| Message ID | 799dcc07f41c2357328e9778fbbded7818af34a7.1706603678.git.haibo1.xu@intel.com |
|---|---|
| State | New |
| Headers | show |
| Series | Add ACPI NUMA support for RISC-V | expand |
On Wed, Jan 31, 2024 at 10:32:00AM +0800, Haibo Xu wrote: > Add acpi_numa.c file to enable parse NUMA information from > ACPI SRAT and SLIT tables. SRAT table provide CPUs(Hart) and > memory nodes to proximity domain mapping, while SLIT table > provide the distance metrics between proximity domains. > > Signed-off-by: Haibo Xu <haibo1.xu@intel.com> > --- > arch/riscv/include/asm/acpi.h | 15 +++- > arch/riscv/kernel/Makefile | 1 + > arch/riscv/kernel/acpi.c | 5 -- > arch/riscv/kernel/acpi_numa.c | 133 ++++++++++++++++++++++++++++++++++ > arch/riscv/kernel/setup.c | 4 +- > arch/riscv/kernel/smpboot.c | 2 - > drivers/acpi/numa/srat.c | 3 +- > include/linux/acpi.h | 4 + > 8 files changed, 156 insertions(+), 11 deletions(-) > create mode 100644 arch/riscv/kernel/acpi_numa.c > > diff --git a/arch/riscv/include/asm/acpi.h b/arch/riscv/include/asm/acpi.h > index 7dad0cf9d701..e0a1f84404f3 100644 > --- a/arch/riscv/include/asm/acpi.h > +++ b/arch/riscv/include/asm/acpi.h > @@ -61,11 +61,14 @@ static inline void arch_fix_phys_package_id(int num, u32 slot) { } > > void acpi_init_rintc_map(void); > struct acpi_madt_rintc *acpi_cpu_get_madt_rintc(int cpu); > -u32 get_acpi_id_for_cpu(int cpu); > +static inline u32 get_acpi_id_for_cpu(int cpu) > +{ > + return acpi_cpu_get_madt_rintc(cpu)->uid; > +} > + > int acpi_get_riscv_isa(struct acpi_table_header *table, > unsigned int cpu, const char **isa); > > -static inline int acpi_numa_get_nid(unsigned int cpu) { return NUMA_NO_NODE; } > void acpi_get_cbo_block_size(struct acpi_table_header *table, u32 *cbom_size, > u32 *cboz_size, u32 *cbop_size); > #else > @@ -87,4 +90,12 @@ static inline void acpi_get_cbo_block_size(struct acpi_table_header *table, > > #endif /* CONFIG_ACPI */ > > +#ifdef CONFIG_ACPI_NUMA > +int acpi_numa_get_nid(unsigned int cpu); > +void acpi_map_cpus_to_nodes(void); > +#else > +static inline int acpi_numa_get_nid(unsigned int cpu) { return NUMA_NO_NODE; } > +static inline void acpi_map_cpus_to_nodes(void) { } > +#endif /* CONFIG_ACPI_NUMA */ > + > #endif /*_ASM_ACPI_H*/ > diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile > index f71910718053..5d3e9cf89b76 100644 > --- a/arch/riscv/kernel/Makefile > +++ b/arch/riscv/kernel/Makefile > @@ -105,3 +105,4 @@ obj-$(CONFIG_COMPAT) += compat_vdso/ > > obj-$(CONFIG_64BIT) += pi/ > obj-$(CONFIG_ACPI) += acpi.o > +obj-$(CONFIG_ACPI_NUMA) += acpi_numa.o > diff --git a/arch/riscv/kernel/acpi.c b/arch/riscv/kernel/acpi.c > index e619edc8b0cc..040bdbfea2b4 100644 > --- a/arch/riscv/kernel/acpi.c > +++ b/arch/riscv/kernel/acpi.c > @@ -191,11 +191,6 @@ struct acpi_madt_rintc *acpi_cpu_get_madt_rintc(int cpu) > return &cpu_madt_rintc[cpu]; > } > > -u32 get_acpi_id_for_cpu(int cpu) > -{ > - return acpi_cpu_get_madt_rintc(cpu)->uid; > -} > - > /* > * __acpi_map_table() will be called before paging_init(), so early_ioremap() > * or early_memremap() should be called here to for ACPI table mapping. > diff --git a/arch/riscv/kernel/acpi_numa.c b/arch/riscv/kernel/acpi_numa.c > new file mode 100644 > index 000000000000..493642a61457 > --- /dev/null > +++ b/arch/riscv/kernel/acpi_numa.c > @@ -0,0 +1,133 @@ > +// SPDX-License-Identifier: GPL-2.0 > +/* > + * ACPI 6.6 based NUMA setup for RISCV > + * Lots of code was borrowed from arch/arm64/kernel/acpi_numa.c > + * > + * Copyright 2004 Andi Kleen, SuSE Labs. > + * Copyright (C) 2013-2016, Linaro Ltd. > + * Author: Hanjun Guo <hanjun.guo@linaro.org> > + * Copyright (C) 2024 Intel Corporation. > + * > + * Reads the ACPI SRAT table to figure out what memory belongs to which CPUs. > + * > + * Called from acpi_numa_init while reading the SRAT and SLIT tables. > + * Assumes all memory regions belonging to a single proximity domain > + * are in one chunk. Holes between them will be included in the node. > + */ > + > +#define pr_fmt(fmt) "ACPI: NUMA: " fmt > + > +#include <linux/acpi.h> > +#include <linux/bitmap.h> > +#include <linux/kernel.h> > +#include <linux/mm.h> > +#include <linux/memblock.h> > +#include <linux/mmzone.h> > +#include <linux/module.h> > +#include <linux/topology.h> > + > +#include <asm/numa.h> > + > +static int acpi_early_node_map[NR_CPUS] __initdata = { NUMA_NO_NODE }; > + > +int __init acpi_numa_get_nid(unsigned int cpu) > +{ > + return acpi_early_node_map[cpu]; > +} > + > +static inline int get_cpu_for_acpi_id(u32 uid) > +{ > + int cpu; > + > + for (cpu = 0; cpu < nr_cpu_ids; cpu++) > + if (uid == get_acpi_id_for_cpu(cpu)) > + return cpu; > + > + return -EINVAL; > +} > + > +static int __init acpi_parse_rintc_pxm(union acpi_subtable_headers *header, > + const unsigned long end) Please check alignment. > +{ > + struct acpi_srat_rintc_affinity *pa; > + int cpu, pxm, node; > + > + if (srat_disabled()) > + return -EINVAL; > + > + pa = (struct acpi_srat_rintc_affinity *)header; > + if (!pa) > + return -EINVAL; > + > + if (!(pa->flags & ACPI_SRAT_RINTC_ENABLED)) > + return 0; > + > + pxm = pa->proximity_domain; > + node = pxm_to_node(pxm); > + > + /* > + * If we can't map the UID to a logical cpu this > + * means that the UID is not part of possible cpus > + * so we do not need a NUMA mapping for it, skip > + * the SRAT entry and keep parsing. > + */ > + cpu = get_cpu_for_acpi_id(pa->acpi_processor_uid); > + if (cpu < 0) > + return 0; > + > + acpi_early_node_map[cpu] = node; > + pr_info("SRAT: PXM %d -> HARTID 0x%lx -> Node %d\n", pxm, > + cpuid_to_hartid_map(cpu), node); > + > + return 0; > +} > + > +void __init acpi_map_cpus_to_nodes(void) > +{ > + int i; > + > + /* > + * In ACPI, SMP and CPU NUMA information is provided in separate > + * static tables, namely the MADT and the SRAT. > + * > + * Thus, it is simpler to first create the cpu logical map through > + * an MADT walk and then map the logical cpus to their node ids > + * as separate steps. > + */ > + acpi_table_parse_entries(ACPI_SIG_SRAT, sizeof(struct acpi_table_srat), > + ACPI_SRAT_TYPE_RINTC_AFFINITY, > + acpi_parse_rintc_pxm, 0); > + Alignment here as well. > + for (i = 0; i < nr_cpu_ids; i++) > + early_map_cpu_to_node(i, acpi_numa_get_nid(i)); > +} > + > +/* Callback for Proximity Domain -> logical node ID mapping */ > +void __init acpi_numa_rintc_affinity_init(struct acpi_srat_rintc_affinity *pa) > +{ > + int pxm, node; > + > + if (srat_disabled()) > + return; > + > + if (pa->header.length < sizeof(struct acpi_srat_rintc_affinity)) { > + pr_err("SRAT: Invalid SRAT header length: %d\n", > + pa->header.length); Can we merge these into single line? > + bad_srat(); > + return; > + } > + > + if (!(pa->flags & ACPI_SRAT_RINTC_ENABLED)) > + return; > + > + pxm = pa->proximity_domain; > + node = acpi_map_pxm_to_node(pxm); > + > + if (node == NUMA_NO_NODE) { > + pr_err("SRAT: Too many proximity domains %d\n", pxm); > + bad_srat(); > + return; > + } > + > + node_set(node, numa_nodes_parsed); > +} > diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c > index 4f73c0ae44b2..a2cde65b69e9 100644 > --- a/arch/riscv/kernel/setup.c > +++ b/arch/riscv/kernel/setup.c > @@ -281,8 +281,10 @@ void __init setup_arch(char **cmdline_p) > setup_smp(); > #endif > > - if (!acpi_disabled) > + if (!acpi_disabled) { > acpi_init_rintc_map(); > + acpi_map_cpus_to_nodes(); Is it not possible to fill up both in single parsing of MADT? > + } > > riscv_init_cbo_blocksizes(); > riscv_fill_hwcap(); > diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c > index 519b6bd946e5..b188d83d1ec4 100644 > --- a/arch/riscv/kernel/smpboot.c > +++ b/arch/riscv/kernel/smpboot.c > @@ -101,7 +101,6 @@ static int __init acpi_parse_rintc(union acpi_subtable_headers *header, const un > if (hart == cpuid_to_hartid_map(0)) { > BUG_ON(found_boot_cpu); > found_boot_cpu = true; > - early_map_cpu_to_node(0, acpi_numa_get_nid(cpu_count)); > return 0; > } > > @@ -111,7 +110,6 @@ static int __init acpi_parse_rintc(union acpi_subtable_headers *header, const un > } > > cpuid_to_hartid_map(cpu_count) = hart; > - early_map_cpu_to_node(cpu_count, acpi_numa_get_nid(cpu_count)); > cpu_count++; > > return 0; > diff --git a/drivers/acpi/numa/srat.c b/drivers/acpi/numa/srat.c > index 503abcf6125d..1f0462cef47c 100644 > --- a/drivers/acpi/numa/srat.c > +++ b/drivers/acpi/numa/srat.c > @@ -219,7 +219,8 @@ int __init srat_disabled(void) > return acpi_numa < 0; > } > > -#if defined(CONFIG_X86) || defined(CONFIG_ARM64) || defined(CONFIG_LOONGARCH) > +#if defined(CONFIG_X86) || defined(CONFIG_ARM64) || defined(CONFIG_LOONGARCH) || \ > + defined(CONFIG_RISCV) Please check alignment. Or make it single line if fits in 100 chars. Also, it looks it covers most of the architectures now. Is it possible to simplify / remove the condition? I hope IA64 is removed now? May be you need to update the comment at #endif too. Thanks Sunil > /* > * Callback for SLIT parsing. pxm_to_node() returns NUMA_NO_NODE for > * I/O localities since SRAT does not list them. I/O localities are > diff --git a/include/linux/acpi.h b/include/linux/acpi.h > index a65273db55c6..be78a9d28927 100644 > --- a/include/linux/acpi.h > +++ b/include/linux/acpi.h > @@ -269,8 +269,12 @@ acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa) { } > > int acpi_numa_memory_affinity_init (struct acpi_srat_mem_affinity *ma); > > +#ifdef CONFIG_RISCV > +void acpi_numa_rintc_affinity_init(struct acpi_srat_rintc_affinity *pa); > +#else > static inline void > acpi_numa_rintc_affinity_init(struct acpi_srat_rintc_affinity *pa) { } > +#endif > > #ifndef PHYS_CPUID_INVALID > typedef u32 phys_cpuid_t; > -- > 2.34.1 >
On Tue, Mar 5, 2024 at 1:24 PM Sunil V L <sunilvl@ventanamicro.com> wrote: > > On Wed, Jan 31, 2024 at 10:32:00AM +0800, Haibo Xu wrote: > > Add acpi_numa.c file to enable parse NUMA information from > > ACPI SRAT and SLIT tables. SRAT table provide CPUs(Hart) and > > memory nodes to proximity domain mapping, while SLIT table > > provide the distance metrics between proximity domains. > > > > Signed-off-by: Haibo Xu <haibo1.xu@intel.com> > > --- > > arch/riscv/include/asm/acpi.h | 15 +++- > > arch/riscv/kernel/Makefile | 1 + > > arch/riscv/kernel/acpi.c | 5 -- > > arch/riscv/kernel/acpi_numa.c | 133 ++++++++++++++++++++++++++++++++++ > > arch/riscv/kernel/setup.c | 4 +- > > arch/riscv/kernel/smpboot.c | 2 - > > drivers/acpi/numa/srat.c | 3 +- > > include/linux/acpi.h | 4 + > > 8 files changed, 156 insertions(+), 11 deletions(-) > > create mode 100644 arch/riscv/kernel/acpi_numa.c > > > > diff --git a/arch/riscv/include/asm/acpi.h b/arch/riscv/include/asm/acpi.h > > index 7dad0cf9d701..e0a1f84404f3 100644 > > --- a/arch/riscv/include/asm/acpi.h > > +++ b/arch/riscv/include/asm/acpi.h > > @@ -61,11 +61,14 @@ static inline void arch_fix_phys_package_id(int num, u32 slot) { } > > > > void acpi_init_rintc_map(void); > > struct acpi_madt_rintc *acpi_cpu_get_madt_rintc(int cpu); > > -u32 get_acpi_id_for_cpu(int cpu); > > +static inline u32 get_acpi_id_for_cpu(int cpu) > > +{ > > + return acpi_cpu_get_madt_rintc(cpu)->uid; > > +} > > + > > int acpi_get_riscv_isa(struct acpi_table_header *table, > > unsigned int cpu, const char **isa); > > > > -static inline int acpi_numa_get_nid(unsigned int cpu) { return NUMA_NO_NODE; } > > void acpi_get_cbo_block_size(struct acpi_table_header *table, u32 *cbom_size, > > u32 *cboz_size, u32 *cbop_size); > > #else > > @@ -87,4 +90,12 @@ static inline void acpi_get_cbo_block_size(struct acpi_table_header *table, > > > > #endif /* CONFIG_ACPI */ > > > > +#ifdef CONFIG_ACPI_NUMA > > +int acpi_numa_get_nid(unsigned int cpu); > > +void acpi_map_cpus_to_nodes(void); > > +#else > > +static inline int acpi_numa_get_nid(unsigned int cpu) { return NUMA_NO_NODE; } > > +static inline void acpi_map_cpus_to_nodes(void) { } > > +#endif /* CONFIG_ACPI_NUMA */ > > + > > #endif /*_ASM_ACPI_H*/ > > diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile > > index f71910718053..5d3e9cf89b76 100644 > > --- a/arch/riscv/kernel/Makefile > > +++ b/arch/riscv/kernel/Makefile > > @@ -105,3 +105,4 @@ obj-$(CONFIG_COMPAT) += compat_vdso/ > > > > obj-$(CONFIG_64BIT) += pi/ > > obj-$(CONFIG_ACPI) += acpi.o > > +obj-$(CONFIG_ACPI_NUMA) += acpi_numa.o > > diff --git a/arch/riscv/kernel/acpi.c b/arch/riscv/kernel/acpi.c > > index e619edc8b0cc..040bdbfea2b4 100644 > > --- a/arch/riscv/kernel/acpi.c > > +++ b/arch/riscv/kernel/acpi.c > > @@ -191,11 +191,6 @@ struct acpi_madt_rintc *acpi_cpu_get_madt_rintc(int cpu) > > return &cpu_madt_rintc[cpu]; > > } > > > > -u32 get_acpi_id_for_cpu(int cpu) > > -{ > > - return acpi_cpu_get_madt_rintc(cpu)->uid; > > -} > > - > > /* > > * __acpi_map_table() will be called before paging_init(), so early_ioremap() > > * or early_memremap() should be called here to for ACPI table mapping. > > diff --git a/arch/riscv/kernel/acpi_numa.c b/arch/riscv/kernel/acpi_numa.c > > new file mode 100644 > > index 000000000000..493642a61457 > > --- /dev/null > > +++ b/arch/riscv/kernel/acpi_numa.c > > @@ -0,0 +1,133 @@ > > +// SPDX-License-Identifier: GPL-2.0 > > +/* > > + * ACPI 6.6 based NUMA setup for RISCV > > + * Lots of code was borrowed from arch/arm64/kernel/acpi_numa.c > > + * > > + * Copyright 2004 Andi Kleen, SuSE Labs. > > + * Copyright (C) 2013-2016, Linaro Ltd. > > + * Author: Hanjun Guo <hanjun.guo@linaro.org> > > + * Copyright (C) 2024 Intel Corporation. > > + * > > + * Reads the ACPI SRAT table to figure out what memory belongs to which CPUs. > > + * > > + * Called from acpi_numa_init while reading the SRAT and SLIT tables. > > + * Assumes all memory regions belonging to a single proximity domain > > + * are in one chunk. Holes between them will be included in the node. > > + */ > > + > > +#define pr_fmt(fmt) "ACPI: NUMA: " fmt > > + > > +#include <linux/acpi.h> > > +#include <linux/bitmap.h> > > +#include <linux/kernel.h> > > +#include <linux/mm.h> > > +#include <linux/memblock.h> > > +#include <linux/mmzone.h> > > +#include <linux/module.h> > > +#include <linux/topology.h> > > + > > +#include <asm/numa.h> > > + > > +static int acpi_early_node_map[NR_CPUS] __initdata = { NUMA_NO_NODE }; > > + > > +int __init acpi_numa_get_nid(unsigned int cpu) > > +{ > > + return acpi_early_node_map[cpu]; > > +} > > + > > +static inline int get_cpu_for_acpi_id(u32 uid) > > +{ > > + int cpu; > > + > > + for (cpu = 0; cpu < nr_cpu_ids; cpu++) > > + if (uid == get_acpi_id_for_cpu(cpu)) > > + return cpu; > > + > > + return -EINVAL; > > +} > > + > > +static int __init acpi_parse_rintc_pxm(union acpi_subtable_headers *header, > > + const unsigned long end) > > Please check alignment. > Sure. > > +{ > > + struct acpi_srat_rintc_affinity *pa; > > + int cpu, pxm, node; > > + > > + if (srat_disabled()) > > + return -EINVAL; > > + > > + pa = (struct acpi_srat_rintc_affinity *)header; > > + if (!pa) > > + return -EINVAL; > > + > > + if (!(pa->flags & ACPI_SRAT_RINTC_ENABLED)) > > + return 0; > > + > > + pxm = pa->proximity_domain; > > + node = pxm_to_node(pxm); > > + > > + /* > > + * If we can't map the UID to a logical cpu this > > + * means that the UID is not part of possible cpus > > + * so we do not need a NUMA mapping for it, skip > > + * the SRAT entry and keep parsing. > > + */ > > + cpu = get_cpu_for_acpi_id(pa->acpi_processor_uid); > > + if (cpu < 0) > > + return 0; > > + > > + acpi_early_node_map[cpu] = node; > > + pr_info("SRAT: PXM %d -> HARTID 0x%lx -> Node %d\n", pxm, > > + cpuid_to_hartid_map(cpu), node); > > + > > + return 0; > > +} > > + > > +void __init acpi_map_cpus_to_nodes(void) > > +{ > > + int i; > > + > > + /* > > + * In ACPI, SMP and CPU NUMA information is provided in separate > > + * static tables, namely the MADT and the SRAT. > > + * > > + * Thus, it is simpler to first create the cpu logical map through > > + * an MADT walk and then map the logical cpus to their node ids > > + * as separate steps. > > + */ > > + acpi_table_parse_entries(ACPI_SIG_SRAT, sizeof(struct acpi_table_srat), > > + ACPI_SRAT_TYPE_RINTC_AFFINITY, > > + acpi_parse_rintc_pxm, 0); > > + > Alignment here as well. > Sure. > > + for (i = 0; i < nr_cpu_ids; i++) > > + early_map_cpu_to_node(i, acpi_numa_get_nid(i)); > > +} > > + > > +/* Callback for Proximity Domain -> logical node ID mapping */ > > +void __init acpi_numa_rintc_affinity_init(struct acpi_srat_rintc_affinity *pa) > > +{ > > + int pxm, node; > > + > > + if (srat_disabled()) > > + return; > > + > > + if (pa->header.length < sizeof(struct acpi_srat_rintc_affinity)) { > > + pr_err("SRAT: Invalid SRAT header length: %d\n", > > + pa->header.length); > Can we merge these into single line? > > > + bad_srat(); > > + return; > > + } > > + > > + if (!(pa->flags & ACPI_SRAT_RINTC_ENABLED)) > > + return; > > + > > + pxm = pa->proximity_domain; > > + node = acpi_map_pxm_to_node(pxm); > > + > > + if (node == NUMA_NO_NODE) { > > + pr_err("SRAT: Too many proximity domains %d\n", pxm); > > + bad_srat(); > > + return; > > + } > > + > > + node_set(node, numa_nodes_parsed); > > +} > > diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c > > index 4f73c0ae44b2..a2cde65b69e9 100644 > > --- a/arch/riscv/kernel/setup.c > > +++ b/arch/riscv/kernel/setup.c > > @@ -281,8 +281,10 @@ void __init setup_arch(char **cmdline_p) > > setup_smp(); > > #endif > > > > - if (!acpi_disabled) > > + if (!acpi_disabled) { > > acpi_init_rintc_map(); > > + acpi_map_cpus_to_nodes(); > Is it not possible to fill up both in single parsing of MADT? > I think it's not possible to fill both in a single MADT parse since the NUMA info is provided in a separate SRAT table. For RISC-V, currently we parsed 2 times of the MADT. FIrst one in setup_smp()->acpi_parse_and_init_cpus() call to build up cpuid_to_hartid_map. Second one in acpi_init_rintc_map call to build the cpu_madt_rintc[] cache structure. Since the first one depends on the CONFIG_SMP, I am not sure whether it's possible to combine these two parts into one. > > + } > > > > riscv_init_cbo_blocksizes(); > > riscv_fill_hwcap(); > > diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c > > index 519b6bd946e5..b188d83d1ec4 100644 > > --- a/arch/riscv/kernel/smpboot.c > > +++ b/arch/riscv/kernel/smpboot.c > > @@ -101,7 +101,6 @@ static int __init acpi_parse_rintc(union acpi_subtable_headers *header, const un > > if (hart == cpuid_to_hartid_map(0)) { > > BUG_ON(found_boot_cpu); > > found_boot_cpu = true; > > - early_map_cpu_to_node(0, acpi_numa_get_nid(cpu_count)); > > return 0; > > } > > > > @@ -111,7 +110,6 @@ static int __init acpi_parse_rintc(union acpi_subtable_headers *header, const un > > } > > > > cpuid_to_hartid_map(cpu_count) = hart; > > - early_map_cpu_to_node(cpu_count, acpi_numa_get_nid(cpu_count)); > > cpu_count++; > > > > return 0; > > diff --git a/drivers/acpi/numa/srat.c b/drivers/acpi/numa/srat.c > > index 503abcf6125d..1f0462cef47c 100644 > > --- a/drivers/acpi/numa/srat.c > > +++ b/drivers/acpi/numa/srat.c > > @@ -219,7 +219,8 @@ int __init srat_disabled(void) > > return acpi_numa < 0; > > } > > > > -#if defined(CONFIG_X86) || defined(CONFIG_ARM64) || defined(CONFIG_LOONGARCH) > > +#if defined(CONFIG_X86) || defined(CONFIG_ARM64) || defined(CONFIG_LOONGARCH) || \ > > + defined(CONFIG_RISCV) > Please check alignment. Or make it single line if fits in 100 chars. > Also, it looks it covers most of the architectures now. Is it possible > to simplify / remove the condition? I hope IA64 is removed now? > Good catch! Since IA64 support was removed in commit cf8e8658100d4(https://lwn.net/Articles/923376/). I think it's possible to remove the condition. Will fix it in v2. Thanks, Haibo > May be you need to update the comment at #endif too. > > Thanks > Sunil > > > /* > > * Callback for SLIT parsing. pxm_to_node() returns NUMA_NO_NODE for > > * I/O localities since SRAT does not list them. I/O localities are > > diff --git a/include/linux/acpi.h b/include/linux/acpi.h > > index a65273db55c6..be78a9d28927 100644 > > --- a/include/linux/acpi.h > > +++ b/include/linux/acpi.h > > @@ -269,8 +269,12 @@ acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa) { } > > > > int acpi_numa_memory_affinity_init (struct acpi_srat_mem_affinity *ma); > > > > +#ifdef CONFIG_RISCV > > +void acpi_numa_rintc_affinity_init(struct acpi_srat_rintc_affinity *pa); > > +#else > > static inline void > > acpi_numa_rintc_affinity_init(struct acpi_srat_rintc_affinity *pa) { } > > +#endif > > > > #ifndef PHYS_CPUID_INVALID > > typedef u32 phys_cpuid_t; > > -- > > 2.34.1 > >
On Tue, Mar 05, 2024 at 05:54:03PM +0800, Haibo Xu wrote: > On Tue, Mar 5, 2024 at 1:24 PM Sunil V L <sunilvl@ventanamicro.com> wrote: > > > > On Wed, Jan 31, 2024 at 10:32:00AM +0800, Haibo Xu wrote: > > > Add acpi_numa.c file to enable parse NUMA information from > > > ACPI SRAT and SLIT tables. SRAT table provide CPUs(Hart) and > > > memory nodes to proximity domain mapping, while SLIT table > > > provide the distance metrics between proximity domains. > > > > > > Signed-off-by: Haibo Xu <haibo1.xu@intel.com> > > > --- > > > arch/riscv/include/asm/acpi.h | 15 +++- > > > arch/riscv/kernel/Makefile | 1 + > > > arch/riscv/kernel/acpi.c | 5 -- > > > arch/riscv/kernel/acpi_numa.c | 133 ++++++++++++++++++++++++++++++++++ > > > arch/riscv/kernel/setup.c | 4 +- > > > arch/riscv/kernel/smpboot.c | 2 - > > > drivers/acpi/numa/srat.c | 3 +- > > > include/linux/acpi.h | 4 + > > > 8 files changed, 156 insertions(+), 11 deletions(-) > > > create mode 100644 arch/riscv/kernel/acpi_numa.c > > > > > > diff --git a/arch/riscv/include/asm/acpi.h b/arch/riscv/include/asm/acpi.h > > > index 7dad0cf9d701..e0a1f84404f3 100644 > > > --- a/arch/riscv/include/asm/acpi.h > > > +++ b/arch/riscv/include/asm/acpi.h > > > @@ -61,11 +61,14 @@ static inline void arch_fix_phys_package_id(int num, u32 slot) { } > > > > > > void acpi_init_rintc_map(void); > > > struct acpi_madt_rintc *acpi_cpu_get_madt_rintc(int cpu); > > > -u32 get_acpi_id_for_cpu(int cpu); > > > +static inline u32 get_acpi_id_for_cpu(int cpu) > > > +{ > > > + return acpi_cpu_get_madt_rintc(cpu)->uid; > > > +} > > > + > > > int acpi_get_riscv_isa(struct acpi_table_header *table, > > > unsigned int cpu, const char **isa); > > > > > > -static inline int acpi_numa_get_nid(unsigned int cpu) { return NUMA_NO_NODE; } > > > void acpi_get_cbo_block_size(struct acpi_table_header *table, u32 *cbom_size, > > > u32 *cboz_size, u32 *cbop_size); > > > #else > > > @@ -87,4 +90,12 @@ static inline void acpi_get_cbo_block_size(struct acpi_table_header *table, > > > > > > #endif /* CONFIG_ACPI */ > > > > > > +#ifdef CONFIG_ACPI_NUMA > > > +int acpi_numa_get_nid(unsigned int cpu); > > > +void acpi_map_cpus_to_nodes(void); > > > +#else > > > +static inline int acpi_numa_get_nid(unsigned int cpu) { return NUMA_NO_NODE; } > > > +static inline void acpi_map_cpus_to_nodes(void) { } > > > +#endif /* CONFIG_ACPI_NUMA */ > > > + > > > #endif /*_ASM_ACPI_H*/ > > > diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile > > > index f71910718053..5d3e9cf89b76 100644 > > > --- a/arch/riscv/kernel/Makefile > > > +++ b/arch/riscv/kernel/Makefile > > > @@ -105,3 +105,4 @@ obj-$(CONFIG_COMPAT) += compat_vdso/ > > > > > > obj-$(CONFIG_64BIT) += pi/ > > > obj-$(CONFIG_ACPI) += acpi.o > > > +obj-$(CONFIG_ACPI_NUMA) += acpi_numa.o > > > diff --git a/arch/riscv/kernel/acpi.c b/arch/riscv/kernel/acpi.c > > > index e619edc8b0cc..040bdbfea2b4 100644 > > > --- a/arch/riscv/kernel/acpi.c > > > +++ b/arch/riscv/kernel/acpi.c > > > @@ -191,11 +191,6 @@ struct acpi_madt_rintc *acpi_cpu_get_madt_rintc(int cpu) > > > return &cpu_madt_rintc[cpu]; > > > } > > > > > > -u32 get_acpi_id_for_cpu(int cpu) > > > -{ > > > - return acpi_cpu_get_madt_rintc(cpu)->uid; > > > -} > > > - > > > /* > > > * __acpi_map_table() will be called before paging_init(), so early_ioremap() > > > * or early_memremap() should be called here to for ACPI table mapping. > > > diff --git a/arch/riscv/kernel/acpi_numa.c b/arch/riscv/kernel/acpi_numa.c > > > new file mode 100644 > > > index 000000000000..493642a61457 > > > --- /dev/null > > > +++ b/arch/riscv/kernel/acpi_numa.c > > > @@ -0,0 +1,133 @@ > > > +// SPDX-License-Identifier: GPL-2.0 > > > +/* > > > + * ACPI 6.6 based NUMA setup for RISCV > > > + * Lots of code was borrowed from arch/arm64/kernel/acpi_numa.c > > > + * > > > + * Copyright 2004 Andi Kleen, SuSE Labs. > > > + * Copyright (C) 2013-2016, Linaro Ltd. > > > + * Author: Hanjun Guo <hanjun.guo@linaro.org> > > > + * Copyright (C) 2024 Intel Corporation. > > > + * > > > + * Reads the ACPI SRAT table to figure out what memory belongs to which CPUs. > > > + * > > > + * Called from acpi_numa_init while reading the SRAT and SLIT tables. > > > + * Assumes all memory regions belonging to a single proximity domain > > > + * are in one chunk. Holes between them will be included in the node. > > > + */ > > > + > > > +#define pr_fmt(fmt) "ACPI: NUMA: " fmt > > > + > > > +#include <linux/acpi.h> > > > +#include <linux/bitmap.h> > > > +#include <linux/kernel.h> > > > +#include <linux/mm.h> > > > +#include <linux/memblock.h> > > > +#include <linux/mmzone.h> > > > +#include <linux/module.h> > > > +#include <linux/topology.h> > > > + > > > +#include <asm/numa.h> > > > + > > > +static int acpi_early_node_map[NR_CPUS] __initdata = { NUMA_NO_NODE }; > > > + > > > +int __init acpi_numa_get_nid(unsigned int cpu) > > > +{ > > > + return acpi_early_node_map[cpu]; > > > +} > > > + > > > +static inline int get_cpu_for_acpi_id(u32 uid) > > > +{ > > > + int cpu; > > > + > > > + for (cpu = 0; cpu < nr_cpu_ids; cpu++) > > > + if (uid == get_acpi_id_for_cpu(cpu)) > > > + return cpu; > > > + > > > + return -EINVAL; > > > +} > > > + > > > +static int __init acpi_parse_rintc_pxm(union acpi_subtable_headers *header, > > > + const unsigned long end) > > > > Please check alignment. > > > > Sure. > > > > +{ > > > + struct acpi_srat_rintc_affinity *pa; > > > + int cpu, pxm, node; > > > + > > > + if (srat_disabled()) > > > + return -EINVAL; > > > + > > > + pa = (struct acpi_srat_rintc_affinity *)header; > > > + if (!pa) > > > + return -EINVAL; > > > + > > > + if (!(pa->flags & ACPI_SRAT_RINTC_ENABLED)) > > > + return 0; > > > + > > > + pxm = pa->proximity_domain; > > > + node = pxm_to_node(pxm); > > > + > > > + /* > > > + * If we can't map the UID to a logical cpu this > > > + * means that the UID is not part of possible cpus > > > + * so we do not need a NUMA mapping for it, skip > > > + * the SRAT entry and keep parsing. > > > + */ > > > + cpu = get_cpu_for_acpi_id(pa->acpi_processor_uid); > > > + if (cpu < 0) > > > + return 0; > > > + > > > + acpi_early_node_map[cpu] = node; > > > + pr_info("SRAT: PXM %d -> HARTID 0x%lx -> Node %d\n", pxm, > > > + cpuid_to_hartid_map(cpu), node); > > > + > > > + return 0; > > > +} > > > + > > > +void __init acpi_map_cpus_to_nodes(void) > > > +{ > > > + int i; > > > + > > > + /* > > > + * In ACPI, SMP and CPU NUMA information is provided in separate > > > + * static tables, namely the MADT and the SRAT. > > > + * > > > + * Thus, it is simpler to first create the cpu logical map through > > > + * an MADT walk and then map the logical cpus to their node ids > > > + * as separate steps. > > > + */ > > > + acpi_table_parse_entries(ACPI_SIG_SRAT, sizeof(struct acpi_table_srat), > > > + ACPI_SRAT_TYPE_RINTC_AFFINITY, > > > + acpi_parse_rintc_pxm, 0); > > > + > > Alignment here as well. > > > > Sure. > > > > + for (i = 0; i < nr_cpu_ids; i++) > > > + early_map_cpu_to_node(i, acpi_numa_get_nid(i)); > > > +} > > > + > > > +/* Callback for Proximity Domain -> logical node ID mapping */ > > > +void __init acpi_numa_rintc_affinity_init(struct acpi_srat_rintc_affinity *pa) > > > +{ > > > + int pxm, node; > > > + > > > + if (srat_disabled()) > > > + return; > > > + > > > + if (pa->header.length < sizeof(struct acpi_srat_rintc_affinity)) { > > > + pr_err("SRAT: Invalid SRAT header length: %d\n", > > > + pa->header.length); > > Can we merge these into single line? > > > > > + bad_srat(); > > > + return; > > > + } > > > + > > > + if (!(pa->flags & ACPI_SRAT_RINTC_ENABLED)) > > > + return; > > > + > > > + pxm = pa->proximity_domain; > > > + node = acpi_map_pxm_to_node(pxm); > > > + > > > + if (node == NUMA_NO_NODE) { > > > + pr_err("SRAT: Too many proximity domains %d\n", pxm); > > > + bad_srat(); > > > + return; > > > + } > > > + > > > + node_set(node, numa_nodes_parsed); > > > +} > > > diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c > > > index 4f73c0ae44b2..a2cde65b69e9 100644 > > > --- a/arch/riscv/kernel/setup.c > > > +++ b/arch/riscv/kernel/setup.c > > > @@ -281,8 +281,10 @@ void __init setup_arch(char **cmdline_p) > > > setup_smp(); > > > #endif > > > > > > - if (!acpi_disabled) > > > + if (!acpi_disabled) { > > > acpi_init_rintc_map(); > > > + acpi_map_cpus_to_nodes(); > > Is it not possible to fill up both in single parsing of MADT? > > > > I think it's not possible to fill both in a single MADT parse since > the NUMA info is provided in a separate SRAT table. > Ahh, yes. My mistake. This looks good to me. Thanks, Sunil
diff --git a/arch/riscv/include/asm/acpi.h b/arch/riscv/include/asm/acpi.h index 7dad0cf9d701..e0a1f84404f3 100644 --- a/arch/riscv/include/asm/acpi.h +++ b/arch/riscv/include/asm/acpi.h @@ -61,11 +61,14 @@ static inline void arch_fix_phys_package_id(int num, u32 slot) { } void acpi_init_rintc_map(void); struct acpi_madt_rintc *acpi_cpu_get_madt_rintc(int cpu); -u32 get_acpi_id_for_cpu(int cpu); +static inline u32 get_acpi_id_for_cpu(int cpu) +{ + return acpi_cpu_get_madt_rintc(cpu)->uid; +} + int acpi_get_riscv_isa(struct acpi_table_header *table, unsigned int cpu, const char **isa); -static inline int acpi_numa_get_nid(unsigned int cpu) { return NUMA_NO_NODE; } void acpi_get_cbo_block_size(struct acpi_table_header *table, u32 *cbom_size, u32 *cboz_size, u32 *cbop_size); #else @@ -87,4 +90,12 @@ static inline void acpi_get_cbo_block_size(struct acpi_table_header *table, #endif /* CONFIG_ACPI */ +#ifdef CONFIG_ACPI_NUMA +int acpi_numa_get_nid(unsigned int cpu); +void acpi_map_cpus_to_nodes(void); +#else +static inline int acpi_numa_get_nid(unsigned int cpu) { return NUMA_NO_NODE; } +static inline void acpi_map_cpus_to_nodes(void) { } +#endif /* CONFIG_ACPI_NUMA */ + #endif /*_ASM_ACPI_H*/ diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index f71910718053..5d3e9cf89b76 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -105,3 +105,4 @@ obj-$(CONFIG_COMPAT) += compat_vdso/ obj-$(CONFIG_64BIT) += pi/ obj-$(CONFIG_ACPI) += acpi.o +obj-$(CONFIG_ACPI_NUMA) += acpi_numa.o diff --git a/arch/riscv/kernel/acpi.c b/arch/riscv/kernel/acpi.c index e619edc8b0cc..040bdbfea2b4 100644 --- a/arch/riscv/kernel/acpi.c +++ b/arch/riscv/kernel/acpi.c @@ -191,11 +191,6 @@ struct acpi_madt_rintc *acpi_cpu_get_madt_rintc(int cpu) return &cpu_madt_rintc[cpu]; } -u32 get_acpi_id_for_cpu(int cpu) -{ - return acpi_cpu_get_madt_rintc(cpu)->uid; -} - /* * __acpi_map_table() will be called before paging_init(), so early_ioremap() * or early_memremap() should be called here to for ACPI table mapping. diff --git a/arch/riscv/kernel/acpi_numa.c b/arch/riscv/kernel/acpi_numa.c new file mode 100644 index 000000000000..493642a61457 --- /dev/null +++ b/arch/riscv/kernel/acpi_numa.c @@ -0,0 +1,133 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * ACPI 6.6 based NUMA setup for RISCV + * Lots of code was borrowed from arch/arm64/kernel/acpi_numa.c + * + * Copyright 2004 Andi Kleen, SuSE Labs. + * Copyright (C) 2013-2016, Linaro Ltd. + * Author: Hanjun Guo <hanjun.guo@linaro.org> + * Copyright (C) 2024 Intel Corporation. + * + * Reads the ACPI SRAT table to figure out what memory belongs to which CPUs. + * + * Called from acpi_numa_init while reading the SRAT and SLIT tables. + * Assumes all memory regions belonging to a single proximity domain + * are in one chunk. Holes between them will be included in the node. + */ + +#define pr_fmt(fmt) "ACPI: NUMA: " fmt + +#include <linux/acpi.h> +#include <linux/bitmap.h> +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/memblock.h> +#include <linux/mmzone.h> +#include <linux/module.h> +#include <linux/topology.h> + +#include <asm/numa.h> + +static int acpi_early_node_map[NR_CPUS] __initdata = { NUMA_NO_NODE }; + +int __init acpi_numa_get_nid(unsigned int cpu) +{ + return acpi_early_node_map[cpu]; +} + +static inline int get_cpu_for_acpi_id(u32 uid) +{ + int cpu; + + for (cpu = 0; cpu < nr_cpu_ids; cpu++) + if (uid == get_acpi_id_for_cpu(cpu)) + return cpu; + + return -EINVAL; +} + +static int __init acpi_parse_rintc_pxm(union acpi_subtable_headers *header, + const unsigned long end) +{ + struct acpi_srat_rintc_affinity *pa; + int cpu, pxm, node; + + if (srat_disabled()) + return -EINVAL; + + pa = (struct acpi_srat_rintc_affinity *)header; + if (!pa) + return -EINVAL; + + if (!(pa->flags & ACPI_SRAT_RINTC_ENABLED)) + return 0; + + pxm = pa->proximity_domain; + node = pxm_to_node(pxm); + + /* + * If we can't map the UID to a logical cpu this + * means that the UID is not part of possible cpus + * so we do not need a NUMA mapping for it, skip + * the SRAT entry and keep parsing. + */ + cpu = get_cpu_for_acpi_id(pa->acpi_processor_uid); + if (cpu < 0) + return 0; + + acpi_early_node_map[cpu] = node; + pr_info("SRAT: PXM %d -> HARTID 0x%lx -> Node %d\n", pxm, + cpuid_to_hartid_map(cpu), node); + + return 0; +} + +void __init acpi_map_cpus_to_nodes(void) +{ + int i; + + /* + * In ACPI, SMP and CPU NUMA information is provided in separate + * static tables, namely the MADT and the SRAT. + * + * Thus, it is simpler to first create the cpu logical map through + * an MADT walk and then map the logical cpus to their node ids + * as separate steps. + */ + acpi_table_parse_entries(ACPI_SIG_SRAT, sizeof(struct acpi_table_srat), + ACPI_SRAT_TYPE_RINTC_AFFINITY, + acpi_parse_rintc_pxm, 0); + + for (i = 0; i < nr_cpu_ids; i++) + early_map_cpu_to_node(i, acpi_numa_get_nid(i)); +} + +/* Callback for Proximity Domain -> logical node ID mapping */ +void __init acpi_numa_rintc_affinity_init(struct acpi_srat_rintc_affinity *pa) +{ + int pxm, node; + + if (srat_disabled()) + return; + + if (pa->header.length < sizeof(struct acpi_srat_rintc_affinity)) { + pr_err("SRAT: Invalid SRAT header length: %d\n", + pa->header.length); + bad_srat(); + return; + } + + if (!(pa->flags & ACPI_SRAT_RINTC_ENABLED)) + return; + + pxm = pa->proximity_domain; + node = acpi_map_pxm_to_node(pxm); + + if (node == NUMA_NO_NODE) { + pr_err("SRAT: Too many proximity domains %d\n", pxm); + bad_srat(); + return; + } + + node_set(node, numa_nodes_parsed); +} diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index 4f73c0ae44b2..a2cde65b69e9 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -281,8 +281,10 @@ void __init setup_arch(char **cmdline_p) setup_smp(); #endif - if (!acpi_disabled) + if (!acpi_disabled) { acpi_init_rintc_map(); + acpi_map_cpus_to_nodes(); + } riscv_init_cbo_blocksizes(); riscv_fill_hwcap(); diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c index 519b6bd946e5..b188d83d1ec4 100644 --- a/arch/riscv/kernel/smpboot.c +++ b/arch/riscv/kernel/smpboot.c @@ -101,7 +101,6 @@ static int __init acpi_parse_rintc(union acpi_subtable_headers *header, const un if (hart == cpuid_to_hartid_map(0)) { BUG_ON(found_boot_cpu); found_boot_cpu = true; - early_map_cpu_to_node(0, acpi_numa_get_nid(cpu_count)); return 0; } @@ -111,7 +110,6 @@ static int __init acpi_parse_rintc(union acpi_subtable_headers *header, const un } cpuid_to_hartid_map(cpu_count) = hart; - early_map_cpu_to_node(cpu_count, acpi_numa_get_nid(cpu_count)); cpu_count++; return 0; diff --git a/drivers/acpi/numa/srat.c b/drivers/acpi/numa/srat.c index 503abcf6125d..1f0462cef47c 100644 --- a/drivers/acpi/numa/srat.c +++ b/drivers/acpi/numa/srat.c @@ -219,7 +219,8 @@ int __init srat_disabled(void) return acpi_numa < 0; } -#if defined(CONFIG_X86) || defined(CONFIG_ARM64) || defined(CONFIG_LOONGARCH) +#if defined(CONFIG_X86) || defined(CONFIG_ARM64) || defined(CONFIG_LOONGARCH) || \ + defined(CONFIG_RISCV) /* * Callback for SLIT parsing. pxm_to_node() returns NUMA_NO_NODE for * I/O localities since SRAT does not list them. I/O localities are diff --git a/include/linux/acpi.h b/include/linux/acpi.h index a65273db55c6..be78a9d28927 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -269,8 +269,12 @@ acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa) { } int acpi_numa_memory_affinity_init (struct acpi_srat_mem_affinity *ma); +#ifdef CONFIG_RISCV +void acpi_numa_rintc_affinity_init(struct acpi_srat_rintc_affinity *pa); +#else static inline void acpi_numa_rintc_affinity_init(struct acpi_srat_rintc_affinity *pa) { } +#endif #ifndef PHYS_CPUID_INVALID typedef u32 phys_cpuid_t;
Add acpi_numa.c file to enable parse NUMA information from ACPI SRAT and SLIT tables. SRAT table provide CPUs(Hart) and memory nodes to proximity domain mapping, while SLIT table provide the distance metrics between proximity domains. Signed-off-by: Haibo Xu <haibo1.xu@intel.com> --- arch/riscv/include/asm/acpi.h | 15 +++- arch/riscv/kernel/Makefile | 1 + arch/riscv/kernel/acpi.c | 5 -- arch/riscv/kernel/acpi_numa.c | 133 ++++++++++++++++++++++++++++++++++ arch/riscv/kernel/setup.c | 4 +- arch/riscv/kernel/smpboot.c | 2 - drivers/acpi/numa/srat.c | 3 +- include/linux/acpi.h | 4 + 8 files changed, 156 insertions(+), 11 deletions(-) create mode 100644 arch/riscv/kernel/acpi_numa.c