On Tue, 2019-09-03 at 08:23 +0200, Christophe Leroy wrote:

Le 03/09/2019 à 07:24, Alastair D'Silva a écrit :

quoted

From: Alastair D'Silva <redacted>

This operation takes a significant amount of time when hotplugging
large amounts of memory (~50 seconds with 890GB of persistent
memory).

This was orignally in commit fb5924fddf9e
("powerpc/mm: Flush cache on memory hot(un)plug") to support
memtrace,
but the flush on add is not needed as it is flushed on remove.

Signed-off-by: Alastair D'Silva <redacted>
---
  arch/powerpc/mm/mem.c | 7 -------
  1 file changed, 7 deletions(-)

diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 854aaea2c6ae..2a14b5b93e19 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c

@@ -111,7 +111,6 @@ int __ref arch_add_memory(int nid, u64 start,

u64 size,
  {
  	unsigned long start_pfn = start >> PAGE_SHIFT;
  	unsigned long nr_pages = size >> PAGE_SHIFT;
-	u64 i;
  	int rc;
  
  	resize_hpt_for_hotplug(memblock_phys_mem_size());

@@ -124,12 +123,6 @@ int __ref arch_add_memory(int nid, u64 start,

u64 size,
  		return -EFAULT;
  	}
  
-	for (i = 0; i < size; i += FLUSH_CHUNK_SIZE) {
-		flush_dcache_range(start + i,
-				   min(start + size, start + i +
FLUSH_CHUNK_SIZE));
-		cond_resched();
-	}
-

So you are removing the code you added in patch 4. Why not move this
one 
before patch 4 ?

I put them in this order so that if someone did want the flushes in
arch_add_memory, they could drop the later patch, but not trigger RCU
stalls.

-- 
Alastair D'Silva
Open Source Developer
Linux Technology Centre, IBM Australia
mob: 0423 762 819