mm: introduce arch_reserved_kernel_pages()

Currently arch specific code can reserve memory blocks but
alloc_large_system_hash() may not take it into consideration when sizing
the hashes.  This can lead to bigger hash than required and lead to no
available memory for other purposes.  This is specifically true for
systems with CONFIG_DEFERRED_STRUCT_PAGE_INIT enabled.

One approach to solve this problem would be to walk through the memblock
regions and calculate the available memory and base the size of hash
system on the available memory.

The other approach would be to depend on the architecture to provide the
number of pages that are reserved.  This change provides hooks to allow
the architecture to provide the required info.

Link: http://lkml.kernel.org/r/1472476010-4709-2-git-send-email-srikar@linux.vnet.ibm.com
Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Suggested-by: Mel Gorman <mgorman@techsingularity.net>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Cc: Hari Bathini <hbathini@linux.vnet.ibm.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Balbir Singh <bsingharora@gmail.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 0a063b4e44563e4c5c2283ab27b7b8672db03737..046077b4209d65b82e3534b3338a6ea0500c78a3 100644 (file)
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1924,6 +1924,9 @@ extern void show_mem(unsigned int flags);
 extern long si_mem_available(void);
 extern void si_meminfo(struct sysinfo * val);
 extern void si_meminfo_node(struct sysinfo *val, int nid);
+#ifdef __HAVE_ARCH_RESERVED_KERNEL_PAGES
+extern unsigned long arch_reserved_kernel_pages(void);
+#endif
 
 extern __printf(3, 4)
 void warn_alloc_failed(gfp_t gfp_mask, unsigned int order,

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index f6a5a221496af735d53721a520f2bad1ed8ada8b..e00f545c239896ecd5a44c4aabbc6aea55d64862 100644 (file)
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -6940,6 +6940,17 @@ static int __init set_hashdist(char *str)
 __setup("hashdist=", set_hashdist);
 #endif
 
+#ifndef __HAVE_ARCH_RESERVED_KERNEL_PAGES
+/*
+ * Returns the number of pages that arch has reserved but
+ * is not known to alloc_large_system_hash().
+ */
+static unsigned long __init arch_reserved_kernel_pages(void)
+{
+       return 0;
+}
+#endif
+
 /*
  * allocate a large system hash table from bootmem
  * - it is assumed that the hash table must contain an exact power-of-2
@@ -6964,6 +6975,7 @@ void *__init alloc_large_system_hash(const char *tablename,
        if (!numentries) {
                /* round applicable memory size up to nearest megabyte */
                numentries = nr_kernel_pages;
+               numentries -= arch_reserved_kernel_pages();
 
                /* It isn't necessary when PAGE_SIZE >= 1MB */
                if (PAGE_SHIFT < 20)