Hi Masaki-san,
what is the status of this patch? Do you have any concerns?
TIA,
Petr T
On Fri, 13 Apr 2018 18:29:59 +0200
Petr Tesarik <ptesarik@xxxxxxx> wrote:
> When page cache is filtered out (dump level bitmap includes 2 or 4),
> makedumpfile checks the PG_swapcache bit, but since kernel commit
> 6326fec1122cde256bd2a8c63f2606e08e44ce1d (v4.10-rc1~7) this bit is
> an alias for PG_owner_priv_1, which is also used by filesystem
> code (PG_checked) and Xen (PG_pinned and PG_foreign).
>
> With these kernels, the PG_swapcache flag is valid only if
> PG_swapbacked is set. A Linux kernel patch has already been
> submitted to export the value of PG_swapbacked in VMCOREINFO.
>
> Since there are released kernels in the wild which do not export the
> value, a fallback is implemented. I considered these three situations:
>
> 1. Kernels before v2.6.28-rc1~244:
> PG_swapbacked does not exist, so it must not be checked.
> Instead, check PG_swapcache, which is never overloaded for
> another purpose.
>
> 2. Kernels between v2.6.28-rc1~244 and v4.10-rc1~7:
> It is sufficient to check only PG_swapcache, but PG_swapbacked
> may also be checked (it is always set if PG_swapcache is set).
>
> 3. Kernels since v4.10-rc1~7:
> PG_swapbacked must be checked.
>
> If PG_swapbacked value is known (exported or read from debuginfo),
> it is always safe to use it (case 2 or 3). If PG_swapbacked is not
> known, it is safe to ignore it for cases 1 and 2, but not 3.
> Thankfully, the new value of PG_swapcache (since v4.10-rc1~7) is
> less than PG_private (which is known), whereas the old value had
> always been greater than PG_private. Moreover, the flags between
> PG_private and PG_swapbacked haven't changed since v4.10-rc1~7, so
> PG_swapbacked can fall back to PG_private + 6 if unknown.
>
> Without this patch, all Xen dumps are unusable, because PG_pinned is
> set for all page table pages.
>
> Signed-off-by: Petr Tesarik <ptesarik@xxxxxxxx>
> ---
> makedumpfile.c | 19 ++++++++++++++++++-
> makedumpfile.h | 2 ++
> 2 files changed, 20 insertions(+), 1 deletion(-)
>
> diff --git a/makedumpfile.c b/makedumpfile.c
> index 175ba68..ec04a88 100644
> --- a/makedumpfile.c
> +++ b/makedumpfile.c
> @@ -252,7 +252,18 @@ isHugetlb(unsigned long dtor)
> static int
> is_cache_page(unsigned long flags)
> {
> - return isLRU(flags) || isSwapCache(flags);
> + if (isLRU(flags))
> + return TRUE;
> +
> + /* PG_swapcache is valid only if:
> + * a. PG_swapbacked bit is set, or
> + * b. PG_swapbacked did not exist (kernels before 4.10-rc1).
> + */
> + if ((NUMBER(PG_swapbacked) == NOT_FOUND_NUMBER || isSwapBacked(flags))
> + && isSwapCache(flags))
> + return TRUE;
> +
> + return FALSE;
> }
>
> static inline unsigned long
> @@ -1735,6 +1746,7 @@ get_structure_info(void)
> ENUM_NUMBER_INIT(PG_lru, "PG_lru");
> ENUM_NUMBER_INIT(PG_private, "PG_private");
> ENUM_NUMBER_INIT(PG_swapcache, "PG_swapcache");
> + ENUM_NUMBER_INIT(PG_swapbacked, "PG_swapbacked");
> ENUM_NUMBER_INIT(PG_buddy, "PG_buddy");
> ENUM_NUMBER_INIT(PG_slab, "PG_slab");
> ENUM_NUMBER_INIT(PG_hwpoison, "PG_hwpoison");
> @@ -1988,6 +2000,9 @@ get_value_for_old_linux(void)
> NUMBER(PG_private) = PG_private_ORIGINAL;
> if (NUMBER(PG_swapcache) == NOT_FOUND_NUMBER)
> NUMBER(PG_swapcache) = PG_swapcache_ORIGINAL;
> + if (NUMBER(PG_swapbacked) == NOT_FOUND_NUMBER
> + && NUMBER(PG_swapcache) < NUMBER(PG_private))
> + NUMBER(PG_swapbacked) = NUMBER(PG_private) + 6;
> if (NUMBER(PG_slab) == NOT_FOUND_NUMBER)
> NUMBER(PG_slab) = PG_slab_ORIGINAL;
> if (NUMBER(PG_head_mask) == NOT_FOUND_NUMBER)
> @@ -2264,6 +2279,7 @@ write_vmcoreinfo_data(void)
> WRITE_NUMBER("PG_private", PG_private);
> WRITE_NUMBER("PG_head_mask", PG_head_mask);
> WRITE_NUMBER("PG_swapcache", PG_swapcache);
> + WRITE_NUMBER("PG_swapbacked", PG_swapbacked);
> WRITE_NUMBER("PG_buddy", PG_buddy);
> WRITE_NUMBER("PG_slab", PG_slab);
> WRITE_NUMBER("PG_hwpoison", PG_hwpoison);
> @@ -2658,6 +2674,7 @@ read_vmcoreinfo(void)
> READ_NUMBER("PG_private", PG_private);
> READ_NUMBER("PG_head_mask", PG_head_mask);
> READ_NUMBER("PG_swapcache", PG_swapcache);
> + READ_NUMBER("PG_swapbacked", PG_swapbacked);
> READ_NUMBER("PG_slab", PG_slab);
> READ_NUMBER("PG_buddy", PG_buddy);
> READ_NUMBER("PG_hwpoison", PG_hwpoison);
> diff --git a/makedumpfile.h b/makedumpfile.h
> index 6205ef3..fe306bb 100644
> --- a/makedumpfile.h
> +++ b/makedumpfile.h
> @@ -155,6 +155,7 @@ test_bit(int nr, unsigned long addr)
> #define isPrivate(flags) test_bit(NUMBER(PG_private), flags)
> #define isCompoundHead(flags) (!!((flags) & NUMBER(PG_head_mask)))
> #define isSwapCache(flags) test_bit(NUMBER(PG_swapcache), flags)
> +#define isSwapBacked(flags) test_bit(NUMBER(PG_swapbacked), flags)
> #define isHWPOISON(flags) (test_bit(NUMBER(PG_hwpoison), flags) \
> && (NUMBER(PG_hwpoison) != NOT_FOUND_NUMBER))
>
> @@ -1881,6 +1882,7 @@ struct number_table {
> long PG_head;
> long PG_head_mask;
> long PG_swapcache;
> + long PG_swapbacked;
> long PG_buddy;
> long PG_slab;
> long PG_hwpoison;
_______________________________________________
kexec mailing list
kexec@xxxxxxxxxxxxxxxxxxx
http://lists.infradead.org/mailman/listinfo/kexec
