[PATCH] x86: OLPC: speed up device tree creation during boot

[Andres Salomon]

Calling alloc_bootmem() for tiny chunks of memory over and over is really
slow; on an XO-1, it caused the time between when the kernel started
booting and when the display came alive (post-lxfb probe) to increase
to 44s.  This patch optimizes the prom_early_alloc function by
calling alloc_bootmem for 4k-sized blocks of memory, and handing out
chunks of that to callers.  With this hack, the time between kernel load
and display initialization decreased to 23s.  If there's a better way to
do this early in the boot process, please let me know.

(Note: increasing the chunk size to 16k didn't noticably affect boot time,
and wasted 9k.)

Signed-off-by: Andres Salomon <dilinger at queued.net>
---
 arch/x86/kernel/olpc_dt.c |   27 +++++++++++++++++++++++----
 1 files changed, 23 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kernel/olpc_dt.c b/arch/x86/kernel/olpc_dt.c
index f660a11..44dd2ae 100644
--- a/arch/x86/kernel/olpc_dt.c
+++ b/arch/x86/kernel/olpc_dt.c
@@ -123,16 +123,35 @@ static int __init olpc_dt_pkg2path(phandle node, char *buf,
 }
 
 static unsigned int prom_early_allocated __initdata;
+#define DT_CHUNK_SIZE (1<<12)
 
 void * __init prom_early_alloc(unsigned long size)
 {
+	static u8 *mem = NULL;
+	static size_t free_mem = 0;
 	void *res;
 
-	res = alloc_bootmem(size);
-	if (res)
-		memset(res, 0, size);
+	if (free_mem >= size) {
+		/* allocate from the local cache */
+		free_mem -= size;
+		res = mem;
+		mem += size;
+		return res;
+	}
 
-	prom_early_allocated += size;
+	/*
+	 * To mimimize the number of allocations, grab 4k of memory (that's
+	 * an arbitrary choice that matches PAGE_SIZE on the platforms we care
+	 * about, and minimizes wasted bootmem) and hand off chunks of it to
+	 * callers.
+	 */
+	res = alloc_bootmem(DT_CHUNK_SIZE);
+	if (res) {
+		prom_early_allocated += DT_CHUNK_SIZE;
+		memset(res, 0, DT_CHUNK_SIZE);
+		free_mem = DT_CHUNK_SIZE - size;
+		mem = res + size;
+	}
 
 	return res;
 }
-- 
1.5.6.5