Skip to contentSkip to conversation

Add support for memmap on memory feature on ppc64

PATCH Applied Aneesh Kumar K.V 1 participant 7 messages Aug 8, 2023

Subsystems (10)
lore
Share & tools
lore
#0 lore raw

v8 cover Add support for memmap on memory feature on ppc64

This patch series update memmap on memory feature to fall back to memmap allocation outside the memory block if the alignment rules are not met. This makes the feature more useful on architectures like ppc64 where alignment rules are different with 64K page size.

This patch series is dependent on dax vmemmap optimization series posted here
https://lore.kernel.org/linux-mm/[email protected]/

Changes from v7:
* Drop patch 7 because we are still discussing a runtime update of this feature is useful.

Changes from v6:
* Update comments in the code
* Update commit message for patch 7

Changes from v5:
* Update commit message
* Move memory alloc/free to the callers in patch 6
* Address review feedback w.r.t patch 4

Changes from v4:
* Use altmap.free instead of altmap.reserve
* Address review feedback

Changes from v3:
* Extend the module parameter memmap_on_memory to force allocation even though we can waste hotplug memory.

Changes from v2:
* Rebase to latest linus tree
* Redo the series based on review feedback. Multiple changes to the patchset.

Changes from v1:
* update the memblock to store vmemmap_altmap details. This is required so that when we remove the memory we can find the altmap details which is needed on some architectures.
* rebase to latest linus tree

Aneesh Kumar K.V (6):
mm/memory_hotplug: Simplify ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE kconfig mm/memory_hotplug: Allow memmap on memory hotplug request to fallback mm/memory_hotplug: Allow architecture to override memmap on memory
support check
mm/memory_hotplug: Support memmap_on_memory when memmap is not aligned
to pageblocks
powerpc/book3s64/memhotplug: Enable memmap on memory for radix mm/memory_hotplug: Embed vmem_altmap details in memory block

 .../admin-guide/mm/memory-hotplug.rst         |  12 ++
 arch/arm64/Kconfig                            |   4 +-
 arch/powerpc/Kconfig                          |   1 +
 arch/powerpc/include/asm/pgtable.h            |  21 ++
 .../platforms/pseries/hotplug-memory.c        |   2 +-
 arch/x86/Kconfig                              |   4 +-
 drivers/acpi/acpi_memhotplug.c                |   3 +-
 drivers/base/memory.c                         |  27 ++-
 include/linux/memory.h                        |   8 +-
 include/linux/memory_hotplug.h                |   3 +-
 mm/Kconfig                                    |   3 +
 mm/memory_hotplug.c                           | 185 ++++++++++++++----
 12 files changed, 209 insertions(+), 64 deletions(-)
Signature · 1 line
2.41.0
#1 lore raw

PATCH v8 1/6 mm/memory_hotplug: Simplify ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE kconfig

Instead of adding menu entry with all supported architectures, add mm/Kconfig variable and select the same from supported architectures.

No functional change in this patch.

---
 arch/arm64/Kconfig | 4 +---
 arch/x86/Kconfig   | 4 +---
 mm/Kconfig         | 3 +++
 3 files changed, 5 insertions(+), 6 deletions(-)
arch/arm64/Kconfig +1 -3
index b1573257a4d6..0f749cfab8e6 100644
@@ -78,6 +78,7 @@ config ARM64
 	select ARCH_INLINE_SPIN_UNLOCK_IRQ if !PREEMPTION
 	select ARCH_INLINE_SPIN_UNLOCK_IRQRESTORE if !PREEMPTION
 	select ARCH_KEEP_MEMBLOCK
+	select ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE
 	select ARCH_USE_CMPXCHG_LOCKREF
 	select ARCH_USE_GNU_PROPERTY
 	select ARCH_USE_MEMTEST
@@ -347,9 +348,6 @@ config GENERIC_CSUM
 config GENERIC_CALIBRATE_DELAY
 	def_bool y
 
-config ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE
-	def_bool y
-
 config SMP
 	def_bool y
 
arch/x86/Kconfig +1 -3
index 78224aa76409..d0258e92a8af 100644
@@ -102,6 +102,7 @@ config X86
 	select ARCH_HAS_DEBUG_WX
 	select ARCH_HAS_ZONE_DMA_SET if EXPERT
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
+	select ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE
 	select ARCH_MIGHT_HAVE_ACPI_PDC		if ACPI
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
@@ -2610,9 +2611,6 @@ config ARCH_HAS_ADD_PAGES
 	def_bool y
 	depends on ARCH_ENABLE_MEMORY_HOTPLUG
 
-config ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE
-	def_bool y
-
 menu "Power management and ACPI options"
 
 config ARCH_HIBERNATION_HEADER
mm/Kconfig +3 -0
index 5fe49c030961..721dc88423c7 100644
@@ -571,6 +571,9 @@ config MHP_MEMMAP_ON_MEMORY
 
 endif # MEMORY_HOTPLUG
 
+config ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE
+       bool
+
 # Heavily threaded applications may benefit from splitting the mm-wide
 # page_table_lock, so that faults on different parts of the user address
 # space can be handled with less contention: split it at this NR_CPUS.
Signature · 1 line
2.41.0
#2 lore raw

PATCH v8 2/6 mm/memory_hotplug: Allow memmap on memory hotplug request to fallback

In reply to Aneesh Kumar K.V

If not supported, fallback to not using memap on memmory. This avoids the need for callers to do the fallback.

---
 drivers/acpi/acpi_memhotplug.c |  3 +--
 include/linux/memory_hotplug.h |  3 ++-
 mm/memory_hotplug.c            | 13 ++++++-------
 3 files changed, 9 insertions(+), 10 deletions(-)
drivers/acpi/acpi_memhotplug.c +1 -2
index 24f662d8bd39..d0c1a71007d0 100644
@@ -211,8 +211,7 @@ static int acpi_memory_enable_device(struct acpi_memory_device *mem_device)
 		if (!info->length)
 			continue;
 
-		if (mhp_supports_memmap_on_memory(info->length))
-			mhp_flags |= MHP_MEMMAP_ON_MEMORY;
+		mhp_flags |= MHP_MEMMAP_ON_MEMORY;
 		result = __add_memory(mgid, info->start_addr, info->length,
 				      mhp_flags);
 
include/linux/memory_hotplug.h +2 -1
index 013c69753c91..7d2076583494 100644
@@ -97,6 +97,8 @@ typedef int __bitwise mhp_t;
  * To do so, we will use the beginning of the hot-added range to build
  * the page tables for the memmap array that describes the entire range.
  * Only selected architectures support it with SPARSE_VMEMMAP.
+ * This is only a hint, the core kernel can decide to not do this based on
+ * different alignment checks.
  */
 #define MHP_MEMMAP_ON_MEMORY   ((__force mhp_t)BIT(1))
 /*
@@ -354,7 +356,6 @@ extern struct zone *zone_for_pfn_range(int online_type, int nid,
 extern int arch_create_linear_mapping(int nid, u64 start, u64 size,
 				      struct mhp_params *params);
 void arch_remove_linear_mapping(u64 start, u64 size);
-extern bool mhp_supports_memmap_on_memory(unsigned long size);
 #endif /* CONFIG_MEMORY_HOTPLUG */
 
 #endif /* __LINUX_MEMORY_HOTPLUG_H */
mm/memory_hotplug.c +6 -7
index 7cfd13c91568..eca32ccd45cc 100644
@@ -1247,7 +1247,7 @@ static int online_memory_block(struct memory_block *mem, void *arg)
 	return device_online(&mem->dev);
 }
 
-bool mhp_supports_memmap_on_memory(unsigned long size)
+static bool mhp_supports_memmap_on_memory(unsigned long size)
 {
 	unsigned long nr_vmemmap_pages = size / PAGE_SIZE;
 	unsigned long vmemmap_size = nr_vmemmap_pages * sizeof(struct page);
@@ -1339,13 +1339,12 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
 	 * Self hosted memmap array
 	 */
 	if (mhp_flags & MHP_MEMMAP_ON_MEMORY) {
-		if (!mhp_supports_memmap_on_memory(size)) {
-			ret = -EINVAL;
-			goto error;
+		if (mhp_supports_memmap_on_memory(size)) {
+			mhp_altmap.free = PHYS_PFN(size);
+			mhp_altmap.base_pfn = PHYS_PFN(start);
+			params.altmap = &mhp_altmap;
 		}
-		mhp_altmap.free = PHYS_PFN(size);
-		mhp_altmap.base_pfn = PHYS_PFN(start);
-		params.altmap = &mhp_altmap;
+		/* fallback to not using altmap  */
 	}
 
 	/* call arch's memory hotadd */
Signature · 1 line
2.41.0
#3 lore raw

PATCH v8 3/6 mm/memory_hotplug: Allow architecture to override memmap on memory support check

In reply to Aneesh Kumar K.V

Some architectures would want different restrictions. Hence add an architecture-specific override.

The PMD_SIZE check is moved there.

---
 mm/memory_hotplug.c | 24 ++++++++++++++++++++----
 1 file changed, 20 insertions(+), 4 deletions(-)
mm/memory_hotplug.c +20 -4
index eca32ccd45cc..746cb7c08c64 100644
@@ -1247,10 +1247,26 @@ static int online_memory_block(struct memory_block *mem, void *arg)
 	return device_online(&mem->dev);
 }
 
+static inline unsigned long memory_block_memmap_size(void)
+{
+	return PHYS_PFN(memory_block_size_bytes()) * sizeof(struct page);
+}
+
+#ifndef arch_supports_memmap_on_memory
+static inline bool arch_supports_memmap_on_memory(unsigned long vmemmap_size)
+{
+	/*
+	 * As default, we want the vmemmap to span a complete PMD such that we
+	 * can map the vmemmap using a single PMD if supported by the
+	 * architecture.
+	 */
+	return IS_ALIGNED(vmemmap_size, PMD_SIZE);
+}
+#endif
+
 static bool mhp_supports_memmap_on_memory(unsigned long size)
 {
-	unsigned long nr_vmemmap_pages = size / PAGE_SIZE;
-	unsigned long vmemmap_size = nr_vmemmap_pages * sizeof(struct page);
+	unsigned long vmemmap_size = memory_block_memmap_size();
 	unsigned long remaining_size = size - vmemmap_size;
 
 	/*
@@ -1281,8 +1297,8 @@ static bool mhp_supports_memmap_on_memory(unsigned long size)
 	 */
 	return mhp_memmap_on_memory() &&
 	       size == memory_block_size_bytes() &&
-	       IS_ALIGNED(vmemmap_size, PMD_SIZE) &&
-	       IS_ALIGNED(remaining_size, (pageblock_nr_pages << PAGE_SHIFT));
+	       IS_ALIGNED(remaining_size, (pageblock_nr_pages << PAGE_SHIFT)) &&
+	       arch_supports_memmap_on_memory(vmemmap_size);
 }
 
 /*
Signature · 1 line
2.41.0
#4 lore raw

PATCH v8 4/6 mm/memory_hotplug: Support memmap_on_memory when memmap is not aligned to pageblocks

In reply to Aneesh Kumar K.V

Currently, memmap_on_memory feature is only supported with memory block sizes that result in vmemmap pages covering full page blocks. This is because memory onlining/offlining code requires applicable ranges to be pageblock-aligned, for example, to set the migratetypes properly.

This patch helps to lift that restriction by reserving more pages than required for vmemmap space. This helps the start address to be page block aligned with different memory block sizes. Using this facility implies the kernel will be reserving some pages for every memoryblock. This allows the memmap on memory feature to be widely useful with different memory block size values.

For ex: with 64K page size and 256MiB memory block size, we require 4 pages to map vmemmap pages, To align things correctly we end up adding a reserve of 28 pages. ie, for every 4096 pages 28 pages get reserved.

---
 .../admin-guide/mm/memory-hotplug.rst         |  12 ++
 mm/memory_hotplug.c                           | 120 +++++++++++++++---
 2 files changed, 113 insertions(+), 19 deletions(-)
Documentation/admin-guide/mm/memory-hotplug.rst +12 -0
index bd77841041af..2994958c7ce8 100644
@@ -433,6 +433,18 @@ The following module parameters are currently defined:
 				 memory in a way that huge pages in bigger
 				 granularity cannot be formed on hotplugged
 				 memory.
+
+				 With value "force" it could result in memory
+				 wastage due to memmap size limitations. For
+				 example, if the memmap for a memory block
+				 requires 1 MiB, but the pageblock size is 2
+				 MiB, 1 MiB of hotplugged memory will be wasted.
+				 Note that there are still cases where the
+				 feature cannot be enforced: for example, if the
+				 memmap is smaller than a single page, or if the
+				 architecture does not support the forced mode
+				 in all configurations.
+
 ``online_policy``		 read-write: Set the basic policy used for
 				 automatic zone selection when onlining memory
 				 blocks without specifying a target zone.
mm/memory_hotplug.c +101 -19

175 lines not on this page · raw message

Signature · 1 line
2.41.0
#5 lore raw

PATCH v8 5/6 powerpc/book3s64/memhotplug: Enable memmap on memory for radix

In reply to Aneesh Kumar K.V

Radix vmemmap mapping can map things correctly at the PMD level or PTE level based on different device boundary checks. Hence we skip the restrictions w.r.t vmemmap size to be multiple of PMD_SIZE. This also makes the feature widely useful because to use PMD_SIZE vmemmap area we require a memory block size of 2GiB

We can also use MHP_RESERVE_PAGES_MEMMAP_ON_MEMORY to that the feature can work with a memory block size of 256MB. Using altmap.reserve feature to align things correctly at pageblock granularity. We can end up losing some pages in memory with this. For ex: with a 256MiB memory block size, we require 4 pages to map vmemmap pages, In order to align things correctly we end up adding a reserve of 28 pages. ie, for every 4096 pages 28 pages get reserved.

---
 arch/powerpc/Kconfig                          |  1 +
 arch/powerpc/include/asm/pgtable.h            | 21 +++++++++++++++++++
 .../platforms/pseries/hotplug-memory.c        |  2 +-
 3 files changed, 23 insertions(+), 1 deletion(-)
arch/powerpc/Kconfig +1 -0
index d0497d13f5b4..938294c996dc 100644
@@ -157,6 +157,7 @@ config PPC
 	select ARCH_HAS_UBSAN_SANITIZE_ALL
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select ARCH_KEEP_MEMBLOCK
+	select ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE	if PPC_RADIX_MMU
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
 	select ARCH_OPTIONAL_KERNEL_RWX		if ARCH_HAS_STRICT_KERNEL_RWX
arch/powerpc/include/asm/pgtable.h +21 -0
index a4893b17705a..33464e6d6431 100644
@@ -161,6 +161,27 @@ static inline pgtable_t pmd_pgtable(pmd_t pmd)
 int __meminit vmemmap_populated(unsigned long vmemmap_addr, int vmemmap_map_size);
 bool altmap_cross_boundary(struct vmem_altmap *altmap, unsigned long start,
 			   unsigned long page_size);
+/*
+ * mm/memory_hotplug.c:mhp_supports_memmap_on_memory goes into details
+ * some of the restrictions. We don't check for PMD_SIZE because our
+ * vmemmap allocation code can fallback correctly. The pageblock
+ * alignment requirement is met using altmap->reserve blocks.
+ */
+#define arch_supports_memmap_on_memory arch_supports_memmap_on_memory
+static inline bool arch_supports_memmap_on_memory(unsigned long vmemmap_size)
+{
+	if (!radix_enabled())
+		return false;
+	/*
+	 * With 4K page size and 2M PMD_SIZE, we can align
+	 * things better with memory block size value
+	 * starting from 128MB. Hence align things with PMD_SIZE.
+	 */
+	if (IS_ENABLED(CONFIG_PPC_4K_PAGES))
+		return IS_ALIGNED(vmemmap_size, PMD_SIZE);
+	return true;
+}
+
 #endif /* CONFIG_PPC64 */
 
 #endif /* __ASSEMBLY__ */
arch/powerpc/platforms/pseries/hotplug-memory.c +1 -1
index 9c62c2c3b3d0..4f3d6a2f9065 100644
@@ -637,7 +637,7 @@ static int dlpar_add_lmb(struct drmem_lmb *lmb)
 		nid = first_online_node;
 
 	/* Add the memory */
-	rc = __add_memory(nid, lmb->base_addr, block_sz, MHP_NONE);
+	rc = __add_memory(nid, lmb->base_addr, block_sz, MHP_MEMMAP_ON_MEMORY);
 	if (rc) {
 		invalidate_lmb_associativity_index(lmb);
 		return rc;
Signature · 1 line
2.41.0
#6 lore raw

PATCH v8 6/6 mm/memory_hotplug: Embed vmem_altmap details in memory block

In reply to Aneesh Kumar K.V

With memmap on memory, some architecture needs more details w.r.t altmap such as base_pfn, end_pfn, etc to unmap vmemmap memory. Instead of computing them again when we remove a memory block, embed vmem_altmap details in struct memory_block if we are using memmap on memory block feature.

---
 drivers/base/memory.c  | 27 +++++++++++++--------
 include/linux/memory.h |  8 ++-----
 mm/memory_hotplug.c    | 54 ++++++++++++++++++++++++++----------------
 3 files changed, 52 insertions(+), 37 deletions(-)
drivers/base/memory.c +17 -10
index b456ac213610..8191709c9ad2 100644
@@ -105,7 +105,8 @@ EXPORT_SYMBOL(unregister_memory_notifier);
 static void memory_block_release(struct device *dev)
 {
 	struct memory_block *mem = to_memory_block(dev);
-
+	/* Verify that the altmap is freed */
+	WARN_ON(mem->altmap);
 	kfree(mem);
 }
 
@@ -183,7 +184,7 @@ static int memory_block_online(struct memory_block *mem)
 {
 	unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr);
 	unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block;
-	unsigned long nr_vmemmap_pages = mem->nr_vmemmap_pages;
+	unsigned long nr_vmemmap_pages = 0;
 	struct zone *zone;
 	int ret;
 
@@ -200,6 +201,9 @@ static int memory_block_online(struct memory_block *mem)
 	 * stage helps to keep accounting easier to follow - e.g vmemmaps
 	 * belong to the same zone as the memory they backed.
 	 */
+	if (mem->altmap)
+		nr_vmemmap_pages = mem->altmap->free;
+
 	if (nr_vmemmap_pages) {
 		ret = mhp_init_memmap_on_memory(start_pfn, nr_vmemmap_pages, zone);
 		if (ret)
@@ -230,7 +234,7 @@ static int memory_block_offline(struct memory_block *mem)
 {
 	unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr);
 	unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block;
-	unsigned long nr_vmemmap_pages = mem->nr_vmemmap_pages;
+	unsigned long nr_vmemmap_pages = 0;
 	int ret;
 
 	if (!mem->zone)
@@ -240,6 +244,9 @@ static int memory_block_offline(struct memory_block *mem)
 	 * Unaccount before offlining, such that unpopulated zone and kthreads
 	 * can properly be torn down in offline_pages().
 	 */
+	if (mem->altmap)
+		nr_vmemmap_pages = mem->altmap->free;
+
 	if (nr_vmemmap_pages)
 		adjust_present_page_count(pfn_to_page(start_pfn), mem->group,
 					  -nr_vmemmap_pages);
@@ -726,7 +733,7 @@ void memory_block_add_nid(struct memory_block *mem, int nid,
 #endif
 
 static int add_memory_block(unsigned long block_id, unsigned long state,
-			    unsigned long nr_vmemmap_pages,
+			    struct vmem_altmap *altmap,
 			    struct memory_group *group)
 {
 	struct memory_block *mem;
@@ -744,7 +751,7 @@ static int add_memory_block(unsigned long block_id, unsigned long state,
 	mem->start_section_nr = block_id * sections_per_block;
 	mem->state = state;
 	mem->nid = NUMA_NO_NODE;
-	mem->nr_vmemmap_pages = nr_vmemmap_pages;
+	mem->altmap = altmap;
 	INIT_LIST_HEAD(&mem->group_next);
 
 #ifndef CONFIG_NUMA
@@ -783,14 +790,14 @@ static int __init add_boot_memory_block(unsigned long base_section_nr)
 	if (section_count == 0)
 		return 0;
 	return add_memory_block(memory_block_id(base_section_nr),
-				MEM_ONLINE, 0,  NULL);
+				MEM_ONLINE, NULL,  NULL);
 }
 
 static int add_hotplug_memory_block(unsigned long block_id,
-				    unsigned long nr_vmemmap_pages,
+				    struct vmem_altmap *altmap,
 				    struct memory_group *group)
 {
-	return add_memory_block(block_id, MEM_OFFLINE, nr_vmemmap_pages, group);
+	return add_memory_block(block_id, MEM_OFFLINE, altmap, group);
 }
 
 static void remove_memory_block(struct memory_block *memory)
@@ -818,7 +825,7 @@ static void remove_memory_block(struct memory_block *memory)
  * Called under device_hotplug_lock.
  */
 int create_memory_block_devices(unsigned long start, unsigned long size,
-				unsigned long vmemmap_pages,
+				struct vmem_altmap *altmap,
 				struct memory_group *group)
 {
 	const unsigned long start_block_id = pfn_to_block_id(PFN_DOWN(start));
@@ -832,7 +839,7 @@ int create_memory_block_devices(unsigned long start, unsigned long size,
 		return -EINVAL;
 
 	for (block_id = start_block_id; block_id != end_block_id; block_id++) {
-		ret = add_hotplug_memory_block(block_id, vmemmap_pages, group);
+		ret = add_hotplug_memory_block(block_id, altmap, group);
 		if (ret)
 			break;
 	}
include/linux/memory.h +2 -6
index 31343566c221..f53cfdaaaa41 100644
@@ -77,11 +77,7 @@ struct memory_block {
 	 */
 	struct zone *zone;
 	struct device dev;
-	/*
-	 * Number of vmemmap pages. These pages
-	 * lay at the beginning of the memory block.
-	 */
-	unsigned long nr_vmemmap_pages;
+	struct vmem_altmap *altmap;
 	struct memory_group *group;	/* group (if any) for this block */
 	struct list_head group_next;	/* next block inside memory group */
 #if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_MEMORY_HOTPLUG)
@@ -147,7 +143,7 @@ static inline int hotplug_memory_notifier(notifier_fn_t fn, int pri)
 extern int register_memory_notifier(struct notifier_block *nb);
 extern void unregister_memory_notifier(struct notifier_block *nb);
 int create_memory_block_devices(unsigned long start, unsigned long size,
-				unsigned long vmemmap_pages,
+				struct vmem_altmap *altmap,
 				struct memory_group *group);
 void remove_memory_block_devices(unsigned long start, unsigned long size);
 extern void memory_dev_init(void);
mm/memory_hotplug.c +33 -21

112 lines not on this page · raw message

Signature · 1 line
2.41.0