Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Date:   Tue, 3 Jul 2018 14:16:55 -0300
From:   Murilo Opsfelder Araujo <muriloo@linux.ibm.com>
To:     "Gautham R. Shenoy" <ego@linux.vnet.ibm.com>
Cc:     Michael Ellerman <mpe@ellerman.id.au>,
        Benjamin Herrenschmidt <benh@kernel.crashing.org>,
        Michael Neuling <mikey@neuling.org>,
        Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>,
        Akshay Adiga <akshay.adiga@linux.vnet.ibm.com>,
        Shilpasri G Bhat <shilpa.bhat@linux.vnet.ibm.com>,
        "Oliver O'Halloran" <oohall@gmail.com>,
        Nicholas Piggin <npiggin@gmail.com>,
        linuxppc-dev@lists.ozlabs.org, linux-kernel@vger.kernel.org
Subject: Re: [v2 PATCH 1/2] powerpc: Detect the presence of big-cores via
 "ibm, thread-groups"
References: <cover.1530609795.git.ego@linux.vnet.ibm.com>
 <b922aa0ea79a83ad733508c861900a08c4fee25a.1530609795.git.ego@linux.vnet.ibm.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <b922aa0ea79a83ad733508c861900a08c4fee25a.1530609795.git.ego@linux.vnet.ibm.com>
User-Agent: Mutt/1.10.0 (2018-05-17)
Message-Id: <20180703171655.GA6474@kermit-br-ibm-com.br.ibm.com>
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Tue, Jul 03, 2018 at 04:33:50PM +0530, Gautham R. Shenoy wrote:
> From: "Gautham R. Shenoy" <ego@linux.vnet.ibm.com>
> 
> On IBM POWER9, the device tree exposes a property array identifed by
> "ibm,thread-groups" which will indicate which groups of threads share a
> particular set of resources.
> 
> As of today we only have one form of grouping identifying the group of
> threads in the core that share the L1 cache, translation cache and
> instruction data flow.
> 
> This patch defines the helper function to parse the contents of
> "ibm,thread-groups" and a new structure to contain the parsed output.
> 
> The patch also creates the sysfs file named "small_core_siblings" that
> returns the physical ids of the threads in the core that share the L1
> cache, translation cache and instruction data flow.
> 
> Signed-off-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
> ---
>  Documentation/ABI/testing/sysfs-devices-system-cpu |   8 ++
>  arch/powerpc/include/asm/cputhreads.h              |  22 +++++
>  arch/powerpc/kernel/setup-common.c                 | 110 +++++++++++++++++++++
>  arch/powerpc/kernel/sysfs.c                        |  35 +++++++
>  4 files changed, 175 insertions(+)
> 
> diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu
> index 9c5e7732..53a823a 100644
> --- a/Documentation/ABI/testing/sysfs-devices-system-cpu
> +++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
> @@ -487,3 +487,11 @@ Description:	Information about CPU vulnerabilities
>  		"Not affected"	  CPU is not affected by the vulnerability
>  		"Vulnerable"	  CPU is affected and no mitigation in effect
>  		"Mitigation: $M"  CPU is affected and mitigation $M is in effect
> +
> +What: 		/sys/devices/system/cpu/cpu[0-9]+/small_core_sibings

s/small_core_sibings/small_core_siblings

By the way, big_core_siblings was mentioned in the introductory email.

> +Date:		03-Jul-2018
> +KernelVersion:	v4.18.0
> +Contact:	Gautham R. Shenoy <ego@linux.vnet.ibm.com>
> +Description:	List of Physical ids of CPUs which share the the L1 cache,
> +		translation cache and instruction data-flow with this CPU.
> +Values:		Comma separated list of decimal integers.
> diff --git a/arch/powerpc/include/asm/cputhreads.h b/arch/powerpc/include/asm/cputhreads.h
> index d71a909..33226d7 100644
> --- a/arch/powerpc/include/asm/cputhreads.h
> +++ b/arch/powerpc/include/asm/cputhreads.h
> @@ -23,11 +23,13 @@
>  extern int threads_per_core;
>  extern int threads_per_subcore;
>  extern int threads_shift;
> +extern bool has_big_cores;
>  extern cpumask_t threads_core_mask;
>  #else
>  #define threads_per_core	1
>  #define threads_per_subcore	1
>  #define threads_shift		0
> +#define has_big_cores		0
>  #define threads_core_mask	(*get_cpu_mask(0))
>  #endif
>  
> @@ -69,12 +71,32 @@ static inline cpumask_t cpu_online_cores_map(void)
>  	return cpu_thread_mask_to_cores(cpu_online_mask);
>  }
>  
> +#define MAX_THREAD_LIST_SIZE	8
> +struct thread_groups {
> +	unsigned int property;
> +	unsigned int nr_groups;
> +	unsigned int threads_per_group;
> +	unsigned int thread_list[MAX_THREAD_LIST_SIZE];
> +};
> +
>  #ifdef CONFIG_SMP
>  int cpu_core_index_of_thread(int cpu);
>  int cpu_first_thread_of_core(int core);
> +int parse_thread_groups(struct device_node *dn, struct thread_groups *tg);
> +int get_cpu_thread_group_start(int cpu, struct thread_groups *tg);
>  #else
>  static inline int cpu_core_index_of_thread(int cpu) { return cpu; }
>  static inline int cpu_first_thread_of_core(int core) { return core; }
> +static inline int parse_thread_groups(struct device_node *dn,
> +				      struct thread_groups *tg)
> +{
> +	return -ENODATA;
> +}
> +
> +static inline int get_cpu_thread_group_start(int cpu, struct thread_groups *tg)
> +{
> +	return -1;
> +}
>  #endif
>  
>  static inline int cpu_thread_in_core(int cpu)
> diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
> index 40b44bb..a78ec66 100644
> --- a/arch/powerpc/kernel/setup-common.c
> +++ b/arch/powerpc/kernel/setup-common.c
> @@ -402,10 +402,12 @@ void __init check_for_initrd(void)
>  #ifdef CONFIG_SMP
>  
>  int threads_per_core, threads_per_subcore, threads_shift;
> +bool has_big_cores = true;
>  cpumask_t threads_core_mask;
>  EXPORT_SYMBOL_GPL(threads_per_core);
>  EXPORT_SYMBOL_GPL(threads_per_subcore);
>  EXPORT_SYMBOL_GPL(threads_shift);
> +EXPORT_SYMBOL_GPL(has_big_cores);
>  EXPORT_SYMBOL_GPL(threads_core_mask);
>  
>  static void __init cpu_init_thread_core_maps(int tpc)
> @@ -433,6 +435,108 @@ static void __init cpu_init_thread_core_maps(int tpc)
>  
>  u32 *cpu_to_phys_id = NULL;
>  
> +/*
> + * parse_thread_groups: Parses the "ibm,thread-groups" device tree
> + *                      property for the CPU device node dn and stores
> + *                      the parsed output in the thread_groups
> + *                      structure tg.

Perhaps document the arguments of this function, as done in the second
patch?

> + *
> + * ibm,thread-groups[0..N-1] array defines which group of threads in
> + * the CPU-device node can be grouped together based on the property.
> + *
> + * ibm,thread-groups[0] tells us the property based on which the
> + * threads are being grouped together. If this value is 1, it implies
> + * that the threads in the same group share L1, translation cache.
> + *
> + * ibm,thread-groups[1] tells us how many such thread groups exist.
> + *
> + * ibm,thread-groups[2] tells us the number of threads in each such
> + * group.
> + *
> + * ibm,thread-groups[3..N-1] is the list of threads identified by
> + * "ibm,ppc-interrupt-server#s" arranged as per their membership in
> + * the grouping.
> + *
> + * Example: If ibm,thread-groups = [1,2,4,5,6,7,8,9,10,11,12] it
> + * implies that there are 2 groups of 4 threads each, where each group
> + * of threads share L1, translation cache.
> + *
> + * The "ibm,ppc-interrupt-server#s" of the first group is {5,6,7,8}
> + * and the "ibm,ppc-interrupt-server#s" of the second group is {9, 10,
> + * 11, 12} structure
> + *
> + * Returns 0 on success, -EINVAL if the property does not exist,
> + * -ENODATA if property does not have a value, and -EOVERFLOW if the
> + * property data isn't large enough.
> + */
> +int parse_thread_groups(struct device_node *dn,
> +			struct thread_groups *tg)
> +{
> +	unsigned int nr_groups, threads_per_group, property;
> +	int i;
> +	u32 thread_group_array[3 + MAX_THREAD_LIST_SIZE];
> +	u32 *thread_list;
> +	size_t total_threads;
> +	int ret;
> +
> +	ret = of_property_read_u32_array(dn, "ibm,thread-groups",
> +					 thread_group_array, 3);
> +
> +	if (ret)
> +		return ret;
> +
> +	property = thread_group_array[0];
> +	nr_groups = thread_group_array[1];
> +	threads_per_group = thread_group_array[2];
> +	total_threads = nr_groups * threads_per_group;
> +
> +	ret = of_property_read_u32_array(dn, "ibm,thread-groups",
> +					 thread_group_array,
> +					 3 + total_threads);
> +	if (ret)
> +		return ret;
> +
> +	thread_list = &thread_group_array[3];
> +
> +	for (i = 0 ; i < total_threads; i++)
> +		tg->thread_list[i] = thread_list[i];
> +
> +	tg->property = property;
> +	tg->nr_groups = nr_groups;
> +	tg->threads_per_group = threads_per_group;
> +
> +	return 0;
> +}
> +
> +/*
> + * get_cpu_thread_group_start : Searches the thread group in tg->thread_list
> + *                              that @cpu belongs to.

Same here.

> + *
> + * Returns the index to tg->thread_list that points to the the start
> + * of the thread_group that @cpu belongs to.
> + *
> + * Returns -1 if cpu doesn't belong to any of the groups pointed
> + * to by tg->thread_list.
> + */
> +int get_cpu_thread_group_start(int cpu, struct thread_groups *tg)
> +{
> +	int hw_cpu_id = get_hard_smp_processor_id(cpu);
> +	int i, j;
> +
> +	for (i = 0; i < tg->nr_groups; i++) {
> +		int group_start = i * tg->threads_per_group;
> +
> +		for (j = 0; j < tg->threads_per_group; j++) {
> +			int idx = group_start + j;
> +
> +			if (tg->thread_list[idx] == hw_cpu_id)
> +				return group_start;
> +		}
> +	}
> +
> +	return -1;
> +}
> +
>  /**
>   * setup_cpu_maps - initialize the following cpu maps:
>   *                  cpu_possible_mask
> @@ -467,6 +571,7 @@ void __init smp_setup_cpu_maps(void)
>  		const __be32 *intserv;
>  		__be32 cpu_be;
>  		int j, len;
> +		struct thread_groups tg = {.nr_groups = 0};

We assume has_big_cores = true but here we initialize .nr_groups
otherwise.  It's kind of contradictory.

What if has_big_cores is assumed false and members of tg are initialized
with zeroes?

>  
>  		DBG("  * %pOF...\n", dn);
>  
> @@ -505,6 +610,11 @@ void __init smp_setup_cpu_maps(void)
>  			cpu++;
>  		}
>  
> +		if (parse_thread_groups(dn, &tg) ||
> +		    tg.nr_groups < 1 || tg.property != 1) {
> +			has_big_cores = false;
> +		}
> +

parse_thread_groups() returns before setting tg.property if property
doesn't exist.  Are we confident that tg.property won't contain any
garbage that could lead to a false positive here?  Shouldn't we also
initialize .property when declaring tg?

What if this logic is encapsulated in a function?  For example:

    has_big_cores = dt_has_big_cores(dn, &tg);

>  		if (cpu >= nr_cpu_ids) {
>  			of_node_put(dn);
>  			break;
> diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
> index 755dc98..f5717de 100644
> --- a/arch/powerpc/kernel/sysfs.c
> +++ b/arch/powerpc/kernel/sysfs.c
> @@ -18,6 +18,7 @@
>  #include <asm/smp.h>
>  #include <asm/pmc.h>
>  #include <asm/firmware.h>
> +#include <asm/cputhreads.h>
>  
>  #include "cacheinfo.h"
>  #include "setup.h"
> @@ -1025,6 +1026,33 @@ static ssize_t show_physical_id(struct device *dev,
>  }
>  static DEVICE_ATTR(physical_id, 0444, show_physical_id, NULL);
>  
> +static ssize_t show_small_core_siblings(struct device *dev,
> +					struct device_attribute *attr,
> +					char *buf)
> +{
> +	struct cpu *cpu = container_of(dev, struct cpu, dev);
> +	struct device_node *dn = of_get_cpu_node(cpu->dev.id, NULL);
> +	struct thread_groups tg;
> +	int i, j;
> +	ssize_t ret = 0;
> +
> +	if (parse_thread_groups(dn, &tg))
> +		return -ENODATA;
> +
> +	i = get_cpu_thread_group_start(cpu->dev.id, &tg);
> +
> +	if (i == -1)
> +		return -ENODATA;
> +
> +	for (j = 0; j < tg.threads_per_group - 1; j++)
> +		ret += sprintf(buf + ret, "%d,", tg.thread_list[i + j]);
> +
> +	ret += sprintf(buf + ret, "%d\n", tg.thread_list[i + j]);
> +
> +	return ret;
> +}
> +static DEVICE_ATTR(small_core_siblings, 0444, show_small_core_siblings, NULL);
> +
>  static int __init topology_init(void)
>  {
>  	int cpu, r;
> @@ -1048,6 +1076,13 @@ static int __init topology_init(void)
>  			register_cpu(c, cpu);
>  
>  			device_create_file(&c->dev, &dev_attr_physical_id);
> +
> +			if (has_big_cores) {
> +				const struct device_attribute *attr =
> +				       &dev_attr_small_core_siblings;
> +
> +			       device_create_file(&c->dev, attr);
> +			}
>  		}
>  	}
>  	r = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "powerpc/topology:online",
> -- 
> 1.9.4
> 

Cheers
Murilo