Home » Mailing lists » Devel » [PATCH] BC: resource beancounters (v5) (added userpages reclamation)
| [PATCH 10/10] BC: user memory accounting (hooks) [message #7168 is a reply to message #7157] |
Thu, 05 October 2006 15:56   |
Kirill Korotaev
Messages: 137
Registered: January 2006
|
Senior Member |
|
|
Install BC hooks in appropriate places for user memory accounting.
Signed-off-by: Pavel Emelianov <xemul@openvz.org>
Signed-off-by: Kirill Korotaev <dev@openvz.org>
---
fs/binfmt_elf.c | 5 +--
fs/exec.c | 14 +++++++-
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/fremap.c | 10 ++++++
mm/memory.c | 40 +++++++++++++++++++++++-
mm/migrate.c | 10 ++++++
mm/mlock.c | 16 +++++++++
mm/mmap.c | 74 ++++++++++++++++++++++++++++++++++++++-------
mm/mprotect.c | 18 ++++++++++
mm/mremap.c | 22 ++++++++++---
mm/rmap.c | 3 +
mm/shmem.c | 15 +++++++++
17 files changed, 219 insertions(+), 24 deletions(-)
--- ./fs/binfmt_elf.c.bc_userpages 2006-10-05 11:42:42.000000000 +0400
+++ ./fs/binfmt_elf.c 2006-10-05 12:44:20.000000000 +0400
@@ -360,7 +360,7 @@ 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;
@@ -846,7 +846,8 @@ 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) {
--- ./fs/exec.c.bc_userpages 2006-10-05 11:42:42.000000000 +0400
+++ ./fs/exec.c 2006-10-05 12:44:20.000000000 +0400
@@ -50,6 +50,8 @@
#include <linux/cn_proc.h>
#include <linux/audit.h>
+#include <bc/rsspages.h>
+
#include <asm/uaccess.h>
#include <asm/mmu_context.h>
@@ -308,27 +310,35 @@ void install_arg_page(struct vm_area_str
struct mm_struct *mm = vma->vm_mm;
pte_t * pte;
spinlock_t *ptl;
+ struct page_beancounter *pc;
if (unlikely(anon_vma_prepare(vma)))
goto out;
+ if (bc_rsspage_prepare(page, vma, &pc))
+ goto out;
+
flush_dcache_page(page);
pte = get_locked_pte(mm, address, &ptl);
if (!pte)
- goto out;
+ goto out_unch;
if (!pte_none(*pte)) {
pte_unmap_unlock(pte, ptl);
- goto out;
+ goto out_unch;
}
inc_mm_counter(mm, anon_rss);
lru_cache_add_active(page);
set_pte_at(mm, address, pte, pte_mkdirty(pte_mkwrite(mk_pte(
page, vma->vm_page_prot))));
page_add_new_anon_rmap(page, vma, address);
+ bc_rsspage_charge(pc);
pte_unmap_unlock(pte, ptl);
/* no need for flush_tlb */
return;
+
+out_unch:
+ bc_rsspage_release(pc);
out:
__free_page(page);
force_sig(SIGKILL, current);
--- ./include/asm-alpha/mman.h.bc_userpages 2006-09-20 14:46:38.000000000 +0400
+++ ./include/asm-alpha/mman.h 2006-10-05 12:44:20.000000000 +0400
@@ -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.bc_userpages 2006-09-20 14:46:38.000000000 +0400
+++ ./include/asm-generic/mman.h 2006-10-05 12:44:20.000000000 +0400
@@ -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.bc_userpages 2006-09-20 14:46:39.000000000 +0400
+++ ./include/asm-mips/mman.h 2006-10-05 12:44:20.000000000 +0400
@@ -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.bc_userpages 2006-09-20 14:46:39.000000000 +0400
+++ ./include/asm-parisc/mman.h 2006-10-05 12:44:20.000000000 +0400
@@ -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.bc_userpages 2006-09-20 14:46:40.000000000 +0400
+++ ./include/asm-xtensa/mman.h 2006-10-05 12:44:20.000000000 +0400
@@ -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.bc_userpages 2006-10-05 12:14:35.000000000 +0400
+++ ./kernel/fork.c 2006-10-05 12:44:20.000000000 +0400
@@ -50,6 +50,7 @@
#include <linux/random.h>
#include <bc/task.h>
+#include <bc/vmpages.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
@@ -252,6 +253,9 @@ 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) {
@@ -294,6 +298,10 @@ 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:
@@ -344,6 +352,7 @@ 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;
}
@@ -374,6 +383,7 @@ 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);
@@ -508,6 +518,7 @@ 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/fremap.c.bc_userpages 2006-10-05 11:42:43.000000000 +0400
+++ ./mm/fremap.c 2006-10-05 12:44:20.000000000 +0400
@@ -16,6 +16,8 @@
#include <linux/module.h>
#include <linux/syscalls.h>
+#include <bc/rsspages.h>
+
#include <asm/mmu_context.h>
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
@@ -57,6 +59,10 @@ int install_page(struct mm_struct *mm, s
pte_t *pte;
pte_t pte_val;
spinlock_t *ptl;
+ struct page_beancounter *pc;
+
+ if (bc_rsspage_prepare(page, vma, &pc))
+ goto out_nocharge;
pte = get_locked_pte(mm, addr, &ptl);
if (!pte)
@@ -84,10 +90,14 @@ int install_page(struct mm_struct *mm, s
page_add_file_rmap(page);
update_mmu_cache(vma, addr, pte_val);
lazy_mmu_prot_update(pte_val);
+ bc_rsspage_charge(pc);
err = 0;
unlock:
pte_unmap_unlock(pte, ptl);
out:
+ if (err != 0)
+ bc_rsspage_release(pc);
+out_nocharge:
return err;
}
EXPORT_SYMBOL(install_page);
--- ./mm/memory.c.bc_userpages 2006-10-05 11:42:43.000000000 +0400
+++ ./mm/memory.c 2006-10-05 12:44:20.000000000 +0400
@@ -57,6 +57,8 @@
#include <asm/tlbflush.h>
#include <asm/pgtable.h>
+#include <bc/rsspages.h>
+
#include <linux/swapops.h>
#include <linux/elf.h>
@@ -1483,6 +1485,7 @@ static int do_wp_page(struct mm_struct *
pte_t entry;
int reuse = 0, ret = VM_FAULT_MINOR;
struct page *dirty_page = NULL;
+ struct page_beancounter *pc;
old_page = vm_normal_page(vma, address, orig_pte);
if (!old_page)
@@ -1568,6 +1571,9 @@ gotten:
cow_user_page(new_page, old_page, address);
}
+ if (bc_rsspage_prepare(new_page, vma, &pc))
+ goto oom;
+
/*
* Re-check the pte - we dropped the lock
*/
@@ -1596,11 +1602,14 @@ gotten:
update_mmu_cache(vma, address, entry);
lru_cache_add_active(new_page);
page_add_new_anon_rmap(new_page, vma, address);
+ bc_rsspage_charge(pc);
/* Free the old page.. */
new_page = old_page;
ret |= VM_FAULT_WRITE;
- }
+ } else
+ bc_rsspage_release(pc);
+
if (new_page)
page_cache_release(new_page);
if (old_page)
@@ -1977,6 +1986,7 @@ static int do_swap_page(struct mm_struct
swp_entry_t entry;
pte_t pte;
int ret = VM_FAULT_MINOR;
+ struct page_beancounter *pc;
if (!pte_unmap_same(mm, pmd, page_table, orig_pte))
goto out;
@@ -2009,6 +2019,11 @@ static int do_swap_page(struct mm_struct
count_vm_event(PGMAJFAULT);
}
+ if (bc_rsspage_prepare(page, vma, &pc)) {
+ ret = VM_FAULT_OOM;
+ goto out;
+ }
+
delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
mark_page_accessed(page);
lock_page(page);
@@ -2022,6 +2037,7 @@ static int do_swap_page(struct mm_struct
if (unlikely(!PageUptodate(page))) {
ret = VM_FAULT_SIGBUS;
+ bc_rsspage_uncharge(page);
goto out_nomap;
}
@@ -2037,6 +2053,7 @@ static int do_swap_page(struct mm_struct
flush_icache_page(vma, page);
set_pte_at(mm, address, page_table, pte);
page_add_anon_rmap(page, vma, address);
+ bc_rsspage_charge(pc);
swap_free(entry);
if (vm_swap_f
...
|
|
|
|
Current Time: Tue Jul 15 21:38:20 GMT 2025
Total time taken to generate the page: 0.03611 seconds
|
OpenVZ Forum
Members
Search
Help
Register
Login
Home
