Introduce calls to BC code over the kernel to add
accounting of physical pages/privvmpages.
Signed-Off-By: Pavel Emelianov <xemul@sw.ru>
Signed-Off-By: Kirill Korotaev <dev@sw.ru>
---
fs/exec.c | 11 ++++
include/linux/mm.h | 3 -
kernel/fork.c | 2
mm/filemap_xip.c | 2
mm/fremap.c | 11 ++++
mm/memory.c | 141 +++++++++++++++++++++++++++++++++++++++++------------
mm/migrate.c | 3 +
mm/mprotect.c | 12 +++-
mm/rmap.c | 4 +
mm/swapfile.c | 47 ++++++++++++-----
10 files changed, 186 insertions(+), 50 deletions(-)
--- ./fs/exec.c.bcrssch 2006-09-05 12:53:55.000000000 +0400
+++ ./fs/exec.c 2006-09-05 13:51:55.000000000 +0400
@@ -50,6 +50,8 @@
#include <linux/cn_proc.h>
#include <linux/audit.h>
+#include <bc/vmrss.h>
+
#include <asm/uaccess.h>
#include <asm/mmu_context.h>
@@ -308,6 +310,11 @@ void install_arg_page(struct vm_area_str
struct mm_struct *mm = vma->vm_mm;
pte_t * pte;
spinlock_t *ptl;
+ struct page_beancounter *pb;
+
+ pb = bc_alloc_rss_counter();
+ if (IS_ERR(pb))
+ goto out_nopb;
if (unlikely(anon_vma_prepare(vma)))
goto out;
@@ -325,11 +332,15 @@ void install_arg_page(struct vm_area_str
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_vmrss_page_add(page, mm, vma, &pb);
pte_unmap_unlock(pte, ptl);
/* no need for flush_tlb */
+ bc_free_rss_counter(pb);
return;
out:
+ bc_free_rss_counter(pb);
+out_nopb:
__free_page(page);
force_sig(SIGKILL, current);
}
--- ./include/linux/mm.h.bcrssch 2006-09-05 13:47:12.000000000 +0400
+++ ./include/linux/mm.h 2006-09-05 13:51:55.000000000 +0400
@@ -753,7 +753,8 @@ void free_pgd_range(struct mmu_gather **
void free_pgtables(struct mmu_gather **tlb, struct vm_area_struct *start_vma,
unsigned long floor, unsigned long ceiling);
int copy_page_range(struct mm_struct *dst, struct mm_struct *src,
- struct vm_area_struct *vma);
+ struct vm_area_struct *vma,
+ struct vm_area_struct *dst_vma);
int zeromap_page_range(struct vm_area_struct *vma, unsigned long from,
unsigned long size, pgprot_t prot);
void unmap_mapping_range(struct address_space *mapping,
--- ./kernel/fork.c.bcrssch 2006-09-05 13:23:27.000000000 +0400
+++ ./kernel/fork.c 2006-09-05 13:51:55.000000000 +0400
@@ -280,7 +280,7 @@ static inline int dup_mmap(struct mm_str
rb_parent = &tmp->vm_rb;
mm->map_count++;
- retval = copy_page_range(mm, oldmm, mpnt);
+ retval = copy_page_range(mm, oldmm, mpnt, tmp);
if (tmp->vm_ops && tmp->vm_ops->open)
tmp->vm_ops->open(tmp);
--- ./mm/filemap_xip.c.bcrssch 2006-07-10 12:39:20.000000000 +0400
+++ ./mm/filemap_xip.c 2006-09-05 13:51:55.000000000 +0400
@@ -13,6 +13,7 @@
#include <linux/module.h>
#include <linux/uio.h>
#include <linux/rmap.h>
+#include <bc/vmrss.h>
#include <asm/tlbflush.h>
#include "filemap.h"
@@ -189,6 +190,7 @@ __xip_unmap (struct address_space * mapp
/* Nuke the page table entry. */
flush_cache_page(vma, address, pte_pfn(*pte));
pteval = ptep_clear_flush(vma, address, pte);
+ bc_vmrss_page_del(page, mm, vma);
page_remove_rmap(page);
dec_mm_counter(mm, file_rss);
BUG_ON(pte_dirty(pteval));
--- ./mm/fremap.c.bcrssch 2006-09-05 12:53:59.000000000 +0400
+++ ./mm/fremap.c 2006-09-05 13:51:55.000000000 +0400
@@ -16,6 +16,8 @@
#include <linux/module.h>
#include <linux/syscalls.h>
+#include <bc/vmrss.h>
+
#include <asm/mmu_context.h>
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
@@ -33,6 +35,7 @@ static int zap_pte(struct mm_struct *mm,
if (page) {
if (pte_dirty(pte))
set_page_dirty(page);
+ bc_vmrss_page_del(page, mm, vma);
page_remove_rmap(page);
page_cache_release(page);
}
@@ -57,6 +60,11 @@ int install_page(struct mm_struct *mm, s
pte_t *pte;
pte_t pte_val;
spinlock_t *ptl;
+ struct page_beancounter *pb;
+
+ pb = bc_alloc_rss_counter();
+ if (IS_ERR(pb))
+ goto out_nopb;
pte = get_locked_pte(mm, addr, &ptl);
if (!pte)
@@ -82,12 +90,15 @@ int install_page(struct mm_struct *mm, s
pte_val = mk_pte(page, prot);
set_pte_at(mm, addr, pte, pte_val);
page_add_file_rmap(page);
+ bc_vmrss_page_add(page, mm, vma, &pb);
update_mmu_cache(vma, addr, pte_val);
lazy_mmu_prot_update(pte_val);
err = 0;
unlock:
pte_unmap_unlock(pte, ptl);
out:
+ bc_free_rss_counter(pb);
+out_nopb:
return err;
}
EXPORT_SYMBOL(install_page);
--- ./mm/memory.c.bcrssch 2006-09-05 12:53:59.000000000 +0400
+++ ./mm/memory.c 2006-09-05 13:51:55.000000000 +0400
@@ -51,6 +51,9 @@
#include <linux/init.h>
#include <linux/writeback.h>
+#include <bc/vmpages.h>
+#include <bc/vmrss.h>
+
#include <asm/pgalloc.h>
#include <asm/uaccess.h>
#include <asm/tlb.h>
@@ -427,7 +430,9 @@ struct page *vm_normal_page(struct vm_ar
static inline void
copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
pte_t *dst_pte, pte_t *src_pte, struct vm_area_struct *vma,
- unsigned long addr, int *rss)
+ unsigned long addr, int *rss,
+ struct vm_area_struct *dst_vma,
+ struct page_beancounter **ppb)
{
unsigned long vm_flags = vma->vm_flags;
pte_t pte = *src_pte;
@@ -481,6 +486,7 @@ copy_one_pte(struct mm_struct *dst_mm, s
page = vm_normal_page(vma, addr, pte);
if (page) {
get_page(page);
+ bc_vmrss_page_dup(page, dst_mm, dst_vma, ppb);
page_dup_rmap(page);
rss[!!PageAnon(page)]++;
}
@@ -489,20 +495,32 @@ out_set_pte:
set_pte_at(dst_mm, addr, dst_pte, pte);
}
+#define pte_ptrs(a) (PTRS_PER_PTE - ((a >> PAGE_SHIFT)&(PTRS_PER_PTE - 1)))
+
static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
pmd_t *dst_pmd, pmd_t *src_pmd, struct vm_area_struct *vma,
- unsigned long addr, unsigned long end)
+ unsigned long addr, unsigned long end,
+ struct vm_area_struct *dst_vma)
{
pte_t *src_pte, *dst_pte;
spinlock_t *src_ptl, *dst_ptl;
int progress = 0;
- int rss[2];
+ int rss[2], err;
+ struct page_beancounter *pb;
+ err = -ENOMEM;
+ pb = (mm_same_bc(dst_mm, src_mm) ? PB_COPY_SAME : NULL);
again:
+ if (pb != PB_COPY_SAME) {
+ pb = bc_alloc_rss_counter_list(pte_ptrs(addr), pb);
+ if (IS_ERR(pb))
+ goto out;
+ }
+
rss[1] = rss[0] = 0;
dst_pte = pte_alloc_map_lock(dst_mm, dst_pmd, addr, &dst_ptl);
if (!dst_pte)
- return -ENOMEM;
+ goto out;
src_pte = pte_offset_map_nested(src_pmd, addr);
src_ptl = pte_lockptr(src_mm, src_pmd);
spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
@@ -524,7 +542,8 @@ again:
progress++;
continue;
}
- copy_one_pte(dst_mm, src_mm, dst_pte, src_pte, vma, addr, rss);
+ copy_one_pte(dst_mm, src_mm, dst_pte, src_pte, vma, addr, rss,
+ dst_vma, &pb);
progress += 8;
} while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end);
@@ -536,12 +555,18 @@ again:
cond_resched();
if (addr != end)
goto again;
- return 0;
+
+ err = 0;
+out:
+ if (pb != PB_COPY_SAME)
+ bc_free_rss_counter(pb);
+ return err;
}
static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
pud_t *dst_pud, pud_t *src_pud, struct vm_area_struct *vma,
- unsigned long addr, unsigned long end)
+ unsigned long addr, unsigned long end,
+ struct vm_area_struct *dst_vma)
{
pmd_t *src_pmd, *dst_pmd;
unsigned long next;
@@ -555,7 +580,7 @@ static inline int copy_pmd_range(struct
if (pmd_none_or_clear_bad(src_pmd))
continue;
if (copy_pte_range(dst_mm, src_mm, dst_pmd, src_pmd,
- vma, addr, next))
+ vma, addr, next, dst_vma))
return -ENOMEM;
} while (dst_pmd++, src_pmd++, addr = next, addr != end);
return 0;
@@ -563,7 +588,8 @@ static inline int copy_pmd_range(struct
static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
pgd_t *dst_pgd, pgd_t *src_pgd, struct vm_area_struct *vma,
- unsigned long addr, unsigned long end)
+ unsigned long addr, unsigned long end,
+ struct vm_area_struct *dst_vma)
{
pud_t *src_pud, *dst_pud;
unsigned long next;
@@ -577,14 +603,14 @@ static inline int copy_pud_range(struct
if (pud_none_or_clear_bad(src_pud))
continue;
if (copy_pmd_range(dst_mm, src_mm, dst_pud, src_pud,
- vma, addr, next))
+ vma, addr, next, dst_vma))
return -ENOMEM;
} while (dst_pud++, src_pud++, addr = next, addr != end);
return 0;
}
int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
- struct vm_area_struct *vma)
+ struct vm_area_struct *vma, struct vm_area_struct *dst_vma)
{
pgd_t *src_pgd, *dst_pgd;
unsigned long next;
@@ -612,7 +638,7 @@ int copy_page_range(struct mm_struct *ds
if (pgd_none_or_clear_bad(src_pgd))
continue;
if (copy_pud_range(dst_mm, src_mm, dst_pgd, src_pgd,
- vma, addr, next))
+ vma, addr, next, dst_vma))
return -ENOMEM;
} while (dst_pgd++, src_pgd++, addr = next, addr != end);
return 0;
@@ -681,6 +707,7 @@ static unsigned long zap_pte_range(struc
mark_page_accessed(page);
file_rss--;
}
+ bc_vmrss_page_del(page, mm, vma);
page_remove_rmap(page);
tlb_remove_page(tlb, page);
continue;
@@ -1104,8 +1131,9 @@ int get_user_pages(struct task_struct *t
}
EXPORT_SYMBOL(get_user_pages);
-static int zeromap_pte_range(struct mm_struct *mm, pmd_t *pmd,
- unsigned long addr, unsigned long end, pgprot_t prot)
+static int zeromap_pte_range(struct mm_struct *mm,
+ struct vm_area_struct *vma, pmd_t *pmd,
+ unsigned long addr, unsigned long end, pgprot_t prot)
{
pte_t *pte;
spinlock_t *ptl;
@@ -1118,6 +1146,7 @@ static int zeromap_pte_range(struct mm_s
struct page *page = ZERO_PAGE(addr);
pte_t zero_pte = pte_wrprotect(mk_pte(page, prot));
page_cache_get(page);
+ bc_vmrss_page_add_noref(page,
...
|
OpenVZ Forum
Members
Search
Help
Register
Login
Home
