From 061b1bd394ca8628b7c24eb4658ba3535da4249a Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 24 Sep 2008 14:46:44 -0700 Subject: Staging: add TAINT_CRAP for all drivers/staging code We need to add a flag for all code that is in the drivers/staging/ directory to prevent all other kernel developers from worrying about issues here, and to notify users that the drivers might not be as good as they are normally used to. Based on code from Andreas Gruenbacher and Jeff Mahoney to provide a TAINT flag for the support level of a kernel module in the Novell enterprise kernel release. This is the kernel portion of this feature, the ability for the flag to be set needs to be done in the build process and will happen in a follow-up patch. Cc: Andreas Gruenbacher Cc: Jeff Mahoney Signed-off-by: Greg Kroah-Hartman --- kernel/module.c | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'kernel/module.c') diff --git a/kernel/module.c b/kernel/module.c index 9db1191..152b165 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1806,6 +1806,7 @@ static noinline struct module *load_module(void __user *umod, Elf_Ehdr *hdr; Elf_Shdr *sechdrs; char *secstrings, *args, *modmagic, *strtab = NULL; + char *staging; unsigned int i; unsigned int symindex = 0; unsigned int strindex = 0; @@ -1960,6 +1961,14 @@ static noinline struct module *load_module(void __user *umod, goto free_hdr; } + staging = get_modinfo(sechdrs, infoindex, "staging"); + if (staging) { + add_taint_module(mod, TAINT_CRAP); + printk(KERN_WARNING "%s: module is from the staging directory," + " the quality is unknown, you have been warned.\n", + mod->name); + } + /* Now copy in args */ args = strndup_user(uargs, ~0UL >> 1); if (IS_ERR(args)) { @@ -2556,6 +2565,8 @@ static char *module_flags(struct module *mod, char *buf) buf[bx++] = 'P'; if (mod->taints & TAINT_FORCED_MODULE) buf[bx++] = 'F'; + if (mod->taints & TAINT_CRAP) + buf[bx++] = 'C'; /* * TAINT_FORCED_RMMOD: could be added. * TAINT_UNSAFE_SMP, TAINT_MACHINE_CHECK, TAINT_BAD_PAGE don't -- cgit v1.1 From 97e1c18e8d17bd87e1e383b2e9d9fc740332c8e2 Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Fri, 18 Jul 2008 12:16:16 -0400 Subject: tracing: Kernel Tracepoints Implementation of kernel tracepoints. Inspired from the Linux Kernel Markers. Allows complete typing verification by declaring both tracing statement inline functions and probe registration/unregistration static inline functions within the same macro "DEFINE_TRACE". No format string is required. See the tracepoint Documentation and Samples patches for usage examples. Taken from the documentation patch : "A tracepoint placed in code provides a hook to call a function (probe) that you can provide at runtime. A tracepoint can be "on" (a probe is connected to it) or "off" (no probe is attached). When a tracepoint is "off" it has no effect, except for adding a tiny time penalty (checking a condition for a branch) and space penalty (adding a few bytes for the function call at the end of the instrumented function and adds a data structure in a separate section). When a tracepoint is "on", the function you provide is called each time the tracepoint is executed, in the execution context of the caller. When the function provided ends its execution, it returns to the caller (continuing from the tracepoint site). You can put tracepoints at important locations in the code. They are lightweight hooks that can pass an arbitrary number of parameters, which prototypes are described in a tracepoint declaration placed in a header file." Addition and removal of tracepoints is synchronized by RCU using the scheduler (and preempt_disable) as guarantees to find a quiescent state (this is really RCU "classic"). The update side uses rcu_barrier_sched() with call_rcu_sched() and the read/execute side uses "preempt_disable()/preempt_enable()". We make sure the previous array containing probes, which has been scheduled for deletion by the rcu callback, is indeed freed before we proceed to the next update. It therefore limits the rate of modification of a single tracepoint to one update per RCU period. The objective here is to permit fast batch add/removal of probes on _different_ tracepoints. Changelog : - Use #name ":" #proto as string to identify the tracepoint in the tracepoint table. This will make sure not type mismatch happens due to connexion of a probe with the wrong type to a tracepoint declared with the same name in a different header. - Add tracepoint_entry_free_old. - Change __TO_TRACE to get rid of the 'i' iterator. Masami Hiramatsu : Tested on x86-64. Performance impact of a tracepoint : same as markers, except that it adds about 70 bytes of instructions in an unlikely branch of each instrumented function (the for loop, the stack setup and the function call). It currently adds a memory read, a test and a conditional branch at the instrumentation site (in the hot path). Immediate values will eventually change this into a load immediate, test and branch, which removes the memory read which will make the i-cache impact smaller (changing the memory read for a load immediate removes 3-4 bytes per site on x86_32 (depending on mov prefixes), or 7-8 bytes on x86_64, it also saves the d-cache hit). About the performance impact of tracepoints (which is comparable to markers), even without immediate values optimizations, tests done by Hideo Aoki on ia64 show no regression. His test case was using hackbench on a kernel where scheduler instrumentation (about 5 events in code scheduler code) was added. Quoting Hideo Aoki about Markers : I evaluated overhead of kernel marker using linux-2.6-sched-fixes git tree, which includes several markers for LTTng, using an ia64 server. While the immediate trace mark feature isn't implemented on ia64, there is no major performance regression. So, I think that we don't have any issues to propose merging marker point patches into Linus's tree from the viewpoint of performance impact. I prepared two kernels to evaluate. The first one was compiled without CONFIG_MARKERS. The second one was enabled CONFIG_MARKERS. I downloaded the original hackbench from the following URL: http://devresources.linux-foundation.org/craiger/hackbench/src/hackbench.c I ran hackbench 5 times in each condition and calculated the average and difference between the kernels. The parameter of hackbench: every 50 from 50 to 800 The number of CPUs of the server: 2, 4, and 8 Below is the results. As you can see, major performance regression wasn't found in any case. Even if number of processes increases, differences between marker-enabled kernel and marker- disabled kernel doesn't increase. Moreover, if number of CPUs increases, the differences doesn't increase either. Curiously, marker-enabled kernel is better than marker-disabled kernel in more than half cases, although I guess it comes from the difference of memory access pattern. * 2 CPUs Number of | without | with | diff | diff | processes | Marker [Sec] | Marker [Sec] | [Sec] | [%] | -------------------------------------------------------------- 50 | 4.811 | 4.872 | +0.061 | +1.27 | 100 | 9.854 | 10.309 | +0.454 | +4.61 | 150 | 15.602 | 15.040 | -0.562 | -3.6 | 200 | 20.489 | 20.380 | -0.109 | -0.53 | 250 | 25.798 | 25.652 | -0.146 | -0.56 | 300 | 31.260 | 30.797 | -0.463 | -1.48 | 350 | 36.121 | 35.770 | -0.351 | -0.97 | 400 | 42.288 | 42.102 | -0.186 | -0.44 | 450 | 47.778 | 47.253 | -0.526 | -1.1 | 500 | 51.953 | 52.278 | +0.325 | +0.63 | 550 | 58.401 | 57.700 | -0.701 | -1.2 | 600 | 63.334 | 63.222 | -0.112 | -0.18 | 650 | 68.816 | 68.511 | -0.306 | -0.44 | 700 | 74.667 | 74.088 | -0.579 | -0.78 | 750 | 78.612 | 79.582 | +0.970 | +1.23 | 800 | 85.431 | 85.263 | -0.168 | -0.2 | -------------------------------------------------------------- * 4 CPUs Number of | without | with | diff | diff | processes | Marker [Sec] | Marker [Sec] | [Sec] | [%] | -------------------------------------------------------------- 50 | 2.586 | 2.584 | -0.003 | -0.1 | 100 | 5.254 | 5.283 | +0.030 | +0.56 | 150 | 8.012 | 8.074 | +0.061 | +0.76 | 200 | 11.172 | 11.000 | -0.172 | -1.54 | 250 | 13.917 | 14.036 | +0.119 | +0.86 | 300 | 16.905 | 16.543 | -0.362 | -2.14 | 350 | 19.901 | 20.036 | +0.135 | +0.68 | 400 | 22.908 | 23.094 | +0.186 | +0.81 | 450 | 26.273 | 26.101 | -0.172 | -0.66 | 500 | 29.554 | 29.092 | -0.461 | -1.56 | 550 | 32.377 | 32.274 | -0.103 | -0.32 | 600 | 35.855 | 35.322 | -0.533 | -1.49 | 650 | 39.192 | 38.388 | -0.804 | -2.05 | 700 | 41.744 | 41.719 | -0.025 | -0.06 | 750 | 45.016 | 44.496 | -0.520 | -1.16 | 800 | 48.212 | 47.603 | -0.609 | -1.26 | -------------------------------------------------------------- * 8 CPUs Number of | without | with | diff | diff | processes | Marker [Sec] | Marker [Sec] | [Sec] | [%] | -------------------------------------------------------------- 50 | 2.094 | 2.072 | -0.022 | -1.07 | 100 | 4.162 | 4.273 | +0.111 | +2.66 | 150 | 6.485 | 6.540 | +0.055 | +0.84 | 200 | 8.556 | 8.478 | -0.078 | -0.91 | 250 | 10.458 | 10.258 | -0.200 | -1.91 | 300 | 12.425 | 12.750 | +0.325 | +2.62 | 350 | 14.807 | 14.839 | +0.032 | +0.22 | 400 | 16.801 | 16.959 | +0.158 | +0.94 | 450 | 19.478 | 19.009 | -0.470 | -2.41 | 500 | 21.296 | 21.504 | +0.208 | +0.98 | 550 | 23.842 | 23.979 | +0.137 | +0.57 | 600 | 26.309 | 26.111 | -0.198 | -0.75 | 650 | 28.705 | 28.446 | -0.259 | -0.9 | 700 | 31.233 | 31.394 | +0.161 | +0.52 | 750 | 34.064 | 33.720 | -0.344 | -1.01 | 800 | 36.320 | 36.114 | -0.206 | -0.57 | -------------------------------------------------------------- Signed-off-by: Mathieu Desnoyers Acked-by: Masami Hiramatsu Acked-by: 'Peter Zijlstra' Signed-off-by: Ingo Molnar --- kernel/module.c | 66 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 65 insertions(+), 1 deletion(-) (limited to 'kernel/module.c') diff --git a/kernel/module.c b/kernel/module.c index 9db1191..661d73d 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -46,6 +46,7 @@ #include #include #include +#include #if 0 #define DEBUGP printk @@ -1831,6 +1832,8 @@ static noinline struct module *load_module(void __user *umod, #endif unsigned int markersindex; unsigned int markersstringsindex; + unsigned int tracepointsindex; + unsigned int tracepointsstringsindex; struct module *mod; long err = 0; void *percpu = NULL, *ptr = NULL; /* Stops spurious gcc warning */ @@ -2117,6 +2120,9 @@ static noinline struct module *load_module(void __user *umod, markersindex = find_sec(hdr, sechdrs, secstrings, "__markers"); markersstringsindex = find_sec(hdr, sechdrs, secstrings, "__markers_strings"); + tracepointsindex = find_sec(hdr, sechdrs, secstrings, "__tracepoints"); + tracepointsstringsindex = find_sec(hdr, sechdrs, secstrings, + "__tracepoints_strings"); /* Now do relocations. */ for (i = 1; i < hdr->e_shnum; i++) { @@ -2144,6 +2150,12 @@ static noinline struct module *load_module(void __user *umod, mod->num_markers = sechdrs[markersindex].sh_size / sizeof(*mod->markers); #endif +#ifdef CONFIG_TRACEPOINTS + mod->tracepoints = (void *)sechdrs[tracepointsindex].sh_addr; + mod->num_tracepoints = + sechdrs[tracepointsindex].sh_size / sizeof(*mod->tracepoints); +#endif + /* Find duplicate symbols */ err = verify_export_symbols(mod); @@ -2162,11 +2174,16 @@ static noinline struct module *load_module(void __user *umod, add_kallsyms(mod, sechdrs, symindex, strindex, secstrings); + if (!mod->taints) { #ifdef CONFIG_MARKERS - if (!mod->taints) marker_update_probe_range(mod->markers, mod->markers + mod->num_markers); #endif +#ifdef CONFIG_TRACEPOINTS + tracepoint_update_probe_range(mod->tracepoints, + mod->tracepoints + mod->num_tracepoints); +#endif + } err = module_finalize(hdr, sechdrs, mod); if (err < 0) goto cleanup; @@ -2717,3 +2734,50 @@ void module_update_markers(void) mutex_unlock(&module_mutex); } #endif + +#ifdef CONFIG_TRACEPOINTS +void module_update_tracepoints(void) +{ + struct module *mod; + + mutex_lock(&module_mutex); + list_for_each_entry(mod, &modules, list) + if (!mod->taints) + tracepoint_update_probe_range(mod->tracepoints, + mod->tracepoints + mod->num_tracepoints); + mutex_unlock(&module_mutex); +} + +/* + * Returns 0 if current not found. + * Returns 1 if current found. + */ +int module_get_iter_tracepoints(struct tracepoint_iter *iter) +{ + struct module *iter_mod; + int found = 0; + + mutex_lock(&module_mutex); + list_for_each_entry(iter_mod, &modules, list) { + if (!iter_mod->taints) { + /* + * Sorted module list + */ + if (iter_mod < iter->module) + continue; + else if (iter_mod > iter->module) + iter->tracepoint = NULL; + found = tracepoint_get_iter_range(&iter->tracepoint, + iter_mod->tracepoints, + iter_mod->tracepoints + + iter_mod->num_tracepoints); + if (found) { + iter->module = iter_mod; + break; + } + } + } + mutex_unlock(&module_mutex); + return found; +} +#endif -- cgit v1.1 From 90d595fe5ca4b685465c068907e6e554760abea8 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 14 Aug 2008 15:45:09 -0400 Subject: ftrace: enable mcount recording for modules This patch enables the loading of the __mcount_section of modules and changing all the callers of mcount into nops. The modification is done before the init_module function is called, so again, we do not need to use kstop_machine to make these changes. Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar --- kernel/module.c | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'kernel/module.c') diff --git a/kernel/module.c b/kernel/module.c index 661d73d..d753fd9 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -47,6 +47,7 @@ #include #include #include +#include #if 0 #define DEBUGP printk @@ -1834,6 +1835,7 @@ static noinline struct module *load_module(void __user *umod, unsigned int markersstringsindex; unsigned int tracepointsindex; unsigned int tracepointsstringsindex; + unsigned int mcountindex; struct module *mod; long err = 0; void *percpu = NULL, *ptr = NULL; /* Stops spurious gcc warning */ @@ -2124,6 +2126,9 @@ static noinline struct module *load_module(void __user *umod, tracepointsstringsindex = find_sec(hdr, sechdrs, secstrings, "__tracepoints_strings"); + mcountindex = find_sec(hdr, sechdrs, secstrings, + "__mcount_loc"); + /* Now do relocations. */ for (i = 1; i < hdr->e_shnum; i++) { const char *strtab = (char *)sechdrs[strindex].sh_addr; @@ -2184,6 +2189,12 @@ static noinline struct module *load_module(void __user *umod, mod->tracepoints + mod->num_tracepoints); #endif } + + if (mcountindex) { + void *mseg = (void *)sechdrs[mcountindex].sh_addr; + ftrace_init_module(mseg, mseg + sechdrs[mcountindex].sh_size); + } + err = module_finalize(hdr, sechdrs, mod); if (err < 0) goto cleanup; -- cgit v1.1 From fed1939c64d2288938fdc1c367d49082da65e195 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 14 Aug 2008 22:47:19 -0400 Subject: ftrace: remove old pointers to mcount When a mcount pointer is recorded into a table, it is used to add or remove calls to mcount (replacing them with nops). If the code is removed via removing a module, the pointers still exist. At modifying the code a check is always made to make sure the code being replaced is the code expected. In-other-words, the code being replaced is compared to what it is expected to be before being replaced. There is a very small chance that the code being replaced just happens to look like code that calls mcount (very small since the call to mcount is relative). To remove this chance, this patch adds ftrace_release to allow module unloading to remove the pointers to mcount within the module. Another change for init calls is made to not trace calls marked with __init. The tracing can not be started until after init is done anyway. Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar --- kernel/module.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'kernel/module.c') diff --git a/kernel/module.c b/kernel/module.c index d753fd9..7576c2d 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1431,6 +1431,9 @@ static void free_module(struct module *mod) /* Module unload stuff */ module_unload_free(mod); + /* release any pointers to mcount in this module */ + ftrace_release(mod->module_core, mod->core_size); + /* This may be NULL, but that's OK */ module_free(mod, mod->module_init); kfree(mod->args); @@ -1839,6 +1842,7 @@ static noinline struct module *load_module(void __user *umod, struct module *mod; long err = 0; void *percpu = NULL, *ptr = NULL; /* Stops spurious gcc warning */ + void *mseg; struct exception_table_entry *extable; mm_segment_t old_fs; @@ -2190,10 +2194,9 @@ static noinline struct module *load_module(void __user *umod, #endif } - if (mcountindex) { - void *mseg = (void *)sechdrs[mcountindex].sh_addr; - ftrace_init_module(mseg, mseg + sechdrs[mcountindex].sh_size); - } + /* sechdrs[0].sh_size is always zero */ + mseg = (void *)sechdrs[mcountindex].sh_addr; + ftrace_init_module(mseg, mseg + sechdrs[mcountindex].sh_size); err = module_finalize(hdr, sechdrs, mod); if (err < 0) @@ -2264,6 +2267,7 @@ static noinline struct module *load_module(void __user *umod, cleanup: kobject_del(&mod->mkobj.kobj); kobject_put(&mod->mkobj.kobj); + ftrace_release(mod->module_core, mod->core_size); free_unload: module_unload_free(mod); module_free(mod, mod->module_init); -- cgit v1.1 From e94320939f44e0cbaccc3f259a5778abced4949c Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Tue, 23 Sep 2008 23:51:11 +0400 Subject: modules: fix module "notes" kobject leak Fix "notes" kobject leak It happens every rmmod if KALLSYMS=y and SYSFS=y. # modprobe foo kobject: 'foo' (ffffffffa00743d0): kobject_add_internal: parent: 'module', set: 'module' kobject: 'holders' (ffff88017e7c5770): kobject_add_internal: parent: 'foo', set: '' kobject: 'foo' (ffffffffa00743d0): kobject_uevent_env kobject: 'foo' (ffffffffa00743d0): fill_kobj_path: path = '/module/foo' kobject: 'notes' (ffff88017fa9b668): kobject_add_internal: parent: 'foo', set: '' ^^^^^ # rmmod foo kobject: 'holders' (ffff88017e7c5770): kobject_cleanup kobject: 'holders' (ffff88017e7c5770): auto cleanup kobject_del kobject: 'holders' (ffff88017e7c5770): calling ktype release kobject: (ffff88017e7c5770): dynamic_kobj_release kobject: 'holders': free name kobject: 'foo' (ffffffffa00743d0): kobject_cleanup kobject: 'foo' (ffffffffa00743d0): does not have a release() function, it is broken and must be fixed. kobject: 'foo' (ffffffffa00743d0): auto cleanup 'remove' event kobject: 'foo' (ffffffffa00743d0): kobject_uevent_env kobject: 'foo' (ffffffffa00743d0): fill_kobj_path: path = '/module/foo' kobject: 'foo' (ffffffffa00743d0): auto cleanup kobject_del kobject: 'foo': free name [whooops] Signed-off-by: Alexey Dobriyan Cc: stable Signed-off-by: Greg Kroah-Hartman --- 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 9db1191..d5fcd24 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1173,7 +1173,7 @@ static void free_notes_attrs(struct module_notes_attrs *notes_attrs, while (i-- > 0) sysfs_remove_bin_file(notes_attrs->dir, ¬es_attrs->attrs[i]); - kobject_del(notes_attrs->dir); + kobject_put(notes_attrs->dir); } kfree(notes_attrs); } -- cgit v1.1 From 346e15beb5343c2eb8216d820f2ed8f150822b08 Mon Sep 17 00:00:00 2001 From: Jason Baron Date: Tue, 12 Aug 2008 16:46:19 -0400 Subject: driver core: basic infrastructure for per-module dynamic debug messages Base infrastructure to enable per-module debug messages. I've introduced CONFIG_DYNAMIC_PRINTK_DEBUG, which when enabled centralizes control of debugging statements on a per-module basis in one /proc file, currently, /dynamic_printk/modules. When, CONFIG_DYNAMIC_PRINTK_DEBUG, is not set, debugging statements can still be enabled as before, often by defining 'DEBUG' for the proper compilation unit. Thus, this patch set has no affect when CONFIG_DYNAMIC_PRINTK_DEBUG is not set. The infrastructure currently ties into all pr_debug() and dev_dbg() calls. That is, if CONFIG_DYNAMIC_PRINTK_DEBUG is set, all pr_debug() and dev_dbg() calls can be dynamically enabled/disabled on a per-module basis. Future plans include extending this functionality to subsystems, that define their own debug levels and flags. Usage: Dynamic debugging is controlled by the debugfs file, /dynamic_printk/modules. This file contains a list of the modules that can be enabled. The format of the file is as follows: . . . : Name of the module in which the debug call resides : whether the messages are enabled or not For example: snd_hda_intel enabled=0 fixup enabled=1 driver enabled=0 Enable a module: $echo "set enabled=1 " > dynamic_printk/modules Disable a module: $echo "set enabled=0 " > dynamic_printk/modules Enable all modules: $echo "set enabled=1 all" > dynamic_printk/modules Disable all modules: $echo "set enabled=0 all" > dynamic_printk/modules Finally, passing "dynamic_printk" at the command line enables debugging for all modules. This mode can be turned off via the above disable command. [gkh: minor cleanups and tweaks to make the build work quietly] Signed-off-by: Jason Baron Signed-off-by: Greg Kroah-Hartman --- kernel/module.c | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'kernel/module.c') diff --git a/kernel/module.c b/kernel/module.c index d5fcd24..c527006 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -784,6 +784,7 @@ sys_delete_module(const char __user *name_user, unsigned int flags) 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); free_module(mod); out: @@ -1783,6 +1784,33 @@ static inline void add_kallsyms(struct module *mod, } #endif /* CONFIG_KALLSYMS */ +#ifdef CONFIG_DYNAMIC_PRINTK_DEBUG +static void dynamic_printk_setup(Elf_Shdr *sechdrs, unsigned int verboseindex) +{ + struct mod_debug *debug_info; + unsigned long pos, end; + unsigned int num_verbose; + + pos = sechdrs[verboseindex].sh_addr; + num_verbose = sechdrs[verboseindex].sh_size / + sizeof(struct mod_debug); + end = pos + (num_verbose * sizeof(struct mod_debug)); + + for (; pos < end; pos += sizeof(struct mod_debug)) { + debug_info = (struct mod_debug *)pos; + register_dynamic_debug_module(debug_info->modname, + debug_info->type, debug_info->logical_modname, + debug_info->flag_names, debug_info->hash, + debug_info->hash2); + } +} +#else +static inline void dynamic_printk_setup(Elf_Shdr *sechdrs, + unsigned int verboseindex) +{ +} +#endif /* CONFIG_DYNAMIC_PRINTK_DEBUG */ + static void *module_alloc_update_bounds(unsigned long size) { void *ret = module_alloc(size); @@ -1831,6 +1859,7 @@ static noinline struct module *load_module(void __user *umod, #endif unsigned int markersindex; unsigned int markersstringsindex; + unsigned int verboseindex; struct module *mod; long err = 0; void *percpu = NULL, *ptr = NULL; /* Stops spurious gcc warning */ @@ -2117,6 +2146,7 @@ static noinline struct module *load_module(void __user *umod, markersindex = find_sec(hdr, sechdrs, secstrings, "__markers"); markersstringsindex = find_sec(hdr, sechdrs, secstrings, "__markers_strings"); + verboseindex = find_sec(hdr, sechdrs, secstrings, "__verbose"); /* Now do relocations. */ for (i = 1; i < hdr->e_shnum; i++) { @@ -2167,6 +2197,7 @@ static noinline struct module *load_module(void __user *umod, marker_update_probe_range(mod->markers, mod->markers + mod->num_markers); #endif + dynamic_printk_setup(sechdrs, verboseindex); err = module_finalize(hdr, sechdrs, mod); if (err < 0) goto cleanup; -- cgit v1.1 From 25ddbb18aae33ad255eb9f35aacebe3af01e1e9c Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Wed, 15 Oct 2008 22:01:41 -0700 Subject: Make the taint flags reliable It's somewhat unlikely that it happens, but right now a race window between interrupts or machine checks or oopses could corrupt the tainted bitmap because it is modified in a non atomic fashion. Convert the taint variable to an unsigned long and use only atomic bit operations on it. Unfortunately this means the intvec sysctl functions cannot be used on it anymore. It turned out the taint sysctl handler could actually be simplified a bit (since it only increases capabilities) so this patch actually removes code. [akpm@linux-foundation.org: remove unneeded include] Signed-off-by: Andi Kleen Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- 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 9db1191..dd9ac6a 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -100,7 +100,7 @@ static inline int strong_try_module_get(struct module *mod) static inline void add_taint_module(struct module *mod, unsigned flag) { add_taint(flag); - mod->taints |= flag; + mod->taints |= (1U << flag); } /* @@ -923,7 +923,7 @@ static const char vermagic[] = VERMAGIC_STRING; static int try_to_force_load(struct module *mod, const char *symname) { #ifdef CONFIG_MODULE_FORCE_LOAD - if (!(tainted & TAINT_FORCED_MODULE)) + if (!test_taint(TAINT_FORCED_MODULE)) printk("%s: no version for \"%s\" found: kernel tainted.\n", mod->name, symname); add_taint_module(mod, TAINT_FORCED_MODULE); @@ -1033,7 +1033,7 @@ static unsigned long resolve_symbol(Elf_Shdr *sechdrs, const unsigned long *crc; ret = find_symbol(name, &owner, &crc, - !(mod->taints & TAINT_PROPRIETARY_MODULE), true); + !(mod->taints & (1 << TAINT_PROPRIETARY_MODULE)), true); if (!IS_ERR_VALUE(ret)) { /* use_module can fail due to OOM, or module initialization or unloading */ @@ -1634,7 +1634,7 @@ static void set_license(struct module *mod, const char *license) license = "unspecified"; if (!license_is_gpl_compatible(license)) { - if (!(tainted & TAINT_PROPRIETARY_MODULE)) + if (!test_taint(TAINT_PROPRIETARY_MODULE)) printk(KERN_WARNING "%s: module license '%s' taints " "kernel.\n", mod->name, license); add_taint_module(mod, TAINT_PROPRIETARY_MODULE); @@ -2552,9 +2552,9 @@ static char *module_flags(struct module *mod, char *buf) mod->state == MODULE_STATE_GOING || mod->state == MODULE_STATE_COMING) { buf[bx++] = '('; - if (mod->taints & TAINT_PROPRIETARY_MODULE) + if (mod->taints & (1 << TAINT_PROPRIETARY_MODULE)) buf[bx++] = 'P'; - if (mod->taints & TAINT_FORCED_MODULE) + if (mod->taints & (1 << TAINT_FORCED_MODULE)) buf[bx++] = 'F'; /* * TAINT_FORCED_RMMOD: could be added. -- cgit v1.1 From 5e458cc0f4770eea45d3c07110f01b3a94c72aa5 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Wed, 22 Oct 2008 10:00:13 -0500 Subject: module: simplify load_module. Linus' recent catch of stack overflow in load_module lead me to look at the code. A couple of helpers to get a section address and get objects from a section can help clean things up a little. (And in case you're wondering, the stack size also dropped from 328 to 284 bytes). Signed-off-by: Rusty Russell --- kernel/module.c | 235 ++++++++++++++++++++++++-------------------------------- 1 file changed, 99 insertions(+), 136 deletions(-) (limited to 'kernel/module.c') diff --git a/kernel/module.c b/kernel/module.c index 0d8d21e..3d25668 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -132,6 +132,29 @@ static unsigned int find_sec(Elf_Ehdr *hdr, return 0; } +/* Find a module section, or NULL. */ +static void *section_addr(Elf_Ehdr *hdr, Elf_Shdr *shdrs, + const char *secstrings, const char *name) +{ + /* Section 0 has sh_addr 0. */ + return (void *)shdrs[find_sec(hdr, shdrs, secstrings, name)].sh_addr; +} + +/* Find a module section, or NULL. Fill in number of "objects" in section. */ +static void *section_objs(Elf_Ehdr *hdr, + Elf_Shdr *sechdrs, + const char *secstrings, + const char *name, + size_t object_size, + unsigned int *num) +{ + unsigned int sec = find_sec(hdr, sechdrs, secstrings, name); + + /* Section 0 has sh_addr 0 and sh_size 0. */ + *num = sechdrs[sec].sh_size / object_size; + return (void *)sechdrs[sec].sh_addr; +} + /* Provided by the linker */ extern const struct kernel_symbol __start___ksymtab[]; extern const struct kernel_symbol __stop___ksymtab[]; @@ -1789,32 +1812,20 @@ static inline void add_kallsyms(struct module *mod, } #endif /* CONFIG_KALLSYMS */ -#ifdef CONFIG_DYNAMIC_PRINTK_DEBUG -static void dynamic_printk_setup(Elf_Shdr *sechdrs, unsigned int verboseindex) +static void dynamic_printk_setup(struct mod_debug *debug, unsigned int num) { - struct mod_debug *debug_info; - unsigned long pos, end; - unsigned int num_verbose; - - pos = sechdrs[verboseindex].sh_addr; - num_verbose = sechdrs[verboseindex].sh_size / - sizeof(struct mod_debug); - end = pos + (num_verbose * sizeof(struct mod_debug)); +#ifdef CONFIG_DYNAMIC_PRINTK_DEBUG + unsigned int i; - for (; pos < end; pos += sizeof(struct mod_debug)) { - debug_info = (struct mod_debug *)pos; - register_dynamic_debug_module(debug_info->modname, - debug_info->type, debug_info->logical_modname, - debug_info->flag_names, debug_info->hash, - debug_info->hash2); + 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); } -} -#else -static inline void dynamic_printk_setup(Elf_Shdr *sechdrs, - unsigned int verboseindex) -{ -} #endif /* CONFIG_DYNAMIC_PRINTK_DEBUG */ +} static void *module_alloc_update_bounds(unsigned long size) { @@ -1843,37 +1854,14 @@ static noinline struct module *load_module(void __user *umod, unsigned int i; unsigned int symindex = 0; unsigned int strindex = 0; - unsigned int setupindex; - unsigned int exindex; - unsigned int exportindex; - unsigned int modindex; - unsigned int obsparmindex; - unsigned int infoindex; - unsigned int gplindex; - unsigned int crcindex; - unsigned int gplcrcindex; - unsigned int versindex; - unsigned int pcpuindex; - unsigned int gplfutureindex; - unsigned int gplfuturecrcindex; + unsigned int modindex, versindex, infoindex, pcpuindex; unsigned int unwindex = 0; -#ifdef CONFIG_UNUSED_SYMBOLS - unsigned int unusedindex; - unsigned int unusedcrcindex; - unsigned int unusedgplindex; - unsigned int unusedgplcrcindex; -#endif - unsigned int markersindex; - unsigned int markersstringsindex; - unsigned int verboseindex; - unsigned int tracepointsindex; - unsigned int tracepointsstringsindex; - unsigned int mcountindex; + unsigned int num_kp, num_mcount; + struct kernel_param *kp; struct module *mod; long err = 0; void *percpu = NULL, *ptr = NULL; /* Stops spurious gcc warning */ - void *mseg; - struct exception_table_entry *extable; + unsigned long *mseg; mm_segment_t old_fs; DEBUGP("load_module: umod=%p, len=%lu, uargs=%p\n", @@ -1937,6 +1925,7 @@ static noinline struct module *load_module(void __user *umod, err = -ENOEXEC; goto free_hdr; } + /* This is temporary: point mod into copy of data. */ mod = (void *)sechdrs[modindex].sh_addr; if (symindex == 0) { @@ -1946,22 +1935,6 @@ static noinline struct module *load_module(void __user *umod, goto free_hdr; } - /* Optional sections */ - exportindex = find_sec(hdr, sechdrs, secstrings, "__ksymtab"); - gplindex = find_sec(hdr, sechdrs, secstrings, "__ksymtab_gpl"); - gplfutureindex = find_sec(hdr, sechdrs, secstrings, "__ksymtab_gpl_future"); - crcindex = find_sec(hdr, sechdrs, secstrings, "__kcrctab"); - gplcrcindex = find_sec(hdr, sechdrs, secstrings, "__kcrctab_gpl"); - gplfuturecrcindex = find_sec(hdr, sechdrs, secstrings, "__kcrctab_gpl_future"); -#ifdef CONFIG_UNUSED_SYMBOLS - unusedindex = find_sec(hdr, sechdrs, secstrings, "__ksymtab_unused"); - unusedgplindex = find_sec(hdr, sechdrs, secstrings, "__ksymtab_unused_gpl"); - unusedcrcindex = find_sec(hdr, sechdrs, secstrings, "__kcrctab_unused"); - unusedgplcrcindex = find_sec(hdr, sechdrs, secstrings, "__kcrctab_unused_gpl"); -#endif - setupindex = find_sec(hdr, sechdrs, secstrings, "__param"); - exindex = find_sec(hdr, sechdrs, secstrings, "__ex_table"); - obsparmindex = find_sec(hdr, sechdrs, secstrings, "__obsparm"); versindex = find_sec(hdr, sechdrs, secstrings, "__versions"); infoindex = find_sec(hdr, sechdrs, secstrings, ".modinfo"); pcpuindex = find_pcpusec(hdr, sechdrs, secstrings); @@ -2117,42 +2090,57 @@ static noinline struct module *load_module(void __user *umod, if (err < 0) goto cleanup; - /* Set up EXPORTed & EXPORT_GPLed symbols (section 0 is 0 length) */ - mod->num_syms = sechdrs[exportindex].sh_size / sizeof(*mod->syms); - mod->syms = (void *)sechdrs[exportindex].sh_addr; - if (crcindex) - mod->crcs = (void *)sechdrs[crcindex].sh_addr; - mod->num_gpl_syms = sechdrs[gplindex].sh_size / sizeof(*mod->gpl_syms); - mod->gpl_syms = (void *)sechdrs[gplindex].sh_addr; - if (gplcrcindex) - mod->gpl_crcs = (void *)sechdrs[gplcrcindex].sh_addr; - mod->num_gpl_future_syms = sechdrs[gplfutureindex].sh_size / - sizeof(*mod->gpl_future_syms); - mod->gpl_future_syms = (void *)sechdrs[gplfutureindex].sh_addr; - if (gplfuturecrcindex) - mod->gpl_future_crcs = (void *)sechdrs[gplfuturecrcindex].sh_addr; + /* 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->syms = section_objs(hdr, sechdrs, secstrings, "__ksymtab", + sizeof(*mod->syms), &mod->num_syms); + mod->crcs = section_addr(hdr, sechdrs, secstrings, "__kcrctab"); + mod->gpl_syms = section_objs(hdr, sechdrs, secstrings, "__ksymtab_gpl", + sizeof(*mod->gpl_syms), + &mod->num_gpl_syms); + mod->gpl_crcs = section_addr(hdr, sechdrs, secstrings, "__kcrctab_gpl"); + mod->gpl_future_syms = section_objs(hdr, sechdrs, secstrings, + "__ksymtab_gpl_future", + sizeof(*mod->gpl_future_syms), + &mod->num_gpl_future_syms); + mod->gpl_future_crcs = section_addr(hdr, sechdrs, secstrings, + "__kcrctab_gpl_future"); #ifdef CONFIG_UNUSED_SYMBOLS - mod->num_unused_syms = sechdrs[unusedindex].sh_size / - sizeof(*mod->unused_syms); - mod->num_unused_gpl_syms = sechdrs[unusedgplindex].sh_size / - sizeof(*mod->unused_gpl_syms); - mod->unused_syms = (void *)sechdrs[unusedindex].sh_addr; - if (unusedcrcindex) - mod->unused_crcs = (void *)sechdrs[unusedcrcindex].sh_addr; - mod->unused_gpl_syms = (void *)sechdrs[unusedgplindex].sh_addr; - if (unusedgplcrcindex) - mod->unused_gpl_crcs - = (void *)sechdrs[unusedgplcrcindex].sh_addr; + mod->unused_syms = section_objs(hdr, sechdrs, secstrings, + "__ksymtab_unused", + sizeof(*mod->unused_syms), + &mod->num_unused_syms); + mod->unused_crcs = section_addr(hdr, sechdrs, secstrings, + "__kcrctab_unused"); + mod->unused_gpl_syms = section_objs(hdr, sechdrs, secstrings, + "__ksymtab_unused_gpl", + sizeof(*mod->unused_gpl_syms), + &mod->num_unused_gpl_syms); + mod->unused_gpl_crcs = section_addr(hdr, sechdrs, secstrings, + "__kcrctab_unused_gpl"); +#endif + +#ifdef CONFIG_MARKERS + mod->markers = section_objs(hdr, sechdrs, secstrings, "__markers", + sizeof(*mod->markers), &mod->num_markers); +#endif +#ifdef CONFIG_TRACEPOINTS + mod->tracepoints = section_objs(hdr, sechdrs, secstrings, + "__tracepoints", + sizeof(*mod->tracepoints), + &mod->num_tracepoints); #endif #ifdef CONFIG_MODVERSIONS - if ((mod->num_syms && !crcindex) - || (mod->num_gpl_syms && !gplcrcindex) - || (mod->num_gpl_future_syms && !gplfuturecrcindex) + if ((mod->num_syms && !mod->crcs) + || (mod->num_gpl_syms && !mod->gpl_crcs) + || (mod->num_gpl_future_syms && !mod->gpl_future_crcs) #ifdef CONFIG_UNUSED_SYMBOLS - || (mod->num_unused_syms && !unusedcrcindex) - || (mod->num_unused_gpl_syms && !unusedgplcrcindex) + || (mod->num_unused_syms && !mod->unused_crcs) + || (mod->num_unused_gpl_syms && !mod->unused_gpl_crcs) #endif ) { printk(KERN_WARNING "%s: No versions for exported symbols.\n", mod->name); @@ -2161,16 +2149,6 @@ static noinline struct module *load_module(void __user *umod, goto cleanup; } #endif - markersindex = find_sec(hdr, sechdrs, secstrings, "__markers"); - markersstringsindex = find_sec(hdr, sechdrs, secstrings, - "__markers_strings"); - verboseindex = find_sec(hdr, sechdrs, secstrings, "__verbose"); - tracepointsindex = find_sec(hdr, sechdrs, secstrings, "__tracepoints"); - tracepointsstringsindex = find_sec(hdr, sechdrs, secstrings, - "__tracepoints_strings"); - - mcountindex = find_sec(hdr, sechdrs, secstrings, - "__mcount_loc"); /* Now do relocations. */ for (i = 1; i < hdr->e_shnum; i++) { @@ -2193,28 +2171,16 @@ static noinline struct module *load_module(void __user *umod, if (err < 0) goto cleanup; } -#ifdef CONFIG_MARKERS - mod->markers = (void *)sechdrs[markersindex].sh_addr; - mod->num_markers = - sechdrs[markersindex].sh_size / sizeof(*mod->markers); -#endif -#ifdef CONFIG_TRACEPOINTS - mod->tracepoints = (void *)sechdrs[tracepointsindex].sh_addr; - mod->num_tracepoints = - sechdrs[tracepointsindex].sh_size / sizeof(*mod->tracepoints); -#endif - /* Find duplicate symbols */ err = verify_export_symbols(mod); - if (err < 0) goto cleanup; /* Set up and sort exception table */ - mod->num_exentries = sechdrs[exindex].sh_size / sizeof(*mod->extable); - mod->extable = extable = (void *)sechdrs[exindex].sh_addr; - sort_extable(extable, extable + mod->num_exentries); + mod->extable = section_objs(hdr, sechdrs, secstrings, "__ex_table", + sizeof(*mod->extable), &mod->num_exentries); + sort_extable(mod->extable, mod->extable + mod->num_exentries); /* Finally, copy percpu area over. */ percpu_modcopy(mod->percpu, (void *)sechdrs[pcpuindex].sh_addr, @@ -2223,11 +2189,17 @@ static noinline struct module *load_module(void __user *umod, add_kallsyms(mod, sechdrs, symindex, strindex, secstrings); if (!mod->taints) { + struct mod_debug *debug; + unsigned int num_debug; + #ifdef CONFIG_MARKERS marker_update_probe_range(mod->markers, mod->markers + mod->num_markers); #endif - dynamic_printk_setup(sechdrs, verboseindex); + debug = section_objs(hdr, sechdrs, secstrings, "__verbose", + sizeof(*debug), &num_debug); + dynamic_printk_setup(debug, num_debug); + #ifdef CONFIG_TRACEPOINTS tracepoint_update_probe_range(mod->tracepoints, mod->tracepoints + mod->num_tracepoints); @@ -2235,8 +2207,9 @@ static noinline struct module *load_module(void __user *umod, } /* sechdrs[0].sh_size is always zero */ - mseg = (void *)sechdrs[mcountindex].sh_addr; - ftrace_init_module(mseg, mseg + sechdrs[mcountindex].sh_size); + mseg = section_objs(hdr, sechdrs, secstrings, "__mcount_loc", + sizeof(*mseg), &num_mcount); + ftrace_init_module(mseg, mseg + num_mcount); err = module_finalize(hdr, sechdrs, mod); if (err < 0) @@ -2261,7 +2234,7 @@ static noinline struct module *load_module(void __user *umod, set_fs(old_fs); mod->args = args; - if (obsparmindex) + if (section_addr(hdr, sechdrs, secstrings, "__obsparm")) printk(KERN_WARNING "%s: Ignoring obsolete parameters\n", mod->name); @@ -2270,21 +2243,11 @@ static noinline struct module *load_module(void __user *umod, * strong_try_module_get() will fail. */ stop_machine(__link_module, mod, NULL); - /* Size of section 0 is 0, so this works well if no params */ - err = parse_args(mod->name, mod->args, - (struct kernel_param *) - sechdrs[setupindex].sh_addr, - sechdrs[setupindex].sh_size - / sizeof(struct kernel_param), - NULL); + err = parse_args(mod->name, mod->args, kp, num_kp, NULL); if (err < 0) goto unlink; - err = mod_sysfs_setup(mod, - (struct kernel_param *) - sechdrs[setupindex].sh_addr, - sechdrs[setupindex].sh_size - / sizeof(struct kernel_param)); + err = mod_sysfs_setup(mod, kp, num_kp); if (err < 0) goto unlink; add_sect_attrs(mod, hdr->e_shnum, secstrings, sechdrs); -- cgit v1.1 From d72b37513cdfbd3f53f3d485a8c403cc96d2c95f Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Sat, 30 Aug 2008 10:09:00 +0200 Subject: Remove stop_machine during module load v2 Remove stop_machine during module load v2 module loading currently does a stop_machine on each module load to insert the module into the global module lists. Especially on larger systems this can be quite expensive. It does that to handle concurrent lock lessmodule list readers like kallsyms. I don't think stop_machine() is actually needed to insert something into a list though. There are no concurrent writers because the module mutex is taken. And the RCU list functions know how to insert a node into a list with the right memory ordering so that concurrent readers don't go off into the wood. So remove the stop_machine for the module list insert and just do a list_add_rcu() instead. Module removal will still do a stop_machine of course, it needs that for other reasons. v2: Revised readers based on Paul's comments. All readers that only rely on disabled preemption need to be changed to list_for_each_rcu(). Done that. The others are ok because they have the modules mutex. Also added a possible missing preempt disable for print_modules(). [cc Paul McKenney for review. It's not RCU, but quite similar.] Acked-by: Paul E. McKenney Signed-off-by: Rusty Russell --- kernel/module.c | 47 ++++++++++++++++++++++------------------------- 1 file changed, 22 insertions(+), 25 deletions(-) (limited to 'kernel/module.c') diff --git a/kernel/module.c b/kernel/module.c index 3d25668..c0f1826 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -42,6 +42,7 @@ #include #include #include +#include #include #include #include @@ -63,7 +64,7 @@ #define INIT_OFFSET_MASK (1UL << (BITS_PER_LONG-1)) /* List of modules, protected by module_mutex or preempt_disable - * (add/delete uses stop_machine). */ + * (delete uses stop_machine/add uses RCU list operations). */ static DEFINE_MUTEX(module_mutex); static LIST_HEAD(modules); @@ -241,7 +242,7 @@ static bool each_symbol(bool (*fn)(const struct symsearch *arr, if (each_symbol_in_section(arr, ARRAY_SIZE(arr), NULL, fn, data)) return true; - list_for_each_entry(mod, &modules, list) { + list_for_each_entry_rcu(mod, &modules, list) { struct symsearch arr[] = { { mod->syms, mod->syms + mod->num_syms, mod->crcs, NOT_GPL_ONLY, false }, @@ -1417,17 +1418,6 @@ static void mod_kobject_remove(struct module *mod) } /* - * link the module with the whole machine is stopped with interrupts off - * - this defends against kallsyms not taking locks - */ -static int __link_module(void *_mod) -{ - struct module *mod = _mod; - list_add(&mod->list, &modules); - return 0; -} - -/* * unlink the module with the whole machine is stopped with interrupts off * - this defends against kallsyms not taking locks */ @@ -2239,9 +2229,13 @@ static noinline struct module *load_module(void __user *umod, mod->name); /* Now sew it into the lists so we can get lockdep and oops - * info during argument parsing. Noone should access us, since - * strong_try_module_get() will fail. */ - stop_machine(__link_module, mod, NULL); + * info during argument parsing. Noone should access us, since + * strong_try_module_get() will fail. + * lockdep/oops can run asynchronous, so use the RCU list insertion + * function to insert in a way safe to concurrent readers. + * The mutex protects against concurrent writers. + */ + list_add_rcu(&mod->list, &modules); err = parse_args(mod->name, mod->args, kp, num_kp, NULL); if (err < 0) @@ -2436,7 +2430,7 @@ const char *module_address_lookup(unsigned long addr, const char *ret = NULL; preempt_disable(); - list_for_each_entry(mod, &modules, list) { + list_for_each_entry_rcu(mod, &modules, list) { if (within(addr, mod->module_init, mod->init_size) || within(addr, mod->module_core, mod->core_size)) { if (modname) @@ -2459,7 +2453,7 @@ int lookup_module_symbol_name(unsigned long addr, char *symname) struct module *mod; preempt_disable(); - list_for_each_entry(mod, &modules, list) { + list_for_each_entry_rcu(mod, &modules, list) { if (within(addr, mod->module_init, mod->init_size) || within(addr, mod->module_core, mod->core_size)) { const char *sym; @@ -2483,7 +2477,7 @@ int lookup_module_symbol_attrs(unsigned long addr, unsigned long *size, struct module *mod; preempt_disable(); - list_for_each_entry(mod, &modules, list) { + list_for_each_entry_rcu(mod, &modules, list) { if (within(addr, mod->module_init, mod->init_size) || within(addr, mod->module_core, mod->core_size)) { const char *sym; @@ -2510,7 +2504,7 @@ int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type, struct module *mod; preempt_disable(); - list_for_each_entry(mod, &modules, list) { + list_for_each_entry_rcu(mod, &modules, list) { if (symnum < mod->num_symtab) { *value = mod->symtab[symnum].st_value; *type = mod->symtab[symnum].st_info; @@ -2553,7 +2547,7 @@ unsigned long module_kallsyms_lookup_name(const char *name) ret = mod_find_symname(mod, colon+1); *colon = ':'; } else { - list_for_each_entry(mod, &modules, list) + list_for_each_entry_rcu(mod, &modules, list) if ((ret = mod_find_symname(mod, name)) != 0) break; } @@ -2656,7 +2650,7 @@ const struct exception_table_entry *search_module_extables(unsigned long addr) struct module *mod; preempt_disable(); - list_for_each_entry(mod, &modules, list) { + list_for_each_entry_rcu(mod, &modules, list) { if (mod->num_exentries == 0) continue; @@ -2682,7 +2676,7 @@ int is_module_address(unsigned long addr) preempt_disable(); - list_for_each_entry(mod, &modules, list) { + list_for_each_entry_rcu(mod, &modules, list) { if (within(addr, mod->module_core, mod->core_size)) { preempt_enable(); return 1; @@ -2703,7 +2697,7 @@ struct module *__module_text_address(unsigned long addr) if (addr < module_addr_min || addr > module_addr_max) return NULL; - list_for_each_entry(mod, &modules, list) + 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)) return mod; @@ -2728,8 +2722,11 @@ void print_modules(void) char buf[8]; printk("Modules linked in:"); - list_for_each_entry(mod, &modules, list) + /* Most callers should already have preempt disabled, but make sure */ + preempt_disable(); + list_for_each_entry_rcu(mod, &modules, list) printk(" %s%s", mod->name, module_flags(mod, buf)); + preempt_enable(); if (last_unloaded_module[0]) printk(" [last unloaded: %s]", last_unloaded_module); printk("\n"); -- cgit v1.1 From 3b5d5c6b0ccba733a313f8752ebc3f8015628ba3 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Mon, 6 Oct 2008 13:19:27 +0400 Subject: proc: move /proc/modules boilerplate to kernel/module.c Signed-off-by: Alexey Dobriyan --- kernel/module.c | 59 +++++++++++++++++++++++++++++++++++++++------------------ 1 file changed, 41 insertions(+), 18 deletions(-) (limited to 'kernel/module.c') diff --git a/kernel/module.c b/kernel/module.c index 0d8d21e..6fded84 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -20,11 +20,13 @@ #include #include #include +#include #include #include #include #include #include +#include #include #include #include @@ -2599,23 +2601,6 @@ unsigned long module_kallsyms_lookup_name(const char *name) } #endif /* CONFIG_KALLSYMS */ -/* Called by the /proc file system to return a list of modules. */ -static void *m_start(struct seq_file *m, loff_t *pos) -{ - mutex_lock(&module_mutex); - return seq_list_start(&modules, *pos); -} - -static void *m_next(struct seq_file *m, void *p, loff_t *pos) -{ - return seq_list_next(p, &modules, pos); -} - -static void m_stop(struct seq_file *m, void *p) -{ - mutex_unlock(&module_mutex); -} - static char *module_flags(struct module *mod, char *buf) { int bx = 0; @@ -2649,6 +2634,24 @@ static char *module_flags(struct module *mod, char *buf) return buf; } +#ifdef CONFIG_PROC_FS +/* Called by the /proc file system to return a list of modules. */ +static void *m_start(struct seq_file *m, loff_t *pos) +{ + mutex_lock(&module_mutex); + return seq_list_start(&modules, *pos); +} + +static void *m_next(struct seq_file *m, void *p, loff_t *pos) +{ + return seq_list_next(p, &modules, pos); +} + +static void m_stop(struct seq_file *m, void *p) +{ + mutex_unlock(&module_mutex); +} + static int m_show(struct seq_file *m, void *p) { struct module *mod = list_entry(p, struct module, list); @@ -2679,13 +2682,33 @@ static int m_show(struct seq_file *m, void *p) Where refcount is a number or -, and deps is a comma-separated list of depends or -. */ -const struct seq_operations modules_op = { +static const struct seq_operations modules_op = { .start = m_start, .next = m_next, .stop = m_stop, .show = m_show }; +static int modules_open(struct inode *inode, struct file *file) +{ + return seq_open(file, &modules_op); +} + +static const struct file_operations proc_modules_operations = { + .open = modules_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +static int __init proc_modules_init(void) +{ + proc_create("modules", 0, NULL, &proc_modules_operations); + return 0; +} +module_init(proc_modules_init); +#endif + /* Given an address, look for it in the module exception tables. */ const struct exception_table_entry *search_module_extables(unsigned long addr) { -- cgit v1.1