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.
Cc: Andrew Morton <[email protected]>
Cc: David Hildenbrand <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: Oscar Salvador <[email protected]>
Cc: Dan Williams <[email protected]>
Cc: Dave Jiang <[email protected]>
Cc: Dave Hansen <[email protected]>
Cc: Huang Ying <[email protected]>
Suggested-by: David Hildenbrand <[email protected]>
Signed-off-by: Vishal Verma <[email protected]>
---
mm/memory_hotplug.c | 165 +++++++++++++++++++++++++++++++---------------------
1 file changed, 100 insertions(+), 65 deletions(-)
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index f8d3e7427e32..43dbd71a4910 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1380,6 +1380,44 @@ static bool mhp_supports_memmap_on_memory(unsigned long size)
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_memory(unsigned long size)
*/
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;
@@ -1436,28 +1470,21 @@ 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)) {
- mhp_altmap.free = memory_block_memmap_on_memory_pages();
- params.altmap = kmalloc(sizeof(struct vmem_altmap), GFP_KERNEL);
- if (!params.altmap)
+ 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) {
@@ -1494,8 +1521,6 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
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);
@@ -2146,47 +2171,20 @@ 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 */
@@ -2219,6 +2217,43 @@ static int __ref try_remove_memory(u64 start, u64 size)
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;
}
--
2.41.0
> +
> +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;
> }
Why is the firmware, memblock and nid handling not kept in this outer
function?
We really shouldn't be doing per memory block what needs to be done per
memblock: remove_memory_block_devices() and arch_remove_memory().
--
Cheers,
David / dhildenb
On Mon, 2023-10-02 at 11:28 +0200, David Hildenbrand wrote:
>
> > +
> > +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;
> > }
>
> Why is the firmware, memblock and nid handling not kept in this outer
> function?
>
> We really shouldn't be doing per memory block what needs to be done per
> memblock: remove_memory_block_devices() and arch_remove_memory().
Ah yes makes sense since we only do create_memory_block_devices() and
arch_add_memory() in the per memory block inner loop during addition.
How should the locking work in this case though?
The original code holds the mem_hotplug_begin() lock over
arch_remove_memory() and all of the nid and memblock stuff. Should I
just hold the lock and release it in the inner loop for each memory
block, and then also acquire and release it separately for the memblock
and nid stuff in the outer function?
Here's the incremental diff for what I'm thinking:
---
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 43dbd71a4910..13380178173d 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -2171,7 +2171,7 @@ void try_offline_node(int nid)
}
EXPORT_SYMBOL(try_offline_node);
-static void __ref __try_remove_memory(int nid, u64 start, u64 size)
+static void __ref remove_memory_block_and_altmap(int nid, u64 start, u64 size)
{
int rc = 0;
struct memory_block *mem;
@@ -2187,9 +2187,6 @@ static void __ref __try_remove_memory(int nid, u64 start, u64 size)
mem->altmap = NULL;
}
- /* remove memmap entry */
- firmware_map_remove(start, start + size, "System RAM");
-
/*
* Memory block device removal under the device_hotplug_lock is
* a barrier against racing online attempts.
@@ -2206,16 +2203,6 @@ static void __ref __try_remove_memory(int nid, u64 start, u64 size)
kfree(altmap);
}
- if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK)) {
- memblock_phys_free(start, size);
- memblock_remove(start, size);
- }
-
- release_mem_region_adjustable(start, size);
-
- if (nid != NUMA_NO_NODE)
- try_offline_node(nid);
-
mem_hotplug_done();
}
@@ -2249,11 +2236,29 @@ static int __ref try_remove_memory(u64 start, u64 size)
for (cur_start = start; cur_start < start + size;
cur_start += memblock_size)
- __try_remove_memory(nid, cur_start, memblock_size);
+ remove_memory_block_and_altmap(nid, cur_start,
+ memblock_size);
} else {
- __try_remove_memory(nid, start, size);
+ remove_memory_block_and_altmap(nid, start, size);
}
+ /* remove memmap entry */
+ firmware_map_remove(start, start + size, "System RAM");
+
+ mem_hotplug_begin();
+
+ if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK)) {
+ memblock_phys_free(start, size);
+ memblock_remove(start, size);
+ }
+
+ release_mem_region_adjustable(start, size);
+
+ if (nid != NUMA_NO_NODE)
+ try_offline_node(nid);
+
+ mem_hotplug_done();
+
return 0;
}
On 03.10.23 22:03, Verma, Vishal L wrote:
> On Mon, 2023-10-02 at 11:28 +0200, David Hildenbrand wrote:
>>
>>> +
>>> +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;
>>> }
>>
>> Why is the firmware, memblock and nid handling not kept in this outer
>> function?
>>
>> We really shouldn't be doing per memory block what needs to be done per
>> memblock: remove_memory_block_devices() and arch_remove_memory().
>
>
> Ah yes makes sense since we only do create_memory_block_devices() and
> arch_add_memory() in the per memory block inner loop during addition.
>
> How should the locking work in this case though?
Sorry, I had to process a family NMI the last couple of days.
>
> The original code holds the mem_hotplug_begin() lock over
> arch_remove_memory() and all of the nid and memblock stuff. Should I
> just hold the lock and release it in the inner loop for each memory
> block, and then also acquire and release it separately for the memblock
> and nid stuff in the outer function?
I think we have to hold it over the whole operation.
I saw that you sent a v5, I'll comment there.
--
Cheers,
David / dhildenb