[RFCv2 08/25] pseries: Automatically resize HPT for memory hot add/remove

[David Gibson]

We've now implemented code in the pseries platform to use the new PAPR
interface to allow resizing the hash page table (HPT) at runtime.

This patch uses that interface to automatically attempt to resize the HPT
when memory is hot added or removed.  This tries to always keep the HPT at
a reasonable size for our current memory size.

Signed-off-by: David Gibson <david at gibson.dropbear.id.au>
Reviewed-by: Paul Mackerras <paulus at samba.org>
---
 arch/powerpc/include/asm/sparsemem.h |  1 +
 arch/powerpc/mm/hash_utils_64.c      | 29 +++++++++++++++++++++++++++++
 arch/powerpc/mm/mem.c                |  4 ++++
 3 files changed, 34 insertions(+)

diff --git a/arch/powerpc/include/asm/sparsemem.h b/arch/powerpc/include/asm/sparsemem.h
index f6fc0ee..737335c 100644
--- a/arch/powerpc/include/asm/sparsemem.h
+++ b/arch/powerpc/include/asm/sparsemem.h
@@ -16,6 +16,7 @@
 #endif /* CONFIG_SPARSEMEM */
 
 #ifdef CONFIG_MEMORY_HOTPLUG
+extern void resize_hpt_for_hotplug(unsigned long new_mem_size);
 extern int create_section_mapping(unsigned long start, unsigned long end);
 extern int remove_section_mapping(unsigned long start, unsigned long end);
 #ifdef CONFIG_NUMA
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 0809bea..6fbc27a 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -645,6 +645,35 @@ static unsigned long __init htab_get_table_size(void)
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG
+void resize_hpt_for_hotplug(unsigned long new_mem_size)
+{
+	unsigned target_hpt_shift;
+
+	if (!ppc_md.resize_hpt)
+		return;
+
+	target_hpt_shift = htab_shift_for_mem_size(new_mem_size);
+
+	/*
+	 * To avoid lots of HPT resizes if memory size is fluctuating
+	 * across a boundary, we deliberately have some hysterisis
+	 * here: we immediately increase the HPT size if the target
+	 * shift exceeds the current shift, but we won't attempt to
+	 * reduce unless the target shift is at least 2 below the
+	 * current shift
+	 */
+	if ((target_hpt_shift > ppc64_pft_size)
+	    || (target_hpt_shift < (ppc64_pft_size - 1))) {
+		int rc;
+
+		rc = ppc_md.resize_hpt(target_hpt_shift);
+		if (rc)
+			printk(KERN_WARNING
+			       "Unable to resize hash page table to target order %d: %d\n",
+			       target_hpt_shift, rc);
+	}
+}
+
 int create_section_mapping(unsigned long start, unsigned long end)
 {
 	int rc = htab_bolt_mapping(start, end, __pa(start),
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index f980da6..4938ee7 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -121,6 +121,8 @@ int arch_add_memory(int nid, u64 start, u64 size, bool for_device)
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 	int rc;
 
+	resize_hpt_for_hotplug(memblock_phys_mem_size());
+
 	pgdata = NODE_DATA(nid);
 
 	start = (unsigned long)__va(start);
@@ -161,6 +163,8 @@ int arch_remove_memory(u64 start, u64 size)
 	 */
 	vm_unmap_aliases();
 
+	resize_hpt_for_hotplug(memblock_phys_mem_size());
+
 	return ret;
 }
 #endif
-- 
2.5.0