diff mbox series

[v2] makedumpfile: exclude pages that are logically offline

Message ID 20181122100938.5567-1-david@redhat.com (mailing list archive)
State Not Applicable, archived
Headers show
Series [v2] makedumpfile: exclude pages that are logically offline | expand

Commit Message

David Hildenbrand Nov. 22, 2018, 10:09 a.m. UTC
Linux marks pages that are logically offline via a page flag (map count).
Such pages e.g. include pages infated as part of a balloon driver or
pages that were not actually onlined when onlining the whole section.

While the hypervisor usually allows to read such inflated memory, we
basically read and dump data that is completely irrelevant. Also, this
might result in quite some overhead in the hypervisor. In addition,
we saw some problems under Hyper-V, whereby we can crash the kernel by
dumping, when reading memory of a partially onlined memory segment
(for memory added by the Hyper-V balloon driver).

Therefore, don't read and dump pages that are marked as being logically
offline.

Signed-off-by: David Hildenbrand <david@redhat.com>
---

v1 -> v2:
- Fix PAGE_BUDDY_MAPCOUNT_VALUE vs. PAGE_OFFLINE_MAPCOUNT_VALUE

 makedumpfile.c | 34 ++++++++++++++++++++++++++++++----
 makedumpfile.h |  1 +
 2 files changed, 31 insertions(+), 4 deletions(-)

Comments

Kazuhito Hagio Nov. 27, 2018, 4:32 p.m. UTC | #1
> Linux marks pages that are logically offline via a page flag (map count).
> Such pages e.g. include pages infated as part of a balloon driver or
> pages that were not actually onlined when onlining the whole section.
> 
> While the hypervisor usually allows to read such inflated memory, we
> basically read and dump data that is completely irrelevant. Also, this
> might result in quite some overhead in the hypervisor. In addition,
> we saw some problems under Hyper-V, whereby we can crash the kernel by
> dumping, when reading memory of a partially onlined memory segment
> (for memory added by the Hyper-V balloon driver).
> 
> Therefore, don't read and dump pages that are marked as being logically
> offline.
> 
> Signed-off-by: David Hildenbrand <david@redhat.com>

Thanks for the v2 update.
I'm going to merge this patch after the kernel patches are merged
and it tests fine with the kernel.

Kazu

> ---
> 
> v1 -> v2:
> - Fix PAGE_BUDDY_MAPCOUNT_VALUE vs. PAGE_OFFLINE_MAPCOUNT_VALUE
> 
>  makedumpfile.c | 34 ++++++++++++++++++++++++++++++----
>  makedumpfile.h |  1 +
>  2 files changed, 31 insertions(+), 4 deletions(-)
> 
> diff --git a/makedumpfile.c b/makedumpfile.c
> index 8923538..a5f2ea9 100644
> --- a/makedumpfile.c
> +++ b/makedumpfile.c
> @@ -88,6 +88,7 @@ mdf_pfn_t pfn_cache_private;
>  mdf_pfn_t pfn_user;
>  mdf_pfn_t pfn_free;
>  mdf_pfn_t pfn_hwpoison;
> +mdf_pfn_t pfn_offline;
> 
>  mdf_pfn_t num_dumped;
> 
> @@ -249,6 +250,21 @@ isHugetlb(unsigned long dtor)
>                      && (SYMBOL(free_huge_page) == dtor));
>  }
> 
> +static int
> +isOffline(unsigned long flags, unsigned int _mapcount)
> +{
> +	if (NUMBER(PAGE_OFFLINE_MAPCOUNT_VALUE) == NOT_FOUND_NUMBER)
> +		return FALSE;
> +
> +	if (flags & (1UL << NUMBER(PG_slab)))
> +		return FALSE;
> +
> +	if (_mapcount == (int)NUMBER(PAGE_OFFLINE_MAPCOUNT_VALUE))
> +		return TRUE;
> +
> +	return FALSE;
> +}
> +
>  static int
>  is_cache_page(unsigned long flags)
>  {
> @@ -2287,6 +2303,8 @@ write_vmcoreinfo_data(void)
>  	WRITE_NUMBER("PG_hwpoison", PG_hwpoison);
> 
>  	WRITE_NUMBER("PAGE_BUDDY_MAPCOUNT_VALUE", PAGE_BUDDY_MAPCOUNT_VALUE);
> +	WRITE_NUMBER("PAGE_OFFLINE_MAPCOUNT_VALUE",
> +		     PAGE_OFFLINE_MAPCOUNT_VALUE);
>  	WRITE_NUMBER("phys_base", phys_base);
> 
>  	WRITE_NUMBER("HUGETLB_PAGE_DTOR", HUGETLB_PAGE_DTOR);
> @@ -2687,6 +2705,7 @@ read_vmcoreinfo(void)
>  	READ_SRCFILE("pud_t", pud_t);
> 
>  	READ_NUMBER("PAGE_BUDDY_MAPCOUNT_VALUE", PAGE_BUDDY_MAPCOUNT_VALUE);
> +	READ_NUMBER("PAGE_OFFLINE_MAPCOUNT_VALUE", PAGE_OFFLINE_MAPCOUNT_VALUE);
>  	READ_NUMBER("phys_base", phys_base);
>  #ifdef __aarch64__
>  	READ_NUMBER("VA_BITS", VA_BITS);
> @@ -6041,6 +6060,12 @@ __exclude_unnecessary_pages(unsigned long mem_map,
>  		else if (isHWPOISON(flags)) {
>  			pfn_counter = &pfn_hwpoison;
>  		}
> +		/*
> +		 * Exclude pages that are logically offline.
> +		 */
> +		else if (isOffline(flags, _mapcount)) {
> +			pfn_counter = &pfn_offline;
> +		}
>  		/*
>  		 * Unexcludable page
>  		 */
> @@ -7522,7 +7547,7 @@ write_elf_pages_cyclic(struct cache_data *cd_header, struct cache_data *cd_page)
>  	 */
>  	if (info->flag_cyclic) {
>  		pfn_zero = pfn_cache = pfn_cache_private = 0;
> -		pfn_user = pfn_free = pfn_hwpoison = 0;
> +		pfn_user = pfn_free = pfn_hwpoison = pfn_offline = 0;
>  		pfn_memhole = info->max_mapnr;
>  	}
> 
> @@ -8804,7 +8829,7 @@ write_kdump_pages_and_bitmap_cyclic(struct cache_data *cd_header, struct cache_d
>  		 * Reset counter for debug message.
>  		 */
>  		pfn_zero = pfn_cache = pfn_cache_private = 0;
> -		pfn_user = pfn_free = pfn_hwpoison = 0;
> +		pfn_user = pfn_free = pfn_hwpoison = pfn_offline = 0;
>  		pfn_memhole = info->max_mapnr;
> 
>  		/*
> @@ -9749,7 +9774,7 @@ print_report(void)
>  	pfn_original = info->max_mapnr - pfn_memhole;
> 
>  	pfn_excluded = pfn_zero + pfn_cache + pfn_cache_private
> -	    + pfn_user + pfn_free + pfn_hwpoison;
> +	    + pfn_user + pfn_free + pfn_hwpoison + pfn_offline;
>  	shrinking = (pfn_original - pfn_excluded) * 100;
>  	shrinking = shrinking / pfn_original;
> 
> @@ -9763,6 +9788,7 @@ print_report(void)
>  	REPORT_MSG("    User process data pages : 0x%016llx\n", pfn_user);
>  	REPORT_MSG("    Free pages              : 0x%016llx\n", pfn_free);
>  	REPORT_MSG("    Hwpoison pages          : 0x%016llx\n", pfn_hwpoison);
> +	REPORT_MSG("    Offline pages           : 0x%016llx\n", pfn_offline);
>  	REPORT_MSG("  Remaining pages  : 0x%016llx\n",
>  	    pfn_original - pfn_excluded);
>  	REPORT_MSG("  (The number of pages is reduced to %lld%%.)\n",
> @@ -9790,7 +9816,7 @@ print_mem_usage(void)
>  	pfn_original = info->max_mapnr - pfn_memhole;
> 
>  	pfn_excluded = pfn_zero + pfn_cache + pfn_cache_private
> -	    + pfn_user + pfn_free + pfn_hwpoison;
> +	    + pfn_user + pfn_free + pfn_hwpoison + pfn_offline;
>  	shrinking = (pfn_original - pfn_excluded) * 100;
>  	shrinking = shrinking / pfn_original;
>  	total_size = info->page_size * pfn_original;
> diff --git a/makedumpfile.h b/makedumpfile.h
> index f02f86d..e3a2b29 100644
> --- a/makedumpfile.h
> +++ b/makedumpfile.h
> @@ -1927,6 +1927,7 @@ struct number_table {
>  	long    PG_hwpoison;
> 
>  	long	PAGE_BUDDY_MAPCOUNT_VALUE;
> +	long	PAGE_OFFLINE_MAPCOUNT_VALUE;
>  	long	SECTION_SIZE_BITS;
>  	long	MAX_PHYSMEM_BITS;
>  	long    HUGETLB_PAGE_DTOR;
> --
> 2.17.2
>
David Hildenbrand March 7, 2019, 8:41 a.m. UTC | #2
On 27.11.18 17:32, Kazuhito Hagio wrote:
>> Linux marks pages that are logically offline via a page flag (map count).
>> Such pages e.g. include pages infated as part of a balloon driver or
>> pages that were not actually onlined when onlining the whole section.
>>
>> While the hypervisor usually allows to read such inflated memory, we
>> basically read and dump data that is completely irrelevant. Also, this
>> might result in quite some overhead in the hypervisor. In addition,
>> we saw some problems under Hyper-V, whereby we can crash the kernel by
>> dumping, when reading memory of a partially onlined memory segment
>> (for memory added by the Hyper-V balloon driver).
>>
>> Therefore, don't read and dump pages that are marked as being logically
>> offline.
>>
>> Signed-off-by: David Hildenbrand <david@redhat.com>
> 
> Thanks for the v2 update.
> I'm going to merge this patch after the kernel patches are merged
> and it tests fine with the kernel.
> 
> Kazu

Hi Kazu,

the patches are now upstream. Thanks!
Kazuhito Hagio March 11, 2019, 4:40 p.m. UTC | #3
-----Original Message-----
> On 27.11.18 17:32, Kazuhito Hagio wrote:
> >> Linux marks pages that are logically offline via a page flag (map count).
> >> Such pages e.g. include pages infated as part of a balloon driver or
> >> pages that were not actually onlined when onlining the whole section.
> >>
> >> While the hypervisor usually allows to read such inflated memory, we
> >> basically read and dump data that is completely irrelevant. Also, this
> >> might result in quite some overhead in the hypervisor. In addition,
> >> we saw some problems under Hyper-V, whereby we can crash the kernel by
> >> dumping, when reading memory of a partially onlined memory segment
> >> (for memory added by the Hyper-V balloon driver).
> >>
> >> Therefore, don't read and dump pages that are marked as being logically
> >> offline.
> >>
> >> Signed-off-by: David Hildenbrand <david@redhat.com>
> >
> > Thanks for the v2 update.
> > I'm going to merge this patch after the kernel patches are merged
> > and it tests fine with the kernel.
> >
> > Kazu
> 
> Hi Kazu,
> 
> the patches are now upstream. Thanks!

Tested OK at my end, too. Applied to the devel branch.

    Offline pages           : 0x0000000000002400

Thank you!
Kazu

> 
> --
> 
> Thanks,
> 
> David / dhildenb
diff mbox series

Patch

diff --git a/makedumpfile.c b/makedumpfile.c
index 8923538..a5f2ea9 100644
--- a/makedumpfile.c
+++ b/makedumpfile.c
@@ -88,6 +88,7 @@  mdf_pfn_t pfn_cache_private;
 mdf_pfn_t pfn_user;
 mdf_pfn_t pfn_free;
 mdf_pfn_t pfn_hwpoison;
+mdf_pfn_t pfn_offline;
 
 mdf_pfn_t num_dumped;
 
@@ -249,6 +250,21 @@  isHugetlb(unsigned long dtor)
                     && (SYMBOL(free_huge_page) == dtor));
 }
 
+static int
+isOffline(unsigned long flags, unsigned int _mapcount)
+{
+	if (NUMBER(PAGE_OFFLINE_MAPCOUNT_VALUE) == NOT_FOUND_NUMBER)
+		return FALSE;
+
+	if (flags & (1UL << NUMBER(PG_slab)))
+		return FALSE;
+
+	if (_mapcount == (int)NUMBER(PAGE_OFFLINE_MAPCOUNT_VALUE))
+		return TRUE;
+
+	return FALSE;
+}
+
 static int
 is_cache_page(unsigned long flags)
 {
@@ -2287,6 +2303,8 @@  write_vmcoreinfo_data(void)
 	WRITE_NUMBER("PG_hwpoison", PG_hwpoison);
 
 	WRITE_NUMBER("PAGE_BUDDY_MAPCOUNT_VALUE", PAGE_BUDDY_MAPCOUNT_VALUE);
+	WRITE_NUMBER("PAGE_OFFLINE_MAPCOUNT_VALUE",
+		     PAGE_OFFLINE_MAPCOUNT_VALUE);
 	WRITE_NUMBER("phys_base", phys_base);
 
 	WRITE_NUMBER("HUGETLB_PAGE_DTOR", HUGETLB_PAGE_DTOR);
@@ -2687,6 +2705,7 @@  read_vmcoreinfo(void)
 	READ_SRCFILE("pud_t", pud_t);
 
 	READ_NUMBER("PAGE_BUDDY_MAPCOUNT_VALUE", PAGE_BUDDY_MAPCOUNT_VALUE);
+	READ_NUMBER("PAGE_OFFLINE_MAPCOUNT_VALUE", PAGE_OFFLINE_MAPCOUNT_VALUE);
 	READ_NUMBER("phys_base", phys_base);
 #ifdef __aarch64__
 	READ_NUMBER("VA_BITS", VA_BITS);
@@ -6041,6 +6060,12 @@  __exclude_unnecessary_pages(unsigned long mem_map,
 		else if (isHWPOISON(flags)) {
 			pfn_counter = &pfn_hwpoison;
 		}
+		/*
+		 * Exclude pages that are logically offline.
+		 */
+		else if (isOffline(flags, _mapcount)) {
+			pfn_counter = &pfn_offline;
+		}
 		/*
 		 * Unexcludable page
 		 */
@@ -7522,7 +7547,7 @@  write_elf_pages_cyclic(struct cache_data *cd_header, struct cache_data *cd_page)
 	 */
 	if (info->flag_cyclic) {
 		pfn_zero = pfn_cache = pfn_cache_private = 0;
-		pfn_user = pfn_free = pfn_hwpoison = 0;
+		pfn_user = pfn_free = pfn_hwpoison = pfn_offline = 0;
 		pfn_memhole = info->max_mapnr;
 	}
 
@@ -8804,7 +8829,7 @@  write_kdump_pages_and_bitmap_cyclic(struct cache_data *cd_header, struct cache_d
 		 * Reset counter for debug message.
 		 */
 		pfn_zero = pfn_cache = pfn_cache_private = 0;
-		pfn_user = pfn_free = pfn_hwpoison = 0;
+		pfn_user = pfn_free = pfn_hwpoison = pfn_offline = 0;
 		pfn_memhole = info->max_mapnr;
 
 		/*
@@ -9749,7 +9774,7 @@  print_report(void)
 	pfn_original = info->max_mapnr - pfn_memhole;
 
 	pfn_excluded = pfn_zero + pfn_cache + pfn_cache_private
-	    + pfn_user + pfn_free + pfn_hwpoison;
+	    + pfn_user + pfn_free + pfn_hwpoison + pfn_offline;
 	shrinking = (pfn_original - pfn_excluded) * 100;
 	shrinking = shrinking / pfn_original;
 
@@ -9763,6 +9788,7 @@  print_report(void)
 	REPORT_MSG("    User process data pages : 0x%016llx\n", pfn_user);
 	REPORT_MSG("    Free pages              : 0x%016llx\n", pfn_free);
 	REPORT_MSG("    Hwpoison pages          : 0x%016llx\n", pfn_hwpoison);
+	REPORT_MSG("    Offline pages           : 0x%016llx\n", pfn_offline);
 	REPORT_MSG("  Remaining pages  : 0x%016llx\n",
 	    pfn_original - pfn_excluded);
 	REPORT_MSG("  (The number of pages is reduced to %lld%%.)\n",
@@ -9790,7 +9816,7 @@  print_mem_usage(void)
 	pfn_original = info->max_mapnr - pfn_memhole;
 
 	pfn_excluded = pfn_zero + pfn_cache + pfn_cache_private
-	    + pfn_user + pfn_free + pfn_hwpoison;
+	    + pfn_user + pfn_free + pfn_hwpoison + pfn_offline;
 	shrinking = (pfn_original - pfn_excluded) * 100;
 	shrinking = shrinking / pfn_original;
 	total_size = info->page_size * pfn_original;
diff --git a/makedumpfile.h b/makedumpfile.h
index f02f86d..e3a2b29 100644
--- a/makedumpfile.h
+++ b/makedumpfile.h
@@ -1927,6 +1927,7 @@  struct number_table {
 	long    PG_hwpoison;
 
 	long	PAGE_BUDDY_MAPCOUNT_VALUE;
+	long	PAGE_OFFLINE_MAPCOUNT_VALUE;
 	long	SECTION_SIZE_BITS;
 	long	MAX_PHYSMEM_BITS;
 	long    HUGETLB_PAGE_DTOR;