[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index] Re: [Xen-devel] [PATCH 4/8] x86/AMD: distinguish compute units from hyper-threads
On Wed, Jul 11, 2018 at 06:07:42AM -0600, Jan Beulich wrote: > Fam17 replaces CUs by HTs, which we should reflect accordingly, even if > the difference is not very big. The most relevant change (requiring some > code restructuring) is that the topoext feature no longer means there is > a valid CU ID. > > Take the opportunity and convert wrongly plain int variables in > set_cpu_sibling_map() to unsigned int. > > Signed-off-by: Jan Beulich <jbeulich@xxxxxxxx> > > --- a/xen/arch/x86/cpu/amd.c > +++ b/xen/arch/x86/cpu/amd.c > @@ -504,17 +504,23 @@ static void amd_get_topology(struct cpui > u32 eax, ebx, ecx, edx; > > cpuid(0x8000001e, &eax, &ebx, &ecx, &edx); > - c->compute_unit_id = ebx & 0xFF; > c->x86_num_siblings = ((ebx >> 8) & 0x3) + 1; > + > + if (c->x86 < 0x17) > + c->compute_unit_id = ebx & 0xFF; > + else { > + c->cpu_core_id = ebx & 0xFF; > + c->x86_max_cores /= c->x86_num_siblings; > + } > } > > if (opt_cpu_info) > printk("CPU %d(%d) -> Processor %d, %s %d\n", > cpu, c->x86_max_cores, c->phys_proc_id, > - cpu_has(c, X86_FEATURE_TOPOEXT) ? "Compute Unit" : > - "Core", > - cpu_has(c, X86_FEATURE_TOPOEXT) ? c->compute_unit_id : > - c->cpu_core_id); > + c->compute_unit_id != INVALID_CUID ? "Compute Unit" > + : "Core", > + c->compute_unit_id != INVALID_CUID ? > c->compute_unit_id > + : c->cpu_core_id); > } > > static void early_init_amd(struct cpuinfo_x86 *c) > --- a/xen/arch/x86/smpboot.c > +++ b/xen/arch/x86/smpboot.c > @@ -236,33 +236,41 @@ static void link_thread_siblings(int cpu > cpumask_set_cpu(cpu2, per_cpu(cpu_core_mask, cpu1)); > } > > -static void set_cpu_sibling_map(int cpu) > +static void set_cpu_sibling_map(unsigned int cpu) > { > - int i; > + unsigned int i; > struct cpuinfo_x86 *c = cpu_data; > > cpumask_set_cpu(cpu, &cpu_sibling_setup_map); > > cpumask_set_cpu(cpu, socket_cpumask[cpu_to_socket(cpu)]); > + cpumask_set_cpu(cpu, per_cpu(cpu_core_mask, cpu)); > + cpumask_set_cpu(cpu, per_cpu(cpu_sibling_mask, cpu)); > > if ( c[cpu].x86_num_siblings > 1 ) > { > for_each_cpu ( i, &cpu_sibling_setup_map ) > { > - if ( cpu_has(c, X86_FEATURE_TOPOEXT) ) { > - if ( (c[cpu].phys_proc_id == c[i].phys_proc_id) && > - (c[cpu].compute_unit_id == c[i].compute_unit_id) ) > + if ( cpu == i || c[cpu].phys_proc_id != c[i].phys_proc_id ) > + continue; > + if ( c[cpu].compute_unit_id != INVALID_CUID && > + c[i].compute_unit_id != INVALID_CUID ) > + { > + if ( c[cpu].compute_unit_id == c[i].compute_unit_id ) > link_thread_siblings(cpu, i); > - } else if ( (c[cpu].phys_proc_id == c[i].phys_proc_id) && > - (c[cpu].cpu_core_id == c[i].cpu_core_id) ) { > - link_thread_siblings(cpu, i); > } > + else if ( c[cpu].cpu_core_id != XEN_INVALID_CORE_ID && > + c[i].cpu_core_id != XEN_INVALID_CORE_ID ) > + { > + if ( c[cpu].cpu_core_id == c[i].cpu_core_id ) > + link_thread_siblings(cpu, i); > + } > + else > + printk(XENLOG_WARNING > + "CPU%u: unclear relationship with CPU%u\n", > + cpu, i); > } > } > - else > - { > - cpumask_set_cpu(cpu, per_cpu(cpu_sibling_mask, cpu)); > - } > > if ( c[cpu].x86_max_cores == 1 ) > { > > > > Side note: if cpu_core_id isn't the logical cpu, it might be worth updating the comments in processor.h Reviewed-by: Brian Woods <brian.woods@xxxxxxx> -- Brian Woods _______________________________________________ Xen-devel mailing list Xen-devel@xxxxxxxxxxxxxxxxxxxx https://lists.xenproject.org/mailman/listinfo/xen-devel
|
Lists.xenproject.org is hosted with RackSpace, monitoring our |