2/9
--
SUSE Labs, Novell Inc.
Mempools have 2 problems.
The first is that mempool_alloc can possibly get stuck in __alloc_pages
when they should opt to fail, and take an element from their reserved pool.
The second is that it will happily eat emergency PF_MEMALLOC reserves
instead of going to their reserved pools.
Fix the first by passing __GFP_NORETRY in the allocation calls in
mempool_alloc. Fix the second by introducing a __GFP_MEMPOOL flag
which directs the page allocator not to allocate from the reserve
pool.
Index: linux-2.6/include/linux/gfp.h
===================================================================
--- linux-2.6.orig/include/linux/gfp.h 2005-04-12 22:26:10.000000000 +1000
+++ linux-2.6/include/linux/gfp.h 2005-04-12 22:26:11.000000000 +1000
@@ -38,14 +38,16 @@ struct vm_area_struct;
#define __GFP_NO_GROW 0x2000u /* Slab internal usage */
#define __GFP_COMP 0x4000u /* Add compound page metadata */
#define __GFP_ZERO 0x8000u /* Return zeroed page on success */
+#define __GFP_MEMPOOL 0x10000u/* Mempool allocation */
-#define __GFP_BITS_SHIFT 16 /* Room for 16 __GFP_FOO bits */
+#define __GFP_BITS_SHIFT 17 /* Room for 17 __GFP_FOO bits */
#define __GFP_BITS_MASK ((1 << __GFP_BITS_SHIFT) - 1)
/* if you forget to add the bitmask here kernel will crash, period */
#define GFP_LEVEL_MASK (__GFP_WAIT|__GFP_HIGH|__GFP_IO|__GFP_FS| \
__GFP_COLD|__GFP_NOWARN|__GFP_REPEAT|__GFP_NOFAIL| \
- __GFP_NORETRY|__GFP_NO_GROW|__GFP_COMP|__GFP_ZERO)
+ __GFP_NORETRY|__GFP_NO_GROW|__GFP_COMP|__GFP_ZERO| \
+ __GFP_MEMPOOL)
#define GFP_ATOMIC (__GFP_HIGH)
#define GFP_NOIO (__GFP_WAIT)
Index: linux-2.6/mm/page_alloc.c
===================================================================
--- linux-2.6.orig/mm/page_alloc.c 2005-04-12 22:05:44.000000000 +1000
+++ linux-2.6/mm/page_alloc.c 2005-04-12 22:26:11.000000000 +1000
@@ -799,14 +799,18 @@ __alloc_pages(unsigned int __nocast gfp_
}
/* This allocation should allow future memory freeing. */
- if (((p->flags & PF_MEMALLOC) || unlikely(test_thread_flag(TIF_MEMDIE))) && !in_interrupt()) {
- /* go through the zonelist yet again, ignoring mins */
- for (i = 0; (z = zones[i]) != NULL; i++) {
- if (!cpuset_zone_allowed(z))
- continue;
- page = buffered_rmqueue(z, order, gfp_mask);
- if (page)
- goto got_pg;
+
+ if (((p->flags & PF_MEMALLOC) || unlikely(test_thread_flag(TIF_MEMDIE)))
+ && !in_interrupt()) {
+ if (!(gfp_mask & __GFP_MEMPOOL)) {
+ /* go through the zonelist yet again, ignoring mins */
+ for (i = 0; (z = zones[i]) != NULL; i++) {
+ if (!cpuset_zone_allowed(z))
+ continue;
+ page = buffered_rmqueue(z, order, gfp_mask);
+ if (page)
+ goto got_pg;
+ }
}
goto nopage;
}
Index: linux-2.6/mm/mempool.c
===================================================================
--- linux-2.6.orig/mm/mempool.c 2005-04-12 22:05:44.000000000 +1000
+++ linux-2.6/mm/mempool.c 2005-04-12 22:26:11.000000000 +1000
@@ -198,11 +198,16 @@ void * mempool_alloc(mempool_t *pool, un
void *element;
unsigned long flags;
DEFINE_WAIT(wait);
- int gfp_nowait = gfp_mask & ~(__GFP_WAIT | __GFP_IO);
+ int gfp_nowait;
+
+ gfp_mask |= __GFP_MEMPOOL;
+ gfp_mask |= __GFP_NORETRY; /* don't loop in __alloc_pages */
+ gfp_mask |= __GFP_NOWARN; /* failures are OK */
+ gfp_nowait = gfp_mask & ~(__GFP_WAIT | __GFP_IO);
might_sleep_if(gfp_mask & __GFP_WAIT);
repeat_alloc:
- element = pool->alloc(gfp_nowait|__GFP_NOWARN, pool->pool_data);
+ element = pool->alloc(gfp_nowait, pool->pool_data);
if (likely(element != NULL))
return element;
[Index of Archives]
[Kernel Newbies]
[Netfilter]
[Bugtraq]
[Photo]
[Stuff]
[Gimp]
[Yosemite News]
[MIPS Linux]
[ARM Linux]
[Linux Security]
[Linux RAID]
[Video 4 Linux]
[Linux for the blind]
[Linux Resources]
