powerpc/mm: Track backing pages allocated by vmemmap_populate()

We need to keep track of the backing pages that get allocated by
vmemmap_populate() so that when we use kdump, the dump-capture kernel knows
where these pages are.

We use a simple linked list of structures that contain the physical address
of the backing page and corresponding virtual address to track the backing
pages.
To save space, we just use a pointer to the next struct vmemmap_backing. We
can also do this because we never remove nodes.  We call the pointer "list"
to be compatible with changes made to the crash utility.

vmemmap_populate() is called either at boot-time or on a memory hotplug
operation. We don't have to worry about the boot-time calls because they
will be inherently single-threaded, and for a memory hotplug operation
vmemmap_populate() is called through:
sparse_add_one_section()
            |
            V
kmalloc_section_memmap()
            |
            V
sparse_mem_map_populate()
            |
            V
vmemmap_populate()
and in sparse_add_one_section() we're protected by pgdat_resize_lock().
So, we don't need a spinlock to protect the vmemmap_list.

We allocate space for the vmemmap_backing structs by allocating whole pages
in vmemmap_list_alloc() and then handing out chunks of this to
vmemmap_list_populate().

This means that we waste at most just under one page, but this keeps the code
is simple.

Signed-off-by: Mark Nelson <markn@au1.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

2 files changed, 49 insertions, 0 deletions

diff --git a/arch/powerpc/include/asm/pgalloc-64.h b/arch/powerpc/include/asm/pgalloc-64.h
index 605f5c5398d1..292725cec2e3 100644
--- a/arch/powerpc/include/asm/pgalloc-64.h
+++ b/arch/powerpc/include/asm/pgalloc-64.h
@@ -11,6 +11,12 @@
 #include <linux/cpumask.h>
 #include <linux/percpu.h>
 
+struct vmemmap_backing {
+        struct vmemmap_backing *list;
+        unsigned long phys;
+        unsigned long virt_addr;
+};
+
 /*
  * Functions that deal with pagetables that could be at any level of
  * the table need to be passed an "index_size" so they know how to
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index d7fa50b09b4a..e267f223fdff 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -252,6 +252,47 @@ static void __meminit vmemmap_create_mapping(unsigned long start,
 }
 #endif /* CONFIG_PPC_BOOK3E */
 
+struct vmemmap_backing *vmemmap_list;
+
+static __meminit struct vmemmap_backing * vmemmap_list_alloc(int node)
+{
+        static struct vmemmap_backing *next;
+        static int num_left;
+
+        /* allocate a page when required and hand out chunks */
+        if (!next || !num_left) {
+                next = vmemmap_alloc_block(PAGE_SIZE, node);
+                if (unlikely(!next)) {
+                        WARN_ON(1);
+                        return NULL;
+                }
+                num_left = PAGE_SIZE / sizeof(struct vmemmap_backing);
+        }
+
+        num_left--;
+
+        return next++;
+}
+
+static __meminit void vmemmap_list_populate(unsigned long phys,
+                                            unsigned long start,
+                                            int node)
+{
+        struct vmemmap_backing *vmem_back;
+
+        vmem_back = vmemmap_list_alloc(node);
+        if (unlikely(!vmem_back)) {
+                WARN_ON(1);
+                return;
+        }
+
+        vmem_back->phys = phys;
+        vmem_back->virt_addr = start;
+        vmem_back->list = vmemmap_list;
+
+        vmemmap_list = vmem_back;
+}
+
 int __meminit vmemmap_populate(struct page *start_page,
                                unsigned long nr_pages, int node)
 {
@@ -276,6 +317,8 @@ int __meminit vmemmap_populate(struct page *start_page,
                 if (!p)
                         return -ENOMEM;
 
+                vmemmap_list_populate(__pa(p), start, node);
+
                 pr_debug("      * %016lx..%016lx allocated at %p\n",
                          start, start + page_size, p);