remarkable-linux/lib/genalloc.c
Thadeu Lima de Souza Cascardo eedce141cd genalloc: stop crashing the system when destroying a pool
The genalloc code uses the bitmap API from include/linux/bitmap.h and
lib/bitmap.c, which is based on long values.  Both bitmap_set from
lib/bitmap.c and bitmap_set_ll, which is the lockless version from
genalloc.c, use BITMAP_LAST_WORD_MASK to set the first bits in a long in
the bitmap.

That one uses (1 << bits) - 1, 0b111, if you are setting the first three
bits.  This means that the API counts from the least significant bits
(LSB from now on) to the MSB.  The LSB in the first long is bit 0, then.
The same works for the lookup functions.

The genalloc code uses longs for the bitmap, as it should.  In
include/linux/genalloc.h, struct gen_pool_chunk has unsigned long
bits[0] as its last member.  When allocating the struct, genalloc should
reserve enough space for the bitmap.  This should be a proper number of
longs that can fit the amount of bits in the bitmap.

However, genalloc allocates an integer number of bytes that fit the
amount of bits, but may not be an integer amount of longs.  9 bytes, for
example, could be allocated for 70 bits.

This is a problem in itself if the Least Significat Bit in a long is in
the byte with the largest address, which happens in Big Endian machines.
This means genalloc is not allocating the byte in which it will try to
set or check for a bit.

This may end up in memory corruption, where genalloc will try to set the
bits it has not allocated.  In fact, genalloc may not set these bits
because it may find them already set, because they were not zeroed since
they were not allocated.  And that's what causes a BUG when
gen_pool_destroy is called and check for any set bits.

What really happens is that genalloc uses kmalloc_node with __GFP_ZERO
on gen_pool_add_virt.  With SLAB and SLUB, this means the whole slab
will be cleared, not only the requested bytes.  Since struct
gen_pool_chunk has a size that is a multiple of 8, and slab sizes are
multiples of 8, we get lucky and allocate and clear the right amount of
bytes.

Hower, this is not the case with SLOB or with older code that did memset
after allocating instead of using __GFP_ZERO.

So, a simple module as this (running 3.6.0), will cause a crash when
rmmod'ed.

  [root@phantom-lp2 foo]# cat foo.c
  #include <linux/kernel.h>
  #include <linux/module.h>
  #include <linux/init.h>
  #include <linux/genalloc.h>

  MODULE_LICENSE("GPL");
  MODULE_VERSION("0.1");

  static struct gen_pool *foo_pool;

  static __init int foo_init(void)
  {
          int ret;
          foo_pool = gen_pool_create(10, -1);
          if (!foo_pool)
                  return -ENOMEM;
          ret = gen_pool_add(foo_pool, 0xa0000000, 32 << 10, -1);
          if (ret) {
                  gen_pool_destroy(foo_pool);
                  return ret;
          }
          return 0;
  }

  static __exit void foo_exit(void)
  {
          gen_pool_destroy(foo_pool);
  }

  module_init(foo_init);
  module_exit(foo_exit);
  [root@phantom-lp2 foo]# zcat /proc/config.gz | grep SLOB
  CONFIG_SLOB=y
  [root@phantom-lp2 foo]# insmod ./foo.ko
  [root@phantom-lp2 foo]# rmmod foo
  ------------[ cut here ]------------
  kernel BUG at lib/genalloc.c:243!
  cpu 0x4: Vector: 700 (Program Check) at [c0000000bb0e7960]
      pc: c0000000003cb50c: .gen_pool_destroy+0xac/0x110
      lr: c0000000003cb4fc: .gen_pool_destroy+0x9c/0x110
      sp: c0000000bb0e7be0
     msr: 8000000000029032
    current = 0xc0000000bb0e0000
    paca    = 0xc000000006d30e00   softe: 0        irq_happened: 0x01
      pid   = 13044, comm = rmmod
  kernel BUG at lib/genalloc.c:243!
  [c0000000bb0e7ca0] d000000004b00020 .foo_exit+0x20/0x38 [foo]
  [c0000000bb0e7d20] c0000000000dff98 .SyS_delete_module+0x1a8/0x290
  [c0000000bb0e7e30] c0000000000097d4 syscall_exit+0x0/0x94
  --- Exception: c00 (System Call) at 000000800753d1a0
  SP (fffd0b0e640) is in userspace

Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo@linux.vnet.ibm.com>
Cc: Paul Gortmaker <paul.gortmaker@windriver.com>
Cc: Benjamin Gaignard <benjamin.gaignard@stericsson.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-10-25 14:37:52 -07:00

483 lines
13 KiB
C

/*
* Basic general purpose allocator for managing special purpose
* memory, for example, memory that is not managed by the regular
* kmalloc/kfree interface. Uses for this includes on-device special
* memory, uncached memory etc.
*
* It is safe to use the allocator in NMI handlers and other special
* unblockable contexts that could otherwise deadlock on locks. This
* is implemented by using atomic operations and retries on any
* conflicts. The disadvantage is that there may be livelocks in
* extreme cases. For better scalability, one allocator can be used
* for each CPU.
*
* The lockless operation only works if there is enough memory
* available. If new memory is added to the pool a lock has to be
* still taken. So any user relying on locklessness has to ensure
* that sufficient memory is preallocated.
*
* The basic atomic operation of this allocator is cmpxchg on long.
* On architectures that don't have NMI-safe cmpxchg implementation,
* the allocator can NOT be used in NMI handler. So code uses the
* allocator in NMI handler should depend on
* CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG.
*
* Copyright 2005 (C) Jes Sorensen <jes@trained-monkey.org>
*
* This source code is licensed under the GNU General Public License,
* Version 2. See the file COPYING for more details.
*/
#include <linux/slab.h>
#include <linux/export.h>
#include <linux/bitmap.h>
#include <linux/rculist.h>
#include <linux/interrupt.h>
#include <linux/genalloc.h>
static int set_bits_ll(unsigned long *addr, unsigned long mask_to_set)
{
unsigned long val, nval;
nval = *addr;
do {
val = nval;
if (val & mask_to_set)
return -EBUSY;
cpu_relax();
} while ((nval = cmpxchg(addr, val, val | mask_to_set)) != val);
return 0;
}
static int clear_bits_ll(unsigned long *addr, unsigned long mask_to_clear)
{
unsigned long val, nval;
nval = *addr;
do {
val = nval;
if ((val & mask_to_clear) != mask_to_clear)
return -EBUSY;
cpu_relax();
} while ((nval = cmpxchg(addr, val, val & ~mask_to_clear)) != val);
return 0;
}
/*
* bitmap_set_ll - set the specified number of bits at the specified position
* @map: pointer to a bitmap
* @start: a bit position in @map
* @nr: number of bits to set
*
* Set @nr bits start from @start in @map lock-lessly. Several users
* can set/clear the same bitmap simultaneously without lock. If two
* users set the same bit, one user will return remain bits, otherwise
* return 0.
*/
static int bitmap_set_ll(unsigned long *map, int start, int nr)
{
unsigned long *p = map + BIT_WORD(start);
const int size = start + nr;
int bits_to_set = BITS_PER_LONG - (start % BITS_PER_LONG);
unsigned long mask_to_set = BITMAP_FIRST_WORD_MASK(start);
while (nr - bits_to_set >= 0) {
if (set_bits_ll(p, mask_to_set))
return nr;
nr -= bits_to_set;
bits_to_set = BITS_PER_LONG;
mask_to_set = ~0UL;
p++;
}
if (nr) {
mask_to_set &= BITMAP_LAST_WORD_MASK(size);
if (set_bits_ll(p, mask_to_set))
return nr;
}
return 0;
}
/*
* bitmap_clear_ll - clear the specified number of bits at the specified position
* @map: pointer to a bitmap
* @start: a bit position in @map
* @nr: number of bits to set
*
* Clear @nr bits start from @start in @map lock-lessly. Several users
* can set/clear the same bitmap simultaneously without lock. If two
* users clear the same bit, one user will return remain bits,
* otherwise return 0.
*/
static int bitmap_clear_ll(unsigned long *map, int start, int nr)
{
unsigned long *p = map + BIT_WORD(start);
const int size = start + nr;
int bits_to_clear = BITS_PER_LONG - (start % BITS_PER_LONG);
unsigned long mask_to_clear = BITMAP_FIRST_WORD_MASK(start);
while (nr - bits_to_clear >= 0) {
if (clear_bits_ll(p, mask_to_clear))
return nr;
nr -= bits_to_clear;
bits_to_clear = BITS_PER_LONG;
mask_to_clear = ~0UL;
p++;
}
if (nr) {
mask_to_clear &= BITMAP_LAST_WORD_MASK(size);
if (clear_bits_ll(p, mask_to_clear))
return nr;
}
return 0;
}
/**
* gen_pool_create - create a new special memory pool
* @min_alloc_order: log base 2 of number of bytes each bitmap bit represents
* @nid: node id of the node the pool structure should be allocated on, or -1
*
* Create a new special memory pool that can be used to manage special purpose
* memory not managed by the regular kmalloc/kfree interface.
*/
struct gen_pool *gen_pool_create(int min_alloc_order, int nid)
{
struct gen_pool *pool;
pool = kmalloc_node(sizeof(struct gen_pool), GFP_KERNEL, nid);
if (pool != NULL) {
spin_lock_init(&pool->lock);
INIT_LIST_HEAD(&pool->chunks);
pool->min_alloc_order = min_alloc_order;
pool->algo = gen_pool_first_fit;
pool->data = NULL;
}
return pool;
}
EXPORT_SYMBOL(gen_pool_create);
/**
* gen_pool_add_virt - add a new chunk of special memory to the pool
* @pool: pool to add new memory chunk to
* @virt: virtual starting address of memory chunk to add to pool
* @phys: physical starting address of memory chunk to add to pool
* @size: size in bytes of the memory chunk to add to pool
* @nid: node id of the node the chunk structure and bitmap should be
* allocated on, or -1
*
* Add a new chunk of special memory to the specified pool.
*
* Returns 0 on success or a -ve errno on failure.
*/
int gen_pool_add_virt(struct gen_pool *pool, unsigned long virt, phys_addr_t phys,
size_t size, int nid)
{
struct gen_pool_chunk *chunk;
int nbits = size >> pool->min_alloc_order;
int nbytes = sizeof(struct gen_pool_chunk) +
BITS_TO_LONGS(nbits) * sizeof(long);
chunk = kmalloc_node(nbytes, GFP_KERNEL | __GFP_ZERO, nid);
if (unlikely(chunk == NULL))
return -ENOMEM;
chunk->phys_addr = phys;
chunk->start_addr = virt;
chunk->end_addr = virt + size;
atomic_set(&chunk->avail, size);
spin_lock(&pool->lock);
list_add_rcu(&chunk->next_chunk, &pool->chunks);
spin_unlock(&pool->lock);
return 0;
}
EXPORT_SYMBOL(gen_pool_add_virt);
/**
* gen_pool_virt_to_phys - return the physical address of memory
* @pool: pool to allocate from
* @addr: starting address of memory
*
* Returns the physical address on success, or -1 on error.
*/
phys_addr_t gen_pool_virt_to_phys(struct gen_pool *pool, unsigned long addr)
{
struct gen_pool_chunk *chunk;
phys_addr_t paddr = -1;
rcu_read_lock();
list_for_each_entry_rcu(chunk, &pool->chunks, next_chunk) {
if (addr >= chunk->start_addr && addr < chunk->end_addr) {
paddr = chunk->phys_addr + (addr - chunk->start_addr);
break;
}
}
rcu_read_unlock();
return paddr;
}
EXPORT_SYMBOL(gen_pool_virt_to_phys);
/**
* gen_pool_destroy - destroy a special memory pool
* @pool: pool to destroy
*
* Destroy the specified special memory pool. Verifies that there are no
* outstanding allocations.
*/
void gen_pool_destroy(struct gen_pool *pool)
{
struct list_head *_chunk, *_next_chunk;
struct gen_pool_chunk *chunk;
int order = pool->min_alloc_order;
int bit, end_bit;
list_for_each_safe(_chunk, _next_chunk, &pool->chunks) {
chunk = list_entry(_chunk, struct gen_pool_chunk, next_chunk);
list_del(&chunk->next_chunk);
end_bit = (chunk->end_addr - chunk->start_addr) >> order;
bit = find_next_bit(chunk->bits, end_bit, 0);
BUG_ON(bit < end_bit);
kfree(chunk);
}
kfree(pool);
return;
}
EXPORT_SYMBOL(gen_pool_destroy);
/**
* gen_pool_alloc - allocate special memory from the pool
* @pool: pool to allocate from
* @size: number of bytes to allocate from the pool
*
* Allocate the requested number of bytes from the specified pool.
* Uses the pool allocation function (with first-fit algorithm by default).
* Can not be used in NMI handler on architectures without
* NMI-safe cmpxchg implementation.
*/
unsigned long gen_pool_alloc(struct gen_pool *pool, size_t size)
{
struct gen_pool_chunk *chunk;
unsigned long addr = 0;
int order = pool->min_alloc_order;
int nbits, start_bit = 0, end_bit, remain;
#ifndef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG
BUG_ON(in_nmi());
#endif
if (size == 0)
return 0;
nbits = (size + (1UL << order) - 1) >> order;
rcu_read_lock();
list_for_each_entry_rcu(chunk, &pool->chunks, next_chunk) {
if (size > atomic_read(&chunk->avail))
continue;
end_bit = (chunk->end_addr - chunk->start_addr) >> order;
retry:
start_bit = pool->algo(chunk->bits, end_bit, start_bit, nbits,
pool->data);
if (start_bit >= end_bit)
continue;
remain = bitmap_set_ll(chunk->bits, start_bit, nbits);
if (remain) {
remain = bitmap_clear_ll(chunk->bits, start_bit,
nbits - remain);
BUG_ON(remain);
goto retry;
}
addr = chunk->start_addr + ((unsigned long)start_bit << order);
size = nbits << order;
atomic_sub(size, &chunk->avail);
break;
}
rcu_read_unlock();
return addr;
}
EXPORT_SYMBOL(gen_pool_alloc);
/**
* gen_pool_free - free allocated special memory back to the pool
* @pool: pool to free to
* @addr: starting address of memory to free back to pool
* @size: size in bytes of memory to free
*
* Free previously allocated special memory back to the specified
* pool. Can not be used in NMI handler on architectures without
* NMI-safe cmpxchg implementation.
*/
void gen_pool_free(struct gen_pool *pool, unsigned long addr, size_t size)
{
struct gen_pool_chunk *chunk;
int order = pool->min_alloc_order;
int start_bit, nbits, remain;
#ifndef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG
BUG_ON(in_nmi());
#endif
nbits = (size + (1UL << order) - 1) >> order;
rcu_read_lock();
list_for_each_entry_rcu(chunk, &pool->chunks, next_chunk) {
if (addr >= chunk->start_addr && addr < chunk->end_addr) {
BUG_ON(addr + size > chunk->end_addr);
start_bit = (addr - chunk->start_addr) >> order;
remain = bitmap_clear_ll(chunk->bits, start_bit, nbits);
BUG_ON(remain);
size = nbits << order;
atomic_add(size, &chunk->avail);
rcu_read_unlock();
return;
}
}
rcu_read_unlock();
BUG();
}
EXPORT_SYMBOL(gen_pool_free);
/**
* gen_pool_for_each_chunk - call func for every chunk of generic memory pool
* @pool: the generic memory pool
* @func: func to call
* @data: additional data used by @func
*
* Call @func for every chunk of generic memory pool. The @func is
* called with rcu_read_lock held.
*/
void gen_pool_for_each_chunk(struct gen_pool *pool,
void (*func)(struct gen_pool *pool, struct gen_pool_chunk *chunk, void *data),
void *data)
{
struct gen_pool_chunk *chunk;
rcu_read_lock();
list_for_each_entry_rcu(chunk, &(pool)->chunks, next_chunk)
func(pool, chunk, data);
rcu_read_unlock();
}
EXPORT_SYMBOL(gen_pool_for_each_chunk);
/**
* gen_pool_avail - get available free space of the pool
* @pool: pool to get available free space
*
* Return available free space of the specified pool.
*/
size_t gen_pool_avail(struct gen_pool *pool)
{
struct gen_pool_chunk *chunk;
size_t avail = 0;
rcu_read_lock();
list_for_each_entry_rcu(chunk, &pool->chunks, next_chunk)
avail += atomic_read(&chunk->avail);
rcu_read_unlock();
return avail;
}
EXPORT_SYMBOL_GPL(gen_pool_avail);
/**
* gen_pool_size - get size in bytes of memory managed by the pool
* @pool: pool to get size
*
* Return size in bytes of memory managed by the pool.
*/
size_t gen_pool_size(struct gen_pool *pool)
{
struct gen_pool_chunk *chunk;
size_t size = 0;
rcu_read_lock();
list_for_each_entry_rcu(chunk, &pool->chunks, next_chunk)
size += chunk->end_addr - chunk->start_addr;
rcu_read_unlock();
return size;
}
EXPORT_SYMBOL_GPL(gen_pool_size);
/**
* gen_pool_set_algo - set the allocation algorithm
* @pool: pool to change allocation algorithm
* @algo: custom algorithm function
* @data: additional data used by @algo
*
* Call @algo for each memory allocation in the pool.
* If @algo is NULL use gen_pool_first_fit as default
* memory allocation function.
*/
void gen_pool_set_algo(struct gen_pool *pool, genpool_algo_t algo, void *data)
{
rcu_read_lock();
pool->algo = algo;
if (!pool->algo)
pool->algo = gen_pool_first_fit;
pool->data = data;
rcu_read_unlock();
}
EXPORT_SYMBOL(gen_pool_set_algo);
/**
* gen_pool_first_fit - find the first available region
* of memory matching the size requirement (no alignment constraint)
* @map: The address to base the search on
* @size: The bitmap size in bits
* @start: The bitnumber to start searching at
* @nr: The number of zeroed bits we're looking for
* @data: additional data - unused
*/
unsigned long gen_pool_first_fit(unsigned long *map, unsigned long size,
unsigned long start, unsigned int nr, void *data)
{
return bitmap_find_next_zero_area(map, size, start, nr, 0);
}
EXPORT_SYMBOL(gen_pool_first_fit);
/**
* gen_pool_best_fit - find the best fitting region of memory
* macthing the size requirement (no alignment constraint)
* @map: The address to base the search on
* @size: The bitmap size in bits
* @start: The bitnumber to start searching at
* @nr: The number of zeroed bits we're looking for
* @data: additional data - unused
*
* Iterate over the bitmap to find the smallest free region
* which we can allocate the memory.
*/
unsigned long gen_pool_best_fit(unsigned long *map, unsigned long size,
unsigned long start, unsigned int nr, void *data)
{
unsigned long start_bit = size;
unsigned long len = size + 1;
unsigned long index;
index = bitmap_find_next_zero_area(map, size, start, nr, 0);
while (index < size) {
int next_bit = find_next_bit(map, size, index + nr);
if ((next_bit - index) < len) {
len = next_bit - index;
start_bit = index;
if (len == nr)
return start_bit;
}
index = bitmap_find_next_zero_area(map, size,
next_bit + 1, nr, 0);
}
return start_bit;
}
EXPORT_SYMBOL(gen_pool_best_fit);