[PATCH v2 4/4] powerpc/mm/radix: Create separate mappings for hot-plugged memory

Aneesh Kumar K.V aneesh.kumar at linux.ibm.com
Thu Jun 25 16:45:47 AEST 2020


To enable memory unplug without splitting kernel page table
mapping, we force the max mapping size to the LMB size. LMB
size is the unit in which hypervisor will do memory add/remove
operation.

This implies on pseries system, we now end up mapping
memory with 2M page size instead of 1G. To improve
that we want hypervisor to hint the kernel about the hotplug
memory range.  This was added that as part of

commit b6eca183e23e ("powerpc/kernel: Enables memory
hot-remove after reboot on pseries guests")

But we still don't do that on PowerVM. Once we get PowerVM
updated, we can then force the 2M mapping only to hot-pluggable
memory region using memblock_is_hotpluggable(). Till then
let's depend on LMB size for finding the mapping page size
for linear range.

Signed-off-by: Bharata B Rao <bharata at linux.ibm.com>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar at linux.ibm.com>
---
 arch/powerpc/mm/book3s64/radix_pgtable.c | 83 ++++++++++++++++++++----
 arch/powerpc/platforms/powernv/setup.c   | 10 ++-
 2 files changed, 81 insertions(+), 12 deletions(-)

diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c
index 78ad11812e0d..a4179e4da49d 100644
--- a/arch/powerpc/mm/book3s64/radix_pgtable.c
+++ b/arch/powerpc/mm/book3s64/radix_pgtable.c
@@ -15,6 +15,7 @@
 #include <linux/mm.h>
 #include <linux/hugetlb.h>
 #include <linux/string_helpers.h>
+#include <linux/memory.h>
 
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
@@ -34,6 +35,7 @@
 
 unsigned int mmu_pid_bits;
 unsigned int mmu_base_pid;
+unsigned int radix_mem_block_size;
 
 static __ref void *early_alloc_pgtable(unsigned long size, int nid,
 			unsigned long region_start, unsigned long region_end)
@@ -266,6 +268,7 @@ static unsigned long next_boundary(unsigned long addr, unsigned long end)
 
 static int __meminit create_physical_mapping(unsigned long start,
 					     unsigned long end,
+					     unsigned long max_mapping_size,
 					     int nid, pgprot_t _prot)
 {
 	unsigned long vaddr, addr, mapping_size = 0;
@@ -279,6 +282,8 @@ static int __meminit create_physical_mapping(unsigned long start,
 		int rc;
 
 		gap = next_boundary(addr, end) - addr;
+		if (gap > max_mapping_size)
+			gap = max_mapping_size;
 		previous_size = mapping_size;
 		prev_exec = exec;
 
@@ -329,8 +334,9 @@ static void __init radix_init_pgtable(void)
 
 	/* We don't support slb for radix */
 	mmu_slb_size = 0;
+
 	/*
-	 * Create the linear mapping, using standard page size for now
+	 * Create the linear mapping
 	 */
 	for_each_memblock(memory, reg) {
 		/*
@@ -346,6 +352,7 @@ static void __init radix_init_pgtable(void)
 
 		WARN_ON(create_physical_mapping(reg->base,
 						reg->base + reg->size,
+						radix_mem_block_size,
 						-1, PAGE_KERNEL));
 	}
 
@@ -486,6 +493,49 @@ static int __init radix_dt_scan_page_sizes(unsigned long node,
 	return 1;
 }
 
+static int __init probe_memory_block_size(unsigned long node, const char *uname, int
+					  depth, void *data)
+{
+	const __be32 *block_size;
+	int len;
+
+	if (depth != 1)
+		return 0;
+
+	if (!strcmp(uname, "ibm,dynamic-reconfiguration-memory")) {
+
+		block_size = of_get_flat_dt_prop(node, "ibm,lmb-size", &len);
+		if (!block_size || len < dt_root_size_cells * sizeof(__be32))
+			/*
+			 * Nothing in the device tree
+			 */
+			return MIN_MEMORY_BLOCK_SIZE;
+
+		return dt_mem_next_cell(dt_root_size_cells, &block_size);
+
+	}
+
+	return 0;
+}
+
+static unsigned long radix_memory_block_size(void)
+{
+	unsigned long mem_block_size = MIN_MEMORY_BLOCK_SIZE;
+
+	if (firmware_has_feature(FW_FEATURE_OPAL)) {
+
+		mem_block_size = 1UL * 1024 * 1024 * 1024;
+
+	} else if (firmware_has_feature(FW_FEATURE_LPAR)) {
+		mem_block_size = of_scan_flat_dt(probe_memory_block_size, NULL);
+		if (!mem_block_size)
+			mem_block_size = MIN_MEMORY_BLOCK_SIZE;
+	}
+
+	return mem_block_size;
+}
+
+
 void __init radix__early_init_devtree(void)
 {
 	int rc;
@@ -494,17 +544,27 @@ void __init radix__early_init_devtree(void)
 	 * Try to find the available page sizes in the device-tree
 	 */
 	rc = of_scan_flat_dt(radix_dt_scan_page_sizes, NULL);
-	if (rc != 0)  /* Found */
-		goto found;
+	if (rc == 0) {
+		/*
+		 * no page size details found in device tree
+		 * let's assume we have page 4k and 64k support
+		 */
+		mmu_psize_defs[MMU_PAGE_4K].shift = 12;
+		mmu_psize_defs[MMU_PAGE_4K].ap = 0x0;
+
+		mmu_psize_defs[MMU_PAGE_64K].shift = 16;
+		mmu_psize_defs[MMU_PAGE_64K].ap = 0x5;
+	}
+
 	/*
-	 * let's assume we have page 4k and 64k support
+	 * Max mapping size used when mapping pages. We don't use
+	 * ppc_md.memory_block_size() here because this get called
+	 * early and we don't have machine probe called yet. Also
+	 * the pseries implementation only check for ibm,lmb-size.
+	 * All hypervisor supporting radix do expose that device
+	 * tree node.
 	 */
-	mmu_psize_defs[MMU_PAGE_4K].shift = 12;
-	mmu_psize_defs[MMU_PAGE_4K].ap = 0x0;
-
-	mmu_psize_defs[MMU_PAGE_64K].shift = 16;
-	mmu_psize_defs[MMU_PAGE_64K].ap = 0x5;
-found:
+	radix_mem_block_size = radix_memory_block_size();
 	return;
 }
 
@@ -856,7 +916,8 @@ int __meminit radix__create_section_mapping(unsigned long start,
 		return -1;
 	}
 
-	return create_physical_mapping(__pa(start), __pa(end), nid, prot);
+	return create_physical_mapping(__pa(start), __pa(end),
+				       radix_mem_block_size, nid, prot);
 }
 
 int __meminit radix__remove_section_mapping(unsigned long start, unsigned long end)
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index 3bc188da82ba..6e2f614590a3 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -399,7 +399,15 @@ static void pnv_kexec_cpu_down(int crash_shutdown, int secondary)
 #ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
 static unsigned long pnv_memory_block_size(void)
 {
-	return 256UL * 1024 * 1024;
+	/*
+	 * We map the kernel linear region with 1GB large pages on radix. For
+	 * memory hot unplug to work our memory block size must be at least
+	 * this size.
+	 */
+	if (radix_enabled())
+		return 1UL * 1024 * 1024 * 1024;
+	else
+		return 256UL * 1024 * 1024;
 }
 #endif
 
-- 
2.26.2



More information about the Linuxppc-dev mailing list