summaryrefslogtreecommitdiff
path: root/drivers/base/node.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/base/node.c')
-rw-r--r--drivers/base/node.c309
1 files changed, 172 insertions, 137 deletions
diff --git a/drivers/base/node.c b/drivers/base/node.c
index 9de524e56307..00cf4532f121 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -7,6 +7,7 @@
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/memory.h>
+#include <linux/mempolicy.h>
#include <linux/vmstat.h>
#include <linux/notifier.h>
#include <linux/node.h>
@@ -20,15 +21,15 @@
#include <linux/pm_runtime.h>
#include <linux/swap.h>
#include <linux/slab.h>
-#include <linux/hugetlb.h>
+#include <linux/memblock.h>
-static struct bus_type node_subsys = {
+static const struct bus_type node_subsys = {
.name = "node",
.dev_name = "node",
};
static inline ssize_t cpumap_read(struct file *file, struct kobject *kobj,
- struct bin_attribute *attr, char *buf,
+ const struct bin_attribute *attr, char *buf,
loff_t off, size_t count)
{
struct device *dev = kobj_to_dev(kobj);
@@ -46,10 +47,10 @@ static inline ssize_t cpumap_read(struct file *file, struct kobject *kobj,
return n;
}
-static BIN_ATTR_RO(cpumap, CPUMAP_FILE_MAX_BYTES);
+static const BIN_ATTR_RO(cpumap, CPUMAP_FILE_MAX_BYTES);
static inline ssize_t cpulist_read(struct file *file, struct kobject *kobj,
- struct bin_attribute *attr, char *buf,
+ const struct bin_attribute *attr, char *buf,
loff_t off, size_t count)
{
struct device *dev = kobj_to_dev(kobj);
@@ -67,7 +68,7 @@ static inline ssize_t cpulist_read(struct file *file, struct kobject *kobj,
return n;
}
-static BIN_ATTR_RO(cpulist, CPULIST_FILE_MAX_BYTES);
+static const BIN_ATTR_RO(cpulist, CPULIST_FILE_MAX_BYTES);
/**
* struct node_access_nodes - Access class device to hold user visible
@@ -75,14 +76,14 @@ static BIN_ATTR_RO(cpulist, CPULIST_FILE_MAX_BYTES);
* @dev: Device for this memory access class
* @list_node: List element in the node's access list
* @access: The access class rank
- * @hmem_attrs: Heterogeneous memory performance attributes
+ * @coord: Heterogeneous memory performance coordinates
*/
struct node_access_nodes {
struct device dev;
struct list_head list_node;
unsigned int access;
#ifdef CONFIG_HMEM_REPORTING
- struct node_hmem_attrs hmem_attrs;
+ struct access_coordinate coord;
#endif
};
#define to_access_nodes(dev) container_of(dev, struct node_access_nodes, dev)
@@ -111,6 +112,27 @@ static const struct attribute_group *node_access_node_groups[] = {
NULL,
};
+#ifdef CONFIG_MEMORY_HOTPLUG
+static BLOCKING_NOTIFIER_HEAD(node_chain);
+
+int register_node_notifier(struct notifier_block *nb)
+{
+ return blocking_notifier_chain_register(&node_chain, nb);
+}
+EXPORT_SYMBOL(register_node_notifier);
+
+void unregister_node_notifier(struct notifier_block *nb)
+{
+ blocking_notifier_chain_unregister(&node_chain, nb);
+}
+EXPORT_SYMBOL(unregister_node_notifier);
+
+int node_notify(unsigned long val, void *v)
+{
+ return blocking_notifier_call_chain(&node_chain, val, v);
+}
+#endif
+
static void node_remove_accesses(struct node *node)
{
struct node_access_nodes *c, *cnext;
@@ -127,7 +149,7 @@ static void node_access_release(struct device *dev)
}
static struct node_access_nodes *node_init_node_access(struct node *node,
- unsigned int access)
+ enum access_coordinate_class access)
{
struct node_access_nodes *access_node;
struct device *dev;
@@ -168,7 +190,7 @@ static ssize_t property##_show(struct device *dev, \
char *buf) \
{ \
return sysfs_emit(buf, "%u\n", \
- to_access_nodes(dev)->hmem_attrs.property); \
+ to_access_nodes(dev)->coord.property); \
} \
static DEVICE_ATTR_RO(property)
@@ -188,11 +210,11 @@ static struct attribute *access_attrs[] = {
/**
* node_set_perf_attrs - Set the performance values for given access class
* @nid: Node identifier to be set
- * @hmem_attrs: Heterogeneous memory performance attributes
+ * @coord: Heterogeneous memory performance coordinates
* @access: The access class the for the given attributes
*/
-void node_set_perf_attrs(unsigned int nid, struct node_hmem_attrs *hmem_attrs,
- unsigned int access)
+void node_set_perf_attrs(unsigned int nid, struct access_coordinate *coord,
+ enum access_coordinate_class access)
{
struct node_access_nodes *c;
struct node *node;
@@ -206,7 +228,7 @@ void node_set_perf_attrs(unsigned int nid, struct node_hmem_attrs *hmem_attrs,
if (!c)
return;
- c->hmem_attrs = *hmem_attrs;
+ c->coord = *coord;
for (i = 0; access_attrs[i] != NULL; i++) {
if (sysfs_add_file_to_group(&c->dev.kobj, access_attrs[i],
"initiators")) {
@@ -215,7 +237,54 @@ void node_set_perf_attrs(unsigned int nid, struct node_hmem_attrs *hmem_attrs,
break;
}
}
+
+ /* When setting CPU access coordinates, update mempolicy */
+ if (access == ACCESS_COORDINATE_CPU) {
+ if (mempolicy_set_node_perf(nid, coord)) {
+ pr_info("failed to set mempolicy attrs for node %d\n",
+ nid);
+ }
+ }
+}
+EXPORT_SYMBOL_GPL(node_set_perf_attrs);
+
+/**
+ * node_update_perf_attrs - Update the performance values for given access class
+ * @nid: Node identifier to be updated
+ * @coord: Heterogeneous memory performance coordinates
+ * @access: The access class for the given attributes
+ */
+void node_update_perf_attrs(unsigned int nid, struct access_coordinate *coord,
+ enum access_coordinate_class access)
+{
+ struct node_access_nodes *access_node;
+ struct node *node;
+ int i;
+
+ if (WARN_ON_ONCE(!node_online(nid)))
+ return;
+
+ node = node_devices[nid];
+ list_for_each_entry(access_node, &node->access_list, list_node) {
+ if (access_node->access != access)
+ continue;
+
+ access_node->coord = *coord;
+ for (i = 0; access_attrs[i]; i++) {
+ sysfs_notify(&access_node->dev.kobj,
+ NULL, access_attrs[i]->name);
+ }
+ break;
+ }
+
+ /* When setting CPU access coordinates, update mempolicy */
+ if (access != ACCESS_COORDINATE_CPU)
+ return;
+
+ if (mempolicy_set_node_perf(nid, coord))
+ pr_info("failed to set mempolicy attrs for node %d\n", nid);
}
+EXPORT_SYMBOL_GPL(node_update_perf_attrs);
/**
* struct node_cache_info - Internal tracking for memory node caches
@@ -244,12 +313,14 @@ CACHE_ATTR(size, "%llu")
CACHE_ATTR(line_size, "%u")
CACHE_ATTR(indexing, "%u")
CACHE_ATTR(write_policy, "%u")
+CACHE_ATTR(address_mode, "%#x")
static struct attribute *cache_attrs[] = {
&dev_attr_indexing.attr,
&dev_attr_size.attr,
&dev_attr_line_size.attr,
&dev_attr_write_policy.attr,
+ &dev_attr_address_mode.attr,
NULL,
};
ATTRIBUTE_GROUPS(cache);
@@ -446,8 +517,8 @@ static ssize_t node_read_meminfo(struct device *dev,
"Node %d AnonHugePages: %8lu kB\n"
"Node %d ShmemHugePages: %8lu kB\n"
"Node %d ShmemPmdMapped: %8lu kB\n"
- "Node %d FileHugePages: %8lu kB\n"
- "Node %d FilePmdMapped: %8lu kB\n"
+ "Node %d FileHugePages: %8lu kB\n"
+ "Node %d FilePmdMapped: %8lu kB\n"
#endif
#ifdef CONFIG_UNACCEPTED_MEMORY
"Node %d Unaccepted: %8lu kB\n"
@@ -466,8 +537,8 @@ static ssize_t node_read_meminfo(struct device *dev,
nid, K(node_page_state(pgdat, NR_PAGETABLE)),
nid, K(node_page_state(pgdat, NR_SECONDARY_PAGETABLE)),
nid, 0UL,
- nid, K(sum_zone_node_page_state(nid, NR_BOUNCE)),
- nid, K(node_page_state(pgdat, NR_WRITEBACK_TEMP)),
+ nid, 0UL,
+ nid, 0UL,
nid, K(sreclaimable +
node_page_state(pgdat, NR_KERNEL_MISC_RECLAIMABLE)),
nid, K(sreclaimable + sunreclaimable),
@@ -578,7 +649,7 @@ static struct attribute *node_dev_attrs[] = {
NULL
};
-static struct bin_attribute *node_dev_bin_attrs[] = {
+static const struct bin_attribute *node_dev_bin_attrs[] = {
&bin_attr_cpumap,
&bin_attr_cpulist,
NULL
@@ -586,7 +657,7 @@ static struct bin_attribute *node_dev_bin_attrs[] = {
static const struct attribute_group node_dev_group = {
.attrs = node_dev_attrs,
- .bin_attrs = node_dev_bin_attrs
+ .bin_attrs = node_dev_bin_attrs,
};
static const struct attribute_group *node_dev_groups[] = {
@@ -605,48 +676,6 @@ static void node_device_release(struct device *dev)
kfree(to_node(dev));
}
-/*
- * register_node - Setup a sysfs device for a node.
- * @num - Node number to use when creating the device.
- *
- * Initialize and register the node device.
- */
-static int register_node(struct node *node, int num)
-{
- int error;
-
- node->dev.id = num;
- node->dev.bus = &node_subsys;
- node->dev.release = node_device_release;
- node->dev.groups = node_dev_groups;
- error = device_register(&node->dev);
-
- if (error) {
- put_device(&node->dev);
- } else {
- hugetlb_register_node(node);
- compaction_register_node(node);
- }
-
- return error;
-}
-
-/**
- * unregister_node - unregister a node device
- * @node: node going away
- *
- * Unregisters a node device @node. All the devices on the node must be
- * unregistered before calling this function.
- */
-void unregister_node(struct node *node)
-{
- hugetlb_unregister_node(node);
- compaction_unregister_node(node);
- node_remove_accesses(node);
- node_remove_caches(node);
- device_unregister(&node->dev);
-}
-
struct node *node_devices[MAX_NUMNODES];
/*
@@ -690,7 +719,7 @@ int register_cpu_under_node(unsigned int cpu, unsigned int nid)
*/
int register_memory_node_under_compute_node(unsigned int mem_nid,
unsigned int cpu_nid,
- unsigned int access)
+ enum access_coordinate_class access)
{
struct node *init_node, *targ_node;
struct node_access_nodes *initiator, *target;
@@ -745,23 +774,11 @@ int unregister_cpu_under_node(unsigned int cpu, unsigned int nid)
}
#ifdef CONFIG_MEMORY_HOTPLUG
-static int __ref get_nid_for_pfn(unsigned long pfn)
-{
-#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
- if (system_state < SYSTEM_RUNNING)
- return early_pfn_to_nid(pfn);
-#endif
- return pfn_to_nid(pfn);
-}
-
static void do_register_memory_block_under_node(int nid,
- struct memory_block *mem_blk,
- enum meminit_context context)
+ struct memory_block *mem_blk)
{
int ret;
- memory_block_add_nid(mem_blk, nid, context);
-
ret = sysfs_create_link_nowarn(&node_devices[nid]->dev.kobj,
&mem_blk->dev.kobj,
kobject_name(&mem_blk->dev.kobj));
@@ -780,46 +797,6 @@ static void do_register_memory_block_under_node(int nid,
ret);
}
-/* register memory section under specified node if it spans that node */
-static int register_mem_block_under_node_early(struct memory_block *mem_blk,
- void *arg)
-{
- unsigned long memory_block_pfns = memory_block_size_bytes() / PAGE_SIZE;
- unsigned long start_pfn = section_nr_to_pfn(mem_blk->start_section_nr);
- unsigned long end_pfn = start_pfn + memory_block_pfns - 1;
- int nid = *(int *)arg;
- unsigned long pfn;
-
- for (pfn = start_pfn; pfn <= end_pfn; pfn++) {
- int page_nid;
-
- /*
- * memory block could have several absent sections from start.
- * skip pfn range from absent section
- */
- if (!pfn_in_present_section(pfn)) {
- pfn = round_down(pfn + PAGES_PER_SECTION,
- PAGES_PER_SECTION) - 1;
- continue;
- }
-
- /*
- * We need to check if page belongs to nid only at the boot
- * case because node's ranges can be interleaved.
- */
- page_nid = get_nid_for_pfn(pfn);
- if (page_nid < 0)
- continue;
- if (page_nid != nid)
- continue;
-
- do_register_memory_block_under_node(nid, mem_blk, MEMINIT_EARLY);
- return 0;
- }
- /* mem section does not span the specified node */
- return 0;
-}
-
/*
* During hotplug we know that all pages in the memory block belong to the same
* node.
@@ -829,7 +806,7 @@ 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, MEMINIT_HOTPLUG);
+ do_register_memory_block_under_node(nid, mem_blk);
return 0;
}
@@ -848,33 +825,77 @@ void unregister_memory_block_under_nodes(struct memory_block *mem_blk)
kobject_name(&node_devices[mem_blk->nid]->dev.kobj));
}
-void register_memory_blocks_under_node(int nid, unsigned long start_pfn,
- unsigned long end_pfn,
- enum meminit_context context)
+/* register all memory blocks under the corresponding nodes */
+static void register_memory_blocks_under_nodes(void)
{
- walk_memory_blocks_func_t func;
+ struct memblock_region *r;
+
+ for_each_mem_region(r) {
+ const unsigned long start_block_id = phys_to_block_id(r->base);
+ const unsigned long end_block_id = phys_to_block_id(r->base + r->size - 1);
+ const int nid = memblock_get_region_node(r);
+ unsigned long block_id;
+
+ if (!node_online(nid))
+ continue;
- if (context == MEMINIT_HOTPLUG)
- func = register_mem_block_under_node_hotplug;
- else
- func = register_mem_block_under_node_early;
+ for (block_id = start_block_id; block_id <= end_block_id; block_id++) {
+ struct memory_block *mem;
+
+ mem = find_memory_block_by_id(block_id);
+ if (!mem)
+ continue;
+
+ memory_block_add_nid_early(mem, nid);
+ do_register_memory_block_under_node(nid, mem);
+ put_device(&mem->dev);
+ }
+ }
+}
+
+void register_memory_blocks_under_node_hotplug(int nid, unsigned long start_pfn,
+ unsigned long end_pfn)
+{
walk_memory_blocks(PFN_PHYS(start_pfn), PFN_PHYS(end_pfn - start_pfn),
- (void *)&nid, func);
+ (void *)&nid, register_mem_block_under_node_hotplug);
return;
}
#endif /* CONFIG_MEMORY_HOTPLUG */
-int __register_one_node(int nid)
+/**
+ * register_node - Initialize and register the node device.
+ * @nid: Node number to use when creating the device.
+ *
+ * Return: 0 on success, -errno otherwise
+ */
+int register_node(int nid)
{
int error;
int cpu;
+ struct node *node;
- node_devices[nid] = kzalloc(sizeof(struct node), GFP_KERNEL);
- if (!node_devices[nid])
+ node = kzalloc(sizeof(struct node), GFP_KERNEL);
+ if (!node)
return -ENOMEM;
- error = register_node(node_devices[nid], nid);
+ INIT_LIST_HEAD(&node->access_list);
+
+ node->dev.id = nid;
+ node->dev.bus = &node_subsys;
+ node->dev.release = node_device_release;
+ node->dev.groups = node_dev_groups;
+
+ error = device_register(&node->dev);
+ if (error) {
+ put_device(&node->dev);
+ return error;
+ }
+
+ node_devices[nid] = node;
+ hugetlb_register_node(node);
+ compaction_register_node(node);
+ reclaim_register_node(node);
/* link cpu under this node */
for_each_present_cpu(cpu) {
@@ -882,18 +903,30 @@ int __register_one_node(int nid)
register_cpu_under_node(cpu, nid);
}
- INIT_LIST_HEAD(&node_devices[nid]->access_list);
node_init_caches(nid);
return error;
}
-
-void unregister_one_node(int nid)
+/**
+ * unregister_node - unregister a node device
+ * @nid: nid of the node going away
+ *
+ * Unregisters the node device at node id @nid. All the devices on the
+ * node must be unregistered before calling this function.
+ */
+void unregister_node(int nid)
{
- if (!node_devices[nid])
+ struct node *node = node_devices[nid];
+
+ if (!node)
return;
- unregister_node(node_devices[nid]);
+ hugetlb_unregister_node(node);
+ compaction_unregister_node(node);
+ reclaim_unregister_node(node);
+ node_remove_accesses(node);
+ node_remove_caches(node);
+ device_unregister(&node->dev);
node_devices[nid] = NULL;
}
@@ -966,11 +999,13 @@ void __init node_dev_init(void)
/*
* Create all node devices, which will properly link the node
- * to applicable memory block devices and already created cpu devices.
+ * to already created cpu devices.
*/
for_each_online_node(i) {
- ret = register_one_node(i);
+ ret = register_node(i);
if (ret)
panic("%s() failed to add node: %d\n", __func__, ret);
}
+
+ register_memory_blocks_under_nodes();
}