OpenVZ Forum


Home » Mailing lists » Devel » [RFC][PATCH] UBC: user resource beancounters
[RFC][PATCH 5/7] UBC: kernel memory accounting (core) [message #5200 is a reply to message #5192] Wed, 16 August 2006 15:39 Go to previous messageGo to previous message
dev is currently offline  dev
Messages: 1693
Registered: September 2005
Location: Moscow
Senior Member
Introduce UB_KMEMSIZE resource which accounts kernel
objects allocated by task's request.

Reference to UB is kept on struct page or slab object.
For slabs each struct slab contains a set of pointers
corresponding objects are charged to.

Allocation charge rules:
1. Pages - if allocation is performed with __GFP_UBC flag - page
is charged to current's exec_ub.
2. Slabs - kmem_cache may be created with SLAB_UBC flag - in this
case each allocation is charged. Caches used by kmalloc are
created with SLAB_UBC | SLAB_UBC_NOCHARGE flags. In this case
only __GFP_UBC allocations are charged.

Signed-Off-By: Pavel Emelianov <xemul@sw.ru>
Signed-Off-By: Kirill Korotaev <dev@sw.ru>

---
include/linux/gfp.h | 8 ++-
include/linux/mm.h | 6 ++
include/linux/slab.h | 4 +
include/linux/vmalloc.h | 1
include/ub/beancounter.h | 4 +
include/ub/kmem.h | 33 ++++++++++++
kernel/ub/Makefile | 1
kernel/ub/beancounter.c | 3 +
kernel/ub/kmem.c | 89 ++++++++++++++++++++++++++++++++++
mm/mempool.c | 2
mm/page_alloc.c | 11 ++++
mm/slab.c | 121 ++++++++++++++++++++++++++++++++++++++---------
mm/vmalloc.c | 6 ++
13 files changed, 264 insertions(+), 25 deletions(-)

--- ./include/linux/gfp.h.kmemcore 2006-08-16 19:10:38.000000000 +0400
+++ ./include/linux/gfp.h 2006-08-16 19:12:56.000000000 +0400
@@ -46,15 +46,18 @@ struct vm_area_struct;
#define __GFP_NOMEMALLOC ((__force gfp_t)0x10000u) /* Don't use emergency reserves */
#define __GFP_HARDWALL ((__force gfp_t)0x20000u) /* Enforce hardwall cpuset memory allocs */
#define __GFP_THISNODE ((__force gfp_t)0x40000u)/* No fallback, no policies */
+#define __GFP_UBC ((__force gfp_t)0x80000u) /* Charge allocation with UB */
+#define __GFP_UBC_LIMIT ((__force gfp_t)0x100000u) /* Charge against UB limit */

-#define __GFP_BITS_SHIFT 20 /* Room for 20 __GFP_FOO bits */
+#define __GFP_BITS_SHIFT 21 /* Room for 20 __GFP_FOO bits */
#define __GFP_BITS_MASK ((__force gfp_t)((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_NOMEMALLOC|__GFP_HARDWALL|__GFP_THISNODE)
+ __GFP_NOMEMALLOC|__GFP_HARDWALL|__GFP_THISNODE| \
+ __GFP_UBC|__GFP_UBC_LIMIT)

/* This equals 0, but use constants in case they ever change */
#define GFP_NOWAIT (GFP_ATOMIC & ~__GFP_HIGH)
@@ -63,6 +66,7 @@ struct vm_area_struct;
#define GFP_NOIO (__GFP_WAIT)
#define GFP_NOFS (__GFP_WAIT | __GFP_IO)
#define GFP_KERNEL (__GFP_WAIT | __GFP_IO | __GFP_FS)
+#define GFP_KERNEL_UBC (__GFP_WAIT | __GFP_IO | __GFP_FS | __GFP_UBC)
#define GFP_USER (__GFP_WAIT | __GFP_IO | __GFP_FS | __GFP_HARDWALL)
#define GFP_HIGHUSER (__GFP_WAIT | __GFP_IO | __GFP_FS | __GFP_HARDWALL | \
__GFP_HIGHMEM)
--- ./include/linux/mm.h.kmemcore 2006-08-16 19:10:38.000000000 +0400
+++ ./include/linux/mm.h 2006-08-16 19:10:51.000000000 +0400
@@ -274,8 +274,14 @@ struct page {
unsigned int gfp_mask;
unsigned long trace[8];
#endif
+#ifdef CONFIG_USER_RESOURCE
+ union {
+ struct user_beancounter *page_ub;
+ } bc;
+#endif
};

+#define page_ub(page) ((page)->bc.page_ub)
#define page_private(page) ((page)->private)
#define set_page_private(page, v) ((page)->private = (v))

--- ./include/linux/slab.h.kmemcore 2006-08-16 19:10:38.000000000 +0400
+++ ./include/linux/slab.h 2006-08-16 19:10:51.000000000 +0400
@@ -46,6 +46,8 @@ typedef struct kmem_cache kmem_cache_t;
#define SLAB_PANIC 0x00040000UL /* panic if kmem_cache_create() fails */
#define SLAB_DESTROY_BY_RCU 0x00080000UL /* defer freeing pages to RCU */
#define SLAB_MEM_SPREAD 0x00100000UL /* Spread some memory over cpuset */
+#define SLAB_UBC 0x00200000UL /* Account with UB */
+#define SLAB_UBC_NOCHARGE 0x00400000UL /* Explicit accounting */

/* flags passed to a constructor func */
#define SLAB_CTOR_CONSTRUCTOR 0x001UL /* if not set, then deconstructor */
@@ -293,6 +295,8 @@ extern kmem_cache_t *bio_cachep;

extern atomic_t slab_reclaim_pages;

+struct user_beancounter;
+struct user_beancounter **kmem_cache_ubp(kmem_cache_t *cachep, void *obj);
#endif /* __KERNEL__ */

#endif /* _LINUX_SLAB_H */
--- ./include/linux/vmalloc.h.kmemcore 2006-08-16 19:10:38.000000000 +0400
+++ ./include/linux/vmalloc.h 2006-08-16 19:10:51.000000000 +0400
@@ -36,6 +36,7 @@ struct vm_struct {
* Highlevel APIs for driver use
*/
extern void *vmalloc(unsigned long size);
+extern void *vmalloc_ub(unsigned long size);
extern void *vmalloc_user(unsigned long size);
extern void *vmalloc_node(unsigned long size, int node);
extern void *vmalloc_exec(unsigned long size);
--- ./include/ub/beancounter.h.kmemcore 2006-08-16 19:10:38.000000000 +0400
+++ ./include/ub/beancounter.h 2006-08-16 19:10:51.000000000 +0400
@@ -12,7 +12,9 @@
* Resource list.
*/

-#define UB_RESOURCES 0
+#define UB_KMEMSIZE 0
+
+#define UB_RESOURCES 1

struct ubparm {
/*
--- ./include/ub/kmem.h.kmemcore 2006-08-16 19:10:38.000000000 +0400
+++ ./include/ub/kmem.h 2006-08-16 19:10:51.000000000 +0400
@@ -0,0 +1,33 @@
+/*
+ * include/ub/kmem.h
+ *
+ * Copyright (C) 2006 OpenVZ. SWsoft Inc
+ *
+ */
+
+#ifndef __UB_KMEM_H_
+#define __UB_KMEM_H_
+
+#include <linux/config.h>
+
+/*
+ * UB_KMEMSIZE accounting
+ */
+
+struct mm_struct;
+struct page;
+struct user_beancounter;
+
+#ifdef CONFIG_USER_RESOURCE
+int ub_page_charge(struct page *page, int order, gfp_t flags);
+void ub_page_uncharge(struct page *page, int order);
+
+int ub_slab_charge(kmem_cache_t *cachep, void *obj, gfp_t flags);
+void ub_slab_uncharge(kmem_cache_t *cachep, void *obj);
+#else
+#define ub_page_charge(pg, o, mask) (0)
+#define ub_page_uncharge(pg, o) do { } while (0)
+#define ub_slab_charge(cachep, o) (0)
+#define ub_slab_uncharge(cachep, o) do { } while (0)
+#endif
+#endif /* __UB_SLAB_H_ */
--- ./kernel/ub/Makefile.kmemcore 2006-08-16 19:10:38.000000000 +0400
+++ ./kernel/ub/Makefile 2006-08-16 19:10:51.000000000 +0400
@@ -7,3 +7,4 @@
obj-$(CONFIG_USER_RESOURCE) += beancounter.o
obj-$(CONFIG_USER_RESOURCE) += misc.o
obj-y += sys.o
+obj-$(CONFIG_USER_RESOURCE) += kmem.o
--- ./kernel/ub/beancounter.c.kmemcore 2006-08-16 19:10:38.000000000 +0400
+++ ./kernel/ub/beancounter.c 2006-08-16 19:10:51.000000000 +0400
@@ -20,6 +20,7 @@ static void init_beancounter_struct(stru
struct user_beancounter ub0;

const char *ub_rnames[] = {
+ "kmemsize", /* 0 */
};

#define ub_hash_fun(x) ((((x) >> 8) ^ (x)) & (UB_HASH_SIZE - 1))
@@ -356,6 +357,8 @@ static void init_beancounter_syslimits(s
{
int k;

+ ub->ub_parms[UB_KMEMSIZE].limit = 32 * 1024 * 1024;
+
for (k = 0; k < UB_RESOURCES; k++)
ub->ub_parms[k].barrier = ub->ub_parms[k].limit;
}
--- ./kernel/ub/kmem.c.kmemcore 2006-08-16 19:10:38.000000000 +0400
+++ ./kernel/ub/kmem.c 2006-08-16 19:10:51.000000000 +0400
@@ -0,0 +1,89 @@
+/*
+ * kernel/ub/kmem.c
+ *
+ * Copyright (C) 2006 OpenVZ. SWsoft Inc
+ *
+ */
+
+#include <linux/sched.h>
+#include <linux/gfp.h>
+#include <linux/slab.h>
+#include <linux/mm.h>
+
+#include <ub/beancounter.h>
+#include <ub/kmem.h>
+#include <ub/task.h>
+
+/*
+ * Slab accounting
+ */
+
+int ub_slab_charge(kmem_cache_t *cachep, void *objp, gfp_t flags)
+{
+ unsigned int size;
+ struct user_beancounter *ub, **slab_ubp;
+
+ ub = get_exec_ub();
+ if (ub == NULL)
+ return 0;
+
+ size = kmem_cache_size(cachep);
+ if (charge_beancounter(ub, UB_KMEMSIZE, size,
+ (flags & __GFP_UBC_LIMIT ? UB_LIMIT : UB_BARRIER)))
+ return -ENOMEM;
+
+ slab_ubp = kmem_cache_ubp(cachep, objp);
+ *slab_ubp = get_beancounter(ub);
+ return 0;
+}
+
+void ub_slab_uncharge(kmem_cache_t *cachep, void *objp)
+{
+ unsigned int size;
+ struct user_beancounter *ub, **slab_ubp;
+
+ slab_ubp = kmem_cache_ubp(cachep, objp);
+ if (*slab_ubp == NULL)
+ return;
+
+ ub = *slab_ubp;
+ size = kmem_cache_size(cachep);
+ uncharge_beancounter(ub, UB_KMEMSIZE, size);
+ put_beancounter(ub);
+ *slab_ubp = NULL;
+}
+
+/*
+ * Pages accounting
+ */
+
+int ub_page_charge(struct page *page, int order, gfp_t flags)
+{
+ struct user_beancounter *ub;
+
+ BUG_ON(page_ub(page) != NULL);
+
+ ub = get_exec_ub();
+ if (ub == NULL)
+ return 0;
+
+ if (charge_beancounter(ub, UB_KMEMSIZE, PAGE_SIZE << order,
+ (flags & __GFP_UBC_LIMIT ? UB_LIMIT : UB_BARRIER)))
+ return -ENOMEM;
+
+ page_ub(page) = get_beancounter(ub);
+ return 0;
+}
+
+void ub_page_uncharge(struct page *page, int order)
+{
+ struct user_beancounter *ub;
+
+ ub = page_ub(page);
+ if (ub == NULL)
+ return;
+
+ uncharge_beancounter(ub, UB_KMEMSIZE, PAGE_SIZE << order);
+ put_beancounter(ub);
+ page_ub(page) = NULL;
+}
--- ./mm/mempool.c.kmemcore 2006-08-16 19:10:38.000000000 +0400
+++ ./mm/mempool.c 2006-08-16 19:10:51.000000000 +0400
@@ -119,6 +119,7 @@ int mempool_resize(mempool_t *pool, int
unsigned long flags;

BUG_ON(new_min_nr <= 0);
+ gfp_mask &= ~__GFP_UBC;

spin_lock_irqsave(&pool->lock, flags);
if (new_min_nr <= pool->min_nr) {
@@ -212,6 +213,7 @@ void * mempool_alloc(mempool_t *pool, gf
gfp_mask |= __GFP_NOMEMALLOC; /* don't allocate emergency reserves */
gfp_mask |= __GFP_NORETRY; /* don't loop in __alloc_pages */
gfp_mask |= __GFP_NOWARN; /* failures are OK */
+ gfp_mask &= ~__GFP_UBC; /* do not charge */

gfp_temp = gfp_mask & ~(__GFP_WAIT|__GFP_IO);

--- ./mm/page_alloc.c.kmemcore 2006-08-16 19:10:38.000000000 +0400
+++ ./mm/page_alloc.c 2006-08-16 19:10:51.000000000 +0400
@@ -38,6 +38,8 @@
#include <linux/mempolicy.h>
#include <linux/stop_machine.h>

+#include <ub/kmem.h>
+
#include <asm/tlbflush.h>
#include <asm/div64.h>
#include "internal.h"
 ...

[ Show the rest of the message ]

Report message to a moderator

[Message index]
 
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Previous Topic: [PATCH] vzlist: Fix "cast from pointer to integer of different size" warnings
Next Topic: [RFC][PATCH 1/2] add user namespace [try #2]
Goto Forum:
  

[ Syndicate this forum (XML) ] [ RSS ] [ PDF ]

Current Time: Thu Apr 03 11:14:19 GMT 2025

Total time taken to generate the page: 0.05522 seconds
Powered by FUDforum Powered by Virtuozzo Containers