_chunk_addr(struct pcpu_chunk *chunk, + unsigned int cpu, int page_idx) +{ + return (unsigned long)chunk->vm->addr + + (pcpu_page_idx(cpu, page_idx) << PAGE_SHIFT); +} + +static bool pcpu_chunk_page_occupied(struct pcpu_chunk *chunk, + int page_idx) +{ + return *pcpu_chunk_pagep(chunk, 0, page_idx) != NULL; +} + +/** + * pcpu_realloc - versatile realloc + * @p: the current pointer (can be NULL for new allocations) + * @size: the current size (can be 0 for new allocations) + * @new_size: the wanted new size (can be 0 for free) + * + * More robust realloc which can be used to allocate, resize or free a + * memory area of arbitrary size. If the needed size goes over + * PAGE_SIZE, kernel VM is used. + * + * RETURNS: + * The new pointer on success, NULL on failure. + */ +static void *pcpu_realloc(void *p, size_t size, size_t new_size) +{ + void *new; + + if (new_size <= PAGE_SIZE) + new = kmalloc(new_size, GFP_KERNEL); + else + new = vmalloc(new_size); + if (new_size && !new) + return NULL; + + memcpy(new, p, min(size, new_size)); + if (new_size > size) + memset(new + size, 0, new_size - size); + + if (size <= PAGE_SIZE) + kfree(p); + else + vfree(p); + + return new; +} + +/** + * pcpu_chunk_relocate - put chunk in the appropriate chunk slot + * @chunk: chunk of interest + * @oslot: the previous slot it was on + * + * This function is called after an allocation or free changed @chunk. + * New slot according to the changed state is determined and @chunk is + * moved to the slot. + */ +static void pcpu_chunk_relocate(struct pcpu_chunk *chunk, int oslot) +{ + int nslot = pcpu_chunk_slot(chunk); + + if (oslot != nslot) { + if (oslot < nslot) + list_move(&chunk->list, &pcpu_slot[nslot]); + else + list_move_tail(&chunk->list, &pcpu_slot[nslot]); + } +} + +static struct rb_node **pcpu_chunk_rb_search(void *addr, + struct rb_node **parentp) +{ + struct rb_node **p = &pcpu_addr_root.rb_node; + struct rb_node *parent = NULL; + struct pcpu_chunk *chunk; + + while (*p) { + parent = *p; + chunk = rb_entry(parent, struct pcpu_chunk, rb_node); + + if (addr < chunk->vm->addr) + p = &(*p)->rb_left; + else if (addr > chunk->vm->addr) + p = &(*p)->rb_right; + else + break; + } + + if (parentp) + *parentp = parent; + return p; +} + +/** + * pcpu_chunk_addr_search - search for chunk containing specified address + * @addr: address to search for + * + * Look for chunk which might contain @addr. More specifically, it + * searchs for the chunk with the highest start address which isn't + * beyond @addr. + * + * RETURNS: + * The address of the found chunk. + */ +static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr) +{ + struct rb_node *n, *parent; + struct pcpu_chunk *chunk; + + n = *pcpu_chunk_rb_search(addr, &parent); + if (!n) { + /* no exactly matching chunk, the parent is the closest */ + n = parent; + BUG_ON(!n); + } + chunk = rb_entry(n, struct pcpu_chunk, rb_node); + + if (addr < chunk->vm->addr) { + /* the parent was the next one, look for the previous one */ + n = rb_prev(n); + BUG_ON(!n); + chunk = rb_entry(n, struct pcpu_chunk, rb_node); + } + + return chunk; +} + +/** + * pcpu_chunk_addr_insert - insert chunk into address rb tree + * @new: chunk to insert + * + * Insert @new into address rb tree. + */ +static void pcpu_chunk_addr_insert(struct pcpu_chunk *new) +{ + struct rb_node **p, *parent; + + p = pcpu_chunk_rb_search(new->vm->addr, &parent); + BUG_ON(*p); + rb_link_node(&new->rb_node, parent, p); + rb_insert_color(&new->rb_node, &pcpu_addr_root); +} + +/** + * pcpu_split_block - split a map block + * @chunk: chunk of interest + * @i: index of map block to split + * @head: head size (can be 0) + * @tail: tail size (can be 0) + * + * Split the @i'th map block into two or three blocks. If @head is + * non-zero, @head bytes block is inserted before block @i moving it + * to @i+1 and reducing its size by @head bytes. + * + * If @tail is non-zero, the target block, which can be @i or @i+1 + * depending on @head, is reduced by @tail bytes and @tail byte block + * is inserted after the target block. + * + * RETURNS: + * 0 on success, -errno on failure. + */ +static int pcpu_split_block(struct pcpu_chunk *chunk, int i, int head, int tail) +{ + int nr_extra = !!head + !!tail; + int target = chunk->map_used + nr_extra; + + /* reallocation required? */ + if (chunk->map_alloc < target) { + int new_alloc = chunk->map_alloc; + int *new; + + while (new_alloc < target) + new_alloc *= 2; + + new = pcpu_realloc(chunk->map, + chunk->map_alloc * sizeof(new[0]), + new_alloc * sizeof(new[0])); + if (!new) + return -ENOMEM; + + chunk->map_alloc = new_alloc; + chunk->map = new; + } + + /* insert a new subblock */ + memmove(&chunk->map[i + nr_extra], &chunk->map[i], + sizeof(chunk->map[0]) * (chunk->map_used - i)); + chunk->map_used += nr_extra; + + if (head) { + chunk->map[i + 1] = chunk->map[i] - head; + chunk->map[i++] = head; + } + if (tail) { + chunk->map[i++] -= tail; + chunk->map[i] = tail; + } + return 0; +} + +/** + * pcpu_alloc_area - allocate area from a pcpu_chunk + * @chunk: chunk of interest + * @size: wanted size + * @align: wanted align + * + * Try to allocate @size bytes area aligned at @align from @chunk. + * Note that this function only allocates the offset. It doesn't + * populate or map the area. + * + * RETURNS: + * Allocated offset in @chunk on success, -errno on failure. + */ +static int pcpu_alloc_area(struct pcpu_chunk *chunk, int size, int align) +{ + int oslot = pcpu_chunk_slot(chunk); + int max_contig = 0; + int i, off; + + /* + * The static chunk initially doesn't have map attached + * because kmalloc wasn't available during init. Give it one. + */ + if (unlikely(!chunk->map)) { + chunk->map = pcpu_realloc(NULL, 0, + PCPU_DFL_MAP_ALLOC * sizeof(chunk->map[0])); + if (!chunk->map) + return -ENOMEM; + + chunk->map_alloc = PCPU_DFL_MAP_ALLOC; + chunk->map[chunk->map_used++] = -pcpu_static_size; + if (chunk->free_size) + chunk->map[chunk->map_used++] = chunk->free_size; + } + + for (i = 0, off = 0; i < chunk->map_used; off += abs(chunk->map[i++])) { + bool is_last = i + 1 == chunk->map_used; + int head, tail; + + /* extra for alignment requirement */ + head = ALIGN(off, align) - off; + BUG_ON(i == 0 && head != 0); + + if (chunk->map[i] < 0) + continue; + if (chunk->map[i] < head + size) { + max_contig = max(chunk->map[i], max_contig); + continue; + } + + /* + * If head is small or the previous block is free, + * merge'em. Note that 'small' is defined as smaller + * than sizeof(int), which is very small but isn't too + * uncommon for percpu allocations. + */ + if (head && (head < sizeof(int) || chunk->map[i - 1] > 0)) { + if (chunk->map[i - 1] > 0) + chunk->map[i - 1] += head; + else { + chunk->map[i - 1] -= head; + chunk->free_size -= head; + } + chunk->map[i] -= head; + off += head; + head = 0; + } + + /* if tail is small, just keep it around */ + tail = chunk->map[i] - head - size; + if (tail < sizeof(int)) + tail = 0; + + /* split if warranted */ + if (head || tail) { + if (pcpu_split_block(chunk, i, head, tail)) + return -ENOMEM; + if (head) { + i++; + off += head; + max_contig = max(chunk->map[i - 1], max_contig); + } + if (tail) + max_contig = max(chunk->map[i + 1], max_contig); + } + + /* update hint and mark allocated */ + if (is_last) + chunk->contig_hint = max_contig; /* fully scanned */ + else + chunk->contig_hint = max(chunk->contig_hint, + max_contig); + + chunk->free_size -= chunk->map[i]; + chunk->map[i] = -chunk->map[i]; + + pcpu_chunk_relocate(chunk, oslot); + return off; + } + + chunk->contig_hint = max_contig; /* fully scanned */ + pcpu_chunk_relocate(chunk, oslot); + + /* + * Tell the upper layer that this chunk has no area left. + * Note that this is not an error condition but a notification + * to upper layer that it needs to look at other chunks. + * -ENOSPC is chosen as it isn't used in memory subsystem and + * matches the meaning in a way. + */ + return -ENOSPC; +} + +/** + * pcpu_free_area - free area to a pcpu_chunk + * @chunk: chunk of interest + * @freeme: offset of area to free + * + * Free area starting from @freeme to @chunk. Note that this function + * only modifies the allocation map. It doesn't depopulate or unmap + * the area. + */ +static void pcpu_free_area(struct pcpu_chunk *chunk, int freeme) +{ + int oslot = pcpu_chunk_slot(chunk); + int i, off; + + for (i = 0, off = 0; i < chunk->map_used; off += abs(chunk->map[i++])) + if (off == freeme) + break; + BUG_ON(off != freeme); + BUG_ON(chunk->map[i] > 0); + + chunk->map[i] = -chunk->map[i]; + chunk->free_size += chunk->map[i]; + + /* merge with previous? */ + if (i > 0 && chunk->map[i - 1] >= 0) { + chunk->map[i - 1] += chunk->map[i]; + chunk->map_used--; + memmove(&chunk->map[i], &chunk->map[i + 1], + (chunk->map_used - i) * sizeof(chunk->map[0])); + i--; + } + /* merge with next? */ + if (i + 1 < chunk->map_used && chunk->map[i + 1] >= 0) { + chunk->map[i] += chunk->map[i + 1]; + chunk->map_used--; + memmove(&chunk->map[i + 1], &chunk->map[i + 2], + (chunk->map_used - (i + 1)) * sizeof(chunk->map[0])); + } + + chunk->contig_hint = max(chunk->map[i], chunk->contig_hint); + pcpu_chunk_relocate(chunk, oslot); +} + +/** + * pcpu_unmap - unmap pages out of a pcpu_chunk + * @chunk: chunk of interest + * @page_start: page index of the first page to unmap + * @page_end: page index of the last page to unmap + 1 + * @flush: whether to flush cache and tlb or not + * + * For each cpu, unmap pages [@page_start,@page_end) out of @chunk. + * If @flush is true, vcache is flushed before unmapping and tlb + * after. + */ +static void pcpu_unmap(struct pcpu_chunk *chunk, int page_start, int page_end, + bool flush) +{ + unsigned int last = num_possible_cpus() - 1; + unsigned int cpu; + + /* + * Each flushing trial can be very expensive, issue flush on + * the whole region at once rather than doing it for each cpu. + * This could be an overkill but is more scalable. + */ + if (flush) + flush_cache_vunmap(pcpu_chunk_addr(chunk, 0, page_start), + pcpu_chunk_addr(chunk, last, page_end)); + + for_each_possible_cpu(cpu) + unmap_kernel_range_noflush( + pcpu_chunk_addr(chunk, cpu, page_start), + (page_end - page_start) << PAGE_SHIFT); + + /* ditto as flush_cache_vunmap() */ + if (flush) + flush_tlb_kernel_range(pcpu_chunk_addr(chunk, 0, page_start), + pcpu_chunk_addr(chunk, last, page_end)); +} + +/** + * pcpu_depopulate_chunk - depopulate and unmap an area of a pcpu_chunk + * @chunk: chunk to depopulate + * @off: offset to the area to depopulate + * @size: size of the area to depopulate + * @flush: whether to flush cache and tlb or not + * + * For each cpu, depopulate and unmap pages [@page_start,@page_end) + * from @chunk. If @flush is true, vcache is flushed before unmapping + * and tlb after. + */ +static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, size_t off, + size_t size, bool flush) +{ + int page_start = PFN_DOWN(off); + int page_end = PFN_UP(off + size); + int unmap_start = -1; + int uninitialized_var(unmap_end); + unsigned int cpu; + int i; + + for (i = page_start; i < page_end; i++) { + for_each_possible_cpu(cpu) { + struct page **pagep = pcpu_chunk_pagep(chunk, cpu, i); + + if (!*pagep) + continue; + + __free_page(*pagep); + + /* + * If it's partial depopulation, it might get + * populated or depopulated again. Mark the + * page gone. + */ + *pagep = NULL; + + unmap_start = unmap_start < 0 ? i : unmap_start; + unmap_end = i + 1; + } + } + + if (unmap_start >= 0) + pcpu_unmap(chunk, unmap_start, unmap_end, flush); +} + +/** + * pcpu_map - map pages into a pcpu_chunk + * @chunk: chunk of interest + * @page_start: page index of the first page to map + * @page_end: page index of the last page to map + 1 + * + * For each cpu, map pages [@page_start,@page_end) into @chunk. + * vcache is flushed afterwards. + */ +static int pcpu_map(struct pcpu_chunk *chunk, int page_start, int page_end) +{ + unsigned int last = num_possible_cpus() - 1; + unsigned int cpu; + int err; + + for_each_possible_cpu(cpu) { + err = map_kernel_range_noflush( + pcpu_chunk_addr(chunk, cpu, page_start), + (page_end - page_start) << PAGE_SHIFT, + PAGE_KERNEL, + pcpu_chunk_pagep(chunk, cpu, page_start)); + if (err < 0) + return err; + } + + /* flush at once, please read comments in pcpu_unmap() */ + flush_cache_vmap(pcpu_chunk_addr(chunk, 0, page_start), + pcpu_chunk_addr(chunk, last, page_end)); + return 0; +} + +/** + * pcpu_populate_chunk - populate and map an area of a pcpu_chunk + * @chunk: chunk of interest + * @off: offset to the area to populate + * @size: size of the area to populate + * + * For each cpu, populate and map pages [@page_start,@page_end) into + * @chunk. The area is cleared on return. + */ +static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int off, int size) +{ + const gfp_t alloc_mask = GFP_KERNEL | __GFP_HIGHMEM | __GFP_COLD; + int page_start = PFN_DOWN(off); + int page_end = PFN_UP(off + size); + int map_start = -1; + int map_end; + unsigned int cpu; + int i; + + for (i = page_start; i < page_end; i++) { + if (pcpu_chunk_page_occupied(chunk, i)) { + if (map_start >= 0) { + if (pcpu_map(chunk, map_start, map_end)) + goto err; + map_start = -1; + } + continue; + } + + map_start = map_start < 0 ? i : map_start; + map_end = i + 1; + + for_each_possible_cpu(cpu) { + struct page **pagep = pcpu_chunk_pagep(chunk, cpu, i); + + *pagep = alloc_pages_node(cpu_to_node(cpu), + alloc_mask, 0); + if (!*pagep) + goto err; + } + } + + if (map_start >= 0 && pcpu_map(chunk, map_start, map_end)) + goto err; + + for_each_possible_cpu(cpu) + memset(chunk->vm->addr + (cpu << pcpu_unit_shift) + off, 0, + size); + + return 0; +err: + /* likely under heavy memory pressure, give memory back */ + pcpu_depopulate_chunk(chunk, off, size, true); + return -ENOMEM; +} + +static void free_pcpu_chunk(struct pcpu_chunk *chunk) +{ + if (!chunk) + return; + if (chunk->vm) + free_vm_area(chunk->vm); + pcpu_realloc(chunk->map, chunk->map_alloc * sizeof(chunk->map[0]), 0); + kfree(chunk); +} + +static struct pcpu_chunk *alloc_pcpu_chunk(void) +{ + struct pcpu_chunk *chunk; + + chunk = kzalloc(pcpu_chunk_struct_size, GFP_KERNEL); + if (!chunk) + return NULL; + + chunk->map = pcpu_realloc(NULL, 0, + PCPU_DFL_MAP_ALLOC * sizeof(chunk->map[0])); + chunk->map_alloc = PCPU_DFL_MAP_ALLOC; + chunk->map[chunk->map_used++] = pcpu_unit_size; + + chunk->vm = get_vm_area(pcpu_chunk_size, GFP_KERNEL); + if (!chunk->vm) { + free_pcpu_chunk(chunk); + return NULL; + } + + INIT_LIST_HEAD(&chunk->list); + chunk->free_size = pcpu_unit_size; + chunk->contig_hint = pcpu_unit_size; + + return chunk; +} + +/** + * __alloc_percpu - allocate percpu area + * @size: size of area to allocate + * @align: alignment of area (max PAGE_SIZE) + * + * Allocate percpu area of @size bytes aligned at @align. Might + * sleep. Might trigger writeouts. + * + * RETURNS: + * Percpu pointer to the allocated area on success, NULL on failure. + */ +void *__alloc_percpu(size_t size, size_t align) +{ + void *ptr = NULL; + struct pcpu_chunk *chunk; + int slot, off; + + if (unlikely(!size || size > PAGE_SIZE << PCPU_MIN_UNIT_PAGES_SHIFT || + align > PAGE_SIZE)) { + WARN(true, "illegal size (%zu) or align (%zu) for " + "percpu allocation\n", size, align); + return NULL; + } + + mutex_lock(&pcpu_mutex); + + /* allocate area */ + for (slot = pcpu_size_to_slot(size); slot < pcpu_nr_slots; slot++) { + list_for_each_entry(chunk, &pcpu_slot[slot], list) { + if (size > chunk->contig_hint) + continue; + off = pcpu_alloc_area(chunk, size, align); + if (off >= 0) + goto area_found; + if (off != -ENOSPC) + goto out_unlock; + } + } + + /* hmmm... no space left, create a new chunk */ + chunk = alloc_pcpu_chunk(); + if (!chunk) + goto out_unlock; + pcpu_chunk_relocate(chunk, -1); + pcpu_chunk_addr_insert(chunk); + + off = pcpu_alloc_area(chunk, size, align); + if (off < 0) + goto out_unlock; + +area_found: + /* populate, map and clear the area */ + if (pcpu_populate_chunk(chunk, off, size)) { + pcpu_free_area(chunk, off); + goto out_unlock; + } + + ptr = __addr_to_pcpu_ptr(chunk->vm->addr + off); +out_unlock: + mutex_unlock(&pcpu_mutex); + return ptr; +} +EXPORT_SYMBOL_GPL(__alloc_percpu); + +static void pcpu_kill_chunk(struct pcpu_chunk *chunk) +{ + pcpu_depopulate_chunk(chunk, 0, pcpu_unit_size, false); + list_del(&chunk->list); + rb_erase(&chunk->rb_node, &pcpu_addr_root); + free_pcpu_chunk(chunk); +} + +/** + * free_percpu - free percpu area + * @ptr: pointer to area to free + * + * Free percpu area @ptr. Might sleep. + */ +void free_percpu(void *ptr) +{ + void *addr = __pcpu_ptr_to_addr(ptr); + struct pcpu_chunk *chunk; + int off; + + if (!ptr) + return; + + mutex_lock(&pcpu_mutex); + + chunk = pcpu_chunk_addr_search(addr); + off = addr - chunk->vm->addr; + + pcpu_free_area(chunk, off); + + /* the chunk became fully free, kill one if there are other free ones */ + if (chunk->free_size == pcpu_unit_size) { + struct pcpu_chunk *pos; + + list_for_each_entry(pos, + &pcpu_slot[pcpu_chunk_slot(chunk)], list) + if (pos != chunk) { + pcpu_kill_chunk(pos); + break; + } + } + + mutex_unlock(&pcpu_mutex); +} +EXPORT_SYMBOL_GPL(free_percpu); + +/** + * pcpu_setup_static - initialize kernel static percpu area + * @populate_pte_fn: callback to allocate pagetable + * @pages: num_possible_cpus() * PFN_UP(cpu_size) pages + * + * Initialize kernel static percpu area. The caller should allocate + * all the necessary pages and pass them in @pages. + * @populate_pte_fn() is called on each page to be used for percpu + * mapping and is responsible for making sure all the necessary page + * tables for the page is allocated. + * + * RETURNS: + * The determined pcpu_unit_size which can be used to initialize + * percpu access. + */ +size_t __init pcpu_setup_static(pcpu_populate_pte_fn_t populate_pte_fn, + struct page **pages, size_t cpu_size) +{ + static struct vm_struct static_vm; + struct pcpu_chunk *static_chunk; + int nr_cpu_pages = DIV_ROUND_UP(cpu_size, PAGE_SIZE); + unsigned int cpu; + int err, i; + + pcpu_unit_pages_shift = max_t(int, PCPU_MIN_UNIT_PAGES_SHIFT, + order_base_2(cpu_size) - PAGE_SHIFT); + + pcpu_static_size = cpu_size; + pcpu_unit_pages = 1 << pcpu_unit_pages_shift; + pcpu_unit_shift = PAGE_SHIFT + pcpu_unit_pages_shift; + pcpu_unit_size = 1 << pcpu_unit_shift; + pcpu_chunk_size = num_possible_cpus() * pcpu_unit_size; + pcpu_nr_slots = pcpu_size_to_slot(pcpu_unit_size) + 1; + pcpu_chunk_struct_size = sizeof(struct pcpu_chunk) + + (1 << pcpu_unit_pages_shift) * sizeof(struct page *); + + /* allocate chunk slots */ + pcpu_slot = alloc_bootmem(pcpu_nr_slots * sizeof(pcpu_slot[0])); + for (i = 0; i < pcpu_nr_slots; i++) + INIT_LIST_HEAD(&pcpu_slot[i]); + + /* init and register vm area */ + static_vm.flags = VM_ALLOC; + static_vm.size = pcpu_chunk_size; + vm_area_register_early(&static_vm); + + /* init static_chunk */ + static_chunk = alloc_bootmem(pcpu_chunk_struct_size); + INIT_LIST_HEAD(&static_chunk->list); + static_chunk->vm = &static_vm; + static_chunk->free_size = pcpu_unit_size - pcpu_static_size; + static_chunk->contig_hint = static_chunk->free_size; + + /* assign pages and map them */ + for_each_possible_cpu(cpu) { + for (i = 0; i < nr_cpu_pages; i++) { + *pcpu_chunk_pagep(static_chunk, cpu, i) = *pages++; + populate_pte_fn(pcpu_chunk_addr(static_chunk, cpu, i)); + } + } + + err = pcpu_map(static_chunk, 0, nr_cpu_pages); + if (err) + panic("failed to setup static percpu area, err=%d\n", err); + + /* link static_chunk in */ + pcpu_chunk_relocate(static_chunk, -1); + pcpu_chunk_addr_insert(static_chunk); + + /* we're done */ + pcpu_base_addr = (void *)pcpu_chunk_addr(static_chunk, 0, 0); + return pcpu_unit_size; +} -- cgit v1.2.3-70-g09d2 From 8d408b4be37bc49c9086531f2ebe411cf5731746 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 24 Feb 2009 11:57:21 +0900 Subject: percpu: give more latitude to arch specific first chunk initialization Impact: more latitude for first percpu chunk allocation The first percpu chunk serves the kernel static percpu area and may or may not contain extra room for further dynamic allocation. Initialization of the first chunk needs to be done before normal memory allocation service is up, so it has its own init path - pcpu_setup_static(). It seems archs need more latitude while initializing the first chunk for example to take advantage of large page mapping. This patch makes the following changes to allow this. * Define PERCPU_DYNAMIC_RESERVE to give arch hint about how much space to reserve in the first chunk for further dynamic allocation. * Rename pcpu_setup_static() to pcpu_setup_first_chunk(). * Make pcpu_setup_first_chunk() much more flexible by fetching page pointer by callback and adding optional @unit_size, @free_size and @base_addr arguments which allow archs to selectively part of chunk initialization to their likings. Signed-off-by: Tejun Heo --- arch/x86/kernel/setup_percpu.c | 15 ++++- include/linux/percpu.h | 39 ++++++++++- mm/percpu.c | 149 ++++++++++++++++++++++++++++++++--------- 3 files changed, 167 insertions(+), 36 deletions(-) (limited to 'include/linux/percpu.h') diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index 671e6528a82..d928e888720 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -41,6 +41,16 @@ unsigned long __per_cpu_offset[NR_CPUS] __read_mostly = { }; EXPORT_SYMBOL(__per_cpu_offset); +static struct page **pcpu4k_pages __initdata; +static int pcpu4k_nr_static_pages __initdata; + +static struct page * __init pcpu4k_get_page(unsigned int cpu, int pageno) +{ + if (pageno < pcpu4k_nr_static_pages) + return pcpu4k_pages[cpu * pcpu4k_nr_static_pages + pageno]; + return NULL; +} + static void __init pcpu4k_populate_pte(unsigned long addr) { populate_extra_pte(addr); @@ -109,7 +119,10 @@ void __init setup_per_cpu_areas(void) } } - pcpu_unit_size = pcpu_setup_static(pcpu4k_populate_pte, pages, size); + pcpu4k_pages = pages; + pcpu4k_nr_static_pages = nr_cpu_pages; + pcpu_unit_size = pcpu_setup_first_chunk(pcpu4k_get_page, size, 0, 0, + NULL, pcpu4k_populate_pte); free_bootmem(__pa(pages), pages_size); diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 18080995ff3..910beb0abea 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -78,12 +78,47 @@ #ifdef CONFIG_HAVE_DYNAMIC_PER_CPU_AREA +/* minimum unit size, also is the maximum supported allocation size */ +#define PCPU_MIN_UNIT_SIZE (16UL << PAGE_SHIFT) + +/* + * PERCPU_DYNAMIC_RESERVE indicates the amount of free area to piggy + * back on the first chunk if arch is manually allocating and mapping + * it for faster access (as a part of large page mapping for example). + * Note that dynamic percpu allocator covers both static and dynamic + * areas, so these values are bigger than PERCPU_MODULE_RESERVE. + * + * On typical configuration with modules, the following values leave + * about 8k of free space on the first chunk after boot on both x86_32 + * and 64 when module support is enabled. When module support is + * disabled, it's much tighter. + */ +#ifndef PERCPU_DYNAMIC_RESERVE +# if BITS_PER_LONG > 32 +# ifdef CONFIG_MODULES +# define PERCPU_DYNAMIC_RESERVE (6 << PAGE_SHIFT) +# else +# define PERCPU_DYNAMIC_RESERVE (4 << PAGE_SHIFT) +# endif +# else +# ifdef CONFIG_MODULES +# define PERCPU_DYNAMIC_RESERVE (4 << PAGE_SHIFT) +# else +# define PERCPU_DYNAMIC_RESERVE (2 << PAGE_SHIFT) +# endif +# endif +#endif /* PERCPU_DYNAMIC_RESERVE */ + extern void *pcpu_base_addr; +typedef struct page * (*pcpu_get_page_fn_t)(unsigned int cpu, int pageno); typedef void (*pcpu_populate_pte_fn_t)(unsigned long addr); -extern size_t __init pcpu_setup_static(pcpu_populate_pte_fn_t populate_pte_fn, - struct page **pages, size_t cpu_size); +extern size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn, + size_t static_size, size_t unit_size, + size_t free_size, void *base_addr, + pcpu_populate_pte_fn_t populate_pte_fn); + /* * Use this to get to a cpu's version of the per-cpu object * dynamically allocated. Non-atomic access to the current CPU's diff --git a/mm/percpu.c b/mm/percpu.c index d9e6e5d1dbd..9ac01980cce 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -48,8 +48,8 @@ * - define __addr_to_pcpu_ptr() and __pcpu_ptr_to_addr() to translate * regular address to percpu pointer and back * - * - use pcpu_setup_static() during percpu area initialization to - * setup kernel static percpu area + * - use pcpu_setup_first_chunk() during percpu area initialization to + * setup the first chunk containing the kernel static percpu area */ #include @@ -67,7 +67,6 @@ #include #include -#define PCPU_MIN_UNIT_PAGES 16 /* max alloc size in pages */ #define PCPU_SLOT_BASE_SHIFT 5 /* 1-31 shares the same slot */ #define PCPU_DFL_MAP_ALLOC 16 /* start a map with 16 ents */ @@ -80,6 +79,7 @@ struct pcpu_chunk { int map_used; /* # of map entries used */ int map_alloc; /* # of map entries allocated */ int *map; /* allocation map */ + bool immutable; /* no [de]population allowed */ struct page *page[]; /* #cpus * UNIT_PAGES */ }; @@ -521,6 +521,9 @@ static void pcpu_unmap(struct pcpu_chunk *chunk, int page_start, int page_end, unsigned int last = num_possible_cpus() - 1; unsigned int cpu; + /* unmap must not be done on immutable chunk */ + WARN_ON(chunk->immutable); + /* * Each flushing trial can be very expensive, issue flush on * the whole region at once rather than doing it for each cpu. @@ -602,6 +605,9 @@ static int pcpu_map(struct pcpu_chunk *chunk, int page_start, int page_end) unsigned int cpu; int err; + /* map must not be done on immutable chunk */ + WARN_ON(chunk->immutable); + for_each_possible_cpu(cpu) { err = map_kernel_range_noflush( pcpu_chunk_addr(chunk, cpu, page_start), @@ -727,8 +733,7 @@ void *__alloc_percpu(size_t size, size_t align) struct pcpu_chunk *chunk; int slot, off; - if (unlikely(!size || size > PCPU_MIN_UNIT_PAGES * PAGE_SIZE || - align > PAGE_SIZE)) { + if (unlikely(!size || size > PCPU_MIN_UNIT_SIZE || align > PAGE_SIZE)) { WARN(true, "illegal size (%zu) or align (%zu) for " "percpu allocation\n", size, align); return NULL; @@ -776,6 +781,7 @@ EXPORT_SYMBOL_GPL(__alloc_percpu); static void pcpu_kill_chunk(struct pcpu_chunk *chunk) { + WARN_ON(chunk->immutable); pcpu_depopulate_chunk(chunk, 0, pcpu_unit_size, false); list_del(&chunk->list); rb_erase(&chunk->rb_node, &pcpu_addr_root); @@ -821,33 +827,73 @@ void free_percpu(void *ptr) EXPORT_SYMBOL_GPL(free_percpu); /** - * pcpu_setup_static - initialize kernel static percpu area - * @populate_pte_fn: callback to allocate pagetable - * @pages: num_possible_cpus() * PFN_UP(cpu_size) pages - * @cpu_size: the size of static percpu area in bytes - * - * Initialize kernel static percpu area. The caller should allocate - * all the necessary pages and pass them in @pages. - * @populate_pte_fn() is called on each page to be used for percpu - * mapping and is responsible for making sure all the necessary page - * tables for the page is allocated. + * pcpu_setup_first_chunk - initialize the first percpu chunk + * @get_page_fn: callback to fetch page pointer + * @static_size: the size of static percpu area in bytes + * @unit_size: unit size in bytes, must be multiple of PAGE_SIZE, 0 for auto + * @free_size: free size in bytes, 0 for auto + * @base_addr: mapped address, NULL for auto + * @populate_pte_fn: callback to allocate pagetable, NULL if unnecessary + * + * Initialize the first percpu chunk which contains the kernel static + * perpcu area. This function is to be called from arch percpu area + * setup path. The first two parameters are mandatory. The rest are + * optional. + * + * @get_page_fn() should return pointer to percpu page given cpu + * number and page number. It should at least return enough pages to + * cover the static area. The returned pages for static area should + * have been initialized with valid data. If @unit_size is specified, + * it can also return pages after the static area. NULL return + * indicates end of pages for the cpu. Note that @get_page_fn() must + * return the same number of pages for all cpus. + * + * @unit_size, if non-zero, determines unit size and must be aligned + * to PAGE_SIZE and equal to or larger than @static_size + @free_size. + * + * @free_size determines the number of free bytes after the static + * area in the first chunk. If zero, whatever left is available. + * Specifying non-zero value make percpu leave the area after + * @static_size + @free_size alone. + * + * Non-null @base_addr means that the caller already allocated virtual + * region for the first chunk and mapped it. percpu must not mess + * with the chunk. Note that @base_addr with 0 @unit_size or non-NULL + * @populate_pte_fn doesn't make any sense. + * + * @populate_pte_fn is used to populate the pagetable. NULL means the + * caller already populated the pagetable. * * RETURNS: * The determined pcpu_unit_size which can be used to initialize * percpu access. */ -size_t __init pcpu_setup_static(pcpu_populate_pte_fn_t populate_pte_fn, - struct page **pages, size_t cpu_size) +size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn, + size_t static_size, size_t unit_size, + size_t free_size, void *base_addr, + pcpu_populate_pte_fn_t populate_pte_fn) { static struct vm_struct static_vm; struct pcpu_chunk *static_chunk; - int nr_cpu_pages = DIV_ROUND_UP(cpu_size, PAGE_SIZE); unsigned int cpu; + int nr_pages; int err, i; - pcpu_unit_pages = max_t(int, PCPU_MIN_UNIT_PAGES, PFN_UP(cpu_size)); + /* santiy checks */ + BUG_ON(!static_size); + BUG_ON(!unit_size && free_size); + BUG_ON(unit_size && unit_size < static_size + free_size); + BUG_ON(unit_size & ~PAGE_MASK); + BUG_ON(base_addr && !unit_size); + BUG_ON(base_addr && populate_pte_fn); - pcpu_static_size = cpu_size; + if (unit_size) + pcpu_unit_pages = unit_size >> PAGE_SHIFT; + else + pcpu_unit_pages = max_t(int, PCPU_MIN_UNIT_SIZE >> PAGE_SHIFT, + PFN_UP(static_size)); + + pcpu_static_size = static_size; pcpu_unit_size = pcpu_unit_pages << PAGE_SHIFT; pcpu_chunk_size = num_possible_cpus() * pcpu_unit_size; pcpu_chunk_struct_size = sizeof(struct pcpu_chunk) @@ -862,29 +908,66 @@ size_t __init pcpu_setup_static(pcpu_populate_pte_fn_t populate_pte_fn, for (i = 0; i < pcpu_nr_slots; i++) INIT_LIST_HEAD(&pcpu_slot[i]); - /* init and register vm area */ - static_vm.flags = VM_ALLOC; - static_vm.size = pcpu_chunk_size; - vm_area_register_early(&static_vm, PAGE_SIZE); - /* init static_chunk */ static_chunk = alloc_bootmem(pcpu_chunk_struct_size); INIT_LIST_HEAD(&static_chunk->list); static_chunk->vm = &static_vm; - static_chunk->free_size = pcpu_unit_size - pcpu_static_size; + + if (free_size) + static_chunk->free_size = free_size; + else + static_chunk->free_size = pcpu_unit_size - pcpu_static_size; + static_chunk->contig_hint = static_chunk->free_size; - /* assign pages and map them */ + /* allocate vm address */ + static_vm.flags = VM_ALLOC; + static_vm.size = pcpu_chunk_size; + + if (!base_addr) + vm_area_register_early(&static_vm, PAGE_SIZE); + else { + /* + * Pages already mapped. No need to remap into + * vmalloc area. In this case the static chunk can't + * be mapped or unmapped by percpu and is marked + * immutable. + */ + static_vm.addr = base_addr; + static_chunk->immutable = true; + } + + /* assign pages */ + nr_pages = -1; for_each_possible_cpu(cpu) { - for (i = 0; i < nr_cpu_pages; i++) { - *pcpu_chunk_pagep(static_chunk, cpu, i) = *pages++; - populate_pte_fn(pcpu_chunk_addr(static_chunk, cpu, i)); + for (i = 0; i < pcpu_unit_pages; i++) { + struct page *page = get_page_fn(cpu, i); + + if (!page) + break; + *pcpu_chunk_pagep(static_chunk, cpu, i) = page; } + + BUG_ON(i < PFN_UP(pcpu_static_size)); + + if (nr_pages < 0) + nr_pages = i; + else + BUG_ON(nr_pages != i); } - err = pcpu_map(static_chunk, 0, nr_cpu_pages); - if (err) - panic("failed to setup static percpu area, err=%d\n", err); + /* map them */ + if (populate_pte_fn) { + for_each_possible_cpu(cpu) + for (i = 0; i < nr_pages; i++) + populate_pte_fn(pcpu_chunk_addr(static_chunk, + cpu, i)); + + err = pcpu_map(static_chunk, 0, nr_pages); + if (err) + panic("failed to setup static percpu area, err=%d\n", + err); + } /* link static_chunk in */ pcpu_chunk_relocate(static_chunk, -1); -- cgit v1.2.3-70-g09d2 From d2b0261506602bd969164879206027b30358ffdf Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 25 Feb 2009 14:36:45 +0100 Subject: alloc_percpu: fix UP build Impact: build fix the !SMP branch had a 'gfp' leftover: include/linux/percpu.h: In function '__alloc_percpu': include/linux/percpu.h:160: error: 'gfp' undeclared (first use in this function) include/linux/percpu.h:160: error: (Each undeclared identifier is reported only once include/linux/percpu.h:160: error: for each function it appears in.) Use GFP_KERNEL like the SMP version does. Cc: Rusty Russell Cc: Tejun Heo Signed-off-by: Ingo Molnar --- include/linux/percpu.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/percpu.h') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 910beb0abea..d8e5a9abbce 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -157,7 +157,7 @@ static inline void *__alloc_percpu(size_t size, size_t align) * percpu sections on SMP for which this path isn't used. */ WARN_ON_ONCE(align > __alignof__(unsigned long long)); - return kzalloc(size, gfp); + return kzalloc(size, GFP_KERNEL); } static inline void free_percpu(void *p) -- cgit v1.2.3-70-g09d2 From e317603694bfd17b28a40de9d65e1a4ec12f816e Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 26 Feb 2009 10:54:17 +0900 Subject: percpu: fix too low alignment restriction on UP UP __alloc_percpu() triggered WARN_ON_ONCE() if the requested alignment is larger than that of unsigned long long, which is too small for all the cacheline aligned allocations. Bump it up to SMP_CACHE_BYTES which kmalloc allocations generally guarantee. Signed-off-by: Tejun Heo Reported-by: Ingo Molnar --- include/linux/percpu.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/percpu.h') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index d8e5a9abbce..545b068bcb7 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -156,7 +156,7 @@ static inline void *__alloc_percpu(size_t size, size_t align) * 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 > __alignof__(unsigned long long)); + WARN_ON_ONCE(align > SMP_CACHE_BYTES); return kzalloc(size, GFP_KERNEL); } -- cgit v1.2.3-70-g09d2 From 6a242909b01120f6f3d571c0b75e20ec61f0d8d3 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 6 Mar 2009 14:33:58 +0900 Subject: percpu: clean up percpu constants Impact: cleaup Make the following cleanups. * There isn't much arch-specific about PERCPU_MODULE_RESERVE. Always define it whether arch overrides PERCPU_ENOUGH_ROOM or not. * blackfin overrides PERCPU_ENOUGH_ROOM to align static area size. Do it by default. * percpu allocation sizes doesn't have much to do with the page size. Don't use PAGE_SHIFT in their definition. Signed-off-by: Tejun Heo Cc: Bryan Wu --- arch/blackfin/include/asm/percpu.h | 10 ---------- include/linux/percpu.h | 24 +++++++++++++----------- 2 files changed, 13 insertions(+), 21 deletions(-) (limited to 'include/linux/percpu.h') diff --git a/arch/blackfin/include/asm/percpu.h b/arch/blackfin/include/asm/percpu.h index 797c0c16506..c94c7bc88c7 100644 --- a/arch/blackfin/include/asm/percpu.h +++ b/arch/blackfin/include/asm/percpu.h @@ -3,14 +3,4 @@ #include -#ifdef CONFIG_MODULES -#define PERCPU_MODULE_RESERVE 8192 -#else -#define PERCPU_MODULE_RESERVE 0 -#endif - -#define PERCPU_ENOUGH_ROOM \ - (ALIGN(__per_cpu_end - __per_cpu_start, SMP_CACHE_BYTES) + \ - PERCPU_MODULE_RESERVE) - #endif /* __ARCH_BLACKFIN_PERCPU__ */ diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 545b068bcb7..2d34b038fe7 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -5,6 +5,7 @@ #include /* For kmalloc() */ #include #include +#include #include @@ -52,17 +53,18 @@ #define EXPORT_PER_CPU_SYMBOL(var) EXPORT_SYMBOL(per_cpu__##var) #define EXPORT_PER_CPU_SYMBOL_GPL(var) EXPORT_SYMBOL_GPL(per_cpu__##var) -/* Enough to cover all DEFINE_PER_CPUs in kernel, including modules. */ -#ifndef PERCPU_ENOUGH_ROOM +/* enough to cover all DEFINE_PER_CPUs in modules */ #ifdef CONFIG_MODULES -#define PERCPU_MODULE_RESERVE 8192 +#define PERCPU_MODULE_RESERVE (8 << 10) #else -#define PERCPU_MODULE_RESERVE 0 +#define PERCPU_MODULE_RESERVE 0 #endif +#ifndef PERCPU_ENOUGH_ROOM #define PERCPU_ENOUGH_ROOM \ - (__per_cpu_end - __per_cpu_start + PERCPU_MODULE_RESERVE) -#endif /* PERCPU_ENOUGH_ROOM */ + (ALIGN(__per_cpu_end - __per_cpu_start, SMP_CACHE_BYTES) + \ + PERCPU_MODULE_RESERVE) +#endif /* * Must be an lvalue. Since @var must be a simple identifier, @@ -79,7 +81,7 @@ #ifdef CONFIG_HAVE_DYNAMIC_PER_CPU_AREA /* minimum unit size, also is the maximum supported allocation size */ -#define PCPU_MIN_UNIT_SIZE (16UL << PAGE_SHIFT) +#define PCPU_MIN_UNIT_SIZE PFN_ALIGN(64 << 10) /* * PERCPU_DYNAMIC_RESERVE indicates the amount of free area to piggy @@ -96,15 +98,15 @@ #ifndef PERCPU_DYNAMIC_RESERVE # if BITS_PER_LONG > 32 # ifdef CONFIG_MODULES -# define PERCPU_DYNAMIC_RESERVE (6 << PAGE_SHIFT) +# define PERCPU_DYNAMIC_RESERVE (24 << 10) # else -# define PERCPU_DYNAMIC_RESERVE (4 << PAGE_SHIFT) +# define PERCPU_DYNAMIC_RESERVE (16 << 10) # endif # else # ifdef CONFIG_MODULES -# define PERCPU_DYNAMIC_RESERVE (4 << PAGE_SHIFT) +# define PERCPU_DYNAMIC_RESERVE (16 << 10) # else -# define PERCPU_DYNAMIC_RESERVE (2 << PAGE_SHIFT) +# define PERCPU_DYNAMIC_RESERVE (8 << 10) # endif # endif #endif /* PERCPU_DYNAMIC_RESERVE */ -- cgit v1.2.3-70-g09d2 From 2441d15c97d498b18f03ae9fba262ffeae42a08b Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 6 Mar 2009 14:33:59 +0900 Subject: percpu: cosmetic renames in pcpu_setup_first_chunk() Impact: cosmetic, preparation for future changes Make the following renames in pcpur_setup_first_chunk() in preparation for future changes. * s/free_size/dyn_size/ * s/static_vm/first_vm/ * s/static_chunk/schunk/ Signed-off-by: Tejun Heo --- include/linux/percpu.h | 2 +- mm/percpu.c | 58 +++++++++++++++++++++++++------------------------- 2 files changed, 30 insertions(+), 30 deletions(-) (limited to 'include/linux/percpu.h') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 2d34b038fe7..a0b4ea2a335 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -118,7 +118,7 @@ typedef void (*pcpu_populate_pte_fn_t)(unsigned long addr); extern size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn, size_t static_size, size_t unit_size, - size_t free_size, void *base_addr, + size_t dyn_size, void *base_addr, pcpu_populate_pte_fn_t populate_pte_fn); /* diff --git a/mm/percpu.c b/mm/percpu.c index 3d0f5456827..9531590e6b6 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -831,7 +831,7 @@ EXPORT_SYMBOL_GPL(free_percpu); * @get_page_fn: callback to fetch page pointer * @static_size: the size of static percpu area in bytes * @unit_size: unit size in bytes, must be multiple of PAGE_SIZE, 0 for auto - * @free_size: free size in bytes, 0 for auto + * @dyn_size: free size for dynamic allocation in bytes, 0 for auto * @base_addr: mapped address, NULL for auto * @populate_pte_fn: callback to allocate pagetable, NULL if unnecessary * @@ -849,12 +849,12 @@ EXPORT_SYMBOL_GPL(free_percpu); * return the same number of pages for all cpus. * * @unit_size, if non-zero, determines unit size and must be aligned - * to PAGE_SIZE and equal to or larger than @static_size + @free_size. + * to PAGE_SIZE and equal to or larger than @static_size + @dyn_size. * - * @free_size determines the number of free bytes after the static + * @dyn_size determines the number of free bytes after the static * area in the first chunk. If zero, whatever left is available. * Specifying non-zero value make percpu leave the area after - * @static_size + @free_size alone. + * @static_size + @dyn_size alone. * * Non-null @base_addr means that the caller already allocated virtual * region for the first chunk and mapped it. percpu must not mess @@ -870,19 +870,19 @@ EXPORT_SYMBOL_GPL(free_percpu); */ size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn, size_t static_size, size_t unit_size, - size_t free_size, void *base_addr, + size_t dyn_size, void *base_addr, pcpu_populate_pte_fn_t populate_pte_fn) { - static struct vm_struct static_vm; - struct pcpu_chunk *static_chunk; + static struct vm_struct first_vm; + struct pcpu_chunk *schunk; unsigned int cpu; int nr_pages; int err, i; /* santiy checks */ BUG_ON(!static_size); - BUG_ON(!unit_size && free_size); - BUG_ON(unit_size && unit_size < static_size + free_size); + BUG_ON(!unit_size && dyn_size); + BUG_ON(unit_size && unit_size < static_size + dyn_size); BUG_ON(unit_size & ~PAGE_MASK); BUG_ON(base_addr && !unit_size); BUG_ON(base_addr && populate_pte_fn); @@ -908,24 +908,24 @@ size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn, for (i = 0; i < pcpu_nr_slots; i++) INIT_LIST_HEAD(&pcpu_slot[i]); - /* init static_chunk */ - static_chunk = alloc_bootmem(pcpu_chunk_struct_size); - INIT_LIST_HEAD(&static_chunk->list); - static_chunk->vm = &static_vm; + /* init static chunk */ + schunk = alloc_bootmem(pcpu_chunk_struct_size); + INIT_LIST_HEAD(&schunk->list); + schunk->vm = &first_vm; - if (free_size) - static_chunk->free_size = free_size; + if (dyn_size) + schunk->free_size = dyn_size; else - static_chunk->free_size = pcpu_unit_size - pcpu_static_size; + schunk->free_size = pcpu_unit_size - pcpu_static_size; - static_chunk->contig_hint = static_chunk->free_size; + schunk->contig_hint = schunk->free_size; /* allocate vm address */ - static_vm.flags = VM_ALLOC; - static_vm.size = pcpu_chunk_size; + first_vm.flags = VM_ALLOC; + first_vm.size = pcpu_chunk_size; if (!base_addr) - vm_area_register_early(&static_vm, PAGE_SIZE); + vm_area_register_early(&first_vm, PAGE_SIZE); else { /* * Pages already mapped. No need to remap into @@ -933,8 +933,8 @@ size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn, * be mapped or unmapped by percpu and is marked * immutable. */ - static_vm.addr = base_addr; - static_chunk->immutable = true; + first_vm.addr = base_addr; + schunk->immutable = true; } /* assign pages */ @@ -945,7 +945,7 @@ size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn, if (!page) break; - *pcpu_chunk_pagep(static_chunk, cpu, i) = page; + *pcpu_chunk_pagep(schunk, cpu, i) = page; } BUG_ON(i < PFN_UP(pcpu_static_size)); @@ -960,20 +960,20 @@ size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn, if (populate_pte_fn) { for_each_possible_cpu(cpu) for (i = 0; i < nr_pages; i++) - populate_pte_fn(pcpu_chunk_addr(static_chunk, + populate_pte_fn(pcpu_chunk_addr(schunk, cpu, i)); - err = pcpu_map(static_chunk, 0, nr_pages); + err = pcpu_map(schunk, 0, nr_pages); if (err) panic("failed to setup static percpu area, err=%d\n", err); } - /* link static_chunk in */ - pcpu_chunk_relocate(static_chunk, -1); - pcpu_chunk_addr_insert(static_chunk); + /* link the first chunk in */ + pcpu_chunk_relocate(schunk, -1); + pcpu_chunk_addr_insert(schunk); /* we're done */ - pcpu_base_addr = (void *)pcpu_chunk_addr(static_chunk, 0, 0); + pcpu_base_addr = (void *)pcpu_chunk_addr(schunk, 0, 0); return pcpu_unit_size; } -- cgit v1.2.3-70-g09d2 From cafe8816b217b98dc3f268d3b77445da498beb4f Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 6 Mar 2009 14:33:59 +0900 Subject: percpu: use negative for auto for pcpu_setup_first_chunk() arguments Impact: argument semantic cleanup In pcpu_setup_first_chunk(), zero @unit_size and @dyn_size meant auto-sizing. It's okay for @unit_size as 0 doesn't make sense but 0 dynamic reserve size is valid. Alos, if arch @dyn_size is calculated from other parameters, it might end up passing in 0 @dyn_size and malfunction when the size is automatically adjusted. This patch makes both @unit_size and @dyn_size ssize_t and use -1 for auto sizing. Signed-off-by: Tejun Heo --- arch/x86/kernel/setup_percpu.c | 2 +- include/linux/percpu.h | 5 +++-- mm/percpu.c | 46 +++++++++++++++++++++++------------------- 3 files changed, 29 insertions(+), 24 deletions(-) (limited to 'include/linux/percpu.h') diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index c29f301d388..ef3a2cd3fe6 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -344,7 +344,7 @@ static ssize_t __init setup_pcpu_4k(size_t static_size) pr_info("PERCPU: Allocated %d 4k pages, static data %zu bytes\n", pcpu4k_nr_static_pages, static_size); - ret = pcpu_setup_first_chunk(pcpu4k_get_page, static_size, 0, 0, NULL, + ret = pcpu_setup_first_chunk(pcpu4k_get_page, static_size, -1, -1, NULL, pcpu4k_populate_pte); goto out_free_ar; diff --git a/include/linux/percpu.h b/include/linux/percpu.h index a0b4ea2a335..a96fc53bbd6 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -117,8 +117,9 @@ typedef struct page * (*pcpu_get_page_fn_t)(unsigned int cpu, int pageno); typedef void (*pcpu_populate_pte_fn_t)(unsigned long addr); extern size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn, - size_t static_size, size_t unit_size, - size_t dyn_size, void *base_addr, + size_t static_size, + ssize_t unit_size, ssize_t dyn_size, + void *base_addr, pcpu_populate_pte_fn_t populate_pte_fn); /* diff --git a/mm/percpu.c b/mm/percpu.c index 503ccad091a..a84cf9977fa 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -824,8 +824,8 @@ EXPORT_SYMBOL_GPL(free_percpu); * pcpu_setup_first_chunk - initialize the first percpu chunk * @get_page_fn: callback to fetch page pointer * @static_size: the size of static percpu area in bytes - * @unit_size: unit size in bytes, must be multiple of PAGE_SIZE, 0 for auto - * @dyn_size: free size for dynamic allocation in bytes, 0 for auto + * @unit_size: unit size in bytes, must be multiple of PAGE_SIZE, -1 for auto + * @dyn_size: free size for dynamic allocation in bytes, -1 for auto * @base_addr: mapped address, NULL for auto * @populate_pte_fn: callback to allocate pagetable, NULL if unnecessary * @@ -842,13 +842,14 @@ EXPORT_SYMBOL_GPL(free_percpu); * indicates end of pages for the cpu. Note that @get_page_fn() must * return the same number of pages for all cpus. * - * @unit_size, if non-zero, determines unit size and must be aligned - * to PAGE_SIZE and equal to or larger than @static_size + @dyn_size. + * @unit_size, if non-negative, specifies unit size and must be + * aligned to PAGE_SIZE and equal to or larger than @static_size + + * @dyn_size. * - * @dyn_size determines the number of free bytes after the static - * area in the first chunk. If zero, whatever left is available. - * Specifying non-zero value make percpu leave the area after - * @static_size + @dyn_size alone. + * @dyn_size, if non-negative, limits the number of bytes available + * for dynamic allocation in the first chunk. Specifying non-negative + * value make percpu leave alone the area beyond @static_size + + * @dyn_size. * * Non-null @base_addr means that the caller already allocated virtual * region for the first chunk and mapped it. percpu must not mess @@ -863,8 +864,9 @@ EXPORT_SYMBOL_GPL(free_percpu); * percpu access. */ size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn, - size_t static_size, size_t unit_size, - size_t dyn_size, void *base_addr, + size_t static_size, + ssize_t unit_size, ssize_t dyn_size, + void *base_addr, pcpu_populate_pte_fn_t populate_pte_fn) { static struct vm_struct first_vm; @@ -877,13 +879,17 @@ size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn, /* santiy checks */ BUILD_BUG_ON(ARRAY_SIZE(smap) >= PCPU_DFL_MAP_ALLOC); BUG_ON(!static_size); - BUG_ON(!unit_size && dyn_size); - BUG_ON(unit_size && unit_size < static_size + dyn_size); - BUG_ON(unit_size & ~PAGE_MASK); - BUG_ON(base_addr && !unit_size); + if (unit_size >= 0) { + BUG_ON(unit_size < static_size + + (dyn_size >= 0 ? dyn_size : 0)); + BUG_ON(unit_size & ~PAGE_MASK); + } else { + BUG_ON(dyn_size >= 0); + BUG_ON(base_addr); + } BUG_ON(base_addr && populate_pte_fn); - if (unit_size) + if (unit_size >= 0) pcpu_unit_pages = unit_size >> PAGE_SHIFT; else pcpu_unit_pages = max_t(int, PCPU_MIN_UNIT_SIZE >> PAGE_SHIFT, @@ -894,6 +900,9 @@ size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn, pcpu_chunk_struct_size = sizeof(struct pcpu_chunk) + num_possible_cpus() * pcpu_unit_pages * sizeof(struct page *); + if (dyn_size < 0) + dyn_size = pcpu_unit_size - static_size; + /* * Allocate chunk slots. The additional last slot is for * empty chunks. @@ -909,12 +918,7 @@ size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn, schunk->vm = &first_vm; schunk->map = smap; schunk->map_alloc = ARRAY_SIZE(smap); - - if (dyn_size) - schunk->free_size = dyn_size; - else - schunk->free_size = pcpu_unit_size - static_size; - + schunk->free_size = dyn_size; schunk->contig_hint = schunk->free_size; schunk->map[schunk->map_used++] = -static_size; -- cgit v1.2.3-70-g09d2 From edcb463997ed7b2ffa3bac76e3e75957318f2e01 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 6 Mar 2009 14:33:59 +0900 Subject: percpu, module: implement reserved allocation and use it for module percpu variables Impact: add reserved allocation functionality and use it for module percpu variables This patch implements reserved allocation from the first chunk. When setting up the first chunk, arch can ask to set aside certain number of bytes right after the core static area which is available only through a separate reserved allocator. This will be used primarily for module static percpu variables on architectures with limited relocation range to ensure that the module perpcu symbols are inside the relocatable range. If reserved area is requested, the first chunk becomes reserved and isn't available for regular allocation. If the first chunk also includes piggy-back dynamic allocation area, a separate chunk mapping the same region is created to serve dynamic allocation. The first one is called static first chunk and the second dynamic first chunk. Although they share the page map, their different area map initializations guarantee they serve disjoint areas according to their purposes. If arch doesn't setup reserved area, reserved allocation is handled like any other allocation. Signed-off-by: Tejun Heo --- arch/x86/kernel/setup_percpu.c | 8 +-- include/linux/percpu.h | 10 +-- kernel/module.c | 2 +- mm/percpu.c | 153 +++++++++++++++++++++++++++++++++++------ 4 files changed, 144 insertions(+), 29 deletions(-) (limited to 'include/linux/percpu.h') diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index 38e2b2a470a..dd4eabc747c 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -217,7 +217,7 @@ proceed: pr_info("PERCPU: Remapped at %p with large pages, static data " "%zu bytes\n", vm.addr, static_size); - ret = pcpu_setup_first_chunk(pcpur_get_page, static_size, PMD_SIZE, + ret = pcpu_setup_first_chunk(pcpur_get_page, static_size, 0, PMD_SIZE, pcpur_size - static_size, vm.addr, NULL); goto out_free_ar; @@ -297,7 +297,7 @@ static ssize_t __init setup_pcpu_embed(size_t static_size) pr_info("PERCPU: Embedded %zu pages at %p, static data %zu bytes\n", pcpue_size >> PAGE_SHIFT, pcpue_ptr, static_size); - return pcpu_setup_first_chunk(pcpue_get_page, static_size, + return pcpu_setup_first_chunk(pcpue_get_page, static_size, 0, pcpue_unit_size, dyn_size, pcpue_ptr, NULL); } @@ -356,8 +356,8 @@ static ssize_t __init setup_pcpu_4k(size_t static_size) pr_info("PERCPU: Allocated %d 4k pages, static data %zu bytes\n", pcpu4k_nr_static_pages, static_size); - ret = pcpu_setup_first_chunk(pcpu4k_get_page, static_size, -1, -1, NULL, - pcpu4k_populate_pte); + ret = pcpu_setup_first_chunk(pcpu4k_get_page, static_size, 0, -1, -1, + NULL, pcpu4k_populate_pte); goto out_free_ar; enomem: diff --git a/include/linux/percpu.h b/include/linux/percpu.h index a96fc53bbd6..8ff15153ae2 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -117,10 +117,10 @@ typedef struct page * (*pcpu_get_page_fn_t)(unsigned int cpu, int pageno); typedef void (*pcpu_populate_pte_fn_t)(unsigned long addr); extern size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn, - size_t static_size, - ssize_t unit_size, ssize_t dyn_size, - void *base_addr, - pcpu_populate_pte_fn_t populate_pte_fn); + size_t static_size, size_t reserved_size, + ssize_t unit_size, ssize_t dyn_size, + void *base_addr, + pcpu_populate_pte_fn_t populate_pte_fn); /* * Use this to get to a cpu's version of the per-cpu object @@ -129,6 +129,8 @@ extern size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn, */ #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); + #else /* CONFIG_HAVE_DYNAMIC_PER_CPU_AREA */ struct percpu_data { diff --git a/kernel/module.c b/kernel/module.c index 1f0657ae555..f0e04d6b67d 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -381,7 +381,7 @@ static void *percpu_modalloc(unsigned long size, unsigned long align, align = PAGE_SIZE; } - ptr = __alloc_percpu(size, align); + ptr = __alloc_reserved_percpu(size, align); if (!ptr) printk(KERN_WARNING "Could not allocate %lu bytes percpu data\n", size); diff --git a/mm/percpu.c b/mm/percpu.c index 5b47d9fe65f..ef8e169b773 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -94,6 +94,11 @@ static size_t pcpu_chunk_struct_size __read_mostly; void *pcpu_base_addr __read_mostly; EXPORT_SYMBOL_GPL(pcpu_base_addr); +/* optional reserved chunk, only accessible for reserved allocations */ +static struct pcpu_chunk *pcpu_reserved_chunk; +/* offset limit of the reserved chunk */ +static int pcpu_reserved_chunk_limit; + /* * One mutex to rule them all. * @@ -201,13 +206,14 @@ static void *pcpu_realloc(void *p, size_t size, size_t new_size) * * This function is called after an allocation or free changed @chunk. * New slot according to the changed state is determined and @chunk is - * moved to the slot. + * moved to the slot. Note that the reserved chunk is never put on + * chunk slots. */ static void pcpu_chunk_relocate(struct pcpu_chunk *chunk, int oslot) { int nslot = pcpu_chunk_slot(chunk); - if (oslot != nslot) { + if (chunk != pcpu_reserved_chunk && oslot != nslot) { if (oslot < nslot) list_move(&chunk->list, &pcpu_slot[nslot]); else @@ -255,6 +261,15 @@ static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr) struct rb_node *n, *parent; struct pcpu_chunk *chunk; + /* is it in the reserved chunk? */ + if (pcpu_reserved_chunk) { + void *start = pcpu_reserved_chunk->vm->addr; + + if (addr >= start && addr < start + pcpu_reserved_chunk_limit) + return pcpu_reserved_chunk; + } + + /* nah... search the regular ones */ n = *pcpu_chunk_rb_search(addr, &parent); if (!n) { /* no exactly matching chunk, the parent is the closest */ @@ -713,9 +728,10 @@ static struct pcpu_chunk *alloc_pcpu_chunk(void) } /** - * __alloc_percpu - allocate percpu area + * pcpu_alloc - the percpu allocator * @size: size of area to allocate in bytes * @align: alignment of area (max PAGE_SIZE) + * @reserved: allocate from the reserved chunk if available * * Allocate percpu area of @size bytes aligned at @align. Might * sleep. Might trigger writeouts. @@ -723,7 +739,7 @@ static struct pcpu_chunk *alloc_pcpu_chunk(void) * RETURNS: * Percpu pointer to the allocated area on success, NULL on failure. */ -void *__alloc_percpu(size_t size, size_t align) +static void *pcpu_alloc(size_t size, size_t align, bool reserved) { void *ptr = NULL; struct pcpu_chunk *chunk; @@ -737,7 +753,18 @@ void *__alloc_percpu(size_t size, size_t align) mutex_lock(&pcpu_mutex); - /* allocate area */ + /* serve reserved allocations from the reserved chunk if available */ + if (reserved && pcpu_reserved_chunk) { + chunk = pcpu_reserved_chunk; + if (size > chunk->contig_hint) + goto out_unlock; + off = pcpu_alloc_area(chunk, size, align); + if (off >= 0) + goto area_found; + goto out_unlock; + } + + /* search through normal chunks */ for (slot = pcpu_size_to_slot(size); slot < pcpu_nr_slots; slot++) { list_for_each_entry(chunk, &pcpu_slot[slot], list) { if (size > chunk->contig_hint) @@ -773,8 +800,41 @@ out_unlock: mutex_unlock(&pcpu_mutex); return ptr; } + +/** + * __alloc_percpu - allocate dynamic percpu area + * @size: size of area to allocate in bytes + * @align: alignment of area (max PAGE_SIZE) + * + * Allocate percpu area of @size bytes aligned at @align. Might + * sleep. Might trigger writeouts. + * + * RETURNS: + * Percpu pointer to the allocated area on success, NULL on failure. + */ +void *__alloc_percpu(size_t size, size_t align) +{ + return pcpu_alloc(size, align, false); +} EXPORT_SYMBOL_GPL(__alloc_percpu); +/** + * __alloc_reserved_percpu - allocate reserved percpu area + * @size: size of area to allocate in bytes + * @align: alignment of area (max PAGE_SIZE) + * + * Allocate percpu area of @size bytes aligned at @align from reserved + * percpu area if arch has set it up; otherwise, allocation is served + * from the same dynamic area. Might sleep. Might trigger writeouts. + * + * RETURNS: + * Percpu pointer to the allocated area on success, NULL on failure. + */ +void *__alloc_reserved_percpu(size_t size, size_t align) +{ + return pcpu_alloc(size, align, true); +} + static void pcpu_kill_chunk(struct pcpu_chunk *chunk) { WARN_ON(chunk->immutable); @@ -826,6 +886,7 @@ EXPORT_SYMBOL_GPL(free_percpu); * pcpu_setup_first_chunk - initialize the first percpu chunk * @get_page_fn: callback to fetch page pointer * @static_size: the size of static percpu area in bytes + * @reserved_size: the size of reserved percpu area in bytes * @unit_size: unit size in bytes, must be multiple of PAGE_SIZE, -1 for auto * @dyn_size: free size for dynamic allocation in bytes, -1 for auto * @base_addr: mapped address, NULL for auto @@ -844,14 +905,22 @@ EXPORT_SYMBOL_GPL(free_percpu); * indicates end of pages for the cpu. Note that @get_page_fn() must * return the same number of pages for all cpus. * + * @reserved_size, if non-zero, specifies the amount of bytes to + * reserve after the static area in the first chunk. This reserves + * the first chunk such that it's available only through reserved + * percpu allocation. This is primarily used to serve module percpu + * static areas on architectures where the addressing model has + * limited offset range for symbol relocations to guarantee module + * percpu symbols fall inside the relocatable range. + * * @unit_size, if non-negative, specifies unit size and must be * aligned to PAGE_SIZE and equal to or larger than @static_size + - * @dyn_size. + * @reserved_size + @dyn_size. * * @dyn_size, if non-negative, limits the number of bytes available * for dynamic allocation in the first chunk. Specifying non-negative * value make percpu leave alone the area beyond @static_size + - * @dyn_size. + * @reserved_size + @dyn_size. * * Non-null @base_addr means that the caller already allocated virtual * region for the first chunk and mapped it. percpu must not mess @@ -861,28 +930,36 @@ EXPORT_SYMBOL_GPL(free_percpu); * @populate_pte_fn is used to populate the pagetable. NULL means the * caller already populated the pagetable. * + * If the first chunk ends up with both reserved and dynamic areas, it + * is served by two chunks - one to serve the core static and reserved + * areas and the other for the dynamic area. They share the same vm + * and page map but uses different area allocation map to stay away + * from each other. The latter chunk is circulated in the chunk slots + * and available for dynamic allocation like any other chunks. + * * RETURNS: * The determined pcpu_unit_size which can be used to initialize * percpu access. */ size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn, - size_t static_size, + size_t static_size, size_t reserved_size, ssize_t unit_size, ssize_t dyn_size, void *base_addr, pcpu_populate_pte_fn_t populate_pte_fn) { static struct vm_struct first_vm; - static int smap[2]; - struct pcpu_chunk *schunk; + static int smap[2], dmap[2]; + struct pcpu_chunk *schunk, *dchunk = NULL; unsigned int cpu; int nr_pages; int err, i; /* santiy checks */ - BUILD_BUG_ON(ARRAY_SIZE(smap) >= PCPU_DFL_MAP_ALLOC); + BUILD_BUG_ON(ARRAY_SIZE(smap) >= PCPU_DFL_MAP_ALLOC || + ARRAY_SIZE(dmap) >= PCPU_DFL_MAP_ALLOC); BUG_ON(!static_size); if (unit_size >= 0) { - BUG_ON(unit_size < static_size + + BUG_ON(unit_size < static_size + reserved_size + (dyn_size >= 0 ? dyn_size : 0)); BUG_ON(unit_size & ~PAGE_MASK); } else { @@ -895,7 +972,7 @@ size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn, pcpu_unit_pages = unit_size >> PAGE_SHIFT; else pcpu_unit_pages = max_t(int, PCPU_MIN_UNIT_SIZE >> PAGE_SHIFT, - PFN_UP(static_size)); + PFN_UP(static_size + reserved_size)); pcpu_unit_size = pcpu_unit_pages << PAGE_SHIFT; pcpu_chunk_size = num_possible_cpus() * pcpu_unit_size; @@ -903,7 +980,7 @@ size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn, + num_possible_cpus() * pcpu_unit_pages * sizeof(struct page *); if (dyn_size < 0) - dyn_size = pcpu_unit_size - static_size; + dyn_size = pcpu_unit_size - static_size - reserved_size; /* * Allocate chunk slots. The additional last slot is for @@ -914,20 +991,49 @@ size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn, for (i = 0; i < pcpu_nr_slots; i++) INIT_LIST_HEAD(&pcpu_slot[i]); - /* init static chunk */ + /* + * Initialize static chunk. If reserved_size is zero, the + * static chunk covers static area + dynamic allocation area + * in the first chunk. If reserved_size is not zero, it + * covers static area + reserved area (mostly used for module + * static percpu allocation). + */ schunk = alloc_bootmem(pcpu_chunk_struct_size); INIT_LIST_HEAD(&schunk->list); schunk->vm = &first_vm; schunk->map = smap; schunk->map_alloc = ARRAY_SIZE(smap); schunk->page = schunk->page_ar; - schunk->free_size = dyn_size; + + if (reserved_size) { + schunk->free_size = reserved_size; + pcpu_reserved_chunk = schunk; /* not for dynamic alloc */ + } else { + schunk->free_size = dyn_size; + dyn_size = 0; /* dynamic area covered */ + } schunk->contig_hint = schunk->free_size; schunk->map[schunk->map_used++] = -static_size; if (schunk->free_size) schunk->map[schunk->map_used++] = schunk->free_size; + pcpu_reserved_chunk_limit = static_size + schunk->free_size; + + /* init dynamic chunk if necessary */ + if (dyn_size) { + dchunk = alloc_bootmem(sizeof(struct pcpu_chunk)); + INIT_LIST_HEAD(&dchunk->list); + dchunk->vm = &first_vm; + dchunk->map = dmap; + dchunk->map_alloc = ARRAY_SIZE(dmap); + dchunk->page = schunk->page_ar; /* share page map with schunk */ + + dchunk->contig_hint = dchunk->free_size = dyn_size; + dchunk->map[dchunk->map_used++] = -pcpu_reserved_chunk_limit; + dchunk->map[dchunk->map_used++] = dchunk->free_size; + } + /* allocate vm address */ first_vm.flags = VM_ALLOC; first_vm.size = pcpu_chunk_size; @@ -937,12 +1043,14 @@ size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn, else { /* * Pages already mapped. No need to remap into - * vmalloc area. In this case the static chunk can't - * be mapped or unmapped by percpu and is marked + * vmalloc area. In this case the first chunks can't + * be mapped or unmapped by percpu and are marked * immutable. */ first_vm.addr = base_addr; schunk->immutable = true; + if (dchunk) + dchunk->immutable = true; } /* assign pages */ @@ -978,8 +1086,13 @@ size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn, } /* link the first chunk in */ - pcpu_chunk_relocate(schunk, -1); - pcpu_chunk_addr_insert(schunk); + if (!dchunk) { + pcpu_chunk_relocate(schunk, -1); + pcpu_chunk_addr_insert(schunk); + } else { + pcpu_chunk_relocate(dchunk, -1); + pcpu_chunk_addr_insert(dchunk); + } /* we're done */ pcpu_base_addr = (void *)pcpu_chunk_addr(schunk, 0, 0); -- cgit v1.2.3-70-g09d2 From 6b19b0c2400437a3c10059ede0e59b517092e1bd Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 6 Mar 2009 14:33:59 +0900 Subject: x86, percpu: setup reserved percpu area for x86_64 Impact: fix relocation overflow during module load x86_64 uses 32bit relocations for symbol access and static percpu symbols whether in core or modules must be inside 2GB of the percpu segement base which the dynamic percpu allocator doesn't guarantee. This patch makes x86_64 reserve PERCPU_MODULE_RESERVE bytes in the first chunk so that module percpu areas are always allocated from the first chunk which is always inside the relocatable range. This problem exists for any percpu allocator but is easily triggered when using the embedding allocator because the second chunk is located beyond 2GB on it. This patch also changes the meaning of PERCPU_DYNAMIC_RESERVE such that it only indicates the size of the area to reserve for dynamic allocation as static and dynamic areas can be separate. New PERCPU_DYNAMIC_RESERVED is increased by 4k for both 32 and 64bits as the reserved area separation eats away some allocatable space and having slightly more headroom (currently between 4 and 8k after minimal boot sans module area) makes sense for common case performance. x86_32 can address anywhere from anywhere and doesn't need reserving. Mike Galbraith first reported the problem first and bisected it to the embedding percpu allocator commit. Signed-off-by: Tejun Heo Reported-by: Mike Galbraith Reported-by: Jaswinder Singh Rajput --- arch/x86/kernel/setup_percpu.c | 37 ++++++++++++++++++++++++++++--------- include/linux/percpu.h | 35 ++++++++++++----------------------- 2 files changed, 40 insertions(+), 32 deletions(-) (limited to 'include/linux/percpu.h') diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index dd4eabc747c..efa615f2bf4 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -42,6 +42,19 @@ unsigned long __per_cpu_offset[NR_CPUS] __read_mostly = { }; EXPORT_SYMBOL(__per_cpu_offset); +/* + * On x86_64 symbols referenced from code should be reachable using + * 32bit relocations. Reserve space for static percpu variables in + * modules so that they are always served from the first chunk which + * is located at the percpu segment base. On x86_32, anything can + * address anywhere. No need to reserve space in the first chunk. + */ +#ifdef CONFIG_X86_64 +#define PERCPU_FIRST_CHUNK_RESERVE PERCPU_MODULE_RESERVE +#else +#define PERCPU_FIRST_CHUNK_RESERVE 0 +#endif + /** * pcpu_need_numa - determine percpu allocation needs to consider NUMA * @@ -141,7 +154,7 @@ static ssize_t __init setup_pcpu_remap(size_t static_size) { static struct vm_struct vm; pg_data_t *last; - size_t ptrs_size; + size_t ptrs_size, dyn_size; unsigned int cpu; ssize_t ret; @@ -169,12 +182,14 @@ proceed: * Currently supports only single page. Supporting multiple * pages won't be too difficult if it ever becomes necessary. */ - pcpur_size = PFN_ALIGN(static_size + PERCPU_DYNAMIC_RESERVE); + pcpur_size = PFN_ALIGN(static_size + PERCPU_MODULE_RESERVE + + PERCPU_DYNAMIC_RESERVE); if (pcpur_size > PMD_SIZE) { pr_warning("PERCPU: static data is larger than large page, " "can't use large page\n"); return -EINVAL; } + dyn_size = pcpur_size - static_size - PERCPU_FIRST_CHUNK_RESERVE; /* allocate pointer array and alloc large pages */ ptrs_size = PFN_ALIGN(num_possible_cpus() * sizeof(pcpur_ptrs[0])); @@ -217,8 +232,9 @@ proceed: pr_info("PERCPU: Remapped at %p with large pages, static data " "%zu bytes\n", vm.addr, static_size); - ret = pcpu_setup_first_chunk(pcpur_get_page, static_size, 0, PMD_SIZE, - pcpur_size - static_size, vm.addr, NULL); + ret = pcpu_setup_first_chunk(pcpur_get_page, static_size, + PERCPU_FIRST_CHUNK_RESERVE, + PMD_SIZE, dyn_size, vm.addr, NULL); goto out_free_ar; enomem: @@ -276,9 +292,10 @@ static ssize_t __init setup_pcpu_embed(size_t static_size) return -EINVAL; /* allocate and copy */ - pcpue_size = PFN_ALIGN(static_size + PERCPU_DYNAMIC_RESERVE); + pcpue_size = PFN_ALIGN(static_size + PERCPU_MODULE_RESERVE + + PERCPU_DYNAMIC_RESERVE); pcpue_unit_size = max_t(size_t, pcpue_size, PCPU_MIN_UNIT_SIZE); - dyn_size = pcpue_size - static_size; + dyn_size = pcpue_size - static_size - PERCPU_FIRST_CHUNK_RESERVE; pcpue_ptr = pcpu_alloc_bootmem(0, num_possible_cpus() * pcpue_unit_size, PAGE_SIZE); @@ -297,7 +314,8 @@ static ssize_t __init setup_pcpu_embed(size_t static_size) pr_info("PERCPU: Embedded %zu pages at %p, static data %zu bytes\n", pcpue_size >> PAGE_SHIFT, pcpue_ptr, static_size); - return pcpu_setup_first_chunk(pcpue_get_page, static_size, 0, + return pcpu_setup_first_chunk(pcpue_get_page, static_size, + PERCPU_FIRST_CHUNK_RESERVE, pcpue_unit_size, dyn_size, pcpue_ptr, NULL); } @@ -356,8 +374,9 @@ static ssize_t __init setup_pcpu_4k(size_t static_size) pr_info("PERCPU: Allocated %d 4k pages, static data %zu bytes\n", pcpu4k_nr_static_pages, static_size); - ret = pcpu_setup_first_chunk(pcpu4k_get_page, static_size, 0, -1, -1, - NULL, pcpu4k_populate_pte); + ret = pcpu_setup_first_chunk(pcpu4k_get_page, static_size, + PERCPU_FIRST_CHUNK_RESERVE, -1, -1, NULL, + pcpu4k_populate_pte); goto out_free_ar; enomem: diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 8ff15153ae2..54a968b4b92 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -85,31 +85,20 @@ /* * PERCPU_DYNAMIC_RESERVE indicates the amount of free area to piggy - * back on the first chunk if arch is manually allocating and mapping - * it for faster access (as a part of large page mapping for example). - * Note that dynamic percpu allocator covers both static and dynamic - * areas, so these values are bigger than PERCPU_MODULE_RESERVE. + * back on the first chunk for dynamic percpu allocation if arch is + * manually allocating and mapping it for faster access (as a part of + * large page mapping for example). * - * On typical configuration with modules, the following values leave - * about 8k of free space on the first chunk after boot on both x86_32 - * and 64 when module support is enabled. When module support is - * disabled, it's much tighter. + * The following values give between one and two pages of free space + * after typical minimal boot (2-way SMP, single disk and NIC) with + * both defconfig and a distro config on x86_64 and 32. More + * intelligent way to determine this would be nice. */ -#ifndef PERCPU_DYNAMIC_RESERVE -# if BITS_PER_LONG > 32 -# ifdef CONFIG_MODULES -# define PERCPU_DYNAMIC_RESERVE (24 << 10) -# else -# define PERCPU_DYNAMIC_RESERVE (16 << 10) -# endif -# else -# ifdef CONFIG_MODULES -# define PERCPU_DYNAMIC_RESERVE (16 << 10) -# else -# define PERCPU_DYNAMIC_RESERVE (8 << 10) -# endif -# endif -#endif /* PERCPU_DYNAMIC_RESERVE */ +#if BITS_PER_LONG > 32 +#define PERCPU_DYNAMIC_RESERVE (20 << 10) +#else +#define PERCPU_DYNAMIC_RESERVE (12 << 10) +#endif extern void *pcpu_base_addr; -- cgit v1.2.3-70-g09d2