memory tiering: calculate abstract distance based on ACPI HMAT
Subsystems (4)
cover memory tiering: calculate abstract distance based on ACPI HMAT
We have the explicit memory tiers framework to manage systems with multiple types of memory, e.g., DRAM in DIMM slots and CXL memory devices. Where, same kind of memory devices will be grouped into memory types, then put into memory tiers. To describe the performance of a memory type, abstract distance is defined. Which is in direct proportion to the memory latency and inversely proportional to the memory bandwidth. To keep the code as simple as possible, fixed abstract distance is used in dax/kmem to describe slow memory such as Optane DCPMM.
To support more memory types, in this series, we added the abstract distance calculation algorithm management mechanism, provided a algorithm implementation based on ACPI HMAT, and used the general abstract distance calculation interface in dax/kmem driver. So, dax/kmem can support HBM (high bandwidth memory) in addition to the original Optane DCPMM.
Changelog:
v4:
- Fix and optimize the error processing. Thanks Alistair's comments!
- Collected reviewed-by.
v3:
- Move algorithm to calculate abstract distance from read/write latency/bandwidth from hmat.c to memory-ters.c per Alistair's comments.
- Fix memory types putting in kmem.c for error path.
V2:
- Fix a typo in 4/4.
- Collected reviewed-by and tested-by.
V1 (from RFC):
- Added some comments per Aneesh's comments, Thanks!
Best Regards,
Huang, Ying
PATCH 1/4 memory tiering: add abstract distance calculation algorithms management
The abstract distance may be calculated by various drivers, such as ACPI HMAT, CXL CDAT, etc. While it may be used by various code which hot-add memory node, such as dax/kmem etc. To decouple the algorithm users and the providers, the abstract distance calculation algorithms management mechanism is implemented in this patch. It provides interface for the providers to register the implementation, and interface for the users.
Multiple algorithm implementations can cooperate via calculating abstract distance for different memory nodes. The preference of algorithm implementations can be specified via priority (notifier_block.priority).
--- include/linux/memory-tiers.h | 19 ++++++++++++ mm/memory-tiers.c | 59 ++++++++++++++++++++++++++++++++++++ 2 files changed, 78 insertions(+)
include/linux/memory-tiers.h +19 -0
@@ -6,6 +6,7 @@#include <linux/nodemask.h> #include <linux/kref.h> #include <linux/mmzone.h> +#include <linux/notifier.h> /* * Each tier cover a abstrace distance chunk size of 128 */
@@ -36,6 +37,9 @@ struct memory_dev_type *alloc_memory_type(int adistance);void put_memory_type (struct memory_dev_type *memtype);void init_node_memory_type (int node,struct memory_dev_type *default_type);void clear_node_memory_type (int node,struct memory_dev_type *memtype); +int register_mt_adistance_algorithm (struct notifier_block *nb); +int unregister_mt_adistance_algorithm (struct notifier_block *nb); +int mt_calc_adistance (int node,int *adist);#ifdef CONFIG_MIGRATION int next_demotion_node (int node);void node_get_allowed_targets (pg_data_t *pgdat,nodemask_t *targets);
@@ -97,5 +101,20 @@ static inline bool node_is_toptier(int node) {return true; } + +static inline int register_mt_adistance_algorithm (struct notifier_block *nb) +{ +return 0 ; +} + +static inline int unregister_mt_adistance_algorithm (struct notifier_block *nb) +{ +return 0 ; +} + +static inline int mt_calc_adistance (int node,int *adist) +{ +return NOTIFY_DONE ; +}#endif /* CONFIG_NUMA */ #endif /* _LINUX_MEMORY_TIERS_H */
mm/memory-tiers.c +59 -0
77 lines not on this page · raw message
Signature · 1 line
2.39.2
PATCH 2/4 acpi, hmat: refactor hmat_register_target_initiators()
In reply to Huang YingPreviously, in hmat_register_target_initiators(), the performance attributes are calculated and the corresponding sysfs links and files are created too. Which is called during memory onlining.
But now, to calculate the abstract distance of a memory target before memory onlining, we need to calculate the performance attributes for a memory target without creating sysfs links and files.
To do that, hmat_register_target_initiators() is refactored to make it possible to calculate performance attributes separately.
--- drivers/acpi/numa/hmat.c | 81 +++++++++++++++------------------------- 1 file changed, 30 insertions(+), 51 deletions(-)
drivers/acpi/numa/hmat.c +30 -51
@@ -582,28 +582,25 @@ static int initiators_to_nodemask(unsigned long *p_nodes)return 0 ; } -static void hmat_register_target_initiators (struct memory_target *target) +static void hmat_update_target_attrs (struct memory_target *target, +unsigned long *p_nodes,int access) { - static DECLARE_BITMAP(p_nodes, MAX_NUMNODES);struct memory_initiator *initiator; -unsigned int mem_nid, cpu_nid; +unsigned int cpu_nid;struct memory_locality *loc =NULL ;u32 best =0 ; -bool access0done = false;int i; - mem_nid =pxm_to_node (target->memory_pxm); +bitmap_zero (p_nodes,MAX_NUMNODES );/* -* If the Address Range Structure provides a local processor pxm, link +* If the Address Range Structure provides a local processor pxm, set * only that one. Otherwise, find the best performance attributes and -* register all initiators that match. +* collect all initiators that match. */ if (target->processor_pxm !=PXM_INVAL ) { cpu_nid =pxm_to_node (target->processor_pxm); -register_memory_node_under_compute_node (mem_nid, cpu_nid,0 ); - access0done = true; -if (node_state (cpu_nid,N_CPU )) { -register_memory_node_under_compute_node (mem_nid, cpu_nid,1 ); +if (access ==0 ||node_state (cpu_nid,N_CPU )) { +set_bit (target->processor_pxm, p_nodes);return ; } }
@@ -617,47 +614,10 @@ static void hmat_register_target_initiators(struct memory_target *target)* We'll also use the sorting to prime the candidate nodes with known * initiators. */ -bitmap_zero (p_nodes,MAX_NUMNODES );list_sort (NULL , &initiators, initiator_cmp);if (initiators_to_nodemask (p_nodes) <0 )return ; -if (!access0done) { -for (i =WRITE_LATENCY ; i <=READ_BANDWIDTH ; i++) { - loc = localities_types[i]; -if (!loc) -continue ; - - best =0 ; -list_for_each_entry (initiator, &initiators, node) { -u32 value; - -if (!test_bit (initiator->processor_pxm, p_nodes)) -continue ; - - value =hmat_initiator_perf (target, initiator, - loc->hmat_loc); -if (hmat_update_best (loc->hmat_loc->data_type, value, &best)) -bitmap_clear (p_nodes,0 , initiator->processor_pxm); -if (value != best) -clear_bit (initiator->processor_pxm, p_nodes); - } -if (best) -hmat_update_target_access (target, loc->hmat_loc->data_type, - best,0 ); - } - -for_each_set_bit (i, p_nodes,MAX_NUMNODES ) { - cpu_nid =pxm_to_node (i); -register_memory_node_under_compute_node (mem_nid, cpu_nid,0 ); - } - } - -/* Access 1 ignores Generic Initiators */ -bitmap_zero (p_nodes,MAX_NUMNODES ); -if (initiators_to_nodemask (p_nodes) <0 ) -return ; -for (i =WRITE_LATENCY ; i <=READ_BANDWIDTH ; i++) { loc = localities_types[i];if (!loc)
@@ -667,7 +627,7 @@ static void hmat_register_target_initiators(struct memory_target *target)list_for_each_entry (initiator, &initiators, node) {u32 value; -if (!initiator->has_cpu) { +if (access ==1 && !initiator->has_cpu) {clear_bit (initiator->processor_pxm, p_nodes);continue ; }
@@ -681,14 +641,33 @@ static void hmat_register_target_initiators(struct memory_target *target)clear_bit (initiator->processor_pxm, p_nodes); }if (best) -hmat_update_target_access (target, loc->hmat_loc->data_type, best,1 ); +hmat_update_target_access (target, loc->hmat_loc->data_type, best, access); } +} + +static void __hmat_register_target_initiators (struct memory_target *target, +unsigned long *p_nodes, +int access) +{ +unsigned int mem_nid, cpu_nid; +int i; + + mem_nid =pxm_to_node (target->memory_pxm); +hmat_update_target_attrs (target, p_nodes, access);for_each_set_bit (i, p_nodes,MAX_NUMNODES ) { cpu_nid =pxm_to_node (i); -register_memory_node_under_compute_node (mem_nid, cpu_nid,1 ); +register_memory_node_under_compute_node (mem_nid, cpu_nid, access); } } +static void hmat_register_target_initiators (struct memory_target *target) +{ + static DECLARE_BITMAP(p_nodes, MAX_NUMNODES); + +__hmat_register_target_initiators (target, p_nodes,0 ); +__hmat_register_target_initiators (target, p_nodes,1 ); +} +static void hmat_register_target_cache (struct memory_target *target) {unsigned mem_nid =pxm_to_node (target->memory_pxm);
Signature · 1 line
2.39.2
PATCH 3/4 acpi, hmat: calculate abstract distance with HMAT
In reply to Huang YingA memory tiering abstract distance calculation algorithm based on ACPI HMAT is implemented. The basic idea is as follows.
The performance attributes of system default DRAM nodes are recorded as the base line. Whose abstract distance is MEMTIER_ADISTANCE_DRAM. Then, the ratio of the abstract distance of a memory node (target) to MEMTIER_ADISTANCE_DRAM is scaled based on the ratio of the performance attributes of the node to that of the default DRAM nodes.
The functions to record the read/write latency/bandwidth of the default DRAM nodes and calculate abstract distance according to read/write latency/bandwidth ratio will be used by CXL CDAT (Coherent Device Attribute Table) and other memory device drivers. So, they are put in memory-tiers.c.
--- drivers/acpi/numa/hmat.c | 65 +++++++++++++++++++++- include/linux/memory-tiers.h | 18 ++++++ mm/memory-tiers.c | 103 ++++++++++++++++++++++++++++++++++- 3 files changed, 183 insertions(+), 3 deletions(-)
drivers/acpi/numa/hmat.c +63 -2
@@ -24,6 +24,7 @@#include <linux/node.h> #include <linux/sysfs.h> #include <linux/dax.h> +#include <linux/memory-tiers.h> static u8 hmat_revision;static int hmat_disable__initdata ;
@@ -759,6 +760,61 @@ static int hmat_callback(struct notifier_block *self,return NOTIFY_OK ; } +static int hmat_set_default_dram_perf (void ) +{ +int rc; +int nid, pxm; +struct memory_target *target; +struct node_hmem_attrs *attrs; + +if (!default_dram_type) +return -EIO ; + +for_each_node_mask (nid, default_dram_type->nodes) { + pxm =node_to_pxm (nid); + target =find_mem_target (pxm); +if (!target) +continue ; + attrs = &target->hmem_attrs[1 ]; + rc =mt_set_default_dram_perf (nid, attrs,"ACPI HMAT" ); +if (rc) +return rc; + } + +return 0 ; +} + +static int hmat_calculate_adistance (struct notifier_block *self, +unsigned long nid,void *data) +{ + static DECLARE_BITMAP(p_nodes, MAX_NUMNODES); +struct memory_target *target; +struct node_hmem_attrs *perf; +int *adist = data; +int pxm; + + pxm =node_to_pxm (nid); + target =find_mem_target (pxm); +if (!target) +return NOTIFY_OK ; + +mutex_lock (&target_lock); +hmat_update_target_attrs (target, p_nodes,1 ); +mutex_unlock (&target_lock); + + perf = &target->hmem_attrs[1 ]; + +if (mt_perf_to_adistance (perf, adist)) +return NOTIFY_OK ; + +return NOTIFY_STOP ; +} + +static struct notifier_block hmat_adist_nb__meminitdata = { + .notifier_call = hmat_calculate_adistance, + .priority =100 , +}; +static __init void hmat_free_structures (void ) {struct memory_target *target, *tnext;
@@ -841,8 +897,13 @@ static __init int hmat_init(void)hmat_register_targets ();/* Keep the table and structures if the notifier may use them */ -if (!hotplug_memory_notifier (hmat_callback,HMAT_CALLBACK_PRI )) -return 0 ; +if (hotplug_memory_notifier (hmat_callback,HMAT_CALLBACK_PRI )) + goto out_put; + +if (!hmat_set_default_dram_perf ()) +register_mt_adistance_algorithm (&hmat_adist_nb); + +return 0 ; out_put:hmat_free_structures ();acpi_put_table (tbl);
include/linux/memory-tiers.h +18 -0
@@ -31,8 +31,11 @@ struct memory_dev_type {struct kref kref; }; +struct node_hmem_attrs ; +#ifdef CONFIG_NUMA extern bool numa_demotion_enabled; +extern struct memory_dev_type *default_dram_type;struct memory_dev_type *alloc_memory_type (int adistance);void put_memory_type (struct memory_dev_type *memtype);void init_node_memory_type (int node,struct memory_dev_type *default_type);
@@ -40,6 +43,9 @@ void clear_node_memory_type(int node, struct memory_dev_type *memtype);int register_mt_adistance_algorithm (struct notifier_block *nb);int unregister_mt_adistance_algorithm (struct notifier_block *nb);int mt_calc_adistance (int node,int *adist); +int mt_set_default_dram_perf (int nid,struct node_hmem_attrs *perf, +const char *source); +int mt_perf_to_adistance (struct node_hmem_attrs *perf,int *adist);#ifdef CONFIG_MIGRATION int next_demotion_node (int node);void node_get_allowed_targets (pg_data_t *pgdat,nodemask_t *targets);
@@ -64,6 +70,7 @@ static inline bool node_is_toptier(int node)#else #define numa_demotion_enabled false +#define default_dram_type NULL/* * CONFIG_NUMA implementation returns non NULL error. */
@@ -116,5 +123,16 @@ static inline int mt_calc_adistance(int node, int *adist) {return NOTIFY_DONE ; } + +static inline int mt_set_default_dram_perf (int nid,struct node_hmem_attrs *perf, +const char *source) +{ +return -EIO ; +} + +static inline int mt_perf_to_adistance (struct node_hmem_attrs *perf,int *adist) +{ +return -EIO ; +}#endif /* CONFIG_NUMA */ #endif /* _LINUX_MEMORY_TIERS_H */
mm/memory-tiers.c +102 -1
121 lines not on this page · raw message
Signature · 1 line
2.39.2
Re: [PATCH -V4 3/4] acpi, hmat: calculate abstract distance with HMAT
Quoted 9 lines · Huang Ying
A memory tiering abstract distance calculation algorithm based on ACPI HMAT is implemented. The basic idea is as follows.
The performance attributes of system default DRAM nodes are recorded as the base line. Whose abstract distance is
MEMTIER_ADISTANCE_DRAM. Then, the ratio of the abstract distance of a memory node (target) toMEMTIER_ADISTANCE_DRAMis scaled based on the ratio of the performance attributes of the node to that of the default DRAM nodes.
Quoted 5 lines
The functions to record the read/write latency/bandwidth of the default DRAM nodes and calculate abstract distance according to read/write latency/bandwidth ratio will be used by CXL CDAT (Coherent Device Attribute Table) and other memory device drivers. So, they are put in
memory-tiers.c.
Thanks for addressing my previous comments, please add:
Quoted 289 lines
Signed-off-by "Huang, Ying" <[email protected]>Tested-by Bharata B Rao <[email protected]>Reviewed-by Dave Jiang <[email protected]>Cc Aneesh Kumar K.V <[email protected]>Cc Wei Xu <[email protected]>Cc Alistair Popple <[email protected]>Cc Dan Williams <[email protected]>Cc Dave Hansen <[email protected]>Cc Davidlohr Bueso <[email protected]>Cc Johannes Weiner <[email protected]>Cc Jonathan Cameron <[email protected]>Cc Michal Hocko <[email protected]>Cc Yang Shi <[email protected]>Cc Rafael J Wysocki <[email protected]>--- drivers/acpi/numa/hmat.c | 65 +++++++++++++++++++++- include/linux/memory-tiers.h | 18 ++++++ mm/memory-tiers.c | 103 ++++++++++++++++++++++++++++++++++- 3 files changed, 183 insertions(+), 3 deletions(-)drivers/acpi/numa/hmat.c +63
-2@@ -24,6 +24,7 @@#include <linux/node.h> #include <linux/sysfs.h> #include <linux/dax.h> +#include <linux/memory-tiers.h> static u8 hmat_revision;static int hmat_disable__initdata ;@@ -759,6 +760,61 @@ static int hmat_callback(struct notifier_block *self,return NOTIFY_OK ; } +static int hmat_set_default_dram_perf (void ) +{ +int rc; +int nid, pxm; +struct memory_target *target; +struct node_hmem_attrs *attrs; + +if (!default_dram_type) +return -EIO ; + +for_each_node_mask (nid, default_dram_type->nodes) { + pxm =node_to_pxm (nid); + target =find_mem_target (pxm); +if (!target) +continue ; + attrs = &target->hmem_attrs[1 ]; + rc =mt_set_default_dram_perf (nid, attrs,"ACPI HMAT" ); +if (rc) +return rc; + } + +return 0 ; +} + +static int hmat_calculate_adistance (struct notifier_block *self, +unsigned long nid,void *data) +{ + static DECLARE_BITMAP(p_nodes, MAX_NUMNODES); +struct memory_target *target; +struct node_hmem_attrs *perf; +int *adist = data; +int pxm; + + pxm =node_to_pxm (nid); + target =find_mem_target (pxm); +if (!target) +return NOTIFY_OK ; + +mutex_lock (&target_lock); +hmat_update_target_attrs (target, p_nodes,1 ); +mutex_unlock (&target_lock); + + perf = &target->hmem_attrs[1 ]; + +if (mt_perf_to_adistance (perf, adist)) +return NOTIFY_OK ; + +return NOTIFY_STOP ; +} + +static struct notifier_block hmat_adist_nb__meminitdata = { + .notifier_call = hmat_calculate_adistance, + .priority =100 , +}; +static __init void hmat_free_structures (void ) {struct memory_target *target, *tnext;@@ -841,8 +897,13 @@ static __init int hmat_init(void)hmat_register_targets ();/* Keep the table and structures if the notifier may use them */ -if (!hotplug_memory_notifier (hmat_callback,HMAT_CALLBACK_PRI )) -return 0 ; +if (hotplug_memory_notifier (hmat_callback,HMAT_CALLBACK_PRI )) + goto out_put; + +if (!hmat_set_default_dram_perf ()) +register_mt_adistance_algorithm (&hmat_adist_nb); + +return 0 ; out_put:hmat_free_structures ();acpi_put_table (tbl);include/linux/memory-tiers.h +18
-0@@ -31,8 +31,11 @@ struct memory_dev_type {struct kref kref; }; +struct node_hmem_attrs ; +#ifdef CONFIG_NUMA extern bool numa_demotion_enabled; +extern struct memory_dev_type *default_dram_type;struct memory_dev_type *alloc_memory_type (int adistance);void put_memory_type (struct memory_dev_type *memtype);void init_node_memory_type (int node,struct memory_dev_type *default_type);@@ -40,6 +43,9 @@ void clear_node_memory_type(int node, struct memory_dev_type *memtype);int register_mt_adistance_algorithm (struct notifier_block *nb);int unregister_mt_adistance_algorithm (struct notifier_block *nb);int mt_calc_adistance (int node,int *adist); +int mt_set_default_dram_perf (int nid,struct node_hmem_attrs *perf, +const char *source); +int mt_perf_to_adistance (struct node_hmem_attrs *perf,int *adist);#ifdef CONFIG_MIGRATION int next_demotion_node (int node);void node_get_allowed_targets (pg_data_t *pgdat,nodemask_t *targets);@@ -64,6 +70,7 @@ static inline bool node_is_toptier(int node)#else #define numa_demotion_enabled false +#define default_dram_type NULL/* * CONFIG_NUMA implementation returns non NULL error. */ @@ -116,5 +123,16 @@ static inline int mt_calc_adistance(int node, int *adist) {return NOTIFY_DONE ; } + +static inline int mt_set_default_dram_perf (int nid,struct node_hmem_attrs *perf, +const char *source) +{ +return -EIO ; +} + +static inline int mt_perf_to_adistance (struct node_hmem_attrs *perf,int *adist) +{ +return -EIO ; +}#endif /* CONFIG_NUMA */ #endif /* _LINUX_MEMORY_TIERS_H */ mm/memory-tiers.c +102
-1@@ -37,7 +37,7 @@ struct node_memory_type_map {static DEFINE_MUTEX (memory_tier_lock);static LIST_HEAD (memory_tiers);static struct node_memory_type_map node_memory_types[MAX_NUMNODES ]; -static struct memory_dev_type *default_dram_type; +struct memory_dev_type *default_dram_type;static struct bus_type memory_tier_subsys = { .name ="memory_tiering" ,@@ -108,6 +108,11 @@ static struct demotion_nodes *node_demotion __read_mostly;static BLOCKING_NOTIFIER_HEAD (mt_adistance_algorithms); +static bool default_dram_perf_error; +static struct node_hmem_attrs default_dram_perf; +static int default_dram_perf_ref_nid =NUMA_NO_NODE ; +static const char *default_dram_perf_ref_source; +static inline struct memory_tier *to_memory_tier (struct device *device) { return container_of(device, struct memory_tier, dev);@@ -595,6 +600,102 @@ void clear_node_memory_type(int node, struct memory_dev_type *memtype) }EXPORT_SYMBOL_GPL (clear_node_memory_type); +static void dump_hmem_attrs (struct node_hmem_attrs *attrs,const char *prefix) +{ +pr_info ( +"%sread_latency: %u, write_latency: %u, read_bandwidth: %u, write_bandwidth: %u\n" , + prefix, attrs->read_latency, attrs->write_latency, + attrs->read_bandwidth, attrs->write_bandwidth); +} + +int mt_set_default_dram_perf (int nid,struct node_hmem_attrs *perf, +const char *source) +{ +int rc =0 ; + +mutex_lock (&memory_tier_lock); +if (default_dram_perf_error) { + rc = -EIO ; + goto out; + } + +if (perf->read_latency + perf->write_latency ==0 || + perf->read_bandwidth + perf->write_bandwidth ==0 ) { + rc = -EINVAL ; + goto out; + } + +if (default_dram_perf_ref_nid ==NUMA_NO_NODE ) { + default_dram_perf = *perf; + default_dram_perf_ref_nid = nid; + default_dram_perf_ref_source =kstrdup (source,GFP_KERNEL ); + goto out; + } + +/* +* The performance of all default DRAM nodes is expected to be +* same (that is, the variation is less than 10%). And it +* will be used as base to calculate the abstract distance of +* other memory nodes. +*/ +if (abs (perf->read_latency - default_dram_perf.read_latency) *10 > + default_dram_perf.read_latency || +abs (perf->write_latency - default_dram_perf.write_latency) *10 > + default_dram_perf.write_latency || +abs (perf->read_bandwidth - default_dram_perf.read_bandwidth) *10 > + default_dram_perf.read_bandwidth || +abs (perf->write_bandwidth - default_dram_perf.write_bandwidth) *10 > + default_dram_perf.write_bandwidth) { +pr_info ( +"memory-tiers: the performance of DRAM node %d mismatches that of the reference\n" +"DRAM node %d.\n" , nid, default_dram_perf_ref_nid); +pr_info (" performance of reference DRAM node %d:\n" , + default_dram_perf_ref_nid); +dump_hmem_attrs (&default_dram_perf," " ); +pr_info (" performance of DRAM node %d:\n" , nid); +dump_hmem_attrs (perf," " ); +pr_info ( +" disable default DRAM node performance based abstract distance algorithm.\n" ); + default_dram_perf_error = true; + rc = -EINVAL ; + } + +out: +mutex_unlock (&memory_tier_lock); +return rc; +} + +int mt_perf_to_adistance (struct node_hmem_attrs *perf,int *adist) +{ +if (default_dram_perf_error) +return -EIO ; + +if (default_dram_perf_ref_nid ==NUMA_NO_NODE ) +return -ENOENT ; + +if (perf->read_latency + perf->write_latency ==0 || + perf->read_bandwidth + perf->write_bandwidth ==0 ) +return -EINVAL ; + +mutex_lock (&memory_tier_lock); +/* +* The abstract distance of a memory node is in direct proportion to +* its memory latency (read + write) and inversely proportional to its +* memory bandwidth (read + write). The abstract distance, memory +* latency, and memory bandwidth of the default DRAM nodes are used as +* the base. +*/ + *adist =MEMTIER_ADISTANCE_DRAM * + (perf->read_latency + perf->write_latency) / + (default_dram_perf.read_latency + default_dram_perf.write_latency) * + (default_dram_perf.read_bandwidth + default_dram_perf.write_bandwidth) / + (perf->read_bandwidth + perf->write_bandwidth); +mutex_unlock (&memory_tier_lock); + +return 0 ; +} +EXPORT_SYMBOL_GPL (mt_perf_to_adistance); +/** * register_mt_adistance_algorithm() - Register memory tiering abstract distance algorithm * @nb: The notifier block which describe the algorithm
PATCH 4/4 dax, kmem: calculate abstract distance with general interface
In reply to Huang YingPreviously, a fixed abstract distance MEMTIER_DEFAULT_DAX_ADISTANCE is used for slow memory type in kmem driver. This limits the usage of kmem driver, for example, it cannot be used for HBM (high bandwidth memory).
So, we use the general abstract distance calculation mechanism in kmem drivers to get more accurate abstract distance on systems with proper support. The original MEMTIER_DEFAULT_DAX_ADISTANCE is used as fallback only.
Now, multiple memory types may be managed by kmem. These memory types are put into the "kmem_memory_types" list and protected by kmem_memory_type_lock.
--- drivers/dax/kmem.c | 62 ++++++++++++++++++++++++++++-------- include/linux/memory-tiers.h | 2 ++ mm/memory-tiers.c | 3 +- 3 files changed, 53 insertions(+), 14 deletions(-)
drivers/dax/kmem.c +49 -13
@@ -49,14 +49,52 @@ struct dax_kmem_data {struct resource *res[]; }; -static struct memory_dev_type *dax_slowmem_type; +static DEFINE_MUTEX (kmem_memory_type_lock); +static LIST_HEAD (kmem_memory_types); + +static struct memory_dev_type *kmem_find_alloc_memory_type (int adist) +{ +bool found = false; +struct memory_dev_type *mtype; + +mutex_lock (&kmem_memory_type_lock); +list_for_each_entry (mtype, &kmem_memory_types, list) { +if (mtype->adistance == adist) { + found = true; +break ; + } + } +if (!found) { + mtype =alloc_memory_type (adist); +if (!IS_ERR (mtype)) +list_add (&mtype->list, &kmem_memory_types); + } +mutex_unlock (&kmem_memory_type_lock); + +return mtype; +} + +static void kmem_put_memory_types (void ) +{ +struct memory_dev_type *mtype, *mtn; + +mutex_lock (&kmem_memory_type_lock); +list_for_each_entry_safe (mtype, mtn, &kmem_memory_types, list) { +list_del (&mtype->list); +put_memory_type (mtype); + } +mutex_unlock (&kmem_memory_type_lock); +} +static int dev_dax_kmem_probe (struct dev_dax *dev_dax) {struct device *dev = &dev_dax->dev;unsigned long total_len =0 ;struct dax_kmem_data *data; +struct memory_dev_type *mtype;int i, rc, mapped =0 ;int numa_node; +int adist =MEMTIER_DEFAULT_DAX_ADISTANCE ;/* * Ensure good NUMA information for the persistent memory.
@@ -71,6 +109,11 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)return -EINVAL ; } +mt_calc_adistance (numa_node, &adist); + mtype =kmem_find_alloc_memory_type (adist); +if (IS_ERR (mtype)) +return PTR_ERR (mtype); +for (i =0 ; i < dev_dax->nr_range; i++) {struct range range;
@@ -88,7 +131,7 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)return -EINVAL ; } -init_node_memory_type (numa_node, dax_slowmem_type); +init_node_memory_type (numa_node, mtype); rc = -ENOMEM ; data =kzalloc (struct_size (data, res, dev_dax->nr_range),GFP_KERNEL );
@@ -167,7 +210,7 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax) err_res_name:kfree (data); err_dax_kmem_data: -clear_node_memory_type (numa_node, dax_slowmem_type); +clear_node_memory_type (numa_node, mtype);return rc; }
@@ -219,7 +262,7 @@ static void dev_dax_kmem_remove(struct dev_dax *dev_dax)* for that. This implies this reference will be around * till next reboot. */ - clear_node_memory_type(node, dax_slowmem_type); + clear_node_memory_type(node, NULL); } }#else
@@ -251,12 +294,6 @@ static int __init dax_kmem_init(void)if (!kmem_name)return -ENOMEM ; - dax_slowmem_type =alloc_memory_type (MEMTIER_DEFAULT_DAX_ADISTANCE ); -if (IS_ERR (dax_slowmem_type)) { - rc =PTR_ERR (dax_slowmem_type); - goto err_dax_slowmem_type; - } - rc =dax_driver_register (&device_dax_kmem_driver);if (rc) goto error_dax_driver;
@@ -264,8 +301,7 @@ static int __init dax_kmem_init(void)return rc; error_dax_driver: -put_memory_type (dax_slowmem_type); -err_dax_slowmem_type: +kmem_put_memory_types ();kfree_const (kmem_name);return rc; }
@@ -275,7 +311,7 @@ static void __exit dax_kmem_exit(void)dax_driver_unregister (&device_dax_kmem_driver);if (!any_hotremove_failed)kfree_const (kmem_name); -put_memory_type (dax_slowmem_type); +kmem_put_memory_types (); }MODULE_AUTHOR ("Intel Corporation" );
include/linux/memory-tiers.h +2 -0
@@ -24,6 +24,8 @@ struct memory_tier;struct memory_dev_type {/* list of memory types that are part of same tier as this type */ struct list_head tier_sibiling; +/* list of memory types that are managed by one driver */ +struct list_head list;/* abstract distance for this specific memory type */ int adistance;/* Nodes of same abstract distance */
mm/memory-tiers.c +2 -1
@@ -586,13 +586,14 @@ EXPORT_SYMBOL_GPL(init_node_memory_type);void clear_node_memory_type (int node,struct memory_dev_type *memtype) {mutex_lock (&memory_tier_lock); -if (node_memory_types[node].memtype == memtype) +if (node_memory_types[node].memtype == memtype || !memtype) node_memory_types[node].map_count--;/* * If we umapped all the attached devices to this node, * clear the node memory type. */ if (!node_memory_types[node].map_count) { + memtype = node_memory_types[node].memtype; node_memory_types[node].memtype =NULL ;put_memory_type (memtype); }
Signature · 1 line
2.39.2
Re: [PATCH -V4 4/4] dax, kmem: calculate abstract distance with general interface
Quoted 5 lines · Huang Ying
Previously, a fixed abstract distance
MEMTIER_DEFAULT_DAX_ADISTANCEis used for slow memory type in kmem driver. This limits the usage of kmem driver, for example, it cannot be used for HBM (high bandwidth memory).
Quoted 8 lines
So, we use the general abstract distance calculation mechanism in kmem drivers to get more accurate abstract distance on systems with proper support. The original
MEMTIER_DEFAULT_DAX_ADISTANCEis used as fallback only.Now, multiple memory types may be managed by kmem. These memory types are put into the "
kmem_memory_types" list and protected bykmem_memory_type_lock.
Looks good, please add:
Quoted 182 lines
Signed-off-by "Huang, Ying" <[email protected]>Tested-by Bharata B Rao <[email protected]>Reviewed-by Dave Jiang <[email protected]>Cc Aneesh Kumar K.V <[email protected]>Cc Wei Xu <[email protected]>Cc Alistair Popple <[email protected]>Cc Dan Williams <[email protected]>Cc Dave Hansen <[email protected]>Cc Davidlohr Bueso <[email protected]>Cc Johannes Weiner <[email protected]>Cc Jonathan Cameron <[email protected]>Cc Michal Hocko <[email protected]>Cc Yang Shi <[email protected]>Cc Rafael J Wysocki <[email protected]>--- drivers/dax/kmem.c | 62 ++++++++++++++++++++++++++++-------- include/linux/memory-tiers.h | 2 ++ mm/memory-tiers.c | 3 +- 3 files changed, 53 insertions(+), 14 deletions(-)drivers/dax/kmem.c +49
-13@@ -49,14 +49,52 @@ struct dax_kmem_data {struct resource *res[]; }; -static struct memory_dev_type *dax_slowmem_type; +static DEFINE_MUTEX (kmem_memory_type_lock); +static LIST_HEAD (kmem_memory_types); + +static struct memory_dev_type *kmem_find_alloc_memory_type (int adist) +{ +bool found = false; +struct memory_dev_type *mtype; + +mutex_lock (&kmem_memory_type_lock); +list_for_each_entry (mtype, &kmem_memory_types, list) { +if (mtype->adistance == adist) { + found = true; +break ; + } + } +if (!found) { + mtype =alloc_memory_type (adist); +if (!IS_ERR (mtype)) +list_add (&mtype->list, &kmem_memory_types); + } +mutex_unlock (&kmem_memory_type_lock); + +return mtype; +} + +static void kmem_put_memory_types (void ) +{ +struct memory_dev_type *mtype, *mtn; + +mutex_lock (&kmem_memory_type_lock); +list_for_each_entry_safe (mtype, mtn, &kmem_memory_types, list) { +list_del (&mtype->list); +put_memory_type (mtype); + } +mutex_unlock (&kmem_memory_type_lock); +} +static int dev_dax_kmem_probe (struct dev_dax *dev_dax) {struct device *dev = &dev_dax->dev;unsigned long total_len =0 ;struct dax_kmem_data *data; +struct memory_dev_type *mtype;int i, rc, mapped =0 ;int numa_node; +int adist =MEMTIER_DEFAULT_DAX_ADISTANCE ;/* * Ensure good NUMA information for the persistent memory. @@ -71,6 +109,11 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)return -EINVAL ; } +mt_calc_adistance (numa_node, &adist); + mtype =kmem_find_alloc_memory_type (adist); +if (IS_ERR (mtype)) +return PTR_ERR (mtype); +for (i =0 ; i < dev_dax->nr_range; i++) {struct range range;@@ -88,7 +131,7 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)return -EINVAL ; } -init_node_memory_type (numa_node, dax_slowmem_type); +init_node_memory_type (numa_node, mtype); rc = -ENOMEM ; data =kzalloc (struct_size (data, res, dev_dax->nr_range),GFP_KERNEL );@@ -167,7 +210,7 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax) err_res_name:kfree (data); err_dax_kmem_data: -clear_node_memory_type (numa_node, dax_slowmem_type); +clear_node_memory_type (numa_node, mtype);return rc; }@@ -219,7 +262,7 @@ static void dev_dax_kmem_remove(struct dev_dax *dev_dax)* for that. This implies this reference will be around * till next reboot. */ - clear_node_memory_type(node, dax_slowmem_type); + clear_node_memory_type(node, NULL); } }#else @@ -251,12 +294,6 @@ static int __init dax_kmem_init(void)if (!kmem_name)return -ENOMEM ; - dax_slowmem_type =alloc_memory_type (MEMTIER_DEFAULT_DAX_ADISTANCE ); -if (IS_ERR (dax_slowmem_type)) { - rc =PTR_ERR (dax_slowmem_type); - goto err_dax_slowmem_type; - } - rc =dax_driver_register (&device_dax_kmem_driver);if (rc) goto error_dax_driver;@@ -264,8 +301,7 @@ static int __init dax_kmem_init(void)return rc; error_dax_driver: -put_memory_type (dax_slowmem_type); -err_dax_slowmem_type: +kmem_put_memory_types ();kfree_const (kmem_name);return rc; }@@ -275,7 +311,7 @@ static void __exit dax_kmem_exit(void)dax_driver_unregister (&device_dax_kmem_driver);if (!any_hotremove_failed)kfree_const (kmem_name); -put_memory_type (dax_slowmem_type); +kmem_put_memory_types (); }MODULE_AUTHOR ("Intel Corporation" );include/linux/memory-tiers.h +2
-0@@ -24,6 +24,8 @@ struct memory_tier;struct memory_dev_type {/* list of memory types that are part of same tier as this type */ struct list_head tier_sibiling; +/* list of memory types that are managed by one driver */ +struct list_head list;/* abstract distance for this specific memory type */ int adistance;/* Nodes of same abstract distance */ mm/memory-tiers.c +2
-1@@ -586,13 +586,14 @@ EXPORT_SYMBOL_GPL(init_node_memory_type);void clear_node_memory_type (int node,struct memory_dev_type *memtype) {mutex_lock (&memory_tier_lock); -if (node_memory_types[node].memtype == memtype) +if (node_memory_types[node].memtype == memtype || !memtype) node_memory_types[node].map_count--;/* * If we umapped all the attached devices to this node, * clear the node memory type. */ if (!node_memory_types[node].map_count) { + memtype = node_memory_types[node].memtype; node_memory_types[node].memtype =NULL ;put_memory_type (memtype); }