powerpc: Add support for dynamic reconfiguration memory in kexec/kdump kernels

Kdump kernel needs to use only those memory regions that it is allowed
to use (crashkernel, rtas, tce, etc.).  Each of these regions have
their own sizes and are currently added under 'linux,usable-memory'
property under each memory@xxx node of the device tree.

The ibm,dynamic-memory property of ibm,dynamic-reconfiguration-memory
node (on POWER6) now stores in it the representation for most of the
logical memory blocks with the size of each memory block being a
constant (lmb_size).  If one or more or part of the above mentioned
regions lie under one of the lmb from ibm,dynamic-memory property,
there is a need to identify those regions within the given lmb.

This makes the kernel recognize a new 'linux,drconf-usable-memory'
property added by kexec-tools.  Each entry in this property is of the
form of a count followed by that many (base, size) pairs for the above
mentioned regions.  The number of cells in the count value is given by
the #size-cells property of the root node.

Signed-off-by: Chandru Siddalingappa <chandru@in.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>

arch/powerpc/kernel/prom.c

@@ -888,9 +888,10 @@ static u64 __init dt_mem_next_cell(int s, cell_t **cellp)
  */
 static int __init early_init_dt_scan_drconf_memory(unsigned long node)
 {
-	cell_t *dm, *ls;
+	cell_t *dm, *ls, *usm;
 	unsigned long l, n, flags;
 	u64 base, size, lmb_size;
+	unsigned int is_kexec_kdump = 0, rngs;
 
 	ls = (cell_t *)of_get_flat_dt_prop(node, "ibm,lmb-size", &l);
 	if (ls == NULL || l < dt_root_size_cells * sizeof(cell_t))
@@ -905,6 +906,12 @@ static int __init early_init_dt_scan_drconf_memory(unsigned long node)
 	if (l < (n * (dt_root_addr_cells + 4) + 1) * sizeof(cell_t))
 		return 0;
 
+	/* check if this is a kexec/kdump kernel. */
+	usm = (cell_t *)of_get_flat_dt_prop(node, "linux,drconf-usable-memory",
+						 &l);
+	if (usm != NULL)
+		is_kexec_kdump = 1;
+
 	for (; n != 0; --n) {
 		base = dt_mem_next_cell(dt_root_addr_cells, &dm);
 		flags = dm[3];
@@ -915,13 +922,34 @@ static int __init early_init_dt_scan_drconf_memory(unsigned long node)
 		if ((flags & 0x80) || !(flags & 0x8))
 			continue;
 		size = lmb_size;
-		if (iommu_is_off) {
-			if (base >= 0x80000000ul)
+		rngs = 1;
+		if (is_kexec_kdump) {
+			/*
+			 * For each lmb in ibm,dynamic-memory, a corresponding
+			 * entry in linux,drconf-usable-memory property contains
+			 * a counter 'p' followed by 'p' (base, size) duple.
+			 * Now read the counter from
+			 * linux,drconf-usable-memory property
+			 */
+			rngs = dt_mem_next_cell(dt_root_size_cells, &usm);
+			if (!rngs) /* there are no (base, size) duple */
 				continue;
-			if ((base + size) > 0x80000000ul)
-				size = 0x80000000ul - base;
 		}
-		lmb_add(base, size);
+		do {
+			if (is_kexec_kdump) {
+				base = dt_mem_next_cell(dt_root_addr_cells,
+							 &usm);
+				size = dt_mem_next_cell(dt_root_size_cells,
+							 &usm);
+			}
+			if (iommu_is_off) {
+				if (base >= 0x80000000ul)
+					continue;
+				if ((base + size) > 0x80000000ul)
+					size = 0x80000000ul - base;
+			}
+			lmb_add(base, size);
+		} while (--rngs);
 	}
 	lmb_dump_all();
 	return 0;

arch/powerpc/mm/numa.c

@@ -150,6 +150,21 @@ static const int *of_get_associativity(struct device_node *dev)
 	return of_get_property(dev, "ibm,associativity", NULL);
 }
 
+/*
+ * Returns the property linux,drconf-usable-memory if
+ * it exists (the property exists only in kexec/kdump kernels,
+ * added by kexec-tools)
+ */
+static const u32 *of_get_usable_memory(struct device_node *memory)
+{
+	const u32 *prop;
+	u32 len;
+	prop = of_get_property(memory, "linux,drconf-usable-memory", &len);
+	if (!prop || len < sizeof(unsigned int))
+		return 0;
+	return prop;
+}
+
 /* Returns nid in the range [0..MAX_NUMNODES-1], or -1 if no useful numa
  * info is found.
  */
@@ -486,15 +501,30 @@ static unsigned long __init numa_enforce_memory_limit(unsigned long start,
 	return lmb_end_of_DRAM() - start;
 }
 
+/*
+ * Reads the counter for a given entry in
+ * linux,drconf-usable-memory property
+ */
+static inline int __init read_usm_ranges(const u32 **usm)
+{
+	/*
+	 * For each lmb in ibm,dynamic-memory a corresponding
+	 * entry in linux,drconf-usable-memory property contains
+	 * a counter followed by that many (base, size) duple.
+	 * read the counter from linux,drconf-usable-memory
+	 */
+	return read_n_cells(n_mem_size_cells, usm);
+}
+
 /*
  * Extract NUMA information from the ibm,dynamic-reconfiguration-memory
  * node.  This assumes n_mem_{addr,size}_cells have been set.
  */
 static void __init parse_drconf_memory(struct device_node *memory)
 {
-	const u32 *dm;
-	unsigned int n, rc;
-	unsigned long lmb_size, size;
+	const u32 *dm, *usm;
+	unsigned int n, rc, ranges, is_kexec_kdump = 0;
+	unsigned long lmb_size, base, size, sz;
 	int nid;
 	struct assoc_arrays aa;
 
@@ -510,6 +540,11 @@ static void __init parse_drconf_memory(struct device_node *memory)
 	if (rc)
 		return;
 
+	/* check if this is a kexec/kdump kernel */
+	usm = of_get_usable_memory(memory);
+	if (usm != NULL)
+		is_kexec_kdump = 1;
+
 	for (; n != 0; --n) {
 		struct of_drconf_cell drmem;
 
@@ -521,21 +556,31 @@ static void __init parse_drconf_memory(struct device_node *memory)
 		    || !(drmem.flags & DRCONF_MEM_ASSIGNED))
 			continue;
 
-		nid = of_drconf_to_nid_single(&drmem, &aa);
+		base = drmem.base_addr;
+		size = lmb_size;
+		ranges = 1;
 
-		fake_numa_create_new_node(
-				((drmem.base_addr + lmb_size) >> PAGE_SHIFT),
+		if (is_kexec_kdump) {
+			ranges = read_usm_ranges(&usm);
+			if (!ranges) /* there are no (base, size) duple */
+				continue;
+		}
+		do {
+			if (is_kexec_kdump) {
+				base = read_n_cells(n_mem_addr_cells, &usm);
+				size = read_n_cells(n_mem_size_cells, &usm);
+			}
+			nid = of_drconf_to_nid_single(&drmem, &aa);
+			fake_numa_create_new_node(
+				((base + size) >> PAGE_SHIFT),
 					   &nid);
-
-		node_set_online(nid);
-
-		size = numa_enforce_memory_limit(drmem.base_addr, lmb_size);
-		if (!size)
-			continue;
-
-		add_active_range(nid, drmem.base_addr >> PAGE_SHIFT,
-				 (drmem.base_addr >> PAGE_SHIFT)
-				 + (size >> PAGE_SHIFT));
+			node_set_online(nid);
+			sz = numa_enforce_memory_limit(base, size);
+			if (sz)
+				add_active_range(nid, base >> PAGE_SHIFT,
+						 (base >> PAGE_SHIFT)
+						 + (sz >> PAGE_SHIFT));
+		} while (--ranges);
 	}
 }