Update Linux to v5.4.2
Change-Id: Idf6911045d9d382da2cfe01b1edff026404ac8fd
diff --git a/drivers/base/node.c b/drivers/base/node.c
index 1ac4c36..296546f 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -17,6 +17,7 @@
#include <linux/nodemask.h>
#include <linux/cpu.h>
#include <linux/device.h>
+#include <linux/pm_runtime.h>
#include <linux/swap.h>
#include <linux/slab.h>
@@ -59,6 +60,303 @@
static DEVICE_ATTR(cpumap, S_IRUGO, node_read_cpumask, NULL);
static DEVICE_ATTR(cpulist, S_IRUGO, node_read_cpulist, NULL);
+/**
+ * struct node_access_nodes - Access class device to hold user visible
+ * relationships to other nodes.
+ * @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
+ */
+struct node_access_nodes {
+ struct device dev;
+ struct list_head list_node;
+ unsigned access;
+#ifdef CONFIG_HMEM_REPORTING
+ struct node_hmem_attrs hmem_attrs;
+#endif
+};
+#define to_access_nodes(dev) container_of(dev, struct node_access_nodes, dev)
+
+static struct attribute *node_init_access_node_attrs[] = {
+ NULL,
+};
+
+static struct attribute *node_targ_access_node_attrs[] = {
+ NULL,
+};
+
+static const struct attribute_group initiators = {
+ .name = "initiators",
+ .attrs = node_init_access_node_attrs,
+};
+
+static const struct attribute_group targets = {
+ .name = "targets",
+ .attrs = node_targ_access_node_attrs,
+};
+
+static const struct attribute_group *node_access_node_groups[] = {
+ &initiators,
+ &targets,
+ NULL,
+};
+
+static void node_remove_accesses(struct node *node)
+{
+ struct node_access_nodes *c, *cnext;
+
+ list_for_each_entry_safe(c, cnext, &node->access_list, list_node) {
+ list_del(&c->list_node);
+ device_unregister(&c->dev);
+ }
+}
+
+static void node_access_release(struct device *dev)
+{
+ kfree(to_access_nodes(dev));
+}
+
+static struct node_access_nodes *node_init_node_access(struct node *node,
+ unsigned access)
+{
+ struct node_access_nodes *access_node;
+ struct device *dev;
+
+ list_for_each_entry(access_node, &node->access_list, list_node)
+ if (access_node->access == access)
+ return access_node;
+
+ access_node = kzalloc(sizeof(*access_node), GFP_KERNEL);
+ if (!access_node)
+ return NULL;
+
+ access_node->access = access;
+ dev = &access_node->dev;
+ dev->parent = &node->dev;
+ dev->release = node_access_release;
+ dev->groups = node_access_node_groups;
+ if (dev_set_name(dev, "access%u", access))
+ goto free;
+
+ if (device_register(dev))
+ goto free_name;
+
+ pm_runtime_no_callbacks(dev);
+ list_add_tail(&access_node->list_node, &node->access_list);
+ return access_node;
+free_name:
+ kfree_const(dev->kobj.name);
+free:
+ kfree(access_node);
+ return NULL;
+}
+
+#ifdef CONFIG_HMEM_REPORTING
+#define ACCESS_ATTR(name) \
+static ssize_t name##_show(struct device *dev, \
+ struct device_attribute *attr, \
+ char *buf) \
+{ \
+ return sprintf(buf, "%u\n", to_access_nodes(dev)->hmem_attrs.name); \
+} \
+static DEVICE_ATTR_RO(name);
+
+ACCESS_ATTR(read_bandwidth)
+ACCESS_ATTR(read_latency)
+ACCESS_ATTR(write_bandwidth)
+ACCESS_ATTR(write_latency)
+
+static struct attribute *access_attrs[] = {
+ &dev_attr_read_bandwidth.attr,
+ &dev_attr_read_latency.attr,
+ &dev_attr_write_bandwidth.attr,
+ &dev_attr_write_latency.attr,
+ NULL,
+};
+
+/**
+ * node_set_perf_attrs - Set the performance values for given access class
+ * @nid: Node identifier to be set
+ * @hmem_attrs: Heterogeneous memory performance attributes
+ * @access: The access class the for the given attributes
+ */
+void node_set_perf_attrs(unsigned int nid, struct node_hmem_attrs *hmem_attrs,
+ unsigned access)
+{
+ struct node_access_nodes *c;
+ struct node *node;
+ int i;
+
+ if (WARN_ON_ONCE(!node_online(nid)))
+ return;
+
+ node = node_devices[nid];
+ c = node_init_node_access(node, access);
+ if (!c)
+ return;
+
+ c->hmem_attrs = *hmem_attrs;
+ for (i = 0; access_attrs[i] != NULL; i++) {
+ if (sysfs_add_file_to_group(&c->dev.kobj, access_attrs[i],
+ "initiators")) {
+ pr_info("failed to add performance attribute to node %d\n",
+ nid);
+ break;
+ }
+ }
+}
+
+/**
+ * struct node_cache_info - Internal tracking for memory node caches
+ * @dev: Device represeting the cache level
+ * @node: List element for tracking in the node
+ * @cache_attrs:Attributes for this cache level
+ */
+struct node_cache_info {
+ struct device dev;
+ struct list_head node;
+ struct node_cache_attrs cache_attrs;
+};
+#define to_cache_info(device) container_of(device, struct node_cache_info, dev)
+
+#define CACHE_ATTR(name, fmt) \
+static ssize_t name##_show(struct device *dev, \
+ struct device_attribute *attr, \
+ char *buf) \
+{ \
+ return sprintf(buf, fmt "\n", to_cache_info(dev)->cache_attrs.name);\
+} \
+DEVICE_ATTR_RO(name);
+
+CACHE_ATTR(size, "%llu")
+CACHE_ATTR(line_size, "%u")
+CACHE_ATTR(indexing, "%u")
+CACHE_ATTR(write_policy, "%u")
+
+static struct attribute *cache_attrs[] = {
+ &dev_attr_indexing.attr,
+ &dev_attr_size.attr,
+ &dev_attr_line_size.attr,
+ &dev_attr_write_policy.attr,
+ NULL,
+};
+ATTRIBUTE_GROUPS(cache);
+
+static void node_cache_release(struct device *dev)
+{
+ kfree(dev);
+}
+
+static void node_cacheinfo_release(struct device *dev)
+{
+ struct node_cache_info *info = to_cache_info(dev);
+ kfree(info);
+}
+
+static void node_init_cache_dev(struct node *node)
+{
+ struct device *dev;
+
+ dev = kzalloc(sizeof(*dev), GFP_KERNEL);
+ if (!dev)
+ return;
+
+ dev->parent = &node->dev;
+ dev->release = node_cache_release;
+ if (dev_set_name(dev, "memory_side_cache"))
+ goto free_dev;
+
+ if (device_register(dev))
+ goto free_name;
+
+ pm_runtime_no_callbacks(dev);
+ node->cache_dev = dev;
+ return;
+free_name:
+ kfree_const(dev->kobj.name);
+free_dev:
+ kfree(dev);
+}
+
+/**
+ * node_add_cache() - add cache attribute to a memory node
+ * @nid: Node identifier that has new cache attributes
+ * @cache_attrs: Attributes for the cache being added
+ */
+void node_add_cache(unsigned int nid, struct node_cache_attrs *cache_attrs)
+{
+ struct node_cache_info *info;
+ struct device *dev;
+ struct node *node;
+
+ if (!node_online(nid) || !node_devices[nid])
+ return;
+
+ node = node_devices[nid];
+ list_for_each_entry(info, &node->cache_attrs, node) {
+ if (info->cache_attrs.level == cache_attrs->level) {
+ dev_warn(&node->dev,
+ "attempt to add duplicate cache level:%d\n",
+ cache_attrs->level);
+ return;
+ }
+ }
+
+ if (!node->cache_dev)
+ node_init_cache_dev(node);
+ if (!node->cache_dev)
+ return;
+
+ info = kzalloc(sizeof(*info), GFP_KERNEL);
+ if (!info)
+ return;
+
+ dev = &info->dev;
+ dev->parent = node->cache_dev;
+ dev->release = node_cacheinfo_release;
+ dev->groups = cache_groups;
+ if (dev_set_name(dev, "index%d", cache_attrs->level))
+ goto free_cache;
+
+ info->cache_attrs = *cache_attrs;
+ if (device_register(dev)) {
+ dev_warn(&node->dev, "failed to add cache level:%d\n",
+ cache_attrs->level);
+ goto free_name;
+ }
+ pm_runtime_no_callbacks(dev);
+ list_add_tail(&info->node, &node->cache_attrs);
+ return;
+free_name:
+ kfree_const(dev->kobj.name);
+free_cache:
+ kfree(info);
+}
+
+static void node_remove_caches(struct node *node)
+{
+ struct node_cache_info *info, *next;
+
+ if (!node->cache_dev)
+ return;
+
+ list_for_each_entry_safe(info, next, &node->cache_attrs, node) {
+ list_del(&info->node);
+ device_unregister(&info->dev);
+ }
+ device_unregister(node->cache_dev);
+}
+
+static void node_init_caches(unsigned int nid)
+{
+ INIT_LIST_HEAD(&node_devices[nid]->cache_attrs);
+}
+#else
+static void node_init_caches(unsigned int nid) { }
+static void node_remove_caches(struct node *node) { }
+#endif
+
#define K(x) ((x) << (PAGE_SHIFT - 10))
static ssize_t node_read_meminfo(struct device *dev,
struct device_attribute *attr, char *buf)
@@ -67,8 +365,11 @@
int nid = dev->id;
struct pglist_data *pgdat = NODE_DATA(nid);
struct sysinfo i;
+ unsigned long sreclaimable, sunreclaimable;
si_meminfo_node(&i, nid);
+ sreclaimable = node_page_state(pgdat, NR_SLAB_RECLAIMABLE);
+ sunreclaimable = node_page_state(pgdat, NR_SLAB_UNRECLAIMABLE);
n = sprintf(buf,
"Node %d MemTotal: %8lu kB\n"
"Node %d MemFree: %8lu kB\n"
@@ -118,6 +419,7 @@
"Node %d NFS_Unstable: %8lu kB\n"
"Node %d Bounce: %8lu kB\n"
"Node %d WritebackTmp: %8lu kB\n"
+ "Node %d KReclaimable: %8lu kB\n"
"Node %d Slab: %8lu kB\n"
"Node %d SReclaimable: %8lu kB\n"
"Node %d SUnreclaim: %8lu kB\n"
@@ -125,6 +427,8 @@
"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"
#endif
,
nid, K(node_page_state(pgdat, NR_FILE_DIRTY)),
@@ -138,20 +442,25 @@
nid, K(node_page_state(pgdat, NR_UNSTABLE_NFS)),
nid, K(sum_zone_node_page_state(nid, NR_BOUNCE)),
nid, K(node_page_state(pgdat, NR_WRITEBACK_TEMP)),
- nid, K(node_page_state(pgdat, NR_SLAB_RECLAIMABLE) +
- node_page_state(pgdat, NR_SLAB_UNRECLAIMABLE)),
- nid, K(node_page_state(pgdat, NR_SLAB_RECLAIMABLE)),
+ nid, K(sreclaimable +
+ node_page_state(pgdat, NR_KERNEL_MISC_RECLAIMABLE)),
+ nid, K(sreclaimable + sunreclaimable),
+ nid, K(sreclaimable),
+ nid, K(sunreclaimable)
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
- nid, K(node_page_state(pgdat, NR_SLAB_UNRECLAIMABLE)),
+ ,
nid, K(node_page_state(pgdat, NR_ANON_THPS) *
HPAGE_PMD_NR),
nid, K(node_page_state(pgdat, NR_SHMEM_THPS) *
HPAGE_PMD_NR),
nid, K(node_page_state(pgdat, NR_SHMEM_PMDMAPPED) *
- HPAGE_PMD_NR));
-#else
- nid, K(node_page_state(pgdat, NR_SLAB_UNRECLAIMABLE)));
+ HPAGE_PMD_NR),
+ nid, K(node_page_state(pgdat, NR_FILE_THPS) *
+ HPAGE_PMD_NR),
+ nid, K(node_page_state(pgdat, NR_FILE_PMDMAPPED) *
+ HPAGE_PMD_NR)
#endif
+ );
n += hugetlb_report_node_meminfo(nid, buf + n);
return n;
}
@@ -335,7 +644,8 @@
void unregister_node(struct node *node)
{
hugetlb_unregister_node(node); /* no-op, if memoryless node */
-
+ node_remove_accesses(node);
+ node_remove_caches(node);
device_unregister(&node->dev);
}
@@ -367,6 +677,56 @@
kobject_name(&node_devices[nid]->dev.kobj));
}
+/**
+ * register_memory_node_under_compute_node - link memory node to its compute
+ * node for a given access class.
+ * @mem_nid: Memory node number
+ * @cpu_nid: Cpu node number
+ * @access: Access class to register
+ *
+ * Description:
+ * For use with platforms that may have separate memory and compute nodes.
+ * This function will export node relationships linking which memory
+ * initiator nodes can access memory targets at a given ranked access
+ * class.
+ */
+int register_memory_node_under_compute_node(unsigned int mem_nid,
+ unsigned int cpu_nid,
+ unsigned access)
+{
+ struct node *init_node, *targ_node;
+ struct node_access_nodes *initiator, *target;
+ int ret;
+
+ if (!node_online(cpu_nid) || !node_online(mem_nid))
+ return -ENODEV;
+
+ init_node = node_devices[cpu_nid];
+ targ_node = node_devices[mem_nid];
+ initiator = node_init_node_access(init_node, access);
+ target = node_init_node_access(targ_node, access);
+ if (!initiator || !target)
+ return -ENOMEM;
+
+ ret = sysfs_add_link_to_group(&initiator->dev.kobj, "targets",
+ &targ_node->dev.kobj,
+ dev_name(&targ_node->dev));
+ if (ret)
+ return ret;
+
+ ret = sysfs_add_link_to_group(&target->dev.kobj, "initiators",
+ &init_node->dev.kobj,
+ dev_name(&init_node->dev));
+ if (ret)
+ goto err;
+
+ return 0;
+ err:
+ sysfs_remove_link_from_group(&initiator->dev.kobj, "targets",
+ dev_name(&targ_node->dev));
+ return ret;
+}
+
int unregister_cpu_under_node(unsigned int cpu, unsigned int nid)
{
struct device *obj;
@@ -399,17 +759,16 @@
}
/* register memory section under specified node if it spans that node */
-int register_mem_sect_under_node(struct memory_block *mem_blk, void *arg)
+static int register_mem_sect_under_node(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 ret, nid = *(int *)arg;
- unsigned long pfn, sect_start_pfn, sect_end_pfn;
+ unsigned long pfn;
- mem_blk->nid = nid;
-
- sect_start_pfn = section_nr_to_pfn(mem_blk->start_section_nr);
- sect_end_pfn = section_nr_to_pfn(mem_blk->end_section_nr);
- sect_end_pfn += PAGES_PER_SECTION - 1;
- for (pfn = sect_start_pfn; pfn <= sect_end_pfn; pfn++) {
+ for (pfn = start_pfn; pfn <= end_pfn; pfn++) {
int page_nid;
/*
@@ -434,6 +793,13 @@
if (page_nid != nid)
continue;
}
+
+ /*
+ * If this memory block spans multiple nodes, we only indicate
+ * the last processed node.
+ */
+ mem_blk->nid = nid;
+
ret = sysfs_create_link_nowarn(&node_devices[nid]->dev.kobj,
&mem_blk->dev.kobj,
kobject_name(&mem_blk->dev.kobj));
@@ -448,46 +814,26 @@
return 0;
}
-/* unregister memory section under all nodes that it spans */
-int unregister_mem_sect_under_nodes(struct memory_block *mem_blk,
- unsigned long phys_index)
+/*
+ * Unregister a memory block device under the node it spans. Memory blocks
+ * with multiple nodes cannot be offlined and therefore also never be removed.
+ */
+void unregister_memory_block_under_nodes(struct memory_block *mem_blk)
{
- NODEMASK_ALLOC(nodemask_t, unlinked_nodes, GFP_KERNEL);
- unsigned long pfn, sect_start_pfn, sect_end_pfn;
+ if (mem_blk->nid == NUMA_NO_NODE)
+ return;
- if (!mem_blk) {
- NODEMASK_FREE(unlinked_nodes);
- return -EFAULT;
- }
- if (!unlinked_nodes)
- return -ENOMEM;
- nodes_clear(*unlinked_nodes);
-
- sect_start_pfn = section_nr_to_pfn(phys_index);
- sect_end_pfn = sect_start_pfn + PAGES_PER_SECTION - 1;
- for (pfn = sect_start_pfn; pfn <= sect_end_pfn; pfn++) {
- int nid;
-
- nid = get_nid_for_pfn(pfn);
- if (nid < 0)
- continue;
- if (!node_online(nid))
- continue;
- if (node_test_and_set(nid, *unlinked_nodes))
- continue;
- sysfs_remove_link(&node_devices[nid]->dev.kobj,
- kobject_name(&mem_blk->dev.kobj));
- sysfs_remove_link(&mem_blk->dev.kobj,
- kobject_name(&node_devices[nid]->dev.kobj));
- }
- NODEMASK_FREE(unlinked_nodes);
- return 0;
+ sysfs_remove_link(&node_devices[mem_blk->nid]->dev.kobj,
+ kobject_name(&mem_blk->dev.kobj));
+ sysfs_remove_link(&mem_blk->dev.kobj,
+ kobject_name(&node_devices[mem_blk->nid]->dev.kobj));
}
int link_mem_sections(int nid, unsigned long start_pfn, unsigned long end_pfn)
{
- return walk_memory_range(start_pfn, end_pfn, (void *)&nid,
- register_mem_sect_under_node);
+ return walk_memory_blocks(PFN_PHYS(start_pfn),
+ PFN_PHYS(end_pfn - start_pfn), (void *)&nid,
+ register_mem_sect_under_node);
}
#ifdef CONFIG_HUGETLBFS
@@ -575,8 +921,10 @@
register_cpu_under_node(cpu, nid);
}
+ INIT_LIST_HEAD(&node_devices[nid]->access_list);
/* initialize work queue for memory hot plug */
init_node_hugetlb_work(nid);
+ node_init_caches(nid);
return error;
}