diff options
68 files changed, 1854 insertions, 274 deletions
diff --git a/Documentation/ABI/stable/sysfs-devices-node b/Documentation/ABI/stable/sysfs-devices-node index 3e90e1f3bf0a..f7ce68fbd4b9 100644 --- a/Documentation/ABI/stable/sysfs-devices-node +++ b/Documentation/ABI/stable/sysfs-devices-node @@ -90,4 +90,89 @@ Date: December 2009 Contact: Lee Schermerhorn <lee.schermerhorn@hp.com> Description: The node's huge page size control/query attributes. - See Documentation/admin-guide/mm/hugetlbpage.rst
\ No newline at end of file + See Documentation/admin-guide/mm/hugetlbpage.rst + +What: /sys/devices/system/node/nodeX/accessY/ +Date: December 2018 +Contact: Keith Busch <keith.busch@intel.com> +Description: + The node's relationship to other nodes for access class "Y". + +What: /sys/devices/system/node/nodeX/accessY/initiators/ +Date: December 2018 +Contact: Keith Busch <keith.busch@intel.com> +Description: + The directory containing symlinks to memory initiator + nodes that have class "Y" access to this target node's + memory. CPUs and other memory initiators in nodes not in + the list accessing this node's memory may have different + performance. + +What: /sys/devices/system/node/nodeX/accessY/targets/ +Date: December 2018 +Contact: Keith Busch <keith.busch@intel.com> +Description: + The directory containing symlinks to memory targets that + this initiator node has class "Y" access. + +What: /sys/devices/system/node/nodeX/accessY/initiators/read_bandwidth +Date: December 2018 +Contact: Keith Busch <keith.busch@intel.com> +Description: + This node's read bandwidth in MB/s when accessed from + nodes found in this access class's linked initiators. + +What: /sys/devices/system/node/nodeX/accessY/initiators/read_latency +Date: December 2018 +Contact: Keith Busch <keith.busch@intel.com> +Description: + This node's read latency in nanoseconds when accessed + from nodes found in this access class's linked initiators. + +What: /sys/devices/system/node/nodeX/accessY/initiators/write_bandwidth +Date: December 2018 +Contact: Keith Busch <keith.busch@intel.com> +Description: + This node's write bandwidth in MB/s when accessed from + found in this access class's linked initiators. + +What: /sys/devices/system/node/nodeX/accessY/initiators/write_latency +Date: December 2018 +Contact: Keith Busch <keith.busch@intel.com> +Description: + This node's write latency in nanoseconds when access + from nodes found in this class's linked initiators. + +What: /sys/devices/system/node/nodeX/memory_side_cache/indexY/ +Date: December 2018 +Contact: Keith Busch <keith.busch@intel.com> +Description: + The directory containing attributes for the memory-side cache + level 'Y'. + +What: /sys/devices/system/node/nodeX/memory_side_cache/indexY/indexing +Date: December 2018 +Contact: Keith Busch <keith.busch@intel.com> +Description: + The caches associativity indexing: 0 for direct mapped, + non-zero if indexed. + +What: /sys/devices/system/node/nodeX/memory_side_cache/indexY/line_size +Date: December 2018 +Contact: Keith Busch <keith.busch@intel.com> +Description: + The number of bytes accessed from the next cache level on a + cache miss. + +What: /sys/devices/system/node/nodeX/memory_side_cache/indexY/size +Date: December 2018 +Contact: Keith Busch <keith.busch@intel.com> +Description: + The size of this memory side cache in bytes. + +What: /sys/devices/system/node/nodeX/memory_side_cache/indexY/write_policy +Date: December 2018 +Contact: Keith Busch <keith.busch@intel.com> +Description: + The cache write policy: 0 for write-back, 1 for write-through, + other or unknown. diff --git a/Documentation/admin-guide/mm/numaperf.rst b/Documentation/admin-guide/mm/numaperf.rst new file mode 100644 index 000000000000..b79f70c04397 --- /dev/null +++ b/Documentation/admin-guide/mm/numaperf.rst @@ -0,0 +1,169 @@ +.. _numaperf: + +============= +NUMA Locality +============= + +Some platforms may have multiple types of memory attached to a compute +node. These disparate memory ranges may share some characteristics, such +as CPU cache coherence, but may have different performance. For example, +different media types and buses affect bandwidth and latency. + +A system supports such heterogeneous memory by grouping each memory type +under different domains, or "nodes", based on locality and performance +characteristics. Some memory may share the same node as a CPU, and others +are provided as memory only nodes. While memory only nodes do not provide +CPUs, they may still be local to one or more compute nodes relative to +other nodes. The following diagram shows one such example of two compute +nodes with local memory and a memory only node for each of compute node: + + +------------------+ +------------------+ + | Compute Node 0 +-----+ Compute Node 1 | + | Local Node0 Mem | | Local Node1 Mem | + +--------+---------+ +--------+---------+ + | | + +--------+---------+ +--------+---------+ + | Slower Node2 Mem | | Slower Node3 Mem | + +------------------+ +--------+---------+ + +A "memory initiator" is a node containing one or more devices such as +CPUs or separate memory I/O devices that can initiate memory requests. +A "memory target" is a node containing one or more physical address +ranges accessible from one or more memory initiators. + +When multiple memory initiators exist, they may not all have the same +performance when accessing a given memory target. Each initiator-target +pair may be organized into different ranked access classes to represent +this relationship. The highest performing initiator to a given target +is considered to be one of that target's local initiators, and given +the highest access class, 0. Any given target may have one or more +local initiators, and any given initiator may have multiple local +memory targets. + +To aid applications matching memory targets with their initiators, the +kernel provides symlinks to each other. The following example lists the +relationship for the access class "0" memory initiators and targets:: + + # symlinks -v /sys/devices/system/node/nodeX/access0/targets/ + relative: /sys/devices/system/node/nodeX/access0/targets/nodeY -> ../../nodeY + + # symlinks -v /sys/devices/system/node/nodeY/access0/initiators/ + relative: /sys/devices/system/node/nodeY/access0/initiators/nodeX -> ../../nodeX + +A memory initiator may have multiple memory targets in the same access +class. The target memory's initiators in a given class indicate the +nodes' access characteristics share the same performance relative to other +linked initiator nodes. Each target within an initiator's access class, +though, do not necessarily perform the same as each other. + +================ +NUMA Performance +================ + +Applications may wish to consider which node they want their memory to +be allocated from based on the node's performance characteristics. If +the system provides these attributes, the kernel exports them under the +node sysfs hierarchy by appending the attributes directory under the +memory node's access class 0 initiators as follows:: + + /sys/devices/system/node/nodeY/access0/initiators/ + +These attributes apply only when accessed from nodes that have the +are linked under the this access's inititiators. + +The performance characteristics the kernel provides for the local initiators +are exported are as follows:: + + # tree -P "read*|write*" /sys/devices/system/node/nodeY/access0/initiators/ + /sys/devices/system/node/nodeY/access0/initiators/ + |-- read_bandwidth + |-- read_latency + |-- write_bandwidth + `-- write_latency + +The bandwidth attributes are provided in MiB/second. + +The latency attributes are provided in nanoseconds. + +The values reported here correspond to the rated latency and bandwidth +for the platform. + +========== +NUMA Cache +========== + +System memory may be constructed in a hierarchy of elements with various +performance characteristics in order to provide large address space of +slower performing memory cached by a smaller higher performing memory. The +system physical addresses memory initiators are aware of are provided +by the last memory level in the hierarchy. The system meanwhile uses +higher performing memory to transparently cache access to progressively +slower levels. + +The term "far memory" is used to denote the last level memory in the +hierarchy. Each increasing cache level provides higher performing +initiator access, and the term "near memory" represents the fastest +cache provided by the system. + +This numbering is different than CPU caches where the cache level (ex: +L1, L2, L3) uses the CPU-side view where each increased level is lower +performing. In contrast, the memory cache level is centric to the last +level memory, so the higher numbered cache level corresponds to memory +nearer to the CPU, and further from far memory. + +The memory-side caches are not directly addressable by software. When +software accesses a system address, the system will return it from the +near memory cache if it is present. If it is not present, the system +accesses the next level of memory until there is either a hit in that +cache level, or it reaches far memory. + +An application does not need to know about caching attributes in order +to use the system. Software may optionally query the memory cache +attributes in order to maximize the performance out of such a setup. +If the system provides a way for the kernel to discover this information, +for example with ACPI HMAT (Heterogeneous Memory Attribute Table), +the kernel will append these attributes to the NUMA node memory target. + +When the kernel first registers a memory cache with a node, the kernel +will create the following directory:: + + /sys/devices/system/node/nodeX/memory_side_cache/ + +If that directory is not present, the system either does not not provide +a memory-side cache, or that information is not accessible to the kernel. + +The attributes for each level of cache is provided under its cache +level index:: + + /sys/devices/system/node/nodeX/memory_side_cache/indexA/ + /sys/devices/system/node/nodeX/memory_side_cache/indexB/ + /sys/devices/system/node/nodeX/memory_side_cache/indexC/ + +Each cache level's directory provides its attributes. For example, the +following shows a single cache level and the attributes available for +software to query:: + + # tree sys/devices/system/node/node0/memory_side_cache/ + /sys/devices/system/node/node0/memory_side_cache/ + |-- index1 + | |-- indexing + | |-- line_size + | |-- size + | `-- write_policy + +The "indexing" will be 0 if it is a direct-mapped cache, and non-zero +for any other indexed based, multi-way associativity. + +The "line_size" is the number of bytes accessed from the next cache +level on a miss. + +The "size" is the number of bytes provided by this cache level. + +The "write_policy" will be 0 for write-back, and non-zero for +write-through caching. + +======== +See Also +======== +.. [1] https://www.uefi.org/sites/default/files/resources/ACPI_6_2.pdf + Section 5.2.27 diff --git a/Documentation/filesystems/debugfs.txt b/Documentation/filesystems/debugfs.txt index 4f45f71149cb..4a0a9c3f4af6 100644 --- a/Documentation/filesystems/debugfs.txt +++ b/Documentation/filesystems/debugfs.txt @@ -31,10 +31,10 @@ This call, if successful, will make a directory called name underneath the indicated parent directory. If parent is NULL, the directory will be created in the debugfs root. On success, the return value is a struct dentry pointer which can be used to create files in the directory (and to -clean it up at the end). A NULL return value indicates that something went -wrong. If ERR_PTR(-ENODEV) is returned, that is an indication that the -kernel has been built without debugfs support and none of the functions -described below will work. +clean it up at the end). An ERR_PTR(-ERROR) return value indicates that +something went wrong. If ERR_PTR(-ENODEV) is returned, that is an +indication that the kernel has been built without debugfs support and none +of the functions described below will work. The most general way to create a file within a debugfs directory is with: @@ -48,8 +48,9 @@ should hold the file, data will be stored in the i_private field of the resulting inode structure, and fops is a set of file operations which implement the file's behavior. At a minimum, the read() and/or write() operations should be provided; others can be included as needed. Again, -the return value will be a dentry pointer to the created file, NULL for -error, or ERR_PTR(-ENODEV) if debugfs support is missing. +the return value will be a dentry pointer to the created file, +ERR_PTR(-ERROR) on error, or ERR_PTR(-ENODEV) if debugfs support is +missing. Create a file with an initial size, the following function can be used instead: @@ -214,7 +215,8 @@ can be removed with: void debugfs_remove(struct dentry *dentry); -The dentry value can be NULL, in which case nothing will be removed. +The dentry value can be NULL or an error value, in which case nothing will +be removed. Once upon a time, debugfs users were required to remember the dentry pointer for every debugfs file they created so that all files could be diff --git a/arch/arm64/kernel/acpi_numa.c b/arch/arm64/kernel/acpi_numa.c index eac1d0cc595c..7ff800045434 100644 --- a/arch/arm64/kernel/acpi_numa.c +++ b/arch/arm64/kernel/acpi_numa.c @@ -45,7 +45,7 @@ static inline int get_cpu_for_acpi_id(u32 uid) return -EINVAL; } -static int __init acpi_parse_gicc_pxm(struct acpi_subtable_header *header, +static int __init acpi_parse_gicc_pxm(union acpi_subtable_headers *header, const unsigned long end) { struct acpi_srat_gicc_affinity *pa; diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 824de7038967..bb4b3f07761a 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -586,7 +586,7 @@ acpi_map_gic_cpu_interface(struct acpi_madt_generic_interrupt *processor) } static int __init -acpi_parse_gic_cpu_interface(struct acpi_subtable_header *header, +acpi_parse_gic_cpu_interface(union acpi_subtable_headers *header, const unsigned long end) { struct acpi_madt_generic_interrupt *processor; @@ -595,7 +595,7 @@ acpi_parse_gic_cpu_interface(struct acpi_subtable_header *header, if (BAD_MADT_GICC_ENTRY(processor, end)) return -EINVAL; - acpi_table_print_madt_entry(header); + acpi_table_print_madt_entry(&header->common); acpi_map_gic_cpu_interface(processor); diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c index 41eb281709da..1435e7a1a8cd 100644 --- a/arch/ia64/kernel/acpi.c +++ b/arch/ia64/kernel/acpi.c @@ -177,7 +177,7 @@ struct acpi_table_madt *acpi_madt __initdata; static u8 has_8259; static int __init -acpi_parse_lapic_addr_ovr(struct acpi_subtable_header * header, +acpi_parse_lapic_addr_ovr(union acpi_subtable_headers * header, const unsigned long end) { struct acpi_madt_local_apic_override *lapic; @@ -195,7 +195,7 @@ acpi_parse_lapic_addr_ovr(struct acpi_subtable_header * header, } static int __init -acpi_parse_lsapic(struct acpi_subtable_header * header, const unsigned long end) +acpi_parse_lsapic(union acpi_subtable_headers *header, const unsigned long end) { struct acpi_madt_local_sapic *lsapic; @@ -216,7 +216,7 @@ acpi_parse_lsapic(struct acpi_subtable_header * header, const unsigned long end) } static int __init -acpi_parse_lapic_nmi(struct acpi_subtable_header * header, const unsigned long end) +acpi_parse_lapic_nmi(union acpi_subtable_headers * header, const unsigned long end) { struct acpi_madt_local_apic_nmi *lacpi_nmi; @@ -230,7 +230,7 @@ acpi_parse_lapic_nmi(struct acpi_subtable_header * header, const unsigned long e } static int __init -acpi_parse_iosapic(struct acpi_subtable_header * header, const unsigned long end) +acpi_parse_iosapic(union acpi_subtable_headers * header, const unsigned long end) { struct acpi_madt_io_sapic *iosapic; @@ -245,7 +245,7 @@ acpi_parse_iosapic(struct acpi_subtable_header * header, const unsigned long end static unsigned int __initdata acpi_madt_rev; static int __init -acpi_parse_plat_int_src(struct acpi_subtable_header * header, +acpi_parse_plat_int_src(union acpi_subtable_headers * header, const unsigned long end) { struct acpi_madt_interrupt_source *plintsrc; @@ -329,7 +329,7 @@ unsigned int get_cpei_target_cpu(void) } static int __init -acpi_parse_int_src_ovr(struct acpi_subtable_header * header, +acpi_parse_int_src_ovr(union acpi_subtable_headers * header, const unsigned long end) { struct acpi_madt_interrupt_override *p; @@ -350,7 +350,7 @@ acpi_parse_int_src_ovr(struct acpi_subtable_header * header, } static int __init -acpi_parse_nmi_src(struct acpi_subtable_header * header, const unsigned long end) +acpi_parse_nmi_src(union acpi_subtable_headers * header, const unsigned long end) { struct acpi_madt_nmi_source *nmi_src; diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 8dcbf6890714..9fc92e4539d8 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -197,7 +197,7 @@ static int acpi_register_lapic(int id, u32 acpiid, u8 enabled) } static int __init -acpi_parse_x2apic(struct acpi_subtable_header *header, const unsigned long end) +acpi_parse_x2apic(union acpi_subtable_headers *header, const unsigned long end) { struct acpi_madt_local_x2apic *processor = NULL; #ifdef CONFIG_X86_X2APIC @@ -210,7 +210,7 @@ acpi_parse_x2apic(struct acpi_subtable_header *header, const unsigned long end) if (BAD_MADT_ENTRY(processor, end)) return -EINVAL; - acpi_table_print_madt_entry(header); + acpi_table_print_madt_entry(&header->common); #ifdef CONFIG_X86_X2APIC apic_id = processor->local_apic_id; @@ -242,7 +242,7 @@ acpi_parse_x2apic(struct acpi_subtable_header *header, const unsigned long end) } static int __init -acpi_parse_lapic(struct acpi_subtable_header * header, const unsigned long end) +acpi_parse_lapic(union acpi_subtable_headers * header, const unsigned long end) { struct acpi_madt_local_apic *processor = NULL; @@ -251,7 +251,7 @@ acpi_parse_lapic(struct acpi_subtable_header * header, const unsigned long end) if (BAD_MADT_ENTRY(processor, end)) return -EINVAL; - acpi_table_print_madt_entry(header); + acpi_table_print_madt_entry(&header->common); /* Ignore invalid ID */ if (processor->id == 0xff) @@ -272,7 +272,7 @@ acpi_parse_lapic(struct acpi_subtable_header * header, const unsigned long end) } static int __init -acpi_parse_sapic(struct acpi_subtable_header *header, const unsigned long end) +acpi_parse_sapic(union acpi_subtable_headers *header, const unsigned long end) { struct acpi_madt_local_sapic *processor = NULL; @@ -281,7 +281,7 @@ acpi_parse_sapic(struct acpi_subtable_header *header, const unsigned long end) if (BAD_MADT_ENTRY(processor, end)) return -EINVAL; - acpi_table_print_madt_entry(header); + acpi_table_print_madt_entry(&header->common); acpi_register_lapic((processor->id << 8) | processor->eid,/* APIC ID */ processor->processor_id, /* ACPI ID */ @@ -291,7 +291,7 @@ acpi_parse_sapic(struct acpi_subtable_header *header, const unsigned long end) } static int __init -acpi_parse_lapic_addr_ovr(struct acpi_subtable_header * header, +acpi_parse_lapic_addr_ovr(union acpi_subtable_headers * header, const unsigned long end) { struct acpi_madt_local_apic_override *lapic_addr_ovr = NULL; @@ -301,7 +301,7 @@ acpi_parse_lapic_addr_ovr(struct acpi_subtable_header * header, if (BAD_MADT_ENTRY(lapic_addr_ovr, end)) return -EINVAL; - acpi_table_print_madt_entry(header); + acpi_table_print_madt_entry(&header->common); acpi_lapic_addr = lapic_addr_ovr->address; @@ -309,7 +309,7 @@ acpi_parse_lapic_addr_ovr(struct acpi_subtable_header * header, } static int __init -acpi_parse_x2apic_nmi(struct acpi_subtable_header *header, +acpi_parse_x2apic_nmi(union acpi_subtable_headers *header, const unsigned long end) { struct acpi_madt_local_x2apic_nmi *x2apic_nmi = NULL; @@ -319,7 +319,7 @@ acpi_parse_x2apic_nmi(struct acpi_subtable_header *header, if (BAD_MADT_ENTRY(x2apic_nmi, end)) return -EINVAL; - acpi_table_print_madt_entry(header); + acpi_table_print_madt_entry(&header->common); if (x2apic_nmi->lint != 1) printk(KERN_WARNING PREFIX "NMI not connected to LINT 1!\n"); @@ -328,7 +328,7 @@ acpi_parse_x2apic_nmi(struct acpi_subtable_header *header, } static int __init -acpi_parse_lapic_nmi(struct acpi_subtable_header * header, const unsigned long end) +acpi_parse_lapic_nmi(union acpi_subtable_headers * header, const unsigned long end) { struct acpi_madt_local_apic_nmi *lapic_nmi = NULL; @@ -337,7 +337,7 @@ acpi_parse_lapic_nmi(struct acpi_subtable_header * header, const unsigned long e if (BAD_MADT_ENTRY(lapic_nmi, end)) return -EINVAL; |