powerpc/memtrace: Remove memory in chunks

When hot-removing memory release_mem_region_adjustable() splits iomem
resources if they are not the exact size of the memory being
hot-deleted. Adding this memory back to the kernel adds a new resource.

Eg a node has memory 0x0 - 0xfffffffff. Hot-removing 1GB from
0xf40000000 results in the single resource 0x0-0xfffffffff being split
into two resources: 0x0-0xf3fffffff and 0xf80000000-0xfffffffff.

When we hot-add the memory back we now have three resources:
0x0-0xf3fffffff, 0xf40000000-0xf7fffffff, and 0xf80000000-0xfffffffff.

This is an issue if we try to remove some memory that overlaps
resources. Eg when trying to remove 2GB at address 0xf40000000,
release_mem_region_adjustable() fails as it expects the chunk of memory
to be within the boundaries of a single resource. We then get the
warning: "Unable to release resource" and attempting to use memtrace
again gives us this error: "bash: echo: write error: Resource
temporarily unavailable"

This patch makes memtrace remove memory in chunks that are always the
same size from an address that is always equal to end_of_memory -
n*size, for some n. So hotremoving and hotadding memory of different
sizes will now not attempt to remove memory that spans multiple
resources.

Signed-off-by: Rashmica Gupta <rashmica.g@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

diff --git a/arch/powerpc/platforms/powernv/memtrace.c b/arch/powerpc/platforms/powernv/memtrace.c
index 51dc398ae3f7a2431b39f6705a4cfc495a378aeb..a29fdf8a2e56ed5ab70d663f2bb40e04fe821e72 100644 (file)
--- a/arch/powerpc/platforms/powernv/memtrace.c
+++ b/arch/powerpc/platforms/powernv/memtrace.c
@@ -90,17 +90,15 @@ static bool memtrace_offline_pages(u32 nid, u64 start_pfn, u64 nr_pages)
        walk_memory_range(start_pfn, end_pfn, (void *)MEM_OFFLINE,
                          change_memblock_state);
 
-       lock_device_hotplug();
-       remove_memory(nid, start_pfn << PAGE_SHIFT, nr_pages << PAGE_SHIFT);
-       unlock_device_hotplug();
 
        return true;
 }
 
 static u64 memtrace_alloc_node(u32 nid, u64 size)
 {
-       u64 start_pfn, end_pfn, nr_pages;
+       u64 start_pfn, end_pfn, nr_pages, pfn;
        u64 base_pfn;
+       u64 bytes = memory_block_size_bytes();
 
        if (!node_spanned_pages(nid))
                return 0;
@@ -113,8 +111,21 @@ static u64 memtrace_alloc_node(u32 nid, u64 size)
        end_pfn = round_down(end_pfn - nr_pages, nr_pages);
 
        for (base_pfn = end_pfn; base_pfn > start_pfn; base_pfn -= nr_pages) {
-               if (memtrace_offline_pages(nid, base_pfn, nr_pages) == true)
+               if (memtrace_offline_pages(nid, base_pfn, nr_pages) == true) {
+                       /*
+                        * Remove memory in memory block size chunks so that
+                        * iomem resources are always split to the same size and
+                        * we never try to remove memory that spans two iomem
+                        * resources.
+                        */
+                       lock_device_hotplug();
+                       end_pfn = base_pfn + nr_pages;
+                       for (pfn = base_pfn; pfn < end_pfn; pfn += bytes>> PAGE_SHIFT) {
+                               remove_memory(nid, pfn << PAGE_SHIFT, bytes);
+                       }
+                       unlock_device_hotplug();
                        return base_pfn << PAGE_SHIFT;
+               }
        }
 
        return 0;