From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jeremy Linton Subject: Re: [PATCH v9 00/12] Support PPTT for ARM64 Date: Tue, 29 May 2018 16:52:04 -0500 Message-ID: References: <20180511235807.30834-1-jeremy.linton@arm.com> <20180517170523.h7tuvbzdfluuidcz@armageddon.cambridge.arm.com> <09fb3fe7-d703-43f1-74f7-f8cb5ff1f67a@arm.com> <551905a6-eaa8-97df-06ec-1ceedfbc164f@arm.com> <20180529150823.GD17159@arm.com> Mime-Version: 1.0 Content-Type: text/plain; charset=utf-8; format=flowed Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: Content-Language: en-US Sender: linux-kernel-owner@vger.kernel.org To: Geert Uytterhoeven , Will Deacon Cc: Sudeep Holla , Catalin Marinas , ACPI Devel Maling List , Mark Rutland , austinwc@codeaurora.org, tnowicki@caviumnetworks.com, Palmer Dabbelt , linux-riscv@lists.infradead.org, Morten.Rasmussen@arm.com, vkilari@codeaurora.org, Lorenzo Pieralisi , jhugo@codeaurora.org, Al Stone , Len Brown , John Garry , wangxiongfeng2@huawei.com, Dietmar Eggemann , Linux ARM , Ard Biesheuvel , Greg KH , "Rafael J. Wysocki" Linux List-Id: linux-acpi@vger.kernel.org Hi, On 05/29/2018 10:51 AM, Geert Uytterhoeven wrote: > Hi Will, > > On Tue, May 29, 2018 at 5:08 PM, Will Deacon wrote: >> On Tue, May 29, 2018 at 02:18:40PM +0100, Sudeep Holla wrote: >>> On 29/05/18 12:56, Geert Uytterhoeven wrote: >>>> On Tue, May 29, 2018 at 1:14 PM, Sudeep Holla wrote: >>>>> On 29/05/18 11:48, Geert Uytterhoeven wrote: >>>>>> System supend still works fine on systems with big cores only: >>>>>> >>>>>> R-Car H3 ES1.0 (4xCA57 (4xCA53 disabled in firmware)) >>>>>> R-Car M3-N (2xCA57) >>>>>> >>>>>> Reverting this commit fixes the issue for me. >>>>> >>>>> I can't find anything that relates to system suspend in these patches >>>>> unless they are messing with something during CPU hot plug-in back >>>>> during resume. >>>> >>>> It's only the last patch that introduces the breakage. >>>> >>> >>> As specified in the commit log, it won't change any behavior for DT >>> systems if it's non-NUMA or single node system. So I am still wondering >>> what could trigger this regression. >> >> I wonder if we're somehow giving an uninitialised/invalid NUMA configuration >> to the scheduler, although I can't see how this would happen. >> >> Geert -- if you enable CONFIG_DEBUG_PER_CPU_MAPS=y and apply the diff below >> do you see anything shouting in dmesg? > > Thanks, but unfortunately it doesn't help. > I added some debug code to print cpumask, but so far I don't see anything > suspicious. I suspect most of the problem is related to the node mask changing at unexpected times (particularly cores being removed from the mask). Once I understand that more, there may be a simpler patch. OTOH, I've been testing with this, and with it, I can't seem to duplicate the problem with CONFIG_NUMA disabled I found. diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h index df48212f767b..7450ef5ed733 100644 --- a/arch/arm64/include/asm/topology.h +++ b/arch/arm64/include/asm/topology.h @@ -12,6 +12,7 @@ struct cpu_topology { cpumask_t thread_sibling; cpumask_t core_sibling; cpumask_t llc_siblings; + cpumask_t node_siblings; /* maintain a stable node sibling list */ }; extern struct cpu_topology cpu_topology[NR_CPUS]; diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index f3e2e3aec0b0..f4eb80852d78 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -677,8 +677,9 @@ void __init smp_prepare_cpus(unsigned int max_cpus) init_cpu_topology(); this_cpu = smp_processor_id(); - store_cpu_topology(this_cpu); numa_store_cpu_info(this_cpu); + store_cpu_topology(this_cpu); + /* * If UP is mandated by "nosmp" (which implies "maxcpus=0"), don't set diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c index 7415c166281f..6819c764537d 100644 --- a/arch/arm64/kernel/topology.c +++ b/arch/arm64/kernel/topology.c @@ -215,7 +215,7 @@ EXPORT_SYMBOL_GPL(cpu_topology); const struct cpumask *cpu_coregroup_mask(int cpu) { - const cpumask_t *core_mask = cpumask_of_node(cpu_to_node(cpu)); + const cpumask_t *core_mask = &cpu_topology[cpu].node_siblings; /* Find the smaller of NUMA, core or LLC siblings */ if (cpumask_subset(&cpu_topology[cpu].core_sibling, core_mask)) { @@ -233,12 +233,16 @@ const struct cpumask *cpu_coregroup_mask(int cpu) static void update_siblings_masks(unsigned int cpuid) { struct cpu_topology *cpu_topo, *cpuid_topo = &cpu_topology[cpuid]; + int node = cpu_to_node(cpuid); int cpu; /* update core and thread sibling masks */ for_each_possible_cpu(cpu) { cpu_topo = &cpu_topology[cpu]; + if (cpu_to_node(cpu) == node) + cpumask_set_cpu(cpu, &cpu_topo->node_siblings); + if (cpuid_topo->llc_id == cpu_topo->llc_id) cpumask_set_cpu(cpu, &cpuid_topo->llc_siblings); @@ -311,6 +315,9 @@ static void __init reset_cpu_topology(void) cpumask_clear(&cpu_topo->llc_siblings); cpumask_set_cpu(cpu, &cpu_topo->llc_siblings); + cpumask_clear(&cpu_topo->node_siblings); + cpumask_set_cpu(cpu, &cpu_topo->node_siblings); + cpumask_clear(&cpu_topo->core_sibling); cpumask_set_cpu(cpu, &cpu_topo->core_sibling); cpumask_clear(&cpu_topo->thread_sibling); -- 2.14.3 From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S967406AbeE2VwK (ORCPT ); Tue, 29 May 2018 17:52:10 -0400 Received: from usa-sjc-mx-foss1.foss.arm.com ([217.140.101.70]:48228 "EHLO foss.arm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S966304AbeE2VwH (ORCPT ); Tue, 29 May 2018 17:52:07 -0400 Subject: Re: [PATCH v9 00/12] Support PPTT for ARM64 To: Geert Uytterhoeven , Will Deacon Cc: Sudeep Holla , Catalin Marinas , ACPI Devel Maling List , Mark Rutland , austinwc@codeaurora.org, tnowicki@caviumnetworks.com, Palmer Dabbelt , linux-riscv@lists.infradead.org, Morten.Rasmussen@arm.com, vkilari@codeaurora.org, Lorenzo Pieralisi , jhugo@codeaurora.org, Al Stone , Len Brown , John Garry , wangxiongfeng2@huawei.com, Dietmar Eggemann , Linux ARM , Ard Biesheuvel , Greg KH , "Rafael J. Wysocki" , Linux Kernel Mailing List , Hanjun Guo , Linux-Renesas References: <20180511235807.30834-1-jeremy.linton@arm.com> <20180517170523.h7tuvbzdfluuidcz@armageddon.cambridge.arm.com> <09fb3fe7-d703-43f1-74f7-f8cb5ff1f67a@arm.com> <551905a6-eaa8-97df-06ec-1ceedfbc164f@arm.com> <20180529150823.GD17159@arm.com> From: Jeremy Linton Message-ID: Date: Tue, 29 May 2018 16:52:04 -0500 User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:52.0) Gecko/20100101 Thunderbird/52.7.0 MIME-Version: 1.0 In-Reply-To: Content-Type: text/plain; charset=utf-8; format=flowed Content-Language: en-US Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Hi, On 05/29/2018 10:51 AM, Geert Uytterhoeven wrote: > Hi Will, > > On Tue, May 29, 2018 at 5:08 PM, Will Deacon wrote: >> On Tue, May 29, 2018 at 02:18:40PM +0100, Sudeep Holla wrote: >>> On 29/05/18 12:56, Geert Uytterhoeven wrote: >>>> On Tue, May 29, 2018 at 1:14 PM, Sudeep Holla wrote: >>>>> On 29/05/18 11:48, Geert Uytterhoeven wrote: >>>>>> System supend still works fine on systems with big cores only: >>>>>> >>>>>> R-Car H3 ES1.0 (4xCA57 (4xCA53 disabled in firmware)) >>>>>> R-Car M3-N (2xCA57) >>>>>> >>>>>> Reverting this commit fixes the issue for me. >>>>> >>>>> I can't find anything that relates to system suspend in these patches >>>>> unless they are messing with something during CPU hot plug-in back >>>>> during resume. >>>> >>>> It's only the last patch that introduces the breakage. >>>> >>> >>> As specified in the commit log, it won't change any behavior for DT >>> systems if it's non-NUMA or single node system. So I am still wondering >>> what could trigger this regression. >> >> I wonder if we're somehow giving an uninitialised/invalid NUMA configuration >> to the scheduler, although I can't see how this would happen. >> >> Geert -- if you enable CONFIG_DEBUG_PER_CPU_MAPS=y and apply the diff below >> do you see anything shouting in dmesg? > > Thanks, but unfortunately it doesn't help. > I added some debug code to print cpumask, but so far I don't see anything > suspicious. I suspect most of the problem is related to the node mask changing at unexpected times (particularly cores being removed from the mask). Once I understand that more, there may be a simpler patch. OTOH, I've been testing with this, and with it, I can't seem to duplicate the problem with CONFIG_NUMA disabled I found. diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h index df48212f767b..7450ef5ed733 100644 --- a/arch/arm64/include/asm/topology.h +++ b/arch/arm64/include/asm/topology.h @@ -12,6 +12,7 @@ struct cpu_topology { cpumask_t thread_sibling; cpumask_t core_sibling; cpumask_t llc_siblings; + cpumask_t node_siblings; /* maintain a stable node sibling list */ }; extern struct cpu_topology cpu_topology[NR_CPUS]; diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index f3e2e3aec0b0..f4eb80852d78 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -677,8 +677,9 @@ void __init smp_prepare_cpus(unsigned int max_cpus) init_cpu_topology(); this_cpu = smp_processor_id(); - store_cpu_topology(this_cpu); numa_store_cpu_info(this_cpu); + store_cpu_topology(this_cpu); + /* * If UP is mandated by "nosmp" (which implies "maxcpus=0"), don't set diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c index 7415c166281f..6819c764537d 100644 --- a/arch/arm64/kernel/topology.c +++ b/arch/arm64/kernel/topology.c @@ -215,7 +215,7 @@ EXPORT_SYMBOL_GPL(cpu_topology); const struct cpumask *cpu_coregroup_mask(int cpu) { - const cpumask_t *core_mask = cpumask_of_node(cpu_to_node(cpu)); + const cpumask_t *core_mask = &cpu_topology[cpu].node_siblings; /* Find the smaller of NUMA, core or LLC siblings */ if (cpumask_subset(&cpu_topology[cpu].core_sibling, core_mask)) { @@ -233,12 +233,16 @@ const struct cpumask *cpu_coregroup_mask(int cpu) static void update_siblings_masks(unsigned int cpuid) { struct cpu_topology *cpu_topo, *cpuid_topo = &cpu_topology[cpuid]; + int node = cpu_to_node(cpuid); int cpu; /* update core and thread sibling masks */ for_each_possible_cpu(cpu) { cpu_topo = &cpu_topology[cpu]; + if (cpu_to_node(cpu) == node) + cpumask_set_cpu(cpu, &cpu_topo->node_siblings); + if (cpuid_topo->llc_id == cpu_topo->llc_id) cpumask_set_cpu(cpu, &cpuid_topo->llc_siblings); @@ -311,6 +315,9 @@ static void __init reset_cpu_topology(void) cpumask_clear(&cpu_topo->llc_siblings); cpumask_set_cpu(cpu, &cpu_topo->llc_siblings); + cpumask_clear(&cpu_topo->node_siblings); + cpumask_set_cpu(cpu, &cpu_topo->node_siblings); + cpumask_clear(&cpu_topo->core_sibling); cpumask_set_cpu(cpu, &cpu_topo->core_sibling); cpumask_clear(&cpu_topo->thread_sibling); -- 2.14.3 From mboxrd@z Thu Jan 1 00:00:00 1970 From: jeremy.linton@arm.com (Jeremy Linton) Date: Tue, 29 May 2018 16:52:04 -0500 Subject: [PATCH v9 00/12] Support PPTT for ARM64 In-Reply-To: References: <20180511235807.30834-1-jeremy.linton@arm.com> <20180517170523.h7tuvbzdfluuidcz@armageddon.cambridge.arm.com> <09fb3fe7-d703-43f1-74f7-f8cb5ff1f67a@arm.com> <551905a6-eaa8-97df-06ec-1ceedfbc164f@arm.com> <20180529150823.GD17159@arm.com> Message-ID: To: linux-riscv@lists.infradead.org List-Id: linux-riscv.lists.infradead.org Hi, On 05/29/2018 10:51 AM, Geert Uytterhoeven wrote: > Hi Will, > > On Tue, May 29, 2018 at 5:08 PM, Will Deacon wrote: >> On Tue, May 29, 2018 at 02:18:40PM +0100, Sudeep Holla wrote: >>> On 29/05/18 12:56, Geert Uytterhoeven wrote: >>>> On Tue, May 29, 2018 at 1:14 PM, Sudeep Holla wrote: >>>>> On 29/05/18 11:48, Geert Uytterhoeven wrote: >>>>>> System supend still works fine on systems with big cores only: >>>>>> >>>>>> R-Car H3 ES1.0 (4xCA57 (4xCA53 disabled in firmware)) >>>>>> R-Car M3-N (2xCA57) >>>>>> >>>>>> Reverting this commit fixes the issue for me. >>>>> >>>>> I can't find anything that relates to system suspend in these patches >>>>> unless they are messing with something during CPU hot plug-in back >>>>> during resume. >>>> >>>> It's only the last patch that introduces the breakage. >>>> >>> >>> As specified in the commit log, it won't change any behavior for DT >>> systems if it's non-NUMA or single node system. So I am still wondering >>> what could trigger this regression. >> >> I wonder if we're somehow giving an uninitialised/invalid NUMA configuration >> to the scheduler, although I can't see how this would happen. >> >> Geert -- if you enable CONFIG_DEBUG_PER_CPU_MAPS=y and apply the diff below >> do you see anything shouting in dmesg? > > Thanks, but unfortunately it doesn't help. > I added some debug code to print cpumask, but so far I don't see anything > suspicious. I suspect most of the problem is related to the node mask changing at unexpected times (particularly cores being removed from the mask). Once I understand that more, there may be a simpler patch. OTOH, I've been testing with this, and with it, I can't seem to duplicate the problem with CONFIG_NUMA disabled I found. diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h index df48212f767b..7450ef5ed733 100644 --- a/arch/arm64/include/asm/topology.h +++ b/arch/arm64/include/asm/topology.h @@ -12,6 +12,7 @@ struct cpu_topology { cpumask_t thread_sibling; cpumask_t core_sibling; cpumask_t llc_siblings; + cpumask_t node_siblings; /* maintain a stable node sibling list */ }; extern struct cpu_topology cpu_topology[NR_CPUS]; diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index f3e2e3aec0b0..f4eb80852d78 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -677,8 +677,9 @@ void __init smp_prepare_cpus(unsigned int max_cpus) init_cpu_topology(); this_cpu = smp_processor_id(); - store_cpu_topology(this_cpu); numa_store_cpu_info(this_cpu); + store_cpu_topology(this_cpu); + /* * If UP is mandated by "nosmp" (which implies "maxcpus=0"), don't set diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c index 7415c166281f..6819c764537d 100644 --- a/arch/arm64/kernel/topology.c +++ b/arch/arm64/kernel/topology.c @@ -215,7 +215,7 @@ EXPORT_SYMBOL_GPL(cpu_topology); const struct cpumask *cpu_coregroup_mask(int cpu) { - const cpumask_t *core_mask = cpumask_of_node(cpu_to_node(cpu)); + const cpumask_t *core_mask = &cpu_topology[cpu].node_siblings; /* Find the smaller of NUMA, core or LLC siblings */ if (cpumask_subset(&cpu_topology[cpu].core_sibling, core_mask)) { @@ -233,12 +233,16 @@ const struct cpumask *cpu_coregroup_mask(int cpu) static void update_siblings_masks(unsigned int cpuid) { struct cpu_topology *cpu_topo, *cpuid_topo = &cpu_topology[cpuid]; + int node = cpu_to_node(cpuid); int cpu; /* update core and thread sibling masks */ for_each_possible_cpu(cpu) { cpu_topo = &cpu_topology[cpu]; + if (cpu_to_node(cpu) == node) + cpumask_set_cpu(cpu, &cpu_topo->node_siblings); + if (cpuid_topo->llc_id == cpu_topo->llc_id) cpumask_set_cpu(cpu, &cpuid_topo->llc_siblings); @@ -311,6 +315,9 @@ static void __init reset_cpu_topology(void) cpumask_clear(&cpu_topo->llc_siblings); cpumask_set_cpu(cpu, &cpu_topo->llc_siblings); + cpumask_clear(&cpu_topo->node_siblings); + cpumask_set_cpu(cpu, &cpu_topo->node_siblings); + cpumask_clear(&cpu_topo->core_sibling); cpumask_set_cpu(cpu, &cpu_topo->core_sibling); cpumask_clear(&cpu_topo->thread_sibling); -- 2.14.3 From mboxrd@z Thu Jan 1 00:00:00 1970 From: jeremy.linton@arm.com (Jeremy Linton) Date: Tue, 29 May 2018 16:52:04 -0500 Subject: [PATCH v9 00/12] Support PPTT for ARM64 In-Reply-To: References: <20180511235807.30834-1-jeremy.linton@arm.com> <20180517170523.h7tuvbzdfluuidcz@armageddon.cambridge.arm.com> <09fb3fe7-d703-43f1-74f7-f8cb5ff1f67a@arm.com> <551905a6-eaa8-97df-06ec-1ceedfbc164f@arm.com> <20180529150823.GD17159@arm.com> Message-ID: To: linux-arm-kernel@lists.infradead.org List-Id: linux-arm-kernel.lists.infradead.org Hi, On 05/29/2018 10:51 AM, Geert Uytterhoeven wrote: > Hi Will, > > On Tue, May 29, 2018 at 5:08 PM, Will Deacon wrote: >> On Tue, May 29, 2018 at 02:18:40PM +0100, Sudeep Holla wrote: >>> On 29/05/18 12:56, Geert Uytterhoeven wrote: >>>> On Tue, May 29, 2018 at 1:14 PM, Sudeep Holla wrote: >>>>> On 29/05/18 11:48, Geert Uytterhoeven wrote: >>>>>> System supend still works fine on systems with big cores only: >>>>>> >>>>>> R-Car H3 ES1.0 (4xCA57 (4xCA53 disabled in firmware)) >>>>>> R-Car M3-N (2xCA57) >>>>>> >>>>>> Reverting this commit fixes the issue for me. >>>>> >>>>> I can't find anything that relates to system suspend in these patches >>>>> unless they are messing with something during CPU hot plug-in back >>>>> during resume. >>>> >>>> It's only the last patch that introduces the breakage. >>>> >>> >>> As specified in the commit log, it won't change any behavior for DT >>> systems if it's non-NUMA or single node system. So I am still wondering >>> what could trigger this regression. >> >> I wonder if we're somehow giving an uninitialised/invalid NUMA configuration >> to the scheduler, although I can't see how this would happen. >> >> Geert -- if you enable CONFIG_DEBUG_PER_CPU_MAPS=y and apply the diff below >> do you see anything shouting in dmesg? > > Thanks, but unfortunately it doesn't help. > I added some debug code to print cpumask, but so far I don't see anything > suspicious. I suspect most of the problem is related to the node mask changing at unexpected times (particularly cores being removed from the mask). Once I understand that more, there may be a simpler patch. OTOH, I've been testing with this, and with it, I can't seem to duplicate the problem with CONFIG_NUMA disabled I found. diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h index df48212f767b..7450ef5ed733 100644 --- a/arch/arm64/include/asm/topology.h +++ b/arch/arm64/include/asm/topology.h @@ -12,6 +12,7 @@ struct cpu_topology { cpumask_t thread_sibling; cpumask_t core_sibling; cpumask_t llc_siblings; + cpumask_t node_siblings; /* maintain a stable node sibling list */ }; extern struct cpu_topology cpu_topology[NR_CPUS]; diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index f3e2e3aec0b0..f4eb80852d78 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -677,8 +677,9 @@ void __init smp_prepare_cpus(unsigned int max_cpus) init_cpu_topology(); this_cpu = smp_processor_id(); - store_cpu_topology(this_cpu); numa_store_cpu_info(this_cpu); + store_cpu_topology(this_cpu); + /* * If UP is mandated by "nosmp" (which implies "maxcpus=0"), don't set diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c index 7415c166281f..6819c764537d 100644 --- a/arch/arm64/kernel/topology.c +++ b/arch/arm64/kernel/topology.c @@ -215,7 +215,7 @@ EXPORT_SYMBOL_GPL(cpu_topology); const struct cpumask *cpu_coregroup_mask(int cpu) { - const cpumask_t *core_mask = cpumask_of_node(cpu_to_node(cpu)); + const cpumask_t *core_mask = &cpu_topology[cpu].node_siblings; /* Find the smaller of NUMA, core or LLC siblings */ if (cpumask_subset(&cpu_topology[cpu].core_sibling, core_mask)) { @@ -233,12 +233,16 @@ const struct cpumask *cpu_coregroup_mask(int cpu) static void update_siblings_masks(unsigned int cpuid) { struct cpu_topology *cpu_topo, *cpuid_topo = &cpu_topology[cpuid]; + int node = cpu_to_node(cpuid); int cpu; /* update core and thread sibling masks */ for_each_possible_cpu(cpu) { cpu_topo = &cpu_topology[cpu]; + if (cpu_to_node(cpu) == node) + cpumask_set_cpu(cpu, &cpu_topo->node_siblings); + if (cpuid_topo->llc_id == cpu_topo->llc_id) cpumask_set_cpu(cpu, &cpuid_topo->llc_siblings); @@ -311,6 +315,9 @@ static void __init reset_cpu_topology(void) cpumask_clear(&cpu_topo->llc_siblings); cpumask_set_cpu(cpu, &cpu_topo->llc_siblings); + cpumask_clear(&cpu_topo->node_siblings); + cpumask_set_cpu(cpu, &cpu_topo->node_siblings); + cpumask_clear(&cpu_topo->core_sibling); cpumask_set_cpu(cpu, &cpu_topo->core_sibling); cpumask_clear(&cpu_topo->thread_sibling); -- 2.14.3