summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorPetr Tesarik <ptesarik@suse.com>2018-01-31 16:20:26 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2018-01-31 17:18:39 -0800
commitdef9b71ee651a6fee93a10734b94f93a69cdb2d4 (patch)
treefacc9a7783035460106f12e2fc845e5d8225b6c5
parent112d2d29fc087d3078f60db220c4f31f25e59cf0 (diff)
include/linux/mmzone.h: fix explanation of lower bits in the SPARSEMEM mem_map pointer
The comment is confusing. On the one hand, it refers to 32-bit alignment (struct page alignment on 32-bit platforms), but this would only guarantee that the 2 lowest bits must be zero. On the other hand, it claims that at least 3 bits are available, and 3 bits are actually used. This is not broken, because there is a stronger alignment guarantee, just less obvious. Let's fix the comment to make it clear how many bits are available and why. Although memmap arrays are allocated in various places, the resulting pointer is encoded eventually, so I am adding a BUG_ON() here to enforce at runtime that all expected bits are indeed available. I have also added a BUILD_BUG_ON to check that PFN_SECTION_SHIFT is sufficient, because this part of the calculation can be easily checked at build time. [ptesarik@suse.com: v2] Link: http://lkml.kernel.org/r/20180125100516.589ea6af@ezekiel.suse.cz Link: http://lkml.kernel.org/r/20180119080908.3a662e6f@ezekiel.suse.cz Signed-off-by: Petr Tesarik <ptesarik@suse.com> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kemi Wang <kemi.wang@intel.com> Cc: YASUAKI ISHIMATSU <yasu.isimatu@gmail.com> Cc: Andrey Ryabinin <aryabinin@virtuozzo.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-rw-r--r--include/linux/mmzone.h12
-rw-r--r--mm/sparse.c6
2 files changed, 15 insertions, 3 deletions
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 67f2e3c38939..7522a6987595 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -1166,8 +1166,16 @@ extern unsigned long usemap_size(void);
/*
* We use the lower bits of the mem_map pointer to store
- * a little bit of information. There should be at least
- * 3 bits here due to 32-bit alignment.
+ * a little bit of information. The pointer is calculated
+ * as mem_map - section_nr_to_pfn(pnum). The result is
+ * aligned to the minimum alignment of the two values:
+ * 1. All mem_map arrays are page-aligned.
+ * 2. section_nr_to_pfn() always clears PFN_SECTION_SHIFT
+ * lowest bits. PFN_SECTION_SHIFT is arch-specific
+ * (equal SECTION_SIZE_BITS - PAGE_SHIFT), and the
+ * worst combination is powerpc with 256k pages,
+ * which results in PFN_SECTION_SHIFT equal 6.
+ * To sum it up, at least 6 bits are available.
*/
#define SECTION_MARKED_PRESENT (1UL<<0)
#define SECTION_HAS_MEM_MAP (1UL<<1)
diff --git a/mm/sparse.c b/mm/sparse.c
index 2609aba121e8..6b8b5e91ceef 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -264,7 +264,11 @@ unsigned long __init node_memmap_size_bytes(int nid, unsigned long start_pfn,
*/
static unsigned long sparse_encode_mem_map(struct page *mem_map, unsigned long pnum)
{
- return (unsigned long)(mem_map - (section_nr_to_pfn(pnum)));
+ unsigned long coded_mem_map =
+ (unsigned long)(mem_map - (section_nr_to_pfn(pnum)));
+ BUILD_BUG_ON(SECTION_MAP_LAST_BIT > (1UL<<PFN_SECTION_SHIFT));
+ BUG_ON(coded_mem_map & ~SECTION_MAP_MASK);
+ return coded_mem_map;
}
/*