ACPI: Support generic initiator proximity domains
Subsystems (7)
cover ACPI: Support generic initiator proximity domains
ACPI 6.3 introduced a new entity that can be part of a NUMA proximity domain. It may share such a domain with the existing options (memory, cpu etc) but it may also exist on it's own.
The intent is to allow the description of the NUMA properties (particulary via HMAT) of accelerators and other initiators of memory activity that are not the host processor running the operating system.
To illustrate one use case for this feature.
A multiqueue high performance ethernet adaptor is connected to a pair of SoCs via an appropriate interconnect. The system memory is attached to the two SoCs. The ethernet adaptor driver wants to load balance the location of it's memory buffers between the two different SoCs to avoid saturating the interconnect. Under current models the ethernet adaptor must be assigned to an existing NUMA domain (via _PXM). None of these are able to indicate that the ethernet adaptor is equidistant from two separate memory / processor nodes. By assigning it to a node with none of the traditional elements, we can represent this and the driver is able to load balance between the nodes
improving performance. We have hardware where 5-10% performance
improvement may be easily achieved using this approach. As CCIX and similar interconnects become common, this situation will occur more often.
This patch set introduces 'just enough' to make them work for arm64. It should be trivial to support other architectures, I just don't suitable NUMA systems readily available to test.
There are a few quirks that need to be considered.
1. Fall back nodes
******************
As pre ACPI 6.3 supporting operating systems do not have Generic Initiator Proximity Domains it is possible to specify, via _PXM in DSDT that another device is part of such a GI only node. This currently blows up spectacularly in Linux.
Whilst we can obviously 'now' protect against such a situation (see the related thread on PCI _PXM support and the threadripper board identified there as also falling into the problem of using non existent nodes
https://patchwork.kernel.org/patch/10723311/ ), there is no way to be sure we will never have legacy OSes that are not protected against this. It would also be 'non ideal' to fallback to a default node as there may be a better (non GI) node to pick if GI nodes aren't available.
The work around is that we also have a new system wide OSC bit that allows an operating system to 'annouce' that it supports Generic Initiators. This allows, the firmware to us DSDT magic to 'move' devices between the nodes dependent on whether our new nodes are there or not.
2. New ways of assigning a proximity domain for devices
*******************************************************
Until now, the only way firmware could indicate that a particular device (outside the 'special' set of cpus etc) was to be found in a particular Proximity Domain by the use of _PXM in DSDT.
That is equally valid with GI domains, but we have new options. The SRAT affinity structure includes a handle (ACPI or PCI) to identify devices with the system and specify their proximity domain that way. If both _PXM and this are provided, they should give the same answer.
For now this patch set completely ignores that feature as we don't need it to start the discussion. It will form a follow up set at some point (if no one else fancies doing it).
acpica-tools patches will go via the normal route to there.
Bits of the headers are here in order to have this stand on it's own.
Jonathan Cameron (3):
ACPI: Support Generic Initator only domains
arm64: Support Generic Initiator only domains
ACPI: Let ACPI know we support Generic Initiator Affinity Structures
arch/arm64/kernel/smp.c | 8 +++++ drivers/acpi/bus.c | 1 + drivers/acpi/numa.c | 62 +++++++++++++++++++++++++++++++++- drivers/base/node.c | 3 ++ include/acpi/actbl3.h | 37 +++++++++++++++++++- include/asm-generic/topology.h | 3 ++ include/linux/acpi.h | 1 + include/linux/nodemask.h | 1 + include/linux/topology.h | 7 ++++ 9 files changed, 121 insertions(+), 2 deletions(-)
Signature · 1 line
2.18.0
PATCH 1/3 ACPI: Support Generic Initator only domains
Generic Initiators are a new ACPI concept that allows for the description of proximity domains that contain a device which performs memory access (such as a network card) but neither host CPU nor memory.
This first patch has the parsing code and provides the infrastructure for an architecture to associate these new domains with their nearest memory possessing node.
--- drivers/acpi/numa.c | 62 +++++++++++++++++++++++++++++++++- drivers/base/node.c | 3 ++ include/acpi/actbl3.h | 37 +++++++++++++++++++- include/asm-generic/topology.h | 3 ++ include/linux/nodemask.h | 1 + include/linux/topology.h | 7 ++++ 6 files changed, 111 insertions(+), 2 deletions(-)
drivers/acpi/numa.c +61 -1
@@ -183,6 +183,38 @@ acpi_table_print_srat_entry(struct acpi_subtable_header *header) }break ; +case ACPI_SRAT_TYPE_GENERIC_INITIATOR_AFFINITY : + { +struct acpi_srat_gi_affinity *p = + (struct acpi_srat_gi_affinity *)header; +char name[9 ] = {}; + +if (p->flags &ACPI_SRAT_GI_PCI_HANDLE ) { +/* +* For pci devices this may be the only place they +* are assigned a proximity domain +*/ +pr_debug ("SRAT Generic Initiator(Seg:%u BDF:%u) in proximity domain %d %s\n" , + p->pci_handle.segment, + p->pci_handle.bdf, + p->proximity_domain, + (p->flags &ACPI_SRAT_GI_ENABLED ) ? +"enabled" :"disabled" ); + }else { +/* +* In this case we can rely on the device having a +* proximity domain reference +*/ +memcpy (name, p->acpi_handle.hid,8 ); +pr_info ("SRAT Generic Initiator(HID=%s UID=%u) in proximity domain %d %s\n" , + name, + p->acpi_handle.uid, + p->proximity_domain, + (p->flags &ACPI_SRAT_GI_ENABLED ) ? +"enabled" :"disabled" ); + } + } +break ;default :pr_warn ("Found unsupported SRAT entry (type = 0x%x)\n" , header->type);
@@ -391,6 +423,32 @@ acpi_parse_gicc_affinity(struct acpi_subtable_header *header,return 0 ; } +static int __init +acpi_parse_gi_affinity (struct acpi_subtable_header *header, +const unsigned long end) +{ +struct acpi_srat_gi_affinity *gi_affinity; +int node; + + gi_affinity = (struct acpi_srat_gi_affinity *)header; +if (!gi_affinity) +return -EINVAL ; +acpi_table_print_srat_entry (header); + +if (!(gi_affinity->flags &ACPI_SRAT_GI_ENABLED )) +return EINVAL ; + + node =acpi_map_pxm_to_node (gi_affinity->proximity_domain); +if (node ==NUMA_NO_NODE || node >=MAX_NUMNODES ) { +pr_err ("SRAT: Too many proximity domains.\n" ); +return -EINVAL ; + } +node_set (node, numa_nodes_parsed); +node_set_state (node,N_GENERIC_INITIATOR ); + +return 0 ; +} +static int __initdata parsed_numa_memblks; static int __init
@@ -446,7 +504,7 @@ int __init acpi_numa_init(void)/* SRAT: System Resource Affinity Table */ if (!acpi_table_parse (ACPI_SIG_SRAT , acpi_parse_srat)) { -struct acpi_subtable_proc srat_proc[3 ]; +struct acpi_subtable_proc srat_proc[4 ];memset (srat_proc,0 ,sizeof (srat_proc)); srat_proc[0 ].id =ACPI_SRAT_TYPE_CPU_AFFINITY ;
@@ -455,6 +513,8 @@ int __init acpi_numa_init(void) srat_proc[1 ].handler = acpi_parse_x2apic_affinity; srat_proc[2 ].id =ACPI_SRAT_TYPE_GICC_AFFINITY ; srat_proc[2 ].handler = acpi_parse_gicc_affinity; + srat_proc[3 ].id =ACPI_SRAT_TYPE_GENERIC_INITIATOR_AFFINITY ; + srat_proc[3 ].handler = acpi_parse_gi_affinity; acpi_table_parse_entries_array(ACPI_SIG_SRAT, sizeof(struct acpi_table_srat),
drivers/base/node.c +3 -0
@@ -634,6 +634,8 @@ static struct node_attr node_state_attr[] = { #endif [N_MEMORY] = _NODE_ATTR(has_memory, N_MEMORY), [N_CPU] = _NODE_ATTR(has_cpu, N_CPU), + [N_GENERIC_INITIATOR ] =_NODE_ATTR (has_generic_initiator, + N_GENERIC_INITIATOR), };static struct attribute *node_state_attrs[] = {
@@ -645,6 +647,7 @@ static struct attribute *node_state_attrs[] = {#endif &node_state_attr[N_MEMORY ].attr.attr, &node_state_attr[N_CPU ].attr.attr, + &node_state_attr[N_GENERIC_INITIATOR ].attr.attr, NULL };
include/acpi/actbl3.h +36 -1
@@ -190,7 +190,8 @@ enum acpi_srat_type {ACPI_SRAT_TYPE_X2APIC_CPU_AFFINITY =2 ,ACPI_SRAT_TYPE_GICC_AFFINITY =3 ,ACPI_SRAT_TYPE_GIC_ITS_AFFINITY =4 ,/* ACPI 6.2 */ - ACPI_SRAT_TYPE_RESERVED = 5 /* 5 and greater are reserved */ +ACPI_SRAT_TYPE_GENERIC_INITIATOR_AFFINITY =5 ,/* ACPI 6.3 */ + ACPI_SRAT_TYPE_RESERVED = 6 /* 6 and greater are reserved */ };/*
@@ -271,6 +272,40 @@ struct acpi_srat_gic_its_affinity {u32 its_id; }; +/* Flags for struct acpi_srat_gi_affinity */ + +#define ACPI_SRAT_GI_ENABLED (1)/* 00: Use affinity structure */ +#define ACPI_SRAT_GI_ACPI_HANDLE (0)/* 01: */ +#define ACPI_SRAT_GI_PCI_HANDLE (1 << 1)/* 01: */ + +/* Handles to associate the generic initiator with types of ACPI device */ + +struct acpi_srat_gi_acpi_handle { +char hid[8 ]; +u32 uid; +u32 reserved; +}; + +struct acpi_srat_gi_pci_handle { +u16 segment; +u16 bdf; +u8 reserved[12 ]; +}; + +/* 5 : Generic Initiator Affinity (ACPI 6.3) */ + +struct acpi_srat_gi_affinity { +struct acpi_subtable_header header; +u8 reserved; +u8 device_handl_type; +u32 proximity_domain; +union { +struct acpi_srat_gi_acpi_handle acpi_handle; +struct acpi_srat_gi_pci_handle pci_handle; + }; +u32 flags; +u32 reserved2; +};/******************************************************************************* * * STAO - Status Override Table (_STA override) - ACPI 6.0
include/asm-generic/topology.h +3 -0
@@ -71,6 +71,9 @@#ifndef set_cpu_numa_mem#define set_cpu_numa_mem (cpu, node)#endif +#ifndef set_gi_numa_mem +#define set_gi_numa_mem (gi, node) +#endif #endif /* !CONFIG_NUMA || !CONFIG_HAVE_MEMORYLESS_NODES */
include/linux/nodemask.h +1 -0
@@ -399,6 +399,7 @@ enum node_states {#endif N_MEMORY ,/* The node has memory(regular, high, movable) */ N_CPU ,/* The node has one or more cpus */ +N_GENERIC_INITIATOR ,/* The node is a GI only node */ NR_NODE_STATES };
include/linux/topology.h +7 -0
@@ -125,6 +125,13 @@ static inline void set_numa_mem(int node) }#endif +#ifndef set_gi_numa_mem +static inline void set_gi_numa_mem (int gi,int node) +{ + _node_numa_mem_[gi] = node; +} +#endif +#ifndef node_to_mem_nodestatic inline int node_to_mem_node (int node) {
Signature · 1 line
2.18.0
Re: [PATCH 1/3] ACPI: Support Generic Initator only domains
Quoted 17 lines · Jonathan Cameron
drivers/acpi/numa.c +17
-0+case ACPI_SRAT_TYPE_GENERIC_INITIATOR_AFFINITY : + { +struct acpi_srat_gi_affinity *p = + (struct acpi_srat_gi_affinity *)header; +char name[9 ] = {}; + +if (p->flags &ACPI_SRAT_GI_PCI_HANDLE ) { +/* +* For pci devices this may be the only place they +* are assigned a proximity domain +*/ +pr_debug ("SRAT Generic Initiator(Seg:%u BDF:%u) in proximity domain %d %s\n" , + p->pci_handle.segment, + p->pci_handle.bdf, + p->proximity_domain, + (p->flags &ACPI_SRAT_GI_ENABLED ) ? +"enabled" :"disabled" );
<snip>
include/acpi/actbl3.h struct acpi_srat_gic_its_affinity { · line 279
Quoted 3 lines
include/acpi/actbl3.h +3
-0+#define ACPI_SRAT_GI_ENABLED (1)/* 00: Use affinity structure */ +#define ACPI_SRAT_GI_ACPI_HANDLE (0)/* 01: */ +#define ACPI_SRAT_GI_PCI_HANDLE (1 << 1)/* 01: */
It looks like you're reading reserved bits. My copy of the 6.3 spec says PCI Handle is 1, and is set in Device Handle Type field, not in the Flags.
Quoted 14 lines
include/acpi/actbl3.h +14
-0+/* 5 : Generic Initiator Affinity (ACPI 6.3) */ + +struct acpi_srat_gi_affinity { +struct acpi_subtable_header header; +u8 reserved; +u8 device_handl_type; +u32 proximity_domain; +union { +struct acpi_srat_gi_acpi_handle acpi_handle; +struct acpi_srat_gi_pci_handle pci_handle; + }; +u32 flags; +u32 reserved2; +};
Re: [PATCH 1/3] ACPI: Support Generic Initator only domains
Quoted 21 lines · On Tue, 12 Feb 2019 14:47:36 -0700 Keith Busch <[email protected]> wrote:
Quoted 17 lines · Jonathan Cameron
drivers/acpi/numa.c +17
-0+case ACPI_SRAT_TYPE_GENERIC_INITIATOR_AFFINITY : + { +struct acpi_srat_gi_affinity *p = + (struct acpi_srat_gi_affinity *)header; +char name[9 ] = {}; + +if (p->flags &ACPI_SRAT_GI_PCI_HANDLE ) { +/* +* For pci devices this may be the only place they +* are assigned a proximity domain +*/ +pr_debug ("SRAT Generic Initiator(Seg:%u BDF:%u) in proximity domain %d %s\n" , + p->pci_handle.segment, + p->pci_handle.bdf, + p->proximity_domain, + (p->flags &ACPI_SRAT_GI_ENABLED ) ? +"enabled" :"disabled" );<snip>
Quoted 6 lines
include/acpi/actbl3.h struct acpi_srat_gic_its_affinity { · line 279
Quoted 3 lines
include/acpi/actbl3.h +3
-0+#define ACPI_SRAT_GI_ENABLED (1)/* 00: Use affinity structure */ +#define ACPI_SRAT_GI_ACPI_HANDLE (0)/* 01: */ +#define ACPI_SRAT_GI_PCI_HANDLE (1 << 1)/* 01: */ It looks like you're reading reserved bits. My copy of the 6.3 spec says PCI Handle is 1, and is set in Device Handle Type field, not in the Flags.
Good spot.
Sorry, wrote this long before spec publish and some details got tidied up. I fixed iasl end but forgot to actually update the reading of it. Oops! As you can probably guess that my test was using an ACPI handle so didn't hit this at all. I'll shove a PCIe card in the machine to check those as well.
Will fix up for v2!
Thanks,
Jonathan
Quoted 15 lines
Quoted 15 lines
include/acpi/actbl3.h +14
-0+/* 5 : Generic Initiator Affinity (ACPI 6.3) */ + +struct acpi_srat_gi_affinity { +struct acpi_subtable_header header; +u8 reserved; +u8 device_handl_type; +u32 proximity_domain; +union { +struct acpi_srat_gi_acpi_handle acpi_handle; +struct acpi_srat_gi_pci_handle pci_handle; + }; +u32 flags; +u32 reserved2; +};
PATCH 2/3 arm64: Support Generic Initiator only domains
In reply to Jonathan CameronThe one thing that currently needs doing from an architecture point of view is associating the GI domain with its nearest memory domain. This allows all the standard NUMA aware code to get a 'reasonable' answer.
A clever driver might elect to do load balancing etc if there are multiple host / memory domains nearby, but that's a decision for the driver.
--- arch/arm64/kernel/smp.c | 8 ++++++++ 1 file changed, 8 insertions(+)
arch/arm64/kernel/smp.c +8 -0
@@ -698,6 +698,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus) {int err;unsigned int cpu; +unsigned int node;unsigned int this_cpu;init_cpu_topology ();
@@ -736,6 +737,13 @@ void __init smp_prepare_cpus(unsigned int max_cpus)set_cpu_present (cpu, true);numa_store_cpu_info (cpu); } + +/* +* Walk the numa domains and set the node to numa memory reference +* for any that are Generic Initiator Only. +*/ +for_each_node_state (node,N_GENERIC_INITIATOR ) +set_gi_numa_mem (node,local_memory_node (node)); }void (*__smp_cross_call)(const struct cpumask *,unsigned int );
Signature · 1 line
2.18.0
PATCH 3/3 ACPI: Let ACPI know we support Generic Initiator Affinity Structures
In reply to Jonathan CameronUntil we tell ACPI that we support generic initiators, it will have to operate in fall back domain mode and all _PXM entries should be on existing non GI domains.
This patch sets the relevant OSC bit to make that happen.
---
Note that this will need platform guards unless we make generic initiators work on all ACPI platforms from the start.
drivers/acpi/bus.c | 1 + include/linux/acpi.h | 1 + 2 files changed, 2 insertions(+)
drivers/acpi/bus.c +1 -0
@@ -315,6 +315,7 @@ static void acpi_bus_osc_support(void) capbuf[OSC_SUPPORT_DWORD ] |=OSC_SB_HOTPLUG_OST_SUPPORT ; capbuf[OSC_SUPPORT_DWORD ] |=OSC_SB_PCLPI_SUPPORT ; + capbuf[OSC_SUPPORT_DWORD ] |=OSC_SB_GENERIC_INITIATOR_SUPPORT ;#ifdef CONFIG_X86 if (boot_cpu_has (X86_FEATURE_HWP )) {
include/linux/acpi.h +1 -0
@@ -498,6 +498,7 @@ acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context);#define OSC_SB_PCLPI_SUPPORT 0x00000080#define OSC_SB_OSLPI_SUPPORT 0x00000100#define OSC_SB_CPC_DIVERSE_HIGH_SUPPORT 0x00001000 +#define OSC_SB_GENERIC_INITIATOR_SUPPORT 0x00002000extern bool osc_sb_apei_support_acked;extern bool osc_pc_lpi_support_confirmed;
Signature · 1 line
2.18.0