virtio-mem: Allow to specify an ACPI PXM as nid

We want to allow to specify (similar as for a DIMM), to which node a
virtio-mem device (and, therefore, its memory) belongs. Add a new
virtio-mem feature flag and export pxm_to_node, so it can be used in kernel
module context.

Acked-by: Michal Hocko <mhocko@suse.com> # for the export
Acked-by: "Rafael J. Wysocki" <rafael@kernel.org> # for the export
Acked-by: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Tested-by: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Igor Mammedov <imammedo@redhat.com>
Cc: Dave Young <dyoung@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Cc: Stefan Hajnoczi <stefanha@redhat.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Len Brown <lenb@kernel.org>
Cc: linux-acpi@vger.kernel.org
Signed-off-by: David Hildenbrand <david@redhat.com>
Link: https://lore.kernel.org/r/20200507140139.17083-4-david@redhat.com
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
This commit is contained in:
David Hildenbrand 2020-05-07 16:01:27 +02:00 committed by Michael S. Tsirkin
parent dfb0b2e46d
commit f2af6d3978
3 changed files with 47 additions and 3 deletions

View File

@ -35,6 +35,7 @@ int pxm_to_node(int pxm)
return NUMA_NO_NODE;
return pxm_to_node_map[pxm];
}
EXPORT_SYMBOL(pxm_to_node);
int node_to_pxm(int node)
{

View File

@ -21,6 +21,8 @@
#include <linux/bitmap.h>
#include <linux/lockdep.h>
#include <acpi/acpi_numa.h>
enum virtio_mem_mb_state {
/* Unplugged, not added to Linux. Can be reused later. */
VIRTIO_MEM_MB_STATE_UNUSED = 0,
@ -72,6 +74,8 @@ struct virtio_mem {
/* The device block size (for communicating with the device). */
uint32_t device_block_size;
/* The translated node id. NUMA_NO_NODE in case not specified. */
int nid;
/* Physical start address of the memory region. */
uint64_t addr;
/* Maximum region size in bytes. */
@ -389,7 +393,10 @@ static int virtio_mem_sb_bitmap_prepare_next_mb(struct virtio_mem *vm)
static int virtio_mem_mb_add(struct virtio_mem *vm, unsigned long mb_id)
{
const uint64_t addr = virtio_mem_mb_id_to_phys(mb_id);
int nid = memory_add_physaddr_to_nid(addr);
int nid = vm->nid;
if (nid == NUMA_NO_NODE)
nid = memory_add_physaddr_to_nid(addr);
dev_dbg(&vm->vdev->dev, "adding memory block: %lu\n", mb_id);
return add_memory(nid, addr, memory_block_size_bytes());
@ -407,7 +414,10 @@ static int virtio_mem_mb_add(struct virtio_mem *vm, unsigned long mb_id)
static int virtio_mem_mb_remove(struct virtio_mem *vm, unsigned long mb_id)
{
const uint64_t addr = virtio_mem_mb_id_to_phys(mb_id);
int nid = memory_add_physaddr_to_nid(addr);
int nid = vm->nid;
if (nid == NUMA_NO_NODE)
nid = memory_add_physaddr_to_nid(addr);
dev_dbg(&vm->vdev->dev, "removing memory block: %lu\n", mb_id);
return remove_memory(nid, addr, memory_block_size_bytes());
@ -426,6 +436,17 @@ static void virtio_mem_retry(struct virtio_mem *vm)
spin_unlock_irqrestore(&vm->removal_lock, flags);
}
static int virtio_mem_translate_node_id(struct virtio_mem *vm, uint16_t node_id)
{
int node = NUMA_NO_NODE;
#if defined(CONFIG_ACPI_NUMA)
if (virtio_has_feature(vm->vdev, VIRTIO_MEM_F_ACPI_PXM))
node = pxm_to_node(node_id);
#endif
return node;
}
/*
* Test if a virtio-mem device overlaps with the given range. Can be called
* from (notifier) callbacks lockless.
@ -1267,6 +1288,7 @@ static bool virtio_mem_any_memory_present(unsigned long start,
static int virtio_mem_init(struct virtio_mem *vm)
{
const uint64_t phys_limit = 1UL << MAX_PHYSMEM_BITS;
uint16_t node_id;
if (!vm->vdev->config->get) {
dev_err(&vm->vdev->dev, "config access disabled\n");
@ -1287,6 +1309,9 @@ static int virtio_mem_init(struct virtio_mem *vm)
&vm->plugged_size);
virtio_cread(vm->vdev, struct virtio_mem_config, block_size,
&vm->device_block_size);
virtio_cread(vm->vdev, struct virtio_mem_config, node_id,
&node_id);
vm->nid = virtio_mem_translate_node_id(vm, node_id);
virtio_cread(vm->vdev, struct virtio_mem_config, addr, &vm->addr);
virtio_cread(vm->vdev, struct virtio_mem_config, region_size,
&vm->region_size);
@ -1365,6 +1390,8 @@ static int virtio_mem_init(struct virtio_mem *vm)
memory_block_size_bytes());
dev_info(&vm->vdev->dev, "subblock size: 0x%x",
vm->subblock_size);
if (vm->nid != NUMA_NO_NODE)
dev_info(&vm->vdev->dev, "nid: %d", vm->nid);
return 0;
}
@ -1508,12 +1535,20 @@ static int virtio_mem_restore(struct virtio_device *vdev)
}
#endif
static unsigned int virtio_mem_features[] = {
#if defined(CONFIG_NUMA) && defined(CONFIG_ACPI_NUMA)
VIRTIO_MEM_F_ACPI_PXM,
#endif
};
static struct virtio_device_id virtio_mem_id_table[] = {
{ VIRTIO_ID_MEM, VIRTIO_DEV_ANY_ID },
{ 0 },
};
static struct virtio_driver virtio_mem_driver = {
.feature_table = virtio_mem_features,
.feature_table_size = ARRAY_SIZE(virtio_mem_features),
.driver.name = KBUILD_MODNAME,
.driver.owner = THIS_MODULE,
.id_table = virtio_mem_id_table,

View File

@ -83,6 +83,12 @@
* device is busy.
*/
/* --- virtio-mem: feature bits --- */
/* node_id is an ACPI PXM and is valid */
#define VIRTIO_MEM_F_ACPI_PXM 0
/* --- virtio-mem: guest -> host requests --- */
/* request to plug memory blocks */
@ -177,7 +183,9 @@ struct virtio_mem_resp {
struct virtio_mem_config {
/* Block size and alignment. Cannot change. */
__u32 block_size;
__u32 padding;
/* Valid with VIRTIO_MEM_F_ACPI_PXM. Cannot change. */
__u16 node_id;
__u16 padding;
/* Start address of the memory region. Cannot change. */
__u64 addr;
/* Region size (maximum). Cannot change. */