mm: zero reserved and unavailable struct pages

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).

One example of such memory: trim_low_memory_range() unconditionally
reserves from pfn 0, but e820__memblock_setup() might provide the
exiting memory from pfn 1 (i.e.  KVM).

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().

===

Here is more detailed example of problem that this patch is addressing:

Run tested on qemu with the following arguments:

	-enable-kvm -cpu kvm64 -m 512 -smp 2

This patch reports that there are 98 unavailable pages.

They are: pfn 0 and pfns in range [159, 255].

Note, trim_low_memory_range() reserves only pfns in range [0, 15], it does
not reserve [159, 255] ones.

e820__memblock_setup() reports linux that the following physical ranges are
available:
    [1 , 158]
[256, 130783]

Notice, that exactly unavailable pfns are missing!

Now, lets check what we have in zone 0: [1, 131039]

pfn 0, is not part of the zone, but pfns [1, 158], are.

However, the bigger problem we have if we do not initialize these struct
pages is with memory hotplug.  Because, that path operates at 2M
boundaries (section_nr).  And checks if 2M range of pages is hot
removable.  It starts with first pfn from zone, rounds it down to 2M
boundary (sturct pages are allocated at 2M boundaries when vmemmap is
created), and checks if that section is hot removable.  In this case
start with pfn 1 and convert it down to pfn 0.  Later pfn is converted
to struct page, and some fields are checked.  Now, if we do not zero
struct pages, we get unpredictable results.

In fact when CONFIG_VM_DEBUG is enabled, and we explicitly set all
vmemmap memory to ones, the following panic is observed with kernel test
without this patch applied:

  BUG: unable to handle kernel NULL pointer dereference at          (null)
  IP: is_pageblock_removable_nolock+0x35/0x90
  PGD 0 P4D 0
  Oops: 0000 [#1] PREEMPT
  ...
  task: ffff88001f4e2900 task.stack: ffffc90000314000
  RIP: 0010:is_pageblock_removable_nolock+0x35/0x90
  Call Trace:
   ? is_mem_section_removable+0x5a/0xd0
   show_mem_removable+0x6b/0xa0
   dev_attr_show+0x1b/0x50
   sysfs_kf_seq_show+0xa1/0x100
   kernfs_seq_show+0x22/0x30
   seq_read+0x1ac/0x3a0
   kernfs_fop_read+0x36/0x190
   ? security_file_permission+0x90/0xb0
   __vfs_read+0x16/0x30
   vfs_read+0x81/0x130
   SyS_read+0x44/0xa0
   entry_SYSCALL_64_fastpath+0x1f/0xbd

Link: http://lkml.kernel.org/r/20171013173214.27300-7-pasha.tatashin@oracle.com
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>
Tested-by: Bob Picco <bob.picco@oracle.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Sam Ravnborg <sam@ravnborg.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index ce0e5634c2f93ec314f6b3aaa38ab747595c9036..7ed0f7782d16729e95c72d80a3515d751ce7612f 100644 (file)
--- 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 unavailable 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 7c1e82a1aa7716ba0ad1adcce8f9060af7b9e713..703599fa828874c5acb9daecb72e89be4532621e 100644 (file)
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -95,6 +95,15 @@ extern int mmap_rnd_compat_bits __read_mostly;
 #define mm_forbids_zeropage(X) (0)
 #endif
 
+/*
+ * On some architectures it is expensive to call memset() for small sizes.
+ * Those architectures should provide their own implementation of "struct page"
+ * zeroing by defining this macro in <asm/pgtable.h>.
+ */
+#ifndef mm_zero_struct_page
+#define mm_zero_struct_page(pp)  ((void)memset((pp), 0, sizeof(struct page)))
+#endif
+
 /*
  * Default maximum number of active map areas, this limits the number of vmas
  * per mm struct. Users can overwrite this number by sysctl but there is a
@@ -2030,6 +2039,12 @@ 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 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 805f30dd1c26ef3755b485b5452c589c0e00493d..c37343ef2889e4e88ecec31c8c6b7dfb6738a129 100644 (file)
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -6215,6 +6215,44 @@ 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++;
+               }
+       }
+
+       /*
+        * Struct pages that do not have backing memory. This could be because
+        * firmware is using some of this memory, or for some other reasons.
+        * Once memblock is changed so such behaviour is not allowed: i.e.
+        * list of "reserved" memory must be a subset of list of "memory", then
+        * this code can be removed.
+        */
+       if (pgcnt)
+               pr_info("Reserved but unavailable: %lld pages", pgcnt);
+}
+#endif /* CONFIG_HAVE_MEMBLOCK */
+
 #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
 
 #if MAX_NUMNODES > 1
@@ -6638,6 +6676,7 @@ 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)
@@ -6801,6 +6840,7 @@ 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)