mm: zero hash tables in allocator

Add a new flag HASH_ZERO which when provided grantees that the hash
table that is returned by alloc_large_system_hash() is zeroed.  In most
cases that is what is needed by the caller.  Use page level allocator's
__GFP_ZERO flags to zero the memory.  It is using memset() which is
efficient method to zero memory and is optimized for most platforms.

Link: http://lkml.kernel.org/r/1488432825-92126-3-git-send-email-pasha.tatashin@oracle.com
Signed-off-by: Pavel Tatashin <pasha.tatashin@oracle.com>
Reviewed-by: Babu Moger <babu.moger@oracle.com>
Cc: David Miller <davem@davemloft.net>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h
index 962164d..e223d91 100644 (file)
--- a/include/linux/bootmem.h
+++ b/include/linux/bootmem.h
@@ -358,6 +358,7 @@ extern void *alloc_large_system_hash(const char *tablename,
 #define HASH_EARLY     0x00000001      /* Allocating during early boot? */
 #define HASH_SMALL     0x00000002      /* sub-page allocation allowed, min
                                         * shift passed via *_hash_shift */
+#define HASH_ZERO      0x00000004      /* Zero allocated hash table */
 
 /* Only NUMA needs hash distribution. 64bit NUMA architectures have
  * sufficient vmalloc space.

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 387f20d..34240e2 100644 (file)
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -7198,6 +7198,7 @@ void *__init alloc_large_system_hash(const char *tablename,
        unsigned long long max = high_limit;
        unsigned long log2qty, size;
        void *table = NULL;
+       gfp_t gfp_flags;
 
        /* allow the kernel cmdline to have a say */
        if (!numentries) {
@@ -7242,12 +7243,17 @@ void *__init alloc_large_system_hash(const char *tablename,
 
        log2qty = ilog2(numentries);
 
+       /*
+        * memblock allocator returns zeroed memory already, so HASH_ZERO is
+        * currently not used when HASH_EARLY is specified.
+        */
+       gfp_flags = (flags & HASH_ZERO) ? GFP_ATOMIC | __GFP_ZERO : GFP_ATOMIC;
        do {
                size = bucketsize << log2qty;
                if (flags & HASH_EARLY)
                        table = memblock_virt_alloc_nopanic(size, 0);
                else if (hashdist)
-                       table = __vmalloc(size, GFP_ATOMIC, PAGE_KERNEL);
+                       table = __vmalloc(size, gfp_flags, PAGE_KERNEL);
                else {
                        /*
                         * If bucketsize is not a power-of-two, we may free
@@ -7255,8 +7261,8 @@ void *__init alloc_large_system_hash(const char *tablename,
                         * alloc_pages_exact() automatically does
                         */
                        if (get_order(size) < MAX_ORDER) {
-                               table = alloc_pages_exact(size, GFP_ATOMIC);
-                               kmemleak_alloc(table, size, 1, GFP_ATOMIC);
+                               table = alloc_pages_exact(size, gfp_flags);
+                               kmemleak_alloc(table, size, 1, gfp_flags);
                        }
                }
        } while (!table && size > PAGE_SIZE && --log2qty);