From 1d93e52eb48df986a3c4d5ad8a520bf1f6837367 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 11 Feb 2009 08:47:19 -0700 Subject: dmaengine: update kerneldoc Some of the kerneldoc comments in the dmaengine header describe already removed structure members. Remove them. Also add a short description for dma_device->device_is_tx_complete. Signed-off-by: Johannes Weiner Signed-off-by: Dan Williams --- include/linux/dmaengine.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 3e68469c1885..087e79acf8c7 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -97,7 +97,6 @@ typedef struct { DECLARE_BITMAP(bits, DMA_TX_TYPE_END); } dma_cap_mask_t; /** * struct dma_chan_percpu - the per-CPU part of struct dma_chan - * @refcount: local_t used for open-coded "bigref" counting * @memcpy_count: transaction counter * @bytes_transferred: byte counter */ @@ -114,9 +113,6 @@ struct dma_chan_percpu { * @cookie: last cookie value returned to client * @chan_id: channel ID for sysfs * @dev: class device for sysfs - * @refcount: kref, used in "bigref" slow-mode - * @slow_ref: indicates that the DMA channel is free - * @rcu: the DMA channel's RCU head * @device_node: used to add this to the device chan list * @local: per-cpu pointer to a struct dma_chan_percpu * @client-count: how many clients are using this channel @@ -211,8 +207,6 @@ struct dma_async_tx_descriptor { * @global_node: list_head for global dma_device_list * @cap_mask: one or more dma_capability flags * @max_xor: maximum number of xor sources, 0 if no capability - * @refcount: reference count - * @done: IO completion struct * @dev_id: unique device ID * @dev: struct device reference for dma mapping api * @device_alloc_chan_resources: allocate resources and return the @@ -225,6 +219,7 @@ struct dma_async_tx_descriptor { * @device_prep_dma_interrupt: prepares an end of chain interrupt operation * @device_prep_slave_sg: prepares a slave dma operation * @device_terminate_all: terminate all pending operations + * @device_is_tx_complete: poll for transaction completion * @device_issue_pending: push pending transactions to hardware */ struct dma_device { -- cgit v1.2.3 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') diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c index 4b1c319d30c3..22590cf688ae 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 9cc769b587ff..68fd3d292799 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 3577ffd90d45..c80cfe1260ec 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 fc17fd91ab57..9d30ac956328 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 0cd415ee62a2..74541ca49536 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 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') diff --git a/block/blktrace.c b/block/blktrace.c index 39cc3bfe56e4..487766237d28 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 c80cfe1260ec..1fdaee93c04d 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 743f5542d65a..3a3dad801354 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 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') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 1fdaee93c04d..d99e24ae1811 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 4297bc41bfd2..3653c570232b 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 From f0aa6617903648077dffe5cfcf7c4458f4610fa7 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 20 Feb 2009 16:29:08 +0900 Subject: vmalloc: implement vm_area_register_early() Impact: allow multiple early vm areas There are places where kernel VM area needs to be allocated before vmalloc is initialized. This is done by allocating static vm_struct, initializing several fields and linking it to vmlist and later vmalloc initialization picking up these from vmlist. This is currently done manually and if there's more than one such areas, there's no defined way to arbitrate who gets which address. This patch implements vm_area_register_early(), which takes vm_area struct with flags and size initialized, assigns address to it and puts it on the vmlist. This way, multiple early vm areas can determine which addresses they should use. The only current user - alpha mm init - is converted to use it. Signed-off-by: Tejun Heo --- arch/alpha/mm/init.c | 20 +++++++++++++------- include/linux/vmalloc.h | 1 + mm/vmalloc.c | 24 ++++++++++++++++++++++++ 3 files changed, 38 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/arch/alpha/mm/init.c b/arch/alpha/mm/init.c index 5d7a16eab312..df6df025ded4 100644 --- a/arch/alpha/mm/init.c +++ b/arch/alpha/mm/init.c @@ -189,9 +189,21 @@ callback_init(void * kernel_end) if (alpha_using_srm) { static struct vm_struct console_remap_vm; - unsigned long vaddr = VMALLOC_START; + unsigned long nr_pages = 0; + unsigned long vaddr; unsigned long i, j; + /* calculate needed size */ + for (i = 0; i < crb->map_entries; ++i) + nr_pages += crb->map[i].count; + + /* register the vm area */ + console_remap_vm.flags = VM_ALLOC; + console_remap_vm.size = nr_pages << PAGE_SHIFT; + vm_area_register_early(&console_remap_vm); + + vaddr = (unsigned long)consle_remap_vm.addr; + /* Set up the third level PTEs and update the virtual addresses of the CRB entries. */ for (i = 0; i < crb->map_entries; ++i) { @@ -213,12 +225,6 @@ callback_init(void * kernel_end) vaddr += PAGE_SIZE; } } - - /* Let vmalloc know that we've allocated some space. */ - console_remap_vm.flags = VM_ALLOC; - console_remap_vm.addr = (void *) VMALLOC_START; - console_remap_vm.size = vaddr - VMALLOC_START; - vmlist = &console_remap_vm; } callback_init_done = 1; diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 506e7620a986..bbc051392298 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -106,5 +106,6 @@ extern long vwrite(char *buf, char *addr, unsigned long count); */ extern rwlock_t vmlist_lock; extern struct vm_struct *vmlist; +extern __init void vm_area_register_early(struct vm_struct *vm); #endif /* _LINUX_VMALLOC_H */ diff --git a/mm/vmalloc.c b/mm/vmalloc.c index c37924a2ee36..d206261ad9ef 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include @@ -982,6 +983,29 @@ void *vm_map_ram(struct page **pages, unsigned int count, int node, pgprot_t pro } EXPORT_SYMBOL(vm_map_ram); +/** + * vm_area_register_early - register vmap area early during boot + * @vm: vm_struct to register + * @size: size of area to register + * + * This function is used to register kernel vm area before + * vmalloc_init() is called. @vm->size and @vm->flags should contain + * proper values on entry and other fields should be zero. On return, + * vm->addr contains the allocated address. + * + * DO NOT USE THIS FUNCTION UNLESS YOU KNOW WHAT YOU'RE DOING. + */ +void __init vm_area_register_early(struct vm_struct *vm) +{ + static size_t vm_init_off __initdata; + + vm->addr = (void *)VMALLOC_START + vm_init_off; + vm_init_off = PFN_ALIGN(vm_init_off + vm->size); + + vm->next = vmlist; + vmlist = vm; +} + void __init vmalloc_init(void) { struct vmap_area *va; -- cgit v1.2.3 From 8fc48985006da4ceba24508db64ec77fc0dfe3bb Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 20 Feb 2009 16:29:08 +0900 Subject: vmalloc: add un/map_kernel_range_noflush() Impact: two more public map/unmap functions Implement map_kernel_range_noflush() and unmap_kernel_range_noflush(). These functions respectively map and unmap address range in kernel VM area but doesn't do any vcache or tlb flushing. These will be used by new percpu allocator. Signed-off-by: Tejun Heo Cc: Nick Piggin --- include/linux/vmalloc.h | 3 +++ mm/vmalloc.c | 67 ++++++++++++++++++++++++++++++++++++++++++++++--- 2 files changed, 67 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index bbc051392298..599ba7984310 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -91,6 +91,9 @@ extern struct vm_struct *remove_vm_area(const void *addr); extern int map_vm_area(struct vm_struct *area, pgprot_t prot, struct page ***pages); +extern int map_kernel_range_noflush(unsigned long start, unsigned long size, + pgprot_t prot, struct page **pages); +extern void unmap_kernel_range_noflush(unsigned long addr, unsigned long size); extern void unmap_kernel_range(unsigned long addr, unsigned long size); /* Allocate/destroy a 'vmalloc' VM area. */ diff --git a/mm/vmalloc.c b/mm/vmalloc.c index d206261ad9ef..224eca9650a8 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -153,8 +153,8 @@ static int vmap_pud_range(pgd_t *pgd, unsigned long addr, * * Ie. pte at addr+N*PAGE_SIZE shall point to pfn corresponding to pages[N] */ -static int vmap_page_range(unsigned long start, unsigned long end, - pgprot_t prot, struct page **pages) +static int vmap_page_range_noflush(unsigned long start, unsigned long end, + pgprot_t prot, struct page **pages) { pgd_t *pgd; unsigned long next; @@ -170,13 +170,22 @@ static int vmap_page_range(unsigned long start, unsigned long end, if (err) break; } while (pgd++, addr = next, addr != end); - flush_cache_vmap(start, end); if (unlikely(err)) return err; return nr; } +static int vmap_page_range(unsigned long start, unsigned long end, + pgprot_t prot, struct page **pages) +{ + int ret; + + ret = vmap_page_range_noflush(start, end, prot, pages); + flush_cache_vmap(start, end); + return ret; +} + static inline int is_vmalloc_or_module_addr(const void *x) { /* @@ -1033,6 +1042,58 @@ void __init vmalloc_init(void) vmap_initialized = true; } +/** + * map_kernel_range_noflush - map kernel VM area with the specified pages + * @addr: start of the VM area to map + * @size: size of the VM area to map + * @prot: page protection flags to use + * @pages: pages to map + * + * Map PFN_UP(@size) pages at @addr. The VM area @addr and @size + * specify should have been allocated using get_vm_area() and its + * friends. + * + * NOTE: + * This function does NOT do any cache flushing. The caller is + * responsible for calling flush_cache_vmap() on to-be-mapped areas + * before calling this function. + * + * RETURNS: + * The number of pages mapped on success, -errno on failure. + */ +int map_kernel_range_noflush(unsigned long addr, unsigned long size, + pgprot_t prot, struct page **pages) +{ + return vmap_page_range_noflush(addr, addr + size, prot, pages); +} + +/** + * unmap_kernel_range_noflush - unmap kernel VM area + * @addr: start of the VM area to unmap + * @size: size of the VM area to unmap + * + * Unmap PFN_UP(@size) pages at @addr. The VM area @addr and @size + * specify should have been allocated using get_vm_area() and its + * friends. + * + * NOTE: + * This function does NOT do any cache flushing. The caller is + * responsible for calling flush_cache_vunmap() on to-be-mapped areas + * before calling this function and flush_tlb_kernel_range() after. + */ +void unmap_kernel_range_noflush(unsigned long addr, unsigned long size) +{ + vunmap_page_range(addr, addr + size); +} + +/** + * unmap_kernel_range - unmap kernel VM area and flush cache and TLB + * @addr: start of the VM area to unmap + * @size: size of the VM area to unmap + * + * Similar to unmap_kernel_range_noflush() but flushes vcache before + * the unmapping and tlb after. + */ void unmap_kernel_range(unsigned long addr, unsigned long size) { unsigned long end = addr + size; -- cgit v1.2.3 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') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index d99e24ae1811..18080995ff3e 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 52b3497b8748..1f0657ae555b 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 72255be57f89..818569b68f46 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 000000000000..4617d97e877c --- /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 From c132937556f56ee4b831ef4b23f1846e05fde102 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 24 Feb 2009 11:57:20 +0900 Subject: bootmem: clean up arch-specific bootmem wrapping Impact: cleaner and consistent bootmem wrapping By setting CONFIG_HAVE_ARCH_BOOTMEM_NODE, archs can define arch-specific wrappers for bootmem allocation. However, this is done a bit strangely in that only the high level convenience macros can be changed while lower level, but still exported, interface functions can't be wrapped. This not only is messy but also leads to strange situation where alloc_bootmem() does what the arch wants it to do but the equivalent __alloc_bootmem() call doesn't although they should be able to be used interchangeably. This patch updates bootmem such that archs can override / wrap the backend function - alloc_bootmem_core() instead of the highlevel interface functions to allow simpler and consistent wrapping. Also, HAVE_ARCH_BOOTMEM_NODE is renamed to HAVE_ARCH_BOOTMEM. Signed-off-by: Tejun Heo Cc: Johannes Weiner --- arch/avr32/Kconfig | 2 +- arch/x86/Kconfig | 2 +- arch/x86/include/asm/mmzone_32.h | 43 +++++----------------------------------- include/linux/bootmem.h | 10 ++++------ mm/bootmem.c | 14 ++++++++++--- 5 files changed, 22 insertions(+), 49 deletions(-) (limited to 'include') diff --git a/arch/avr32/Kconfig b/arch/avr32/Kconfig index b189680d18b0..05fe3053dcae 100644 --- a/arch/avr32/Kconfig +++ b/arch/avr32/Kconfig @@ -181,7 +181,7 @@ source "kernel/Kconfig.preempt" config QUICKLIST def_bool y -config HAVE_ARCH_BOOTMEM_NODE +config HAVE_ARCH_BOOTMEM def_bool n config ARCH_HAVE_MEMORY_PRESENT diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index d3f6eadfd4ba..6fd3b2302ed9 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1111,7 +1111,7 @@ config NODES_SHIFT Specify the maximum number of NUMA Nodes available on the target system. Increases memory reserved to accomodate various tables. -config HAVE_ARCH_BOOTMEM_NODE +config HAVE_ARCH_BOOTMEM def_bool y depends on X86_32 && NUMA diff --git a/arch/x86/include/asm/mmzone_32.h b/arch/x86/include/asm/mmzone_32.h index 07f1af494ca5..1e0fa9e63afa 100644 --- a/arch/x86/include/asm/mmzone_32.h +++ b/arch/x86/include/asm/mmzone_32.h @@ -93,45 +93,12 @@ static inline int pfn_valid(int pfn) #endif /* CONFIG_DISCONTIGMEM */ #ifdef CONFIG_NEED_MULTIPLE_NODES - -/* - * Following are macros that are specific to this numa platform. - */ -#define reserve_bootmem(addr, size, flags) \ - reserve_bootmem_node(NODE_DATA(0), (addr), (size), (flags)) -#define alloc_bootmem(x) \ - __alloc_bootmem_node(NODE_DATA(0), (x), SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS)) -#define alloc_bootmem_nopanic(x) \ - __alloc_bootmem_node_nopanic(NODE_DATA(0), (x), SMP_CACHE_BYTES, \ - __pa(MAX_DMA_ADDRESS)) -#define alloc_bootmem_low(x) \ - __alloc_bootmem_node(NODE_DATA(0), (x), SMP_CACHE_BYTES, 0) -#define alloc_bootmem_pages(x) \ - __alloc_bootmem_node(NODE_DATA(0), (x), PAGE_SIZE, __pa(MAX_DMA_ADDRESS)) -#define alloc_bootmem_pages_nopanic(x) \ - __alloc_bootmem_node_nopanic(NODE_DATA(0), (x), PAGE_SIZE, \ - __pa(MAX_DMA_ADDRESS)) -#define alloc_bootmem_low_pages(x) \ - __alloc_bootmem_node(NODE_DATA(0), (x), PAGE_SIZE, 0) -#define alloc_bootmem_node(pgdat, x) \ -({ \ - struct pglist_data __maybe_unused \ - *__alloc_bootmem_node__pgdat = (pgdat); \ - __alloc_bootmem_node(NODE_DATA(0), (x), SMP_CACHE_BYTES, \ - __pa(MAX_DMA_ADDRESS)); \ -}) -#define alloc_bootmem_pages_node(pgdat, x) \ -({ \ - struct pglist_data __maybe_unused \ - *__alloc_bootmem_node__pgdat = (pgdat); \ - __alloc_bootmem_node(NODE_DATA(0), (x), PAGE_SIZE, \ - __pa(MAX_DMA_ADDRESS)); \ -}) -#define alloc_bootmem_low_pages_node(pgdat, x) \ +/* always use node 0 for bootmem on this numa platform */ +#define alloc_bootmem_core(__bdata, size, align, goal, limit) \ ({ \ - struct pglist_data __maybe_unused \ - *__alloc_bootmem_node__pgdat = (pgdat); \ - __alloc_bootmem_node(NODE_DATA(0), (x), PAGE_SIZE, 0); \ + bootmem_data_t __maybe_unused * __abm_bdata_dummy = (__bdata); \ + __alloc_bootmem_core(NODE_DATA(0)->bdata, \ + (size), (align), (goal), (limit)); \ }) #endif /* CONFIG_NEED_MULTIPLE_NODES */ diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 95837bfb5256..3a87f93081ed 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -69,10 +69,9 @@ extern int reserve_bootmem_node(pg_data_t *pgdat, unsigned long physaddr, unsigned long size, int flags); -#ifndef CONFIG_HAVE_ARCH_BOOTMEM_NODE -extern int reserve_bootmem(unsigned long addr, unsigned long size, int flags); -#endif - +extern int reserve_bootmem(unsigned long addr, + unsigned long size, + int flags); extern void *__alloc_bootmem_nopanic(unsigned long size, unsigned long align, unsigned long goal); @@ -94,7 +93,7 @@ extern void *__alloc_bootmem_low_node(pg_data_t *pgdat, unsigned long size, unsigned long align, unsigned long goal); -#ifndef CONFIG_HAVE_ARCH_BOOTMEM_NODE + #define alloc_bootmem(x) \ __alloc_bootmem(x, SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS)) #define alloc_bootmem_nopanic(x) \ @@ -113,7 +112,6 @@ extern void *__alloc_bootmem_low_node(pg_data_t *pgdat, __alloc_bootmem_node(pgdat, x, PAGE_SIZE, __pa(MAX_DMA_ADDRESS)) #define alloc_bootmem_low_pages_node(pgdat, x) \ __alloc_bootmem_low_node(pgdat, x, PAGE_SIZE, 0) -#endif /* !CONFIG_HAVE_ARCH_BOOTMEM_NODE */ extern int reserve_bootmem_generic(unsigned long addr, unsigned long size, int flags); diff --git a/mm/bootmem.c b/mm/bootmem.c index 51a0ccf61e0e..d7140c008ba8 100644 --- a/mm/bootmem.c +++ b/mm/bootmem.c @@ -37,6 +37,16 @@ static struct list_head bdata_list __initdata = LIST_HEAD_INIT(bdata_list); static int bootmem_debug; +/* + * If an arch needs to apply workarounds to bootmem allocation, it can + * set CONFIG_HAVE_ARCH_BOOTMEM and define a wrapper around + * __alloc_bootmem_core(). + */ +#ifndef CONFIG_HAVE_ARCH_BOOTMEM +#define alloc_bootmem_core(bdata, size, align, goal, limit) \ + __alloc_bootmem_core((bdata), (size), (align), (goal), (limit)) +#endif + static int __init bootmem_debug_setup(char *buf) { bootmem_debug = 1; @@ -382,7 +392,6 @@ int __init reserve_bootmem_node(pg_data_t *pgdat, unsigned long physaddr, return mark_bootmem_node(pgdat->bdata, start, end, 1, flags); } -#ifndef CONFIG_HAVE_ARCH_BOOTMEM_NODE /** * reserve_bootmem - mark a page range as usable * @addr: starting address of the range @@ -403,7 +412,6 @@ int __init reserve_bootmem(unsigned long addr, unsigned long size, return mark_bootmem(start, end, 1, flags); } -#endif /* !CONFIG_HAVE_ARCH_BOOTMEM_NODE */ static unsigned long align_idx(struct bootmem_data *bdata, unsigned long idx, unsigned long step) @@ -428,7 +436,7 @@ static unsigned long align_off(struct bootmem_data *bdata, unsigned long off, return ALIGN(base + off, align) - base; } -static void * __init alloc_bootmem_core(struct bootmem_data *bdata, +static void * __init __alloc_bootmem_core(struct bootmem_data *bdata, unsigned long size, unsigned long align, unsigned long goal, unsigned long limit) { -- cgit v1.2.3 From 2d0aae41695257603fc281b519677131ab5a752b Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 24 Feb 2009 11:57:21 +0900 Subject: bootmem: reorder interface functions and add a missing one Impact: cleanup and addition of missing interface wrapper The interface functions in bootmem.h was ordered in not so orderly manner. Reorder them such that * functions allocating the same area group together - ie. alloc_bootmem group and alloc_bootmem_low group. * functions w/o node parameter come before the ones w/ node parameter. * nopanic variants are immediately below their panicky counterparts. While at it, add alloc_bootmem_pages_node_nopanic() which was missing. Signed-off-by: Tejun Heo Cc: Johannes Weiner --- include/linux/bootmem.h | 30 +++++++++++++++++------------- 1 file changed, 17 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 3a87f93081ed..455d83219fae 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -65,22 +65,20 @@ extern void free_bootmem(unsigned long addr, unsigned long size); #define BOOTMEM_DEFAULT 0 #define BOOTMEM_EXCLUSIVE (1<<0) -extern int reserve_bootmem_node(pg_data_t *pgdat, - unsigned long physaddr, - unsigned long size, - int flags); extern int reserve_bootmem(unsigned long addr, unsigned long size, int flags); -extern void *__alloc_bootmem_nopanic(unsigned long size, +extern int reserve_bootmem_node(pg_data_t *pgdat, + unsigned long physaddr, + unsigned long size, + int flags); + +extern void *__alloc_bootmem(unsigned long size, unsigned long align, unsigned long goal); -extern void *__alloc_bootmem(unsigned long size, +extern void *__alloc_bootmem_nopanic(unsigned long size, unsigned long align, unsigned long goal); -extern void *__alloc_bootmem_low(unsigned long size, - unsigned long align, - unsigned long goal); extern void *__alloc_bootmem_node(pg_data_t *pgdat, unsigned long size, unsigned long align, @@ -89,6 +87,9 @@ extern void *__alloc_bootmem_node_nopanic(pg_data_t *pgdat, unsigned long size, unsigned long align, unsigned long goal); +extern void *__alloc_bootmem_low(unsigned long size, + unsigned long align, + unsigned long goal); extern void *__alloc_bootmem_low_node(pg_data_t *pgdat, unsigned long size, unsigned long align, @@ -98,18 +99,21 @@ extern void *__alloc_bootmem_low_node(pg_data_t *pgdat, __alloc_bootmem(x, SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS)) #define alloc_bootmem_nopanic(x) \ __alloc_bootmem_nopanic(x, SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS)) -#define alloc_bootmem_low(x) \ - __alloc_bootmem_low(x, SMP_CACHE_BYTES, 0) #define alloc_bootmem_pages(x) \ __alloc_bootmem(x, PAGE_SIZE, __pa(MAX_DMA_ADDRESS)) #define alloc_bootmem_pages_nopanic(x) \ __alloc_bootmem_nopanic(x, PAGE_SIZE, __pa(MAX_DMA_ADDRESS)) -#define alloc_bootmem_low_pages(x) \ - __alloc_bootmem_low(x, PAGE_SIZE, 0) #define alloc_bootmem_node(pgdat, x) \ __alloc_bootmem_node(pgdat, x, SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS)) #define alloc_bootmem_pages_node(pgdat, x) \ __alloc_bootmem_node(pgdat, x, PAGE_SIZE, __pa(MAX_DMA_ADDRESS)) +#define alloc_bootmem_pages_node_nopanic(pgdat, x) \ + __alloc_bootmem_node_nopanic(pgdat, x, PAGE_SIZE, __pa(MAX_DMA_ADDRESS)) + +#define alloc_bootmem_low(x) \ + __alloc_bootmem_low(x, SMP_CACHE_BYTES, 0) +#define alloc_bootmem_low_pages(x) \ + __alloc_bootmem_low(x, PAGE_SIZE, 0) #define alloc_bootmem_low_pages_node(pgdat, x) \ __alloc_bootmem_low_node(pgdat, x, PAGE_SIZE, 0) -- cgit v1.2.3 From c0c0a29379b5848aec2e8f1c58d853d3cb7118b8 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 24 Feb 2009 11:57:21 +0900 Subject: vmalloc: add @align to vm_area_register_early() Impact: allow larger alignment for early vmalloc area allocation Some early vmalloc users might want larger alignment, for example, for custom large page mapping. Add @align to vm_area_register_early(). While at it, drop docbook comment on non-existent @size. Signed-off-by: Tejun Heo Cc: Nick Piggin Cc: Ivan Kokshaysky --- arch/alpha/mm/init.c | 2 +- include/linux/vmalloc.h | 2 +- mm/percpu.c | 2 +- mm/vmalloc.c | 11 +++++++---- 4 files changed, 10 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/arch/alpha/mm/init.c b/arch/alpha/mm/init.c index df6df025ded4..91eddd8505df 100644 --- a/arch/alpha/mm/init.c +++ b/arch/alpha/mm/init.c @@ -200,7 +200,7 @@ callback_init(void * kernel_end) /* register the vm area */ console_remap_vm.flags = VM_ALLOC; console_remap_vm.size = nr_pages << PAGE_SHIFT; - vm_area_register_early(&console_remap_vm); + vm_area_register_early(&console_remap_vm, PAGE_SIZE); vaddr = (unsigned long)consle_remap_vm.addr; diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 599ba7984310..2f6994fdf0e0 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -109,6 +109,6 @@ extern long vwrite(char *buf, char *addr, unsigned long count); */ extern rwlock_t vmlist_lock; extern struct vm_struct *vmlist; -extern __init void vm_area_register_early(struct vm_struct *vm); +extern __init void vm_area_register_early(struct vm_struct *vm, size_t align); #endif /* _LINUX_VMALLOC_H */ diff --git a/mm/percpu.c b/mm/percpu.c index ed92caa2aa3b..41e7a5f5ab1b 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -860,7 +860,7 @@ size_t __init pcpu_setup_static(pcpu_populate_pte_fn_t populate_pte_fn, /* init and register vm area */ static_vm.flags = VM_ALLOC; static_vm.size = pcpu_chunk_size; - vm_area_register_early(&static_vm); + vm_area_register_early(&static_vm, PAGE_SIZE); /* init static_chunk */ static_chunk = alloc_bootmem(pcpu_chunk_struct_size); diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 224eca9650a8..366ae9ea6af2 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -995,7 +995,7 @@ EXPORT_SYMBOL(vm_map_ram); /** * vm_area_register_early - register vmap area early during boot * @vm: vm_struct to register - * @size: size of area to register + * @align: requested alignment * * This function is used to register kernel vm area before * vmalloc_init() is called. @vm->size and @vm->flags should contain @@ -1004,12 +1004,15 @@ EXPORT_SYMBOL(vm_map_ram); * * DO NOT USE THIS FUNCTION UNLESS YOU KNOW WHAT YOU'RE DOING. */ -void __init vm_area_register_early(struct vm_struct *vm) +void __init vm_area_register_early(struct vm_struct *vm, size_t align) { static size_t vm_init_off __initdata; + unsigned long addr; + + addr = ALIGN(VMALLOC_START + vm_init_off, align); + vm_init_off = PFN_ALIGN(addr + vm->size) - VMALLOC_START; - vm->addr = (void *)VMALLOC_START + vm_init_off; - vm_init_off = PFN_ALIGN(vm_init_off + vm->size); + vm->addr = (void *)addr; vm->next = vmlist; vmlist = vm; -- cgit v1.2.3 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') diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index 671e6528a82d..d928e8887201 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 18080995ff3e..910beb0abea2 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 d9e6e5d1dbd4..9ac01980cce0 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 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') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 910beb0abea2..d8e5a9abbce0 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 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') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index d8e5a9abbce0..545b068bcb70 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 From a682604838763981613e42015cd0e39f2989d6bb Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 25 Feb 2009 18:03:42 -0800 Subject: rcu: Teach RCU that idle task is not quiscent state at boot This patch fixes a bug located by Vegard Nossum with the aid of kmemcheck, updated based on review comments from Nick Piggin, Ingo Molnar, and Andrew Morton. And cleans up the variable-name and function-name language. ;-) The boot CPU runs in the context of its idle thread during boot-up. During this time, idle_cpu(0) will always return nonzero, which will fool Classic and Hierarchical RCU into deciding that a large chunk of the boot-up sequence is a big long quiescent state. This in turn causes RCU to prematurely end grace periods during this time. This patch changes the rcutree.c and rcuclassic.c rcu_check_callbacks() function to ignore the idle task as a quiescent state until the system has started up the scheduler in rest_init(), introducing a new non-API function rcu_idle_now_means_idle() to inform RCU of this transition. RCU maintains an internal rcu_idle_cpu_truthful variable to track this state, which is then used by rcu_check_callback() to determine if it should believe idle_cpu(). Because this patch has the effect of disallowing RCU grace periods during long stretches of the boot-up sequence, this patch also introduces Josh Triplett's UP-only optimization that makes synchronize_rcu() be a no-op if num_online_cpus() returns 1. This allows boot-time code that calls synchronize_rcu() to proceed normally. Note, however, that RCU callbacks registered by call_rcu() will likely queue up until later in the boot sequence. Although rcuclassic and rcutree can also use this same optimization after boot completes, rcupreempt must restrict its use of this optimization to the portion of the boot sequence before the scheduler starts up, given that an rcupreempt RCU read-side critical section may be preeempted. In addition, this patch takes Nick Piggin's suggestion to make the system_state global variable be __read_mostly. Changes since v4: o Changes the name of the introduced function and variable to be less emotional. ;-) Changes since v3: o WARN_ON(nr_context_switches() > 0) to verify that RCU switches out of boot-time mode before the first context switch, as suggested by Nick Piggin. Changes since v2: o Created rcu_blocking_is_gp() internal-to-RCU API that determines whether a call to synchronize_rcu() is itself a grace period. o The definition of rcu_blocking_is_gp() for rcuclassic and rcutree checks to see if but a single CPU is online. o The definition of rcu_blocking_is_gp() for rcupreempt checks to see both if but a single CPU is online and if the system is still in early boot. This allows rcupreempt to again work correctly if running on a single CPU after booting is complete. o Added check to rcupreempt's synchronize_sched() for there being but one online CPU. Tested all three variants both SMP and !SMP, booted fine, passed a short rcutorture test on both x86 and Power. Located-by: Vegard Nossum Tested-by: Vegard Nossum Tested-by: Paul E. McKenney Signed-off-by: Paul E. McKenney Signed-off-by: Ingo Molnar --- include/linux/rcuclassic.h | 6 ++++++ include/linux/rcupdate.h | 4 ++++ include/linux/rcupreempt.h | 15 +++++++++++++++ include/linux/rcutree.h | 6 ++++++ init/main.c | 3 ++- kernel/rcuclassic.c | 4 ++-- kernel/rcupdate.c | 12 ++++++++++++ kernel/rcupreempt.c | 3 +++ kernel/rcutree.c | 4 ++-- 9 files changed, 52 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/rcuclassic.h b/include/linux/rcuclassic.h index f3f697df1d71..80044a4f3ab9 100644 --- a/include/linux/rcuclassic.h +++ b/include/linux/rcuclassic.h @@ -181,4 +181,10 @@ extern long rcu_batches_completed_bh(void); #define rcu_enter_nohz() do { } while (0) #define rcu_exit_nohz() do { } while (0) +/* A context switch is a grace period for rcuclassic. */ +static inline int rcu_blocking_is_gp(void) +{ + return num_online_cpus() == 1; +} + #endif /* __LINUX_RCUCLASSIC_H */ diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 921340a7b71c..528343e6da51 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -52,6 +52,9 @@ struct rcu_head { void (*func)(struct rcu_head *head); }; +/* Internal to kernel, but needed by rcupreempt.h. */ +extern int rcu_scheduler_active; + #if defined(CONFIG_CLASSIC_RCU) #include #elif defined(CONFIG_TREE_RCU) @@ -265,6 +268,7 @@ extern void rcu_barrier_sched(void); /* Internal to kernel */ extern void rcu_init(void); +extern void rcu_scheduler_starting(void); extern int rcu_needs_cpu(int cpu); #endif /* __LINUX_RCUPDATE_H */ diff --git a/include/linux/rcupreempt.h b/include/linux/rcupreempt.h index 3e05c09b54a2..74304b4538d8 100644 --- a/include/linux/rcupreempt.h +++ b/include/linux/rcupreempt.h @@ -142,4 +142,19 @@ static inline void rcu_exit_nohz(void) #define rcu_exit_nohz() do { } while (0) #endif /* CONFIG_NO_HZ */ +/* + * A context switch is a grace period for rcupreempt synchronize_rcu() + * only during early boot, before the scheduler has been initialized. + * So, how the heck do we get a context switch? Well, if the caller + * invokes synchronize_rcu(), they are willing to accept a context + * switch, so we simply pretend that one happened. + * + * After boot, there might be a blocked or preempted task in an RCU + * read-side critical section, so we cannot then take the fastpath. + */ +static inline int rcu_blocking_is_gp(void) +{ + return num_online_cpus() == 1 && !rcu_scheduler_active; +} + #endif /* __LINUX_RCUPREEMPT_H */ diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index d4368b7975c3..a722fb67bb2d 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -326,4 +326,10 @@ static inline void rcu_exit_nohz(void) } #endif /* CONFIG_NO_HZ */ +/* A context switch is a grace period for rcutree. */ +static inline int rcu_blocking_is_gp(void) +{ + return num_online_cpus() == 1; +} + #endif /* __LINUX_RCUTREE_H */ diff --git a/init/main.c b/init/main.c index 844209453c02..83697e160b3a 100644 --- a/init/main.c +++ b/init/main.c @@ -97,7 +97,7 @@ static inline void mark_rodata_ro(void) { } extern void tc_init(void); #endif -enum system_states system_state; +enum system_states system_state __read_mostly; EXPORT_SYMBOL(system_state); /* @@ -463,6 +463,7 @@ static noinline void __init_refok rest_init(void) * at least once to get things moving: */ init_idle_bootup_task(current); + rcu_scheduler_starting(); preempt_enable_no_resched(); schedule(); preempt_disable(); diff --git a/kernel/rcuclassic.c b/kernel/rcuclassic.c index bd5a9003497c..654c640a6b9c 100644 --- a/kernel/rcuclassic.c +++ b/kernel/rcuclassic.c @@ -679,8 +679,8 @@ int rcu_needs_cpu(int cpu) void rcu_check_callbacks(int cpu, int user) { if (user || - (idle_cpu(cpu) && !in_softirq() && - hardirq_count() <= (1 << HARDIRQ_SHIFT))) { + (idle_cpu(cpu) && rcu_scheduler_active && + !in_softirq() && hardirq_count() <= (1 << HARDIRQ_SHIFT))) { /* * Get here if this CPU took its interrupt from user diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c index d92a76a881aa..cae8a059cf47 100644 --- a/kernel/rcupdate.c +++ b/kernel/rcupdate.c @@ -44,6 +44,7 @@ #include #include #include +#include enum rcu_barrier { RCU_BARRIER_STD, @@ -55,6 +56,7 @@ static DEFINE_PER_CPU(struct rcu_head, rcu_barrier_head) = {NULL}; static atomic_t rcu_barrier_cpu_count; static DEFINE_MUTEX(rcu_barrier_mutex); static struct completion rcu_barrier_completion; +int rcu_scheduler_active __read_mostly; /* * Awaken the corresponding synchronize_rcu() instance now that a @@ -80,6 +82,10 @@ void wakeme_after_rcu(struct rcu_head *head) void synchronize_rcu(void) { struct rcu_synchronize rcu; + + if (rcu_blocking_is_gp()) + return; + init_completion(&rcu.completion); /* Will wake me after RCU finished. */ call_rcu(&rcu.head, wakeme_after_rcu); @@ -175,3 +181,9 @@ void __init rcu_init(void) __rcu_init(); } +void rcu_scheduler_starting(void) +{ + WARN_ON(num_online_cpus() != 1); + WARN_ON(nr_context_switches() > 0); + rcu_scheduler_active = 1; +} diff --git a/kernel/rcupreempt.c b/kernel/rcupreempt.c index 33cfc50781f9..5d59e850fb71 100644 --- a/kernel/rcupreempt.c +++ b/kernel/rcupreempt.c @@ -1181,6 +1181,9 @@ void __synchronize_sched(void) { struct rcu_synchronize rcu; + if (num_online_cpus() == 1) + return; /* blocking is gp if only one CPU! */ + init_completion(&rcu.completion); /* Will wake me after RCU finished. */ call_rcu_sched(&rcu.head, wakeme_after_rcu); diff --git a/kernel/rcutree.c b/kernel/rcutree.c index b2fd602a6f6f..97ce31579ec0 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -948,8 +948,8 @@ static void rcu_do_batch(struct rcu_data *rdp) void rcu_check_callbacks(int cpu, int user) { if (user || - (idle_cpu(cpu) && !in_softirq() && - hardirq_count() <= (1 << HARDIRQ_SHIFT))) { + (idle_cpu(cpu) && rcu_scheduler_active && + !in_softirq() && hardirq_count() <= (1 << HARDIRQ_SHIFT))) { /* * Get here if this CPU took its interrupt from user -- cgit v1.2.3 From 54e991242850edc8c53f71fa5aa3ba7a93ce38f5 Mon Sep 17 00:00:00 2001 From: Dhaval Giani Date: Fri, 27 Feb 2009 15:13:54 +0530 Subject: sched: don't allow setuid to succeed if the user does not have rt bandwidth Impact: fix hung task with certain (non-default) rt-limit settings Corey Hickey reported that on using setuid to change the uid of a rt process, the process would be unkillable and not be running. This is because there was no rt runtime for that user group. Add in a check to see if a user can attach an rt task to its task group. On failure, return EINVAL, which is also returned in CONFIG_CGROUP_SCHED. Reported-by: Corey Hickey Signed-off-by: Dhaval Giani Acked-by: Peter Zijlstra Signed-off-by: Ingo Molnar --- include/linux/sched.h | 4 ++++ kernel/sched.c | 13 +++++++++++-- kernel/sys.c | 31 ++++++++++++++++++++----------- kernel/user.c | 18 ++++++++++++++++++ 4 files changed, 53 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 8981e52c714f..8c216e057c94 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2291,9 +2291,13 @@ extern long sched_group_rt_runtime(struct task_group *tg); extern int sched_group_set_rt_period(struct task_group *tg, long rt_period_us); extern long sched_group_rt_period(struct task_group *tg); +extern int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk); #endif #endif +extern int task_can_switch_user(struct user_struct *up, + struct task_struct *tsk); + #ifdef CONFIG_TASK_XACCT static inline void add_rchar(struct task_struct *tsk, ssize_t amt) { diff --git a/kernel/sched.c b/kernel/sched.c index c3baa9653d1d..8e2558c2ba67 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -9224,6 +9224,16 @@ static int sched_rt_global_constraints(void) return ret; } + +int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk) +{ + /* Don't accept realtime tasks when there is no way for them to run */ + if (rt_task(tsk) && tg->rt_bandwidth.rt_runtime == 0) + return 0; + + return 1; +} + #else /* !CONFIG_RT_GROUP_SCHED */ static int sched_rt_global_constraints(void) { @@ -9317,8 +9327,7 @@ cpu_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp, struct task_struct *tsk) { #ifdef CONFIG_RT_GROUP_SCHED - /* Don't accept realtime tasks when there is no way for them to run */ - if (rt_task(tsk) && cgroup_tg(cgrp)->rt_bandwidth.rt_runtime == 0) + if (!sched_rt_can_attach(cgroup_tg(cgrp), tsk)) return -EINVAL; #else /* We don't support RT-tasks being in separate groups */ diff --git a/kernel/sys.c b/kernel/sys.c index f145c415bc16..37f458e6882a 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -559,7 +559,7 @@ error: abort_creds(new); return retval; } - + /* * change the user struct in a credentials set to match the new UID */ @@ -571,6 +571,11 @@ static int set_user(struct cred *new) if (!new_user) return -EAGAIN; + if (!task_can_switch_user(new_user, current)) { + free_uid(new_user); + return -EINVAL; + } + if (atomic_read(&new_user->processes) >= current->signal->rlim[RLIMIT_NPROC].rlim_cur && new_user != INIT_USER) { @@ -631,10 +636,11 @@ SYSCALL_DEFINE2(setreuid, uid_t, ruid, uid_t, euid) goto error; } - retval = -EAGAIN; - if (new->uid != old->uid && set_user(new) < 0) - goto error; - + if (new->uid != old->uid) { + retval = set_user(new); + if (retval < 0) + goto error; + } if (ruid != (uid_t) -1 || (euid != (uid_t) -1 && euid != old->uid)) new->suid = new->euid; @@ -680,9 +686,10 @@ SYSCALL_DEFINE1(setuid, uid_t, uid) retval = -EPERM; if (capable(CAP_SETUID)) { new->suid = new->uid = uid; - if (uid != old->uid && set_user(new) < 0) { - retval = -EAGAIN; - goto error; + if (uid != old->uid) { + retval = set_user(new); + if (retval < 0) + goto error; } } else if (uid != old->uid && uid != new->suid) { goto error; @@ -734,11 +741,13 @@ SYSCALL_DEFINE3(setresuid, uid_t, ruid, uid_t, euid, uid_t, suid) goto error; } - retval = -EAGAIN; if (ruid != (uid_t) -1) { new->uid = ruid; - if (ruid != old->uid && set_user(new) < 0) - goto error; + if (ruid != old->uid) { + retval = set_user(new); + if (retval < 0) + goto error; + } } if (euid != (uid_t) -1) new->euid = euid; diff --git a/kernel/user.c b/kernel/user.c index 3551ac742395..6a9b696128c8 100644 --- a/kernel/user.c +++ b/kernel/user.c @@ -362,6 +362,24 @@ static void free_user(struct user_struct *up, unsigned long flags) #endif +#if defined(CONFIG_RT_GROUP_SCHED) && defined(CONFIG_USER_SCHED) +/* + * We need to check if a setuid can take place. This function should be called + * before successfully completing the setuid. + */ +int task_can_switch_user(struct user_struct *up, struct task_struct *tsk) +{ + + return sched_rt_can_attach(up->tg, tsk); + +} +#else +int task_can_switch_user(struct user_struct *up, struct task_struct *tsk) +{ + return 1; +} +#endif + /* * Locate the user_struct for the passed UID. If found, take a ref on it. The * caller must undo that ref with free_uid(). -- cgit v1.2.3 From 17edde520927070a6bf14a6a75027c0b843443e5 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 22 Feb 2009 00:11:09 -0800 Subject: netns: Remove net_alive It turns out that net_alive is unnecessary, and the original problem that led to it being added was simply that the icmp code thought it was a network device and wound up being unable to handle packets while there were still packets in the network namespace. Now that icmp and tcp have been fixed to properly register themselves this problem is no longer present and we have a stronger guarantee that packets will not arrive in a network namespace then that provided by net_alive in netif_receive_skb. So remove net_alive allowing packet reception run a little faster. Additionally document the strong reason why network namespace cleanup is safe so that if something happens again someone else will have a chance of figuring it out. Signed-off-by: Eric W. Biederman Signed-off-by: David S. Miller --- include/net/net_namespace.h | 27 +++++++++++++++++---------- net/core/dev.c | 6 ------ net/core/net_namespace.c | 3 --- 3 files changed, 17 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 6fc13d905c5f..ded434b032a4 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -109,11 +109,6 @@ extern struct list_head net_namespace_list; #ifdef CONFIG_NET_NS extern void __put_net(struct net *net); -static inline int net_alive(struct net *net) -{ - return net && atomic_read(&net->count); -} - static inline struct net *get_net(struct net *net) { atomic_inc(&net->count); @@ -145,11 +140,6 @@ int net_eq(const struct net *net1, const struct net *net2) } #else -static inline int net_alive(struct net *net) -{ - return 1; -} - static inline struct net *get_net(struct net *net) { return net; @@ -234,6 +224,23 @@ struct pernet_operations { void (*exit)(struct net *net); }; +/* + * Use these carefully. If you implement a network device and it + * needs per network namespace operations use device pernet operations, + * otherwise use pernet subsys operations. + * + * This is critically important. Most of the network code cleanup + * runs with the assumption that dev_remove_pack has been called so no + * new packets will arrive during and after the cleanup functions have + * been called. dev_remove_pack is not per namespace so instead the + * guarantee of no more packets arriving in a network namespace is + * provided by ensuring that all network devices and all sockets have + * left the network namespace before the cleanup methods are called. + * + * For the longest time the ipv4 icmp code was registered as a pernet + * device which caused kernel oops, and panics during network + * namespace cleanup. So please don't get this wrong. + */ extern int register_pernet_subsys(struct pernet_operations *); extern void unregister_pernet_subsys(struct pernet_operations *); extern int register_pernet_gen_subsys(int *id, struct pernet_operations *); diff --git a/net/core/dev.c b/net/core/dev.c index 72b0d26fd46d..9e4afe650e7a 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2267,12 +2267,6 @@ int netif_receive_skb(struct sk_buff *skb) rcu_read_lock(); - /* Don't receive packets in an exiting network namespace */ - if (!net_alive(dev_net(skb->dev))) { - kfree_skb(skb); - goto out; - } - #ifdef CONFIG_NET_CLS_ACT if (skb->tc_verd & TC_NCLS) { skb->tc_verd = CLR_TC_NCLS(skb->tc_verd); diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 2adb1a7d361f..e3bebd36f053 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -157,9 +157,6 @@ static void cleanup_net(struct work_struct *work) struct pernet_operations *ops; struct net *net; - /* Be very certain incoming network packets will not find us */ - rcu_barrier(); - net = container_of(work, struct net, work); mutex_lock(&net_mutex); -- cgit v1.2.3 From 9d40bbda599def1e1d155d7f7dca14fe8744bd2b Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Wed, 4 Mar 2009 23:46:25 -0800 Subject: vlan: Fix vlan-in-vlan crashes. As analyzed by Patrick McHardy, vlan needs to reset it's netdev_ops pointer in it's ->init() function but this leaves the compat method pointers stale. Add a netdev_resync_ops() and call it from the vlan code. Any other driver which changes ->netdev_ops after register_netdevice() will need to call this new function after doing so too. With help from Patrick McHardy. Tested-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + net/8021q/vlan_dev.c | 3 ++- net/core/dev.c | 56 ++++++++++++++++++++++++++++------------------- 3 files changed, 37 insertions(+), 23 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ec54785d34f9..659366734f3f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1079,6 +1079,7 @@ extern void synchronize_net(void); extern int register_netdevice_notifier(struct notifier_block *nb); extern int unregister_netdevice_notifier(struct notifier_block *nb); extern int init_dummy_netdev(struct net_device *dev); +extern void netdev_resync_ops(struct net_device *dev); extern int call_netdevice_notifiers(unsigned long val, struct net_device *dev); extern struct net_device *dev_get_by_index(struct net *net, int ifindex); diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 4a19acd3a32b..1b34135cf990 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -553,7 +553,7 @@ static int vlan_dev_neigh_setup(struct net_device *dev, struct neigh_parms *pa) int err = 0; if (netif_device_present(real_dev) && ops->ndo_neigh_setup) - err = ops->ndo_neigh_setup(dev, pa); + err = ops->ndo_neigh_setup(real_dev, pa); return err; } @@ -639,6 +639,7 @@ static int vlan_dev_init(struct net_device *dev) dev->hard_header_len = real_dev->hard_header_len + VLAN_HLEN; dev->netdev_ops = &vlan_netdev_ops; } + netdev_resync_ops(dev); if (is_vlan_dev(real_dev)) subclass = 1; diff --git a/net/core/dev.c b/net/core/dev.c index 2dd484ed3dbb..f1129706ce7b 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4282,6 +4282,39 @@ unsigned long netdev_fix_features(unsigned long features, const char *name) } EXPORT_SYMBOL(netdev_fix_features); +/* Some devices need to (re-)set their netdev_ops inside + * ->init() or similar. If that happens, we have to setup + * the compat pointers again. + */ +void netdev_resync_ops(struct net_device *dev) +{ +#ifdef CONFIG_COMPAT_NET_DEV_OPS + const struct net_device_ops *ops = dev->netdev_ops; + + dev->init = ops->ndo_init; + dev->uninit = ops->ndo_uninit; + dev->open = ops->ndo_open; + dev->change_rx_flags = ops->ndo_change_rx_flags; + dev->set_rx_mode = ops->ndo_set_rx_mode; + dev->set_multicast_list = ops->ndo_set_multicast_list; + dev->set_mac_address = ops->ndo_set_mac_address; + dev->validate_addr = ops->ndo_validate_addr; + dev->do_ioctl = ops->ndo_do_ioctl; + dev->set_config = ops->ndo_set_config; + dev->change_mtu = ops->ndo_change_mtu; + dev->neigh_setup = ops->ndo_neigh_setup; + dev->tx_timeout = ops->ndo_tx_timeout; + dev->get_stats = ops->ndo_get_stats; + dev->vlan_rx_register = ops->ndo_vlan_rx_register; + dev->vlan_rx_add_vid = ops->ndo_vlan_rx_add_vid; + dev->vlan_rx_kill_vid = ops->ndo_vlan_rx_kill_vid; +#ifdef CONFIG_NET_POLL_CONTROLLER + dev->poll_controller = ops->ndo_poll_controller; +#endif +#endif +} +EXPORT_SYMBOL(netdev_resync_ops); + /** * register_netdevice - register a network device * @dev: device to register @@ -4326,28 +4359,7 @@ int register_netdevice(struct net_device *dev) * This is temporary until all network devices are converted. */ if (dev->netdev_ops) { - const struct net_device_ops *ops = dev->netdev_ops; - - dev->init = ops->ndo_init; - dev->uninit = ops->ndo_uninit; - dev->open = ops->ndo_open; - dev->change_rx_flags = ops->ndo_change_rx_flags; - dev->set_rx_mode = ops->ndo_set_rx_mode; - dev->set_multicast_list = ops->ndo_set_multicast_list; - dev->set_mac_address = ops->ndo_set_mac_address; - dev->validate_addr = ops->ndo_validate_addr; - dev->do_ioctl = ops->ndo_do_ioctl; - dev->set_config = ops->ndo_set_config; - dev->change_mtu = ops->ndo_change_mtu; - dev->neigh_setup = ops->ndo_neigh_setup; - dev->tx_timeout = ops->ndo_tx_timeout; - dev->get_stats = ops->ndo_get_stats; - dev->vlan_rx_register = ops->ndo_vlan_rx_register; - dev->vlan_rx_add_vid = ops->ndo_vlan_rx_add_vid; - dev->vlan_rx_kill_vid = ops->ndo_vlan_rx_kill_vid; -#ifdef CONFIG_NET_POLL_CONTROLLER - dev->poll_controller = ops->ndo_poll_controller; -#endif + netdev_resync_ops(dev); } else { char drivername[64]; pr_info("%s (%s): not using net_device_ops yet\n", -- cgit v1.2.3 From e7d3ef13d52a126438f687a1a32da65ff926ed57 Mon Sep 17 00:00:00 2001 From: Stuart Hayes Date: Wed, 4 Mar 2009 11:59:46 -0800 Subject: libata: change drive ready wait after hard reset to 5s This fixes problems during resume with drives that take longer than 1s to be ready. The ATA-6 spec appears to allow 5 seconds for a drive to be ready. On one affected system, this patch changes "PM: resume devices took..." message from 17 seconds to 4 seconds, and gets rid of a lot of ugly timeout/error messages. Without this patch, the libata code moves on after 1s, tries to send a soft reset (which the drive doesn't see because it isn't ready) which also times out, then an IDENTIFY command is sent to the drive which times out, and finally the error handler will try to send another hard reset which will finally get things working. Signed-off-by: Stuart Hayes Signed-off-by: Andrew Morton Signed-off-by: Jeff Garzik --- include/linux/libata.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/libata.h b/include/linux/libata.h index 5d87bc09a1f5..dd818c7decd7 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -275,7 +275,7 @@ enum { * advised to wait only for the following duration before * doing SRST. */ - ATA_TMOUT_PMP_SRST_WAIT = 1000, + ATA_TMOUT_PMP_SRST_WAIT = 5000, /* ATA bus states */ BUS_UNKNOWN = 0, -- cgit v1.2.3 From 5825627c9463581fd9e70f8285685889ae5bb9bb Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Fri, 27 Feb 2009 17:35:43 +0900 Subject: libata: fix dma_unmap_sg misuse libata passes the returned value of dma_map_sg() to dma_unmap_sg(),which is the misuse of dma_unmap_sg(). DMA-mapping.txt says: To unmap a scatterlist, just call: pci_unmap_sg(pdev, sglist, nents, direction); Again, make sure DMA activity has already finished. PLEASE NOTE: The 'nents' argument to the pci_unmap_sg call must be the _same_ one you passed into the pci_map_sg call, it should _NOT_ be the 'count' value _returned_ from the pci_map_sg call. Signed-off-by: FUJITA Tomonori Acked-by: Bartlomiej Zolnierkiewicz Acked-by: Tejun Heo Signed-off-by: Jeff Garzik --- drivers/ata/libata-core.c | 4 ++-- include/linux/libata.h | 1 + 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 9fbf0595f3d4..5e324cea3019 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -4612,7 +4612,7 @@ void ata_sg_clean(struct ata_queued_cmd *qc) VPRINTK("unmapping %u sg elements\n", qc->n_elem); if (qc->n_elem) - dma_unmap_sg(ap->dev, sg, qc->n_elem, dir); + dma_unmap_sg(ap->dev, sg, qc->orig_n_elem, dir); qc->flags &= ~ATA_QCFLAG_DMAMAP; qc->sg = NULL; @@ -4727,7 +4727,7 @@ static int ata_sg_setup(struct ata_queued_cmd *qc) return -1; DPRINTK("%d sg elements mapped\n", n_elem); - + qc->orig_n_elem = qc->n_elem; qc->n_elem = n_elem; qc->flags |= ATA_QCFLAG_DMAMAP; diff --git a/include/linux/libata.h b/include/linux/libata.h index dd818c7decd7..fbf064e13ad5 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -530,6 +530,7 @@ struct ata_queued_cmd { unsigned long flags; /* ATA_QCFLAG_xxx */ unsigned int tag; unsigned int n_elem; + unsigned int orig_n_elem; int dma_dir; -- cgit v1.2.3 From 84bda12af31f930e4200c5244aa111de2485d7b0 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 2 Mar 2009 18:53:26 +0900 Subject: libata: align ap->sector_buf ap->sector_buf is used as DMA target and should at least be aligned on cacheline. This caused problems on some embedded machines. Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- include/linux/libata.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/libata.h b/include/linux/libata.h index fbf064e13ad5..dc18b87ed722 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -751,7 +751,8 @@ struct ata_port { acpi_handle acpi_handle; struct ata_acpi_gtm __acpi_init_gtm; /* use ata_acpi_init_gtm() */ #endif - u8 sector_buf[ATA_SECT_SIZE]; /* owned by EH */ + /* owned by EH */ + u8 sector_buf[ATA_SECT_SIZE] ____cacheline_aligned; }; /* The following initializer overrides a method to NULL whether one of -- cgit v1.2.3 From 849d7130001ab740a5a4778a561049841fdd77c9 Mon Sep 17 00:00:00 2001 From: Stanislaw Gruszka Date: Thu, 5 Mar 2009 16:10:57 +0100 Subject: ide: allow to wrap interrupt handler Signed-off-by: Stanislaw Gruszka Cc: Andrew Victor [bart: minor checkpatch.pl / CodingStyle fixups] Signed-off-by: Bartlomiej Zolnierkiewicz --- drivers/ide/ide-io.c | 1 + drivers/ide/ide-probe.c | 7 ++++++- include/linux/ide.h | 1 + 3 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/ide/ide-io.c b/drivers/ide/ide-io.c index 9ff90cb1dbf1..a9a6c208288a 100644 --- a/drivers/ide/ide-io.c +++ b/drivers/ide/ide-io.c @@ -1162,6 +1162,7 @@ out_early: return irq_ret; } +EXPORT_SYMBOL_GPL(ide_intr); /** * ide_do_drive_cmd - issue IDE special command diff --git a/drivers/ide/ide-probe.c b/drivers/ide/ide-probe.c index ce0818a993f6..ee8e3e7cad51 100644 --- a/drivers/ide/ide-probe.c +++ b/drivers/ide/ide-probe.c @@ -950,6 +950,7 @@ static int ide_port_setup_devices(ide_hwif_t *hwif) static int init_irq (ide_hwif_t *hwif) { struct ide_io_ports *io_ports = &hwif->io_ports; + irq_handler_t irq_handler; int sa = 0; mutex_lock(&ide_cfg_mtx); @@ -959,6 +960,10 @@ static int init_irq (ide_hwif_t *hwif) hwif->timer.function = &ide_timer_expiry; hwif->timer.data = (unsigned long)hwif; + irq_handler = hwif->host->irq_handler; + if (irq_handler == NULL) + irq_handler = ide_intr; + #if defined(__mc68000__) sa = IRQF_SHARED; #endif /* __mc68000__ */ @@ -969,7 +974,7 @@ static int init_irq (ide_hwif_t *hwif) if (io_ports->ctl_addr) hwif->tp_ops->set_irq(hwif, 1); - if (request_irq(hwif->irq, &ide_intr, sa, hwif->name, hwif)) + if (request_irq(hwif->irq, irq_handler, sa, hwif->name, hwif)) goto out_up; if (!hwif->rqsize) { diff --git a/include/linux/ide.h b/include/linux/ide.h index fe235b65207e..e0cedfe9fad4 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -866,6 +866,7 @@ struct ide_host { unsigned int n_ports; struct device *dev[2]; unsigned int (*init_chipset)(struct pci_dev *); + irq_handler_t irq_handler; unsigned long host_flags; void *host_priv; ide_hwif_t *cur_port; /* for hosts requiring serialization */ -- cgit v1.2.3 From ebcad5aaea26da3cb2ca90b7f31a67a027eb60db Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Thu, 5 Mar 2009 16:10:59 +0100 Subject: remove stale comment from HDIO_GET_IDENTITY returns 256 words currently. Noticed by Norman Diamond. Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/hdreg.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/hdreg.h b/include/linux/hdreg.h index c37e9241fae7..ed21bd3dbd25 100644 --- a/include/linux/hdreg.h +++ b/include/linux/hdreg.h @@ -511,7 +511,6 @@ struct hd_driveid { unsigned short words69_70[2]; /* reserved words 69-70 * future command overlap and queuing */ - /* HDIO_GET_IDENTITY currently returns only words 0 through 70 */ unsigned short words71_74[4]; /* reserved words 71-74 * for IDENTIFY PACKET DEVICE command */ -- cgit v1.2.3 From d42ad15b759d05a87f22b484af63987eff38ea88 Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Thu, 5 Mar 2009 17:20:55 +0100 Subject: ata: add CFA specific identify data words Declare CFA specific identify data words 162 and 163 for future use. Signed-off-by: Sergei Shtylyov Signed-off-by: Jeff Garzik [bart: update patch summary/description] Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ata.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/ata.h b/include/linux/ata.h index 08a86d5cdf1b..9a061accd8b8 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -89,6 +89,8 @@ enum { ATA_ID_DLF = 128, ATA_ID_CSFO = 129, ATA_ID_CFA_POWER = 160, + ATA_ID_CFA_KEY_MGMT = 162, + ATA_ID_CFA_MODES = 163, ATA_ID_ROT_SPEED = 217, ATA_ID_PIO4 = (1 << 1), -- cgit v1.2.3 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') diff --git a/arch/blackfin/include/asm/percpu.h b/arch/blackfin/include/asm/percpu.h index 797c0c165069..c94c7bc88c71 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 545b068bcb70..2d34b038fe70 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 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') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 2d34b038fe70..a0b4ea2a3354 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 3d0f5456827c..9531590e6b69 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 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') diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index c29f301d3885..ef3a2cd3fe64 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 a0b4ea2a3354..a96fc53bbd62 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 503ccad091af..a84cf9977faf 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 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') diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index 38e2b2a470a5..dd4eabc747c8 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 a96fc53bbd62..8ff15153ae20 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 1f0657ae555b..f0e04d6b67d8 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 5b47d9fe65f5..ef8e169b7731 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 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') diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index dd4eabc747c8..efa615f2bf43 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 8ff15153ae20..54a968b4b924 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 From ab96ddec7213004b632d24dc2cdcd2df5f16f50b Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Sat, 7 Mar 2009 13:39:22 -0800 Subject: Input: serio - fix protocol number for TouchIT213 Protocol 0x37 has been reserved for iNexio devices and Sahara was supposed to get 0x38. Reported-by: Claudio Nieder Signed-off-by: Dmitry Torokhov --- include/linux/serio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/serio.h b/include/linux/serio.h index 1bcb357a01a1..e0417e4d3f15 100644 --- a/include/linux/serio.h +++ b/include/linux/serio.h @@ -212,7 +212,7 @@ static inline void serio_unpin_driver(struct serio *serio) #define SERIO_FUJITSU 0x35 #define SERIO_ZHENHUA 0x36 #define SERIO_INEXIO 0x37 -#define SERIO_TOUCHIT213 0x37 +#define SERIO_TOUCHIT213 0x38 #define SERIO_W8001 0x39 #endif -- cgit v1.2.3 From 129f8ae9b1b5be94517da76009ea956e89104ce8 Mon Sep 17 00:00:00 2001 From: Dave Jones Date: Mon, 9 Mar 2009 15:07:33 -0400 Subject: Revert "[CPUFREQ] Disable sysfs ui for p4-clockmod." This reverts commit e088e4c9cdb618675874becb91b2fd581ee707e6. Removing the sysfs interface for p4-clockmod was flagged as a regression in bug 12826. Course of action: - Find out the remaining causes of overheating, and fix them if possible. ACPI should be doing the right thing automatically. If it isn't, we need to fix that. - mark p4-clockmod ui as deprecated - try again with the removal in six months. It's not really feasible to printk about the deprecation, because it needs to happen at all the sysfs entry points, which means adding a lot of strcmp("p4-clockmod".. calls to the core, which.. bleuch. Signed-off-by: Dave Jones --- arch/x86/kernel/cpu/cpufreq/p4-clockmod.c | 1 - drivers/cpufreq/cpufreq.c | 51 +++++++++++-------------------- include/linux/cpufreq.h | 1 - 3 files changed, 18 insertions(+), 35 deletions(-) (limited to 'include') diff --git a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c index b585e04cbc9e..3178c3acd97e 100644 --- a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c +++ b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c @@ -277,7 +277,6 @@ static struct cpufreq_driver p4clockmod_driver = { .name = "p4-clockmod", .owner = THIS_MODULE, .attr = p4clockmod_attr, - .hide_interface = 1, }; diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index b55cb67435bd..d6daf3c507d3 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -754,11 +754,6 @@ static struct kobj_type ktype_cpufreq = { .release = cpufreq_sysfs_release, }; -static struct kobj_type ktype_empty_cpufreq = { - .sysfs_ops = &sysfs_ops, - .release = cpufreq_sysfs_release, -}; - /** * cpufreq_add_dev - add a CPU device @@ -892,36 +887,26 @@ static int cpufreq_add_dev(struct sys_device *sys_dev) memcpy(&new_policy, policy, sizeof(struct cpufreq_policy)); /* prepare interface data */ - if (!cpufreq_driver->hide_interface) { - ret = kobject_init_and_add(&policy->kobj, &ktype_cpufreq, - &sys_dev->kobj, "cpufreq"); + ret = kobject_init_and_add(&policy->kobj, &ktype_cpufreq, &sys_dev->kobj, + "cpufreq"); + if (ret) + goto err_out_driver_exit; + + /* set up files for this cpu device */ + drv_attr = cpufreq_driver->attr; + while ((drv_attr) && (*drv_attr)) { + ret = sysfs_create_file(&policy->kobj, &((*drv_attr)->attr)); if (ret) goto err_out_driver_exit; - - /* set up files for this cpu device */ - drv_attr = cpufreq_driver->attr; - while ((drv_attr) && (*drv_attr)) { - ret = sysfs_create_file(&policy->kobj, - &((*drv_attr)->attr)); - if (ret) - goto err_out_driver_exit; - drv_attr++; - } - if (cpufreq_driver->get) { - ret = sysfs_create_file(&policy->kobj, - &cpuinfo_cur_freq.attr); - if (ret) - goto err_out_driver_exit; - } - if (cpufreq_driver->target) { - ret = sysfs_create_file(&policy->kobj, - &scaling_cur_freq.attr); - if (ret) - goto err_out_driver_exit; - } - } else { - ret = kobject_init_and_add(&policy->kobj, &ktype_empty_cpufreq, - &sys_dev->kobj, "cpufreq"); + drv_attr++; + } + if (cpufreq_driver->get) { + ret = sysfs_create_file(&policy->kobj, &cpuinfo_cur_freq.attr); + if (ret) + goto err_out_driver_exit; + } + if (cpufreq_driver->target) { + ret = sysfs_create_file(&policy->kobj, &scaling_cur_freq.attr); if (ret) goto err_out_driver_exit; } diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 384b38d3e8e2..161042746afc 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -234,7 +234,6 @@ struct cpufreq_driver { int (*suspend) (struct cpufreq_policy *policy, pm_message_t pmsg); int (*resume) (struct cpufreq_policy *policy); struct freq_attr **attr; - bool hide_interface; }; /* flags */ -- cgit v1.2.3