module.c

Kernel code of linux kernel

/*
   Copyright (C) 2002 Richard Henderson
   Copyright (C) 2001 Rusty Russell, 2002 Rusty Russell IBM.

    This program is free software; you can redistribute it and/or modify
    it under the terms of the GNU General Public License as published by
    the Free Software Foundation; either version 2 of the License, or
    (at your option) any later version.

    This program is distributed in the hope that it will be useful,
    but WITHOUT ANY WARRANTY; without even the implied warranty of
    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
    GNU General Public License for more details.

    You should have received a copy of the GNU General Public License
    along with this program; if not, write to the Free Software
    Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
*/
#include <linux/module.h>
#include <linux/moduleloader.h>
#include <linux/init.h>
#include <linux/kallsyms.h>
#include <linux/sysfs.h>
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <linux/elf.h>
#include <linux/seq_file.h>
#include <linux/syscalls.h>
#include <linux/fcntl.h>
#include <linux/rcupdate.h>
#include <linux/capability.h>
#include <linux/cpu.h>
#include <linux/moduleparam.h>
#include <linux/errno.h>
#include <linux/err.h>
#include <linux/vermagic.h>
#include <linux/notifier.h>
#include <linux/sched.h>
#include <linux/stop_machine.h>
#include <linux/device.h>
#include <linux/string.h>
#include <linux/mutex.h>
#include <linux/unwind.h>
#include <asm/uaccess.h>
#include <asm/cacheflush.h>
#include <linux/license.h>
#include <asm/sections.h>

#if 0
#define DEBUGP printk
#else
#define DEBUGP(fmt , a...)
#endif

#ifndef ARCH_SHF_SMALL
#define ARCH_SHF_SMALL 0
#endif

/* If this is set, the section belongs in the init part of the module */
#define INIT_OFFSET_MASK (1UL << (BITS_PER_LONG-1))

/* List of modules, protected by module_mutex or preempt_disable
 * (add/delete uses stop_machine). */
static DEFINE_MUTEX(module_mutex);
static LIST_HEAD(modules);

/* Waiting for a module to finish initializing? */
static DECLARE_WAIT_QUEUE_HEAD(module_wq);

static BLOCKING_NOTIFIER_HEAD(module_notify_list);

/* Bounds of module allocation, for speeding __module_text_address */
static unsigned long module_addr_min = -1UL, module_addr_max = 0;

int register_module_notifier(struct notifier_block * nb)
{
	return blocking_notifier_chain_register(&module_notify_list, nb);
}
EXPORT_SYMBOL(register_module_notifier);

int unregister_module_notifier(struct notifier_block * nb)
{
	return blocking_notifier_chain_unregister(&module_notify_list, nb);
}
EXPORT_SYMBOL(unregister_module_notifier);

/* We require a truly strong try_module_get(): 0 means failure due to
   ongoing or failed initialization etc. */
static inline int strong_try_module_get(struct module *mod)
{
	if (mod && mod->state == MODULE_STATE_COMING)
		return -EBUSY;
	if (try_module_get(mod))
		return 0;
	else
		return -ENOENT;
}

static inline void add_taint_module(struct module *mod, unsigned flag)
{
	add_taint(flag);
	mod->taints |= flag;
}

/*
 * A thread that wants to hold a reference to a module only while it
 * is running can call this to safely exit.  nfsd and lockd use this.
 */
void __module_put_and_exit(struct module *mod, long code)
{
	module_put(mod);
	do_exit(code);
}
EXPORT_SYMBOL(__module_put_and_exit);

/* Find a module section: 0 means not found. */
static unsigned int find_sec(Elf_Ehdr *hdr,
			     Elf_Shdr *sechdrs,
			     const char *secstrings,
			     const char *name)
{
	unsigned int i;

	for (i = 1; i < hdr->e_shnum; i++)
		/* Alloc bit cleared means "ignore it." */
		if ((sechdrs[i].sh_flags & SHF_ALLOC)
		    && strcmp(secstrings+sechdrs[i].sh_name, name) == 0)
			return i;
	return 0;
}

/* Provided by the linker */
extern const struct kernel_symbol __start___ksymtab[];
extern const struct kernel_symbol __stop___ksymtab[];
extern const struct kernel_symbol __start___ksymtab_gpl[];
extern const struct kernel_symbol __stop___ksymtab_gpl[];
extern const struct kernel_symbol __start___ksymtab_gpl_future[];
extern const struct kernel_symbol __stop___ksymtab_gpl_future[];
extern const struct kernel_symbol __start___ksymtab_gpl_future[];
extern const struct kernel_symbol __stop___ksymtab_gpl_future[];
extern const unsigned long __start___kcrctab[];
extern const unsigned long __start___kcrctab_gpl[];
extern const unsigned long __start___kcrctab_gpl_future[];
#ifdef CONFIG_UNUSED_SYMBOLS
extern const struct kernel_symbol __start___ksymtab_unused[];
extern const struct kernel_symbol __stop___ksymtab_unused[];
extern const struct kernel_symbol __start___ksymtab_unused_gpl[];
extern const struct kernel_symbol __stop___ksymtab_unused_gpl[];
extern const unsigned long __start___kcrctab_unused[];
extern const unsigned long __start___kcrctab_unused_gpl[];
#endif

#ifndef CONFIG_MODVERSIONS
#define symversion(base, idx) NULL
#else
#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,
				   bool (*fn)(const struct symsearch *syms,
					      struct module *owner,
					      unsigned int symnum, void *data),
				   void *data)
{
	unsigned int i, j;

	for (j = 0; j < arrsize; j++) {
		for (i = 0; i < arr[j].stop - arr[j].start; i++)
			if (fn(&arr[j], owner, i, data))
				return true;
	}

	return false;
}

/* 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)
{
	struct module *mod;
	const struct symsearch arr[] = {
		{ __start___ksymtab, __stop___ksymtab, __start___kcrctab,
		  NOT_GPL_ONLY, false },
		{ __start___ksymtab_gpl, __stop___ksymtab_gpl,
		  __start___kcrctab_gpl,
		  GPL_ONLY, false },
		{ __start___ksymtab_gpl_future, __stop___ksymtab_gpl_future,
		  __start___kcrctab_gpl_future,
		  WILL_BE_GPL_ONLY, false },
#ifdef CONFIG_UNUSED_SYMBOLS
		{ __start___ksymtab_unused, __stop___ksymtab_unused,
		  __start___kcrctab_unused,
		  NOT_GPL_ONLY, true },
		{ __start___ksymtab_unused_gpl, __stop___ksymtab_unused_gpl,
		  __start___kcrctab_unused_gpl,
		  GPL_ONLY, true },
#endif
	};

	if (each_symbol_in_section(arr, ARRAY_SIZE(arr), NULL, fn, data))
		return true;

	list_for_each_entry(mod, &modules, list) {
		struct symsearch arr[] = {
			{ mod->syms, mod->syms + mod->num_syms, mod->crcs,
			  NOT_GPL_ONLY, false },
			{ mod->gpl_syms, mod->gpl_syms + mod->num_gpl_syms,
			  mod->gpl_crcs,
			  GPL_ONLY, false },
			{ mod->gpl_future_syms,
			  mod->gpl_future_syms + mod->num_gpl_future_syms,
			  mod->gpl_future_crcs,
			  WILL_BE_GPL_ONLY, false },
#ifdef CONFIG_UNUSED_SYMBOLS
			{ mod->unused_syms,
			  mod->unused_syms + mod->num_unused_syms,
			  mod->unused_crcs,
			  NOT_GPL_ONLY, true },
			{ mod->unused_gpl_syms,
			  mod->unused_gpl_syms + mod->num_unused_gpl_syms,
			  mod->unused_gpl_crcs,
			  GPL_ONLY, true },
#endif
		};

		if (each_symbol_in_section(arr, ARRAY_SIZE(arr), mod, fn, data))
			return true;
	}
	return false;
}

struct find_symbol_arg {
	/* Input */
	const char *name;
	bool gplok;
	bool warn;

	/* Output */
	struct module *owner;
	const unsigned long *crc;
	unsigned long value;
};

static bool find_symbol_in_section(const struct symsearch *syms,
				   struct module *owner,
				   unsigned int symnum, void *data)
{
	struct find_symbol_arg *fsa = data;

	if (strcmp(syms->start[symnum].name, fsa->name) != 0)
		return false;

	if (!fsa->gplok) {
		if (syms->licence == GPL_ONLY)
			return false;
		if (syms->licence == WILL_BE_GPL_ONLY && fsa->warn) {
			printk(KERN_WARNING "Symbol %s is being used "
			       "by a non-GPL module, which will not "
			       "be allowed in the future\n", fsa->name);
			printk(KERN_WARNING "Please see the file "
			       "Documentation/feature-removal-schedule.txt "
			       "in the kernel source tree for more details.\n");
		}
	}

#ifdef CONFIG_UNUSED_SYMBOLS
	if (syms->unused && fsa->warn) {
		printk(KERN_WARNING "Symbol %s is marked as UNUSED, "
		       "however this module is using it.\n", fsa->name);
		printk(KERN_WARNING
		       "This symbol will go away in the future.\n");
		printk(KERN_WARNING
		       "Please evalute if this is the right api to use and if "
		       "it really is, submit a report the linux kernel "
		       "mailinglist together with submitting your code for "
		       "inclusion.\n");
	}
#endif

	fsa->owner = owner;
	fsa->crc = symversion(syms->crcs, symnum);
	fsa->value = syms->start[symnum].value;
	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)
{
	struct find_symbol_arg fsa;

	fsa.name = name;
	fsa.gplok = gplok;
	fsa.warn = warn;

	if (each_symbol(find_symbol_in_section, &fsa)) {
		if (owner)
			*owner = fsa.owner;
		if (crc)
			*crc = fsa.crc;
		return fsa.value;
	}

	DEBUGP("Failed to find symbol %s\n", name);
	return -ENOENT;
}

/* Search for module by name: must hold module_mutex. */
static struct module *find_module(const char *name)
{
	struct module *mod;

	list_for_each_entry(mod, &modules, list) {
		if (strcmp(mod->name, name) == 0)
			return mod;
	}
	return NULL;
}

#ifdef CONFIG_SMP
/* Number of blocks used and allocated. */
static unsigned int pcpu_num_used, pcpu_num_allocated;
/* Size of each block.  -ve means used. */
static int *pcpu_size;

static int split_block(unsigned int i, unsigned short size)
{
	/* Reallocation required? */
	if (pcpu_num_used + 1 > pcpu_num_allocated) {
		int *new;

		new = krealloc(pcpu_size, sizeof(new[0])*pcpu_num_allocated*2,
			       GFP_KERNEL);
		if (!new)
			return 0;

		pcpu_num_allocated *= 2;
		pcpu_size = new;
	}

	/* Insert a new subblock */
	memmove(&pcpu_size[i+1], &pcpu_size[i],
		sizeof(pcpu_size[0]) * (pcpu_num_used - i));
	pcpu_num_used++;

	pcpu_size[i+1] -= size;
	pcpu_size[i] = size;
	return 1;
}

static inline unsigned int block_size(int val)
{
	if (val < 0)
		return -val;
	return val;
}

static void *percpu_modalloc(unsigned long size, unsigned long align,
			     const char *name)
{
	unsigned long extra;
	unsigned int i;
	void *ptr;

	if (align > PAGE_SIZE) {
		printk(KERN_WARNING "%s: per-cpu alignment %li > %li\n",
		       name, align, PAGE_SIZE);
		align = PAGE_SIZE;
	}

	ptr = __per_cpu_start;
	for (i = 0; i < pcpu_num_used; ptr += block_size(pcpu_size[i]), i++) {
		/* Extra for alignment requirement. */
		extra = ALIGN((unsigned long)ptr, align) - (unsigned long)ptr;
		BUG_ON(i == 0 && extra != 0);

		if (pcpu_size[i] < 0 || pcpu_size[i] < extra + size)
			continue;

		/* Transfer extra to previous block. */
		if (pcpu_size[i-1] < 0)
			pcpu_size[i-1] -= extra;
		else
			pcpu_size[i-1] += extra;
		pcpu_size[i] -= extra;
		ptr += extra;

		/* Split block if warranted */
		if (pcpu_size[i] - size > sizeof(unsigned long))
			if (!split_block(i, size))
				return NULL;

		/* Mark allocated */
		pcpu_size[i] = -pcpu_size[i];
		return ptr;
	}

	printk(KERN_WARNING "Could not allocate %lu bytes percpu data\n",
	       size);
	return NULL;
}

static void percpu_modfree(void *freeme)
{
	unsigned int i;
	void *ptr = __per_cpu_start + block_size(pcpu_size[0]);

	/* First entry is core kernel percpu data. */
	for (i = 1; i < pcpu_num_used; ptr += block_size(pcpu_size[i]), i++) {
		if (ptr == freeme) {
			pcpu_size[i] = -pcpu_size[i];
			goto free;
		}
	}
	BUG();

 free:
	/* Merge with previous? */
	if (pcpu_size[i-1] >= 0) {
		pcpu_size[i-1] += pcpu_size[i];
		pcpu_num_used--;
		memmove(&pcpu_size[i], &pcpu_size[i+1],
			(pcpu_num_used - i) * sizeof(pcpu_size[0]));
		i--;
	}
	/* Merge with next? */
	if (i+1 < pcpu_num_used && pcpu_size[i+1] >= 0) {
		pcpu_size[i] += pcpu_size[i+1];
		pcpu_num_used--;
		memmove(&pcpu_size[i+1], &pcpu_size[i+2],
			(pcpu_num_used - (i+1)) * sizeof(pcpu_size[0]));
	}
}

static unsigned int find_pcpusec(Elf_Ehdr *hdr,
				 Elf_Shdr *sechdrs,
				 const char *secstrings)
{
	return find_sec(hdr, sechdrs, secstrings, ".data.percpu");
}

static void percpu_modcopy(void *pcpudest, const void *from, unsigned long size)
{
	int cpu;

	for_each_possible_cpu(cpu)
		memcpy(pcpudest + per_cpu_offset(cpu), from, size);
}

static int percpu_modinit(void)
{
	pcpu_num_used = 2;
	pcpu_num_allocated = 2;
	pcpu_size = kmalloc(sizeof(pcpu_size[0]) * pcpu_num_allocated,
			    GFP_KERNEL);
	/* Static in-kernel percpu data (used). */
	pcpu_size[0] = -(__per_cpu_end-__per_cpu_start);
	/* Free room. */
	pcpu_size[1] = PERCPU_ENOUGH_ROOM + pcpu_size[0];
	if (pcpu_size[1] < 0) {
		printk(KERN_ERR "No per-cpu room for modules.\n");
		pcpu_num_used = 1;
	}

	return 0;
}
__initcall(percpu_modinit);
#else /* ... !CONFIG_SMP */
static inline void *percpu_modalloc(unsigned long size, unsigned long align,
				    const char *name)
{
	return NULL;
}
static inline void percpu_modfree(void *pcpuptr)
{
	BUG();
}