From 9a21d69f580d34f2605e2d6a9c08fc8e55ec247b Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Tue, 7 Sep 2021 19:55:09 -0700
Subject: [PATCH] mm/memory_hotplug: remove nid parameter from remove_memory()
and friends
References: git fixes (mm/hotplug)
Patch-mainline: v5.15-rc1
Git-commit: e1c158e4956612e7bada4c03dfb99210af4d6cde
There is only a single user remaining. We can simply lookup the nid only
used for node offlining purposes when walking our memory blocks. We don't
expect to remove multi-nid ranges; and if we'd ever do, we most probably
don't care about removing multi-nid ranges that actually result in empty
nodes.
If ever required, we can detect the "multi-nid" scenario and simply try
offlining all online nodes.
Link: https://lkml.kernel.org/r/20210712124052.26491-4-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Acked-by: Michael Ellerman <mpe@ellerman.id.au> (powerpc)
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Len Brown <lenb@kernel.org>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Nathan Lynch <nathanl@linux.ibm.com>
Cc: Laurent Dufour <ldufour@linux.ibm.com>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Cc: Scott Cheloha <cheloha@linux.ibm.com>
Cc: Anton Blanchard <anton@ozlabs.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Baoquan He <bhe@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Christophe Leroy <christophe.leroy@c-s.fr>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jia He <justin.he@arm.com>
Cc: Joe Perches <joe@perches.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Michel Lespinasse <michel@lespinasse.org>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Pankaj Gupta <pankaj.gupta@ionos.com>
Cc: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Pierre Morel <pmorel@linux.ibm.com>
Cc: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Cc: Rich Felker <dalias@libc.org>
Cc: Sergei Trofimovich <slyfox@gentoo.org>
Cc: Thiago Jung Bauermann <bauerman@linux.ibm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Vitaly Kuznetsov <vkuznets@redhat.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Wei Yang <richard.weiyang@linux.alibaba.com>
Cc: Will Deacon <will@kernel.org>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
arch/powerpc/platforms/pseries/hotplug-memory.c | 9 ++++----
drivers/acpi/acpi_memhotplug.c | 7 +------
drivers/dax/kmem.c | 3 +--
drivers/virtio/virtio_mem.c | 4 ++--
include/linux/memory_hotplug.h | 10 ++++-----
mm/memory_hotplug.c | 28 +++++++++++++++----------
6 files changed, 30 insertions(+), 31 deletions(-)
diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c
index d4f28ee4d5dc..533cb1335b7f 100644
--- a/arch/powerpc/platforms/pseries/hotplug-memory.c
+++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
@@ -284,7 +284,7 @@ static int pseries_remove_memblock(unsigned long base, unsigned long memblock_si
{
unsigned long block_sz, start_pfn;
int sections_per_block;
- int i, nid;
+ int i;
start_pfn = base >> PAGE_SHIFT;
@@ -295,10 +295,9 @@ static int pseries_remove_memblock(unsigned long base, unsigned long memblock_si
block_sz = pseries_memory_block_size();
sections_per_block = block_sz / MIN_MEMORY_BLOCK_SIZE;
- nid = memory_add_physaddr_to_nid(base);
for (i = 0; i < sections_per_block; i++) {
- __remove_memory(nid, base, MIN_MEMORY_BLOCK_SIZE);
+ __remove_memory(base, MIN_MEMORY_BLOCK_SIZE);
base += MIN_MEMORY_BLOCK_SIZE;
}
@@ -385,7 +384,7 @@ static int dlpar_remove_lmb(struct drmem_lmb *lmb)
block_sz = pseries_memory_block_size();
- __remove_memory(mem_block->nid, lmb->base_addr, block_sz);
+ __remove_memory(lmb->base_addr, block_sz);
put_device(&mem_block->dev);
/* Update memory regions for memory remove */
@@ -658,7 +657,7 @@ static int dlpar_add_lmb(struct drmem_lmb *lmb)
rc = dlpar_online_lmb(lmb);
if (rc) {
- __remove_memory(nid, lmb->base_addr, block_sz);
+ __remove_memory(lmb->base_addr, block_sz);
invalidate_lmb_associativity_index(lmb);
} else {
lmb->flags |= DRCONF_MEM_ASSIGNED;
diff --git a/drivers/acpi/acpi_memhotplug.c b/drivers/acpi/acpi_memhotplug.c
index 8cc195c4c861..1d01d9414c40 100644
--- a/drivers/acpi/acpi_memhotplug.c
+++ b/drivers/acpi/acpi_memhotplug.c
@@ -239,19 +239,14 @@ static int acpi_memory_enable_device(struct acpi_memory_device *mem_device)
static void acpi_memory_remove_memory(struct acpi_memory_device *mem_device)
{
- acpi_handle handle = mem_device->device->handle;
struct acpi_memory_info *info, *n;
- int nid = acpi_get_node(handle);
list_for_each_entry_safe(info, n, &mem_device->res_list, list) {
if (!info->enabled)
continue;
- if (nid == NUMA_NO_NODE)
- nid = memory_add_physaddr_to_nid(info->start_addr);
-
acpi_unbind_memory_blocks(info);
- __remove_memory(nid, info->start_addr, info->length);
+ __remove_memory(info->start_addr, info->length);
list_del(&info->list);
kfree(info);
}
diff --git a/drivers/dax/kmem.c b/drivers/dax/kmem.c
index ac231cc36359..99e0f60c4c26 100644
--- a/drivers/dax/kmem.c
+++ b/drivers/dax/kmem.c
@@ -156,8 +156,7 @@ static void dev_dax_kmem_remove(struct dev_dax *dev_dax)
if (rc)
continue;
- rc = remove_memory(dev_dax->target_node, range.start,
- range_len(&range));
+ rc = remove_memory(range.start, range_len(&range));
if (rc == 0) {
release_resource(data->res[i]);
kfree(data->res[i]);
diff --git a/drivers/virtio/virtio_mem.c b/drivers/virtio/virtio_mem.c
index b91bc810a87e..7e83ed373e00 100644
--- a/drivers/virtio/virtio_mem.c
+++ b/drivers/virtio/virtio_mem.c
@@ -677,7 +677,7 @@ static int virtio_mem_remove_memory(struct virtio_mem *vm, uint64_t addr,
dev_dbg(&vm->vdev->dev, "removing memory: 0x%llx - 0x%llx\n", addr,
addr + size - 1);
- rc = remove_memory(vm->nid, addr, size);
+ rc = remove_memory(addr, size);
if (!rc) {
atomic64_sub(size, &vm->offline_size);
/*
@@ -720,7 +720,7 @@ static int virtio_mem_offline_and_remove_memory(struct virtio_mem *vm,
"offlining and removing memory: 0x%llx - 0x%llx\n", addr,
addr + size - 1);
- rc = offline_and_remove_memory(vm->nid, addr, size);
+ rc = offline_and_remove_memory(addr, size);
if (!rc) {
atomic64_sub(size, &vm->offline_size);
/*
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 010a192298b5..068e3dcf4690 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -292,9 +292,9 @@ static inline void pgdat_resize_init(struct pglist_data *pgdat) {}
extern void try_offline_node(int nid);
extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages);
-extern int remove_memory(int nid, u64 start, u64 size);
-extern void __remove_memory(int nid, u64 start, u64 size);
-extern int offline_and_remove_memory(int nid, u64 start, u64 size);
+extern int remove_memory(u64 start, u64 size);
+extern void __remove_memory(u64 start, u64 size);
+extern int offline_and_remove_memory(u64 start, u64 size);
#else
static inline void try_offline_node(int nid) {}
@@ -304,12 +304,12 @@ static inline int offline_pages(unsigned long start_pfn, unsigned long nr_pages)
return -EINVAL;
}
-static inline int remove_memory(int nid, u64 start, u64 size)
+static inline int remove_memory(u64 start, u64 size)
{
return -EBUSY;
}
-static inline void __remove_memory(int nid, u64 start, u64 size) {}
+static inline void __remove_memory(u64 start, u64 size) {}
#endif /* CONFIG_MEMORY_HOTREMOVE */
extern void set_zone_contiguous(struct zone *zone);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index da684e4c8742..2267a4cea2b6 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1746,7 +1746,9 @@ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages)
static int check_memblock_offlined_cb(struct memory_block *mem, void *arg)
{
int ret = !is_memblock_offlined(mem);
+ int *nid = arg;
+ *nid = mem->nid;
if (unlikely(ret)) {
phys_addr_t beginpa, endpa;
@@ -1839,12 +1841,12 @@ void try_offline_node(int nid)
}
EXPORT_SYMBOL(try_offline_node);
-static int __ref try_remove_memory(int nid, u64 start, u64 size)
+static int __ref try_remove_memory(u64 start, u64 size)
{
- int rc = 0;
struct vmem_altmap mhp_altmap = {};
struct vmem_altmap *altmap = NULL;
unsigned long nr_vmemmap_pages;
+ int rc = 0, nid = NUMA_NO_NODE;
BUG_ON(check_hotplug_memory_range(start, size));
@@ -1852,8 +1854,12 @@ static int __ref try_remove_memory(int nid, u64 start, u64 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, NULL, check_memblock_offlined_cb);
+ rc = walk_memory_blocks(start, size, &nid, check_memblock_offlined_cb);
if (rc)
return rc;
@@ -1902,7 +1908,8 @@ static int __ref try_remove_memory(int nid, u64 start, u64 size)
release_mem_region_adjustable(start, size);
- try_offline_node(nid);
+ if (nid != NUMA_NO_NODE)
+ try_offline_node(nid);
mem_hotplug_done();
return 0;
@@ -1910,7 +1917,6 @@ static int __ref try_remove_memory(int nid, u64 start, u64 size)
/**
* __remove_memory - Remove memory if every memory block is offline
- * @nid: the node ID
* @start: physical address of the region to remove
* @size: size of the region to remove
*
@@ -1918,14 +1924,14 @@ static int __ref try_remove_memory(int nid, u64 start, u64 size)
* and online/offline operations before this call, as required by
* try_offline_node().
*/
-void __remove_memory(int nid, u64 start, u64 size)
+void __remove_memory(u64 start, u64 size)
{
/*
* trigger BUG() if some memory is not offlined prior to calling this
* function
*/
- if (try_remove_memory(nid, start, size))
+ if (try_remove_memory(start, size))
BUG();
}
@@ -1933,12 +1939,12 @@ void __remove_memory(int nid, u64 start, u64 size)
* Remove memory if every memory block is offline, otherwise return -EBUSY is
* some memory is not offline
*/
-int remove_memory(int nid, u64 start, u64 size)
+int remove_memory(u64 start, u64 size)
{
int rc;
lock_device_hotplug();
- rc = try_remove_memory(nid, start, size);
+ rc = try_remove_memory(start, size);
unlock_device_hotplug();
return rc;
@@ -1998,7 +2004,7 @@ static int try_reonline_memory_block(struct memory_block *mem, void *arg)
* unplugged all memory (so it's no longer in use) and want to offline + remove
* that memory.
*/
-int offline_and_remove_memory(int nid, u64 start, u64 size)
+int offline_and_remove_memory(u64 start, u64 size)
{
const unsigned long mb_count = size / memory_block_size_bytes();
uint8_t *online_types, *tmp;
@@ -2034,7 +2040,7 @@ int offline_and_remove_memory(int nid, u64 start, u64 size)
* This cannot fail as it cannot get onlined in the meantime.
*/
if (!rc) {
- rc = try_remove_memory(nid, start, size);
+ rc = try_remove_memory(start, size);
if (rc)
pr_err("%s: Failed to remove memory: %d", __func__, rc);
}