Michael Ellerman
2021-Jun-08 11:11 UTC
[PATCH v1 05/12] mm/memory_hotplug: remove nid parameter from remove_memory() and friends
David Hildenbrand <david at redhat.com> writes:> There is only a single user remaining. We can simply try to offline all > online nodes - which is fast, because we usually span pages and can skip > such nodes right away.That makes me slightly nervous, because our big powerpc boxes tend to trip on these scaling issues before others. But the spanned pages check is just: void try_offline_node(int nid) { pg_data_t *pgdat = NODE_DATA(nid); ... if (pgdat->node_spanned_pages) return; So I guess that's pretty cheap, and it's only O(nodes), which should never get that big.> Cc: Michael Ellerman <mpe at ellerman.id.au> > Cc: Benjamin Herrenschmidt <benh at kernel.crashing.org> > Cc: Paul Mackerras <paulus at samba.org> > Cc: "Rafael J. Wysocki" <rjw at rjwysocki.net> > Cc: Len Brown <lenb at kernel.org> > Cc: Dan Williams <dan.j.williams at intel.com> > Cc: Vishal Verma <vishal.l.verma at intel.com> > Cc: Dave Jiang <dave.jiang at intel.com> > Cc: "Michael S. Tsirkin" <mst at redhat.com> > Cc: Jason Wang <jasowang at redhat.com> > Cc: Andrew Morton <akpm at linux-foundation.org> > Cc: Nathan Lynch <nathanl at linux.ibm.com> > Cc: Laurent Dufour <ldufour at linux.ibm.com> > Cc: "Aneesh Kumar K.V" <aneesh.kumar at linux.ibm.com> > Cc: Scott Cheloha <cheloha at linux.ibm.com> > Cc: Anton Blanchard <anton at ozlabs.org> > Cc: linuxppc-dev at lists.ozlabs.org > Cc: linux-acpi at vger.kernel.org > Cc: nvdimm at lists.linux.dev > Signed-off-by: David Hildenbrand <david at redhat.com> > --- > .../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 | 20 +++++++++---------- > 6 files changed, 23 insertions(+), 30 deletions(-) > > diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c > index 8377f1f7c78e..4a9232ddbefe 100644 > --- a/arch/powerpc/platforms/pseries/hotplug-memory.c > +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c > @@ -286,7 +286,7 @@ 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; > > @@ -297,10 +297,9 @@ 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; > } > > @@ -386,7 +385,7 @@ 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 */ > @@ -638,7 +637,7 @@ 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;Acked-by: Michael Ellerman <mpe at ellerman.id.au> (powerpc) cheers
David Hildenbrand
2021-Jun-08 11:18 UTC
[PATCH v1 05/12] mm/memory_hotplug: remove nid parameter from remove_memory() and friends
On 08.06.21 13:11, Michael Ellerman wrote:> David Hildenbrand <david at redhat.com> writes: >> There is only a single user remaining. We can simply try to offline all >> online nodes - which is fast, because we usually span pages and can skip >> such nodes right away. > > That makes me slightly nervous, because our big powerpc boxes tend to > trip on these scaling issues before others. > > But the spanned pages check is just: > > void try_offline_node(int nid) > { > pg_data_t *pgdat = NODE_DATA(nid); > ... > if (pgdat->node_spanned_pages) > return; > > So I guess that's pretty cheap, and it's only O(nodes), which should > never get that big.Exactly. And if it does turn out to be a problem, we can walk all memory blocks before removing them, collecting the nid(s). -- Thanks, David / dhildenb