| 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: <20140317093937.GB2210@quack.suse.cz>
Date: Mon, 17 Mar 2014 10:39:37 +0100
From: Jan Kara <jack@...e.cz>
To: John Stultz <john.stultz@...aro.org>
Cc: LKML <linux-kernel@...r.kernel.org>,
Andrew Morton <akpm@...ux-foundation.org>,
Android Kernel Team <kernel-team@...roid.com>,
Johannes Weiner <hannes@...xchg.org>,
Robert Love <rlove@...gle.com>, Mel Gorman <mel@....ul.ie>,
Hugh Dickins <hughd@...gle.com>, Dave Hansen <dave@...1.net>,
Rik van Riel <riel@...hat.com>,
Dmitry Adamushko <dmitry.adamushko@...il.com>,
Neil Brown <neilb@...e.de>,
Andrea Arcangeli <aarcange@...hat.com>,
Mike Hommey <mh@...ndium.org>, Taras Glek <tglek@...illa.com>,
Dhaval Giani <dgiani@...illa.com>, Jan Kara <jack@...e.cz>,
KOSAKI Motohiro <kosaki.motohiro@...il.com>,
Michel Lespinasse <walken@...gle.com>,
Minchan Kim <minchan@...nel.org>,
"linux-mm@...ck.org" <linux-mm@...ck.org>
Subject: Re: [PATCH 2/3] vrange: Add purged page detection on setting memory
non-volatile
On Fri 14-03-14 11:33:32, John Stultz wrote:
> Users of volatile ranges will need to know if memory was discarded.
> This patch adds the purged state tracking required to inform userland
> when it marks memory as non-volatile that some memory in that range
> was purged and needs to be regenerated.
>
> This simplified implementation which uses some of the logic from
> Minchan's earlier efforts, so credit to Minchan for his work.
Some minor comments below...
>
> Cc: Andrew Morton <akpm@...ux-foundation.org>
> Cc: Android Kernel Team <kernel-team@...roid.com>
> Cc: Johannes Weiner <hannes@...xchg.org>
> Cc: Robert Love <rlove@...gle.com>
> Cc: Mel Gorman <mel@....ul.ie>
> Cc: Hugh Dickins <hughd@...gle.com>
> Cc: Dave Hansen <dave@...1.net>
> Cc: Rik van Riel <riel@...hat.com>
> Cc: Dmitry Adamushko <dmitry.adamushko@...il.com>
> Cc: Neil Brown <neilb@...e.de>
> Cc: Andrea Arcangeli <aarcange@...hat.com>
> Cc: Mike Hommey <mh@...ndium.org>
> Cc: Taras Glek <tglek@...illa.com>
> Cc: Dhaval Giani <dgiani@...illa.com>
> Cc: Jan Kara <jack@...e.cz>
> Cc: KOSAKI Motohiro <kosaki.motohiro@...il.com>
> Cc: Michel Lespinasse <walken@...gle.com>
> Cc: Minchan Kim <minchan@...nel.org>
> Cc: linux-mm@...ck.org <linux-mm@...ck.org>
> Signed-off-by: John Stultz <john.stultz@...aro.org>
> ---
> include/linux/swap.h | 15 +++++++++++--
> include/linux/vrange.h | 13 ++++++++++++
> mm/vrange.c | 57 ++++++++++++++++++++++++++++++++++++++++++++++++++
> 3 files changed, 83 insertions(+), 2 deletions(-)
>
> diff --git a/include/linux/swap.h b/include/linux/swap.h
> index 46ba0c6..18c12f9 100644
> --- a/include/linux/swap.h
> +++ b/include/linux/swap.h
> @@ -70,8 +70,19 @@ static inline int current_is_kswapd(void)
> #define SWP_HWPOISON_NUM 0
> #endif
>
> -#define MAX_SWAPFILES \
> - ((1 << MAX_SWAPFILES_SHIFT) - SWP_MIGRATION_NUM - SWP_HWPOISON_NUM)
> +
> +/*
> + * Purged volatile range pages
> + */
> +#define SWP_VRANGE_PURGED_NUM 1
> +#define SWP_VRANGE_PURGED (MAX_SWAPFILES + SWP_HWPOISON_NUM + SWP_MIGRATION_NUM)
> +
> +
> +#define MAX_SWAPFILES ((1 << MAX_SWAPFILES_SHIFT) \
> + - SWP_MIGRATION_NUM \
> + - SWP_HWPOISON_NUM \
> + - SWP_VRANGE_PURGED_NUM \
> + )
>
> /*
> * Magic header for a swap area. The first part of the union is
> diff --git a/include/linux/vrange.h b/include/linux/vrange.h
> index 652396b..c4a1616 100644
> --- a/include/linux/vrange.h
> +++ b/include/linux/vrange.h
> @@ -1,7 +1,20 @@
> #ifndef _LINUX_VRANGE_H
> #define _LINUX_VRANGE_H
>
> +#include <linux/swap.h>
> +#include <linux/swapops.h>
> +
> #define VRANGE_NONVOLATILE 0
> #define VRANGE_VOLATILE 1
>
> +static inline swp_entry_t swp_entry_mk_vrange_purged(void)
> +{
> + return swp_entry(SWP_VRANGE_PURGED, 0);
> +}
> +
> +static inline int entry_is_vrange_purged(swp_entry_t entry)
> +{
> + return swp_type(entry) == SWP_VRANGE_PURGED;
> +}
> +
> #endif /* _LINUX_VRANGE_H */
> diff --git a/mm/vrange.c b/mm/vrange.c
> index acb4356..844571b 100644
> --- a/mm/vrange.c
> +++ b/mm/vrange.c
> @@ -8,6 +8,60 @@
> #include <linux/mm_inline.h>
> #include "internal.h"
>
> +struct vrange_walker {
> + struct vm_area_struct *vma;
> + int pages_purged;
Maybe call this 'was_page_purged'? To better suggest the value is bool
and not a number of pages... Or make that 'bool' instead of 'int'?
> +};
> +
> +static int vrange_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
> + struct mm_walk *walk)
> +{
> + struct vrange_walker *vw = walk->private;
> + pte_t *pte;
> + spinlock_t *ptl;
> +
> + if (pmd_trans_huge(*pmd))
> + return 0;
> + if (pmd_trans_unstable(pmd))
> + return 0;
> +
> + pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
> + for (; addr != end; pte++, addr += PAGE_SIZE) {
> + if (!pte_present(*pte)) {
> + swp_entry_t vrange_entry = pte_to_swp_entry(*pte);
> +
> + if (unlikely(entry_is_vrange_purged(vrange_entry))) {
> + vw->pages_purged = 1;
> + break;
> + }
> + }
> + }
> + pte_unmap_unlock(pte - 1, ptl);
> + cond_resched();
> +
> + return 0;
> +}
> +
> +static unsigned long vrange_check_purged(struct mm_struct *mm,
What's the point of this function returning ulong when everything else
expects 'int'?
> + struct vm_area_struct *vma,
> + unsigned long start,
> + unsigned long end)
> +{
> + struct vrange_walker vw;
> + struct mm_walk vrange_walk = {
> + .pmd_entry = vrange_pte_range,
> + .mm = vma->vm_mm,
> + .private = &vw,
> + };
> + vw.pages_purged = 0;
> + vw.vma = vma;
> +
> + walk_page_range(start, end, &vrange_walk);
> +
> + return vw.pages_purged;
> +
> +}
> +
> static ssize_t do_vrange(struct mm_struct *mm, unsigned long start,
> unsigned long end, int mode, int *purged)
> {
> @@ -57,6 +111,9 @@ static ssize_t do_vrange(struct mm_struct *mm, unsigned long start,
> break;
> case VRANGE_NONVOLATILE:
> new_flags &= ~VM_VOLATILE;
> + lpurged |= vrange_check_purged(mm, vma,
> + vma->vm_start,
> + vma->vm_end);
Hum, why don't you actually just call vrange_check_purge() once for the
whole syscall range? walk_page_range() seems to handle multiple vmas just
fine...
> }
>
> pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
> --
> 1.8.3.2
>
Honza
--
Jan Kara <jack@...e.cz>
SUSE Labs, CR
--
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