From 3861a17bcc0af815f684c6178bc9ec2d790c350e Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Sun, 8 Feb 2009 00:04:02 +0100 Subject: tracing/function-graph-tracer: drop the kernel_text_address check When the function graph tracer picks a return address, it ensures this address is really a kernel text one by calling __kernel_text_address() Actually this path has never been taken.Its role was more likely to debug the tracer on the beginning of its development but this function is wasteful since it is called for every traced function. The fault check is already sufficient. Signed-off-by: Frederic Weisbecker Signed-off-by: Ingo Molnar --- kernel/module.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/module.c') diff --git a/kernel/module.c b/kernel/module.c index ba22484a987e..22d7379709da 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -2735,7 +2735,7 @@ int is_module_address(unsigned long addr) /* Is this a valid kernel address? */ -__notrace_funcgraph struct module *__module_text_address(unsigned long addr) +struct module *__module_text_address(unsigned long addr) { struct module *mod; -- cgit v1.2.3-71-gd317 From e9d376f0fa66bd630fe27403669c6ae6c22a868f Mon Sep 17 00:00:00 2001 From: Jason Baron Date: Thu, 5 Feb 2009 11:51:38 -0500 Subject: dynamic debug: combine dprintk and dynamic printk This patch combines Greg Bank's dprintk() work with the existing dynamic printk patchset, we are now calling it 'dynamic debug'. The new feature of this patchset is a richer /debugfs control file interface, (an example output from my system is at the bottom), which allows fined grained control over the the debug output. The output can be controlled by function, file, module, format string, and line number. for example, enabled all debug messages in module 'nf_conntrack': echo -n 'module nf_conntrack +p' > /mnt/debugfs/dynamic_debug/control to disable them: echo -n 'module nf_conntrack -p' > /mnt/debugfs/dynamic_debug/control A further explanation can be found in the documentation patch. Signed-off-by: Greg Banks Signed-off-by: Jason Baron Signed-off-by: Greg Kroah-Hartman --- Documentation/kernel-parameters.txt | 5 - include/asm-generic/vmlinux.lds.h | 15 +- include/linux/device.h | 2 +- include/linux/dynamic_debug.h | 88 +++++ include/linux/dynamic_printk.h | 93 ----- include/linux/kernel.h | 4 +- kernel/module.c | 25 +- lib/Kconfig.debug | 2 +- lib/Makefile | 2 +- lib/dynamic_debug.c | 756 ++++++++++++++++++++++++++++++++++++ lib/dynamic_printk.c | 414 -------------------- net/netfilter/nf_conntrack_pptp.c | 2 +- scripts/Makefile.lib | 2 +- 13 files changed, 867 insertions(+), 543 deletions(-) create mode 100644 include/linux/dynamic_debug.h delete mode 100644 include/linux/dynamic_printk.h create mode 100644 lib/dynamic_debug.c delete mode 100644 lib/dynamic_printk.c (limited to 'kernel/module.c') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 54f21a5c262b..3a1aa8a4affc 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -1816,11 +1816,6 @@ and is between 256 and 4096 characters. It is defined in the file autoconfiguration. Ranges are in pairs (memory base and size). - dynamic_printk Enables pr_debug()/dev_dbg() calls if - CONFIG_DYNAMIC_PRINTK_DEBUG has been enabled. - These can also be switched on/off via - /dynamic_printk/modules - print-fatal-signals= [KNL] debug: print fatal signals print-fatal-signals=1: print segfault info to diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index c61fab1dd2f8..aca40b93bd28 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -80,6 +80,11 @@ VMLINUX_SYMBOL(__start___tracepoints) = .; \ *(__tracepoints) \ VMLINUX_SYMBOL(__stop___tracepoints) = .; \ + /* implement dynamic printk debug */ \ + . = ALIGN(8); \ + VMLINUX_SYMBOL(__start___verbose) = .; \ + *(__verbose) \ + VMLINUX_SYMBOL(__stop___verbose) = .; \ LIKELY_PROFILE() \ BRANCH_PROFILE() @@ -309,15 +314,7 @@ CPU_DISCARD(init.data) \ CPU_DISCARD(init.rodata) \ MEM_DISCARD(init.data) \ - MEM_DISCARD(init.rodata) \ - /* implement dynamic printk debug */ \ - VMLINUX_SYMBOL(__start___verbose_strings) = .; \ - *(__verbose_strings) \ - VMLINUX_SYMBOL(__stop___verbose_strings) = .; \ - . = ALIGN(8); \ - VMLINUX_SYMBOL(__start___verbose) = .; \ - *(__verbose) \ - VMLINUX_SYMBOL(__stop___verbose) = .; + MEM_DISCARD(init.rodata) #define INIT_TEXT \ *(.init.text) \ diff --git a/include/linux/device.h b/include/linux/device.h index f98d0cfb4f81..2918c0e8fdfd 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -582,7 +582,7 @@ extern const char *dev_driver_string(const struct device *dev); #if defined(DEBUG) #define dev_dbg(dev, format, arg...) \ dev_printk(KERN_DEBUG , dev , format , ## arg) -#elif defined(CONFIG_DYNAMIC_PRINTK_DEBUG) +#elif defined(CONFIG_DYNAMIC_DEBUG) #define dev_dbg(dev, format, ...) do { \ dynamic_dev_dbg(dev, format, ##__VA_ARGS__); \ } while (0) diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h new file mode 100644 index 000000000000..07781aaa1164 --- /dev/null +++ b/include/linux/dynamic_debug.h @@ -0,0 +1,88 @@ +#ifndef _DYNAMIC_DEBUG_H +#define _DYNAMIC_DEBUG_H + +/* dynamic_printk_enabled, and dynamic_printk_enabled2 are bitmasks in which + * bit n is set to 1 if any modname hashes into the bucket n, 0 otherwise. They + * use independent hash functions, to reduce the chance of false positives. + */ +extern long long dynamic_debug_enabled; +extern long long dynamic_debug_enabled2; + +/* + * An instance of this structure is created in a special + * ELF section at every dynamic debug callsite. At runtime, + * the special section is treated as an array of these. + */ +struct _ddebug { + /* + * These fields are used to drive the user interface + * for selecting and displaying debug callsites. + */ + const char *modname; + const char *function; + const char *filename; + const char *format; + char primary_hash; + char secondary_hash; + unsigned int lineno:24; + /* + * The flags field controls the behaviour at the callsite. + * The bits here are changed dynamically when the user + * writes commands to /dynamic_debug/ddebug + */ +#define _DPRINTK_FLAGS_PRINT (1<<0) /* printk() a message using the format */ +#define _DPRINTK_FLAGS_DEFAULT 0 + unsigned int flags:8; +} __attribute__((aligned(8))); + + +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); + +#define __dynamic_dbg_enabled(dd) ({ \ + int __ret = 0; \ + if (unlikely((dynamic_debug_enabled & (1LL << DEBUG_HASH)) && \ + (dynamic_debug_enabled2 & (1LL << DEBUG_HASH2)))) \ + if (unlikely(dd.flags)) \ + __ret = 1; \ + __ret; }) + +#define dynamic_pr_debug(fmt, ...) do { \ + static struct _ddebug descriptor \ + __used \ + __attribute__((section("__verbose"), aligned(8))) = \ + { KBUILD_MODNAME, __func__, __FILE__, fmt, DEBUG_HASH, \ + DEBUG_HASH2, __LINE__, _DPRINTK_FLAGS_DEFAULT }; \ + if (__dynamic_dbg_enabled(descriptor)) \ + printk(KERN_DEBUG KBUILD_MODNAME ":" fmt, \ + ##__VA_ARGS__); \ + } while (0) + + +#define dynamic_dev_dbg(dev, fmt, ...) do { \ + static struct _ddebug descriptor \ + __used \ + __attribute__((section("__verbose"), aligned(8))) = \ + { KBUILD_MODNAME, __func__, __FILE__, fmt, DEBUG_HASH, \ + DEBUG_HASH2, __LINE__, _DPRINTK_FLAGS_DEFAULT }; \ + if (__dynamic_dbg_enabled(descriptor)) \ + dev_printk(KERN_DEBUG, dev, \ + KBUILD_MODNAME ": " fmt, \ + ##__VA_ARGS__); \ + } while (0) + +#else + +static inline int ddebug_remove_module(char *mod) +{ + return 0; +} + +#define dynamic_pr_debug(fmt, ...) do { } while (0) +#define dynamic_dev_dbg(dev, format, ...) do { } while (0) +#endif + +#endif diff --git a/include/linux/dynamic_printk.h b/include/linux/dynamic_printk.h deleted file mode 100644 index 2d528d009074..000000000000 --- a/include/linux/dynamic_printk.h +++ /dev/null @@ -1,93 +0,0 @@ -#ifndef _DYNAMIC_PRINTK_H -#define _DYNAMIC_PRINTK_H - -#define DYNAMIC_DEBUG_HASH_BITS 6 -#define DEBUG_HASH_TABLE_SIZE (1 << DYNAMIC_DEBUG_HASH_BITS) - -#define TYPE_BOOLEAN 1 - -#define DYNAMIC_ENABLED_ALL 0 -#define DYNAMIC_ENABLED_NONE 1 -#define DYNAMIC_ENABLED_SOME 2 - -extern int dynamic_enabled; - -/* dynamic_printk_enabled, and dynamic_printk_enabled2 are bitmasks in which - * bit n is set to 1 if any modname hashes into the bucket n, 0 otherwise. They - * use independent hash functions, to reduce the chance of false positives. - */ -extern long long dynamic_printk_enabled; -extern long long dynamic_printk_enabled2; - -struct mod_debug { - char *modname; - char *logical_modname; - char *flag_names; - int type; - int hash; - int hash2; -} __attribute__((aligned(8))); - -int register_dynamic_debug_module(char *mod_name, int type, char *share_name, - char *flags, int hash, int hash2); - -#if defined(CONFIG_DYNAMIC_PRINTK_DEBUG) -extern int unregister_dynamic_debug_module(char *mod_name); -extern int __dynamic_dbg_enabled_helper(char *modname, int type, - int value, int hash); - -#define __dynamic_dbg_enabled(module, type, value, level, hash) ({ \ - int __ret = 0; \ - if (unlikely((dynamic_printk_enabled & (1LL << DEBUG_HASH)) && \ - (dynamic_printk_enabled2 & (1LL << DEBUG_HASH2)))) \ - __ret = __dynamic_dbg_enabled_helper(module, type, \ - value, hash);\ - __ret; }) - -#define dynamic_pr_debug(fmt, ...) do { \ - static char mod_name[] \ - __attribute__((section("__verbose_strings"))) \ - = KBUILD_MODNAME; \ - static struct mod_debug descriptor \ - __used \ - __attribute__((section("__verbose"), aligned(8))) = \ - { mod_name, mod_name, NULL, TYPE_BOOLEAN, DEBUG_HASH, DEBUG_HASH2 };\ - if (__dynamic_dbg_enabled(KBUILD_MODNAME, TYPE_BOOLEAN, \ - 0, 0, DEBUG_HASH)) \ - printk(KERN_DEBUG KBUILD_MODNAME ":" fmt, \ - ##__VA_ARGS__); \ - } while (0) - -#define dynamic_dev_dbg(dev, format, ...) do { \ - static char mod_name[] \ - __attribute__((section("__verbose_strings"))) \ - = KBUILD_MODNAME; \ - static struct mod_debug descriptor \ - __used \ - __attribute__((section("__verbose"), aligned(8))) = \ - { mod_name, mod_name, NULL, TYPE_BOOLEAN, DEBUG_HASH, DEBUG_HASH2 };\ - if (__dynamic_dbg_enabled(KBUILD_MODNAME, TYPE_BOOLEAN, \ - 0, 0, DEBUG_HASH)) \ - dev_printk(KERN_DEBUG, dev, \ - KBUILD_MODNAME ": " format, \ - ##__VA_ARGS__); \ - } while (0) - -#else - -static inline int unregister_dynamic_debug_module(const char *mod_name) -{ - return 0; -} -static inline int __dynamic_dbg_enabled_helper(char *modname, int type, - int value, int hash) -{ - return 0; -} - -#define __dynamic_dbg_enabled(module, type, value, level, hash) ({ 0; }) -#define dynamic_pr_debug(fmt, ...) do { } while (0) -#define dynamic_dev_dbg(dev, format, ...) do { } while (0) -#endif - -#endif diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 7fa371898e3e..b5496ecbec71 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -16,7 +16,7 @@ #include #include #include -#include +#include #include #include @@ -358,7 +358,7 @@ static inline char *pack_hex_byte(char *buf, u8 byte) #if defined(DEBUG) #define pr_debug(fmt, ...) \ printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) -#elif defined(CONFIG_DYNAMIC_PRINTK_DEBUG) +#elif defined(CONFIG_DYNAMIC_DEBUG) #define pr_debug(fmt, ...) do { \ dynamic_pr_debug(pr_fmt(fmt), ##__VA_ARGS__); \ } while (0) diff --git a/kernel/module.c b/kernel/module.c index 1196f5d11700..77672233387f 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -822,7 +822,7 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user, 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)); - unregister_dynamic_debug_module(mod->name); + ddebug_remove_module(mod->name); free_module(mod); out: @@ -1827,19 +1827,13 @@ static inline void add_kallsyms(struct module *mod, } #endif /* CONFIG_KALLSYMS */ -static void dynamic_printk_setup(struct mod_debug *debug, unsigned int num) +static void dynamic_debug_setup(struct _ddebug *debug, unsigned int num) { -#ifdef CONFIG_DYNAMIC_PRINTK_DEBUG - unsigned int i; - - for (i = 0; i < num; i++) { - register_dynamic_debug_module(debug[i].modname, - debug[i].type, - debug[i].logical_modname, - debug[i].flag_names, - debug[i].hash, debug[i].hash2); - } -#endif /* CONFIG_DYNAMIC_PRINTK_DEBUG */ +#ifdef CONFIG_DYNAMIC_DEBUG + if (ddebug_add_module(debug, num, debug->modname)) + printk(KERN_ERR "dynamic debug error adding module: %s\n", + debug->modname); +#endif } static void *module_alloc_update_bounds(unsigned long size) @@ -2213,12 +2207,13 @@ static noinline struct module *load_module(void __user *umod, add_kallsyms(mod, sechdrs, symindex, strindex, secstrings); if (!mod->taints) { - struct mod_debug *debug; + struct _ddebug *debug; unsigned int num_debug; debug = section_objs(hdr, sechdrs, secstrings, "__verbose", sizeof(*debug), &num_debug); - dynamic_printk_setup(debug, num_debug); + if (debug) + dynamic_debug_setup(debug, num_debug); } /* sechdrs[0].sh_size is always zero */ diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 1bcf9cd4baa0..0dd1c04c7323 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -847,7 +847,7 @@ config BUILD_DOCSRC Say N if you are unsure. -config DYNAMIC_PRINTK_DEBUG +config DYNAMIC_DEBUG bool "Enable dynamic printk() call support" default n depends on PRINTK diff --git a/lib/Makefile b/lib/Makefile index 32b0e64ded27..8633d6be9d21 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -82,7 +82,7 @@ obj-$(CONFIG_HAVE_LMB) += lmb.o obj-$(CONFIG_HAVE_ARCH_TRACEHOOK) += syscall.o -obj-$(CONFIG_DYNAMIC_PRINTK_DEBUG) += dynamic_printk.o +obj-$(CONFIG_DYNAMIC_DEBUG) += dynamic_debug.o hostprogs-y := gen_crc32table clean-files := crc32table.h diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c new file mode 100644 index 000000000000..9e123ae326bc --- /dev/null +++ b/lib/dynamic_debug.c @@ -0,0 +1,756 @@ +/* + * lib/dynamic_debug.c + * + * make pr_debug()/dev_dbg() calls runtime configurable based upon their + * source module. + * + * Copyright (C) 2008 Jason Baron + * By Greg Banks + * Copyright (c) 2008 Silicon Graphics Inc. All Rights Reserved. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +extern struct _ddebug __start___verbose[]; +extern struct _ddebug __stop___verbose[]; + +/* dynamic_debug_enabled, and dynamic_debug_enabled2 are bitmasks in which + * bit n is set to 1 if any modname hashes into the bucket n, 0 otherwise. They + * use independent hash functions, to reduce the chance of false positives. + */ +long long dynamic_debug_enabled; +EXPORT_SYMBOL_GPL(dynamic_debug_enabled); +long long dynamic_debug_enabled2; +EXPORT_SYMBOL_GPL(dynamic_debug_enabled2); + +struct ddebug_table { + struct list_head link; + char *mod_name; + unsigned int num_ddebugs; + unsigned int num_enabled; + struct _ddebug *ddebugs; +}; + +struct ddebug_query { + const char *filename; + const char *module; + const char *function; + const char *format; + unsigned int first_lineno, last_lineno; +}; + +struct ddebug_iter { + struct ddebug_table *table; + unsigned int idx; +}; + +static DEFINE_MUTEX(ddebug_lock); +static LIST_HEAD(ddebug_tables); +static int verbose = 0; + +/* Return the last part of a pathname */ +static inline const char *basename(const char *path) +{ + const char *tail = strrchr(path, '/'); + return tail ? tail+1 : path; +} + +/* format a string into buf[] which describes the _ddebug's flags */ +static char *ddebug_describe_flags(struct _ddebug *dp, char *buf, + size_t maxlen) +{ + char *p = buf; + + BUG_ON(maxlen < 4); + if (dp->flags & _DPRINTK_FLAGS_PRINT) + *p++ = 'p'; + if (p == buf) + *p++ = '-'; + *p = '\0'; + + return buf; +} + +/* + * must be called with ddebug_lock held + */ + +static int disabled_hash(char hash, bool first_table) +{ + struct ddebug_table *dt; + char table_hash_value; + + list_for_each_entry(dt, &ddebug_tables, link) { + if (first_table) + table_hash_value = dt->ddebugs->primary_hash; + else + table_hash_value = dt->ddebugs->secondary_hash; + if (dt->num_enabled && (hash == table_hash_value)) + return 0; + } + return 1; +} + +/* + * Search the tables for _ddebug's which match the given + * `query' and apply the `flags' and `mask' to them. Tells + * the user which ddebug's were changed, or whether none + * were matched. + */ +static void ddebug_change(const struct ddebug_query *query, + unsigned int flags, unsigned int mask) +{ + int i; + struct ddebug_table *dt; + unsigned int newflags; + unsigned int nfound = 0; + char flagbuf[8]; + + /* search for matching ddebugs */ + mutex_lock(&ddebug_lock); + list_for_each_entry(dt, &ddebug_tables, link) { + + /* match against the module name */ + if (query->module != NULL && + strcmp(query->module, dt->mod_name)) + continue; + + for (i = 0 ; i < dt->num_ddebugs ; i++) { + struct _ddebug *dp = &dt->ddebugs[i]; + + /* match against the source filename */ + if (query->filename != NULL && + strcmp(query->filename, dp->filename) && + strcmp(query->filename, basename(dp->filename))) + continue; + + /* match against the function */ + if (query->function != NULL && + strcmp(query->function, dp->function)) + continue; + + /* match against the format */ + if (query->format != NULL && + strstr(dp->format, query->format) == NULL) + continue; + + /* match against the line number range */ + if (query->first_lineno && + dp->lineno < query->first_lineno) + continue; + if (query->last_lineno && + dp->lineno > query->last_lineno) + continue; + + nfound++; + + newflags = (dp->flags & mask) | flags; + if (newflags == dp->flags) + continue; + + if (!newflags) + dt->num_enabled--; + else if (!dp-flags) + dt->num_enabled++; + dp->flags = newflags; + if (newflags) { + dynamic_debug_enabled |= + (1LL << dp->primary_hash); + dynamic_debug_enabled2 |= + (1LL << dp->secondary_hash); + } else { + if (disabled_hash(dp->primary_hash, true)) + dynamic_debug_enabled &= + ~(1LL << dp->primary_hash); + if (disabled_hash(dp->secondary_hash, false)) + dynamic_debug_enabled2 &= + ~(1LL << dp->secondary_hash); + } + if (verbose) + printk(KERN_INFO + "ddebug: changed %s:%d [%s]%s %s\n", + dp->filename, dp->lineno, + dt->mod_name, dp->function, + ddebug_describe_flags(dp, flagbuf, + sizeof(flagbuf))); + } + } + mutex_unlock(&ddebug_lock); + + if (!nfound && verbose) + printk(KERN_INFO "ddebug: no matches for query\n"); +} + +/* + * Wrapper around strsep() to collapse the multiple empty tokens + * that it returns when fed sequences of separator characters. + * Now, if we had strtok_r()... + */ +static inline char *nearly_strtok_r(char **p, const char *sep) +{ + char *r; + + while ((r = strsep(p, sep)) != NULL && *r == '\0') + ; + return r; +} + +/* + * Split the buffer `buf' into space-separated words. + * Return the number of such words or <0 on error. + */ +static int ddebug_tokenize(char *buf, char *words[], int maxwords) +{ + int nwords = 0; + + while (nwords < maxwords && + (words[nwords] = nearly_strtok_r(&buf, " \t\r\n")) != NULL) + nwords++; + if (buf) + return -EINVAL; /* ran out of words[] before bytes */ + + if (verbose) { + int i; + printk(KERN_INFO "%s: split into words:", __func__); + for (i = 0 ; i < nwords ; i++) + printk(" \"%s\"", words[i]); + printk("\n"); + } + + return nwords; +} + +/* + * Parse a single line number. Note that the empty string "" + * is treated as a special case and converted to zero, which + * is later treated as a "don't care" value. + */ +static inline int parse_lineno(const char *str, unsigned int *val) +{ + char *end = NULL; + BUG_ON(str == NULL); + if (*str == '\0') { + *val = 0; + return 0; + } + *val = simple_strtoul(str, &end, 10); + return end == NULL || end == str || *end != '\0' ? -EINVAL : 0; +} + +/* + * Undo octal escaping in a string, inplace. This is useful to + * allow the user to express a query which matches a format + * containing embedded spaces. + */ +#define isodigit(c) ((c) >= '0' && (c) <= '7') +static char *unescape(char *str) +{ + char *in = str; + char *out = str; + + while (*in) { + if (*in == '\\') { + if (in[1] == '\\') { + *out++ = '\\'; + in += 2; + continue; + } else if (in[1] == 't') { + *out++ = '\t'; + in += 2; + continue; + } else if (in[1] == 'n') { + *out++ = '\n'; + in += 2; + continue; + } else if (isodigit(in[1]) && + isodigit(in[2]) && + isodigit(in[3])) { + *out++ = ((in[1] - '0')<<6) | + ((in[2] - '0')<<3) | + (in[3] - '0'); + in += 4; + continue; + } + } + *out++ = *in++; + } + *out = '\0'; + + return str; +} + +/* + * Parse words[] as a ddebug query specification, which is a series + * of (keyword, value) pairs chosen from these possibilities: + * + * func + * file + * file + * module + * format + * line + * line - // where either may be empty + */ +static int ddebug_parse_query(char *words[], int nwords, + struct ddebug_query *query) +{ + unsigned int i; + + /* check we have an even number of words */ + if (nwords % 2 != 0) + return -EINVAL; + memset(query, 0, sizeof(*query)); + + for (i = 0 ; i < nwords ; i += 2) { + if (!strcmp(words[i], "func")) + query->function = words[i+1]; + else if (!strcmp(words[i], "file")) + query->filename = words[i+1]; + else if (!strcmp(words[i], "module")) + query->module = words[i+1]; + else if (!strcmp(words[i], "format")) + query->format = unescape(words[i+1]); + else if (!strcmp(words[i], "line")) { + char *first = words[i+1]; + char *last = strchr(first, '-'); + if (last) + *last++ = '\0'; + if (parse_lineno(first, &query->first_lineno) < 0) + return -EINVAL; + if (last != NULL) { + /* range - */ + if (parse_lineno(last, &query->last_lineno) < 0) + return -EINVAL; + } else { + query->last_lineno = query->first_lineno; + } + } else { + if (verbose) + printk(KERN_ERR "%s: unknown keyword \"%s\"\n", + __func__, words[i]); + return -EINVAL; + } + } + + if (verbose) + printk(KERN_INFO "%s: q->function=\"%s\" q->filename=\"%s\" " + "q->module=\"%s\" q->format=\"%s\" q->lineno=%u-%u\n", + __func__, query->function, query->filename, + query->module, query->format, query->first_lineno, + query->last_lineno); + + return 0; +} + +/* + * Parse `str' as a flags specification, format [-+=][p]+. + * Sets up *maskp and *flagsp to be used when changing the + * flags fields of matched _ddebug's. Returns 0 on success + * or <0 on error. + */ +static int ddebug_parse_flags(const char *str, unsigned int *flagsp, + unsigned int *maskp) +{ + unsigned flags = 0; + int op = '='; + + switch (*str) { + case '+': + case '-': + case '=': + op = *str++; + break; + default: + return -EINVAL; + } + if (verbose) + printk(KERN_INFO "%s: op='%c'\n", __func__, op); + + for ( ; *str ; ++str) { + switch (*str) { + case 'p': + flags |= _DPRINTK_FLAGS_PRINT; + break; + default: + return -EINVAL; + } + } + if (flags == 0) + return -EINVAL; + if (verbose) + printk(KERN_INFO "%s: flags=0x%x\n", __func__, flags); + + /* calculate final *flagsp, *maskp according to mask and op */ + switch (op) { + case '=': + *maskp = 0; + *flagsp = flags; + break; + case '+': + *maskp = ~0U; + *flagsp = flags; + break; + case '-': + *maskp = ~flags; + *flagsp = 0; + break; + } + if (verbose) + printk(KERN_INFO "%s: *flagsp=0x%x *maskp=0x%x\n", + __func__, *flagsp, *maskp); + return 0; +} + +/* + * File_ops->write method for /dynamic_debug/conrol. Gathers the + * command text from userspace, parses and executes it. + */ +static ssize_t ddebug_proc_write(struct file *file, const char __user *ubuf, + size_t len, loff_t *offp) +{ + unsigned int flags = 0, mask = 0; + struct ddebug_query query; +#define MAXWORDS 9 + int nwords; + char *words[MAXWORDS]; + char tmpbuf[256]; + + if (len == 0) + return 0; + /* we don't check *offp -- multiple writes() are allowed */ + if (len > sizeof(tmpbuf)-1) + return -E2BIG; + if (copy_from_user(tmpbuf, ubuf, len)) + return -EFAULT; + tmpbuf[len] = '\0'; + if (verbose) + printk(KERN_INFO "%s: read %d bytes from userspace\n", + __func__, (int)len); + + nwords = ddebug_tokenize(tmpbuf, words, MAXWORDS); + if (nwords < 0) + return -EINVAL; + if (ddebug_parse_query(words, nwords-1, &query)) + return -EINVAL; + if (ddebug_parse_flags(words[nwords-1], &flags, &mask)) + return -EINVAL; + + /* actually go and implement the change */ + ddebug_change(&query, flags, mask); + + *offp += len; + return len; +} + +/* + * Set the iterator to point to the first _ddebug object + * and return a pointer to that first object. Returns + * NULL if there are no _ddebugs at all. + */ +static struct _ddebug *ddebug_iter_first(struct ddebug_iter *iter) +{ + if (list_empty(&ddebug_tables)) { + iter->table = NULL; + iter->idx = 0; + return NULL; + } + iter->table = list_entry(ddebug_tables.next, + struct ddebug_table, link); + iter->idx = 0; + return &iter->table->ddebugs[iter->idx]; +} + +/* + * Advance the iterator to point to the next _ddebug + * object from the one the iterator currently points at, + * and returns a pointer to the new _ddebug. Returns + * NULL if the iterator has seen all the _ddebugs. + */ +static struct _ddebug *ddebug_iter_next(struct ddebug_iter *iter) +{ + if (iter->table == NULL) + return NULL; + if (++iter->idx == iter->table->num_ddebugs) { + /* iterate to next table */ + iter->idx = 0; + if (list_is_last(&iter->table->link, &ddebug_tables)) { + iter->table = NULL; + return NULL; + } + iter->table = list_entry(iter->table->link.next, + struct ddebug_table, link); + } + return &iter->table->ddebugs[iter->idx]; +} + +/* + * Seq_ops start method. Called at the start of every + * read() call from userspace. Takes the ddebug_lock and + * seeks the seq_file's iterator to the given position. + */ +static void *ddebug_proc_start(struct seq_file *m, loff_t *pos) +{ + struct ddebug_iter *iter = m->private; + struct _ddebug *dp; + int n = *pos; + + if (verbose) + printk(KERN_INFO "%s: called m=%p *pos=%lld\n", + __func__, m, (unsigned long long)*pos); + + mutex_lock(&ddebug_lock); + + if (!n) + return SEQ_START_TOKEN; + if (n < 0) + return NULL; + dp = ddebug_iter_first(iter); + while (dp != NULL && --n > 0) + dp = ddebug_iter_next(iter); + return dp; +} + +/* + * Seq_ops next method. Called several times within a read() + * call from userspace, with ddebug_lock held. Walks to the + * next _ddebug object with a special case for the header line. + */ +static void *ddebug_proc_next(struct seq_file *m, void *p, loff_t *pos) +{ + struct ddebug_iter *iter = m->private; + struct _ddebug *dp; + + if (verbose) + printk(KERN_INFO "%s: called m=%p p=%p *pos=%lld\n", + __func__, m, p, (unsigned long long)*pos); + + if (p == SEQ_START_TOKEN) + dp = ddebug_iter_first(iter); + else + dp = ddebug_iter_next(iter); + ++*pos; + return dp; +} + +/* + * Seq_ops show method. Called several times within a read() + * call from userspace, with ddebug_lock held. Formats the + * current _ddebug as a single human-readable line, with a + * special case for the header line. + */ +static int ddebug_proc_show(struct seq_file *m, void *p) +{ + struct ddebug_iter *iter = m->private; + struct _ddebug *dp = p; + char flagsbuf[8]; + + if (verbose) + printk(KERN_INFO "%s: called m=%p p=%p\n", + __func__, m, p); + + if (p == SEQ_START_TOKEN) { + seq_puts(m, + "# filename:lineno [module]function flags format\n"); + return 0; + } + + seq_printf(m, "%s:%u [%s]%s %s \"", + dp->filename, dp->lineno, + iter->table->mod_name, dp->function, + ddebug_describe_flags(dp, flagsbuf, sizeof(flagsbuf))); + seq_escape(m, dp->format, "\t\r\n\""); + seq_puts(m, "\"\n"); + + return 0; +} + +/* + * Seq_ops stop method. Called at the end of each read() + * call from userspace. Drops ddebug_lock. + */ +static void ddebug_proc_stop(struct seq_file *m, void *p) +{ + if (verbose) + printk(KERN_INFO "%s: called m=%p p=%p\n", + __func__, m, p); + mutex_unlock(&ddebug_lock); +} + +static const struct seq_operations ddebug_proc_seqops = { + .start = ddebug_proc_start, + .next = ddebug_proc_next, + .show = ddebug_proc_show, + .stop = ddebug_proc_stop +}; + +/* + * File_ops->open method for /dynamic_debug/control. Does the seq_file + * setup dance, and also creates an iterator to walk the _ddebugs. + * Note that we create a seq_file always, even for O_WRONLY files + * where it's not needed, as doing so simplifies the ->release method. + */ +static int ddebug_proc_open(struct inode *inode, struct file *file) +{ + struct ddebug_iter *iter; + int err; + + if (verbose) + printk(KERN_INFO "%s: called\n", __func__); + + iter = kzalloc(sizeof(*iter), GFP_KERNEL); + if (iter == NULL) + return -ENOMEM; + + err = seq_open(file, &ddebug_proc_seqops); + if (err) { + kfree(iter); + return err; + } + ((struct seq_file *) file->private_data)->private = iter; + return 0; +} + +static const struct file_operations ddebug_proc_fops = { + .owner = THIS_MODULE, + .open = ddebug_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_private, + .write = ddebug_proc_write +}; + +/* + * Allocate a new ddebug_table for the given module + * and add it to the global list. + */ +int ddebug_add_module(struct _ddebug *tab, unsigned int n, + const char *name) +{ + struct ddebug_table *dt; + char *new_name; + + dt = kzalloc(sizeof(*dt), GFP_KERNEL); + if (dt == NULL) + return -ENOMEM; + new_name = kstrdup(name, GFP_KERNEL); + if (new_name == NULL) { + kfree(dt); + return -ENOMEM; + } + dt->mod_name = new_name; + dt->num_ddebugs = n; + dt->num_enabled = 0; + dt->ddebugs = tab; + + mutex_lock(&ddebug_lock); + list_add_tail(&dt->link, &ddebug_tables); + mutex_unlock(&ddebug_lock); + + if (verbose) + printk(KERN_INFO "%u debug prints in module %s\n", + n, dt->mod_name); + return 0; +} +EXPORT_SYMBOL_GPL(ddebug_add_module); + +static void ddebug_table_free(struct ddebug_table *dt) +{ + list_del_init(&dt->link); + kfree(dt->mod_name); + kfree(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) +{ + struct ddebug_table *dt, *nextdt; + int ret = -ENOENT; + + if (verbose) + printk(KERN_INFO "%s: removing module \"%s\"\n", + __func__, mod_name); + + mutex_lock(&ddebug_lock); + list_for_each_entry_safe(dt, nextdt, &ddebug_tables, link) { + if (!strcmp(dt->mod_name, mod_name)) { + ddebug_table_free(dt); + ret = 0; + } + } + mutex_unlock(&ddebug_lock); + return ret; +} +EXPORT_SYMBOL_GPL(ddebug_remove_module); + +static void ddebug_remove_all_tables(void) +{ + mutex_lock(&ddebug_lock); + while (!list_empty(&ddebug_tables)) { + struct ddebug_table *dt = list_entry(ddebug_tables.next, + struct ddebug_table, + link); + ddebug_table_free(dt); + } + mutex_unlock(&ddebug_lock); +} + +static int __init dynamic_debug_init(void) +{ + struct dentry *dir, *file; + struct _ddebug *iter, *iter_start; + const char *modname = NULL; + int ret = 0; + int n = 0; + + dir = debugfs_create_dir("dynamic_debug", NULL); + if (!dir) + return -ENOMEM; + file = debugfs_create_file("control", 0644, dir, NULL, + &ddebug_proc_fops); + if (!file) { + debugfs_remove(dir); + return -ENOMEM; + } + if (__start___verbose != __stop___verbose) { + iter = __start___verbose; + modname = iter->modname; + iter_start = iter; + for (; iter < __stop___verbose; iter++) { + if (strcmp(modname, iter->modname)) { + ret = ddebug_add_module(iter_start, n, modname); + if (ret) + goto out_free; + n = 0; + modname = iter->modname; + iter_start = iter; + } + n++; + } + ret = ddebug_add_module(iter_start, n, modname); + } +out_free: + if (ret) { + ddebug_remove_all_tables(); + debugfs_remove(dir); + debugfs_remove(file); + } + return 0; +} +module_init(dynamic_debug_init); diff --git a/lib/dynamic_printk.c b/lib/dynamic_printk.c deleted file mode 100644 index 165a19763dc9..000000000000 --- a/lib/dynamic_printk.c +++ /dev/null @@ -1,414 +0,0 @@ -/* - * lib/dynamic_printk.c - * - * make pr_debug()/dev_dbg() calls runtime configurable based upon their - * their source module. - * - * Copyright (C) 2008 Red Hat, Inc., Jason Baron - */ - -#include -#include -#include -#include -#include -#include - -extern struct mod_debug __start___verbose[]; -extern struct mod_debug __stop___verbose[]; - -struct debug_name { - struct hlist_node hlist; - struct hlist_node hlist2; - int hash1; - int hash2; - char *name; - int enable; - int type; -}; - -static int nr_entries; -static int num_enabled; -int dynamic_enabled = DYNAMIC_ENABLED_NONE; -static struct hlist_head module_table[DEBUG_HASH_TABLE_SIZE] = - { [0 ... DEBUG_HASH_TABLE_SIZE-1] = HLIST_HEAD_INIT }; -static struct hlist_head module_table2[DEBUG_HASH_TABLE_SIZE] = - { [0 ... DEBUG_HASH_TABLE_SIZE-1] = HLIST_HEAD_INIT }; -static DECLARE_MUTEX(debug_list_mutex); - -/* dynamic_printk_enabled, and dynamic_printk_enabled2 are bitmasks in which - * bit n is set to 1 if any modname hashes into the bucket n, 0 otherwise. They - * use independent hash functions, to reduce the chance of false positives. - */ -long long dynamic_printk_enabled; -EXPORT_SYMBOL_GPL(dynamic_printk_enabled); -long long dynamic_printk_enabled2; -EXPORT_SYMBOL_GPL(dynamic_printk_enabled2); - -/* returns the debug module pointer. */ -static struct debug_name *find_debug_module(char *module_name) -{ - int i; - struct hlist_head *head; - struct hlist_node *node; - struct debug_name *element; - - element = NULL; - for (i = 0; i < DEBUG_HASH_TABLE_SIZE; i++) { - head = &module_table[i]; - hlist_for_each_entry_rcu(element, node, head, hlist) - if (!strcmp(element->name, module_name)) - return element; - } - return NULL; -} - -/* returns the debug module pointer. */ -static struct debug_name *find_debug_module_hash(char *module_name, int hash) -{ - struct hlist_head *head; - struct hlist_node *node; - struct debug_name *element; - - element = NULL; - head = &module_table[hash]; - hlist_for_each_entry_rcu(element, node, head, hlist) - if (!strcmp(element->name, module_name)) - return element; - return NULL; -} - -/* caller must hold mutex*/ -static int __add_debug_module(char *mod_name, int hash, int hash2) -{ - struct debug_name *new; - char *module_name; - int ret = 0; - - if (find_debug_module(mod_name)) { - ret = -EINVAL; - goto out; - } - module_name = kmalloc(strlen(mod_name) + 1, GFP_KERNEL); - if (!module_name) { - ret = -ENOMEM; - goto out; - } - module_name = strcpy(module_name, mod_name); - module_name[strlen(mod_name)] = '\0'; - new = kzalloc(sizeof(struct debug_name), GFP_KERNEL); - if (!new) { - kfree(module_name); - ret = -ENOMEM; - goto out; - } - INIT_HLIST_NODE(&new->hlist); - INIT_HLIST_NODE(&new->hlist2); - new->name = module_name; - new->hash1 = hash; - new->hash2 = hash2; - hlist_add_head_rcu(&new->hlist, &module_table[hash]); - hlist_add_head_rcu(&new->hlist2, &module_table2[hash2]); - nr_entries++; -out: - return ret; -} - -int unregister_dynamic_debug_module(char *mod_name) -{ - struct debug_name *element; - int ret = 0; - - down(&debug_list_mutex); - element = find_debug_module(mod_name); - if (!element) { - ret = -EINVAL; - goto out; - } - hlist_del_rcu(&element->hlist); - hlist_del_rcu(&element->hlist2); - synchronize_rcu(); - kfree(element->name); - if (element->enable) - num_enabled--; - kfree(element); - nr_entries--; -out: - up(&debug_list_mutex); - return ret; -} -EXPORT_SYMBOL_GPL(unregister_dynamic_debug_module); - -int register_dynamic_debug_module(char *mod_name, int type, char *share_name, - char *flags, int hash, int hash2) -{ - struct debug_name *elem; - int ret = 0; - - down(&debug_list_mutex); - elem = find_debug_module(mod_name); - if (!elem) { - if (__add_debug_module(mod_name, hash, hash2)) - goto out; - elem = find_debug_module(mod_name); - if (dynamic_enabled == DYNAMIC_ENABLED_ALL && - !strcmp(mod_name, share_name)) { - elem->enable = true; - num_enabled++; - } - } - elem->type |= type; -out: - up(&debug_list_mutex); - return ret; -} -EXPORT_SYMBOL_GPL(register_dynamic_debug_module); - -int __dynamic_dbg_enabled_helper(char *mod_name, int type, int value, int hash) -{ - struct debug_name *elem; - int ret = 0; - - if (dynamic_enabled == DYNAMIC_ENABLED_ALL) - return 1; - rcu_read_lock(); - elem = find_debug_module_hash(mod_name, hash); - if (elem && elem->enable) - ret = 1; - rcu_read_unlock(); - return ret; -} -EXPORT_SYMBOL_GPL(__dynamic_dbg_enabled_helper); - -static void set_all(bool enable) -{ - struct debug_name *e; - struct hlist_node *node; - int i; - long long enable_mask; - - for (i = 0; i < DEBUG_HASH_TABLE_SIZE; i++) { - if (module_table[i].first != NULL) { - hlist_for_each_entry(e, node, &module_table[i], hlist) { - e->enable = enable; - } - } - } - if (enable) - enable_mask = ULLONG_MAX; - else - enable_mask = 0; - dynamic_printk_enabled = enable_mask; - dynamic_printk_enabled2 = enable_mask; -} - -static int disabled_hash(int i, bool first_table) -{ - struct debug_name *e; - struct hlist_node *node; - - if (first_table) { - hlist_for_each_entry(e, node, &module_table[i], hlist) { - if (e->enable) - return 0; - } - } else { - hlist_for_each_entry(e, node, &module_table2[i], hlist2) { - if (e->enable) - return 0; - } - } - return 1; -} - -static ssize_t pr_debug_write(struct file *file, const char __user *buf, - size_t length, loff_t *ppos) -{ - char *buffer, *s, *value_str, *setting_str; - int err, value; - struct debug_name *elem = NULL; - int all = 0; - - if (length > PAGE_SIZE || length < 0) - return -EINVAL; - - buffer = (char *)__get_free_page(GFP_KERNEL); - if (!buffer) - return -ENOMEM; - - err = -EFAULT; - if (copy_from_user(buffer, buf, length)) - goto out; - - err = -EINVAL; - if (length < PAGE_SIZE) - buffer[length] = '\0'; - else if (buffer[PAGE_SIZE-1]) - goto out; - - err = -EINVAL; - down(&debug_list_mutex); - - if (strncmp("set", buffer, 3)) - goto out_up; - s = buffer + 3; - setting_str = strsep(&s, "="); - if (s == NULL) - goto out_up; - setting_str = strstrip(setting_str); - value_str = strsep(&s, " "); - if (s == NULL) - goto out_up; - s = strstrip(s); - if (!strncmp(s, "all", 3)) - all = 1; - else - elem = find_debug_module(s); - if (!strncmp(setting_str, "enable", 6)) { - value = !!simple_strtol(value_str, NULL, 10); - if (all) { - if (value) { - set_all(true); - num_enabled = nr_entries; - dynamic_enabled = DYNAMIC_ENABLED_ALL; - } else { - set_all(false); - num_enabled = 0; - dynamic_enabled = DYNAMIC_ENABLED_NONE; - } - err = 0; - } else if (elem) { - if (value && (elem->enable == 0)) { - dynamic_printk_enabled |= (1LL << elem->hash1); - dynamic_printk_enabled2 |= (1LL << elem->hash2); - elem->enable = 1; - num_enabled++; - dynamic_enabled = DYNAMIC_ENABLED_SOME; - err = 0; - printk(KERN_DEBUG - "debugging enabled for module %s\n", - elem->name); - } else if (!value && (elem->enable == 1)) { - elem->enable = 0; - num_enabled--; - if (disabled_hash(elem->hash1, true)) - dynamic_printk_enabled &= - ~(1LL << elem->hash1); - if (disabled_hash(elem->hash2, false)) - dynamic_printk_enabled2 &= - ~(1LL << elem->hash2); - if (num_enabled) - dynamic_enabled = DYNAMIC_ENABLED_SOME; - else - dynamic_enabled = DYNAMIC_ENABLED_NONE; - err = 0; - printk(KERN_DEBUG - "debugging disabled for module %s\n", - elem->name); - } - } - } - if (!err) - err = length; -out_up: - up(&debug_list_mutex); -out: - free_page((unsigned long)buffer); - return err; -} - -static void *pr_debug_seq_start(struct seq_file *f, loff_t *pos) -{ - return (*pos < DEBUG_HASH_TABLE_SIZE) ? pos : NULL; -} - -static void *pr_debug_seq_next(struct seq_file *s, void *v, loff_t *pos) -{ - (*pos)++; - if (*pos >= DEBUG_HASH_TABLE_SIZE) - return NULL; - return pos; -} - -static void pr_debug_seq_stop(struct seq_file *s, void *v) -{ - /* Nothing to do */ -} - -static int pr_debug_seq_show(struct seq_file *s, void *v) -{ - struct hlist_head *head; - struct hlist_node *node; - struct debug_name *elem; - unsigned int i = *(loff_t *) v; - - rcu_read_lock(); - head = &module_table[i]; - hlist_for_each_entry_rcu(elem, node, head, hlist) { - seq_printf(s, "%s enabled=%d", elem->name, elem->enable); - seq_printf(s, "\n"); - } - rcu_read_unlock(); - return 0; -} - -static struct seq_operations pr_debug_seq_ops = { - .start = pr_debug_seq_start, - .next = pr_debug_seq_next, - .stop = pr_debug_seq_stop, - .show = pr_debug_seq_show -}; - -static int pr_debug_open(struct inode *inode, struct file *filp) -{ - return seq_open(filp, &pr_debug_seq_ops); -} - -static const struct file_operations pr_debug_operations = { - .open = pr_debug_open, - .read = seq_read, - .write = pr_debug_write, - .llseek = seq_lseek, - .release = seq_release, -}; - -static int __init dynamic_printk_init(void) -{ - struct dentry *dir, *file; - struct mod_debug *iter; - unsigned long value; - - dir = debugfs_create_dir("dynamic_printk", NULL); - if (!dir) - return -ENOMEM; - file = debugfs_create_file("modules", 0644, dir, NULL, - &pr_debug_operations); - if (!file) { - debugfs_remove(dir); - return -ENOMEM; - } - for (value = (unsigned long)__start___verbose; - value < (unsigned long)__stop___verbose; - value += sizeof(struct mod_debug)) { - iter = (struct mod_debug *)value; - register_dynamic_debug_module(iter->modname, - iter->type, - iter->logical_modname, - iter->flag_names, iter->hash, iter->hash2); - } - if (dynamic_enabled == DYNAMIC_ENABLED_ALL) - set_all(true); - return 0; -} -module_init(dynamic_printk_init); -/* may want to move this earlier so we can get traces as early as possible */ - -static int __init dynamic_printk_setup(char *str) -{ - if (str) - return -ENOENT; - dynamic_enabled = DYNAMIC_ENABLED_ALL; - return 0; -} -/* Use early_param(), so we can get debug output as early as possible */ -early_param("dynamic_printk", dynamic_printk_setup); diff --git a/net/netfilter/nf_conntrack_pptp.c b/net/netfilter/nf_conntrack_pptp.c index 9e169ef2e854..12bd09dbd36c 100644 --- a/net/netfilter/nf_conntrack_pptp.c +++ b/net/netfilter/nf_conntrack_pptp.c @@ -66,7 +66,7 @@ void struct nf_conntrack_expect *exp) __read_mostly; EXPORT_SYMBOL_GPL(nf_nat_pptp_hook_expectfn); -#if defined(DEBUG) || defined(CONFIG_DYNAMIC_PRINTK_DEBUG) +#if defined(DEBUG) || defined(CONFIG_DYNAMIC_DEBUG) /* PptpControlMessageType names */ const char *const pptp_msg_name[] = { "UNKNOWN_MESSAGE", diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib index e06365775bdf..c18fa150b6fe 100644 --- a/scripts/Makefile.lib +++ b/scripts/Makefile.lib @@ -97,7 +97,7 @@ modname_flags = $(if $(filter 1,$(words $(modname))),\ -D"KBUILD_MODNAME=KBUILD_STR($(call name-fix,$(modname)))") #hash values -ifdef CONFIG_DYNAMIC_PRINTK_DEBUG +ifdef CONFIG_DYNAMIC_DEBUG debug_flags = -D"DEBUG_HASH=$(shell ./scripts/basic/hash djb2 $(@D)$(modname))"\ -D"DEBUG_HASH2=$(shell ./scripts/basic/hash r5 $(@D)$(modname))" else -- cgit v1.2.3-71-gd317 From e180a6b7759a99a28cbcce3547c4c80822cb6c2a Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Tue, 31 Mar 2009 13:05:29 -0600 Subject: param: fix charp parameters set via sysfs Impact: fix crash on reading from /sys/module/.../ieee80211_default_rc_algo The module_param type "charp" simply sets a char * pointer in the module to the parameter in the commandline string: this is why we keep the (mangled) module command line around. But when set via sysfs (as about 11 charp parameters can be) this memory is freed on the way out of the write(). Future reads hit random mem. So we kstrdup instead: we have to check we're not in early commandline parsing, and we have to note when we've used it so we can reliably kfree the parameter when it's next overwritten, and also on module unload. (Thanks to Randy Dunlap for CONFIG_SYSFS=n fixes) Reported-by: Sitsofe Wheeler Diagnosed-by: Frederic Weisbecker Tested-by: Frederic Weisbecker Tested-by: Christof Schmitt Signed-off-by: Rusty Russell --- include/linux/module.h | 4 ++++ include/linux/moduleparam.h | 10 ++++++++++ kernel/module.c | 14 ++++++++------ kernel/params.c | 26 +++++++++++++++++++++++++- 4 files changed, 47 insertions(+), 7 deletions(-) (limited to 'kernel/module.c') diff --git a/include/linux/module.h b/include/linux/module.h index 145a75528cc1..08e5e75d6122 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -248,6 +248,10 @@ struct module const unsigned long *crcs; unsigned int num_syms; + /* Kernel parameters. */ + struct kernel_param *kp; + unsigned int num_kp; + /* GPL-only exported symbols. */ unsigned int num_gpl_syms; const struct kernel_symbol *gpl_syms; diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h index e4af3399ef48..a4f0b931846c 100644 --- a/include/linux/moduleparam.h +++ b/include/linux/moduleparam.h @@ -138,6 +138,16 @@ extern int parse_args(const char *name, unsigned num, int (*unknown)(char *param, char *val)); +/* Called by module remove. */ +#ifdef CONFIG_SYSFS +extern void destroy_params(const struct kernel_param *params, unsigned num); +#else +static inline void destroy_params(const struct kernel_param *params, + unsigned num) +{ +} +#endif /* !CONFIG_SYSFS */ + /* All the helper functions */ /* The macros to do compile-time type checking stolen from Jakub Jelinek, who IIRC came up with this idea for the 2.4 module init code. */ diff --git a/kernel/module.c b/kernel/module.c index f77ac320d0b5..b862fdb6a372 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1491,6 +1491,9 @@ static void free_module(struct module *mod) /* Module unload stuff */ module_unload_free(mod); + /* Free any allocated parameters. */ + destroy_params(mod->kp, mod->num_kp); + /* release any pointers to mcount in this module */ ftrace_release(mod->module_core, mod->core_size); @@ -1898,8 +1901,7 @@ static noinline struct module *load_module(void __user *umod, unsigned int symindex = 0; unsigned int strindex = 0; unsigned int modindex, versindex, infoindex, pcpuindex; - unsigned int num_kp, num_mcount; - struct kernel_param *kp; + unsigned int num_mcount; struct module *mod; long err = 0; void *percpu = NULL, *ptr = NULL; /* Stops spurious gcc warning */ @@ -2144,8 +2146,8 @@ static noinline struct module *load_module(void __user *umod, /* Now we've got everything in the final locations, we can * find optional sections. */ - kp = section_objs(hdr, sechdrs, secstrings, "__param", sizeof(*kp), - &num_kp); + mod->kp = section_objs(hdr, sechdrs, secstrings, "__param", + sizeof(*mod->kp), &mod->num_kp); mod->syms = section_objs(hdr, sechdrs, secstrings, "__ksymtab", sizeof(*mod->syms), &mod->num_syms); mod->crcs = section_addr(hdr, sechdrs, secstrings, "__kcrctab"); @@ -2291,11 +2293,11 @@ static noinline struct module *load_module(void __user *umod, */ list_add_rcu(&mod->list, &modules); - err = parse_args(mod->name, mod->args, kp, num_kp, NULL); + err = parse_args(mod->name, mod->args, mod->kp, mod->num_kp, NULL); if (err < 0) goto unlink; - err = mod_sysfs_setup(mod, kp, num_kp); + err = mod_sysfs_setup(mod, mod->kp, mod->num_kp); if (err < 0) goto unlink; add_sect_attrs(mod, hdr->e_shnum, secstrings, sechdrs); diff --git a/kernel/params.c b/kernel/params.c index a1e3025b19a9..de273ec85bd2 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -24,6 +24,9 @@ #include #include +/* We abuse the high bits of "perm" to record whether we kmalloc'ed. */ +#define KPARAM_KMALLOCED 0x80000000 + #if 0 #define DEBUGP printk #else @@ -217,7 +220,19 @@ int param_set_charp(const char *val, struct kernel_param *kp) return -ENOSPC; } - *(char **)kp->arg = (char *)val; + if (kp->perm & KPARAM_KMALLOCED) + kfree(*(char **)kp->arg); + + /* This is a hack. We can't need to strdup in early boot, and we + * don't need to; this mangled commandline is preserved. */ + if (slab_is_available()) { + kp->perm |= KPARAM_KMALLOCED; + *(char **)kp->arg = kstrdup(val, GFP_KERNEL); + if (!kp->arg) + return -ENOMEM; + } else + *(const char **)kp->arg = val; + return 0; } @@ -571,6 +586,15 @@ void module_param_sysfs_remove(struct module *mod) } #endif +void destroy_params(const struct kernel_param *params, unsigned num) +{ + unsigned int i; + + for (i = 0; i < num; i++) + if (params[i].perm & KPARAM_KMALLOCED) + kfree(*(char **)params[i].arg); +} + static void __init kernel_add_sysfs_param(const char *name, struct kernel_param *kparam, unsigned int name_skip) -- cgit v1.2.3-71-gd317 From b10153fe31dde3805f8320b61ef147cebe379aee Mon Sep 17 00:00:00 2001 From: Américo Wang Date: Wed, 25 Mar 2009 00:07:19 +0800 Subject: kernel/module.c: fix an unused goto label Impact: cleanup Label 'free_init' is only used when defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP), so move it inside to shut up gcc. Signed-off-by: WANG Cong Cc: Rusty Russell Signed-off-by: Rusty Russell --- kernel/module.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/module.c') diff --git a/kernel/module.c b/kernel/module.c index b862fdb6a372..7af72bbe4cc0 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -2319,8 +2319,8 @@ static noinline struct module *load_module(void __user *umod, ftrace_release(mod->module_core, mod->core_size); free_unload: module_unload_free(mod); - free_init: #if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP) + free_init: percpu_modfree(mod->refptr); #endif module_free(mod, mod->module_init); -- cgit v1.2.3-71-gd317 From 414fd31b2553aaf160ca9b9afe45aa0372b01b92 Mon Sep 17 00:00:00 2001 From: Tim Abbott Date: Fri, 5 Dec 2008 19:03:56 -0500 Subject: module: Make find_symbol return a struct kernel_symbol Impact: Cleanup, internal API change Ksplice needs access to the kernel_symbol structure in order to support modifications to the exported symbol table. Cc: Anders Kaseorg Cc: Jeff Arnold Signed-off-by: Tim Abbott Signed-off-by: Rusty Russell (bugfix and style) --- kernel/module.c | 75 ++++++++++++++++++++++++++++----------------------------- 1 file changed, 37 insertions(+), 38 deletions(-) (limited to 'kernel/module.c') diff --git a/kernel/module.c b/kernel/module.c index 7af72bbe4cc0..2f0fddf3c114 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -283,7 +283,7 @@ struct find_symbol_arg { /* Output */ struct module *owner; const unsigned long *crc; - unsigned long value; + const struct kernel_symbol *sym; }; static bool find_symbol_in_section(const struct symsearch *syms, @@ -324,17 +324,17 @@ static bool find_symbol_in_section(const struct symsearch *syms, fsa->owner = owner; fsa->crc = symversion(syms->crcs, symnum); - fsa->value = syms->start[symnum].value; + fsa->sym = &syms->start[symnum]; return true; } -/* Find a symbol, return value, (optional) crc and (optional) module - * which owns it */ -static unsigned long find_symbol(const char *name, - struct module **owner, - const unsigned long **crc, - bool gplok, - bool warn) +/* Find a symbol and return it, along with, (optional) crc and + * (optional) module which owns it */ +static const struct kernel_symbol *find_symbol(const char *name, + struct module **owner, + const unsigned long **crc, + bool gplok, + bool warn) { struct find_symbol_arg fsa; @@ -347,11 +347,11 @@ static unsigned long find_symbol(const char *name, *owner = fsa.owner; if (crc) *crc = fsa.crc; - return fsa.value; + return fsa.sym; } DEBUGP("Failed to find symbol %s\n", name); - return -ENOENT; + return NULL; } /* Search for module by name: must hold module_mutex. */ @@ -894,7 +894,7 @@ void __symbol_put(const char *symbol) struct module *owner; preempt_disable(); - if (IS_ERR_VALUE(find_symbol(symbol, &owner, NULL, true, false))) + if (!find_symbol(symbol, &owner, NULL, true, false)) BUG(); module_put(owner); preempt_enable(); @@ -1057,7 +1057,7 @@ static inline int check_modstruct_version(Elf_Shdr *sechdrs, { const unsigned long *crc; - if (IS_ERR_VALUE(find_symbol("struct_module", NULL, &crc, true, false))) + if (!find_symbol("struct_module", NULL, &crc, true, false)) BUG(); return check_version(sechdrs, versindex, "struct_module", mod, crc); } @@ -1098,25 +1098,25 @@ static inline int same_magic(const char *amagic, const char *bmagic, /* Resolve a symbol for this module. I.e. if we find one, record usage. Must be holding module_mutex. */ -static unsigned long resolve_symbol(Elf_Shdr *sechdrs, - unsigned int versindex, - const char *name, - struct module *mod) +static const struct kernel_symbol *resolve_symbol(Elf_Shdr *sechdrs, + unsigned int versindex, + const char *name, + struct module *mod) { struct module *owner; - unsigned long ret; + const struct kernel_symbol *sym; const unsigned long *crc; - ret = find_symbol(name, &owner, &crc, + sym = find_symbol(name, &owner, &crc, !(mod->taints & (1 << TAINT_PROPRIETARY_MODULE)), true); - if (!IS_ERR_VALUE(ret)) { - /* use_module can fail due to OOM, - or module initialization or unloading */ + /* use_module can fail due to OOM, + or module initialization or unloading */ + if (sym) { if (!check_version(sechdrs, versindex, name, mod, crc) || !use_module(mod, owner)) - ret = -EINVAL; + sym = NULL; } - return ret; + return sym; } /* @@ -1516,17 +1516,15 @@ static void free_module(struct module *mod) void *__symbol_get(const char *symbol) { struct module *owner; - unsigned long value; + const struct kernel_symbol *sym; preempt_disable(); - value = find_symbol(symbol, &owner, NULL, true, true); - if (IS_ERR_VALUE(value)) - value = 0; - else if (strong_try_module_get(owner)) - value = 0; + sym = find_symbol(symbol, &owner, NULL, true, true); + if (sym && strong_try_module_get(owner)) + sym = NULL; preempt_enable(); - return (void *)value; + return sym ? (void *)sym->value : NULL; } EXPORT_SYMBOL_GPL(__symbol_get); @@ -1554,8 +1552,7 @@ 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++) { - if (!IS_ERR_VALUE(find_symbol(s->name, &owner, - NULL, true, false))) { + if (find_symbol(s->name, &owner, NULL, true, false)) { printk(KERN_ERR "%s: exports duplicate symbol %s" " (owned by %s)\n", @@ -1579,6 +1576,7 @@ static int simplify_symbols(Elf_Shdr *sechdrs, unsigned long secbase; unsigned int i, n = sechdrs[symindex].sh_size / sizeof(Elf_Sym); int ret = 0; + const struct kernel_symbol *ksym; for (i = 1; i < n; i++) { switch (sym[i].st_shndx) { @@ -1598,13 +1596,14 @@ static int simplify_symbols(Elf_Shdr *sechdrs, break; case SHN_UNDEF: - sym[i].st_value - = resolve_symbol(sechdrs, versindex, - strtab + sym[i].st_name, mod); - + ksym = resolve_symbol(sechdrs, versindex, + strtab + sym[i].st_name, mod); /* Ok if resolved. */ - if (!IS_ERR_VALUE(sym[i].st_value)) + if (ksym) { + sym[i].st_value = ksym->value; break; + } + /* Ok if weak. */ if (ELF_ST_BIND(sym[i].st_info) == STB_WEAK) break; -- cgit v1.2.3-71-gd317 From e610499e2656e61975affd0af56b26eb73964c84 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Tue, 31 Mar 2009 13:05:31 -0600 Subject: module: __module_address Impact: New API, cleanup ksplice wants to know the bounds of a module, not just the module text. It makes sense to have __module_address. We then implement is_module_address and __module_text_address in terms of this (and change is_module_text_address() to bool while we're at it). Also, add proper kerneldoc for them all. Cc: Anders Kaseorg Cc: Jeff Arnold Cc: Tim Abbott Signed-off-by: Rusty Russell --- include/linux/module.h | 20 +++++++++---- kernel/module.c | 76 ++++++++++++++++++++++++++++++++++++++------------ 2 files changed, 73 insertions(+), 23 deletions(-) (limited to 'kernel/module.c') diff --git a/include/linux/module.h b/include/linux/module.h index 08e5e75d6122..fd1241e1416f 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -365,7 +365,9 @@ static inline int module_is_live(struct module *mod) /* Is this address in a module? (second is with no locks, for oops) */ struct module *module_text_address(unsigned long addr); struct module *__module_text_address(unsigned long addr); -int is_module_address(unsigned long addr); +struct module *__module_address(unsigned long addr); +bool is_module_address(unsigned long addr); +bool is_module_text_address(unsigned long addr); static inline int within_module_core(unsigned long addr, struct module *mod) { @@ -494,21 +496,29 @@ search_module_extables(unsigned long addr) return NULL; } -/* Is this address in a module? */ static inline struct module *module_text_address(unsigned long addr) { return NULL; } -/* Is this address in a module? (don't take a lock, we're oopsing) */ +static inline struct module *__module_address(unsigned long addr) +{ + return NULL; +} + static inline struct module *__module_text_address(unsigned long addr) { return NULL; } -static inline int is_module_address(unsigned long addr) +static inline bool is_module_address(unsigned long addr) { - return 0; + return false; +} + +static inline bool is_module_text_address(unsigned long addr) +{ + return false; } /* Get/put a kernel symbol (calls should be symmetric) */ diff --git a/kernel/module.c b/kernel/module.c index 2f0fddf3c114..bd15a94f91c1 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -76,7 +76,7 @@ static DECLARE_WAIT_QUEUE_HEAD(module_wq); static BLOCKING_NOTIFIER_HEAD(module_notify_list); -/* Bounds of module allocation, for speeding __module_text_address */ +/* Bounds of module allocation, for speeding __module_address */ static unsigned long module_addr_min = -1UL, module_addr_max = 0; int register_module_notifier(struct notifier_block * nb) @@ -2745,29 +2745,31 @@ const struct exception_table_entry *search_module_extables(unsigned long addr) } /* - * Is this a valid module address? + * is_module_address - is this address inside a module? + * @addr: the address to check. + * + * See is_module_text_address() if you simply want to see if the address + * is code (not data). */ -int is_module_address(unsigned long addr) +bool is_module_address(unsigned long addr) { - struct module *mod; + bool ret; preempt_disable(); - - list_for_each_entry_rcu(mod, &modules, list) { - if (within_module_core(addr, mod)) { - preempt_enable(); - return 1; - } - } - + ret = __module_address(addr) != NULL; preempt_enable(); - return 0; + return ret; } - -/* Is this a valid kernel address? */ -__notrace_funcgraph struct module *__module_text_address(unsigned long addr) +/* + * __module_address - get the module which contains an address. + * @addr: the address. + * + * Must be called with preempt disabled or module mutex held so that + * module doesn't get freed during this. + */ +__notrace_funcgraph struct module *__module_address(unsigned long addr) { struct module *mod; @@ -2775,12 +2777,50 @@ __notrace_funcgraph struct module *__module_text_address(unsigned long addr) return NULL; list_for_each_entry_rcu(mod, &modules, list) - if (within(addr, mod->module_init, mod->init_text_size) - || within(addr, mod->module_core, mod->core_text_size)) + if (within_module_core(addr, mod) + || within_module_init(addr, mod)) return mod; return NULL; } +/* + * is_module_text_address - is this address inside module code? + * @addr: the address to check. + * + * See is_module_address() if you simply want to see if the address is + * anywhere in a module. See kernel_text_address() for testing if an + * address corresponds to kernel or module code. + */ +bool is_module_text_address(unsigned long addr) +{ + bool ret; + + preempt_disable(); + ret = __module_text_address(addr) != NULL; + preempt_enable(); + + return ret; +} + +/* + * __module_text_address - get the module whose code contains an address. + * @addr: the address. + * + * Must be called with preempt disabled or module mutex held so that + * module doesn't get freed during this. + */ +struct module *__module_text_address(unsigned long addr) +{ + struct module *mod = __module_address(addr); + if (mod) { + /* Make sure it's within the text section. */ + if (!within(addr, mod->module_init, mod->init_text_size) + && !within(addr, mod->module_core, mod->core_text_size)) + mod = NULL; + } + return mod; +} + struct module *module_text_address(unsigned long addr) { struct module *mod; -- cgit v1.2.3-71-gd317 From a6e6abd575fcbe6572ebc7a70ad616406d206fa8 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Tue, 31 Mar 2009 13:05:31 -0600 Subject: module: remove module_text_address() Impact: Replace and remove risky (non-EXPORTed) API module_text_address() returns a pointer to the module, which given locking improvements in module.c, is useless except to test for NULL: 1) If the module can't go away, use __module_text_address. 2) Otherwise, just use is_module_text_address(). Cc: linux-mtd@lists.infradead.org Signed-off-by: Rusty Russell --- drivers/mtd/nand/nand_base.c | 4 ++-- include/linux/module.h | 7 ------- kernel/extable.c | 6 +++--- kernel/module.c | 17 ++++------------- 4 files changed, 9 insertions(+), 25 deletions(-) (limited to 'kernel/module.c') diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c index 0c3afccde8a2..5f71371eb1b0 100644 --- a/drivers/mtd/nand/nand_base.c +++ b/drivers/mtd/nand/nand_base.c @@ -2720,14 +2720,14 @@ int nand_scan_tail(struct mtd_info *mtd) return chip->scan_bbt(mtd); } -/* module_text_address() isn't exported, and it's mostly a pointless +/* is_module_text_address() isn't exported, and it's mostly a pointless test if this is a module _anyway_ -- they'd have to try _really_ hard to call us from in-kernel code if the core NAND support is modular. */ #ifdef MODULE #define caller_is_module() (1) #else #define caller_is_module() \ - module_text_address((unsigned long)__builtin_return_address(0)) + is_module_text_address((unsigned long)__builtin_return_address(0)) #endif /** diff --git a/include/linux/module.h b/include/linux/module.h index fd1241e1416f..69761ce0dbf0 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -362,8 +362,6 @@ static inline int module_is_live(struct module *mod) return mod->state != MODULE_STATE_GOING; } -/* Is this address in a module? (second is with no locks, for oops) */ -struct module *module_text_address(unsigned long addr); struct module *__module_text_address(unsigned long addr); struct module *__module_address(unsigned long addr); bool is_module_address(unsigned long addr); @@ -496,11 +494,6 @@ search_module_extables(unsigned long addr) return NULL; } -static inline struct module *module_text_address(unsigned long addr) -{ - return NULL; -} - static inline struct module *__module_address(unsigned long addr) { return NULL; diff --git a/kernel/extable.c b/kernel/extable.c index e136ed8d82ba..384f0da8a03e 100644 --- a/kernel/extable.c +++ b/kernel/extable.c @@ -58,14 +58,14 @@ __notrace_funcgraph int __kernel_text_address(unsigned long addr) { if (core_kernel_text(addr)) return 1; - return __module_text_address(addr) != NULL; + return is_module_text_address(addr); } int kernel_text_address(unsigned long addr) { if (core_kernel_text(addr)) return 1; - return module_text_address(addr) != NULL; + return is_module_text_address(addr); } /* @@ -81,5 +81,5 @@ int func_ptr_is_kernel_text(void *ptr) addr = (unsigned long) dereference_function_descriptor(ptr); if (core_kernel_text(addr)) return 1; - return module_text_address(addr) != NULL; + return is_module_text_address(addr); } diff --git a/kernel/module.c b/kernel/module.c index bd15a94f91c1..8ddca629e079 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -908,8 +908,10 @@ void symbol_put_addr(void *addr) if (core_kernel_text((unsigned long)addr)) return; - if (!(modaddr = module_text_address((unsigned long)addr))) - BUG(); + /* module_text_address is safe here: we're supposed to have reference + * to module from symbol_get, so it can't go away. */ + modaddr = __module_text_address((unsigned long)addr); + BUG_ON(!modaddr); module_put(modaddr); } EXPORT_SYMBOL_GPL(symbol_put_addr); @@ -2821,17 +2823,6 @@ struct module *__module_text_address(unsigned long addr) return mod; } -struct module *module_text_address(unsigned long addr) -{ - struct module *mod; - - preempt_disable(); - mod = __module_text_address(addr); - preempt_enable(); - - return mod; -} - /* Don't grab lock, we're oopsing. */ void print_modules(void) { -- cgit v1.2.3-71-gd317 From 75a66614db21007bcc8c37f9c5d5b922981387b9 Mon Sep 17 00:00:00 2001 From: Anders Kaseorg Date: Fri, 5 Dec 2008 19:03:58 -0500 Subject: Ksplice: Add functions for walking kallsyms symbols Impact: New API kallsyms_lookup_name only returns the first match that it finds. Ksplice needs information about all symbols with a given name in order to correctly resolve local symbols. kallsyms_on_each_symbol provides a generic mechanism for iterating over the kallsyms table. Cc: Jeff Arnold Cc: Tim Abbott Signed-off-by: Anders Kaseorg Signed-off-by: Rusty Russell --- include/linux/kallsyms.h | 15 +++++++++++++++ include/linux/module.h | 12 ++++++++++++ kernel/kallsyms.c | 19 +++++++++++++++++++ kernel/module.c | 19 +++++++++++++++++++ 4 files changed, 65 insertions(+) (limited to 'kernel/module.c') diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h index f3fe34391d8e..792274269f2b 100644 --- a/include/linux/kallsyms.h +++ b/include/linux/kallsyms.h @@ -13,10 +13,17 @@ #define KSYM_SYMBOL_LEN (sizeof("%s+%#lx/%#lx [%s]") + (KSYM_NAME_LEN - 1) + \ 2*(BITS_PER_LONG*3/10) + (MODULE_NAME_LEN - 1) + 1) +struct module; + #ifdef CONFIG_KALLSYMS /* Lookup the address for a symbol. Returns 0 if not found. */ unsigned long kallsyms_lookup_name(const char *name); +/* Call a function on each kallsyms symbol in the core kernel */ +int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *, + unsigned long), + void *data); + extern int kallsyms_lookup_size_offset(unsigned long addr, unsigned long *symbolsize, unsigned long *offset); @@ -43,6 +50,14 @@ static inline unsigned long kallsyms_lookup_name(const char *name) return 0; } +static inline int kallsyms_on_each_symbol(int (*fn)(void *, const char *, + struct module *, + unsigned long), + void *data) +{ + return 0; +} + static inline int kallsyms_lookup_size_offset(unsigned long addr, unsigned long *symbolsize, unsigned long *offset) diff --git a/include/linux/module.h b/include/linux/module.h index 69761ce0dbf0..c3d3fc4ffb18 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -387,6 +387,10 @@ int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type, /* Look for this name: can be of form module:name. */ unsigned long module_kallsyms_lookup_name(const char *name); +int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *, + struct module *, unsigned long), + void *data); + extern void __module_put_and_exit(struct module *mod, long code) __attribute__((noreturn)); #define module_put_and_exit(code) __module_put_and_exit(THIS_MODULE, code); @@ -566,6 +570,14 @@ static inline unsigned long module_kallsyms_lookup_name(const char *name) return 0; } +static inline int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *, + struct module *, + unsigned long), + void *data) +{ + return 0; +} + static inline int register_module_notifier(struct notifier_block * nb) { /* no events will happen anyway, so this can always succeed */ diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c index 7b8b0f21a5b1..374faf9bfdc7 100644 --- a/kernel/kallsyms.c +++ b/kernel/kallsyms.c @@ -161,6 +161,25 @@ unsigned long kallsyms_lookup_name(const char *name) return module_kallsyms_lookup_name(name); } +int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *, + unsigned long), + void *data) +{ + char namebuf[KSYM_NAME_LEN]; + unsigned long i; + unsigned int off; + int ret; + + for (i = 0, off = 0; i < kallsyms_num_syms; i++) { + off = kallsyms_expand_symbol(off, namebuf); + ret = fn(data, namebuf, NULL, kallsyms_addresses[i]); + if (ret != 0) + return ret; + } + return module_kallsyms_on_each_symbol(fn, data); +} +EXPORT_SYMBOL_GPL(kallsyms_on_each_symbol); + static unsigned long get_symbol_pos(unsigned long addr, unsigned long *symbolsize, unsigned long *offset) diff --git a/kernel/module.c b/kernel/module.c index 8ddca629e079..dd4389be9152 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -2612,6 +2612,25 @@ unsigned long module_kallsyms_lookup_name(const char *name) preempt_enable(); return ret; } + +int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *, + struct module *, unsigned long), + void *data) +{ + struct module *mod; + unsigned int i; + int ret; + + list_for_each_entry(mod, &modules, list) { + for (i = 0; i < mod->num_symtab; i++) { + ret = fn(data, mod->strtab + mod->symtab[i].st_name, + mod, mod->symtab[i].st_value); + if (ret != 0) + return ret; + } + } + return 0; +} #endif /* CONFIG_KALLSYMS */ static char *module_flags(struct module *mod, char *buf) -- cgit v1.2.3-71-gd317 From c6b37801911d7f4663c99cad8aa230bc934cea82 Mon Sep 17 00:00:00 2001 From: Tim Abbott Date: Fri, 5 Dec 2008 19:03:59 -0500 Subject: module: Export symbols needed for Ksplice Impact: Expose some module.c symbols Ksplice uses several functions from module.c in order to resolve symbols and implement dependency handling. Calling these functions requires holding module_mutex, so it is exported. (This is just the module part of a bigger add-exports patch from Tim). Cc: Anders Kaseorg Cc: Jeff Arnold Signed-off-by: Tim Abbott Signed-off-by: Rusty Russell --- include/linux/module.h | 28 ++++++++++++++++++++++++++++ kernel/module.c | 43 +++++++++++++++++++------------------------ 2 files changed, 47 insertions(+), 24 deletions(-) (limited to 'kernel/module.c') diff --git a/include/linux/module.h b/include/linux/module.h index c3d3fc4ffb18..d246da0b0f8c 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -354,6 +354,8 @@ struct module #define MODULE_ARCH_INIT {} #endif +extern struct mutex module_mutex; + /* FIXME: It'd be nice to isolate modules during init, too, so they aren't used before they (may) fail. But presently too much code (IDE & SCSI) require entry into the module during init.*/ @@ -379,6 +381,31 @@ static inline int within_module_init(unsigned long addr, struct module *mod) addr < (unsigned long)mod->module_init + mod->init_size; } +/* Search for module by name: must hold module_mutex. */ +struct module *find_module(const char *name); + +struct symsearch { + const struct kernel_symbol *start, *stop; + const unsigned long *crcs; + enum { + NOT_GPL_ONLY, + GPL_ONLY, + WILL_BE_GPL_ONLY, + } licence; + bool unused; +}; + +/* Search for an exported symbol by name. */ +const struct kernel_symbol *find_symbol(const char *name, + struct module **owner, + const unsigned long **crc, + bool gplok, + bool warn); + +/* Walk the exported symbol table */ +bool each_symbol(bool (*fn)(const struct symsearch *arr, struct module *owner, + unsigned int symnum, void *data), void *data); + /* Returns 0 and fills in value, defined and namebuf, or -ERANGE if symnum out of range. */ int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type, @@ -452,6 +479,7 @@ static inline void __module_get(struct module *module) #define symbol_put_addr(p) do { } while(0) #endif /* CONFIG_MODULE_UNLOAD */ +int use_module(struct module *a, struct module *b); /* This is a #define so the string doesn't get put in every .o file */ #define module_name(mod) \ diff --git a/kernel/module.c b/kernel/module.c index dd4389be9152..5fd00766a4dc 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -68,7 +68,8 @@ /* List of modules, protected by module_mutex or preempt_disable * (delete uses stop_machine/add uses RCU list operations). */ -static DEFINE_MUTEX(module_mutex); +DEFINE_MUTEX(module_mutex); +EXPORT_SYMBOL_GPL(module_mutex); static LIST_HEAD(modules); /* Waiting for a module to finish initializing? */ @@ -186,17 +187,6 @@ extern const unsigned long __start___kcrctab_unused_gpl[]; #define symversion(base, idx) ((base != NULL) ? ((base) + (idx)) : NULL) #endif -struct symsearch { - const struct kernel_symbol *start, *stop; - const unsigned long *crcs; - enum { - NOT_GPL_ONLY, - GPL_ONLY, - WILL_BE_GPL_ONLY, - } licence; - bool unused; -}; - static bool each_symbol_in_section(const struct symsearch *arr, unsigned int arrsize, struct module *owner, @@ -217,10 +207,8 @@ static bool each_symbol_in_section(const struct symsearch *arr, } /* Returns true as soon as fn returns true, otherwise false. */ -static bool each_symbol(bool (*fn)(const struct symsearch *arr, - struct module *owner, - unsigned int symnum, void *data), - void *data) +bool each_symbol(bool (*fn)(const struct symsearch *arr, struct module *owner, + unsigned int symnum, void *data), void *data) { struct module *mod; const struct symsearch arr[] = { @@ -273,6 +261,7 @@ static bool each_symbol(bool (*fn)(const struct symsearch *arr, } return false; } +EXPORT_SYMBOL_GPL(each_symbol); struct find_symbol_arg { /* Input */ @@ -330,11 +319,11 @@ 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 */ -static const struct kernel_symbol *find_symbol(const char *name, - struct module **owner, - const unsigned long **crc, - bool gplok, - bool warn) +const struct kernel_symbol *find_symbol(const char *name, + struct module **owner, + const unsigned long **crc, + bool gplok, + bool warn) { struct find_symbol_arg fsa; @@ -353,9 +342,10 @@ static const struct kernel_symbol *find_symbol(const char *name, DEBUGP("Failed to find symbol %s\n", name); return NULL; } +EXPORT_SYMBOL_GPL(find_symbol); /* Search for module by name: must hold module_mutex. */ -static struct module *find_module(const char *name) +struct module *find_module(const char *name) { struct module *mod; @@ -365,6 +355,7 @@ static struct module *find_module(const char *name) } return NULL; } +EXPORT_SYMBOL_GPL(find_module); #ifdef CONFIG_SMP @@ -641,7 +632,7 @@ static int already_uses(struct module *a, struct module *b) } /* Module a uses b */ -static int use_module(struct module *a, struct module *b) +int use_module(struct module *a, struct module *b) { struct module_use *use; int no_warn, err; @@ -674,6 +665,7 @@ static int use_module(struct module *a, struct module *b) no_warn = sysfs_create_link(b->holders_dir, &a->mkobj.kobj, a->name); return 1; } +EXPORT_SYMBOL_GPL(use_module); /* Clear the unload stuff of the module. */ static void module_unload_free(struct module *mod) @@ -951,10 +943,11 @@ static inline void module_unload_free(struct module *mod) { } -static inline int use_module(struct module *a, struct module *b) +int use_module(struct module *a, struct module *b) { return strong_try_module_get(b) == 0; } +EXPORT_SYMBOL_GPL(use_module); static inline void module_unload_init(struct module *mod) { @@ -2803,6 +2796,7 @@ __notrace_funcgraph struct module *__module_address(unsigned long addr) return mod; return NULL; } +EXPORT_SYMBOL_GPL(__module_address); /* * is_module_text_address - is this address inside module code? @@ -2841,6 +2835,7 @@ struct module *__module_text_address(unsigned long addr) } return mod; } +EXPORT_SYMBOL_GPL(__module_text_address); /* Don't grab lock, we're oopsing. */ void print_modules(void) -- cgit v1.2.3-71-gd317 From c6e665c8f0c18ab3686117905765b5139efd6ebd Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Tue, 31 Mar 2009 13:05:33 -0600 Subject: module: clarify the force-loading taint message. Impact: Message cleanup Two of three callers of try_to_force_load() are not because of a missing version, so change the messages: Old: : no version for "magic" found: kernel tainted. New: : bad vermagic: kernel tainted. Old: : no version for "nocrc" found: kernel tainted. New: : no versions for exported symbols: kernel tainted. Old: : no version for "" found: kernel tainted. New: : : kernel tainted. Signed-off-by: Rusty Russell --- kernel/module.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'kernel/module.c') diff --git a/kernel/module.c b/kernel/module.c index 5fd00766a4dc..599fc85bd2cc 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -990,12 +990,12 @@ static struct module_attribute *modinfo_attrs[] = { static const char vermagic[] = VERMAGIC_STRING; -static int try_to_force_load(struct module *mod, const char *symname) +static int try_to_force_load(struct module *mod, const char *reason) { #ifdef CONFIG_MODULE_FORCE_LOAD if (!test_taint(TAINT_FORCED_MODULE)) - printk("%s: no version for \"%s\" found: kernel tainted.\n", - mod->name, symname); + printk(KERN_WARNING "%s: %s: kernel tainted.\n", + mod->name, reason); add_taint_module(mod, TAINT_FORCED_MODULE); return 0; #else @@ -2002,7 +2002,7 @@ static noinline struct module *load_module(void __user *umod, modmagic = get_modinfo(sechdrs, infoindex, "vermagic"); /* This is allowed: modprobe --force will invalidate it. */ if (!modmagic) { - err = try_to_force_load(mod, "magic"); + err = try_to_force_load(mod, "bad vermagic"); if (err) goto free_hdr; } else if (!same_magic(modmagic, vermagic, versindex)) { @@ -2191,8 +2191,8 @@ static noinline struct module *load_module(void __user *umod, || (mod->num_unused_gpl_syms && !mod->unused_gpl_crcs) #endif ) { - printk(KERN_WARNING "%s: No versions for exported symbols.\n", mod->name); - err = try_to_force_load(mod, "nocrc"); + err = try_to_force_load(mod, + "no versions for exported symbols"); if (err) goto cleanup; } -- cgit v1.2.3-71-gd317 From 9cb610d8e35fe3ec95a2fe2030b02f85aeea83c1 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Tue, 31 Mar 2009 13:05:33 -0600 Subject: module: remove the SHF_ALLOC flag on the __versions section. Impact: reduce kernel memory usage This patch just takes off the SHF_ALLOC flag on __versions so we don't keep them around after module load. This saves about 7% of module memory if CONFIG_MODVERSIONS=y. Cc: Shawn Bohrer Signed-off-by: Rusty Russell --- 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 599fc85bd2cc..784bf6d8f8c4 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1961,6 +1961,9 @@ static noinline struct module *load_module(void __user *umod, if (strncmp(secstrings+sechdrs[i].sh_name, ".exit", 5) == 0) sechdrs[i].sh_flags &= ~(unsigned long)SHF_ALLOC; #endif + /* Don't keep __versions around; it's just for loading. */ + if (strcmp(secstrings + sechdrs[i].sh_name, "__versions") == 0) + sechdrs[i].sh_flags &= ~(unsigned long)SHF_ALLOC; } modindex = find_sec(hdr, sechdrs, secstrings, -- cgit v1.2.3-71-gd317 From 8c8ef42aee8fcfb4128bb94c50d55c9f80ade525 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Tue, 31 Mar 2009 13:05:34 -0600 Subject: module: include other structures in module version check With CONFIG_MODVERSIONS, we version 'struct module' using a dummy export, but other things matter too: 1) 'struct modversion_info' determines the layout of the __versions section, 2) 'struct kernel_param' determines the layout of the __params section, 3) 'struct kernel_symbol' determines __ksymtab*. 4) 'struct marker' determines __markers. 5) 'struct tracepoint' determines __tracepoints. So we rename 'struct_module' to 'module_layout' and include these in the signature. Now it's general we can add others later on without confusion. Signed-off-by: Rusty Russell --- kernel/module.c | 18 +++++++++++++----- scripts/mod/modpost.c | 4 ++-- 2 files changed, 15 insertions(+), 7 deletions(-) (limited to 'kernel/module.c') diff --git a/kernel/module.c b/kernel/module.c index 784bf6d8f8c4..e8cf636e614b 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1052,9 +1052,9 @@ static inline int check_modstruct_version(Elf_Shdr *sechdrs, { const unsigned long *crc; - if (!find_symbol("struct_module", NULL, &crc, true, false)) + if (!find_symbol("module_layout", NULL, &crc, true, false)) BUG(); - return check_version(sechdrs, versindex, "struct_module", mod, crc); + return check_version(sechdrs, versindex, "module_layout", mod, crc); } /* First part is kernel version, which we ignore if module has crcs. */ @@ -2858,9 +2858,17 @@ void print_modules(void) } #ifdef CONFIG_MODVERSIONS -/* Generate the signature for struct module here, too, for modversions. */ -void struct_module(struct module *mod) { return; } -EXPORT_SYMBOL(struct_module); +/* Generate the signature for all relevant module structures here. + * If these change, we don't want to try to parse the module. */ +void module_layout(struct module *mod, + struct modversion_info *ver, + struct kernel_param *kp, + struct kernel_symbol *ks, + struct marker *marker, + struct tracepoint *tp) +{ +} +EXPORT_SYMBOL(module_layout); #endif #ifdef CONFIG_MARKERS diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index 7e62303133dc..8cc70612984c 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -1607,12 +1607,12 @@ static void read_symbols(char *modname) parse_elf_finish(&info); - /* Our trick to get versioning for struct_module - it's + /* Our trick to get versioning for module struct etc. - it's * never passed as an argument to an exported function, so * the automatic versioning doesn't pick it up, but it's really * important anyhow */ if (modversions) - mod->unres = alloc_symbol("struct_module", 0, mod->unres); + mod->unres = alloc_symbol("module_layout", 0, mod->unres); } #define SZ 500 -- cgit v1.2.3-71-gd317 From e91defa26c527ceeaff6266c55cdc7e17c9081a2 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Tue, 31 Mar 2009 13:05:35 -0600 Subject: module: don't use stop_machine on module load Kay Sievers discovered that boot times are slowed by about half a second because all the stop_machine_create() calls, and he only probes about 40 modules (I have 125 loaded on this laptop). We only do stop_machine_create() so we can unlink the module if something goes wrong, but it's overkill (and buggy anyway: if stop_machine_create() fails we still call stop_machine_destroy()). Since we are only protecting against kallsyms (esp. oops) walking the list, synchronize_sched() is sufficient (synchronize_rcu() is probably sufficient, but we're not in a hurry). Kay says of this patch: ... no module takes more than 40 millisecs to link now, most of them are between 3 and 8 millisecs. That looks very different to the numbers without this patch and the otherwise same setup, where we get heavy noise in the traces and many delays of up to 200 millisecs until linking, most of them taking 30+ millisecs. Tested-by: Kay Sievers Signed-off-by: Rusty Russell --- kernel/module.c | 12 +++--------- 1 file changed, 3 insertions(+), 9 deletions(-) (limited to 'kernel/module.c') diff --git a/kernel/module.c b/kernel/module.c index e8cf636e614b..1a9a3986b136 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1912,12 +1912,6 @@ static noinline struct module *load_module(void __user *umod, if (len > 64 * 1024 * 1024 || (hdr = vmalloc(len)) == NULL) return ERR_PTR(-ENOMEM); - /* Create stop_machine threads since the error path relies on - * a non-failing stop_machine call. */ - err = stop_machine_create(); - if (err) - goto free_hdr; - if (copy_from_user(hdr, umod, len) != 0) { err = -EFAULT; goto free_hdr; @@ -2303,12 +2297,13 @@ static noinline struct module *load_module(void __user *umod, /* Get rid of temporary copy */ vfree(hdr); - stop_machine_destroy(); /* Done! */ return mod; unlink: - stop_machine(__unlink_module, mod, NULL); + /* Unlink carefully: kallsyms could be walking list. */ + list_del_rcu(&mod->list); + synchronize_sched(); module_arch_cleanup(mod); cleanup: kobject_del(&mod->mkobj.kobj); @@ -2331,7 +2326,6 @@ static noinline struct module *load_module(void __user *umod, kfree(args); free_hdr: vfree(hdr); - stop_machine_destroy(); return ERR_PTR(err); truncated: -- cgit v1.2.3-71-gd317 From 49502677e11079c2e3e01867c922a894ce06a8be Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Tue, 31 Mar 2009 13:05:36 -0600 Subject: module: use strstarts() Impact: minor cleanup. I'm not going to neaten anyone else's code, but I'm happy to clean up my own. Signed-off-by: Rusty Russell --- kernel/module.c | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) (limited to 'kernel/module.c') diff --git a/kernel/module.c b/kernel/module.c index 1a9a3986b136..f6e08b7cff7c 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1673,8 +1673,7 @@ static void layout_sections(struct module *mod, if ((s->sh_flags & masks[m][0]) != masks[m][0] || (s->sh_flags & masks[m][1]) || s->sh_entsize != ~0UL - || strncmp(secstrings + s->sh_name, - ".init", 5) == 0) + || strstarts(secstrings + s->sh_name, ".init")) continue; s->sh_entsize = get_offset(mod, &mod->core_size, s, i); DEBUGP("\t%s\n", secstrings + s->sh_name); @@ -1691,8 +1690,7 @@ static void layout_sections(struct module *mod, if ((s->sh_flags & masks[m][0]) != masks[m][0] || (s->sh_flags & masks[m][1]) || s->sh_entsize != ~0UL - || strncmp(secstrings + s->sh_name, - ".init", 5) != 0) + || !strstarts(secstrings + s->sh_name, ".init")) continue; s->sh_entsize = (get_offset(mod, &mod->init_size, s, i) | INIT_OFFSET_MASK); @@ -1825,8 +1823,7 @@ static char elf_type(const Elf_Sym *sym, else return 'b'; } - if (strncmp(secstrings + sechdrs[sym->st_shndx].sh_name, - ".debug", strlen(".debug")) == 0) + if (strstarts(secstrings + sechdrs[sym->st_shndx].sh_name, ".debug")) return 'n'; return '?'; } @@ -1952,7 +1949,7 @@ static noinline struct module *load_module(void __user *umod, } #ifndef CONFIG_MODULE_UNLOAD /* Don't load .exit sections */ - if (strncmp(secstrings+sechdrs[i].sh_name, ".exit", 5) == 0) + if (strstarts(secstrings+sechdrs[i].sh_name, ".exit")) sechdrs[i].sh_flags &= ~(unsigned long)SHF_ALLOC; #endif /* Don't keep __versions around; it's just for loading. */ -- cgit v1.2.3-71-gd317