[PATCH] Permit inode & dentry hash tables to be allocated > MAX_ORDER size

Here's a patch to allocate memory for big system hash tables with the
bootmem allocator rather than with main page allocator.

It is needed for three reasons:

(1) So that the size can be bigger than MAX_ORDER.  IBM have done some
    testing on their big PPC64 systems (64GB of RAM) with linux-2.4 and found
    that they get better performance if the sizes of the inode cache hash,
    dentry cache hash, buffer head hash and page cache hash are increased
    beyond MAX_ORDER (order 11).

     Now the main allocator can't allocate anything larger than MAX_ORDER, but
     the bootmem allocator can.

     In 2.6 it appears that only the inode and dentry hashes remain of those
     four, but there are other hash tables that could use this service.

(2) Changing MAX_ORDER appears to have a number of effects beyond just
    limiting the maximum size that can be allocated in one go.

(3) Should someone want a hash table in which each bucket isn't a power of
    two in size, memory will be wasted as the chunk of memory allocated will
    be a power of two in size (to hold a power of two number of buckets).

    On the other hand, using the bootmem allocator means the allocation
    will only take up sufficient pages to hold it, rather than the next power
    of two up.

    Admittedly, this point doesn't apply to the dentry and inode hashes,
    but it might to another hash table that might want to use this service.


I've coelesced the meat of the inode and dentry allocation routines into
one such routine in mm/page_alloc.c that the the respective initialisation
functions now call before mem_init() is called.

This routine gets it's approximation of memory size by counting up the
ZONE_NORMAL and ZONE_DMA pages (and ZONE_HIGHMEM if requested) in all the
nodes passed to the main allocator by paging_init() (or wherever the arch
does it).  It does not use max_low_pfn as that doesn't seem to be available
on all archs, and it doesn't use num_physpages since that includes highmem
pages not available to the kernel for allocating data structures upon -
which may not be appropriate when calculating hash table size.

On the off chance that the size of each hash bucket may not be exactly a
power of two, the routine will only allocate as many pages as is necessary
to ensure that the number of buckets is exactly a power of two, rather than
allocating the smallest power-of-two sized chunk of memory that will hold
the same array of buckets.

The maximum size of any single hash table is given by
MAX_SYS_HASH_TABLE_ORDER, as is now defined in linux/mmzone.h.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

1 files changed, 73 insertions, 0 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 444bb534dbd8ee..16d5c2af94ee02 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -55,6 +55,9 @@ EXPORT_SYMBOL(zone_table);
 static char *zone_names[MAX_NR_ZONES] = { "DMA", "Normal", "HighMem" };
 int min_free_kbytes = 1024;
 
+static unsigned long __initdata nr_kernel_pages;
+static unsigned long __initdata nr_all_pages;
+
 /*
  * Temporary debugging check for pages not lying within a given zone.
  */
@@ -1430,6 +1433,10 @@ static void __init free_area_init_core(struct pglist_data *pgdat,
 		if (zholes_size)
 			realsize -= zholes_size[j];
 
+		if (j == ZONE_DMA || j == ZONE_NORMAL)
+			nr_kernel_pages += realsize;
+		nr_all_pages += realsize;
+
 		zone->spanned_pages = size;
 		zone->present_pages = realsize;
 		zone->name = zone_names[j];
@@ -1970,3 +1977,69 @@ int lower_zone_protection_sysctl_handler(ctl_table *table, int write,
 	setup_per_zone_protection();
 	return 0;
 }
+
+/*
+ * allocate a large system hash table from bootmem
+ * - it is assumed that the hash table must contain an exact power-of-2
+ *   quantity of entries
+ */
+void *__init alloc_large_system_hash(const char *tablename,
+				     unsigned long bucketsize,
+				     unsigned long numentries,
+				     int scale,
+				     int consider_highmem,
+				     unsigned int *_hash_shift,
+				     unsigned int *_hash_mask)
+{
+	unsigned long mem, max, log2qty, size;
+	void *table;
+
+	/* round applicable memory size up to nearest megabyte */
+	mem = consider_highmem ? nr_all_pages : nr_kernel_pages;
+	mem += (1UL << (20 - PAGE_SHIFT)) - 1;
+	mem >>= 20 - PAGE_SHIFT;
+	mem <<= 20 - PAGE_SHIFT;
+
+	/* limit to 1 bucket per 2^scale bytes of low memory (rounded up to
+	 * nearest power of 2 in size) */
+	if (scale > PAGE_SHIFT)
+		mem >>= (scale - PAGE_SHIFT);
+	else
+		mem <<= (PAGE_SHIFT - scale);
+
+	mem = 1UL << (long_log2(mem) + 1);
+
+	/* limit allocation size */
+	max = (1UL << (PAGE_SHIFT + MAX_SYS_HASH_TABLE_ORDER)) / bucketsize;
+	if (max > mem)
+		max = mem;
+
+	/* allow the kernel cmdline to have a say */
+	if (!numentries || numentries > max)
+		numentries = max;
+
+	log2qty = long_log2(numentries);
+
+	do {
+		size = bucketsize << log2qty;
+
+		table = (void *) alloc_bootmem(size);
+
+	} while (!table && size > PAGE_SIZE);
+
+	if (!table)
+		panic("Failed to allocate %s hash table\n", tablename);
+
+	printk("%s hash table entries: %d (order: %d, %lu bytes)\n",
+	       tablename,
+	       (1U << log2qty),
+	       long_log2(size) - PAGE_SHIFT,
+	       size);
+
+	if (_hash_shift)
+		*_hash_shift = log2qty;
+	if (_hash_mask)
+		*_hash_mask = (1 << log2qty) - 1;
+
+	return table;
+}