diff mbox

[v7,08/11] mm: zero reserved and unavailable struct pages

Message ID 1503972142-289376-9-git-send-email-pasha.tatashin@oracle.com (mailing list archive)
State New, archived
Headers show

Commit Message

Pavel Tatashin Aug. 29, 2017, 2:02 a.m. UTC
Some memory is reserved but unavailable: not present in memblock.memory
(because not backed by physical pages), but present in memblock.reserved.
Such memory has backing struct pages, but they are not initialized by going
through __init_single_page().

In some cases these struct pages are accessed even if they do not contain
any data. One example is page_to_pfn() might access page->flags if this is
where section information is stored (CONFIG_SPARSEMEM,
SECTION_IN_PAGE_FLAGS).

Since, struct pages are zeroed in __init_single_page(), and not during
allocation time, we must zero such struct pages explicitly.

The patch involves adding a new memblock iterator:
	for_each_resv_unavail_range(i, p_start, p_end)

Which iterates through reserved && !memory lists, and we zero struct pages
explicitly by calling mm_zero_struct_page().

Signed-off-by: Pavel Tatashin <pasha.tatashin@oracle.com>
Reviewed-by: Steven Sistare <steven.sistare@oracle.com>
Reviewed-by: Daniel Jordan <daniel.m.jordan@oracle.com>
Reviewed-by: Bob Picco <bob.picco@oracle.com>
---
 include/linux/memblock.h | 16 ++++++++++++++++
 include/linux/mm.h       |  6 ++++++
 mm/page_alloc.c          | 30 ++++++++++++++++++++++++++++++
 3 files changed, 52 insertions(+)

Comments

kernel test robot Aug. 30, 2017, 9:22 p.m. UTC | #1
Hi Pavel,

[auto build test ERROR on sparc/master]
[also build test ERROR on v4.13-rc7 next-20170829]
[cannot apply to mmotm/master]
[if your patch is applied to the wrong git tree, please drop us a note to help improve the system]

url:    https://github.com/0day-ci/linux/commits/Pavel-Tatashin/complete-deferred-page-initialization/20170831-041021
base:   https://git.kernel.org/pub/scm/linux/kernel/git/davem/sparc.git master
config: tile-allmodconfig (attached as .config)
compiler: tilegx-linux-gcc (GCC) 4.6.2
reproduce:
        wget https://raw.githubusercontent.com/01org/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
        chmod +x ~/bin/make.cross
        # save the attached .config to linux build tree
        make.cross ARCH=tile 

All errors (new ones prefixed by >>):

   In file included from include/linux/pid_namespace.h:6:0,
                    from include/linux/ptrace.h:9,
                    from arch/tile/kernel/asm-offsets.c:35:
>> include/linux/mm.h:1974:33: error: expected '=', ',', ';', 'asm' or '__attribute__' before 'zero_resv_unavail'
   make[2]: *** [arch/tile/kernel/asm-offsets.s] Error 1
   make[2]: Target '__build' not remade because of errors.
   make[1]: *** [prepare0] Error 2
   make[1]: Target 'prepare' not remade because of errors.
   make: *** [sub-make] Error 2

vim +1974 include/linux/mm.h

  1970	
  1971	#ifdef CONFIG_HAVE_MEMBLOCK
  1972	void zero_resv_unavail(void);
  1973	#else
> 1974	static inline void __paginginit zero_resv_unavail(void) {}
  1975	#endif
  1976	

---
0-DAY kernel test infrastructure                Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all                   Intel Corporation
kernel test robot Aug. 30, 2017, 11:12 p.m. UTC | #2
Hi Pavel,

[auto build test ERROR on sparc/master]
[also build test ERROR on v4.13-rc7 next-20170829]
[cannot apply to mmotm/master]
[if your patch is applied to the wrong git tree, please drop us a note to help improve the system]

url:    https://github.com/0day-ci/linux/commits/Pavel-Tatashin/complete-deferred-page-initialization/20170831-041021
base:   https://git.kernel.org/pub/scm/linux/kernel/git/davem/sparc.git master
config: cris-allmodconfig (attached as .config)
compiler: cris-linux-gcc (GCC) 6.2.0
reproduce:
        wget https://raw.githubusercontent.com/01org/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
        chmod +x ~/bin/make.cross
        # save the attached .config to linux build tree
        make.cross ARCH=cris 

All errors (new ones prefixed by >>):

   In file included from mm/page_alloc.c:18:0:
   include/linux/mm.h:1974:33: error: expected '=', ',', ';', 'asm' or '__attribute__' before 'zero_resv_unavail'
    static inline void __paginginit zero_resv_unavail(void) {}
                                    ^~~~~~~~~~~~~~~~~
   mm/page_alloc.c: In function 'free_area_init':
>> mm/page_alloc.c:6863:2: error: implicit declaration of function 'zero_resv_unavail' [-Werror=implicit-function-declaration]
     zero_resv_unavail();
     ^~~~~~~~~~~~~~~~~
   cc1: some warnings being treated as errors

vim +/zero_resv_unavail +6863 mm/page_alloc.c

  6858	
  6859	void __init free_area_init(unsigned long *zones_size)
  6860	{
  6861		free_area_init_node(0, zones_size,
  6862				__pa(PAGE_OFFSET) >> PAGE_SHIFT, NULL);
> 6863		zero_resv_unavail();
  6864	}
  6865	

---
0-DAY kernel test infrastructure                Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all                   Intel Corporation
diff mbox

Patch

diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index bae11c7e7bf3..bdd4268f9323 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -237,6 +237,22 @@  unsigned long memblock_next_valid_pfn(unsigned long pfn, unsigned long max_pfn);
 	for_each_mem_range_rev(i, &memblock.memory, &memblock.reserved,	\
 			       nid, flags, p_start, p_end, p_nid)
 
+/**
+ * for_each_resv_unavail_range - iterate through reserved and unavailable memory
+ * @i: u64 used as loop variable
+ * @flags: pick from blocks based on memory attributes
+ * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL
+ * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL
+ *
+ * Walks over unavailabled but reserved (reserved && !memory) areas of memblock.
+ * Available as soon as memblock is initialized.
+ * Note: because this memory does not belong to any physical node, flags and
+ * nid arguments do not make sense and thus not exported as arguments.
+ */
+#define for_each_resv_unavail_range(i, p_start, p_end)			\
+	for_each_mem_range(i, &memblock.reserved, &memblock.memory,	\
+			   NUMA_NO_NODE, MEMBLOCK_NONE, p_start, p_end, NULL)
+
 static inline void memblock_set_region_flags(struct memblock_region *r,
 					     unsigned long flags)
 {
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 183ac5e733db..0a440ff8f226 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1968,6 +1968,12 @@  extern int __meminit __early_pfn_to_nid(unsigned long pfn,
 					struct mminit_pfnnid_cache *state);
 #endif
 
+#ifdef CONFIG_HAVE_MEMBLOCK
+void zero_resv_unavail(void);
+#else
+static inline void __paginginit zero_resv_unavail(void) {}
+#endif
+
 extern void set_dma_reserve(unsigned long new_dma_reserve);
 extern void memmap_init_zone(unsigned long, int, unsigned long,
 				unsigned long, enum memmap_context);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 4d67fe3dd172..484c16fb5f0d 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -6261,6 +6261,34 @@  void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
 	free_area_init_core(pgdat);
 }
 
+#ifdef CONFIG_HAVE_MEMBLOCK
+/*
+ * Only struct pages that are backed by physical memory are zeroed and
+ * initialized by going through __init_single_page(). But, there are some
+ * struct pages which are reserved in memblock allocator and their fields
+ * may be accessed (for example page_to_pfn() on some configuration accesses
+ * flags). We must explicitly zero those struct pages.
+ */
+void __paginginit zero_resv_unavail(void)
+{
+	phys_addr_t start, end;
+	unsigned long pfn;
+	u64 i, pgcnt;
+
+	/* Loop through ranges that are reserved, but do not have reported
+	 * physical memory backing.
+	 */
+	pgcnt = 0;
+	for_each_resv_unavail_range(i, &start, &end) {
+		for (pfn = PFN_DOWN(start); pfn < PFN_UP(end); pfn++) {
+			mm_zero_struct_page(pfn_to_page(pfn));
+			pgcnt++;
+		}
+	}
+	pr_info("Reserved but unavailable: %lld pages", pgcnt);
+}
+#endif /* CONFIG_HAVE_MEMBLOCK */
+
 #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
 
 #if MAX_NUMNODES > 1
@@ -6684,6 +6712,7 @@  void __init free_area_init_nodes(unsigned long *max_zone_pfn)
 			node_set_state(nid, N_MEMORY);
 		check_for_memory(pgdat, nid);
 	}
+	zero_resv_unavail();
 }
 
 static int __init cmdline_parse_core(char *p, unsigned long *core)
@@ -6847,6 +6876,7 @@  void __init free_area_init(unsigned long *zones_size)
 {
 	free_area_init_node(0, zones_size,
 			__pa(PAGE_OFFSET) >> PAGE_SHIFT, NULL);
+	zero_resv_unavail();
 }
 
 static int page_alloc_cpu_dead(unsigned int cpu)