| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20091106084806.7503b165.kamezawa.hiroyu@jp.fujitsu.com>
Date: Fri, 6 Nov 2009 08:48:06 +0900
From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@...fujitsu.com>
To: Minchan Kim <minchan.kim@...il.com>
Cc: "linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
"linux-mm@...ck.org" <linux-mm@...ck.org>,
"hugh.dickins@...cali.co.uk" <hugh.dickins@...cali.co.uk>,
cl@...ux-foundation.org, akpm@...ux-foundation.org,
"kosaki.motohiro@...fujitsu.com" <kosaki.motohiro@...fujitsu.com>
Subject: Re: [PATCH] show per-process swap usage via procfs
On Fri, 6 Nov 2009 00:11:32 +0900
Minchan Kim <minchan.kim@...il.com> wrote:
> Hi, Kame.
>
Hi,
<snip>
> > /*
> > @@ -597,7 +600,9 @@ copy_one_pte(struct mm_struct *dst_mm, s
> > &src_mm->mmlist);
> > spin_unlock(&mmlist_lock);
> > }
> > - if (is_write_migration_entry(entry) &&
> > + if (!is_migration_entry(entry))
> > + rss[2]++;
>
> First thought I come to is that we believe !is_migration_entry(entry) equal
> swap entry?
> We began supporting HWPOISON.
> HWPOISON would be rare event so some less exact swap accouting may
> be allowed, I think. Is this enough to jusitfy that?
>
Ah, ok, I'll fix here.
> > + else if (is_write_migration_entry(entry) &&
> > is_cow_mapping(vm_flags)) {
> > /*
> > * COW mappings require pages in both parent
> > @@ -648,11 +653,11 @@ static int copy_pte_range(struct mm_stru
> > pte_t *src_pte, *dst_pte;
> > spinlock_t *src_ptl, *dst_ptl;
> > int progress = 0;
> > - int rss[2];
> > + int rss[3];
> > swp_entry_t entry = (swp_entry_t){0};
> >
> > again:
> > - rss[1] = rss[0] = 0;
> > + rss[2] = rss[1] = rss[0] = 0;
> > dst_pte = pte_alloc_map_lock(dst_mm, dst_pmd, addr, &dst_ptl);
> > if (!dst_pte)
> > return -ENOMEM;
> > @@ -688,7 +693,7 @@ again:
> > arch_leave_lazy_mmu_mode();
> > spin_unlock(src_ptl);
> > pte_unmap_nested(orig_src_pte);
> > - add_mm_rss(dst_mm, rss[0], rss[1]);
> > + add_mm_rss(dst_mm, rss[0], rss[1], rss[2]);
> > pte_unmap_unlock(orig_dst_pte, dst_ptl);
> > cond_resched();
> >
> > @@ -818,6 +823,7 @@ static unsigned long zap_pte_range(struc
> > spinlock_t *ptl;
> > int file_rss = 0;
> > int anon_rss = 0;
> > + int swap_usage = 0;
> >
> > pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
> > arch_enter_lazy_mmu_mode();
> > @@ -887,13 +893,18 @@ static unsigned long zap_pte_range(struc
> > if (pte_file(ptent)) {
> > if (unlikely(!(vma->vm_flags & VM_NONLINEAR)))
> > print_bad_pte(vma, addr, ptent, NULL);
> > - } else if
> > - (unlikely(!free_swap_and_cache(pte_to_swp_entry(ptent))))
> > - print_bad_pte(vma, addr, ptent, NULL);
> > + } else {
> > + swp_entry_t ent = pte_to_swp_entry(ptent);
> > +
> > + if (!is_migration_entry(ent))
> > + swap_usage--;
>
> ditto
>
ok, will do.
> > + if (unlikely(!free_swap_and_cache(ent)))
> > + print_bad_pte(vma, addr, ptent, NULL);
> > + }
> > pte_clear_not_present_full(mm, addr, pte, tlb->fullmm);
> > } while (pte++, addr += PAGE_SIZE, (addr != end && *zap_work > 0));
> >
> > - add_mm_rss(mm, file_rss, anon_rss);
> > + add_mm_rss(mm, file_rss, anon_rss, swap_usage);
> > arch_leave_lazy_mmu_mode();
> > pte_unmap_unlock(pte - 1, ptl);
> >
> > @@ -2595,6 +2606,7 @@ static int do_swap_page(struct mm_struct
> > */
> >
> > inc_mm_counter(mm, anon_rss);
> > + dec_mm_counter(mm, swap_usage);
> > pte = mk_pte(page, vma->vm_page_prot);
> > if ((flags & FAULT_FLAG_WRITE) && reuse_swap_page(page)) {
> > pte = maybe_mkwrite(pte_mkdirty(pte), vma);
> > Index: mmotm-2.6.32-Nov2/mm/swapfile.c
> > ===================================================================
> > --- mmotm-2.6.32-Nov2.orig/mm/swapfile.c
> > +++ mmotm-2.6.32-Nov2/mm/swapfile.c
> > @@ -837,6 +837,7 @@ static int unuse_pte(struct vm_area_stru
> > }
> >
> > inc_mm_counter(vma->vm_mm, anon_rss);
> > + dec_mm_counter(vma->vm_mm, swap_usage);
> > get_page(page);
> > set_pte_at(vma->vm_mm, addr, pte,
> > pte_mkold(mk_pte(page, vma->vm_page_prot)));
> > Index: mmotm-2.6.32-Nov2/fs/proc/task_mmu.c
> > ===================================================================
> > --- mmotm-2.6.32-Nov2.orig/fs/proc/task_mmu.c
> > +++ mmotm-2.6.32-Nov2/fs/proc/task_mmu.c
> > @@ -17,7 +17,7 @@
> > void task_mem(struct seq_file *m, struct mm_struct *mm)
> > {
> > unsigned long data, text, lib;
> > - unsigned long hiwater_vm, total_vm, hiwater_rss, total_rss;
> > + unsigned long hiwater_vm, total_vm, hiwater_rss, total_rss, swap;
> >
> > /*
> > * Note: to minimize their overhead, mm maintains hiwater_vm and
> > @@ -36,6 +36,7 @@ void task_mem(struct seq_file *m, struct
> > data = mm->total_vm - mm->shared_vm - mm->stack_vm;
> > text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK)) >> 10;
> > lib = (mm->exec_vm << (PAGE_SHIFT-10)) - text;
> > + swap = get_mm_counter(mm, swap_usage);
> > seq_printf(m,
> > "VmPeak:\t%8lu kB\n"
> > "VmSize:\t%8lu kB\n"
> > @@ -46,7 +47,8 @@ void task_mem(struct seq_file *m, struct
> > "VmStk:\t%8lu kB\n"
> > "VmExe:\t%8lu kB\n"
> > "VmLib:\t%8lu kB\n"
> > - "VmPTE:\t%8lu kB\n",
> > + "VmPTE:\t%8lu kB\n"
> > + "VmSwap:\t%8lu kB\n",
> > hiwater_vm << (PAGE_SHIFT-10),
> > (total_vm - mm->reserved_vm) << (PAGE_SHIFT-10),
> > mm->locked_vm << (PAGE_SHIFT-10),
> > @@ -54,7 +56,8 @@ void task_mem(struct seq_file *m, struct
> > total_rss << (PAGE_SHIFT-10),
> > data << (PAGE_SHIFT-10),
> > mm->stack_vm << (PAGE_SHIFT-10), text, lib,
> > - (PTRS_PER_PTE*sizeof(pte_t)*mm->nr_ptes) >> 10);
> > + (PTRS_PER_PTE*sizeof(pte_t)*mm->nr_ptes) >> 10,
> > + swap << (PAGE_SHIFT - 10));
> > }
> >
> > unsigned long task_vsize(struct mm_struct *mm)
> > Index: mmotm-2.6.32-Nov2/mm/rmap.c
> > ===================================================================
> > --- mmotm-2.6.32-Nov2.orig/mm/rmap.c
> > +++ mmotm-2.6.32-Nov2/mm/rmap.c
> > @@ -834,6 +834,7 @@ static int try_to_unmap_one(struct page
> > spin_unlock(&mmlist_lock);
> > }
> > dec_mm_counter(mm, anon_rss);
> > + inc_mm_counter(mm, swap_usage);
> > } else if (PAGE_MIGRATION) {
> > /*
> > * Store the pfn of the page in a special migration
> > Index: mmotm-2.6.32-Nov2/kernel/fork.c
> > ===================================================================
> > --- mmotm-2.6.32-Nov2.orig/kernel/fork.c
> > +++ mmotm-2.6.32-Nov2/kernel/fork.c
> > @@ -454,6 +454,7 @@ static struct mm_struct * mm_init(struct
> > mm->nr_ptes = 0;
> > set_mm_counter(mm, file_rss, 0);
> > set_mm_counter(mm, anon_rss, 0);
> > + set_mm_counter(mm, swap_usage, 0);
> > spin_lock_init(&mm->page_table_lock);
> > mm->free_area_cache = TASK_UNMAPPED_BASE;
> > mm->cached_hole_size = ~0UL;
> >
> > --
> > To unsubscribe, send a message with 'unsubscribe linux-mm' in
> > the body to majordomo@...ck.org. For more info on Linux MM,
> > see: http://www.linux-mm.org/ .
> > Don't email: <a href=mailto:"dont@...ck.org"> email@...ck.org </a>
> >
>
> That's good.
> From now on, we can chagne scanning of pte to find swap pte
> in smaps_pte_rangem, too. :)
>
Thanks, I'll update this.
-Kame
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists