summaryrefslogtreecommitdiff
path: root/drivers
diff options
context:
space:
mode:
Diffstat (limited to 'drivers')
-rw-r--r--drivers/base/init.c1
-rw-r--r--drivers/base/memory.c147
-rw-r--r--drivers/base/node.c48
-rw-r--r--drivers/block/drbd/drbd_int.h3
-rw-r--r--drivers/block/drbd/drbd_req.c3
-rw-r--r--drivers/dax/super.c2
-rw-r--r--drivers/of/of_reserved_mem.c9
-rw-r--r--drivers/tty/tty_io.c2
-rw-r--r--drivers/virtio/virtio_mem.c9
9 files changed, 157 insertions, 67 deletions
diff --git a/drivers/base/init.c b/drivers/base/init.c
index a9f57c22fb9e..d8d0fe687111 100644
--- a/drivers/base/init.c
+++ b/drivers/base/init.c
@@ -35,5 +35,6 @@ void __init driver_init(void)
auxiliary_bus_init();
cpu_dev_init();
memory_dev_init();
+ node_dev_init();
container_dev_init();
}
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index 365cd4a7f239..7222ff9b5e05 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -215,6 +215,7 @@ static int memory_block_online(struct memory_block *mem)
adjust_present_page_count(pfn_to_page(start_pfn), mem->group,
nr_vmemmap_pages);
+ mem->zone = zone;
return ret;
}
@@ -225,6 +226,9 @@ static int memory_block_offline(struct memory_block *mem)
unsigned long nr_vmemmap_pages = mem->nr_vmemmap_pages;
int ret;
+ if (!mem->zone)
+ return -EINVAL;
+
/*
* Unaccount before offlining, such that unpopulated zone and kthreads
* can properly be torn down in offline_pages().
@@ -234,7 +238,7 @@ static int memory_block_offline(struct memory_block *mem)
-nr_vmemmap_pages);
ret = offline_pages(start_pfn + nr_vmemmap_pages,
- nr_pages - nr_vmemmap_pages, mem->group);
+ nr_pages - nr_vmemmap_pages, mem->zone, mem->group);
if (ret) {
/* offline_pages() failed. Account back. */
if (nr_vmemmap_pages)
@@ -246,6 +250,7 @@ static int memory_block_offline(struct memory_block *mem)
if (nr_vmemmap_pages)
mhp_deinit_memmap_on_memory(start_pfn, nr_vmemmap_pages);
+ mem->zone = NULL;
return ret;
}
@@ -411,11 +416,10 @@ static ssize_t valid_zones_show(struct device *dev,
*/
if (mem->state == MEM_ONLINE) {
/*
- * The block contains more than one zone can not be offlined.
- * This can happen e.g. for ZONE_DMA and ZONE_DMA32
+ * If !mem->zone, the memory block spans multiple zones and
+ * cannot get offlined.
*/
- default_zone = test_pages_in_a_zone(start_pfn,
- start_pfn + nr_pages);
+ default_zone = mem->zone;
if (!default_zone)
return sysfs_emit(buf, "%s\n", "none");
len += sysfs_emit_at(buf, len, "%s", default_zone->name);
@@ -555,6 +559,8 @@ static ssize_t hard_offline_page_store(struct device *dev,
return -EINVAL;
pfn >>= PAGE_SHIFT;
ret = memory_failure(pfn, 0);
+ if (ret == -EOPNOTSUPP)
+ ret = 0;
return ret ? ret : count;
}
@@ -613,11 +619,7 @@ static const struct attribute_group *memory_memblk_attr_groups[] = {
NULL,
};
-/*
- * register_memory - Setup a sysfs device for a memory block
- */
-static
-int register_memory(struct memory_block *memory)
+static int __add_memory_block(struct memory_block *memory)
{
int ret;
@@ -641,9 +643,85 @@ int register_memory(struct memory_block *memory)
return ret;
}
-static int init_memory_block(unsigned long block_id, unsigned long state,
- unsigned long nr_vmemmap_pages,
- struct memory_group *group)
+static struct zone *early_node_zone_for_memory_block(struct memory_block *mem,
+ int nid)
+{
+ const unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr);
+ const unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block;
+ struct zone *zone, *matching_zone = NULL;
+ pg_data_t *pgdat = NODE_DATA(nid);
+ int i;
+
+ /*
+ * This logic only works for early memory, when the applicable zones
+ * already span the memory block. We don't expect overlapping zones on
+ * a single node for early memory. So if we're told that some PFNs
+ * of a node fall into this memory block, we can assume that all node
+ * zones that intersect with the memory block are actually applicable.
+ * No need to look at the memmap.
+ */
+ for (i = 0; i < MAX_NR_ZONES; i++) {
+ zone = pgdat->node_zones + i;
+ if (!populated_zone(zone))
+ continue;
+ if (!zone_intersects(zone, start_pfn, nr_pages))
+ continue;
+ if (!matching_zone) {
+ matching_zone = zone;
+ continue;
+ }
+ /* Spans multiple zones ... */
+ matching_zone = NULL;
+ break;
+ }
+ return matching_zone;
+}
+
+#ifdef CONFIG_NUMA
+/**
+ * memory_block_add_nid() - Indicate that system RAM falling into this memory
+ * block device (partially) belongs to the given node.
+ * @mem: The memory block device.
+ * @nid: The node id.
+ * @context: The memory initialization context.
+ *
+ * Indicate that system RAM falling into this memory block (partially) belongs
+ * to the given node. If the context indicates ("early") that we are adding the
+ * node during node device subsystem initialization, this will also properly
+ * set/adjust mem->zone based on the zone ranges of the given node.
+ */
+void memory_block_add_nid(struct memory_block *mem, int nid,
+ enum meminit_context context)
+{
+ if (context == MEMINIT_EARLY && mem->nid != nid) {
+ /*
+ * For early memory we have to determine the zone when setting
+ * the node id and handle multiple nodes spanning a single
+ * memory block by indicate via zone == NULL that we're not
+ * dealing with a single zone. So if we're setting the node id
+ * the first time, determine if there is a single zone. If we're
+ * setting the node id a second time to a different node,
+ * invalidate the single detected zone.
+ */
+ if (mem->nid == NUMA_NO_NODE)
+ mem->zone = early_node_zone_for_memory_block(mem, nid);
+ else
+ mem->zone = NULL;
+ }
+
+ /*
+ * If this memory block spans multiple nodes, we only indicate
+ * the last processed node. If we span multiple nodes (not applicable
+ * to hotplugged memory), zone == NULL will prohibit memory offlining
+ * and consequently unplug.
+ */
+ mem->nid = nid;
+}
+#endif
+
+static int add_memory_block(unsigned long block_id, unsigned long state,
+ unsigned long nr_vmemmap_pages,
+ struct memory_group *group)
{
struct memory_block *mem;
int ret = 0;
@@ -663,17 +741,30 @@ static int init_memory_block(unsigned long block_id, unsigned long state,
mem->nr_vmemmap_pages = nr_vmemmap_pages;
INIT_LIST_HEAD(&mem->group_next);
+#ifndef CONFIG_NUMA
+ if (state == MEM_ONLINE)
+ /*
+ * MEM_ONLINE at this point implies early memory. With NUMA,
+ * we'll determine the zone when setting the node id via
+ * memory_block_add_nid(). Memory hotplug updated the zone
+ * manually when memory onlining/offlining succeeds.
+ */
+ mem->zone = early_node_zone_for_memory_block(mem, NUMA_NO_NODE);
+#endif /* CONFIG_NUMA */
+
+ ret = __add_memory_block(mem);
+ if (ret)
+ return ret;
+
if (group) {
mem->group = group;
list_add(&mem->group_next, &group->memory_blocks);
}
- ret = register_memory(mem);
-
- return ret;
+ return 0;
}
-static int add_memory_block(unsigned long base_section_nr)
+static int __init add_boot_memory_block(unsigned long base_section_nr)
{
int section_count = 0;
unsigned long nr;
@@ -685,11 +776,18 @@ static int add_memory_block(unsigned long base_section_nr)
if (section_count == 0)
return 0;
- return init_memory_block(memory_block_id(base_section_nr),
- MEM_ONLINE, 0, NULL);
+ return add_memory_block(memory_block_id(base_section_nr),
+ MEM_ONLINE, 0, NULL);
+}
+
+static int add_hotplug_memory_block(unsigned long block_id,
+ unsigned long nr_vmemmap_pages,
+ struct memory_group *group)
+{
+ return add_memory_block(block_id, MEM_OFFLINE, nr_vmemmap_pages, group);
}
-static void unregister_memory(struct memory_block *memory)
+static void remove_memory_block(struct memory_block *memory)
{
if (WARN_ON_ONCE(memory->dev.bus != &memory_subsys))
return;
@@ -728,8 +826,7 @@ int create_memory_block_devices(unsigned long start, unsigned long size,
return -EINVAL;
for (block_id = start_block_id; block_id != end_block_id; block_id++) {
- ret = init_memory_block(block_id, MEM_OFFLINE, vmemmap_pages,
- group);
+ ret = add_hotplug_memory_block(block_id, vmemmap_pages, group);
if (ret)
break;
}
@@ -740,7 +837,7 @@ int create_memory_block_devices(unsigned long start, unsigned long size,
mem = find_memory_block_by_id(block_id);
if (WARN_ON_ONCE(!mem))
continue;
- unregister_memory(mem);
+ remove_memory_block(mem);
}
}
return ret;
@@ -769,7 +866,7 @@ void remove_memory_block_devices(unsigned long start, unsigned long size)
if (WARN_ON_ONCE(!mem))
continue;
unregister_memory_block_under_nodes(mem);
- unregister_memory(mem);
+ remove_memory_block(mem);
}
}
@@ -829,7 +926,7 @@ void __init memory_dev_init(void)
*/
for (nr = 0; nr <= __highest_present_section_nr;
nr += sections_per_block) {
- ret = add_memory_block(nr);
+ ret = add_boot_memory_block(nr);
if (ret)
panic("%s() failed to add memory block: %d\n", __func__,
ret);
diff --git a/drivers/base/node.c b/drivers/base/node.c
index 87acc47e8951..ec8bb24a5a22 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -796,15 +796,12 @@ static int __ref get_nid_for_pfn(unsigned long pfn)
}
static void do_register_memory_block_under_node(int nid,
- struct memory_block *mem_blk)
+ struct memory_block *mem_blk,
+ enum meminit_context context)
{
int ret;
- /*
- * If this memory block spans multiple nodes, we only indicate
- * the last processed node.
- */
- mem_blk->nid = nid;
+ memory_block_add_nid(mem_blk, nid, context);
ret = sysfs_create_link_nowarn(&node_devices[nid]->dev.kobj,
&mem_blk->dev.kobj,
@@ -857,7 +854,7 @@ static int register_mem_block_under_node_early(struct memory_block *mem_blk,
if (page_nid != nid)
continue;
- do_register_memory_block_under_node(nid, mem_blk);
+ do_register_memory_block_under_node(nid, mem_blk, MEMINIT_EARLY);
return 0;
}
/* mem section does not span the specified node */
@@ -873,7 +870,7 @@ static int register_mem_block_under_node_hotplug(struct memory_block *mem_blk,
{
int nid = *(int *)arg;
- do_register_memory_block_under_node(nid, mem_blk);
+ do_register_memory_block_under_node(nid, mem_blk, MEMINIT_HOTPLUG);
return 0;
}
@@ -892,8 +889,9 @@ void unregister_memory_block_under_nodes(struct memory_block *mem_blk)
kobject_name(&node_devices[mem_blk->nid]->dev.kobj));
}
-void link_mem_sections(int nid, unsigned long start_pfn, unsigned long end_pfn,
- enum meminit_context context)
+void register_memory_blocks_under_node(int nid, unsigned long start_pfn,
+ unsigned long end_pfn,
+ enum meminit_context context)
{
walk_memory_blocks_func_t func;
@@ -1065,26 +1063,30 @@ static const struct attribute_group *cpu_root_attr_groups[] = {
};
#define NODE_CALLBACK_PRI 2 /* lower than SLAB */
-static int __init register_node_type(void)
+void __init node_dev_init(void)
{
- int ret;
+ static struct notifier_block node_memory_callback_nb = {
+ .notifier_call = node_memory_callback,
+ .priority = NODE_CALLBACK_PRI,
+ };
+ int ret, i;
BUILD_BUG_ON(ARRAY_SIZE(node_state_attr) != NR_NODE_STATES);
BUILD_BUG_ON(ARRAY_SIZE(node_state_attrs)-1 != NR_NODE_STATES);
ret = subsys_system_register(&node_subsys, cpu_root_attr_groups);
- if (!ret) {
- static struct notifier_block node_memory_callback_nb = {
- .notifier_call = node_memory_callback,
- .priority = NODE_CALLBACK_PRI,
- };
- register_hotmemory_notifier(&node_memory_callback_nb);
- }
+ if (ret)
+ panic("%s() failed to register subsystem: %d\n", __func__, ret);
+
+ register_hotmemory_notifier(&node_memory_callback_nb);
/*
- * Note: we're not going to unregister the node class if we fail
- * to register the node state class attribute files.
+ * Create all node devices, which will properly link the node
+ * to applicable memory block devices and already created cpu devices.
*/
- return ret;
+ for_each_online_node(i) {
+ ret = register_one_node(i);
+ if (ret)
+ panic("%s() failed to add node: %d\n", __func__, ret);
+ }
}
-postcore_initcall(register_node_type);
diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index acb1ad3c0603..4b55e864a0a3 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -637,9 +637,6 @@ enum {
STATE_SENT, /* Do not change state/UUIDs while this is set */
CALLBACK_PENDING, /* Whether we have a call_usermodehelper(, UMH_WAIT_PROC)
* pending, from drbd worker context.
- * If set, bdi_write_congested() returns true,
- * so shrink_page_list() would not recurse into,
- * and potentially deadlock on, this drbd worker.
*/
DISCONNECT_SENT,
diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index c00ae8619519..2f608525a879 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -910,8 +910,7 @@ static bool remote_due_to_read_balancing(struct drbd_device *device, sector_t se
switch (rbm) {
case RB_CONGESTED_REMOTE:
- return bdi_read_congested(
- device->ldev->backing_bdev->bd_disk->bdi);
+ return 0;
case RB_LEAST_PENDING:
return atomic_read(&device->local_cnt) >
atomic_read(&device->ap_pending_cnt) + atomic_read(&device->rs_pending_cnt);
diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index e3029389d809..aedc15eabeac 100644
--- a/drivers/dax/super.c
+++ b/drivers/dax/super.c
@@ -282,7 +282,7 @@ static struct inode *dax_alloc_inode(struct super_block *sb)
struct dax_device *dax_dev;
struct inode *inode;
- dax_dev = kmem_cache_alloc(dax_cache, GFP_KERNEL);
+ dax_dev = alloc_inode_sb(sb, dax_cache, GFP_KERNEL);
if (!dax_dev)
return NULL;
diff --git a/drivers/of/of_reserved_mem.c b/drivers/of/of_reserved_mem.c
index 9c0fb962c22b..75caa6f5d36f 100644
--- a/drivers/of/of_reserved_mem.c
+++ b/drivers/of/of_reserved_mem.c
@@ -22,6 +22,7 @@
#include <linux/slab.h>
#include <linux/memblock.h>
#include <linux/kmemleak.h>
+#include <linux/cma.h>
#include "of_private.h"
@@ -116,12 +117,8 @@ static int __init __reserved_mem_alloc_size(unsigned long node,
if (IS_ENABLED(CONFIG_CMA)
&& of_flat_dt_is_compatible(node, "shared-dma-pool")
&& of_get_flat_dt_prop(node, "reusable", NULL)
- && !nomap) {
- unsigned long order =
- max_t(unsigned long, MAX_ORDER - 1, pageblock_order);
-
- align = max(align, (phys_addr_t)PAGE_SIZE << order);
- }
+ && !nomap)
+ align = max_t(phys_addr_t, align, CMA_MIN_ALIGNMENT_BYTES);
prop = of_get_flat_dt_prop(node, "alloc-ranges", &len);
if (prop) {
diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index 7e8b3bd59c7b..8fec1d8648f5 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -3088,7 +3088,7 @@ struct tty_struct *alloc_tty_struct(struct tty_driver *driver, int idx)
{
struct tty_struct *tty;
- tty = kzalloc(sizeof(*tty), GFP_KERNEL);
+ tty = kzalloc(sizeof(*tty), GFP_KERNEL_ACCOUNT);
if (!tty)
return NULL;
diff --git a/drivers/virtio/virtio_mem.c b/drivers/virtio/virtio_mem.c
index 38becd8d578c..e7d6b679596d 100644
--- a/drivers/virtio/virtio_mem.c
+++ b/drivers/virtio/virtio_mem.c
@@ -2476,13 +2476,10 @@ static int virtio_mem_init_hotplug(struct virtio_mem *vm)
VIRTIO_MEM_DEFAULT_OFFLINE_THRESHOLD);
/*
- * We want subblocks to span at least MAX_ORDER_NR_PAGES and
- * pageblock_nr_pages pages. This:
- * - Is required for now for alloc_contig_range() to work reliably -
- * it doesn't properly handle smaller granularity on ZONE_NORMAL.
+ * TODO: once alloc_contig_range() works reliably with pageblock
+ * granularity on ZONE_NORMAL, use pageblock_nr_pages instead.
*/
- sb_size = max_t(uint64_t, MAX_ORDER_NR_PAGES,
- pageblock_nr_pages) * PAGE_SIZE;
+ sb_size = PAGE_SIZE * MAX_ORDER_NR_PAGES;
sb_size = max_t(uint64_t, vm->device_block_size, sb_size);
if (sb_size < memory_block_size_bytes() && !force_bbm) {
generated by cgit v1.2.3 (git 2.39.0) at 2025-01-20 12:31:19 +0300