From e1783a240f491fb233f04edc042e16b18a7a79ba Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Tue, 5 Jan 2010 15:34:50 +0900 Subject: module: Use this_cpu_xx to dynamically allocate counters Use cpu ops to deal with the per cpu data instead of a local_t. Reduces memory requirements, cache footprint and decreases cycle counts. The this_cpu_xx operations are also used for !SMP mode. Otherwise we could not drop the use of __module_ref_addr() which would make per cpu data handling complicated. this_cpu_xx operations have their own fallback for !SMP. V8-V9: - Leave include asm/module.h since ringbuffer.c depends on it. Nothing else does though. Another patch will deal with that. - Remove spurious free. Signed-off-by: Christoph Lameter Acked-by: Rusty Russell Signed-off-by: Tejun Heo --- kernel/module.c | 29 +++++++++++++++-------------- 1 file changed, 15 insertions(+), 14 deletions(-) (limited to 'kernel/module.c') diff --git a/kernel/module.c b/kernel/module.c index e96b8ed1cb6a..9bf228052ec5 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -474,9 +474,10 @@ static void module_unload_init(struct module *mod) INIT_LIST_HEAD(&mod->modules_which_use_me); for_each_possible_cpu(cpu) - local_set(__module_ref_addr(mod, cpu), 0); + per_cpu_ptr(mod->refptr, cpu)->count = 0; + /* Hold reference count during initialization. */ - local_set(__module_ref_addr(mod, raw_smp_processor_id()), 1); + __this_cpu_write(mod->refptr->count, 1); /* Backwards compatibility macros put refcount during init. */ mod->waiter = current; } @@ -619,7 +620,7 @@ unsigned int module_refcount(struct module *mod) int cpu; for_each_possible_cpu(cpu) - total += local_read(__module_ref_addr(mod, cpu)); + total += per_cpu_ptr(mod->refptr, cpu)->count; return total; } EXPORT_SYMBOL(module_refcount); @@ -796,14 +797,15 @@ static struct module_attribute refcnt = { void module_put(struct module *module) { if (module) { - unsigned int cpu = get_cpu(); - local_dec(__module_ref_addr(module, cpu)); + preempt_disable(); + __this_cpu_dec(module->refptr->count); + trace_module_put(module, _RET_IP_, - local_read(__module_ref_addr(module, cpu))); + __this_cpu_read(module->refptr->count)); /* Maybe they're waiting for us to drop reference? */ if (unlikely(!module_is_live(module))) wake_up_process(module->waiter); - put_cpu(); + preempt_enable(); } } EXPORT_SYMBOL(module_put); @@ -1394,9 +1396,9 @@ static void free_module(struct module *mod) kfree(mod->args); if (mod->percpu) percpu_modfree(mod->percpu); -#if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP) +#if defined(CONFIG_MODULE_UNLOAD) if (mod->refptr) - percpu_modfree(mod->refptr); + free_percpu(mod->refptr); #endif /* Free lock-classes: */ lockdep_free_key_range(mod->module_core, mod->core_size); @@ -2159,9 +2161,8 @@ static noinline struct module *load_module(void __user *umod, mod = (void *)sechdrs[modindex].sh_addr; kmemleak_load_module(mod, hdr, sechdrs, secstrings); -#if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP) - mod->refptr = percpu_modalloc(sizeof(local_t), __alignof__(local_t), - mod->name); +#if defined(CONFIG_MODULE_UNLOAD) + mod->refptr = alloc_percpu(struct module_ref); if (!mod->refptr) { err = -ENOMEM; goto free_init; @@ -2393,8 +2394,8 @@ static noinline struct module *load_module(void __user *umod, kobject_put(&mod->mkobj.kobj); free_unload: module_unload_free(mod); -#if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP) - percpu_modfree(mod->refptr); +#if defined(CONFIG_MODULE_UNLOAD) + free_percpu(mod->refptr); free_init: #endif module_free(mod, mod->module_init); -- cgit v1.3-8-gc7d7 From 361795b1eb7c08e9e65a2ebb4a4e536294d378a2 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 12 Feb 2010 13:41:56 -0800 Subject: sysfs: Use sysfs_attr_init and sysfs_bin_attr_init on module dynamic attributes A little more whack-a-mole annotating the dynamic sysfs attributes. I had everything built into my earlier test kernel, and so I missed these. Signed-off-by: Eric W. Biederman Signed-off-by: Greg Kroah-Hartman --- kernel/module.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'kernel/module.c') diff --git a/kernel/module.c b/kernel/module.c index e5538d5f00ad..c968d3606dca 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1085,6 +1085,7 @@ static void add_sect_attrs(struct module *mod, unsigned int nsect, if (sattr->name == NULL) goto out; sect_attrs->nsections++; + sysfs_attr_init(&sattr->mattr.attr); sattr->mattr.show = module_sect_show; sattr->mattr.store = NULL; sattr->mattr.attr.name = sattr->name; @@ -1180,6 +1181,7 @@ static void add_notes_attrs(struct module *mod, unsigned int nsect, if (sect_empty(&sechdrs[i])) continue; if (sechdrs[i].sh_type == SHT_NOTE) { + sysfs_bin_attr_init(nattr); nattr->attr.name = mod->sect_attrs->attrs[loaded].name; nattr->attr.mode = S_IRUGO; nattr->size = sechdrs[i].sh_size; @@ -1252,6 +1254,7 @@ int module_add_modinfo_attrs(struct module *mod) if (!attr->test || (attr->test && attr->test(mod))) { memcpy(temp_attr, attr, sizeof(*temp_attr)); + sysfs_attr_init(&temp_attr->attr); error = sysfs_create_file(&mod->mkobj.kobj,&temp_attr->attr); ++temp_attr; } -- cgit v1.3-8-gc7d7 From 259354deaaf03d49a02dbb9975d6ec2a54675672 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 10 Mar 2010 18:56:10 +0900 Subject: module: encapsulate percpu handling better and record percpu_size Better encapsulate module static percpu area handling so that code outsidef of CONFIG_SMP ifdef doesn't deal with mod->percpu directly and add mod->percpu_size and record percpu_size in it. Both percpu fields are compiled out on UP. While at it, mark mod->percpu w/ __percpu. This is to prepare for is_module_percpu_address(). Signed-off-by: Tejun Heo Acked-by: Rusty Russell --- include/linux/module.h | 5 +++- kernel/module.c | 66 ++++++++++++++++++++++++++------------------------ 2 files changed, 39 insertions(+), 32 deletions(-) (limited to 'kernel/module.c') diff --git a/include/linux/module.h b/include/linux/module.h index 5e869ffd34aa..87d247ac6761 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -330,8 +330,11 @@ struct module struct module_notes_attrs *notes_attrs; #endif +#ifdef CONFIG_SMP /* Per-cpu data. */ - void *percpu; + void __percpu *percpu; + unsigned int percpu_size; +#endif /* The command line arguments (may be mangled). People like keeping pointers to this stuff */ diff --git a/kernel/module.c b/kernel/module.c index c968d3606dca..e7a6e53fc73e 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -370,27 +370,33 @@ EXPORT_SYMBOL_GPL(find_module); #ifdef CONFIG_SMP -static void *percpu_modalloc(unsigned long size, unsigned long align, - const char *name) +static inline void __percpu *mod_percpu(struct module *mod) { - void *ptr; + return mod->percpu; +} +static int percpu_modalloc(struct module *mod, + unsigned long size, unsigned long align) +{ if (align > PAGE_SIZE) { printk(KERN_WARNING "%s: per-cpu alignment %li > %li\n", - name, align, PAGE_SIZE); + mod->name, align, PAGE_SIZE); align = PAGE_SIZE; } - ptr = __alloc_reserved_percpu(size, align); - if (!ptr) + mod->percpu = __alloc_reserved_percpu(size, align); + if (!mod->percpu) { printk(KERN_WARNING "Could not allocate %lu bytes percpu data\n", size); - return ptr; + return -ENOMEM; + } + mod->percpu_size = size; + return 0; } -static void percpu_modfree(void *freeme) +static void percpu_modfree(struct module *mod) { - free_percpu(freeme); + free_percpu(mod->percpu); } static unsigned int find_pcpusec(Elf_Ehdr *hdr, @@ -400,24 +406,28 @@ static unsigned int find_pcpusec(Elf_Ehdr *hdr, return find_sec(hdr, sechdrs, secstrings, ".data.percpu"); } -static void percpu_modcopy(void *pcpudest, const void *from, unsigned long size) +static void percpu_modcopy(struct module *mod, + const void *from, unsigned long size) { int cpu; for_each_possible_cpu(cpu) - memcpy(pcpudest + per_cpu_offset(cpu), from, size); + memcpy(per_cpu_ptr(mod->percpu, cpu), from, size); } #else /* ... !CONFIG_SMP */ -static inline void *percpu_modalloc(unsigned long size, unsigned long align, - const char *name) +static inline void __percpu *mod_percpu(struct module *mod) { return NULL; } -static inline void percpu_modfree(void *pcpuptr) +static inline int percpu_modalloc(struct module *mod, + unsigned long size, unsigned long align) +{ + return -ENOMEM; +} +static inline void percpu_modfree(struct module *mod) { - BUG(); } static inline unsigned int find_pcpusec(Elf_Ehdr *hdr, Elf_Shdr *sechdrs, @@ -425,8 +435,8 @@ static inline unsigned int find_pcpusec(Elf_Ehdr *hdr, { return 0; } -static inline void percpu_modcopy(void *pcpudst, const void *src, - unsigned long size) +static inline void percpu_modcopy(struct module *mod, + const void *from, unsigned long size) { /* pcpusec should be 0, and size of that section should be 0. */ BUG_ON(size != 0); @@ -1400,8 +1410,7 @@ static void free_module(struct module *mod) /* This may be NULL, but that's OK */ module_free(mod, mod->module_init); kfree(mod->args); - if (mod->percpu) - percpu_modfree(mod->percpu); + percpu_modfree(mod); #if defined(CONFIG_MODULE_UNLOAD) if (mod->refptr) free_percpu(mod->refptr); @@ -1520,7 +1529,7 @@ static int simplify_symbols(Elf_Shdr *sechdrs, default: /* Divert to percpu allocation if a percpu var. */ if (sym[i].st_shndx == pcpuindex) - secbase = (unsigned long)mod->percpu; + secbase = (unsigned long)mod_percpu(mod); else secbase = sechdrs[sym[i].st_shndx].sh_addr; sym[i].st_value += secbase; @@ -1954,7 +1963,7 @@ static noinline struct module *load_module(void __user *umod, unsigned int modindex, versindex, infoindex, pcpuindex; struct module *mod; long err = 0; - void *percpu = NULL, *ptr = NULL; /* Stops spurious gcc warning */ + void *ptr = NULL; /* Stops spurious gcc warning */ unsigned long symoffs, stroffs, *strmap; mm_segment_t old_fs; @@ -2094,15 +2103,11 @@ static noinline struct module *load_module(void __user *umod, if (pcpuindex) { /* We have a special allocation for this section. */ - percpu = percpu_modalloc(sechdrs[pcpuindex].sh_size, - sechdrs[pcpuindex].sh_addralign, - mod->name); - if (!percpu) { - err = -ENOMEM; + err = percpu_modalloc(mod, sechdrs[pcpuindex].sh_size, + sechdrs[pcpuindex].sh_addralign); + if (err) goto free_mod; - } sechdrs[pcpuindex].sh_flags &= ~(unsigned long)SHF_ALLOC; - mod->percpu = percpu; } /* Determine total sizes, and put offsets in sh_entsize. For now @@ -2317,7 +2322,7 @@ static noinline struct module *load_module(void __user *umod, sort_extable(mod->extable, mod->extable + mod->num_exentries); /* Finally, copy percpu area over. */ - percpu_modcopy(mod->percpu, (void *)sechdrs[pcpuindex].sh_addr, + percpu_modcopy(mod, (void *)sechdrs[pcpuindex].sh_addr, sechdrs[pcpuindex].sh_size); add_kallsyms(mod, sechdrs, hdr->e_shnum, symindex, strindex, @@ -2409,8 +2414,7 @@ static noinline struct module *load_module(void __user *umod, module_free(mod, mod->module_core); /* mod will be freed with core. Don't access it beyond this line! */ free_percpu: - if (percpu) - percpu_modfree(percpu); + percpu_modfree(mod); free_mod: kfree(args); kfree(strmap); -- cgit v1.3-8-gc7d7 From 10fad5e46f6c7bdfb01b1a012380a38e3c6ab346 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 10 Mar 2010 18:57:54 +0900 Subject: percpu, module: implement and use is_kernel/module_percpu_address() lockdep has custom code to check whether a pointer belongs to static percpu area which is somewhat broken. Implement proper is_kernel/module_percpu_address() and replace the custom code. On UP, percpu variables are regular static variables and can't be distinguished from them. Always return %false on UP. Signed-off-by: Tejun Heo Acked-by: Peter Zijlstra Cc: Rusty Russell Cc: Ingo Molnar --- include/linux/module.h | 1 + include/linux/percpu.h | 7 +++++++ kernel/lockdep.c | 21 +++++---------------- kernel/module.c | 38 ++++++++++++++++++++++++++++++++++++++ mm/percpu.c | 26 ++++++++++++++++++++++++++ 5 files changed, 77 insertions(+), 16 deletions(-) (limited to 'kernel/module.c') diff --git a/include/linux/module.h b/include/linux/module.h index 87d247ac6761..f0e2659f4e3e 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -395,6 +395,7 @@ static inline int module_is_live(struct module *mod) struct module *__module_text_address(unsigned long addr); struct module *__module_address(unsigned long addr); bool is_module_address(unsigned long addr); +bool is_module_percpu_address(unsigned long addr); bool is_module_text_address(unsigned long addr); static inline int within_module_core(unsigned long addr, struct module *mod) diff --git a/include/linux/percpu.h b/include/linux/percpu.h index a93e5bfdccb8..11d5f834b54a 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -137,6 +137,7 @@ extern int __init pcpu_page_first_chunk(size_t reserved_size, extern void __percpu *__alloc_reserved_percpu(size_t size, size_t align); extern void __percpu *__alloc_percpu(size_t size, size_t align); extern void free_percpu(void __percpu *__pdata); +extern bool is_kernel_percpu_address(unsigned long addr); extern phys_addr_t per_cpu_ptr_to_phys(void *addr); #ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA @@ -163,6 +164,12 @@ static inline void free_percpu(void __percpu *p) kfree(p); } +/* can't distinguish from other static vars, always false */ +static inline bool is_kernel_percpu_address(unsigned long addr) +{ + return false; +} + static inline phys_addr_t per_cpu_ptr_to_phys(void *addr) { return __pa(addr); diff --git a/kernel/lockdep.c b/kernel/lockdep.c index c927a549db2c..9bbb9c841e48 100644 --- a/kernel/lockdep.c +++ b/kernel/lockdep.c @@ -582,9 +582,6 @@ static int static_obj(void *obj) unsigned long start = (unsigned long) &_stext, end = (unsigned long) &_end, addr = (unsigned long) obj; -#ifdef CONFIG_SMP - int i; -#endif /* * static variable? @@ -595,24 +592,16 @@ static int static_obj(void *obj) if (arch_is_kernel_data(addr)) return 1; -#ifdef CONFIG_SMP /* - * percpu var? + * in-kernel percpu var? */ - for_each_possible_cpu(i) { - start = (unsigned long) &__per_cpu_start + per_cpu_offset(i); - end = (unsigned long) &__per_cpu_start + PERCPU_ENOUGH_ROOM - + per_cpu_offset(i); - - if ((addr >= start) && (addr < end)) - return 1; - } -#endif + if (is_kernel_percpu_address(addr)) + return 1; /* - * module var? + * module static or percpu var? */ - return is_module_address(addr); + return is_module_address(addr) || is_module_percpu_address(addr); } /* diff --git a/kernel/module.c b/kernel/module.c index e7a6e53fc73e..9f8d23d8b3a8 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -415,6 +415,40 @@ static void percpu_modcopy(struct module *mod, memcpy(per_cpu_ptr(mod->percpu, cpu), from, size); } +/** + * is_module_percpu_address - test whether address is from module static percpu + * @addr: address to test + * + * Test whether @addr belongs to module static percpu area. + * + * RETURNS: + * %true if @addr is from module static percpu area + */ +bool is_module_percpu_address(unsigned long addr) +{ + struct module *mod; + unsigned int cpu; + + preempt_disable(); + + list_for_each_entry_rcu(mod, &modules, list) { + if (!mod->percpu_size) + continue; + for_each_possible_cpu(cpu) { + void *start = per_cpu_ptr(mod->percpu, cpu); + + if ((void *)addr >= start && + (void *)addr < start + mod->percpu_size) { + preempt_enable(); + return true; + } + } + } + + preempt_enable(); + return false; +} + #else /* ... !CONFIG_SMP */ static inline void __percpu *mod_percpu(struct module *mod) @@ -441,6 +475,10 @@ static inline void percpu_modcopy(struct module *mod, /* pcpusec should be 0, and size of that section should be 0. */ BUG_ON(size != 0); } +bool is_module_percpu_address(unsigned long addr) +{ + return false; +} #endif /* CONFIG_SMP */ diff --git a/mm/percpu.c b/mm/percpu.c index 768419d44ad7..6e09741ddc62 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -1303,6 +1303,32 @@ void free_percpu(void __percpu *ptr) } EXPORT_SYMBOL_GPL(free_percpu); +/** + * is_kernel_percpu_address - test whether address is from static percpu area + * @addr: address to test + * + * Test whether @addr belongs to in-kernel static percpu area. Module + * static percpu areas are not considered. For those, use + * is_module_percpu_address(). + * + * RETURNS: + * %true if @addr is from in-kernel static percpu area, %false otherwise. + */ +bool is_kernel_percpu_address(unsigned long addr) +{ + const size_t static_size = __per_cpu_end - __per_cpu_start; + void __percpu *base = __addr_to_pcpu_ptr(pcpu_base_addr); + unsigned int cpu; + + for_each_possible_cpu(cpu) { + void *start = per_cpu_ptr(base, cpu); + + if ((void *)addr >= start && (void *)addr < start + static_size) + return true; + } + return false; +} + /** * per_cpu_ptr_to_phys - convert translated percpu address to physical address * @addr: the address to be converted to physical address -- cgit v1.3-8-gc7d7 From ae832d1e03ac9bf09fb8a07fb37908ab40c7cd0e Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Wed, 24 Mar 2010 10:57:43 +0800 Subject: tracing: Remove side effect from module tracepoints that caused a GPF Remove the @refcnt argument, because it has side-effects, and arguments with side-effects are not skipped by the jump over disabled instrumentation and are executed even when the tracepoint is disabled. This was also causing a GPF as found by Randy Dunlap: Subject: 2.6.33 GP fault only when built with tracing LKML-Reference: <4BA2B69D.3000309@oracle.com> Note, the current 2.6.34-rc has a fix for the actual cause of the GPF, but this fixes one of its triggers. Tested-by: Randy Dunlap Acked-by: Mathieu Desnoyers Signed-off-by: Li Zefan LKML-Reference: <4BA97FA7.6040406@cn.fujitsu.com> Signed-off-by: Steven Rostedt --- include/linux/module.h | 6 ++---- include/trace/events/module.h | 14 +++++++------- kernel/module.c | 3 +-- 3 files changed, 10 insertions(+), 13 deletions(-) (limited to 'kernel/module.c') diff --git a/include/linux/module.h b/include/linux/module.h index 5e869ffd34aa..393ec39b580a 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -460,8 +460,7 @@ static inline void __module_get(struct module *module) if (module) { preempt_disable(); __this_cpu_inc(module->refptr->count); - trace_module_get(module, _THIS_IP_, - __this_cpu_read(module->refptr->count)); + trace_module_get(module, _THIS_IP_); preempt_enable(); } } @@ -475,8 +474,7 @@ static inline int try_module_get(struct module *module) if (likely(module_is_live(module))) { __this_cpu_inc(module->refptr->count); - trace_module_get(module, _THIS_IP_, - __this_cpu_read(module->refptr->count)); + trace_module_get(module, _THIS_IP_); } else ret = 0; diff --git a/include/trace/events/module.h b/include/trace/events/module.h index 4b0f48ba16a6..a585f8135bd9 100644 --- a/include/trace/events/module.h +++ b/include/trace/events/module.h @@ -53,9 +53,9 @@ TRACE_EVENT(module_free, DECLARE_EVENT_CLASS(module_refcnt, - TP_PROTO(struct module *mod, unsigned long ip, int refcnt), + TP_PROTO(struct module *mod, unsigned long ip), - TP_ARGS(mod, ip, refcnt), + TP_ARGS(mod, ip), TP_STRUCT__entry( __field( unsigned long, ip ) @@ -65,7 +65,7 @@ DECLARE_EVENT_CLASS(module_refcnt, TP_fast_assign( __entry->ip = ip; - __entry->refcnt = refcnt; + __entry->refcnt = __this_cpu_read(mod->refptr->count); __assign_str(name, mod->name); ), @@ -75,16 +75,16 @@ DECLARE_EVENT_CLASS(module_refcnt, DEFINE_EVENT(module_refcnt, module_get, - TP_PROTO(struct module *mod, unsigned long ip, int refcnt), + TP_PROTO(struct module *mod, unsigned long ip), - TP_ARGS(mod, ip, refcnt) + TP_ARGS(mod, ip) ); DEFINE_EVENT(module_refcnt, module_put, - TP_PROTO(struct module *mod, unsigned long ip, int refcnt), + TP_PROTO(struct module *mod, unsigned long ip), - TP_ARGS(mod, ip, refcnt) + TP_ARGS(mod, ip) ); TRACE_EVENT(module_request, diff --git a/kernel/module.c b/kernel/module.c index c968d3606dca..21591ad921f3 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -800,8 +800,7 @@ void module_put(struct module *module) preempt_disable(); __this_cpu_dec(module->refptr->count); - trace_module_put(module, _RET_IP_, - __this_cpu_read(module->refptr->count)); + trace_module_put(module, _RET_IP_); /* Maybe they're waiting for us to drop reference? */ if (unlikely(!module_is_live(module))) wake_up_process(module->waiter); -- cgit v1.3-8-gc7d7 From eb0c53771fb2f5f66b0edb3ebce33be4bbf1c285 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 29 Mar 2010 14:25:18 -0400 Subject: tracing: Fix compile error in module tracepoints when MODULE_UNLOAD not set If modules are configured in the build but unloading of modules is not, then the refcnt is not defined. Place the get/put module tracepoints under CONFIG_MODULE_UNLOAD since it references this field in the module structure. As a side-effect, this patch also reduces the code when MODULE_UNLOAD is not set, because these unused tracepoints are not created. Signed-off-by: Steven Rostedt --- include/trace/events/module.h | 4 ++++ kernel/module.c | 5 +++-- 2 files changed, 7 insertions(+), 2 deletions(-) (limited to 'kernel/module.c') diff --git a/include/trace/events/module.h b/include/trace/events/module.h index a585f8135bd9..f07b44a2b240 100644 --- a/include/trace/events/module.h +++ b/include/trace/events/module.h @@ -51,6 +51,9 @@ TRACE_EVENT(module_free, TP_printk("%s", __get_str(name)) ); +#ifdef CONFIG_MODULE_UNLOAD +/* trace_module_get/put are only used if CONFIG_MODULE_UNLOAD is defined */ + DECLARE_EVENT_CLASS(module_refcnt, TP_PROTO(struct module *mod, unsigned long ip), @@ -86,6 +89,7 @@ DEFINE_EVENT(module_refcnt, module_put, TP_ARGS(mod, ip) ); +#endif /* CONFIG_MODULE_UNLOAD */ TRACE_EVENT(module_request, diff --git a/kernel/module.c b/kernel/module.c index 21591ad921f3..d9e237926b69 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -59,8 +59,6 @@ #define CREATE_TRACE_POINTS #include -EXPORT_TRACEPOINT_SYMBOL(module_get); - #if 0 #define DEBUGP printk #else @@ -467,6 +465,9 @@ MODINFO_ATTR(srcversion); static char last_unloaded_module[MODULE_NAME_LEN+1]; #ifdef CONFIG_MODULE_UNLOAD + +EXPORT_TRACEPOINT_SYMBOL(module_get); + /* Init the unload section of the module. */ static void module_unload_init(struct module *mod) { -- cgit v1.3-8-gc7d7 From 5fbfb18d7a5b846946d52c4a10e3aaa213ec31b6 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Thu, 1 Apr 2010 19:09:40 +1100 Subject: Fix up possibly racy module refcounting Module refcounting is implemented with a per-cpu counter for speed. However there is a race when tallying the counter where a reference may be taken by one CPU and released by another. Reference count summation may then see the decrement without having seen the previous increment, leading to lower than expected count. A module which never has its actual reference drop below 1 may return a reference count of 0 due to this race. Module removal generally runs under stop_machine, which prevents this race causing bugs due to removal of in-use modules. However there are other real bugs in module.c code and driver code (module_refcount is exported) where the callers do not run under stop_machine. Fix this by maintaining running per-cpu counters for the number of module refcount increments and the number of refcount decrements. The increments are tallied after the decrements, so any decrement seen will always have its corresponding increment counted. The final refcount is the difference of the total increments and decrements, preventing a low-refcount from being returned. Signed-off-by: Nick Piggin Acked-by: Rusty Russell Signed-off-by: Linus Torvalds --- include/linux/module.h | 14 +++++++------- kernel/module.c | 35 +++++++++++++++++++++++++++-------- 2 files changed, 34 insertions(+), 15 deletions(-) (limited to 'kernel/module.c') diff --git a/include/linux/module.h b/include/linux/module.h index 8bd399a00343..515d53ae6a79 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -368,7 +368,8 @@ struct module void (*exit)(void); struct module_ref { - int count; + unsigned int incs; + unsigned int decs; } __percpu *refptr; #endif @@ -463,9 +464,9 @@ static inline void __module_get(struct module *module) { if (module) { preempt_disable(); - __this_cpu_inc(module->refptr->count); + __this_cpu_inc(module->refptr->incs); trace_module_get(module, _THIS_IP_, - __this_cpu_read(module->refptr->count)); + __this_cpu_read(module->refptr->incs)); preempt_enable(); } } @@ -478,11 +479,10 @@ static inline int try_module_get(struct module *module) preempt_disable(); if (likely(module_is_live(module))) { - __this_cpu_inc(module->refptr->count); + __this_cpu_inc(module->refptr->incs); trace_module_get(module, _THIS_IP_, - __this_cpu_read(module->refptr->count)); - } - else + __this_cpu_read(module->refptr->incs)); + } else ret = 0; preempt_enable(); diff --git a/kernel/module.c b/kernel/module.c index 9f8d23d8b3a8..1016b75b026a 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -521,11 +521,13 @@ static void module_unload_init(struct module *mod) int cpu; INIT_LIST_HEAD(&mod->modules_which_use_me); - for_each_possible_cpu(cpu) - per_cpu_ptr(mod->refptr, cpu)->count = 0; + for_each_possible_cpu(cpu) { + per_cpu_ptr(mod->refptr, cpu)->incs = 0; + per_cpu_ptr(mod->refptr, cpu)->decs = 0; + } /* Hold reference count during initialization. */ - __this_cpu_write(mod->refptr->count, 1); + __this_cpu_write(mod->refptr->incs, 1); /* Backwards compatibility macros put refcount during init. */ mod->waiter = current; } @@ -664,12 +666,28 @@ static int try_stop_module(struct module *mod, int flags, int *forced) unsigned int module_refcount(struct module *mod) { - unsigned int total = 0; + unsigned int incs = 0, decs = 0; int cpu; for_each_possible_cpu(cpu) - total += per_cpu_ptr(mod->refptr, cpu)->count; - return total; + decs += per_cpu_ptr(mod->refptr, cpu)->decs; + /* + * ensure the incs are added up after the decs. + * module_put ensures incs are visible before decs with smp_wmb. + * + * This 2-count scheme avoids the situation where the refcount + * for CPU0 is read, then CPU0 increments the module refcount, + * then CPU1 drops that refcount, then the refcount for CPU1 is + * read. We would record a decrement but not its corresponding + * increment so we would see a low count (disaster). + * + * Rare situation? But module_refcount can be preempted, and we + * might be tallying up 4096+ CPUs. So it is not impossible. + */ + smp_rmb(); + for_each_possible_cpu(cpu) + incs += per_cpu_ptr(mod->refptr, cpu)->incs; + return incs - decs; } EXPORT_SYMBOL(module_refcount); @@ -846,10 +864,11 @@ void module_put(struct module *module) { if (module) { preempt_disable(); - __this_cpu_dec(module->refptr->count); + smp_wmb(); /* see comment in module_refcount */ + __this_cpu_inc(module->refptr->decs); trace_module_put(module, _RET_IP_, - __this_cpu_read(module->refptr->count)); + __this_cpu_read(module->refptr->decs)); /* Maybe they're waiting for us to drop reference? */ if (unlikely(!module_is_live(module))) wake_up_process(module->waiter); -- cgit v1.3-8-gc7d7 From 3fc1f1e27a5b807791d72e5d992aa33b668a6626 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 6 May 2010 18:49:20 +0200 Subject: stop_machine: reimplement using cpu_stop Reimplement stop_machine using cpu_stop. As cpu stoppers are guaranteed to be available for all online cpus, stop_machine_create/destroy() are no longer necessary and removed. With resource management and synchronization handled by cpu_stop, the new implementation is much simpler. Asking the cpu_stop to execute the stop_cpu() state machine on all online cpus with cpu hotplug disabled is enough. stop_machine itself doesn't need to manage any global resources anymore, so all per-instance information is rolled into struct stop_machine_data and the mutex and all static data variables are removed. The previous implementation created and destroyed RT workqueues as necessary which made stop_machine() calls highly expensive on very large machines. According to Dimitri Sivanich, preventing the dynamic creation/destruction makes booting faster more than twice on very large machines. cpu_stop resources are preallocated for all online cpus and should have the same effect. Signed-off-by: Tejun Heo Acked-by: Rusty Russell Acked-by: Peter Zijlstra Cc: Oleg Nesterov Cc: Dimitri Sivanich --- arch/s390/kernel/time.c | 1 - drivers/xen/manage.c | 14 +--- include/linux/stop_machine.h | 20 ------ kernel/cpu.c | 8 --- kernel/module.c | 14 +--- kernel/stop_machine.c | 158 +++++++++++-------------------------------- 6 files changed, 42 insertions(+), 173 deletions(-) (limited to 'kernel/module.c') diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index fba6dec156bf..03d96569f187 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -390,7 +390,6 @@ static void __init time_init_wq(void) if (time_sync_wq) return; time_sync_wq = create_singlethread_workqueue("timesync"); - stop_machine_create(); } /* diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c index 2ac4440e7b08..8943b8ccee1a 100644 --- a/drivers/xen/manage.c +++ b/drivers/xen/manage.c @@ -80,12 +80,6 @@ static void do_suspend(void) shutting_down = SHUTDOWN_SUSPEND; - err = stop_machine_create(); - if (err) { - printk(KERN_ERR "xen suspend: failed to setup stop_machine %d\n", err); - goto out; - } - #ifdef CONFIG_PREEMPT /* If the kernel is preemptible, we need to freeze all the processes to prevent them from being in the middle of a pagetable update @@ -93,7 +87,7 @@ static void do_suspend(void) err = freeze_processes(); if (err) { printk(KERN_ERR "xen suspend: freeze failed %d\n", err); - goto out_destroy_sm; + goto out; } #endif @@ -136,12 +130,8 @@ out_resume: out_thaw: #ifdef CONFIG_PREEMPT thaw_processes(); - -out_destroy_sm: -#endif - stop_machine_destroy(); - out: +#endif shutting_down = SHUTDOWN_INVALID; } #endif /* CONFIG_PM_SLEEP */ diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h index efcbd6c37947..0e552e72a4c4 100644 --- a/include/linux/stop_machine.h +++ b/include/linux/stop_machine.h @@ -67,23 +67,6 @@ int stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus); */ int __stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus); -/** - * stop_machine_create: create all stop_machine threads - * - * Description: This causes all stop_machine threads to be created before - * stop_machine actually gets called. This can be used by subsystems that - * need a non failing stop_machine infrastructure. - */ -int stop_machine_create(void); - -/** - * stop_machine_destroy: destroy all stop_machine threads - * - * Description: This causes all stop_machine threads which were created with - * stop_machine_create to be destroyed again. - */ -void stop_machine_destroy(void); - #else static inline int stop_machine(int (*fn)(void *), void *data, @@ -96,8 +79,5 @@ static inline int stop_machine(int (*fn)(void *), void *data, return ret; } -static inline int stop_machine_create(void) { return 0; } -static inline void stop_machine_destroy(void) { } - #endif /* CONFIG_SMP */ #endif /* _LINUX_STOP_MACHINE */ diff --git a/kernel/cpu.c b/kernel/cpu.c index 914aedcde849..545777574779 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -266,9 +266,6 @@ int __ref cpu_down(unsigned int cpu) { int err; - err = stop_machine_create(); - if (err) - return err; cpu_maps_update_begin(); if (cpu_hotplug_disabled) { @@ -280,7 +277,6 @@ int __ref cpu_down(unsigned int cpu) out: cpu_maps_update_done(); - stop_machine_destroy(); return err; } EXPORT_SYMBOL(cpu_down); @@ -361,9 +357,6 @@ int disable_nonboot_cpus(void) { int cpu, first_cpu, error; - error = stop_machine_create(); - if (error) - return error; cpu_maps_update_begin(); first_cpu = cpumask_first(cpu_online_mask); /* @@ -394,7 +387,6 @@ int disable_nonboot_cpus(void) printk(KERN_ERR "Non-boot CPUs are not disabled\n"); } cpu_maps_update_done(); - stop_machine_destroy(); return error; } diff --git a/kernel/module.c b/kernel/module.c index 1016b75b026a..0838246d8c94 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -723,16 +723,8 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user, return -EFAULT; name[MODULE_NAME_LEN-1] = '\0'; - /* Create stop_machine threads since free_module relies on - * a non-failing stop_machine call. */ - ret = stop_machine_create(); - if (ret) - return ret; - - if (mutex_lock_interruptible(&module_mutex) != 0) { - ret = -EINTR; - goto out_stop; - } + if (mutex_lock_interruptible(&module_mutex) != 0) + return -EINTR; mod = find_module(name); if (!mod) { @@ -792,8 +784,6 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user, out: mutex_unlock(&module_mutex); -out_stop: - stop_machine_destroy(); return ret; } diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index 7e3f9182aef3..884c7a1afeed 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -388,174 +388,92 @@ enum stopmachine_state { /* Exit */ STOPMACHINE_EXIT, }; -static enum stopmachine_state state; struct stop_machine_data { - int (*fn)(void *); - void *data; - int fnret; + int (*fn)(void *); + void *data; + /* Like num_online_cpus(), but hotplug cpu uses us, so we need this. */ + unsigned int num_threads; + const struct cpumask *active_cpus; + + enum stopmachine_state state; + atomic_t thread_ack; }; -/* Like num_online_cpus(), but hotplug cpu uses us, so we need this. */ -static unsigned int num_threads; -static atomic_t thread_ack; -static DEFINE_MUTEX(lock); -/* setup_lock protects refcount, stop_machine_wq and stop_machine_work. */ -static DEFINE_MUTEX(setup_lock); -/* Users of stop_machine. */ -static int refcount; -static struct workqueue_struct *stop_machine_wq; -static struct stop_machine_data active, idle; -static const struct cpumask *active_cpus; -static void __percpu *stop_machine_work; - -static void set_state(enum stopmachine_state newstate) +static void set_state(struct stop_machine_data *smdata, + enum stopmachine_state newstate) { /* Reset ack counter. */ - atomic_set(&thread_ack, num_threads); + atomic_set(&smdata->thread_ack, smdata->num_threads); smp_wmb(); - state = newstate; + smdata->state = newstate; } /* Last one to ack a state moves to the next state. */ -static void ack_state(void) +static void ack_state(struct stop_machine_data *smdata) { - if (atomic_dec_and_test(&thread_ack)) - set_state(state + 1); + if (atomic_dec_and_test(&smdata->thread_ack)) + set_state(smdata, smdata->state + 1); } -/* This is the actual function which stops the CPU. It runs - * in the context of a dedicated stopmachine workqueue. */ -static void stop_cpu(struct work_struct *unused) +/* This is the cpu_stop function which stops the CPU. */ +static int stop_machine_cpu_stop(void *data) { + struct stop_machine_data *smdata = data; enum stopmachine_state curstate = STOPMACHINE_NONE; - struct stop_machine_data *smdata = &idle; - int cpu = smp_processor_id(); - int err; + int cpu = smp_processor_id(), err = 0; + bool is_active; + + if (!smdata->active_cpus) + is_active = cpu == cpumask_first(cpu_online_mask); + else + is_active = cpumask_test_cpu(cpu, smdata->active_cpus); - if (!active_cpus) { - if (cpu == cpumask_first(cpu_online_mask)) - smdata = &active; - } else { - if (cpumask_test_cpu(cpu, active_cpus)) - smdata = &active; - } /* Simple state machine */ do { /* Chill out and ensure we re-read stopmachine_state. */ cpu_relax(); - if (state != curstate) { - curstate = state; + if (smdata->state != curstate) { + curstate = smdata->state; switch (curstate) { case STOPMACHINE_DISABLE_IRQ: local_irq_disable(); hard_irq_disable(); break; case STOPMACHINE_RUN: - /* On multiple CPUs only a single error code - * is needed to tell that something failed. */ - err = smdata->fn(smdata->data); - if (err) - smdata->fnret = err; + if (is_active) + err = smdata->fn(smdata->data); break; default: break; } - ack_state(); + ack_state(smdata); } } while (curstate != STOPMACHINE_EXIT); local_irq_enable(); + return err; } -/* Callback for CPUs which aren't supposed to do anything. */ -static int chill(void *unused) -{ - return 0; -} - -int stop_machine_create(void) -{ - mutex_lock(&setup_lock); - if (refcount) - goto done; - stop_machine_wq = create_rt_workqueue("kstop"); - if (!stop_machine_wq) - goto err_out; - stop_machine_work = alloc_percpu(struct work_struct); - if (!stop_machine_work) - goto err_out; -done: - refcount++; - mutex_unlock(&setup_lock); - return 0; - -err_out: - if (stop_machine_wq) - destroy_workqueue(stop_machine_wq); - mutex_unlock(&setup_lock); - return -ENOMEM; -} -EXPORT_SYMBOL_GPL(stop_machine_create); - -void stop_machine_destroy(void) -{ - mutex_lock(&setup_lock); - refcount--; - if (refcount) - goto done; - destroy_workqueue(stop_machine_wq); - free_percpu(stop_machine_work); -done: - mutex_unlock(&setup_lock); -} -EXPORT_SYMBOL_GPL(stop_machine_destroy); - int __stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus) { - struct work_struct *sm_work; - int i, ret; - - /* Set up initial state. */ - mutex_lock(&lock); - num_threads = num_online_cpus(); - active_cpus = cpus; - active.fn = fn; - active.data = data; - active.fnret = 0; - idle.fn = chill; - idle.data = NULL; - - set_state(STOPMACHINE_PREPARE); - - /* Schedule the stop_cpu work on all cpus: hold this CPU so one - * doesn't hit this CPU until we're ready. */ - get_cpu(); - for_each_online_cpu(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); - } - /* This will release the thread on our CPU. */ - put_cpu(); - flush_workqueue(stop_machine_wq); - ret = active.fnret; - mutex_unlock(&lock); - return ret; + struct stop_machine_data smdata = { .fn = fn, .data = data, + .num_threads = num_online_cpus(), + .active_cpus = cpus }; + + /* Set the initial state and stop all online cpus. */ + set_state(&smdata, STOPMACHINE_PREPARE); + return stop_cpus(cpu_online_mask, stop_machine_cpu_stop, &smdata); } int stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus) { int ret; - ret = stop_machine_create(); - if (ret) - return ret; /* No CPUs can come up or down during this. */ get_online_cpus(); ret = __stop_machine(fn, data, cpus); put_online_cpus(); - stop_machine_destroy(); return ret; } EXPORT_SYMBOL_GPL(stop_machine); -- cgit v1.3-8-gc7d7 From 480b02df3aa9f07d1c7df0cd8be7a5ca73893455 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Wed, 19 May 2010 17:33:39 -0600 Subject: module: drop the lock while waiting for module to complete initialization. This fixes "gave up waiting for init of module libcrc32c." which happened at boot time due to multiple parallel module loads. The problem was a deadlock: we wait for a module to finish initializing, but we keep the module_lock mutex so it can't complete. In particular, this could reasonably happen if a module does a request_module() in its initialization routine. So we change use_module() to return an errno rather than a bool, and if it's -EBUSY we drop the lock and wait in the caller, then reaquire the lock. Reported-by: Brandon Philips Signed-off-by: Rusty Russell Tested-by: Brandon Philips --- kernel/module.c | 59 ++++++++++++++++++++++++++++++++++++--------------------- 1 file changed, 37 insertions(+), 22 deletions(-) (limited to 'kernel/module.c') diff --git a/kernel/module.c b/kernel/module.c index e2564580f3f1..970d773aec62 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -561,33 +561,26 @@ int use_module(struct module *a, struct module *b) struct module_use *use; int no_warn, err; - if (b == NULL || already_uses(a, b)) return 1; - - /* If we're interrupted or time out, we fail. */ - if (wait_event_interruptible_timeout( - module_wq, (err = strong_try_module_get(b)) != -EBUSY, - 30 * HZ) <= 0) { - printk("%s: gave up waiting for init of module %s.\n", - a->name, b->name); + if (b == NULL || already_uses(a, b)) return 0; - } - /* If strong_try_module_get() returned a different error, we fail. */ + /* If we're interrupted or time out, we fail. */ + err = strong_try_module_get(b); if (err) - return 0; + return err; DEBUGP("Allocating new usage for %s.\n", a->name); use = kmalloc(sizeof(*use), GFP_ATOMIC); if (!use) { printk("%s: out of memory loading\n", a->name); module_put(b); - return 0; + return -ENOMEM; } use->module_which_uses = a; list_add(&use->list, &b->modules_which_use_me); no_warn = sysfs_create_link(b->holders_dir, &a->mkobj.kobj, a->name); - return 1; + return 0; } EXPORT_SYMBOL_GPL(use_module); @@ -880,7 +873,7 @@ static inline void module_unload_free(struct module *mod) int use_module(struct module *a, struct module *b) { - return strong_try_module_get(b) == 0; + return strong_try_module_get(b); } EXPORT_SYMBOL_GPL(use_module); @@ -1051,17 +1044,39 @@ static const struct kernel_symbol *resolve_symbol(Elf_Shdr *sechdrs, struct module *owner; const struct kernel_symbol *sym; const unsigned long *crc; + DEFINE_WAIT(wait); + int err; + long timeleft = 30 * HZ; +again: sym = find_symbol(name, &owner, &crc, !(mod->taints & (1 << TAINT_PROPRIETARY_MODULE)), true); - /* use_module can fail due to OOM, - or module initialization or unloading */ - if (sym) { - if (!check_version(sechdrs, versindex, name, mod, crc, owner) - || !use_module(mod, owner)) - sym = NULL; - } - return sym; + if (!sym) + return NULL; + + if (!check_version(sechdrs, versindex, name, mod, crc, owner)) + return NULL; + + prepare_to_wait(&module_wq, &wait, TASK_INTERRUPTIBLE); + err = use_module(mod, owner); + if (likely(!err) || err != -EBUSY || signal_pending(current)) { + finish_wait(&module_wq, &wait); + return err ? NULL : sym; + } + + /* Module is still loading. Drop lock and wait. */ + mutex_unlock(&module_mutex); + timeleft = schedule_timeout(timeleft); + mutex_lock(&module_mutex); + finish_wait(&module_wq, &wait); + + /* Module might be gone entirely, or replaced. Re-lookup. */ + if (timeleft) + goto again; + + printk(KERN_WARNING "%s: gave up waiting for init of module %s.\n", + mod->name, owner->name); + return NULL; } /* -- cgit v1.3-8-gc7d7 From 67fc4e0cb931d6b4ccf21248e4199b154478ecea Mon Sep 17 00:00:00 2001 From: Jason Wessel Date: Thu, 20 May 2010 21:04:21 -0500 Subject: kdb: core for kgdb back end (2 of 2) This patch contains the hooks and instrumentation into kernel which live outside the kernel/debug directory, which the kdb core will call to run commands like lsmod, dmesg, bt etc... CC: linux-arch@vger.kernel.org Signed-off-by: Jason Wessel Signed-off-by: Martin Hicks --- arch/arm/include/asm/kmap_types.h | 1 + arch/powerpc/include/asm/kmap_types.h | 1 + include/asm-generic/kmap_types.h | 3 ++- init/main.c | 2 ++ kernel/kallsyms.c | 21 ++++++++++++++++++ kernel/module.c | 4 ++++ kernel/printk.c | 16 ++++++++++++++ kernel/sched.c | 7 ++++-- kernel/signal.c | 40 +++++++++++++++++++++++++++++++++++ 9 files changed, 92 insertions(+), 3 deletions(-) (limited to 'kernel/module.c') diff --git a/arch/arm/include/asm/kmap_types.h b/arch/arm/include/asm/kmap_types.h index c4b2ea3fbe42..e51b1e81df05 100644 --- a/arch/arm/include/asm/kmap_types.h +++ b/arch/arm/include/asm/kmap_types.h @@ -20,6 +20,7 @@ enum km_type { KM_SOFTIRQ1, KM_L1_CACHE, KM_L2_CACHE, + KM_KDB, KM_TYPE_NR }; diff --git a/arch/powerpc/include/asm/kmap_types.h b/arch/powerpc/include/asm/kmap_types.h index 916369575c97..bca8fdcd2542 100644 --- a/arch/powerpc/include/asm/kmap_types.h +++ b/arch/powerpc/include/asm/kmap_types.h @@ -26,6 +26,7 @@ enum km_type { KM_SOFTIRQ1, KM_PPC_SYNC_PAGE, KM_PPC_SYNC_ICACHE, + KM_KDB, KM_TYPE_NR }; diff --git a/include/asm-generic/kmap_types.h b/include/asm-generic/kmap_types.h index e5f234a08540..97e807c8c812 100644 --- a/include/asm-generic/kmap_types.h +++ b/include/asm-generic/kmap_types.h @@ -28,7 +28,8 @@ KMAP_D(15) KM_UML_USERCOPY, KMAP_D(16) KM_IRQ_PTE, KMAP_D(17) KM_NMI, KMAP_D(18) KM_NMI_PTE, -KMAP_D(19) KM_TYPE_NR +KMAP_D(19) KM_KDB, +KMAP_D(20) KM_TYPE_NR }; #undef KMAP_D diff --git a/init/main.c b/init/main.c index 5c8540271529..372771333d98 100644 --- a/init/main.c +++ b/init/main.c @@ -62,6 +62,7 @@ #include #include #include +#include #include #include #include @@ -675,6 +676,7 @@ asmlinkage void __init start_kernel(void) buffer_init(); key_init(); security_init(); + kdb_init(KDB_INIT_FULL); vfs_caches_init(totalram_pages); signals_init(); /* rootfs populating might need page-writeback */ diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c index 13aff293f4de..6f6d091b5757 100644 --- a/kernel/kallsyms.c +++ b/kernel/kallsyms.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include #include /* for cond_resched */ @@ -516,6 +517,26 @@ static int kallsyms_open(struct inode *inode, struct file *file) return ret; } +#ifdef CONFIG_KGDB_KDB +const char *kdb_walk_kallsyms(loff_t *pos) +{ + static struct kallsym_iter kdb_walk_kallsyms_iter; + if (*pos == 0) { + memset(&kdb_walk_kallsyms_iter, 0, + sizeof(kdb_walk_kallsyms_iter)); + reset_iter(&kdb_walk_kallsyms_iter, 0); + } + while (1) { + if (!update_iter(&kdb_walk_kallsyms_iter, *pos)) + return NULL; + ++*pos; + /* Some debugging symbols have no name. Ignore them. */ + if (kdb_walk_kallsyms_iter.name[0]) + return kdb_walk_kallsyms_iter.name; + } +} +#endif /* CONFIG_KGDB_KDB */ + static const struct file_operations kallsyms_operations = { .open = kallsyms_open, .read = seq_read, diff --git a/kernel/module.c b/kernel/module.c index e2564580f3f1..b751f1902476 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -77,6 +77,10 @@ DEFINE_MUTEX(module_mutex); EXPORT_SYMBOL_GPL(module_mutex); static LIST_HEAD(modules); +#ifdef CONFIG_KGDB_KDB +struct list_head *kdb_modules = &modules; /* kdb needs the list of modules */ +#endif /* CONFIG_KGDB_KDB */ + /* Block module loading/unloading? */ int modules_disabled = 0; diff --git a/kernel/printk.c b/kernel/printk.c index 75077ad0b537..9213b8b5bb4f 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -413,6 +413,22 @@ SYSCALL_DEFINE3(syslog, int, type, char __user *, buf, int, len) return do_syslog(type, buf, len, SYSLOG_FROM_CALL); } +#ifdef CONFIG_KGDB_KDB +/* kdb dmesg command needs access to the syslog buffer. do_syslog() + * uses locks so it cannot be used during debugging. Just tell kdb + * where the start and end of the physical and logical logs are. This + * is equivalent to do_syslog(3). + */ +void kdb_syslog_data(char *syslog_data[4]) +{ + syslog_data[0] = log_buf; + syslog_data[1] = log_buf + log_buf_len; + syslog_data[2] = log_buf + log_end - + (logged_chars < log_buf_len ? logged_chars : log_buf_len); + syslog_data[3] = log_buf + log_end; +} +#endif /* CONFIG_KGDB_KDB */ + /* * Call the console drivers on a range of log_buf */ diff --git a/kernel/sched.c b/kernel/sched.c index 1d93cd0ae4d3..a25c1324af54 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -7758,9 +7758,9 @@ void normalize_rt_tasks(void) #endif /* CONFIG_MAGIC_SYSRQ */ -#ifdef CONFIG_IA64 +#if defined(CONFIG_IA64) || defined(CONFIG_KGDB_KDB) /* - * These functions are only useful for the IA64 MCA handling. + * These functions are only useful for the IA64 MCA handling, or kdb. * * They can only be called when the whole system has been * stopped - every CPU needs to be quiescent, and no scheduling @@ -7780,6 +7780,9 @@ struct task_struct *curr_task(int cpu) return cpu_curr(cpu); } +#endif /* defined(CONFIG_IA64) || defined(CONFIG_KGDB_KDB) */ + +#ifdef CONFIG_IA64 /** * set_curr_task - set the current task for a given cpu. * @cpu: the processor in question. diff --git a/kernel/signal.c b/kernel/signal.c index dbd7fe073c55..825a3f24ad76 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2735,3 +2735,43 @@ void __init signals_init(void) { sigqueue_cachep = KMEM_CACHE(sigqueue, SLAB_PANIC); } + +#ifdef CONFIG_KGDB_KDB +#include +/* + * kdb_send_sig_info - Allows kdb to send signals without exposing + * signal internals. This function checks if the required locks are + * available before calling the main signal code, to avoid kdb + * deadlocks. + */ +void +kdb_send_sig_info(struct task_struct *t, struct siginfo *info) +{ + static struct task_struct *kdb_prev_t; + int sig, new_t; + if (!spin_trylock(&t->sighand->siglock)) { + kdb_printf("Can't do kill command now.\n" + "The sigmask lock is held somewhere else in " + "kernel, try again later\n"); + return; + } + spin_unlock(&t->sighand->siglock); + new_t = kdb_prev_t != t; + kdb_prev_t = t; + if (t->state != TASK_RUNNING && new_t) { + kdb_printf("Process is not RUNNING, sending a signal from " + "kdb risks deadlock\n" + "on the run queue locks. " + "The signal has _not_ been sent.\n" + "Reissue the kill command if you want to risk " + "the deadlock.\n"); + return; + } + sig = info->si_signo; + if (send_sig_info(sig, info, t)) + kdb_printf("Fail to deliver Signal %d to process %d.\n", + sig, t->pid); + else + kdb_printf("Signal %d is sent to process %d.\n", sig, t->pid); +} +#endif /* CONFIG_KGDB_KDB */ -- cgit v1.3-8-gc7d7 From 2c3c8bea608866d8bd9dcf92657d57fdcac011c5 Mon Sep 17 00:00:00 2001 From: Chris Wright Date: Wed, 12 May 2010 18:28:57 -0700 Subject: sysfs: add struct file* to bin_attr callbacks This allows bin_attr->read,write,mmap callbacks to check file specific data (such as inode owner) as part of any privilege validation. Signed-off-by: Chris Wright Signed-off-by: Greg Kroah-Hartman --- arch/alpha/kernel/pci-sysfs.c | 8 ++++--- arch/mips/txx9/generic/setup.c | 4 ++-- arch/powerpc/sysdev/mv64x60_pci.c | 4 ++-- arch/s390/kernel/ipl.c | 14 ++++++------ drivers/acpi/system.c | 2 +- drivers/base/firmware_class.c | 11 ++++++---- drivers/firmware/dcdbas.c | 4 ++-- drivers/firmware/dell_rbu.c | 10 ++++----- drivers/firmware/efivars.c | 4 ++-- drivers/gpu/drm/drm_sysfs.c | 5 +++-- drivers/misc/c2port/core.c | 4 ++-- drivers/misc/ds1682.c | 6 ++++-- drivers/misc/eeprom/at24.c | 6 ++++-- drivers/misc/eeprom/at25.c | 6 ++++-- drivers/misc/eeprom/eeprom.c | 3 ++- drivers/misc/eeprom/max6875.c | 2 +- drivers/net/netxen/netxen_nic_main.c | 11 ++++++---- drivers/net/qlcnic/qlcnic_main.c | 12 +++++++---- drivers/pci/hotplug/acpiphp_ibm.c | 5 +++-- drivers/pci/pci-sysfs.c | 42 +++++++++++++++++++++++++----------- drivers/pcmcia/cistpl.c | 4 ++-- drivers/power/olpc_battery.c | 2 +- drivers/rapidio/rio-sysfs.c | 6 ++++-- drivers/rtc/rtc-cmos.c | 6 ++++-- drivers/rtc/rtc-ds1305.c | 6 ++++-- drivers/rtc/rtc-ds1307.c | 6 ++++-- drivers/rtc/rtc-ds1511.c | 10 +++++---- drivers/rtc/rtc-ds1553.c | 4 ++-- drivers/rtc/rtc-ds1742.c | 4 ++-- drivers/rtc/rtc-m48t59.c | 4 ++-- drivers/rtc/rtc-stk17ta8.c | 4 ++-- drivers/rtc/rtc-tx4939.c | 4 ++-- drivers/s390/cio/chp.c | 5 +++-- drivers/scsi/3w-sas.c | 4 ++-- drivers/scsi/arcmsr/arcmsr_attr.c | 9 +++++--- drivers/scsi/ibmvscsi/ibmvfc.c | 3 ++- drivers/scsi/ipr.c | 9 +++++--- drivers/scsi/lpfc/lpfc_attr.c | 20 ++++++++++++----- drivers/scsi/qla2xxx/qla_attr.c | 32 +++++++++++++-------------- drivers/staging/udlfb/udlfb.c | 3 ++- drivers/usb/core/sysfs.c | 3 ++- drivers/video/aty/radeon_base.c | 4 ++-- drivers/w1/slaves/w1_ds2431.c | 4 ++-- drivers/w1/slaves/w1_ds2433.c | 4 ++-- drivers/w1/slaves/w1_ds2760.c | 2 +- drivers/w1/w1.c | 4 ++-- drivers/zorro/zorro-sysfs.c | 2 +- fs/sysfs/bin.c | 24 ++++++++++----------- include/linux/sysfs.h | 7 +++--- kernel/ksysfs.c | 3 ++- kernel/module.c | 2 +- net/bridge/br_sysfs_br.c | 2 +- 52 files changed, 220 insertions(+), 149 deletions(-) (limited to 'kernel/module.c') diff --git a/arch/alpha/kernel/pci-sysfs.c b/arch/alpha/kernel/pci-sysfs.c index d979e7c7bc4b..a5fffc882c72 100644 --- a/arch/alpha/kernel/pci-sysfs.c +++ b/arch/alpha/kernel/pci-sysfs.c @@ -53,6 +53,7 @@ static int __pci_mmap_fits(struct pci_dev *pdev, int num, /** * pci_mmap_resource - map a PCI resource into user memory space + * @filp: open sysfs file * @kobj: kobject for mapping * @attr: struct bin_attribute for the file being mapped * @vma: struct vm_area_struct passed into the mmap @@ -60,7 +61,8 @@ static int __pci_mmap_fits(struct pci_dev *pdev, int num, * * Use the bus mapping routines to map a PCI resource into userspace. */ -static int pci_mmap_resource(struct kobject *kobj, struct bin_attribute *attr, +static int pci_mmap_resource(struct file *filp, struct kobject *kobj, + struct bin_attribute *attr, struct vm_area_struct *vma, int sparse) { struct pci_dev *pdev = to_pci_dev(container_of(kobj, @@ -89,14 +91,14 @@ static int pci_mmap_resource(struct kobject *kobj, struct bin_attribute *attr, return hose_mmap_page_range(pdev->sysdata, vma, mmap_type, sparse); } -static int pci_mmap_resource_sparse(struct kobject *kobj, +static int pci_mmap_resource_sparse(struct file *filp, struct kobject *kobj, struct bin_attribute *attr, struct vm_area_struct *vma) { return pci_mmap_resource(kobj, attr, vma, 1); } -static int pci_mmap_resource_dense(struct kobject *kobj, +static int pci_mmap_resource_dense(struct file *filp, struct kobject *kobj, struct bin_attribute *attr, struct vm_area_struct *vma) { diff --git a/arch/mips/txx9/generic/setup.c b/arch/mips/txx9/generic/setup.c index adc69291f9e2..575d219b8001 100644 --- a/arch/mips/txx9/generic/setup.c +++ b/arch/mips/txx9/generic/setup.c @@ -905,7 +905,7 @@ struct txx9_sramc_sysdev { void __iomem *base; }; -static ssize_t txx9_sram_read(struct kobject *kobj, +static ssize_t txx9_sram_read(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t pos, size_t size) { @@ -920,7 +920,7 @@ static ssize_t txx9_sram_read(struct kobject *kobj, return size; } -static ssize_t txx9_sram_write(struct kobject *kobj, +static ssize_t txx9_sram_write(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t pos, size_t size) { diff --git a/arch/powerpc/sysdev/mv64x60_pci.c b/arch/powerpc/sysdev/mv64x60_pci.c index 1456015a22d8..198f288570cc 100644 --- a/arch/powerpc/sysdev/mv64x60_pci.c +++ b/arch/powerpc/sysdev/mv64x60_pci.c @@ -24,7 +24,7 @@ #define MV64X60_VAL_LEN_MAX 11 #define MV64X60_PCICFG_CPCI_HOTSWAP 0x68 -static ssize_t mv64x60_hs_reg_read(struct kobject *kobj, +static ssize_t mv64x60_hs_reg_read(struct file *filp, struct kobject *kobj, struct bin_attribute *attr, char *buf, loff_t off, size_t count) { @@ -45,7 +45,7 @@ static ssize_t mv64x60_hs_reg_read(struct kobject *kobj, return sprintf(buf, "0x%08x\n", v); } -static ssize_t mv64x60_hs_reg_write(struct kobject *kobj, +static ssize_t mv64x60_hs_reg_write(struct file *filp, struct kobject *kobj, struct bin_attribute *attr, char *buf, loff_t off, size_t count) { diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index 72c8b0d070c8..a689070be287 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -403,8 +403,9 @@ static ssize_t sys_ipl_device_show(struct kobject *kobj, static struct kobj_attribute sys_ipl_device_attr = __ATTR(device, S_IRUGO, sys_ipl_device_show, NULL); -static ssize_t ipl_parameter_read(struct kobject *kobj, struct bin_attribute *attr, - char *buf, loff_t off, size_t count) +static ssize_t ipl_parameter_read(struct file *filp, struct kobject *kobj, + struct bin_attribute *attr, char *buf, + loff_t off, size_t count) { return memory_read_from_buffer(buf, count, &off, IPL_PARMBLOCK_START, IPL_PARMBLOCK_SIZE); @@ -419,8 +420,9 @@ static struct bin_attribute ipl_parameter_attr = { .read = &ipl_parameter_read, }; -static ssize_t ipl_scp_data_read(struct kobject *kobj, struct bin_attribute *attr, - char *buf, loff_t off, size_t count) +static ssize_t ipl_scp_data_read(struct file *filp, struct kobject *kobj, + struct bin_attribute *attr, char *buf, + loff_t off, size_t count) { unsigned int size = IPL_PARMBLOCK_START->ipl_info.fcp.scp_data_len; void *scp_data = &IPL_PARMBLOCK_START->ipl_info.fcp.scp_data; @@ -694,7 +696,7 @@ static struct kobj_attribute sys_reipl_ccw_vmparm_attr = /* FCP reipl device attributes */ -static ssize_t reipl_fcp_scpdata_read(struct kobject *kobj, +static ssize_t reipl_fcp_scpdata_read(struct file *filp, struct kobject *kobj, struct bin_attribute *attr, char *buf, loff_t off, size_t count) { @@ -704,7 +706,7 @@ static ssize_t reipl_fcp_scpdata_read(struct kobject *kobj, return memory_read_from_buffer(buf, count, &off, scp_data, size); } -static ssize_t reipl_fcp_scpdata_write(struct kobject *kobj, +static ssize_t reipl_fcp_scpdata_write(struct file *filp, struct kobject *kobj, struct bin_attribute *attr, char *buf, loff_t off, size_t count) { diff --git a/drivers/acpi/system.c b/drivers/acpi/system.c index e35525b39f6b..c79e789ed03a 100644 --- a/drivers/acpi/system.c +++ b/drivers/acpi/system.c @@ -71,7 +71,7 @@ struct acpi_table_attr { struct list_head node; }; -static ssize_t acpi_table_show(struct kobject *kobj, +static ssize_t acpi_table_show(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t offset, size_t count) { diff --git a/drivers/base/firmware_class.c b/drivers/base/firmware_class.c index d98e424675cf..3f093b0dd217 100644 --- a/drivers/base/firmware_class.c +++ b/drivers/base/firmware_class.c @@ -278,8 +278,9 @@ static ssize_t firmware_loading_store(struct device *dev, static DEVICE_ATTR(loading, 0644, firmware_loading_show, firmware_loading_store); static ssize_t -firmware_data_read(struct kobject *kobj, struct bin_attribute *bin_attr, - char *buffer, loff_t offset, size_t count) +firmware_data_read(struct file *filp, struct kobject *kobj, + struct bin_attribute *bin_attr, char *buffer, loff_t offset, + size_t count) { struct device *dev = to_dev(kobj); struct firmware_priv *fw_priv = dev_get_drvdata(dev); @@ -362,6 +363,7 @@ fw_realloc_buffer(struct firmware_priv *fw_priv, int min_size) /** * firmware_data_write - write method for firmware + * @filp: open sysfs file * @kobj: kobject for the device * @bin_attr: bin_attr structure * @buffer: buffer being written @@ -372,8 +374,9 @@ fw_realloc_buffer(struct firmware_priv *fw_priv, int min_size) * the driver as a firmware image. **/ static ssize_t -firmware_data_write(struct kobject *kobj, struct bin_attribute *bin_attr, - char *buffer, loff_t offset, size_t count) +firmware_data_write(struct file* filp, struct kobject *kobj, + struct bin_attribute *bin_attr, char *buffer, + loff_t offset, size_t count) { struct device *dev = to_dev(kobj); struct firmware_priv *fw_priv = dev_get_drvdata(dev); diff --git a/drivers/firmware/dcdbas.c b/drivers/firmware/dcdbas.c index fb09bb3c0ad6..aa9bc9e980e1 100644 --- a/drivers/firmware/dcdbas.c +++ b/drivers/firmware/dcdbas.c @@ -149,7 +149,7 @@ static ssize_t smi_data_buf_size_store(struct device *dev, return count; } -static ssize_t smi_data_read(struct kobject *kobj, +static ssize_t smi_data_read(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t pos, size_t count) { @@ -162,7 +162,7 @@ static ssize_t smi_data_read(struct kobject *kobj, return ret; } -static ssize_t smi_data_write(struct kobject *kobj, +static ssize_t smi_data_write(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t pos, size_t count) { diff --git a/drivers/firmware/dell_rbu.c b/drivers/firmware/dell_rbu.c index 3a4460265b10..2f452f1f7c8a 100644 --- a/drivers/firmware/dell_rbu.c +++ b/drivers/firmware/dell_rbu.c @@ -522,7 +522,7 @@ static ssize_t read_rbu_mono_data(char *buffer, loff_t pos, size_t count) rbu_data.image_update_buffer, rbu_data.bios_image_size); } -static ssize_t read_rbu_data(struct kobject *kobj, +static ssize_t read_rbu_data(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buffer, loff_t pos, size_t count) { @@ -576,7 +576,7 @@ static void callbackfn_rbu(const struct firmware *fw, void *context) release_firmware(fw); } -static ssize_t read_rbu_image_type(struct kobject *kobj, +static ssize_t read_rbu_image_type(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buffer, loff_t pos, size_t count) { @@ -586,7 +586,7 @@ static ssize_t read_rbu_image_type(struct kobject *kobj, return size; } -static ssize_t write_rbu_image_type(struct kobject *kobj, +static ssize_t write_rbu_image_type(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buffer, loff_t pos, size_t count) { @@ -647,7 +647,7 @@ static ssize_t write_rbu_image_type(struct kobject *kobj, return rc; } -static ssize_t read_rbu_packet_size(struct kobject *kobj, +static ssize_t read_rbu_packet_size(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buffer, loff_t pos, size_t count) { @@ -660,7 +660,7 @@ static ssize_t read_rbu_packet_size(struct kobject *kobj, return size; } -static ssize_t write_rbu_packet_size(struct kobject *kobj, +static ssize_t write_rbu_packet_size(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buffer, loff_t pos, size_t count) { diff --git a/drivers/firmware/efivars.c b/drivers/firmware/efivars.c index 81b70bd07586..2a62ec6390e0 100644 --- a/drivers/firmware/efivars.c +++ b/drivers/firmware/efivars.c @@ -402,7 +402,7 @@ efivar_unregister(struct efivar_entry *var) } -static ssize_t efivar_create(struct kobject *kobj, +static ssize_t efivar_create(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t pos, size_t count) { @@ -461,7 +461,7 @@ static ssize_t efivar_create(struct kobject *kobj, return count; } -static ssize_t efivar_delete(struct kobject *kobj, +static ssize_t efivar_delete(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t pos, size_t count) { diff --git a/drivers/gpu/drm/drm_sysfs.c b/drivers/gpu/drm/drm_sysfs.c index 25bbd30ed7af..387166d5a109 100644 --- a/drivers/gpu/drm/drm_sysfs.c +++ b/drivers/gpu/drm/drm_sysfs.c @@ -193,8 +193,9 @@ static ssize_t enabled_show(struct device *device, "disabled"); } -static ssize_t edid_show(struct kobject *kobj, struct bin_attribute *attr, - char *buf, loff_t off, size_t count) +static ssize_t edid_show(struct file *filp, struct kobject *kobj, + struct bin_attribute *attr, char *buf, loff_t off, + size_t count) { struct device *connector_dev = container_of(kobj, struct device, kobj); struct drm_connector *connector = to_drm_connector(connector_dev); diff --git a/drivers/misc/c2port/core.c b/drivers/misc/c2port/core.c index ed090e77c9cd..19fc7c1cb428 100644 --- a/drivers/misc/c2port/core.c +++ b/drivers/misc/c2port/core.c @@ -707,7 +707,7 @@ static ssize_t __c2port_read_flash_data(struct c2port_device *dev, return nread; } -static ssize_t c2port_read_flash_data(struct kobject *kobj, +static ssize_t c2port_read_flash_data(struct file *filp, struct kobject *kobj, struct bin_attribute *attr, char *buffer, loff_t offset, size_t count) { @@ -824,7 +824,7 @@ static ssize_t __c2port_write_flash_data(struct c2port_device *dev, return nwrite; } -static ssize_t c2port_write_flash_data(struct kobject *kobj, +static ssize_t c2port_write_flash_data(struct file *filp, struct kobject *kobj, struct bin_attribute *attr, char *buffer, loff_t offset, size_t count) { diff --git a/drivers/misc/ds1682.c b/drivers/misc/ds1682.c index 9197cfc55015..a513f0aa6432 100644 --- a/drivers/misc/ds1682.c +++ b/drivers/misc/ds1682.c @@ -140,7 +140,8 @@ static const struct attribute_group ds1682_group = { /* * User data attribute */ -static ssize_t ds1682_eeprom_read(struct kobject *kobj, struct bin_attribute *attr, +static ssize_t ds1682_eeprom_read(struct file *filp, struct kobject *kobj, + struct bin_attribute *attr, char *buf, loff_t off, size_t count) { struct i2c_client *client = kobj_to_i2c_client(kobj); @@ -163,7 +164,8 @@ static ssize_t ds1682_eeprom_read(struct kobject *kobj, struct bin_attribute *at return count; } -static ssize_t ds1682_eeprom_write(struct kobject *kobj, struct bin_attribute *attr, +static ssize_t ds1682_eeprom_write(struct file *filp, struct kobject *kobj, + struct bin_attribute *attr, char *buf, loff_t off, size_t count) { struct i2c_client *client = kobj_to_i2c_client(kobj); diff --git a/drivers/misc/eeprom/at24.c b/drivers/misc/eeprom/at24.c index db7d0f21b65d..a79a62f75481 100644 --- a/drivers/misc/eeprom/at24.c +++ b/drivers/misc/eeprom/at24.c @@ -274,7 +274,8 @@ static ssize_t at24_read(struct at24_data *at24, return retval; } -static ssize_t at24_bin_read(struct kobject *kobj, struct bin_attribute *attr, +static ssize_t at24_bin_read(struct file *filp, struct kobject *kobj, + struct bin_attribute *attr, char *buf, loff_t off, size_t count) { struct at24_data *at24; @@ -395,7 +396,8 @@ static ssize_t at24_write(struct at24_data *at24, const char *buf, loff_t off, return retval; } -static ssize_t at24_bin_write(struct kobject *kobj, struct bin_attribute *attr, +static ssize_t at24_bin_write(struct file *filp, struct kobject *kobj, + struct bin_attribute *attr, char *buf, loff_t off, size_t count) { struct at24_data *at24; diff --git a/drivers/misc/eeprom/at25.c b/drivers/misc/eeprom/at25.c index d194212a41f6..c627e4174ccd 100644 --- a/drivers/misc/eeprom/at25.c +++ b/drivers/misc/eeprom/at25.c @@ -126,7 +126,8 @@ at25_ee_read( } static ssize_t -at25_bin_read(struct kobject *kobj, struct bin_attribute *bin_attr, +at25_bin_read(struct file *filp, struct kobject *kobj, + struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct device *dev; @@ -253,7 +254,8 @@ at25_ee_write(struct at25_data *at25, const char *buf, loff_t off, } static ssize_t -at25_bin_write(struct kobject *kobj, struct bin_attribute *bin_attr, +at25_bin_write(struct file *filp, struct kobject *kobj, + struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct device *dev; diff --git a/drivers/misc/eeprom/eeprom.c b/drivers/misc/eeprom/eeprom.c index e306a8cd2f96..45060ddc4e59 100644 --- a/drivers/misc/eeprom/eeprom.c +++ b/drivers/misc/eeprom/eeprom.c @@ -81,7 +81,8 @@ exit: mutex_unlock(&data->update_lock); } -static ssize_t eeprom_read(struct kobject *kobj, struct bin_attribute *bin_attr, +static ssize_t eeprom_read(struct file *filp, struct kobject *kobj, + struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct i2c_client *client = to_i2c_client(container_of(kobj, struct device, kobj)); diff --git a/drivers/misc/eeprom/max6875.c b/drivers/misc/eeprom/max6875.c index fe2909278507..5653a3ce0517 100644 --- a/drivers/misc/eeprom/max6875.c +++ b/drivers/misc/eeprom/max6875.c @@ -107,7 +107,7 @@ exit_up: mutex_unlock(&data->update_lock); } -static ssize_t max6875_read(struct kobject *kobj, +static ssize_t max6875_read(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { diff --git a/drivers/net/netxen/netxen_nic_main.c b/drivers/net/netxen/netxen_nic_main.c index c61a61f177b7..6ce6ce1df6d2 100644 --- a/drivers/net/netxen/netxen_nic_main.c +++ b/drivers/net/netxen/netxen_nic_main.c @@ -2560,7 +2560,8 @@ netxen_sysfs_validate_crb(struct netxen_adapter *adapter, } static ssize_t -netxen_sysfs_read_crb(struct kobject *kobj, struct bin_attribute *attr, +netxen_sysfs_read_crb(struct file *filp, struct kobject *kobj, + struct bin_attribute *attr, char *buf, loff_t offset, size_t size) { struct device *dev = container_of(kobj, struct device, kobj); @@ -2587,7 +2588,8 @@ netxen_sysfs_read_crb(struct kobject *kobj, struct bin_attribute *attr, } static ssize_t -netxen_sysfs_write_crb(struct kobject *kobj, struct bin_attribute *attr, +netxen_sysfs_write_crb(struct file *filp, struct kobject *kobj, + struct bin_attribute *attr, char *buf, loff_t offset, size_t size) { struct device *dev = container_of(kobj, struct device, kobj); @@ -2627,7 +2629,8 @@ netxen_sysfs_validate_mem(struct netxen_adapter *adapter, } static ssize_t -netxen_sysfs_read_mem(struct kobject *kobj, struct bin_attribute *attr, +netxen_sysfs_read_mem(struct file *filp, struct kobject *kobj, + struct bin_attribute *attr, char *buf, loff_t offset, size_t size) { struct device *dev = container_of(kobj, struct device, kobj); @@ -2647,7 +2650,7 @@ netxen_sysfs_read_mem(struct kobject *kobj, struct bin_attribute *attr, return size; } -static ssize_t netxen_sysfs_write_mem(struct kobject *kobj, +static ssize_t netxen_sysfs_write_mem(struct file *filp, struct kobject *kobj, struct bin_attribute *attr, char *buf, loff_t offset, size_t size) { diff --git a/drivers/net/qlcnic/qlcnic_main.c b/drivers/net/qlcnic/qlcnic_main.c index 1003eb76fda3..23ea9caa5261 100644 --- a/drivers/net/qlcnic/qlcnic_main.c +++ b/drivers/net/qlcnic/qlcnic_main.c @@ -2464,7 +2464,8 @@ qlcnic_sysfs_validate_crb(struct qlcnic_adapter *adapter, } static ssize_t -qlcnic_sysfs_read_crb(struct kobject *kobj, struct bin_attribute *attr, +qlcnic_sysfs_read_crb(struct file *filp, struct kobject *kobj, + struct bin_attribute *attr, char *buf, loff_t offset, size_t size) { struct device *dev = container_of(kobj, struct device, kobj); @@ -2488,7 +2489,8 @@ qlcnic_sysfs_read_crb(struct kobject *kobj, struct bin_attribute *attr, } static ssize_t -qlcnic_sysfs_write_crb(struct kobject *kobj, struct bin_attribute *attr, +qlcnic_sysfs_write_crb(struct file *filp, struct kobject *kobj, + struct bin_attribute *attr, char *buf, loff_t offset, size_t size) { struct device *dev = container_of(kobj, struct device, kobj); @@ -2525,7 +2527,8 @@ qlcnic_sysfs_validate_mem(struct qlcnic_adapter *adapter, } static ssize_t -qlcnic_sysfs_read_mem(struct kobject *kobj, struct bin_attribute *attr, +qlcnic_sysfs_read_mem(struct file *filp, struct kobject *kobj, + struct bin_attribute *attr, char *buf, loff_t offset, size_t size) { struct device *dev = container_of(kobj, struct device, kobj); @@ -2546,7 +2549,8 @@ qlcnic_sysfs_read_mem(struct kobject *kobj, struct bin_attribute *attr, } static ssize_t -qlcnic_sysfs_write_mem(struct kobject *kobj, struct bin_attribute *attr, +qlcnic_sysfs_write_mem(struct file *filp, struct kobject *kobj, + struct bin_attribute *attr, char *buf, loff_t offset, size_t size) { struct device *dev = container_of(kobj, struct device, kobj); diff --git a/drivers/pci/hotplug/acpiphp_ibm.c b/drivers/pci/hotplug/acpiphp_ibm.c index 6ecbfb27db9d..e525263210ee 100644 --- a/drivers/pci/hotplug/acpiphp_ibm.c +++ b/drivers/pci/hotplug/acpiphp_ibm.c @@ -108,7 +108,7 @@ static int ibm_set_attention_status(struct hotplug_slot *slot, u8 status); static int ibm_get_attention_status(struct hotplug_slot *slot, u8 *status); static void ibm_handle_events(acpi_handle handle, u32 event, void *context); static int ibm_get_table_from_acpi(char **bufp); -static ssize_t ibm_read_apci_table(struct kobject *kobj, +static ssize_t ibm_read_apci_table(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buffer, loff_t pos, size_t size); static acpi_status __init ibm_find_acpi_device(acpi_handle handle, @@ -351,6 +351,7 @@ read_table_done: /** * ibm_read_apci_table - callback for the sysfs apci_table file + * @filp: the open sysfs file * @kobj: the kobject this binary attribute is a part of * @bin_attr: struct bin_attribute for this file * @buffer: the kernel space buffer to fill @@ -364,7 +365,7 @@ read_table_done: * things get really tricky here... * our solution is to only allow reading the table in all at once. */ -static ssize_t ibm_read_apci_table(struct kobject *kobj, +static ssize_t ibm_read_apci_table(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buffer, loff_t pos, size_t size) { diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c index fad93983bfed..ad44557e65c4 100644 --- a/drivers/pci/pci-sysfs.c +++ b/drivers/pci/pci-sysfs.c @@ -357,7 +357,8 @@ boot_vga_show(struct device *dev, struct device_attribute *attr, char *buf) struct device_attribute vga_attr = __ATTR_RO(boot_vga); static ssize_t -pci_read_config(struct kobject *kobj, struct bin_attribute *bin_attr, +pci_read_config(struct file *filp, struct kobject *kobj, + struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct pci_dev *dev = to_pci_dev(container_of(kobj,struct device,kobj)); @@ -430,7 +431,8 @@ pci_read_config(struct kobject *kobj, struct bin_attribute *bin_attr, } static ssize_t -pci_write_config(struct kobject *kobj, struct bin_attribute *bin_attr, +pci_write_config(struct file* filp, struct kobject *kobj, + struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct pci_dev *dev = to_pci_dev(container_of(kobj,struct device,kobj)); @@ -487,7 +489,8 @@ pci_write_config(struct kobject *kobj, struct bin_attribute *bin_attr, } static ssize_t -read_vpd_attr(struct kobject *kobj, struct bin_attribute *bin_attr, +read_vpd_attr(struct file *filp, struct kobject *kobj, + struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct pci_dev *dev = @@ -502,7 +505,8 @@ read_vpd_attr(struct kobject *kobj, struct bin_attribute *bin_attr, } static ssize_t -write_vpd_attr(struct kobject *kobj, struct bin_attribute *bin_attr, +write_vpd_attr(struct file *filp, struct kobject *kobj, + struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct pci_dev *dev = @@ -519,6 +523,7 @@ write_vpd_attr(struct kobject *kobj, struct bin_attribute *bin_attr, #ifdef HAVE_PCI_LEGACY /** * pci_read_legacy_io - read byte(s) from legacy I/O port space + * @filp: open sysfs file * @kobj: kobject corresponding to file to read from * @bin_attr: struct bin_attribute for this file * @buf: buffer to store results @@ -529,7 +534,8 @@ write_vpd_attr(struct kobject *kobj, struct bin_attribute *bin_attr, * callback routine (pci_legacy_read). */ static ssize_t -pci_read_legacy_io(struct kobject *kobj, struct bin_attribute *bin_attr, +pci_read_legacy_io(struct file *filp, struct kobject *kobj, + struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct pci_bus *bus = to_pci_bus(container_of(kobj, @@ -545,6 +551,7 @@ pci_read_legacy_io(struct kobject *kobj, struct bin_attribute *bin_attr, /** * pci_write_legacy_io - write byte(s) to legacy I/O port space + * @filp: open sysfs file * @kobj: kobject corresponding to file to read from * @bin_attr: struct bin_attribute for this file * @buf: buffer containing value to be written @@ -555,7 +562,8 @@ pci_read_legacy_io(struct kobject *kobj, struct bin_attribute *bin_attr, * callback routine (pci_legacy_write). */ static ssize_t -pci_write_legacy_io(struct kobject *kobj, struct bin_attribute *bin_attr, +pci_write_legacy_io(struct file *filp, struct kobject *kobj, + struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct pci_bus *bus = to_pci_bus(container_of(kobj, @@ -570,6 +578,7 @@ pci_write_legacy_io(struct kobject *kobj, struct bin_attribute *bin_attr, /** * pci_mmap_legacy_mem - map legacy PCI memory into user memory space + * @filp: open sysfs file * @kobj: kobject corresponding to device to be mapped * @attr: struct bin_attribute for this file * @vma: struct vm_area_struct passed to mmap @@ -579,7 +588,8 @@ pci_write_legacy_io(struct kobject *kobj, struct bin_attribute *bin_attr, * memory space. */ static int -pci_mmap_legacy_mem(struct kobject *kobj, struct bin_attribute *attr, +pci_mmap_legacy_mem(struct file *filp, struct kobject *kobj, + struct bin_attribute *attr, struct vm_area_struct *vma) { struct pci_bus *bus = to_pci_bus(container_of(kobj, @@ -591,6 +601,7 @@ pci_mmap_legacy_mem(struct kobject *kobj, struct bin_attribute *attr, /** * pci_mmap_legacy_io - map legacy PCI IO into user memory space + * @filp: open sysfs file * @kobj: kobject corresponding to device to be mapped * @attr: struct bin_attribute for this file * @vma: struct vm_area_struct passed to mmap @@ -600,7 +611,8 @@ pci_mmap_legacy_mem(struct kobject *kobj, struct bin_attribute *attr, * memory space. Returns -ENOSYS if the operation isn't supported */ static int -pci_mmap_legacy_io(struct kobject *kobj, struct bin_attribute *attr, +pci_mmap_legacy_io(struct file *filp, struct kobject *kobj, + struct bin_attribute *attr, struct vm_area_struct *vma) { struct pci_bus *bus = to_pci_bus(container_of(kobj, @@ -750,14 +762,16 @@ pci_mmap_resource(struct kobject *kobj, struct bin_attribute *attr, } static int -pci_mmap_resource_uc(struct kobject *kobj, struct bin_attribute *attr, +pci_mmap_resource_uc(struct file *filp, struct kobject *kobj, + struct bin_attribute *attr, struct vm_area_struct *vma) { return pci_mmap_resource(kobj, attr, vma, 0); } static int -pci_mmap_resource_wc(struct kobject *kobj, struct bin_attribute *attr, +pci_mmap_resource_wc(struct file *filp, struct kobject *kobj, + struct bin_attribute *attr, struct vm_area_struct *vma) { return pci_mmap_resource(kobj, attr, vma, 1); @@ -861,6 +875,7 @@ void __weak pci_remove_resource_files(struct pci_dev *dev) { return; } /** * pci_write_rom - used to enable access to the PCI ROM display + * @filp: sysfs file * @kobj: kernel object handle * @bin_attr: struct bin_attribute for this file * @buf: user input @@ -870,7 +885,8 @@ void __weak pci_remove_resource_files(struct pci_dev *dev) { return; } * writing anything except 0 enables it */ static ssize_t -pci_write_rom(struct kobject *kobj, struct bin_attribute *bin_attr, +pci_write_rom(struct file *filp, struct kobject *kobj, + struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct pci_dev *pdev = to_pci_dev(container_of(kobj, struct device, kobj)); @@ -885,6 +901,7 @@ pci_write_rom(struct kobject *kobj, struct bin_attribute *bin_attr, /** * pci_read_rom - read a PCI ROM + * @filp: sysfs file * @kobj: kernel object handle * @bin_attr: struct bin_attribute for this file * @buf: where to put the data we read from the ROM @@ -895,7 +912,8 @@ pci_write_rom(struct kobject *kobj, struct bin_attribute *bin_attr, * device corresponding to @kobj. */ static ssize_t -pci_read_rom(struct kobject *kobj, struct bin_attribute *bin_attr, +pci_read_rom(struct file *filp, struct kobject *kobj, + struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct pci_dev *pdev = to_pci_dev(container_of(kobj, struct device, kobj)); diff --git a/drivers/pcmcia/cistpl.c b/drivers/pcmcia/cistpl.c index 60d428be0b07..8844bc3e3118 100644 --- a/drivers/pcmcia/cistpl.c +++ b/drivers/pcmcia/cistpl.c @@ -1531,7 +1531,7 @@ static ssize_t pccard_extract_cis(struct pcmcia_socket *s, char *buf, } -static ssize_t pccard_show_cis(struct kobject *kobj, +static ssize_t pccard_show_cis(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { @@ -1562,7 +1562,7 @@ static ssize_t pccard_show_cis(struct kobject *kobj, } -static ssize_t pccard_store_cis(struct kobject *kobj, +static ssize_t pccard_store_cis(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { diff --git a/drivers/power/olpc_battery.c b/drivers/power/olpc_battery.c index 8fefe5a73558..baefcf1cffc9 100644 --- a/drivers/power/olpc_battery.c +++ b/drivers/power/olpc_battery.c @@ -354,7 +354,7 @@ static enum power_supply_property olpc_bat_props[] = { #define EEPROM_END 0x80 #define EEPROM_SIZE (EEPROM_END - EEPROM_START) -static ssize_t olpc_bat_eeprom_read(struct kobject *kobj, +static ssize_t olpc_bat_eeprom_read(struct file *filp, struct kobject *kobj, struct bin_attribute *attr, char *buf, loff_t off, size_t count) { uint8_t ec_byte; diff --git a/drivers/rapidio/rio-sysfs.c b/drivers/rapidio/rio-sysfs.c index ba742e82c57d..00b475658356 100644 --- a/drivers/rapidio/rio-sysfs.c +++ b/drivers/rapidio/rio-sysfs.c @@ -68,7 +68,8 @@ struct device_attribute rio_dev_attrs[] = { }; static ssize_t -rio_read_config(struct kobject *kobj, struct bin_attribute *bin_attr, +rio_read_config(struct file *filp, struct kobject *kobj, + struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct rio_dev *dev = @@ -139,7 +140,8 @@ rio_read_config(struct kobject *kobj, struct bin_attribute *bin_attr, } static ssize_t -rio_write_config(struct kobject *kobj, struct bin_attribute *bin_attr, +rio_write_config(struct file *filp, struct kobject *kobj, + struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct rio_dev *dev = diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c index e9aa814ddd23..ece4dbddc0ea 100644 --- a/drivers/rtc/rtc-cmos.c +++ b/drivers/rtc/rtc-cmos.c @@ -519,7 +519,8 @@ static const struct rtc_class_ops cmos_rtc_ops = { #define NVRAM_OFFSET (RTC_REG_D + 1) static ssize_t -cmos_nvram_read(struct kobject *kobj, struct bin_attribute *attr, +cmos_nvram_read(struct file *filp, struct kobject *kobj, + struct bin_attribute *attr, char *buf, loff_t off, size_t count) { int retval; @@ -547,7 +548,8 @@ cmos_nvram_read(struct kobject *kobj, struct bin_attribute *attr, } static ssize_t -cmos_nvram_write(struct kobject *kobj, struct bin_attribute *attr, +cmos_nvram_write(struct file *filp, struct kobject *kobj, + struct bin_attribute *attr, char *buf, loff_t off, size_t count) { struct cmos_rtc *cmos; diff --git a/drivers/rtc/rtc-ds1305.c b/drivers/rtc/rtc-ds1305.c index 7836c9cec557..48da85e97ca4 100644 --- a/drivers/rtc/rtc-ds1305.c +++ b/drivers/rtc/rtc-ds1305.c @@ -542,7 +542,8 @@ static void msg_init(struct spi_message *m, struct spi_transfer *x, } static ssize_t -ds1305_nvram_read(struct kobject *kobj, struct bin_attribute *attr, +ds1305_nvram_read(struct file *filp, struct kobject *kobj, + struct bin_attribute *attr, char *buf, loff_t off, size_t count) { struct spi_device *spi; @@ -572,7 +573,8 @@ ds1305_nvram_read(struct kobject *kobj, struct bin_attribute *attr, } static ssize_t -ds1305_nvram_write(struct kobject *kobj, struct bin_attribute *attr, +ds1305_nvram_write(struct file *filp, struct kobject *kobj, + struct bin_attribute *attr, char *buf, loff_t off, size_t count) { struct spi_device *spi; diff --git a/drivers/rtc/rtc-ds1307.c b/drivers/rtc/rtc-ds1307.c index c4ec5c158aa1..de033b7ac21f 100644 --- a/drivers/rtc/rtc-ds1307.c +++ b/drivers/rtc/rtc-ds1307.c @@ -556,7 +556,8 @@ static const struct rtc_class_ops ds13xx_rtc_ops = { #define NVRAM_SIZE 56 static ssize_t -ds1307_nvram_read(struct kobject *kobj, struct bin_attribute *attr, +ds1307_nvram_read(struct file *filp, struct kobject *kobj, + struct bin_attribute *attr, char *buf, loff_t off, size_t count) { struct i2c_client *client; @@ -580,7 +581,8 @@ ds1307_nvram_read(struct kobject *kobj, struct bin_attribute *attr, } static ssize_t -ds1307_nvram_write(struct kobject *kobj, struct bin_attribute *attr, +ds1307_nvram_write(struct file *filp, struct kobject *kobj, + struct bin_attribute *attr, char *buf, loff_t off, size_t count) { struct i2c_client *client; diff --git a/drivers/rtc/rtc-ds1511.c b/drivers/rtc/rtc-ds1511.c index 06b8566c4532..37268e97de49 100644 --- a/drivers/rtc/rtc-ds1511.c +++ b/drivers/rtc/rtc-ds1511.c @@ -423,8 +423,9 @@ static const struct rtc_class_ops ds1511_rtc_ops = { }; static ssize_t -ds1511_nvram_read(struct kobject *kobj, struct bin_attribute *ba, - char *buf, loff_t pos, size_t size) +ds1511_nvram_read(struct file *filp, struct kobject *kobj, + struct bin_attribute *ba, + char *buf, loff_t pos, size_t size) { ssize_t count; @@ -452,8 +453,9 @@ ds1511_nvram_read(struct kobject *kobj, struct bin_attribute *ba, } static ssize_t -ds1511_nvram_write(struct kobject *kobj, struct bin_attribute *bin_attr, - char *buf, loff_t pos, size_t size) +ds1511_nvram_write(struct file *filp, struct kobject *kobj, + struct bin_attribute *bin_attr, + char *buf, loff_t pos, size_t size) { ssize_t count; diff --git a/drivers/rtc/rtc-ds1553.c b/drivers/rtc/rtc-ds1553.c index 244f9994bcbb..ff432e2ca275 100644 --- a/drivers/rtc/rtc-ds1553.c +++ b/drivers/rtc/rtc-ds1553.c @@ -252,7 +252,7 @@ static const struct rtc_class_ops ds1553_rtc_ops = { .update_irq_enable = ds1553_rtc_update_irq_enable, }; -static ssize_t ds1553_nvram_read(struct kobject *kobj, +static ssize_t ds1553_nvram_read(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t pos, size_t size) { @@ -267,7 +267,7 @@ static ssize_t ds1553_nvram_read(struct kobject *kobj, return count; } -static ssize_t ds1553_nvram_write(struct kobject *kobj, +static ssize_t ds1553_nvram_write(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t pos, size_t size) { diff --git a/drivers/rtc/rtc-ds1742.c b/drivers/rtc/rtc-ds1742.c index 2b4b0bc42d6f..042630c90dd3 100644 --- a/drivers/rtc/rtc-ds1742.c +++ b/drivers/rtc/rtc-ds1742.c @@ -128,7 +128,7 @@ static const struct rtc_class_ops ds1742_rtc_ops = { .set_time = ds1742_rtc_set_time, }; -static ssize_t ds1742_nvram_read(struct kobject *kobj, +static ssize_t ds1742_nvram_read(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t pos, size_t size) { @@ -143,7 +143,7 @@ static ssize_t ds1742_nvram_read(struct kobject *kobj, return count; } -static ssize_t ds1742_nvram_write(struct kobject *kobj, +static ssize_t ds1742_nvram_write(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t pos, size_t size) { diff --git a/drivers/rtc/rtc-m48t59.c b/drivers/rtc/rtc-m48t59.c index 365ff3ac2348..be8359fdb65a 100644 --- a/drivers/rtc/rtc-m48t59.c +++ b/drivers/rtc/rtc-m48t59.c @@ -343,7 +343,7 @@ static const struct rtc_class_ops m48t02_rtc_ops = { .set_time = m48t59_rtc_set_time, }; -static ssize_t m48t59_nvram_read(struct kobject *kobj, +static ssize_t m48t59_nvram_read(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t pos, size_t size) { @@ -363,7 +363,7 @@ static ssize_t m48t59_nvram_read(struct kobject *kobj, return cnt; } -static ssize_t m48t59_nvram_write(struct kobject *kobj, +static ssize_t m48t59_nvram_write(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t pos, size_t size) { diff --git a/drivers/rtc/rtc-stk17ta8.c b/drivers/rtc/rtc-stk17ta8.c index b53a00198dbe..3b943673cd3e 100644 --- a/drivers/rtc/rtc-stk17ta8.c +++ b/drivers/rtc/rtc-stk17ta8.c @@ -244,7 +244,7 @@ static const struct rtc_class_ops stk17ta8_rtc_ops = { .alarm_irq_enable = stk17ta8_rtc_alarm_irq_enable, }; -static ssize_t stk17ta8_nvram_read(struct kobject *kobj, +static ssize_t stk17ta8_nvram_read(struct file *filp, struct kobject *kobj, struct bin_attribute *attr, char *buf, loff_t pos, size_t size) { @@ -259,7 +259,7 @@ static ssize_t stk17ta8_nvram_read(struct kobject *kobj, return count; } -static ssize_t stk17ta8_nvram_write(struct kobject *kobj, +static ssize_t stk17ta8_nvram_write(struct file *filp, struct kobject *kobj, struct bin_attribute *attr, char *buf, loff_t pos, size_t size) { diff --git a/drivers/rtc/rtc-tx4939.c b/drivers/rtc/rtc-tx4939.c index 20bfc64a15c8..ec6313d15359 100644 --- a/drivers/rtc/rtc-tx4939.c +++ b/drivers/rtc/rtc-tx4939.c @@ -188,7 +188,7 @@ static const struct rtc_class_ops tx4939_rtc_ops = { .alarm_irq_enable = tx4939_rtc_alarm_irq_enable, }; -static ssize_t tx4939_rtc_nvram_read(struct kobject *kobj, +static ssize_t tx4939_rtc_nvram_read(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t pos, size_t size) { @@ -207,7 +207,7 @@ static ssize_t tx4939_rtc_nvram_read(struct kobject *kobj, return count; } -static ssize_t tx4939_rtc_nvram_write(struct kobject *kobj, +static ssize_t tx4939_rtc_nvram_write(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t pos, size_t size) { diff --git a/drivers/s390/cio/chp.c b/drivers/s390/cio/chp.c index 1d16189f2f2d..6c9fa15aac7b 100644 --- a/drivers/s390/cio/chp.c +++ b/drivers/s390/cio/chp.c @@ -135,7 +135,8 @@ static int s390_vary_chpid(struct chp_id chpid, int on) /* * Channel measurement related functions */ -static ssize_t chp_measurement_chars_read(struct kobject *kobj, +static ssize_t chp_measurement_chars_read(struct file *filp, + struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { @@ -182,7 +183,7 @@ static void chp_measurement_copy_block(struct cmg_entry *buf, } while (reference_buf.values[0] != buf->values[0]); } -static ssize_t chp_measurement_read(struct kobject *kobj, +static ssize_t chp_measurement_read(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { diff --git a/drivers/scsi/3w-sas.c b/drivers/scsi/3w-sas.c index 54c5ffb1eaa1..d38000db9237 100644 --- a/drivers/scsi/3w-sas.c +++ b/drivers/scsi/3w-sas.c @@ -98,7 +98,7 @@ static int twl_reset_device_extension(TW_Device_Extension *tw_dev, int ioctl_res /* Functions */ /* This function returns AENs through sysfs */ -static ssize_t twl_sysfs_aen_read(struct kobject *kobj, +static ssize_t twl_sysfs_aen_read(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *outbuf, loff_t offset, size_t count) { @@ -129,7 +129,7 @@ static struct bin_attribute twl_sysfs_aen_read_attr = { }; /* This function returns driver compatibility info through sysfs */ -static ssize_t twl_sysfs_compat_info(struct kobject *kobj, +static ssize_t twl_sysfs_compat_info(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *outbuf, loff_t offset, size_t count) { diff --git a/drivers/scsi/arcmsr/arcmsr_attr.c b/drivers/scsi/arcmsr/arcmsr_attr.c index 5877f29a6005..a4e04c50c436 100644 --- a/drivers/scsi/arcmsr/arcmsr_attr.c +++ b/drivers/scsi/arcmsr/arcmsr_attr.c @@ -59,7 +59,8 @@ struct device_attribute *arcmsr_host_attrs[]; -static ssize_t arcmsr_sysfs_iop_message_read(struct kobject *kobj, +static ssize_t arcmsr_sysfs_iop_message_read(struct file *filp, + struct kobject *kobj, struct bin_attribute *bin, char *buf, loff_t off, size_t count) @@ -105,7 +106,8 @@ static ssize_t arcmsr_sysfs_iop_message_read(struct kobject *kobj, return (allxfer_len); } -static ssize_t arcmsr_sysfs_iop_message_write(struct kobject *kobj, +static ssize_t arcmsr_sysfs_iop_message_write(struct file *filp, + struct kobject *kobj, struct bin_attribute *bin, char *buf, loff_t off, size_t count) @@ -153,7 +155,8 @@ static ssize_t arcmsr_sysfs_iop_message_write(struct kobject *kobj, } } -static ssize_t arcmsr_sysfs_iop_message_clear(struct kobject *kobj, +static ssize_t arcmsr_sysfs_iop_message_clear(struct file *filp, + struct kobject *kobj, struct bin_attribute *bin, char *buf, loff_t off, size_t count) diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c index d18f45c95639..3eb2b7b3d8b0 100644 --- a/drivers/scsi/ibmvscsi/ibmvfc.c +++ b/drivers/scsi/ibmvscsi/ibmvfc.c @@ -2919,6 +2919,7 @@ static DEVICE_ATTR(log_level, S_IRUGO | S_IWUSR, #ifdef CONFIG_SCSI_IBMVFC_TRACE /** * ibmvfc_read_trace - Dump the adapter trace + * @filp: open sysfs file * @kobj: kobject struct * @bin_attr: bin_attribute struct * @buf: buffer @@ -2928,7 +2929,7 @@ static DEVICE_ATTR(log_level, S_IRUGO | S_IWUSR, * Return value: * number of bytes printed to buffer **/ -static ssize_t ibmvfc_read_trace(struct kobject *kobj, +static ssize_t ibmvfc_read_trace(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c index b90c118119d7..6a6661c35b2f 100644 --- a/drivers/scsi/ipr.c +++ b/drivers/scsi/ipr.c @@ -3120,6 +3120,7 @@ restart: #ifdef CONFIG_SCSI_IPR_TRACE /** * ipr_read_trace - Dump the adapter trace + * @filp: open sysfs file * @kobj: kobject struct * @bin_attr: bin_attribute struct * @buf: buffer @@ -3129,7 +3130,7 @@ restart: * Return value: * number of bytes printed to buffer **/ -static ssize_t ipr_read_trace(struct kobject *kobj, +static ssize_t ipr_read_trace(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { @@ -3764,6 +3765,7 @@ static struct device_attribute *ipr_ioa_attrs[] = { #ifdef CONFIG_SCSI_IPR_DUMP /** * ipr_read_dump - Dump the adapter + * @filp: open sysfs file * @kobj: kobject struct * @bin_attr: bin_attribute struct * @buf: buffer @@ -3773,7 +3775,7 @@ static struct device_attribute *ipr_ioa_attrs[] = { * Return value: * number of bytes printed to buffer **/ -static ssize_t ipr_read_dump(struct kobject *kobj, +static ssize_t ipr_read_dump(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { @@ -3927,6 +3929,7 @@ static int ipr_free_dump(struct ipr_ioa_cfg *ioa_cfg) /** * ipr_write_dump - Setup dump state of adapter + * @filp: open sysfs file * @kobj: kobject struct * @bin_attr: bin_attribute struct * @buf: buffer @@ -3936,7 +3939,7 @@ static int ipr_free_dump(struct ipr_ioa_cfg *ioa_cfg) * Return value: * number of bytes printed to buffer **/ -static ssize_t ipr_write_dump(struct kobject *kobj, +static ssize_t ipr_write_dump(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { diff --git a/drivers/scsi/lpfc/lpfc_attr.c b/drivers/scsi/lpfc/lpfc_attr.c index 2e5f376d9ccc..bf33b315f93e 100644 --- a/drivers/scsi/lpfc/lpfc_attr.c +++ b/drivers/scsi/lpfc/lpfc_attr.c @@ -2643,6 +2643,7 @@ static DEVICE_ATTR(lpfc_stat_data_ctrl, S_IRUGO | S_IWUSR, /** * sysfs_drvr_stat_data_read - Read function for lpfc_drvr_stat_data attribute + * @filp: sysfs file * @kobj: Pointer to the kernel object * @bin_attr: Attribute object * @buff: Buffer pointer @@ -2654,7 +2655,8 @@ static DEVICE_ATTR(lpfc_stat_data_ctrl, S_IRUGO | S_IWUSR, * applications. **/ static ssize_t -sysfs_drvr_stat_data_read(struct kobject *kobj, struct bin_attribute *bin_attr, +sysfs_drvr_stat_data_read(struct file *filp, struct kobject *kobj, + struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct device *dev = container_of(kobj, struct device, @@ -3362,6 +3364,7 @@ struct device_attribute *lpfc_vport_attrs[] = { /** * sysfs_ctlreg_write - Write method for writing to ctlreg + * @filp: open sysfs file * @kobj: kernel kobject that contains the kernel class device. * @bin_attr: kernel attributes passed to us. * @buf: contains the data to be written to the adapter IOREG space. @@ -3379,7 +3382,8 @@ struct device_attribute *lpfc_vport_attrs[] = { * value of count, buf contents written **/ static ssize_t -sysfs_ctlreg_write(struct kobject *kobj, struct bin_attribute *bin_attr, +sysfs_ctlreg_write(struct file *filp, struct kobject *kobj, + struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { size_t buf_off; @@ -3415,6 +3419,7 @@ sysfs_ctlreg_write(struct kobject *kobj, struct bin_attribute *bin_attr, /** * sysfs_ctlreg_read - Read method for reading from ctlreg + * @filp: open sysfs file * @kobj: kernel kobject that contains the kernel class device. * @bin_attr: kernel attributes passed to us. * @buf: if successful contains the data from the adapter IOREG space. @@ -3431,7 +3436,8 @@ sysfs_ctlreg_write(struct kobject *kobj, struct bin_attribute *bin_attr, * value of count, buf contents read **/ static ssize_t -sysfs_ctlreg_read(struct kobject *kobj, struct bin_attribute *bin_attr, +sysfs_ctlreg_read(struct file *filp, struct kobject *kobj, + struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { size_t buf_off; @@ -3496,6 +3502,7 @@ sysfs_mbox_idle(struct lpfc_hba *phba) /** * sysfs_mbox_write - Write method for writing information via mbox + * @filp: open sysfs file * @kobj: kernel kobject that contains the kernel class device. * @bin_attr: kernel attributes passed to us. * @buf: contains the data to be written to sysfs mbox. @@ -3516,7 +3523,8 @@ sysfs_mbox_idle(struct lpfc_hba *phba) * count number of bytes transferred **/ static ssize_t -sysfs_mbox_write(struct kobject *kobj, struct bin_attribute *bin_attr, +sysfs_mbox_write(struct file *filp, struct kobject *kobj, + struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct device *dev = container_of(kobj, struct device, kobj); @@ -3571,6 +3579,7 @@ sysfs_mbox_write(struct kobject *kobj, struct bin_attribute *bin_attr, /** * sysfs_mbox_read - Read method for reading information via mbox + * @filp: open sysfs file * @kobj: kernel kobject that contains the kernel class device. * @bin_attr: kernel attributes passed to us. * @buf: contains the data to be read from sysfs mbox. @@ -3593,7 +3602,8 @@ sysfs_mbox_write(struct kobject *kobj, struct bin_attribute *bin_attr, * count number of bytes transferred **/ static ssize_t -sysfs_mbox_read(struct kobject *kobj, struct bin_attribute *bin_attr, +sysfs_mbox_read(struct file *filp, struct kobject *kobj, + struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct device *dev = container_of(kobj, struct device, kobj); diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c index 3b708606b932..1e4cafabba15 100644 --- a/drivers/scsi/qla2xxx/qla_attr.c +++ b/drivers/scsi/qla2xxx/qla_attr.c @@ -16,7 +16,7 @@ static int qla24xx_vport_disable(struct fc_vport *, bool); /* SYSFS attributes --------------------------------------------------------- */ static ssize_t -qla2x00_sysfs_read_fw_dump(struct kobject *kobj, +qla2x00_sysfs_read_fw_dump(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { @@ -32,7 +32,7 @@ qla2x00_sysfs_read_fw_dump(struct kobject *kobj, } static ssize_t -qla2x00_sysfs_write_fw_dump(struct kobject *kobj, +qla2x00_sysfs_write_fw_dump(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { @@ -92,7 +92,7 @@ static struct bin_attribute sysfs_fw_dump_attr = { }; static ssize_t -qla2x00_sysfs_read_nvram(struct kobject *kobj, +qla2x00_sysfs_read_nvram(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { @@ -111,7 +111,7 @@ qla2x00_sysfs_read_nvram(struct kobject *kobj, } static ssize_t -qla2x00_sysfs_write_nvram(struct kobject *kobj, +qla2x00_sysfs_write_nvram(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { @@ -177,7 +177,7 @@ static struct bin_attribute sysfs_nvram_attr = { }; static ssize_t -qla2x00_sysfs_read_optrom(struct kobject *kobj, +qla2x00_sysfs_read_optrom(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { @@ -193,7 +193,7 @@ qla2x00_sysfs_read_optrom(struct kobject *kobj, } static ssize_t -qla2x00_sysfs_write_optrom(struct kobject *kobj, +qla2x00_sysfs_write_optrom(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { @@ -224,7 +224,7 @@ static struct bin_attribute sysfs_optrom_attr = { }; static ssize_t -qla2x00_sysfs_write_optrom_ctl(struct kobject *kobj, +qla2x00_sysfs_write_optrom_ctl(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { @@ -387,7 +387,7 @@ static struct bin_attribute sysfs_optrom_ctl_attr = { }; static ssize_t -qla2x00_sysfs_read_vpd(struct kobject *kobj, +qla2x00_sysfs_read_vpd(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { @@ -408,7 +408,7 @@ qla2x00_sysfs_read_vpd(struct kobject *kobj, } static ssize_t -qla2x00_sysfs_write_vpd(struct kobject *kobj, +qla2x00_sysfs_write_vpd(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { @@ -461,7 +461,7 @@ static struct bin_attribute sysfs_vpd_attr = { }; static ssize_t -qla2x00_sysfs_read_sfp(struct kobject *kobj, +qla2x00_sysfs_read_sfp(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { @@ -522,7 +522,7 @@ static struct bin_attribute sysfs_sfp_attr = { }; static ssize_t -qla2x00_sysfs_write_reset(struct kobject *kobj, +qla2x00_sysfs_write_reset(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { @@ -592,7 +592,7 @@ static struct bin_attribute sysfs_reset_attr = { }; static ssize_t -qla2x00_sysfs_write_edc(struct kobject *kobj, +qla2x00_sysfs_write_edc(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { @@ -650,7 +650,7 @@ static struct bin_attribute sysfs_edc_attr = { }; static ssize_t -qla2x00_sysfs_write_edc_status(struct kobject *kobj, +qla2x00_sysfs_write_edc_status(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { @@ -700,7 +700,7 @@ qla2x00_sysfs_write_edc_status(struct kobject *kobj, } static ssize_t -qla2x00_sysfs_read_edc_status(struct kobject *kobj, +qla2x00_sysfs_read_edc_status(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { @@ -730,7 +730,7 @@ static struct bin_attribute sysfs_edc_status_attr = { }; static ssize_t -qla2x00_sysfs_read_xgmac_stats(struct kobject *kobj, +qla2x00_sysfs_read_xgmac_stats(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { @@ -782,7 +782,7 @@ static struct bin_attribute sysfs_xgmac_stats_attr = { }; static ssize_t -qla2x00_sysfs_read_dcbx_tlv(struct kobject *kobj, +qla2x00_sysfs_read_dcbx_tlv(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { diff --git a/drivers/staging/udlfb/udlfb.c b/drivers/staging/udlfb/udlfb.c index aa8195199a2c..577f2bf6eb23 100644 --- a/drivers/staging/udlfb/udlfb.c +++ b/drivers/staging/udlfb/udlfb.c @@ -1063,7 +1063,8 @@ static ssize_t metrics_misc_show(struct device *fbdev, atomic_read(&dev->lost_pixels) ? "yes" : "no"); } -static ssize_t edid_show(struct kobject *kobj, struct bin_attribute *a, +static ssize_t edid_show(struct file *filp, struct kobject *kobj, + struct bin_attribute *a, char *buf, loff_t off, size_t count) { struct device *fbdev = container_of(kobj, struct device, kobj); struct fb_info *fb_info = dev_get_drvdata(fbdev); diff --git a/drivers/usb/core/sysfs.c b/drivers/usb/core/sysfs.c index 06863befaf3a..448f5b47fc48 100644 --- a/drivers/usb/core/sysfs.c +++ b/drivers/usb/core/sysfs.c @@ -658,7 +658,8 @@ const struct attribute_group *usb_device_groups[] = { /* Binary descriptors */ static ssize_t -read_descriptors(struct kobject *kobj, struct bin_attribute *attr, +read_descriptors(struct file *filp, struct kobject *kobj, + struct bin_attribute *attr, char *buf, loff_t off, size_t count) { struct device *dev = container_of(kobj, struct device, kobj); diff --git a/drivers/video/aty/radeon_base.c b/drivers/video/aty/radeon_base.c index 6c37e8ee5efe..3c1e13ed1cba 100644 --- a/drivers/video/aty/radeon_base.c +++ b/drivers/video/aty/radeon_base.c @@ -2099,7 +2099,7 @@ static ssize_t radeon_show_one_edid(char *buf, loff_t off, size_t count, const u } -static ssize_t radeon_show_edid1(struct kobject *kobj, +static ssize_t radeon_show_edid1(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { @@ -2112,7 +2112,7 @@ static ssize_t radeon_show_edid1(struct kobject *kobj, } -static ssize_t radeon_show_edid2(struct kobject *kobj, +static ssize_t radeon_show_edid2(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { diff --git a/drivers/w1/slaves/w1_ds2431.c b/drivers/w1/slaves/w1_ds2431.c index 2c6c0cf6a20f..84e2410aec1d 100644 --- a/drivers/w1/slaves/w1_ds2431.c +++ b/drivers/w1/slaves/w1_ds2431.c @@ -96,7 +96,7 @@ static int w1_f2d_readblock(struct w1_slave *sl, int off, int count, char *buf) return -1; } -static ssize_t w1_f2d_read_bin(struct kobject *kobj, +static ssize_t w1_f2d_read_bin(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { @@ -202,7 +202,7 @@ retry: return 0; } -static ssize_t w1_f2d_write_bin(struct kobject *kobj, +static ssize_t w1_f2d_write_bin(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { diff --git a/drivers/w1/slaves/w1_ds2433.c b/drivers/w1/slaves/w1_ds2433.c index d2bf32118a98..0f7b8f9c509a 100644 --- a/drivers/w1/slaves/w1_ds2433.c +++ b/drivers/w1/slaves/w1_ds2433.c @@ -92,7 +92,7 @@ static int w1_f23_refresh_block(struct w1_slave *sl, struct w1_f23_data *data, } #endif /* CONFIG_W1_SLAVE_DS2433_CRC */ -static ssize_t w1_f23_read_bin(struct kobject *kobj, +static ssize_t w1_f23_read_bin(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { @@ -206,7 +206,7 @@ static int w1_f23_write(struct w1_slave *sl, int addr, int len, const u8 *data) return 0; } -static ssize_t w1_f23_write_bin(struct kobject *kobj, +static ssize_t w1_f23_write_bin(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { diff --git a/drivers/w1/slaves/w1_ds2760.c b/drivers/w1/slaves/w1_ds2760.c index 6e153343e117..483d45180911 100644 --- a/drivers/w1/slaves/w1_ds2760.c +++ b/drivers/w1/slaves/w1_ds2760.c @@ -97,7 +97,7 @@ int w1_ds2760_recall_eeprom(struct device *dev, int addr) return w1_ds2760_eeprom_cmd(dev, addr, W1_DS2760_RECALL_DATA); } -static ssize_t w1_ds2760_read_bin(struct kobject *kobj, +static ssize_t w1_ds2760_read_bin(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { diff --git a/drivers/w1/w1.c b/drivers/w1/w1.c index ad5897dc4495..2839e281cd65 100644 --- a/drivers/w1/w1.c +++ b/drivers/w1/w1.c @@ -120,7 +120,7 @@ static struct device_attribute w1_slave_attr_id = /* Default family */ -static ssize_t w1_default_write(struct kobject *kobj, +static ssize_t w1_default_write(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { @@ -139,7 +139,7 @@ out_up: return count; } -static ssize_t w1_default_read(struct kobject *kobj, +static ssize_t w1_default_read(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { diff --git a/drivers/zorro/zorro-sysfs.c b/drivers/zorro/zorro-sysfs.c index eb924e0a64ce..26f7184ef9e1 100644 --- a/drivers/zorro/zorro-sysfs.c +++ b/drivers/zorro/zorro-sysfs.c @@ -49,7 +49,7 @@ static ssize_t zorro_show_resource(struct device *dev, struct device_attribute * static DEVICE_ATTR(resource, S_IRUGO, zorro_show_resource, NULL); -static ssize_t zorro_read_config(struct kobject *kobj, +static ssize_t zorro_read_config(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { diff --git a/fs/sysfs/bin.c b/fs/sysfs/bin.c index 806b277453f9..4e321f7353fa 100644 --- a/fs/sysfs/bin.c +++ b/fs/sysfs/bin.c @@ -46,9 +46,9 @@ struct bin_buffer { }; static int -fill_read(struct dentry *dentry, char *buffer, loff_t off, size_t count) +fill_read(struct file *file, char *buffer, loff_t off, size_t count) { - struct sysfs_dirent *attr_sd = dentry->d_fsdata; + struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata; struct bin_attribute *attr = attr_sd->s_bin_attr.bin_attr; struct kobject *kobj = attr_sd->s_parent->s_dir.kobj; int rc; @@ -59,7 +59,7 @@ fill_read(struct dentry *dentry, char *buffer, loff_t off, size_t count) rc = -EIO; if (attr->read) - rc = attr->read(kobj, attr, buffer, off, count); + rc = attr->read(file, kobj, attr, buffer, off, count); sysfs_put_active(attr_sd); @@ -70,8 +70,7 @@ static ssize_t read(struct file *file, char __user *userbuf, size_t bytes, loff_t *off) { struct bin_buffer *bb = file->private_data; - struct dentry *dentry = file->f_path.dentry; - int size = dentry->d_inode->i_size; + int size = file->f_path.dentry->d_inode->i_size; loff_t offs = *off; int count = min_t(size_t, bytes, PAGE_SIZE); char *temp; @@ -92,7 +91,7 @@ read(struct file *file, char __user *userbuf, size_t bytes, loff_t *off) mutex_lock(&bb->mutex); - count = fill_read(dentry, bb->buffer, offs, count); + count = fill_read(file, bb->buffer, offs, count); if (count < 0) { mutex_unlock(&bb->mutex); goto out_free; @@ -117,9 +116,9 @@ read(struct file *file, char __user *userbuf, size_t bytes, loff_t *off) } static int -flush_write(struct dentry *dentry, char *buffer, loff_t offset, size_t count) +flush_write(struct file *file, char *buffer, loff_t offset, size_t count) { - struct sysfs_dirent *attr_sd = dentry->d_fsdata; + struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata; struct bin_attribute *attr = attr_sd->s_bin_attr.bin_attr; struct kobject *kobj = attr_sd->s_parent->s_dir.kobj; int rc; @@ -130,7 +129,7 @@ flush_write(struct dentry *dentry, char *buffer, loff_t offset, size_t count) rc = -EIO; if (attr->write) - rc = attr->write(kobj, attr, buffer, offset, count); + rc = attr->write(file, kobj, attr, buffer, offset, count); sysfs_put_active(attr_sd); @@ -141,8 +140,7 @@ static ssize_t write(struct file *file, const char __user *userbuf, size_t bytes, loff_t *off) { struct bin_buffer *bb = file->private_data; - struct dentry *dentry = file->f_path.dentry; - int size = dentry->d_inode->i_size; + int size = file->f_path.dentry->d_inode->i_size; loff_t offs = *off; int count = min_t(size_t, bytes, PAGE_SIZE); char *temp; @@ -165,7 +163,7 @@ static ssize_t write(struct file *file, const char __user *userbuf, memcpy(bb->buffer, temp, count); - count = flush_write(dentry, bb->buffer, offs, count); + count = flush_write(file, bb->buffer, offs, count); mutex_unlock(&bb->mutex); if (count > 0) @@ -363,7 +361,7 @@ static int mmap(struct file *file, struct vm_area_struct *vma) if (!attr->mmap) goto out_put; - rc = attr->mmap(kobj, attr, vma); + rc = attr->mmap(file, kobj, attr, vma); if (rc) goto out_put; diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index 6903e9204032..f2694eb4dd3d 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -87,17 +87,18 @@ struct attribute_group { #define attr_name(_attr) (_attr).attr.name +struct file; struct vm_area_struct; struct bin_attribute { struct attribute attr; size_t size; void *private; - ssize_t (*read)(struct kobject *, struct bin_attribute *, + ssize_t (*read)(struct file *, struct kobject *, struct bin_attribute *, char *, loff_t, size_t); - ssize_t (*write)(struct kobject *, struct bin_attribute *, + ssize_t (*write)(struct file *,struct kobject *, struct bin_attribute *, char *, loff_t, size_t); - int (*mmap)(struct kobject *, struct bin_attribute *attr, + int (*mmap)(struct file *, struct kobject *, struct bin_attribute *attr, struct vm_area_struct *vma); }; diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c index 21fe3c426948..0b624e791805 100644 --- a/kernel/ksysfs.c +++ b/kernel/ksysfs.c @@ -138,7 +138,8 @@ extern const void __start_notes __attribute__((weak)); extern const void __stop_notes __attribute__((weak)); #define notes_size (&__stop_notes - &__start_notes) -static ssize_t notes_read(struct kobject *kobj, struct bin_attribute *bin_attr, +static ssize_t notes_read(struct file *filp, struct kobject *kobj, + struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { memcpy(buf, &__start_notes + off, count); diff --git a/kernel/module.c b/kernel/module.c index e2564580f3f1..5e14483768bb 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1182,7 +1182,7 @@ struct module_notes_attrs { struct bin_attribute attrs[0]; }; -static ssize_t module_notes_read(struct kobject *kobj, +static ssize_t module_notes_read(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t pos, size_t count) { diff --git a/net/bridge/br_sysfs_br.c b/net/bridge/br_sysfs_br.c index dd321e39e621..486b8f3861d2 100644 --- a/net/bridge/br_sysfs_br.c +++ b/net/bridge/br_sysfs_br.c @@ -659,7 +659,7 @@ static struct attribute_group bridge_group = { * * Returns the number of bytes read. */ -static ssize_t brforward_read(struct kobject *kobj, +static ssize_t brforward_read(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { -- cgit v1.3-8-gc7d7 From 7d52669b14e36f8365070324be009486d387ad00 Mon Sep 17 00:00:00 2001 From: Wenji Huang Date: Mon, 24 May 2010 14:33:12 -0700 Subject: module: remove duplicate declaration of __ksymtab_gpl_future Minor cleanup on duplicate __{start/stop}__ksymtab_gpl_future. Signed-off-by: Wenji Huang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/module.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'kernel/module.c') diff --git a/kernel/module.c b/kernel/module.c index a8014bfb5a4e..625985e70e9d 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -180,8 +180,6 @@ extern const struct kernel_symbol __start___ksymtab_gpl[]; extern const struct kernel_symbol __stop___ksymtab_gpl[]; extern const struct kernel_symbol __start___ksymtab_gpl_future[]; extern const struct kernel_symbol __stop___ksymtab_gpl_future[]; -extern const struct kernel_symbol __start___ksymtab_gpl_future[]; -extern const struct kernel_symbol __stop___ksymtab_gpl_future[]; extern const unsigned long __start___kcrctab[]; extern const unsigned long __start___kcrctab_gpl[]; extern const unsigned long __start___kcrctab_gpl_future[]; -- cgit v1.3-8-gc7d7 From 218ce7351413b8287a80fab1d7b94906a5559f01 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 25 May 2010 16:48:30 -0700 Subject: Revert "module: drop the lock while waiting for module to complete initialization." This reverts commit 480b02df3aa9f07d1c7df0cd8be7a5ca73893455, since Rafael reports that it causes occasional kernel paging request faults in load_module(). Dropping the module lock and re-taking it deep in the call-chain is definitely not the right thing to do. That just turns the mutex from a lock into a "random non-locking data structure" that doesn't actually protect what it's supposed to protect. Requested-and-tested-by: Rafael J. Wysocki Cc: Rusty Russell Cc: Brandon Philips Cc: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/module.c | 59 +++++++++++++++++++++------------------------------------ 1 file changed, 22 insertions(+), 37 deletions(-) (limited to 'kernel/module.c') diff --git a/kernel/module.c b/kernel/module.c index 625985e70e9d..333fbcc96978 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -563,26 +563,33 @@ int use_module(struct module *a, struct module *b) struct module_use *use; int no_warn, err; - if (b == NULL || already_uses(a, b)) - return 0; + if (b == NULL || already_uses(a, b)) return 1; /* If we're interrupted or time out, we fail. */ - err = strong_try_module_get(b); + if (wait_event_interruptible_timeout( + module_wq, (err = strong_try_module_get(b)) != -EBUSY, + 30 * HZ) <= 0) { + printk("%s: gave up waiting for init of module %s.\n", + a->name, b->name); + return 0; + } + + /* If strong_try_module_get() returned a different error, we fail. */ if (err) - return err; + return 0; DEBUGP("Allocating new usage for %s.\n", a->name); use = kmalloc(sizeof(*use), GFP_ATOMIC); if (!use) { printk("%s: out of memory loading\n", a->name); module_put(b); - return -ENOMEM; + return 0; } use->module_which_uses = a; list_add(&use->list, &b->modules_which_use_me); no_warn = sysfs_create_link(b->holders_dir, &a->mkobj.kobj, a->name); - return 0; + return 1; } EXPORT_SYMBOL_GPL(use_module); @@ -875,7 +882,7 @@ static inline void module_unload_free(struct module *mod) int use_module(struct module *a, struct module *b) { - return strong_try_module_get(b); + return strong_try_module_get(b) == 0; } EXPORT_SYMBOL_GPL(use_module); @@ -1046,39 +1053,17 @@ static const struct kernel_symbol *resolve_symbol(Elf_Shdr *sechdrs, struct module *owner; const struct kernel_symbol *sym; const unsigned long *crc; - DEFINE_WAIT(wait); - int err; - long timeleft = 30 * HZ; -again: sym = find_symbol(name, &owner, &crc, !(mod->taints & (1 << TAINT_PROPRIETARY_MODULE)), true); - if (!sym) - return NULL; - - if (!check_version(sechdrs, versindex, name, mod, crc, owner)) - return NULL; - - prepare_to_wait(&module_wq, &wait, TASK_INTERRUPTIBLE); - err = use_module(mod, owner); - if (likely(!err) || err != -EBUSY || signal_pending(current)) { - finish_wait(&module_wq, &wait); - return err ? NULL : sym; - } - - /* Module is still loading. Drop lock and wait. */ - mutex_unlock(&module_mutex); - timeleft = schedule_timeout(timeleft); - mutex_lock(&module_mutex); - finish_wait(&module_wq, &wait); - - /* Module might be gone entirely, or replaced. Re-lookup. */ - if (timeleft) - goto again; - - printk(KERN_WARNING "%s: gave up waiting for init of module %s.\n", - mod->name, owner->name); - return NULL; + /* use_module can fail due to OOM, + or module initialization or unloading */ + if (sym) { + if (!check_version(sechdrs, versindex, name, mod, crc, owner) + || !use_module(mod, owner)) + sym = NULL; + } + return sym; } /* -- cgit v1.3-8-gc7d7 From 293a7cfeedc2b2380a7c7274902323c3cf5f7575 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Mon, 31 May 2010 19:53:50 +0930 Subject: module: fix reference to mod->percpu after freeing module. Rafael sees a sometimes crash at precpu_modfree from kernel/module.c; it only occurred with another (since-reverted) patch, but that patch simply changed timing to uncover this bug, it was otherwise unrelated. The comment about the mod being freed is self-explanatory, but neither Tejun nor I read it. This bug was introduced in 259354deaa, after it had previously been fixed in 6e2b75740b. How embarrassing. Reported-by: "Rafael J. Wysocki" Signed-off-by: Rusty Russell Embarrassingly-Acked-by: Tejun Heo Cc: Masami Hiramatsu Tested-by: "Rafael J. Wysocki" Signed-off-by: Linus Torvalds --- kernel/module.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'kernel/module.c') diff --git a/kernel/module.c b/kernel/module.c index 333fbcc96978..d806e00e4450 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -2014,6 +2014,7 @@ static noinline struct module *load_module(void __user *umod, long err = 0; void *ptr = NULL; /* Stops spurious gcc warning */ unsigned long symoffs, stroffs, *strmap; + void __percpu *percpu; mm_segment_t old_fs; @@ -2158,6 +2159,8 @@ static noinline struct module *load_module(void __user *umod, goto free_mod; sechdrs[pcpuindex].sh_flags &= ~(unsigned long)SHF_ALLOC; } + /* Keep this around for failure path. */ + percpu = mod_percpu(mod); /* Determine total sizes, and put offsets in sh_entsize. For now this is done generically; there doesn't appear to be any @@ -2463,7 +2466,7 @@ static noinline struct module *load_module(void __user *umod, module_free(mod, mod->module_core); /* mod will be freed with core. Don't access it beyond this line! */ free_percpu: - percpu_modfree(mod); + free_percpu(percpu); free_mod: kfree(args); kfree(strmap); -- cgit v1.3-8-gc7d7 From 2c02dfe7fe3fba97a5665d329d039d2415ea5607 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 31 May 2010 12:19:37 -0700 Subject: module: Make the 'usage' lists be two-way When adding a module that depends on another one, we used to create a one-way list of "modules_which_use_me", so that module unloading could see who needs a module. It's actually quite simple to make that list go both ways: so that we not only can see "who uses me", but also see a list of modules that are "used by me". In fact, we always wanted that list in "module_unload_free()": when we unload a module, we want to also release all the other modules that are used by that module. But because we didn't have that list, we used to first iterate over all modules, and then iterate over each "used by me" list of that module. By making the list two-way, we simplify module_unload_free(), and it allows for some trivial fixes later too. Signed-off-by: Linus Torvalds Signed-off-by: Rusty Russell (cleaned & rebased) --- include/linux/module.h | 4 ++- kernel/module.c | 79 ++++++++++++++++++++++++++++++-------------------- 2 files changed, 51 insertions(+), 32 deletions(-) (limited to 'kernel/module.c') diff --git a/include/linux/module.h b/include/linux/module.h index 6914fcad4673..680db9e2ac36 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -359,7 +359,9 @@ struct module #ifdef CONFIG_MODULE_UNLOAD /* What modules depend on me? */ - struct list_head modules_which_use_me; + struct list_head source_list; + /* What modules do I depend on? */ + struct list_head target_list; /* Who is waiting for us to be unloaded */ struct task_struct *waiter; diff --git a/kernel/module.c b/kernel/module.c index 0129769301e3..be18c3e34684 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -523,7 +523,8 @@ static void module_unload_init(struct module *mod) { int cpu; - INIT_LIST_HEAD(&mod->modules_which_use_me); + INIT_LIST_HEAD(&mod->source_list); + INIT_LIST_HEAD(&mod->target_list); for_each_possible_cpu(cpu) { per_cpu_ptr(mod->refptr, cpu)->incs = 0; per_cpu_ptr(mod->refptr, cpu)->decs = 0; @@ -538,8 +539,9 @@ static void module_unload_init(struct module *mod) /* modules using other modules */ struct module_use { - struct list_head list; - struct module *module_which_uses; + struct list_head source_list; + struct list_head target_list; + struct module *source, *target; }; /* Does a already use b? */ @@ -547,8 +549,8 @@ static int already_uses(struct module *a, struct module *b) { struct module_use *use; - list_for_each_entry(use, &b->modules_which_use_me, list) { - if (use->module_which_uses == a) { + list_for_each_entry(use, &b->source_list, source_list) { + if (use->source == a) { DEBUGP("%s uses %s!\n", a->name, b->name); return 1; } @@ -557,6 +559,33 @@ static int already_uses(struct module *a, struct module *b) return 0; } +/* + * Module a uses b + * - we add 'a' as a "source", 'b' as a "target" of module use + * - the module_use is added to the list of 'b' sources (so + * 'b' can walk the list to see who sourced them), and of 'a' + * targets (so 'a' can see what modules it targets). + */ +static int add_module_usage(struct module *a, struct module *b) +{ + int no_warn; + struct module_use *use; + + DEBUGP("Allocating new usage for %s.\n", a->name); + use = kmalloc(sizeof(*use), GFP_ATOMIC); + if (!use) { + printk(KERN_WARNING "%s: out of memory loading\n", a->name); + return -ENOMEM; + } + + use->source = a; + use->target = b; + list_add(&use->source_list, &b->source_list); + list_add(&use->target_list, &a->target_list); + no_warn = sysfs_create_link(b->holders_dir, &a->mkobj.kobj, a->name); + return 0; +} + /* Module a uses b */ int use_module(struct module *a, struct module *b) { @@ -578,17 +607,11 @@ int use_module(struct module *a, struct module *b) if (err) return 0; - DEBUGP("Allocating new usage for %s.\n", a->name); - use = kmalloc(sizeof(*use), GFP_ATOMIC); - if (!use) { - printk("%s: out of memory loading\n", a->name); + err = add_module_usage(a, b); + if (err) { module_put(b); return 0; } - - use->module_which_uses = a; - list_add(&use->list, &b->modules_which_use_me); - no_warn = sysfs_create_link(b->holders_dir, &a->mkobj.kobj, a->name); return 1; } EXPORT_SYMBOL_GPL(use_module); @@ -596,22 +619,16 @@ EXPORT_SYMBOL_GPL(use_module); /* Clear the unload stuff of the module. */ static void module_unload_free(struct module *mod) { - struct module *i; - - list_for_each_entry(i, &modules, list) { - struct module_use *use; + struct module_use *use, *tmp; - list_for_each_entry(use, &i->modules_which_use_me, list) { - if (use->module_which_uses == mod) { - DEBUGP("%s unusing %s\n", mod->name, i->name); - module_put(i); - list_del(&use->list); - kfree(use); - sysfs_remove_link(i->holders_dir, mod->name); - /* There can be at most one match. */ - break; - } - } + list_for_each_entry_safe(use, tmp, &mod->target_list, target_list) { + struct module *i = use->target; + DEBUGP("%s unusing %s\n", mod->name, i->name); + module_put(i); + list_del(&use->source_list); + list_del(&use->target_list); + kfree(use); + sysfs_remove_link(i->holders_dir, mod->name); } } @@ -735,7 +752,7 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user, goto out; } - if (!list_empty(&mod->modules_which_use_me)) { + if (!list_empty(&mod->source_list)) { /* Other modules depend on us: get rid of them first. */ ret = -EWOULDBLOCK; goto out; @@ -799,9 +816,9 @@ static inline void print_unload_info(struct seq_file *m, struct module *mod) /* Always include a trailing , so userspace can differentiate between this and the old multi-field proc format. */ - list_for_each_entry(use, &mod->modules_which_use_me, list) { + list_for_each_entry(use, &mod->source_list, source_list) { printed_something = 1; - seq_printf(m, "%s,", use->module_which_uses->name); + seq_printf(m, "%s,", use->source->name); } if (mod->init != NULL && mod->exit == NULL) { -- cgit v1.3-8-gc7d7 From c8e21ced08b39ef8dfe7236fb2a923a95f645262 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Sat, 5 Jun 2010 11:17:35 -0600 Subject: module: fix kdb's illicit use of struct module_use. Linus changed the structure, and luckily this didn't compile any more. Reported-by: Stephen Rothwell Signed-off-by: Rusty Russell Cc: Jason Wessel Cc: Martin Hicks --- include/linux/module.h | 7 +++++++ kernel/debug/kdb/kdb_main.c | 12 +++--------- kernel/module.c | 11 +---------- 3 files changed, 11 insertions(+), 19 deletions(-) (limited to 'kernel/module.c') diff --git a/include/linux/module.h b/include/linux/module.h index 680db9e2ac36..5d8fca5dcff5 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -181,6 +181,13 @@ void *__symbol_get(const char *symbol); void *__symbol_get_gpl(const char *symbol); #define symbol_get(x) ((typeof(&x))(__symbol_get(MODULE_SYMBOL_PREFIX #x))) +/* modules using other modules: kdb wants to see this. */ +struct module_use { + struct list_head source_list; + struct list_head target_list; + struct module *source, *target; +}; + #ifndef __GENKSYMS__ #ifdef CONFIG_MODVERSIONS /* Mark the CRC weak since genksyms apparently decides not to diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index b724c791b6d4..184cd8209c36 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -1857,12 +1857,6 @@ static int kdb_ef(int argc, const char **argv) } #if defined(CONFIG_MODULES) -/* modules using other modules */ -struct module_use { - struct list_head list; - struct module *module_which_uses; -}; - /* * kdb_lsmod - This function implements the 'lsmod' command. Lists * currently loaded kernel modules. @@ -1894,9 +1888,9 @@ static int kdb_lsmod(int argc, const char **argv) { struct module_use *use; kdb_printf(" [ "); - list_for_each_entry(use, &mod->modules_which_use_me, - list) - kdb_printf("%s ", use->module_which_uses->name); + list_for_each_entry(use, &mod->source_list, + source_list) + kdb_printf("%s ", use->target->name); kdb_printf("]\n"); } #endif diff --git a/kernel/module.c b/kernel/module.c index be18c3e34684..bbb1d812c79c 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -536,14 +536,6 @@ static void module_unload_init(struct module *mod) mod->waiter = current; } -/* modules using other modules */ -struct module_use -{ - struct list_head source_list; - struct list_head target_list; - struct module *source, *target; -}; - /* Does a already use b? */ static int already_uses(struct module *a, struct module *b) { @@ -589,8 +581,7 @@ static int add_module_usage(struct module *a, struct module *b) /* Module a uses b */ int use_module(struct module *a, struct module *b) { - struct module_use *use; - int no_warn, err; + int err; if (b == NULL || already_uses(a, b)) return 1; -- cgit v1.3-8-gc7d7 From 80a3d1bb410e000e176931a076cdf19a1e89a955 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Sat, 5 Jun 2010 11:17:36 -0600 Subject: module: move sysfs exposure to end of load_module This means a little extra work, but is more logical: we don't put anything in sysfs until we're about to put the module into the global list an parse its parameters. This also gives us a logical place to put duplicate module detection in the next patch. Signed-off-by: Rusty Russell --- kernel/module.c | 47 ++++++++++++++++++++++++++++++++++++----------- 1 file changed, 36 insertions(+), 11 deletions(-) (limited to 'kernel/module.c') diff --git a/kernel/module.c b/kernel/module.c index bbb1d812c79c..c690d9885797 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -560,7 +560,6 @@ static int already_uses(struct module *a, struct module *b) */ static int add_module_usage(struct module *a, struct module *b) { - int no_warn; struct module_use *use; DEBUGP("Allocating new usage for %s.\n", a->name); @@ -574,7 +573,6 @@ static int add_module_usage(struct module *a, struct module *b) use->target = b; list_add(&use->source_list, &b->source_list); list_add(&use->target_list, &a->target_list); - no_warn = sysfs_create_link(b->holders_dir, &a->mkobj.kobj, a->name); return 0; } @@ -619,7 +617,6 @@ static void module_unload_free(struct module *mod) list_del(&use->source_list); list_del(&use->target_list); kfree(use); - sysfs_remove_link(i->holders_dir, mod->name); } } @@ -1303,6 +1300,29 @@ static inline void remove_notes_attrs(struct module *mod) #endif #ifdef CONFIG_SYSFS +static void add_usage_links(struct module *mod) +{ +#ifdef CONFIG_MODULE_UNLOAD + struct module_use *use; + int nowarn; + + list_for_each_entry(use, &mod->target_list, target_list) { + nowarn = sysfs_create_link(use->target->holders_dir, + &mod->mkobj.kobj, mod->name); + } +#endif +} + +static void del_usage_links(struct module *mod) +{ +#ifdef CONFIG_MODULE_UNLOAD + struct module_use *use; + + list_for_each_entry(use, &mod->target_list, target_list) + sysfs_remove_link(use->target->holders_dir, mod->name); +#endif +} + int module_add_modinfo_attrs(struct module *mod) { struct module_attribute *attr; @@ -1385,6 +1405,10 @@ int mod_sysfs_setup(struct module *mod, { int err; + err = mod_sysfs_init(mod); + if (err) + goto out; + mod->holders_dir = kobject_create_and_add("holders", &mod->mkobj.kobj); if (!mod->holders_dir) { err = -ENOMEM; @@ -1399,6 +1423,8 @@ int mod_sysfs_setup(struct module *mod, if (err) goto out_unreg_param; + add_usage_links(mod); + kobject_uevent(&mod->mkobj.kobj, KOBJ_ADD); return 0; @@ -1408,6 +1434,7 @@ out_unreg_holders: kobject_put(mod->holders_dir); out_unreg: kobject_put(&mod->mkobj.kobj); +out: return err; } @@ -1422,10 +1449,15 @@ static void mod_sysfs_fini(struct module *mod) { } +static void del_usage_links(struct module *mod) +{ +} + #endif /* CONFIG_SYSFS */ static void mod_kobject_remove(struct module *mod) { + del_usage_links(mod); module_remove_modinfo_attrs(mod); module_param_sysfs_remove(mod); kobject_put(mod->mkobj.drivers_dir); @@ -2242,11 +2274,6 @@ static noinline struct module *load_module(void __user *umod, /* Now we've moved module, initialize linked lists, etc. */ module_unload_init(mod); - /* add kobject, so we can reference it. */ - err = mod_sysfs_init(mod); - if (err) - goto free_unload; - /* Set up license info based on the info section */ set_license(mod, get_modinfo(sechdrs, infoindex, "license")); @@ -2443,6 +2470,7 @@ static noinline struct module *load_module(void __user *umod, err = mod_sysfs_setup(mod, mod->kp, mod->num_kp); if (err < 0) goto unlink; + add_sect_attrs(mod, hdr->e_shnum, secstrings, sechdrs); add_notes_attrs(mod, hdr->e_shnum, secstrings, sechdrs); @@ -2461,9 +2489,6 @@ static noinline struct module *load_module(void __user *umod, module_arch_cleanup(mod); cleanup: free_modinfo(mod); - kobject_del(&mod->mkobj.kobj); - kobject_put(&mod->mkobj.kobj); - free_unload: module_unload_free(mod); #if defined(CONFIG_MODULE_UNLOAD) free_percpu(mod->refptr); -- cgit v1.3-8-gc7d7 From 6407ebb271fc34440b306f305e1efb7685eece26 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Sat, 5 Jun 2010 11:17:36 -0600 Subject: module: Make module sysfs functions private. These were placed in the header in ef665c1a06 to get the various SYSFS/MODULE config combintations to compile. That may have been necessary then, but it's not now. These functions are all local to module.c. Signed-off-by: Rusty Russell Cc: Randy Dunlap --- include/linux/module.h | 33 --------------------------------- kernel/module.c | 29 +++++++++++++++++++++++++---- 2 files changed, 25 insertions(+), 37 deletions(-) (limited to 'kernel/module.c') diff --git a/include/linux/module.h b/include/linux/module.h index 5d8fca5dcff5..8a6b9fdc7ffa 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -672,43 +672,10 @@ static inline int module_get_iter_tracepoints(struct tracepoint_iter *iter) #endif /* CONFIG_MODULES */ -struct device_driver; #ifdef CONFIG_SYSFS -struct module; - extern struct kset *module_kset; extern struct kobj_type module_ktype; extern int module_sysfs_initialized; - -int mod_sysfs_init(struct module *mod); -int mod_sysfs_setup(struct module *mod, - struct kernel_param *kparam, - unsigned int num_params); -int module_add_modinfo_attrs(struct module *mod); -void module_remove_modinfo_attrs(struct module *mod); - -#else /* !CONFIG_SYSFS */ - -static inline int mod_sysfs_init(struct module *mod) -{ - return 0; -} - -static inline int mod_sysfs_setup(struct module *mod, - struct kernel_param *kparam, - unsigned int num_params) -{ - return 0; -} - -static inline int module_add_modinfo_attrs(struct module *mod) -{ - return 0; -} - -static inline void module_remove_modinfo_attrs(struct module *mod) -{ } - #endif /* CONFIG_SYSFS */ #define symbol_request(x) try_then_request_module(symbol_get(x), "symbol:" #x) diff --git a/kernel/module.c b/kernel/module.c index c690d9885797..808aa18dd661 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1323,7 +1323,7 @@ static void del_usage_links(struct module *mod) #endif } -int module_add_modinfo_attrs(struct module *mod) +static int module_add_modinfo_attrs(struct module *mod) { struct module_attribute *attr; struct module_attribute *temp_attr; @@ -1349,7 +1349,7 @@ int module_add_modinfo_attrs(struct module *mod) return error; } -void module_remove_modinfo_attrs(struct module *mod) +static void module_remove_modinfo_attrs(struct module *mod) { struct module_attribute *attr; int i; @@ -1365,7 +1365,7 @@ void module_remove_modinfo_attrs(struct module *mod) kfree(mod->modinfo_attrs); } -int mod_sysfs_init(struct module *mod) +static int mod_sysfs_init(struct module *mod) { int err; struct kobject *kobj; @@ -1399,7 +1399,7 @@ out: return err; } -int mod_sysfs_setup(struct module *mod, +static int mod_sysfs_setup(struct module *mod, struct kernel_param *kparam, unsigned int num_params) { @@ -1445,6 +1445,27 @@ static void mod_sysfs_fini(struct module *mod) #else /* CONFIG_SYSFS */ +static inline int mod_sysfs_init(struct module *mod) +{ + return 0; +} + +static inline int mod_sysfs_setup(struct module *mod, + struct kernel_param *kparam, + unsigned int num_params) +{ + return 0; +} + +static inline int module_add_modinfo_attrs(struct module *mod) +{ + return 0; +} + +static inline void module_remove_modinfo_attrs(struct module *mod) +{ +} + static void mod_sysfs_fini(struct module *mod) { } -- cgit v1.3-8-gc7d7 From 75676500f8298f0ee89db12db97294883c4b768e Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Sat, 5 Jun 2010 11:17:36 -0600 Subject: module: make locking more fine-grained. Kay Sievers reports that we still have some contention over module loading which is slowing boot. Linus also disliked a previous "drop lock and regrab" patch to fix the bne2 "gave up waiting for init of module libcrc32c" message. This is more ambitious: we only grab the lock where we need it. Signed-off-by: Rusty Russell Cc: Brandon Philips Cc: Kay Sievers Cc: Linus Torvalds --- kernel/module.c | 65 +++++++++++++++++++++++++++++++++++++-------------------- 1 file changed, 42 insertions(+), 23 deletions(-) (limited to 'kernel/module.c') diff --git a/kernel/module.c b/kernel/module.c index 808aa18dd661..d293c213c22c 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -72,7 +72,11 @@ /* If this is set, the section belongs in the init part of the module */ #define INIT_OFFSET_MASK (1UL << (BITS_PER_LONG-1)) -/* List of modules, protected by module_mutex or preempt_disable +/* + * Mutex protects: + * 1) List of modules (also safely readable with preempt_disable), + * 2) module_use links, + * 3) module_addr_min/module_addr_max. * (delete uses stop_machine/add uses RCU list operations). */ DEFINE_MUTEX(module_mutex); EXPORT_SYMBOL_GPL(module_mutex); @@ -90,7 +94,8 @@ static DECLARE_WAIT_QUEUE_HEAD(module_wq); static BLOCKING_NOTIFIER_HEAD(module_notify_list); -/* Bounds of module allocation, for speeding __module_address */ +/* Bounds of module allocation, for speeding __module_address. + * Protected by module_mutex. */ static unsigned long module_addr_min = -1UL, module_addr_max = 0; int register_module_notifier(struct notifier_block * nb) @@ -329,7 +334,7 @@ static bool find_symbol_in_section(const struct symsearch *syms, } /* Find a symbol and return it, along with, (optional) crc and - * (optional) module which owns it */ + * (optional) module which owns it. Needs preempt disabled or module_mutex. */ const struct kernel_symbol *find_symbol(const char *name, struct module **owner, const unsigned long **crc, @@ -576,7 +581,7 @@ static int add_module_usage(struct module *a, struct module *b) return 0; } -/* Module a uses b */ +/* Module a uses b: caller needs module_mutex() */ int use_module(struct module *a, struct module *b) { int err; @@ -610,6 +615,7 @@ static void module_unload_free(struct module *mod) { struct module_use *use, *tmp; + mutex_lock(&module_mutex); list_for_each_entry_safe(use, tmp, &mod->target_list, target_list) { struct module *i = use->target; DEBUGP("%s unusing %s\n", mod->name, i->name); @@ -618,6 +624,7 @@ static void module_unload_free(struct module *mod) list_del(&use->target_list); kfree(use); } + mutex_unlock(&module_mutex); } #ifdef CONFIG_MODULE_FORCE_UNLOAD @@ -784,13 +791,14 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user, blocking_notifier_call_chain(&module_notify_list, MODULE_STATE_GOING, mod); async_synchronize_full(); - mutex_lock(&module_mutex); + /* Store the name of the last unloaded module for diagnostic purposes */ strlcpy(last_unloaded_module, mod->name, sizeof(last_unloaded_module)); ddebug_remove_module(mod->name); - free_module(mod); - out: + free_module(mod); + return 0; +out: mutex_unlock(&module_mutex); return ret; } @@ -1006,6 +1014,8 @@ static inline int check_modstruct_version(Elf_Shdr *sechdrs, { const unsigned long *crc; + /* Since this should be found in kernel (which can't be removed), + * no locking is necessary. */ if (!find_symbol(MODULE_SYMBOL_PREFIX "module_layout", NULL, &crc, true, false)) BUG(); @@ -1048,8 +1058,7 @@ static inline int same_magic(const char *amagic, const char *bmagic, } #endif /* CONFIG_MODVERSIONS */ -/* Resolve a symbol for this module. I.e. if we find one, record usage. - Must be holding module_mutex. */ +/* Resolve a symbol for this module. I.e. if we find one, record usage. */ static const struct kernel_symbol *resolve_symbol(Elf_Shdr *sechdrs, unsigned int versindex, const char *name, @@ -1059,6 +1068,7 @@ static const struct kernel_symbol *resolve_symbol(Elf_Shdr *sechdrs, const struct kernel_symbol *sym; const unsigned long *crc; + mutex_lock(&module_mutex); sym = find_symbol(name, &owner, &crc, !(mod->taints & (1 << TAINT_PROPRIETARY_MODULE)), true); /* use_module can fail due to OOM, @@ -1068,6 +1078,7 @@ static const struct kernel_symbol *resolve_symbol(Elf_Shdr *sechdrs, || !use_module(mod, owner)) sym = NULL; } + mutex_unlock(&module_mutex); return sym; } @@ -1306,10 +1317,12 @@ static void add_usage_links(struct module *mod) struct module_use *use; int nowarn; + mutex_lock(&module_mutex); list_for_each_entry(use, &mod->target_list, target_list) { nowarn = sysfs_create_link(use->target->holders_dir, &mod->mkobj.kobj, mod->name); } + mutex_unlock(&module_mutex); #endif } @@ -1318,8 +1331,10 @@ static void del_usage_links(struct module *mod) #ifdef CONFIG_MODULE_UNLOAD struct module_use *use; + mutex_lock(&module_mutex); list_for_each_entry(use, &mod->target_list, target_list) sysfs_remove_link(use->target->holders_dir, mod->name); + mutex_unlock(&module_mutex); #endif } @@ -1497,13 +1512,15 @@ static int __unlink_module(void *_mod) return 0; } -/* Free a module, remove from lists, etc (must hold module_mutex). */ +/* Free a module, remove from lists, etc. */ static void free_module(struct module *mod) { trace_module_free(mod); /* Delete from various lists */ + mutex_lock(&module_mutex); stop_machine(__unlink_module, mod, NULL); + mutex_unlock(&module_mutex); remove_notes_attrs(mod); remove_sect_attrs(mod); mod_kobject_remove(mod); @@ -1575,7 +1592,14 @@ static int verify_export_symbols(struct module *mod) for (i = 0; i < ARRAY_SIZE(arr); i++) { for (s = arr[i].sym; s < arr[i].sym + arr[i].num; s++) { - if (find_symbol(s->name, &owner, NULL, true, false)) { + const struct kernel_symbol *sym; + + /* Stopping preemption makes find_symbol safe. */ + preempt_disable(); + sym = find_symbol(s->name, &owner, NULL, true, false); + preempt_enable(); + + if (sym) { printk(KERN_ERR "%s: exports duplicate symbol %s" " (owned by %s)\n", @@ -2021,11 +2045,13 @@ static void *module_alloc_update_bounds(unsigned long size) void *ret = module_alloc(size); if (ret) { + mutex_lock(&module_mutex); /* Update module bounds. */ if ((unsigned long)ret < module_addr_min) module_addr_min = (unsigned long)ret; if ((unsigned long)ret + size > module_addr_max) module_addr_max = (unsigned long)ret + size; + mutex_unlock(&module_mutex); } return ret; } @@ -2482,7 +2508,9 @@ static noinline struct module *load_module(void __user *umod, * function to insert in a way safe to concurrent readers. * The mutex protects against concurrent writers. */ + mutex_lock(&module_mutex); list_add_rcu(&mod->list, &modules); + mutex_unlock(&module_mutex); err = parse_args(mod->name, mod->args, mod->kp, mod->num_kp, NULL); if (err < 0) @@ -2504,8 +2532,10 @@ static noinline struct module *load_module(void __user *umod, return mod; unlink: + mutex_lock(&module_mutex); /* Unlink carefully: kallsyms could be walking list. */ list_del_rcu(&mod->list); + mutex_unlock(&module_mutex); synchronize_sched(); module_arch_cleanup(mod); cleanup: @@ -2556,19 +2586,10 @@ SYSCALL_DEFINE3(init_module, void __user *, umod, if (!capable(CAP_SYS_MODULE) || modules_disabled) return -EPERM; - /* Only one module load at a time, please */ - if (mutex_lock_interruptible(&module_mutex) != 0) - return -EINTR; - /* Do all the hard work */ mod = load_module(umod, len, uargs); - if (IS_ERR(mod)) { - mutex_unlock(&module_mutex); + if (IS_ERR(mod)) return PTR_ERR(mod); - } - - /* Drop lock so they can recurse */ - mutex_unlock(&module_mutex); blocking_notifier_call_chain(&module_notify_list, MODULE_STATE_COMING, mod); @@ -2585,9 +2606,7 @@ SYSCALL_DEFINE3(init_module, void __user *, umod, module_put(mod); blocking_notifier_call_chain(&module_notify_list, MODULE_STATE_GOING, mod); - mutex_lock(&module_mutex); free_module(mod); - mutex_unlock(&module_mutex); wake_up(&module_wq); return ret; } -- cgit v1.3-8-gc7d7 From 3bafeb6247042dcbb72b0141ec7c7107de9f0b99 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 5 Jun 2010 11:17:36 -0600 Subject: module: move find_module check to end I think Rusty may have made the lock a bit _too_ finegrained there, and didn't add it to some places that needed it. It looks, for example, like PATCH 1/2 actually drops the lock in places where it's needed ("find_module()" is documented to need it, but now load_module() didn't hold it at all when it did the find_module()). Rather than adding a new "module_loading" list, I think we should be able to just use the existing "modules" list, and just fix up the locking a bit. In fact, maybe we could just move the "look up existing module" a bit later - optimistically assuming that the module doesn't exist, and then just undoing the work if it turns out that we were wrong, just before adding ourselves to the list. Signed-off-by: Rusty Russell --- kernel/module.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) (limited to 'kernel/module.c') diff --git a/kernel/module.c b/kernel/module.c index d293c213c22c..28450047852a 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -2226,11 +2226,6 @@ static noinline struct module *load_module(void __user *umod, goto free_mod; } - if (find_module(mod->name)) { - err = -EEXIST; - goto free_mod; - } - mod->state = MODULE_STATE_COMING; /* Allow arches to frob section contents and sizes. */ @@ -2509,6 +2504,12 @@ static noinline struct module *load_module(void __user *umod, * The mutex protects against concurrent writers. */ mutex_lock(&module_mutex); + if (find_module(mod->name)) { + err = -EEXIST; + /* This will also unlock the mutex */ + goto already_exists; + } + list_add_rcu(&mod->list, &modules); mutex_unlock(&module_mutex); @@ -2535,6 +2536,7 @@ static noinline struct module *load_module(void __user *umod, mutex_lock(&module_mutex); /* Unlink carefully: kallsyms could be walking list. */ list_del_rcu(&mod->list); + already_exists: mutex_unlock(&module_mutex); synchronize_sched(); module_arch_cleanup(mod); -- cgit v1.3-8-gc7d7 From be593f4ce4eb1bd40e38fdc403371f149f6f12eb Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Sat, 5 Jun 2010 11:17:37 -0600 Subject: module: verify_export_symbols under the lock It disabled preempt so it was "safe", but nothing stops another module slipping in before this module is added to the global list now we don't hold the lock the whole time. So we check this just after we check for duplicate modules, and just before we put the module in the global list. (find_symbol finds symbols in coming and going modules, too). Signed-off-by: Rusty Russell --- kernel/module.c | 26 ++++++++++---------------- 1 file changed, 10 insertions(+), 16 deletions(-) (limited to 'kernel/module.c') diff --git a/kernel/module.c b/kernel/module.c index 28450047852a..f99558e1945a 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1571,6 +1571,8 @@ EXPORT_SYMBOL_GPL(__symbol_get); /* * Ensure that an exported symbol [global namespace] does not already exist * in the kernel or in some other module's exported symbol table. + * + * You must hold the module_mutex. */ static int verify_export_symbols(struct module *mod) { @@ -1592,14 +1594,7 @@ static int verify_export_symbols(struct module *mod) for (i = 0; i < ARRAY_SIZE(arr); i++) { for (s = arr[i].sym; s < arr[i].sym + arr[i].num; s++) { - const struct kernel_symbol *sym; - - /* Stopping preemption makes find_symbol safe. */ - preempt_disable(); - sym = find_symbol(s->name, &owner, NULL, true, false); - preempt_enable(); - - if (sym) { + if (find_symbol(s->name, &owner, NULL, true, false)) { printk(KERN_ERR "%s: exports duplicate symbol %s" " (owned by %s)\n", @@ -2440,11 +2435,6 @@ static noinline struct module *load_module(void __user *umod, goto cleanup; } - /* Find duplicate symbols */ - err = verify_export_symbols(mod); - if (err < 0) - goto cleanup; - /* Set up and sort exception table */ mod->extable = section_objs(hdr, sechdrs, secstrings, "__ex_table", sizeof(*mod->extable), &mod->num_exentries); @@ -2506,10 +2496,14 @@ static noinline struct module *load_module(void __user *umod, mutex_lock(&module_mutex); if (find_module(mod->name)) { err = -EEXIST; - /* This will also unlock the mutex */ - goto already_exists; + goto unlock; } + /* Find duplicate symbols */ + err = verify_export_symbols(mod); + if (err < 0) + goto unlock; + list_add_rcu(&mod->list, &modules); mutex_unlock(&module_mutex); @@ -2536,7 +2530,7 @@ static noinline struct module *load_module(void __user *umod, mutex_lock(&module_mutex); /* Unlink carefully: kallsyms could be walking list. */ list_del_rcu(&mod->list); - already_exists: + unlock: mutex_unlock(&module_mutex); synchronize_sched(); module_arch_cleanup(mod); -- cgit v1.3-8-gc7d7 From 9bea7f23952d5948f8e5dfdff4de09bb9981fb5f Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Sat, 5 Jun 2010 11:17:37 -0600 Subject: module: fix bne2 "gave up waiting for init of module libcrc32c" Problem: it's hard to avoid an init routine stumbling over a request_module these days. And it's not clear it's always a bad idea: for example, a module like kvm with dynamic dependencies on kvm-intel or kvm-amd would be neater if it could simply request_module the right one. In this particular case, it's libcrc32c: libcrc32c_mod_init crypto_alloc_shash crypto_alloc_tfm crypto_find_alg crypto_alg_mod_lookup crypto_larval_lookup request_module If another module is waiting inside resolve_symbol() for libcrc32c to finish initializing (ie. bne2 depends on libcrc32c) then it does so holding the module lock, and our request_module() can't make progress until that is released. Waiting inside resolve_symbol() without the lock isn't all that hard: we just need to pass the -EBUSY up the call chain so we can sleep where we don't hold the lock. Error reporting is a bit trickier: we need to copy the name of the unfinished module before releasing the lock. Other notes: 1) This also fixes a theoretical issue where a weak dependency would allow symbol version mismatches to be ignored. 2) We rename use_module to ref_module to make life easier for the only external user (the out-of-tree ksplice patches). Signed-off-by: Rusty Russell Cc: Linus Torvalds Cc: Tim Abbot Tested-by: Brandon Philips --- kernel/module.c | 91 +++++++++++++++++++++++++++++++++++++-------------------- 1 file changed, 59 insertions(+), 32 deletions(-) (limited to 'kernel/module.c') diff --git a/kernel/module.c b/kernel/module.c index f99558e1945a..8c6b42840dd1 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -582,33 +582,26 @@ static int add_module_usage(struct module *a, struct module *b) } /* Module a uses b: caller needs module_mutex() */ -int use_module(struct module *a, struct module *b) +int ref_module(struct module *a, struct module *b) { int err; - if (b == NULL || already_uses(a, b)) return 1; - - /* If we're interrupted or time out, we fail. */ - if (wait_event_interruptible_timeout( - module_wq, (err = strong_try_module_get(b)) != -EBUSY, - 30 * HZ) <= 0) { - printk("%s: gave up waiting for init of module %s.\n", - a->name, b->name); + if (b == NULL || already_uses(a, b)) return 0; - } - /* If strong_try_module_get() returned a different error, we fail. */ + /* If module isn't available, we fail. */ + err = strong_try_module_get(b); if (err) - return 0; + return err; err = add_module_usage(a, b); if (err) { module_put(b); - return 0; + return err; } - return 1; + return 0; } -EXPORT_SYMBOL_GPL(use_module); +EXPORT_SYMBOL_GPL(ref_module); /* Clear the unload stuff of the module. */ static void module_unload_free(struct module *mod) @@ -893,11 +886,11 @@ static inline void module_unload_free(struct module *mod) { } -int use_module(struct module *a, struct module *b) +int ref_module(struct module *a, struct module *b) { - return strong_try_module_get(b) == 0; + return strong_try_module_get(b); } -EXPORT_SYMBOL_GPL(use_module); +EXPORT_SYMBOL_GPL(ref_module); static inline void module_unload_init(struct module *mod) { @@ -1062,26 +1055,58 @@ static inline int same_magic(const char *amagic, const char *bmagic, static const struct kernel_symbol *resolve_symbol(Elf_Shdr *sechdrs, unsigned int versindex, const char *name, - struct module *mod) + struct module *mod, + char ownername[]) { struct module *owner; const struct kernel_symbol *sym; const unsigned long *crc; + int err; mutex_lock(&module_mutex); sym = find_symbol(name, &owner, &crc, !(mod->taints & (1 << TAINT_PROPRIETARY_MODULE)), true); - /* use_module can fail due to OOM, - or module initialization or unloading */ - if (sym) { - if (!check_version(sechdrs, versindex, name, mod, crc, owner) - || !use_module(mod, owner)) - sym = NULL; + if (!sym) + goto unlock; + + if (!check_version(sechdrs, versindex, name, mod, crc, owner)) { + sym = ERR_PTR(-EINVAL); + goto getname; } + + err = ref_module(mod, owner); + if (err) { + sym = ERR_PTR(err); + goto getname; + } + +getname: + /* We must make copy under the lock if we failed to get ref. */ + strncpy(ownername, module_name(owner), MODULE_NAME_LEN); +unlock: mutex_unlock(&module_mutex); return sym; } +static const struct kernel_symbol *resolve_symbol_wait(Elf_Shdr *sechdrs, + unsigned int versindex, + const char *name, + struct module *mod) +{ + const struct kernel_symbol *ksym; + char ownername[MODULE_NAME_LEN]; + + if (wait_event_interruptible_timeout(module_wq, + !IS_ERR(ksym = resolve_symbol(sechdrs, versindex, name, + mod, ownername)) || + PTR_ERR(ksym) != -EBUSY, + 30 * HZ) <= 0) { + printk(KERN_WARNING "%s: gave up waiting for init of module %s.\n", + mod->name, ownername); + } + return ksym; +} + /* * /sys/module/foo/sections stuff * J. Corbet @@ -1638,21 +1663,23 @@ static int simplify_symbols(Elf_Shdr *sechdrs, break; case SHN_UNDEF: - ksym = resolve_symbol(sechdrs, versindex, - strtab + sym[i].st_name, mod); + ksym = resolve_symbol_wait(sechdrs, versindex, + strtab + sym[i].st_name, + mod); /* Ok if resolved. */ - if (ksym) { + if (ksym && !IS_ERR(ksym)) { sym[i].st_value = ksym->value; break; } /* Ok if weak. */ - if (ELF_ST_BIND(sym[i].st_info) == STB_WEAK) + if (!ksym && ELF_ST_BIND(sym[i].st_info) == STB_WEAK) break; - printk(KERN_WARNING "%s: Unknown symbol %s\n", - mod->name, strtab + sym[i].st_name); - ret = -ENOENT; + printk(KERN_WARNING "%s: Unknown symbol %s (err %li)\n", + mod->name, strtab + sym[i].st_name, + PTR_ERR(ksym)); + ret = PTR_ERR(ksym) ?: -ENOENT; break; default: -- cgit v1.3-8-gc7d7 From ff49d74ad383f54041378144ca1a229ee9aeaa59 Mon Sep 17 00:00:00 2001 From: Yehuda Sadeh Date: Sat, 3 Jul 2010 13:07:35 +1000 Subject: module: initialize module dynamic debug later We should initialize the module dynamic debug datastructures only after determining that the module is not loaded yet. This fixes a bug that introduced in 2.6.35-rc2, where when a trying to load a module twice, we also load it's dynamic printing data twice which causes all sorts of nasty issues. Also handle the dynamic debug cleanup later on failure. Signed-off-by: Yehuda Sadeh Signed-off-by: Rusty Russell (removed a #ifdef) Signed-off-by: Linus Torvalds --- include/linux/dynamic_debug.h | 4 ++-- kernel/module.c | 23 +++++++++++++++-------- lib/dynamic_debug.c | 2 +- 3 files changed, 18 insertions(+), 11 deletions(-) (limited to 'kernel/module.c') diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h index b3cd4de9432b..52c0da4bdd18 100644 --- a/include/linux/dynamic_debug.h +++ b/include/linux/dynamic_debug.h @@ -40,7 +40,7 @@ int ddebug_add_module(struct _ddebug *tab, unsigned int n, const char *modname); #if defined(CONFIG_DYNAMIC_DEBUG) -extern int ddebug_remove_module(char *mod_name); +extern int ddebug_remove_module(const char *mod_name); #define __dynamic_dbg_enabled(dd) ({ \ int __ret = 0; \ @@ -73,7 +73,7 @@ extern int ddebug_remove_module(char *mod_name); #else -static inline int ddebug_remove_module(char *mod) +static inline int ddebug_remove_module(const char *mod) { return 0; } diff --git a/kernel/module.c b/kernel/module.c index 8c6b42840dd1..5d2d28197c82 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -2062,6 +2062,12 @@ static void dynamic_debug_setup(struct _ddebug *debug, unsigned int num) #endif } +static void dynamic_debug_remove(struct _ddebug *debug) +{ + if (debug) + ddebug_remove_module(debug->modname); +} + static void *module_alloc_update_bounds(unsigned long size) { void *ret = module_alloc(size); @@ -2124,6 +2130,8 @@ static noinline struct module *load_module(void __user *umod, void *ptr = NULL; /* Stops spurious gcc warning */ unsigned long symoffs, stroffs, *strmap; void __percpu *percpu; + struct _ddebug *debug = NULL; + unsigned int num_debug = 0; mm_segment_t old_fs; @@ -2476,15 +2484,9 @@ static noinline struct module *load_module(void __user *umod, kfree(strmap); strmap = NULL; - if (!mod->taints) { - struct _ddebug *debug; - unsigned int num_debug; - + if (!mod->taints) debug = section_objs(hdr, sechdrs, secstrings, "__verbose", sizeof(*debug), &num_debug); - if (debug) - dynamic_debug_setup(debug, num_debug); - } err = module_finalize(hdr, sechdrs, mod); if (err < 0) @@ -2526,10 +2528,13 @@ static noinline struct module *load_module(void __user *umod, goto unlock; } + if (debug) + dynamic_debug_setup(debug, num_debug); + /* Find duplicate symbols */ err = verify_export_symbols(mod); if (err < 0) - goto unlock; + goto ddebug; list_add_rcu(&mod->list, &modules); mutex_unlock(&module_mutex); @@ -2557,6 +2562,8 @@ static noinline struct module *load_module(void __user *umod, mutex_lock(&module_mutex); /* Unlink carefully: kallsyms could be walking list. */ list_del_rcu(&mod->list); + ddebug: + dynamic_debug_remove(debug); unlock: mutex_unlock(&module_mutex); synchronize_sched(); diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c index 3df8eb17a607..02afc2533728 100644 --- a/lib/dynamic_debug.c +++ b/lib/dynamic_debug.c @@ -692,7 +692,7 @@ static void ddebug_table_free(struct ddebug_table *dt) * Called in response to a module being unloaded. Removes * any ddebug_table's which point at the module. */ -int ddebug_remove_module(char *mod_name) +int ddebug_remove_module(const char *mod_name) { struct ddebug_table *dt, *nextdt; int ret = -ENOENT; -- cgit v1.3-8-gc7d7 From b82bab4bbe9efa7bc7177fc20620fff19bd95484 Mon Sep 17 00:00:00 2001 From: Jason Baron Date: Tue, 27 Jul 2010 13:18:01 -0700 Subject: dynamic debug: move ddebug_remove_module() down into free_module() The command echo "file ec.c +p" >/sys/kernel/debug/dynamic_debug/control causes an oops. Move the call to ddebug_remove_module() down into free_module(). In this way it should be called from all error paths. Currently, we are missing the remove if the module init routine fails. Signed-off-by: Jason Baron Reported-by: Thomas Renninger Tested-by: Thomas Renninger Cc: [2.6.32+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/module.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'kernel/module.c') diff --git a/kernel/module.c b/kernel/module.c index 5d2d28197c82..6c562828c85c 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -787,7 +787,6 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user, /* Store the name of the last unloaded module for diagnostic purposes */ strlcpy(last_unloaded_module, mod->name, sizeof(last_unloaded_module)); - ddebug_remove_module(mod->name); free_module(mod); return 0; @@ -1550,6 +1549,9 @@ static void free_module(struct module *mod) remove_sect_attrs(mod); mod_kobject_remove(mod); + /* Remove dynamic debug info */ + ddebug_remove_module(mod->name); + /* Arch-specific cleanup. */ module_arch_cleanup(mod); -- cgit v1.3-8-gc7d7