Revision 882bebaaca4bb1484078d44ef011f918c0e1e14e authored by Ilpo Järvinen on 08 April 2008, 05:33:07 UTC, committed by David S. Miller on 08 April 2008, 05:33:07 UTC
This fixes Bugzilla #10384 tcp_simple_retransmit does L increment without any checking whatsoever for overflowing S+L when Reno is in use. The simplest scenario I can currently think of is rather complex in practice (there might be some more straightforward cases though). Ie., if mss is reduced during mtu probing, it may end up marking everything lost and if some duplicate ACKs arrived prior to that sacked_out will be non-zero as well, leading to S+L > packets_out, tcp_clean_rtx_queue on the next cumulative ACK or tcp_fastretrans_alert on the next duplicate ACK will fix the S counter. More straightforward (but questionable) solution would be to just call tcp_reset_reno_sack() in tcp_simple_retransmit but it would negatively impact the probe's retransmission, ie., the retransmissions would not occur if some duplicate ACKs had arrived. So I had to add reno sacked_out reseting to CA_Loss state when the first cumulative ACK arrives (this stale sacked_out might actually be the explanation for the reports of left_out overflows in kernel prior to 2.6.23 and S+L overflow reports of 2.6.24). However, this alone won't be enough to fix kernel before 2.6.24 because it is building on top of the commit 1b6d427bb7e ([TCP]: Reduce sacked_out with reno when purging write_queue) to keep the sacked_out from overflowing. Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi> Reported-by: Alessandro Suardi <alessandro.suardi@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
1 parent c137f3d
slob.c
/*
* SLOB Allocator: Simple List Of Blocks
*
* Matt Mackall <mpm@selenic.com> 12/30/03
*
* NUMA support by Paul Mundt, 2007.
*
* How SLOB works:
*
* The core of SLOB is a traditional K&R style heap allocator, with
* support for returning aligned objects. The granularity of this
* allocator is as little as 2 bytes, however typically most architectures
* will require 4 bytes on 32-bit and 8 bytes on 64-bit.
*
* The slob heap is a set of linked list of pages from alloc_pages(),
* and within each page, there is a singly-linked list of free blocks
* (slob_t). The heap is grown on demand. To reduce fragmentation,
* heap pages are segregated into three lists, with objects less than
* 256 bytes, objects less than 1024 bytes, and all other objects.
*
* Allocation from heap involves first searching for a page with
* sufficient free blocks (using a next-fit-like approach) followed by
* a first-fit scan of the page. Deallocation inserts objects back
* into the free list in address order, so this is effectively an
* address-ordered first fit.
*
* Above this is an implementation of kmalloc/kfree. Blocks returned
* from kmalloc are prepended with a 4-byte header with the kmalloc size.
* If kmalloc is asked for objects of PAGE_SIZE or larger, it calls
* alloc_pages() directly, allocating compound pages so the page order
* does not have to be separately tracked, and also stores the exact
* allocation size in page->private so that it can be used to accurately
* provide ksize(). These objects are detected in kfree() because slob_page()
* is false for them.
*
* SLAB is emulated on top of SLOB by simply calling constructors and
* destructors for every SLAB allocation. Objects are returned with the
* 4-byte alignment unless the SLAB_HWCACHE_ALIGN flag is set, in which
* case the low-level allocator will fragment blocks to create the proper
* alignment. Again, objects of page-size or greater are allocated by
* calling alloc_pages(). As SLAB objects know their size, no separate
* size bookkeeping is necessary and there is essentially no allocation
* space overhead, and compound pages aren't needed for multi-page
* allocations.
*
* NUMA support in SLOB is fairly simplistic, pushing most of the real
* logic down to the page allocator, and simply doing the node accounting
* on the upper levels. In the event that a node id is explicitly
* provided, alloc_pages_node() with the specified node id is used
* instead. The common case (or when the node id isn't explicitly provided)
* will default to the current node, as per numa_node_id().
*
* Node aware pages are still inserted in to the global freelist, and
* these are scanned for by matching against the node id encoded in the
* page flags. As a result, block allocations that can be satisfied from
* the freelist will only be done so on pages residing on the same node,
* in order to prevent random node placement.
*/
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/mm.h>
#include <linux/cache.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/rcupdate.h>
#include <linux/list.h>
#include <asm/atomic.h>
/*
* slob_block has a field 'units', which indicates size of block if +ve,
* or offset of next block if -ve (in SLOB_UNITs).
*
* Free blocks of size 1 unit simply contain the offset of the next block.
* Those with larger size contain their size in the first SLOB_UNIT of
* memory, and the offset of the next free block in the second SLOB_UNIT.
*/
#if PAGE_SIZE <= (32767 * 2)
typedef s16 slobidx_t;
#else
typedef s32 slobidx_t;
#endif
struct slob_block {
slobidx_t units;
};
typedef struct slob_block slob_t;
/*
* We use struct page fields to manage some slob allocation aspects,
* however to avoid the horrible mess in include/linux/mm_types.h, we'll
* just define our own struct page type variant here.
*/
struct slob_page {
union {
struct {
unsigned long flags; /* mandatory */
atomic_t _count; /* mandatory */
slobidx_t units; /* free units left in page */
unsigned long pad[2];
slob_t *free; /* first free slob_t in page */
struct list_head list; /* linked list of free pages */
};
struct page page;
};
};
static inline void struct_slob_page_wrong_size(void)
{ BUILD_BUG_ON(sizeof(struct slob_page) != sizeof(struct page)); }
/*
* free_slob_page: call before a slob_page is returned to the page allocator.
*/
static inline void free_slob_page(struct slob_page *sp)
{
reset_page_mapcount(&sp->page);
sp->page.mapping = NULL;
}
/*
* All partially free slob pages go on these lists.
*/
#define SLOB_BREAK1 256
#define SLOB_BREAK2 1024
static LIST_HEAD(free_slob_small);
static LIST_HEAD(free_slob_medium);
static LIST_HEAD(free_slob_large);
/*
* slob_page: True for all slob pages (false for bigblock pages)
*/
static inline int slob_page(struct slob_page *sp)
{
return test_bit(PG_active, &sp->flags);
}
static inline void set_slob_page(struct slob_page *sp)
{
__set_bit(PG_active, &sp->flags);
}
static inline void clear_slob_page(struct slob_page *sp)
{
__clear_bit(PG_active, &sp->flags);
}
/*
* slob_page_free: true for pages on free_slob_pages list.
*/
static inline int slob_page_free(struct slob_page *sp)
{
return test_bit(PG_private, &sp->flags);
}
static void set_slob_page_free(struct slob_page *sp, struct list_head *list)
{
list_add(&sp->list, list);
__set_bit(PG_private, &sp->flags);
}
static inline void clear_slob_page_free(struct slob_page *sp)
{
list_del(&sp->list);
__clear_bit(PG_private, &sp->flags);
}
#define SLOB_UNIT sizeof(slob_t)
#define SLOB_UNITS(size) (((size) + SLOB_UNIT - 1)/SLOB_UNIT)
#define SLOB_ALIGN L1_CACHE_BYTES
/*
* struct slob_rcu is inserted at the tail of allocated slob blocks, which
* were created with a SLAB_DESTROY_BY_RCU slab. slob_rcu is used to free
* the block using call_rcu.
*/
struct slob_rcu {
struct rcu_head head;
int size;
};
/*
* slob_lock protects all slob allocator structures.
*/
static DEFINE_SPINLOCK(slob_lock);
/*
* Encode the given size and next info into a free slob block s.
*/
static void set_slob(slob_t *s, slobidx_t size, slob_t *next)
{
slob_t *base = (slob_t *)((unsigned long)s & PAGE_MASK);
slobidx_t offset = next - base;
if (size > 1) {
s[0].units = size;
s[1].units = offset;
} else
s[0].units = -offset;
}
/*
* Return the size of a slob block.
*/
static slobidx_t slob_units(slob_t *s)
{
if (s->units > 0)
return s->units;
return 1;
}
/*
* Return the next free slob block pointer after this one.
*/
static slob_t *slob_next(slob_t *s)
{
slob_t *base = (slob_t *)((unsigned long)s & PAGE_MASK);
slobidx_t next;
if (s[0].units < 0)
next = -s[0].units;
else
next = s[1].units;
return base+next;
}
/*
* Returns true if s is the last free block in its page.
*/
static int slob_last(slob_t *s)
{
return !((unsigned long)slob_next(s) & ~PAGE_MASK);
}
static void *slob_new_page(gfp_t gfp, int order, int node)
{
void *page;
#ifdef CONFIG_NUMA
if (node != -1)
page = alloc_pages_node(node, gfp, order);
else
#endif
page = alloc_pages(gfp, order);
if (!page)
return NULL;
return page_address(page);
}
/*
* Allocate a slob block within a given slob_page sp.
*/
static void *slob_page_alloc(struct slob_page *sp, size_t size, int align)
{
slob_t *prev, *cur, *aligned = 0;
int delta = 0, units = SLOB_UNITS(size);
for (prev = NULL, cur = sp->free; ; prev = cur, cur = slob_next(cur)) {
slobidx_t avail = slob_units(cur);
if (align) {
aligned = (slob_t *)ALIGN((unsigned long)cur, align);
delta = aligned - cur;
}
if (avail >= units + delta) { /* room enough? */
slob_t *next;
if (delta) { /* need to fragment head to align? */
next = slob_next(cur);
set_slob(aligned, avail - delta, next);
set_slob(cur, delta, aligned);
prev = cur;
cur = aligned;
avail = slob_units(cur);
}
next = slob_next(cur);
if (avail == units) { /* exact fit? unlink. */
if (prev)
set_slob(prev, slob_units(prev), next);
else
sp->free = next;
} else { /* fragment */
if (prev)
set_slob(prev, slob_units(prev), cur + units);
else
sp->free = cur + units;
set_slob(cur + units, avail - units, next);
}
sp->units -= units;
if (!sp->units)
clear_slob_page_free(sp);
return cur;
}
if (slob_last(cur))
return NULL;
}
}
/*
* slob_alloc: entry point into the slob allocator.
*/
static void *slob_alloc(size_t size, gfp_t gfp, int align, int node)
{
struct slob_page *sp;
struct list_head *prev;
struct list_head *slob_list;
slob_t *b = NULL;
unsigned long flags;
if (size < SLOB_BREAK1)
slob_list = &free_slob_small;
else if (size < SLOB_BREAK2)
slob_list = &free_slob_medium;
else
slob_list = &free_slob_large;
spin_lock_irqsave(&slob_lock, flags);
/* Iterate through each partially free page, try to find room */
list_for_each_entry(sp, slob_list, list) {
#ifdef CONFIG_NUMA
/*
* If there's a node specification, search for a partial
* page with a matching node id in the freelist.
*/
if (node != -1 && page_to_nid(&sp->page) != node)
continue;
#endif
/* Enough room on this page? */
if (sp->units < SLOB_UNITS(size))
continue;
/* Attempt to alloc */
prev = sp->list.prev;
b = slob_page_alloc(sp, size, align);
if (!b)
continue;
/* Improve fragment distribution and reduce our average
* search time by starting our next search here. (see
* Knuth vol 1, sec 2.5, pg 449) */
if (prev != slob_list->prev &&
slob_list->next != prev->next)
list_move_tail(slob_list, prev->next);
break;
}
spin_unlock_irqrestore(&slob_lock, flags);
/* Not enough space: must allocate a new page */
if (!b) {
b = slob_new_page(gfp & ~__GFP_ZERO, 0, node);
if (!b)
return 0;
sp = (struct slob_page *)virt_to_page(b);
set_slob_page(sp);
spin_lock_irqsave(&slob_lock, flags);
sp->units = SLOB_UNITS(PAGE_SIZE);
sp->free = b;
INIT_LIST_HEAD(&sp->list);
set_slob(b, SLOB_UNITS(PAGE_SIZE), b + SLOB_UNITS(PAGE_SIZE));
set_slob_page_free(sp, slob_list);
b = slob_page_alloc(sp, size, align);
BUG_ON(!b);
spin_unlock_irqrestore(&slob_lock, flags);
}
if (unlikely((gfp & __GFP_ZERO) && b))
memset(b, 0, size);
return b;
}
/*
* slob_free: entry point into the slob allocator.
*/
static void slob_free(void *block, int size)
{
struct slob_page *sp;
slob_t *prev, *next, *b = (slob_t *)block;
slobidx_t units;
unsigned long flags;
if (unlikely(ZERO_OR_NULL_PTR(block)))
return;
BUG_ON(!size);
sp = (struct slob_page *)virt_to_page(block);
units = SLOB_UNITS(size);
spin_lock_irqsave(&slob_lock, flags);
if (sp->units + units == SLOB_UNITS(PAGE_SIZE)) {
/* Go directly to page allocator. Do not pass slob allocator */
if (slob_page_free(sp))
clear_slob_page_free(sp);
clear_slob_page(sp);
free_slob_page(sp);
free_page((unsigned long)b);
goto out;
}
if (!slob_page_free(sp)) {
/* This slob page is about to become partially free. Easy! */
sp->units = units;
sp->free = b;
set_slob(b, units,
(void *)((unsigned long)(b +
SLOB_UNITS(PAGE_SIZE)) & PAGE_MASK));
set_slob_page_free(sp, &free_slob_small);
goto out;
}
/*
* Otherwise the page is already partially free, so find reinsertion
* point.
*/
sp->units += units;
if (b < sp->free) {
if (b + units == sp->free) {
units += slob_units(sp->free);
sp->free = slob_next(sp->free);
}
set_slob(b, units, sp->free);
sp->free = b;
} else {
prev = sp->free;
next = slob_next(prev);
while (b > next) {
prev = next;
next = slob_next(prev);
}
if (!slob_last(prev) && b + units == next) {
units += slob_units(next);
set_slob(b, units, slob_next(next));
} else
set_slob(b, units, next);
if (prev + slob_units(prev) == b) {
units = slob_units(b) + slob_units(prev);
set_slob(prev, units, slob_next(b));
} else
set_slob(prev, slob_units(prev), b);
}
out:
spin_unlock_irqrestore(&slob_lock, flags);
}
/*
* End of slob allocator proper. Begin kmem_cache_alloc and kmalloc frontend.
*/
#ifndef ARCH_KMALLOC_MINALIGN
#define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long)
#endif
#ifndef ARCH_SLAB_MINALIGN
#define ARCH_SLAB_MINALIGN __alignof__(unsigned long)
#endif
void *__kmalloc_node(size_t size, gfp_t gfp, int node)
{
unsigned int *m;
int align = max(ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN);
if (size < PAGE_SIZE - align) {
if (!size)
return ZERO_SIZE_PTR;
m = slob_alloc(size + align, gfp, align, node);
if (m)
*m = size;
return (void *)m + align;
} else {
void *ret;
ret = slob_new_page(gfp | __GFP_COMP, get_order(size), node);
if (ret) {
struct page *page;
page = virt_to_page(ret);
page->private = size;
}
return ret;
}
}
EXPORT_SYMBOL(__kmalloc_node);
void kfree(const void *block)
{
struct slob_page *sp;
if (unlikely(ZERO_OR_NULL_PTR(block)))
return;
sp = (struct slob_page *)virt_to_page(block);
if (slob_page(sp)) {
int align = max(ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN);
unsigned int *m = (unsigned int *)(block - align);
slob_free(m, *m + align);
} else
put_page(&sp->page);
}
EXPORT_SYMBOL(kfree);
/* can't use ksize for kmem_cache_alloc memory, only kmalloc */
size_t ksize(const void *block)
{
struct slob_page *sp;
BUG_ON(!block);
if (unlikely(block == ZERO_SIZE_PTR))
return 0;
sp = (struct slob_page *)virt_to_page(block);
if (slob_page(sp))
return ((slob_t *)block - 1)->units + SLOB_UNIT;
else
return sp->page.private;
}
EXPORT_SYMBOL(ksize);
struct kmem_cache {
unsigned int size, align;
unsigned long flags;
const char *name;
void (*ctor)(struct kmem_cache *, void *);
};
struct kmem_cache *kmem_cache_create(const char *name, size_t size,
size_t align, unsigned long flags,
void (*ctor)(struct kmem_cache *, void *))
{
struct kmem_cache *c;
c = slob_alloc(sizeof(struct kmem_cache), flags, 0, -1);
if (c) {
c->name = name;
c->size = size;
if (flags & SLAB_DESTROY_BY_RCU) {
/* leave room for rcu footer at the end of object */
c->size += sizeof(struct slob_rcu);
}
c->flags = flags;
c->ctor = ctor;
/* ignore alignment unless it's forced */
c->align = (flags & SLAB_HWCACHE_ALIGN) ? SLOB_ALIGN : 0;
if (c->align < ARCH_SLAB_MINALIGN)
c->align = ARCH_SLAB_MINALIGN;
if (c->align < align)
c->align = align;
} else if (flags & SLAB_PANIC)
panic("Cannot create slab cache %s\n", name);
return c;
}
EXPORT_SYMBOL(kmem_cache_create);
void kmem_cache_destroy(struct kmem_cache *c)
{
slob_free(c, sizeof(struct kmem_cache));
}
EXPORT_SYMBOL(kmem_cache_destroy);
void *kmem_cache_alloc_node(struct kmem_cache *c, gfp_t flags, int node)
{
void *b;
if (c->size < PAGE_SIZE)
b = slob_alloc(c->size, flags, c->align, node);
else
b = slob_new_page(flags, get_order(c->size), node);
if (c->ctor)
c->ctor(c, b);
return b;
}
EXPORT_SYMBOL(kmem_cache_alloc_node);
static void __kmem_cache_free(void *b, int size)
{
if (size < PAGE_SIZE)
slob_free(b, size);
else
free_pages((unsigned long)b, get_order(size));
}
static void kmem_rcu_free(struct rcu_head *head)
{
struct slob_rcu *slob_rcu = (struct slob_rcu *)head;
void *b = (void *)slob_rcu - (slob_rcu->size - sizeof(struct slob_rcu));
__kmem_cache_free(b, slob_rcu->size);
}
void kmem_cache_free(struct kmem_cache *c, void *b)
{
if (unlikely(c->flags & SLAB_DESTROY_BY_RCU)) {
struct slob_rcu *slob_rcu;
slob_rcu = b + (c->size - sizeof(struct slob_rcu));
INIT_RCU_HEAD(&slob_rcu->head);
slob_rcu->size = c->size;
call_rcu(&slob_rcu->head, kmem_rcu_free);
} else {
__kmem_cache_free(b, c->size);
}
}
EXPORT_SYMBOL(kmem_cache_free);
unsigned int kmem_cache_size(struct kmem_cache *c)
{
return c->size;
}
EXPORT_SYMBOL(kmem_cache_size);
const char *kmem_cache_name(struct kmem_cache *c)
{
return c->name;
}
EXPORT_SYMBOL(kmem_cache_name);
int kmem_cache_shrink(struct kmem_cache *d)
{
return 0;
}
EXPORT_SYMBOL(kmem_cache_shrink);
int kmem_ptr_validate(struct kmem_cache *a, const void *b)
{
return 0;
}
static unsigned int slob_ready __read_mostly;
int slab_is_available(void)
{
return slob_ready;
}
void __init kmem_cache_init(void)
{
slob_ready = 1;
}
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...