OpenVZ Forum


Home » Mailing lists » Devel » BC: resource beancounters (v6) (with userpages reclamation + configfs)
[PATCH 9/13] BC: privvmpages accounting (hooks) [message #8169 is a reply to message #8159] Thu, 09 November 2006 16:57 Go to previous messageGo to previous message
dev is currently offline  dev
Messages: 1693
Registered: September 2005
Location: Moscow
Senior Member
BC privvmpages accounting hooks in generic code.

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

---

fs/binfmt_elf.c | 5 +--
include/asm-alpha/mman.h | 1
include/asm-generic/mman.h | 1
include/asm-mips/mman.h | 1
include/asm-parisc/mman.h | 1
include/asm-xtensa/mman.h | 1
kernel/fork.c | 11 ++++++
mm/mlock.c | 16 +++++++++
mm/mmap.c | 74 ++++++++++++++++++++++++++++++++++++++-------
mm/mprotect.c | 18 ++++++++++
mm/mremap.c | 22 ++++++++++---
mm/shmem.c | 23 +++++++++++++
12 files changed, 153 insertions(+), 21 deletions(-)

--- ./fs/binfmt_elf.c.bcvmpagesk 2006-11-03 17:46:10.000000000 +0300
+++ ./fs/binfmt_elf.c 2006-11-03 17:50:04.000000000 +0300
@@ -363,7 +363,7 @@ static unsigned long load_elf_interp(str
eppnt = elf_phdata;
for (i = 0; i < interp_elf_ex->e_phnum; i++, eppnt++) {
if (eppnt->p_type == PT_LOAD) {
- int elf_type = MAP_PRIVATE | MAP_DENYWRITE;
+ int elf_type = MAP_PRIVATE|MAP_DENYWRITE|MAP_EXECPRIO;
int elf_prot = 0;
unsigned long vaddr = 0;
unsigned long k, map_addr;
@@ -849,7 +849,8 @@ static int load_elf_binary(struct linux_
if (elf_ppnt->p_flags & PF_X)
elf_prot |= PROT_EXEC;

- elf_flags = MAP_PRIVATE | MAP_DENYWRITE | MAP_EXECUTABLE;
+ elf_flags = MAP_PRIVATE | MAP_DENYWRITE | MAP_EXECUTABLE |
+ MAP_EXECPRIO;

vaddr = elf_ppnt->p_vaddr;
if (loc->elf_ex.e_type == ET_EXEC || load_addr_set) {
--- ./include/asm-alpha/mman.h.bcvmpagesk 2006-11-03 17:46:10.000000000 +0300
+++ ./include/asm-alpha/mman.h 2006-11-03 17:50:04.000000000 +0300
@@ -14,6 +14,7 @@
#define MAP_TYPE 0x0f /* Mask for type of mapping (OSF/1 is _wrong_) */
#define MAP_FIXED 0x100 /* Interpret addr exactly */
#define MAP_ANONYMOUS 0x10 /* don't use a file */
+#define MAP_EXECPRIO 0x20 /* charge with BC_LIMIT severity */

/* not used by linux, but here to make sure we don't clash with OSF/1 defines */
#define _MAP_HASSEMAPHORE 0x0200
--- ./include/asm-generic/mman.h.bcvmpagesk 2006-11-03 17:46:10.000000000 +0300
+++ ./include/asm-generic/mman.h 2006-11-03 17:50:04.000000000 +0300
@@ -19,6 +19,7 @@
#define MAP_TYPE 0x0f /* Mask for type of mapping */
#define MAP_FIXED 0x10 /* Interpret addr exactly */
#define MAP_ANONYMOUS 0x20 /* don't use a file */
+#define MAP_EXECPRIO 0x2000 /* charge with BC_LIMIT severity */

#define MS_ASYNC 1 /* sync memory asynchronously */
#define MS_INVALIDATE 2 /* invalidate the caches */
--- ./include/asm-mips/mman.h.bcvmpagesk 2006-11-03 17:46:10.000000000 +0300
+++ ./include/asm-mips/mman.h 2006-11-03 17:50:04.000000000 +0300
@@ -46,6 +46,7 @@
#define MAP_LOCKED 0x8000 /* pages are locked */
#define MAP_POPULATE 0x10000 /* populate (prefault) pagetables */
#define MAP_NONBLOCK 0x20000 /* do not block on IO */
+#define MAP_EXECPRIO 0x40000 /* charge with BC_LIMIT severity */

/*
* Flags for msync
--- ./include/asm-parisc/mman.h.bcvmpagesk 2006-11-03 17:46:10.000000000 +0300
+++ ./include/asm-parisc/mman.h 2006-11-03 17:50:04.000000000 +0300
@@ -22,6 +22,7 @@
#define MAP_GROWSDOWN 0x8000 /* stack-like segment */
#define MAP_POPULATE 0x10000 /* populate (prefault) pagetables */
#define MAP_NONBLOCK 0x20000 /* do not block on IO */
+#define MAP_EXECPRIO 0x40000 /* charge with BC_LIMIT severity */

#define MS_SYNC 1 /* synchronous memory sync */
#define MS_ASYNC 2 /* sync memory asynchronously */
--- ./include/asm-xtensa/mman.h.bcvmpagesk 2006-11-03 17:46:10.000000000 +0300
+++ ./include/asm-xtensa/mman.h 2006-11-03 17:50:04.000000000 +0300
@@ -53,6 +53,7 @@
#define MAP_LOCKED 0x8000 /* pages are locked */
#define MAP_POPULATE 0x10000 /* populate (prefault) pagetables */
#define MAP_NONBLOCK 0x20000 /* do not block on IO */
+#define MAP_EXECPRIO 0x40000 /* charge with BC_LIMIT severity */

/*
* Flags for msync
--- ./kernel/fork.c.bcvmpagesk 2006-11-03 17:48:46.000000000 +0300
+++ ./kernel/fork.c 2006-11-03 17:50:04.000000000 +0300
@@ -50,6 +50,7 @@ static inline int dup_mmap(struct mm_str
#include <linux/random.h>

#include <bc/task.h>
+#include <bc/vmpages.h>

#include <asm/pgtable.h>
#include <asm/pgalloc.h>
@@ -257,6 +257,9 @@ static inline int dup_mmap(struct mm_str
tmp->vm_flags &= ~VM_LOCKED;
tmp->vm_mm = mm;
tmp->vm_next = NULL;
+ vma_set_bc(tmp);
+ if (bc_vma_charge(tmp))
+ goto fail_charge;
anon_vma_link(tmp);
file = tmp->vm_file;
if (file) {
@@ -299,6 +302,10 @@ out:
flush_tlb_mm(oldmm);
up_write(&oldmm->mmap_sem);
return retval;
+
+fail_charge:
+ mpol_free(pol);
+ vma_release_bc(tmp);
fail_nomem_policy:
kmem_cache_free(vm_area_cachep, tmp);
fail_nomem:
@@ -349,6 +356,7 @@ static struct mm_struct * mm_init(struct
mm->cached_hole_size = ~0UL;

if (likely(!mm_alloc_pgd(mm))) {
+ mm_init_beancounter(mm);
mm->def_flags = 0;
return mm;
}
@@ -379,6 +387,7 @@ struct mm_struct * mm_alloc(void)
void fastcall __mmdrop(struct mm_struct *mm)
{
BUG_ON(mm == &init_mm);
+ mm_free_beancounter(mm);
mm_free_pgd(mm);
destroy_context(mm);
free_mm(mm);
@@ -526,6 +535,7 @@ fail_nocontext:
* If init_new_context() failed, we cannot use mmput() to free the mm
* because it calls destroy_context()
*/
+ mm_free_beancounter(mm);
mm_free_pgd(mm);
free_mm(mm);
return NULL;
--- ./mm/mlock.c.bcvmpagesk 2006-11-03 17:46:10.000000000 +0300
+++ ./mm/mlock.c 2006-11-03 17:50:04.000000000 +0300
@@ -11,6 +11,7 @@
#include <linux/mempolicy.h>
#include <linux/syscalls.h>

+#include <bc/vmpages.h>

static int mlock_fixup(struct vm_area_struct *vma, struct vm_area_struct **prev,
unsigned long start, unsigned long end, unsigned int newflags)
@@ -19,12 +20,21 @@ static int mlock_fixup(struct vm_area_st
pgoff_t pgoff;
int pages;
int ret = 0;
-
+ int bc_recharge;
+
+ bc_recharge = BC_NOCHARGE;
if (newflags == vma->vm_flags) {
*prev = vma;
goto out;
}

+ bc_recharge = bc_need_memory_recharge(vma, vma->vm_file, newflags);
+ if (bc_recharge == BC_CHARGE) {
+ ret = __bc_memory_charge(mm, end - start, BC_BARRIER);
+ if (ret < 0)
+ goto out;
+ }
+
pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
*prev = vma_merge(mm, *prev, start, end, newflags, vma->anon_vma,
vma->vm_file, pgoff, vma_policy(vma));
@@ -48,6 +58,8 @@ static int mlock_fixup(struct vm_area_st
}

success:
+ if (bc_recharge == BC_UNCHARGE)
+ __bc_memory_uncharge(mm, end - start);
/*
* vm_flags is protected by the mmap_sem held in write mode.
* It's okay if try_to_unmap_one unmaps a page just after we
@@ -67,6 +79,8 @@ success:

vma->vm_mm->locked_vm -= pages;
out:
+ if (ret < 0 && bc_recharge == BC_CHARGE)
+ __bc_memory_uncharge(mm, end - start);
if (ret == -ENOMEM)
ret = -EAGAIN;
return ret;
--- ./mm/mmap.c.bcvmpagesk 2006-11-03 17:46:10.000000000 +0300
+++ ./mm/mmap.c 2006-11-03 17:50:04.000000000 +0300
@@ -26,6 +26,8 @@
#include <linux/mempolicy.h>
#include <linux/rmap.h>

+#include <bc/vmpages.h>
+
#include <asm/uaccess.h>
#include <asm/cacheflush.h>
#include <asm/tlb.h>
@@ -37,6 +39,7 @@
static void unmap_region(struct mm_struct *mm,
struct vm_area_struct *vma, struct vm_area_struct *prev,
unsigned long start, unsigned long end);
+static unsigned long __do_brk(unsigned long addr, unsigned long len, int prio);

/*
* WARNING: the debugging will use recursive algorithms so never enable this
@@ -224,6 +227,8 @@ static struct vm_area_struct *remove_vma
struct vm_area_struct *next = vma->vm_next;

might_sleep();
+
+ bc_vma_uncharge(vma);
if (vma->vm_ops && vma->vm_ops->close)
vma->vm_ops->close(vma);
if (vma->vm_file)
@@ -271,7 +276,7 @@ asmlinkage unsigned long sys_brk(unsigne
goto out;

/* Ok, looks good - let it rip. */
- if (do_brk(oldbrk, newbrk-oldbrk) != oldbrk)
+ if (__do_brk(oldbrk, newbrk-oldbrk, BC_BARRIER) != oldbrk)
goto out;
set_brk:
mm->brk = brk;
@@ -620,6 +625,7 @@ again: remove_next = 1 + (end > next->
fput(file);
mm->map_count--;
mpol_free(vma_policy(next));
+ vma_release_bc(next);
kmem_cache_free(vm_area_cachep, next);
/*
* In mprotect's case 6 (see comments on vma_merge),
@@ -761,15 +767,17 @@ struct vm_area_struct *vma_merge(struct
*/
if (prev && prev->vm_end == addr &&
mpol_equal(vma_policy(prev), policy) &&
+ bc_equal(mm->mm_bc, prev->vma_bc) &&
can_vma_merge_after(prev, vm_flags,
- anon_vma, file, pgoff)) {
+ anon_vma, file, pgoff)) {
/*
* OK, it can. Can we now merge in the successor as well?
*/
if (next && end == next->vm_start &&
mpol_equal(policy, vma_policy(next)) &&
+ bc_equal(mm->mm_bc, next->vma_bc) &&
can_vma_merge_before(next, vm_flags,
- anon_vma, file, pgoff+pglen) &&
+ anon_vma, file, pgoff + pglen) &&
is_mergeable_anon_vma(prev->anon_vma,
next->anon_vma)) {
/* cases 1, 6 */
@@ -786,8 +794,9 @@ struct vm_area_struct *vma_merge(struct
*/
if (next && end == next->vm_start &&
mpol_equal(policy, vma_policy(next)) &&
+ bc_equal(mm->mm_bc, next->vma_bc) &&
can_vma_merge_before(next, vm_flags,
- anon_vma, file, pgoff+pglen)) {
+ anon_vma, file, pgoff + pglen)) {
if (prev && addr < prev->vm_end) /* case 4 */
vma_adjust(prev, prev->vm_start,
addr, prev->vm_pgoff, NULL);
@@ -828,6 +837,7 @@ struct anon_vma *find_mergeable_anon_vma

if (near->anon_vma && vma->vm_end == near->vm_start &&
m ...

[ 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
Previous Topic: Re: Re: [RFC] [PATCH 0/4] uid_ns: introduction
Next Topic: [PATCH] ext3: small fix for previous retries patch in ext3_prepare_write()
Goto Forum:
  

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

Current Time: Mon Sep 08 19:35:13 GMT 2025

Total time taken to generate the page: 0.11703 seconds
Powered by FUDforum Powered by Virtuozzo Containers