The quilt patch titled
Subject: mm/memory_hotplug: split memmap_on_memory requests across memblocks
has been removed from the -mm tree. Its filename was
mm-memory_hotplug-split-memmap_on_memory-requests-across-memblocks.patch
This patch was dropped because an updated version will be merged
------------------------------------------------------
From: Vishal Verma <vishal.l.verma@xxxxxxxxx>
Subject: mm/memory_hotplug: split memmap_on_memory requests across memblocks
Date: Thu, 28 Sep 2023 14:30:10 -0600
Patch series "mm: use memmap_on_memory semantics for dax/kmem", v4.
The dax/kmem driver can potentially hot-add large amounts of memory
originating from CXL memory expanders, or NVDIMMs, or other 'device
memories'. There is a chance there isn't enough regular system memory
available to fit the memmap for this new memory. It's therefore
desirable, if all other conditions are met, for the kmem managed memory to
place its memmap on the newly added memory itself.
The main hurdle for accomplishing this for kmem is that memmap_on_memory
can only be done if the memory being added is equal to the size of one
memblock. To overcome this, allow the hotplug code to split an
add_memory() request into memblock-sized chunks, and try_remove_memory()
to also expect and handle such a scenario.
Patch 1 teaches the memory_hotplug code to allow for splitting
add_memory() and remove_memory() requests over memblock sized chunks.
Patch 2 adds a sysfs control for the kmem driver that would allow an
opt-out of using memmap_on_memory for the memory being added.
This patch (of 2):
The MHP_MEMMAP_ON_MEMORY flag for hotplugged memory is restricted to
'memblock_size' chunks of memory being added. Adding a larger span of
memory precludes memmap_on_memory semantics.
For users of hotplug such as kmem, large amounts of memory might get added
from the CXL subsystem. In some cases, this amount may exceed the
available 'main memory' to store the memmap for the memory being added.
In this case, it is useful to have a way to place the memmap on the memory
being added, even if it means splitting the addition into memblock-sized
chunks.
Change add_memory_resource() to loop over memblock-sized chunks of memory
if caller requested memmap_on_memory, and if other conditions for it are
met. Teach try_remove_memory() to also expect that a memory range being
removed might have been split up into memblock sized chunks, and to loop
through those as needed.
Link: https://lkml.kernel.org/r/20230928-vv-kmem_memmap-v4-0-6ff73fec519a@xxxxxxxxx
Link: https://lkml.kernel.org/r/20230928-vv-kmem_memmap-v4-1-6ff73fec519a@xxxxxxxxx
Signed-off-by: Vishal Verma <vishal.l.verma@xxxxxxxxx>
Suggested-by: David Hildenbrand <david@xxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxx>
Cc: Oscar Salvador <osalvador@xxxxxxx>
Cc: Dan Williams <dan.j.williams@xxxxxxxxx>
Cc: Dave Jiang <dave.jiang@xxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
Cc: Huang Ying <ying.huang@xxxxxxxxx>
Cc: Aneesh Kumar K.V <aneesh.kumar@xxxxxxxxxxxxx>
Cc: Jeff Moyer <jmoyer@xxxxxxxxxx>
Cc: Jonathan Cameron <Jonathan.Cameron@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/memory_hotplug.c | 166 +++++++++++++++++++++++++-----------------
1 file changed, 100 insertions(+), 66 deletions(-)
--- a/mm/memory_hotplug.c~mm-memory_hotplug-split-memmap_on_memory-requests-across-memblocks
+++ a/mm/memory_hotplug.c
@@ -1380,6 +1380,44 @@ static bool mhp_supports_memmap_on_memor
return arch_supports_memmap_on_memory(vmemmap_size);
}
+static int add_memory_create_devices(int nid, struct memory_group *group,
+ u64 start, u64 size, mhp_t mhp_flags)
+{
+ struct mhp_params params = { .pgprot = pgprot_mhp(PAGE_KERNEL) };
+ struct vmem_altmap mhp_altmap = {
+ .base_pfn = PHYS_PFN(start),
+ .end_pfn = PHYS_PFN(start + size - 1),
+ };
+ int ret;
+
+ if ((mhp_flags & MHP_MEMMAP_ON_MEMORY)) {
+ mhp_altmap.free = memory_block_memmap_on_memory_pages();
+ params.altmap = kmalloc(sizeof(struct vmem_altmap), GFP_KERNEL);
+ if (!params.altmap)
+ return -ENOMEM;
+
+ memcpy(params.altmap, &mhp_altmap, sizeof(mhp_altmap));
+ }
+
+ /* call arch's memory hotadd */
+ ret = arch_add_memory(nid, start, size, ¶ms);
+ if (ret < 0)
+ goto error;
+
+ /* create memory block devices after memory was added */
+ ret = create_memory_block_devices(start, size, params.altmap, group);
+ if (ret)
+ goto err_bdev;
+
+ return 0;
+
+err_bdev:
+ arch_remove_memory(start, size, NULL);
+error:
+ kfree(params.altmap);
+ return ret;
+}
+
/*
* NOTE: The caller must call lock_device_hotplug() to serialize hotplug
* and online/offline operations (triggered e.g. by sysfs).
@@ -1388,14 +1426,10 @@ static bool mhp_supports_memmap_on_memor
*/
int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
{
- struct mhp_params params = { .pgprot = pgprot_mhp(PAGE_KERNEL) };
+ unsigned long memblock_size = memory_block_size_bytes();
enum memblock_flags memblock_flags = MEMBLOCK_NONE;
- struct vmem_altmap mhp_altmap = {
- .base_pfn = PHYS_PFN(res->start),
- .end_pfn = PHYS_PFN(res->end),
- };
struct memory_group *group = NULL;
- u64 start, size;
+ u64 start, size, cur_start;
bool new_node = false;
int ret;
@@ -1436,30 +1470,22 @@ int __ref add_memory_resource(int nid, s
/*
* Self hosted memmap array
*/
- if (mhp_flags & MHP_MEMMAP_ON_MEMORY) {
- if (mhp_supports_memmap_on_memory(size)) {
- mhp_altmap.free = memory_block_memmap_on_memory_pages();
- params.altmap = kmalloc(sizeof(struct vmem_altmap), GFP_KERNEL);
- if (!params.altmap) {
- ret = -ENOMEM;
+ if ((mhp_flags & MHP_MEMMAP_ON_MEMORY) &&
+ mhp_supports_memmap_on_memory(memblock_size)) {
+ for (cur_start = start; cur_start < start + size;
+ cur_start += memblock_size) {
+ ret = add_memory_create_devices(nid, group, cur_start,
+ memblock_size,
+ mhp_flags);
+ if (ret)
goto error;
- }
-
- memcpy(params.altmap, &mhp_altmap, sizeof(mhp_altmap));
}
/* fallback to not using altmap */
- }
-
- /* call arch's memory hotadd */
- ret = arch_add_memory(nid, start, size, ¶ms);
- if (ret < 0)
- goto error_free;
-
- /* create memory block devices after memory was added */
- ret = create_memory_block_devices(start, size, params.altmap, group);
- if (ret) {
- arch_remove_memory(start, size, NULL);
- goto error_free;
+ } else {
+ ret = add_memory_create_devices(nid, group, start, size,
+ mhp_flags);
+ if (ret)
+ goto error;
}
if (new_node) {
@@ -1496,8 +1522,6 @@ int __ref add_memory_resource(int nid, s
walk_memory_blocks(start, size, NULL, online_memory_block);
return ret;
-error_free:
- kfree(params.altmap);
error:
if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK))
memblock_remove(start, size);
@@ -2148,47 +2172,20 @@ void try_offline_node(int nid)
}
EXPORT_SYMBOL(try_offline_node);
-static int __ref try_remove_memory(u64 start, u64 size)
+static void __ref __try_remove_memory(int nid, u64 start, u64 size)
{
+ int rc = 0;
struct memory_block *mem;
- int rc = 0, nid = NUMA_NO_NODE;
struct vmem_altmap *altmap = NULL;
- BUG_ON(check_hotplug_memory_range(start, size));
-
- /*
- * All memory blocks must be offlined before removing memory. Check
- * whether all memory blocks in question are offline and return error
- * if this is not the case.
- *
- * While at it, determine the nid. Note that if we'd have mixed nodes,
- * we'd only try to offline the last determined one -- which is good
- * enough for the cases we care about.
- */
- rc = walk_memory_blocks(start, size, &nid, check_memblock_offlined_cb);
- if (rc)
- return rc;
-
- /*
- * We only support removing memory added with MHP_MEMMAP_ON_MEMORY in
- * the same granularity it was added - a single memory block.
- */
- if (mhp_memmap_on_memory()) {
- rc = walk_memory_blocks(start, size, &mem, test_has_altmap_cb);
- if (rc) {
- if (size != memory_block_size_bytes()) {
- pr_warn("Refuse to remove %#llx - %#llx,"
- "wrong granularity\n",
- start, start + size);
- return -EINVAL;
- }
- altmap = mem->altmap;
- /*
- * Mark altmap NULL so that we can add a debug
- * check on memblock free.
- */
- mem->altmap = NULL;
- }
+ rc = walk_memory_blocks(start, size, &mem, test_has_altmap_cb);
+ if (rc) {
+ altmap = mem->altmap;
+ /*
+ * Mark altmap NULL so that we can add a debug
+ * check on memblock free.
+ */
+ mem->altmap = NULL;
}
/* remove memmap entry */
@@ -2221,6 +2218,43 @@ static int __ref try_remove_memory(u64 s
try_offline_node(nid);
mem_hotplug_done();
+}
+
+static int __ref try_remove_memory(u64 start, u64 size)
+{
+ int rc, nid = NUMA_NO_NODE;
+
+ BUG_ON(check_hotplug_memory_range(start, size));
+
+ /*
+ * All memory blocks must be offlined before removing memory. Check
+ * whether all memory blocks in question are offline and return error
+ * if this is not the case.
+ *
+ * While at it, determine the nid. Note that if we'd have mixed nodes,
+ * we'd only try to offline the last determined one -- which is good
+ * enough for the cases we care about.
+ */
+ rc = walk_memory_blocks(start, size, &nid, check_memblock_offlined_cb);
+ if (rc)
+ return rc;
+
+ /*
+ * For memmap_on_memory, the altmaps could have been added on
+ * a per-memblock basis. Loop through the entire range if so,
+ * and remove each memblock and its altmap.
+ */
+ if (mhp_memmap_on_memory()) {
+ unsigned long memblock_size = memory_block_size_bytes();
+ u64 cur_start;
+
+ for (cur_start = start; cur_start < start + size;
+ cur_start += memblock_size)
+ __try_remove_memory(nid, cur_start, memblock_size);
+ } else {
+ __try_remove_memory(nid, start, size);
+ }
+
return 0;
}
_
Patches currently in -mm which might be from vishal.l.verma@xxxxxxxxx are
dax-kmem-allow-kmem-to-add-memory-with-memmap_on_memory.patch
