commit 456797da792fa7cbf6698febf275fe9b36691f78 upstream.
arm64's method of defining a default cpu topology requires only minimal changes to apply to RISC-V also. The current arm64 implementation exits early in a uniprocessor configuration by reading MPIDR & claiming that uniprocessor can rely on the default values.
This is appears to be a hangover from prior to '3102bc0e6ac7 ("arm64: topology: Stop using MPIDR for topology information")', because the current code just assigns default values for multiprocessor systems.
With the MPIDR references removed, store_cpu_topolgy() can be moved to the common arch_topology code.
Reviewed-by: Sudeep Holla sudeep.holla@arm.com Acked-by: Catalin Marinas catalin.marinas@arm.com Reviewed-by: Atish Patra atishp@rivosinc.com Signed-off-by: Conor Dooley conor.dooley@microchip.com --- arch/arm64/kernel/topology.c | 40 ------------------------------------ drivers/base/arch_topology.c | 19 +++++++++++++++++ 2 files changed, 19 insertions(+), 40 deletions(-)
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c index 113903db666c..3d3a673c6704 100644 --- a/arch/arm64/kernel/topology.c +++ b/arch/arm64/kernel/topology.c @@ -21,46 +21,6 @@ #include <asm/cputype.h> #include <asm/topology.h>
-void store_cpu_topology(unsigned int cpuid) -{ - struct cpu_topology *cpuid_topo = &cpu_topology[cpuid]; - u64 mpidr; - - if (cpuid_topo->package_id != -1) - goto topology_populated; - - mpidr = read_cpuid_mpidr(); - - /* Uniprocessor systems can rely on default topology values */ - if (mpidr & MPIDR_UP_BITMASK) - return; - - /* - * This would be the place to create cpu topology based on MPIDR. - * - * However, it cannot be trusted to depict the actual topology; some - * pieces of the architecture enforce an artificial cap on Aff0 values - * (e.g. GICv3's ICC_SGI1R_EL1 limits it to 15), leading to an - * artificial cycling of Aff1, Aff2 and Aff3 values. IOW, these end up - * having absolutely no relationship to the actual underlying system - * topology, and cannot be reasonably used as core / package ID. - * - * If the MT bit is set, Aff0 *could* be used to define a thread ID, but - * we still wouldn't be able to obtain a sane core ID. This means we - * need to entirely ignore MPIDR for any topology deduction. - */ - cpuid_topo->thread_id = -1; - cpuid_topo->core_id = cpuid; - cpuid_topo->package_id = cpu_to_node(cpuid); - - pr_debug("CPU%u: cluster %d core %d thread %d mpidr %#016llx\n", - cpuid, cpuid_topo->package_id, cpuid_topo->core_id, - cpuid_topo->thread_id, mpidr); - -topology_populated: - update_siblings_masks(cpuid); -} - #ifdef CONFIG_ACPI static bool __init acpi_cpu_is_threaded(int cpu) { diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c index 503404f3280e..0dfe20d18b8d 100644 --- a/drivers/base/arch_topology.c +++ b/drivers/base/arch_topology.c @@ -538,4 +538,23 @@ void __init init_cpu_topology(void) else if (of_have_populated_dt() && parse_dt_topology()) reset_cpu_topology(); } + +void store_cpu_topology(unsigned int cpuid) +{ + struct cpu_topology *cpuid_topo = &cpu_topology[cpuid]; + + if (cpuid_topo->package_id != -1) + goto topology_populated; + + cpuid_topo->thread_id = -1; + cpuid_topo->core_id = cpuid; + cpuid_topo->package_id = cpu_to_node(cpuid); + + pr_debug("CPU%u: package %d core %d thread %d\n", + cpuid, cpuid_topo->package_id, cpuid_topo->core_id, + cpuid_topo->thread_id); + +topology_populated: + update_siblings_masks(cpuid); +} #endif
commit fbd92809997a391f28075f1c8b5ee314c225557c upstream.
RISC-V has no sane defaults to fall back on where there is no cpu-map in the devicetree. Without sane defaults, the package, core and thread IDs are all set to -1. This causes user-visible inaccuracies for tools like hwloc/lstopo which rely on the sysfs cpu topology files to detect a system's topology.
On a PolarFire SoC, which should have 4 harts with a thread each, lstopo currently reports:
Machine (793MB total) Package L#0 NUMANode L#0 (P#0 793MB) Core L#0 L1d L#0 (32KB) + L1i L#0 (32KB) + PU L#0 (P#0) L1d L#1 (32KB) + L1i L#1 (32KB) + PU L#1 (P#1) L1d L#2 (32KB) + L1i L#2 (32KB) + PU L#2 (P#2) L1d L#3 (32KB) + L1i L#3 (32KB) + PU L#3 (P#3)
Adding calls to store_cpu_topology() in {boot,smp} hart bringup code results in the correct topolgy being reported:
Machine (793MB total) Package L#0 NUMANode L#0 (P#0 793MB) L1d L#0 (32KB) + L1i L#0 (32KB) + Core L#0 + PU L#0 (P#0) L1d L#1 (32KB) + L1i L#1 (32KB) + Core L#1 + PU L#1 (P#1) L1d L#2 (32KB) + L1i L#2 (32KB) + Core L#2 + PU L#2 (P#2) L1d L#3 (32KB) + L1i L#3 (32KB) + Core L#3 + PU L#3 (P#3)
CC: stable@vger.kernel.org # 456797da792f: arm64: topology: move store_cpu_topology() to shared code Fixes: 03f11f03dbfe ("RISC-V: Parse cpu topology during boot.") Reported-by: Brice Goglin Brice.Goglin@inria.fr Link: https://github.com/open-mpi/hwloc/issues/536 Reviewed-by: Sudeep Holla sudeep.holla@arm.com Reviewed-by: Atish Patra atishp@rivosinc.com Signed-off-by: Conor Dooley conor.dooley@microchip.com --- I just resolved the conflicts. Tested in QEMU only. SMP doesn't seem to work in 5.4, using the same command that works for 5.10. --- arch/riscv/Kconfig | 2 +- arch/riscv/kernel/smpboot.c | 4 +++- 2 files changed, 4 insertions(+), 2 deletions(-)
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index b21549a34447..e0a77af5c130 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -51,7 +51,7 @@ config RISCV select PCI_MSI if PCI select RISCV_TIMER select GENERIC_IRQ_MULTI_HANDLER - select GENERIC_ARCH_TOPOLOGY if SMP + select GENERIC_ARCH_TOPOLOGY select ARCH_HAS_PTE_SPECIAL select ARCH_HAS_MMIOWB select HAVE_EBPF_JIT if 64BIT diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c index 261f4087cc39..0576a6b2bcc5 100644 --- a/arch/riscv/kernel/smpboot.c +++ b/arch/riscv/kernel/smpboot.c @@ -46,6 +46,8 @@ void __init smp_prepare_cpus(unsigned int max_cpus) { int cpuid;
+ store_cpu_topology(smp_processor_id()); + /* This covers non-smp usecase mandated by "nosmp" option */ if (max_cpus == 0) return; @@ -142,8 +144,8 @@ asmlinkage __visible void __init smp_callin(void) current->active_mm = mm;
trap_init(); + store_cpu_topology(smp_processor_id()); notify_cpu_starting(smp_processor_id()); - update_siblings_masks(smp_processor_id()); set_cpu_online(smp_processor_id(), 1); /* * Remote TLB flushes are ignored while the CPU is offline, so emit
linux-stable-mirror@lists.linaro.org
-
Conor Dooley