| Message ID | 20220610135229.182859-5-aneesh.kumar@linux.ibm.com (mailing list archive) |
|---|---|
| State | New |
| Headers | show |
| Series | mm/demotion: Memory tiers and demotion | expand |
On Fri, 2022-06-10 at 19:22 +0530, Aneesh Kumar K.V wrote: > By default, all nodes are assigned to DEFAULT_MEMORY_TIER which > is the memory tier designated for nodes with DRAM > > Set dax kmem device node's tier to MEMORY_TIER_PMEM. MEMORY_TIER_PMEM > is assigned a default rank value of 100 and appears below DEFAULT_MEMORY_TIER > in demotion order. > > Signed-off-by: Jagdish Gediya <jvgediya@linux.ibm.com> > Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> > --- > drivers/dax/kmem.c | 4 ++ > include/linux/memory-tiers.h | 1 + > mm/memory-tiers.c | 78 ++++++++++++++++++++++++++++++++++++ > 3 files changed, 83 insertions(+) > > diff --git a/drivers/dax/kmem.c b/drivers/dax/kmem.c > index a37622060fff..0cb3de3d138f 100644 > --- a/drivers/dax/kmem.c > +++ b/drivers/dax/kmem.c > @@ -11,6 +11,7 @@ > #include <linux/fs.h> > #include <linux/mm.h> > #include <linux/mman.h> > +#include <linux/memory-tiers.h> > #include "dax-private.h" > #include "bus.h" > > > @@ -147,6 +148,9 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax) > > > dev_set_drvdata(dev, data); > > > +#ifdef CONFIG_TIERED_MEMORY > + node_create_and_set_memory_tier(numa_node, MEMORY_TIER_PMEM); > +#endif > return 0; > > > err_request_mem: > diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h > index 44c3c3b16a36..e102ec73ab80 100644 > --- a/include/linux/memory-tiers.h > +++ b/include/linux/memory-tiers.h > @@ -18,6 +18,7 @@ > #define MAX_MEMORY_TIERS 3 > > > extern bool numa_demotion_enabled; > +int node_create_and_set_memory_tier(int node, int tier); > #else > #define numa_demotion_enabled false > > > diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c > index c3123a457d90..00d393a5a628 100644 > --- a/mm/memory-tiers.c > +++ b/mm/memory-tiers.c > @@ -67,6 +67,84 @@ static struct memory_tier *register_memory_tier(unsigned int tier, > return memtier; > } > > > +static struct memory_tier *__node_get_memory_tier(int node) > +{ > + struct memory_tier *memtier; > + > + list_for_each_entry(memtier, &memory_tiers, list) { > + if (node_isset(node, memtier->nodelist)) > + return memtier; > + } > + return NULL; > +} > + I suggest to add NODE_DATA(nid)->mem_tier before this patch. That is, part of [9/13]. That will make code much simpler and easier to review. And, in addition to dax_kmem, whenever a normal node is onlined, we need to add it to the default memory tier. I found this is done in [5/13]. IMHO, we should move that part before this patch. Best Regards, Huang, Ying > +static struct memory_tier *__get_memory_tier_from_id(int id) > +{ > + struct memory_tier *memtier; > + > + list_for_each_entry(memtier, &memory_tiers, list) { > + if (memtier->id == id) > + return memtier; > + } > + return NULL; > +} > + > +static int __node_create_and_set_memory_tier(int node, int tier) > +{ > + int ret = 0; > + struct memory_tier *memtier; > + > + memtier = __get_memory_tier_from_id(tier); > + if (!memtier) { > + int rank; > + > + rank = get_rank_from_tier(tier); > + if (rank == -1) { > + ret = -EINVAL; > + goto out; > + } > + memtier = register_memory_tier(tier, rank); > + if (!memtier) { > + ret = -EINVAL; > + goto out; > + } > + } > + node_set(node, memtier->nodelist); > +out: > + return ret; > +} > + > +int node_create_and_set_memory_tier(int node, int tier) > +{ > + struct memory_tier *current_tier; > + int ret = 0; > + > + mutex_lock(&memory_tier_lock); > + > + current_tier = __node_get_memory_tier(node); > + if (!current_tier) { > + ret = __node_create_and_set_memory_tier(node, tier); > + goto out; > + } > + > + if (current_tier->id == tier) > + goto out; > + > + node_clear(node, current_tier->nodelist); > + > + ret = __node_create_and_set_memory_tier(node, tier); > + if (ret) { > + /* reset it back to older tier */ > + node_set(node, current_tier->nodelist); > + goto out; > + } > +out: > + mutex_unlock(&memory_tier_lock); > + > + return ret; > +} > +EXPORT_SYMBOL_GPL(node_create_and_set_memory_tier); > + > static int __init memory_tier_init(void) > { > struct memory_tier *memtier;
On 6/13/22 12:29 PM, Ying Huang wrote: > On Fri, 2022-06-10 at 19:22 +0530, Aneesh Kumar K.V wrote: >> By default, all nodes are assigned to DEFAULT_MEMORY_TIER which >> is the memory tier designated for nodes with DRAM >> >> Set dax kmem device node's tier to MEMORY_TIER_PMEM. MEMORY_TIER_PMEM >> is assigned a default rank value of 100 and appears below DEFAULT_MEMORY_TIER >> in demotion order. >> >> Signed-off-by: Jagdish Gediya <jvgediya@linux.ibm.com> >> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> >> --- >> drivers/dax/kmem.c | 4 ++ >> include/linux/memory-tiers.h | 1 + >> mm/memory-tiers.c | 78 ++++++++++++++++++++++++++++++++++++ >> 3 files changed, 83 insertions(+) >> >> diff --git a/drivers/dax/kmem.c b/drivers/dax/kmem.c >> index a37622060fff..0cb3de3d138f 100644 >> --- a/drivers/dax/kmem.c >> +++ b/drivers/dax/kmem.c >> @@ -11,6 +11,7 @@ >> #include <linux/fs.h> >> #include <linux/mm.h> >> #include <linux/mman.h> >> +#include <linux/memory-tiers.h> >> #include "dax-private.h" >> #include "bus.h" >> >> >> @@ -147,6 +148,9 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax) >> >> >> dev_set_drvdata(dev, data); >> >> >> +#ifdef CONFIG_TIERED_MEMORY >> + node_create_and_set_memory_tier(numa_node, MEMORY_TIER_PMEM); >> +#endif >> return 0; >> >> >> err_request_mem: >> diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h >> index 44c3c3b16a36..e102ec73ab80 100644 >> --- a/include/linux/memory-tiers.h >> +++ b/include/linux/memory-tiers.h >> @@ -18,6 +18,7 @@ >> #define MAX_MEMORY_TIERS 3 >> >> >> extern bool numa_demotion_enabled; >> +int node_create_and_set_memory_tier(int node, int tier); >> #else >> #define numa_demotion_enabled false >> >> >> diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c >> index c3123a457d90..00d393a5a628 100644 >> --- a/mm/memory-tiers.c >> +++ b/mm/memory-tiers.c >> @@ -67,6 +67,84 @@ static struct memory_tier *register_memory_tier(unsigned int tier, >> return memtier; >> } >> >> >> +static struct memory_tier *__node_get_memory_tier(int node) >> +{ >> + struct memory_tier *memtier; >> + >> + list_for_each_entry(memtier, &memory_tiers, list) { >> + if (node_isset(node, memtier->nodelist)) >> + return memtier; >> + } >> + return NULL; >> +} >> + > > I suggest to add NODE_DATA(nid)->mem_tier before this patch. That is, > part of [9/13]. That will make code much simpler and easier to > review. > I would still like to keep introducing that NODE_DATA()->memtier later, so that the everything before that can be reviewed with simpler locking. __node_get_memory_tier() get fixed in patch 9 where all the details of that lockless access is documented. This also enables one to look at the history later. > And, in addition to dax_kmem, whenever a normal node is onlined, we > need to add it to the default memory tier. I found this is done in > [5/13]. IMHO, we should move that part before this patch. > Sure will move the hotplug callback earlier. -aneesh
diff --git a/drivers/dax/kmem.c b/drivers/dax/kmem.c index a37622060fff..0cb3de3d138f 100644 --- a/drivers/dax/kmem.c +++ b/drivers/dax/kmem.c @@ -11,6 +11,7 @@ #include <linux/fs.h> #include <linux/mm.h> #include <linux/mman.h> +#include <linux/memory-tiers.h> #include "dax-private.h" #include "bus.h" @@ -147,6 +148,9 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax) dev_set_drvdata(dev, data); +#ifdef CONFIG_TIERED_MEMORY + node_create_and_set_memory_tier(numa_node, MEMORY_TIER_PMEM); +#endif return 0; err_request_mem: diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h index 44c3c3b16a36..e102ec73ab80 100644 --- a/include/linux/memory-tiers.h +++ b/include/linux/memory-tiers.h @@ -18,6 +18,7 @@ #define MAX_MEMORY_TIERS 3 extern bool numa_demotion_enabled; +int node_create_and_set_memory_tier(int node, int tier); #else #define numa_demotion_enabled false diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c index c3123a457d90..00d393a5a628 100644 --- a/mm/memory-tiers.c +++ b/mm/memory-tiers.c @@ -67,6 +67,84 @@ static struct memory_tier *register_memory_tier(unsigned int tier, return memtier; } +static struct memory_tier *__node_get_memory_tier(int node) +{ + struct memory_tier *memtier; + + list_for_each_entry(memtier, &memory_tiers, list) { + if (node_isset(node, memtier->nodelist)) + return memtier; + } + return NULL; +} + +static struct memory_tier *__get_memory_tier_from_id(int id) +{ + struct memory_tier *memtier; + + list_for_each_entry(memtier, &memory_tiers, list) { + if (memtier->id == id) + return memtier; + } + return NULL; +} + +static int __node_create_and_set_memory_tier(int node, int tier) +{ + int ret = 0; + struct memory_tier *memtier; + + memtier = __get_memory_tier_from_id(tier); + if (!memtier) { + int rank; + + rank = get_rank_from_tier(tier); + if (rank == -1) { + ret = -EINVAL; + goto out; + } + memtier = register_memory_tier(tier, rank); + if (!memtier) { + ret = -EINVAL; + goto out; + } + } + node_set(node, memtier->nodelist); +out: + return ret; +} + +int node_create_and_set_memory_tier(int node, int tier) +{ + struct memory_tier *current_tier; + int ret = 0; + + mutex_lock(&memory_tier_lock); + + current_tier = __node_get_memory_tier(node); + if (!current_tier) { + ret = __node_create_and_set_memory_tier(node, tier); + goto out; + } + + if (current_tier->id == tier) + goto out; + + node_clear(node, current_tier->nodelist); + + ret = __node_create_and_set_memory_tier(node, tier); + if (ret) { + /* reset it back to older tier */ + node_set(node, current_tier->nodelist); + goto out; + } +out: + mutex_unlock(&memory_tier_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(node_create_and_set_memory_tier); + static int __init memory_tier_init(void) { struct memory_tier *memtier;