powerpc/pseries: Automatically resize HPT for memory hot add/remove

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@gibson.dropbear.id.au>
Reviewed-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

diff --git a/arch/powerpc/include/asm/sparsemem.h b/arch/powerpc/include/asm/sparsemem.h
index f6fc0ee813d7afad1cd4572674b363fa5b9e0430..737335c891e4099aa5b1675de696fd5652b708c6 100644 (file)
--- 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 a3371d4e35b647451c883da3a979ea34724135f6..12d679df50bd17c3c1ba5bbf5fab3949b4a00167 100644 (file)
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -749,6 +749,35 @@ 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 (!mmu_hash_ops.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 = mmu_hash_ops.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 hash__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 5f844337de2128801a465455d3c0790a3564972d..9ee536ec0739514eef0af5ce2e6724e09fca3f79 100644 (file)
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -134,6 +134,8 @@ 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);
@@ -174,6 +176,8 @@ int arch_remove_memory(u64 start, u64 size)
         */
        vm_unmap_aliases();
 
+       resize_hpt_for_hotplug(memblock_phys_mem_size());
+
        return ret;
 }
 #endif