From: David Gibson <david@gibson.dropbear.id.au>
To: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Cc: Nathan Lynch <nathanl@linux.ibm.com>,
Daniel Henrique Barboza <danielhb413@gmail.com>,
linuxppc-dev@lists.ozlabs.org
Subject: Re: [PATCH v6 3/6] powerpc/pseries: Consolidate different NUMA distance update code paths
Date: Fri, 6 Aug 2021 16:37:47 +1000 [thread overview]
Message-ID: <YQzYu8KpqV2L/rIW@yekko> (raw)
In-Reply-To: <20210727100311.310969-4-aneesh.kumar@linux.ibm.com>
[-- Attachment #1: Type: text/plain, Size: 11361 bytes --]
On Tue, Jul 27, 2021 at 03:33:08PM +0530, Aneesh Kumar K.V wrote:
> The associativity details of the newly added resourced are collected from
> the hypervisor via "ibm,configure-connector" rtas call. Update the numa
> distance details of the newly added numa node after the above call.
>
> Instead of updating NUMA distance every time we lookup a node id
> from the associativity property, add helpers that can be used
> during boot which does this only once. Also remove the distance
> update from node id lookup helpers.
>
> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
> ---
> arch/powerpc/include/asm/topology.h | 2 +
> arch/powerpc/mm/numa.c | 178 +++++++++++++-----
> arch/powerpc/platforms/pseries/hotplug-cpu.c | 2 +
> .../platforms/pseries/hotplug-memory.c | 2 +
> 4 files changed, 138 insertions(+), 46 deletions(-)
>
> diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
> index e4db64c0e184..a6425a70c37b 100644
> --- a/arch/powerpc/include/asm/topology.h
> +++ b/arch/powerpc/include/asm/topology.h
> @@ -64,6 +64,7 @@ static inline int early_cpu_to_node(int cpu)
> }
>
> int of_drconf_to_nid_single(struct drmem_lmb *lmb);
> +void update_numa_distance(struct device_node *node);
>
> #else
>
> @@ -93,6 +94,7 @@ static inline int of_drconf_to_nid_single(struct drmem_lmb *lmb)
> return first_online_node;
> }
>
> +static inline void update_numa_distance(struct device_node *node) {}
> #endif /* CONFIG_NUMA */
>
> #if defined(CONFIG_NUMA) && defined(CONFIG_PPC_SPLPAR)
> diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
> index 368719b14dcc..c695faf67d68 100644
> --- a/arch/powerpc/mm/numa.c
> +++ b/arch/powerpc/mm/numa.c
> @@ -208,22 +208,6 @@ int __node_distance(int a, int b)
> }
> EXPORT_SYMBOL(__node_distance);
>
> -static void initialize_distance_lookup_table(int nid,
> - const __be32 *associativity)
> -{
> - int i;
> -
> - if (affinity_form != FORM1_AFFINITY)
> - return;
> -
> - for (i = 0; i < distance_ref_points_depth; i++) {
> - const __be32 *entry;
> -
> - entry = &associativity[be32_to_cpu(distance_ref_points[i]) - 1];
> - distance_lookup_table[nid][i] = of_read_number(entry, 1);
> - }
> -}
> -
> /*
> * Returns nid in the range [0..nr_node_ids], or -1 if no useful NUMA
> * info is found.
> @@ -241,15 +225,6 @@ static int associativity_to_nid(const __be32 *associativity)
> /* POWER4 LPAR uses 0xffff as invalid node */
> if (nid == 0xffff || nid >= nr_node_ids)
> nid = NUMA_NO_NODE;
> -
> - if (nid > 0 &&
> - of_read_number(associativity, 1) >= distance_ref_points_depth) {
> - /*
> - * Skip the length field and send start of associativity array
> - */
> - initialize_distance_lookup_table(nid, associativity + 1);
> - }
> -
> out:
> return nid;
> }
> @@ -287,6 +262,48 @@ int of_node_to_nid(struct device_node *device)
> }
> EXPORT_SYMBOL(of_node_to_nid);
>
> +static void __initialize_form1_numa_distance(const __be32 *associativity)
> +{
> + int i, nid;
> +
> + if (affinity_form != FORM1_AFFINITY)
> + return;
> +
> + nid = associativity_to_nid(associativity);
> + if (nid != NUMA_NO_NODE) {
> + for (i = 0; i < distance_ref_points_depth; i++) {
> + const __be32 *entry;
> +
> + entry = &associativity[be32_to_cpu(distance_ref_points[i])];
> + distance_lookup_table[nid][i] = of_read_number(entry, 1);
So, in the conversion from the old initialize_distance_lookup_table()
you change this from accepting a bare associativity list, to requiring
the length on the front. [*]
> + }
> + }
> +}
> +
> +static void initialize_form1_numa_distance(struct device_node *node)
> +{
> + const __be32 *associativity;
> +
> + associativity = of_get_associativity(node);
> + if (!associativity)
> + return;
> +
> + __initialize_form1_numa_distance(associativity);
> +}
> +
> +/*
> + * Used to update distance information w.r.t newly added node.
> + */
> +void update_numa_distance(struct device_node *node)
> +{
> + if (affinity_form == FORM0_AFFINITY)
> + return;
> + else if (affinity_form == FORM1_AFFINITY) {
> + initialize_form1_numa_distance(node);
> + return;
> + }
> +}
> +
> static int __init find_primary_domain_index(void)
> {
> int index;
> @@ -433,6 +450,48 @@ static int of_get_assoc_arrays(struct assoc_arrays *aa)
> return 0;
> }
>
> +static int get_nid_and_numa_distance(struct drmem_lmb *lmb)
> +{
> + struct assoc_arrays aa = { .arrays = NULL };
> + int default_nid = NUMA_NO_NODE;
You never change default_nid, so it seems like it would be clearer to
get rid of this and just use NUMA_NO_NODE inline everywhere below.
> + int nid = default_nid;
> + int rc, index;
> +
> + if ((primary_domain_index < 0) || !numa_enabled)
> + return default_nid;
> +
> + rc = of_get_assoc_arrays(&aa);
> + if (rc)
> + return default_nid;
> +
> + if (primary_domain_index <= aa.array_sz &&
> + !(lmb->flags & DRCONF_MEM_AI_INVALID) && lmb->aa_index < aa.n_arrays) {
> + index = lmb->aa_index * aa.array_sz + primary_domain_index - 1;
> + nid = of_read_number(&aa.arrays[index], 1);
> +
> + if (nid == 0xffff || nid >= nr_node_ids)
> + nid = default_nid;
> + if (nid > 0 && affinity_form == FORM1_AFFINITY) {
Is the nid > 0 test assuming something about what are and aren't valid
nids? Should it be nid != NUMA_NO_NODE instead?
> + int i;
> + const __be32 *associativity;
> +
> + index = lmb->aa_index * aa.array_sz;
> + associativity = &aa.arrays[index];
Again, you can reuse form1_numa_distance() here if it weren't for the
fact that you broke it at [*] above to no longer accept bare
associativity lists.
> + /*
> + * lookup array associativity entries have different format
> + * There is no length of the array as the first element.
> + */
> + for (i = 0; i < distance_ref_points_depth; i++) {
> + const __be32 *entry;
> +
> + entry = &associativity[be32_to_cpu(distance_ref_points[i]) - 1];
> + distance_lookup_table[nid][i] = of_read_number(entry, 1);
> + }
> + }
> + }
> + return nid;
> +}
> +
> /*
> * This is like of_node_to_nid_single() for memory represented in the
> * ibm,dynamic-reconfiguration-memory node.
> @@ -458,21 +517,14 @@ int of_drconf_to_nid_single(struct drmem_lmb *lmb)
>
> if (nid == 0xffff || nid >= nr_node_ids)
> nid = default_nid;
> -
> - if (nid > 0) {
> - index = lmb->aa_index * aa.array_sz;
> - initialize_distance_lookup_table(nid,
> - &aa.arrays[index]);
> - }
> }
> -
> return nid;
> }
>
> #ifdef CONFIG_PPC_SPLPAR
> -static int vphn_get_nid(long lcpu)
> +
> +static int __vphn_get_associativity(long lcpu, __be32 *associativity)
> {
> - __be32 associativity[VPHN_ASSOC_BUFSIZE] = {0};
> long rc, hwid;
>
> /*
> @@ -492,12 +544,30 @@ static int vphn_get_nid(long lcpu)
>
> rc = hcall_vphn(hwid, VPHN_FLAG_VCPU, associativity);
> if (rc == H_SUCCESS)
> - return associativity_to_nid(associativity);
> + return 0;
> }
>
> + return -1;
> +}
> +
> +static int vphn_get_nid(long lcpu)
> +{
> + __be32 associativity[VPHN_ASSOC_BUFSIZE] = {0};
> +
> +
> + if (!__vphn_get_associativity(lcpu, associativity))
> + return associativity_to_nid(associativity);
> +
> return NUMA_NO_NODE;
> +
> }
> #else
> +
> +static int __vphn_get_associativity(long lcpu, __be32 *associativity)
> +{
> + return -1;
> +}
> +
> static int vphn_get_nid(long unused)
> {
> return NUMA_NO_NODE;
> @@ -692,7 +762,7 @@ static int __init numa_setup_drmem_lmb(struct drmem_lmb *lmb,
> size = read_n_cells(n_mem_size_cells, usm);
> }
>
> - nid = of_drconf_to_nid_single(lmb);
> + nid = get_nid_and_numa_distance(lmb);
> fake_numa_create_new_node(((base + size) >> PAGE_SHIFT),
> &nid);
> node_set_online(nid);
> @@ -709,6 +779,7 @@ static int __init parse_numa_properties(void)
> struct device_node *memory;
> int default_nid = 0;
> unsigned long i;
> + const __be32 *associativity;
>
> if (numa_enabled == 0) {
> printk(KERN_WARNING "NUMA disabled by user\n");
> @@ -734,18 +805,30 @@ static int __init parse_numa_properties(void)
> * each node to be onlined must have NODE_DATA etc backing it.
> */
> for_each_present_cpu(i) {
> + __be32 vphn_assoc[VPHN_ASSOC_BUFSIZE];
> struct device_node *cpu;
> - int nid = vphn_get_nid(i);
> + int nid = NUMA_NO_NODE;
>
> - /*
> - * Don't fall back to default_nid yet -- we will plug
> - * cpus into nodes once the memory scan has discovered
> - * the topology.
> - */
> - if (nid == NUMA_NO_NODE) {
> + memset(vphn_assoc, 0, VPHN_ASSOC_BUFSIZE * sizeof(__be32));
> +
> + if (__vphn_get_associativity(i, vphn_assoc) == 0) {
> + nid = associativity_to_nid(vphn_assoc);
> + __initialize_form1_numa_distance(vphn_assoc);
> + } else {
> +
> + /*
> + * Don't fall back to default_nid yet -- we will plug
> + * cpus into nodes once the memory scan has discovered
> + * the topology.
> + */
> cpu = of_get_cpu_node(i, NULL);
> BUG_ON(!cpu);
> - nid = of_node_to_nid_single(cpu);
> +
> + associativity = of_get_associativity(cpu);
> + if (associativity) {
> + nid = associativity_to_nid(associativity);
> + __initialize_form1_numa_distance(associativity);
> + }
> of_node_put(cpu);
> }
>
> @@ -781,8 +864,11 @@ static int __init parse_numa_properties(void)
> * have associativity properties. If none, then
> * everything goes to default_nid.
> */
> - nid = of_node_to_nid_single(memory);
> - if (nid < 0)
> + associativity = of_get_associativity(memory);
> + if (associativity) {
> + nid = associativity_to_nid(associativity);
> + __initialize_form1_numa_distance(associativity);
> + } else
> nid = default_nid;
>
> fake_numa_create_new_node(((start + size) >> PAGE_SHIFT), &nid);
> diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
> index 7e970f81d8ff..778b6ab35f0d 100644
> --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
> +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
> @@ -498,6 +498,8 @@ static ssize_t dlpar_cpu_add(u32 drc_index)
> return saved_rc;
> }
>
> + update_numa_distance(dn);
> +
> rc = dlpar_online_cpu(dn);
> if (rc) {
> saved_rc = rc;
> diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c
> index 377d852f5a9a..ee1d81d7e54a 100644
> --- a/arch/powerpc/platforms/pseries/hotplug-memory.c
> +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
> @@ -180,6 +180,8 @@ static int update_lmb_associativity_index(struct drmem_lmb *lmb)
> return -ENODEV;
> }
>
> + update_numa_distance(lmb_node);
> +
> dr_node = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory");
> if (!dr_node) {
> dlpar_free_cc_nodes(lmb_node);
--
David Gibson | I'll have my music baroque, and my code
david AT gibson.dropbear.id.au | minimalist, thank you. NOT _the_ _other_
| _way_ _around_!
http://www.ozlabs.org/~dgibson
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]
next prev parent reply other threads:[~2021-08-06 6:50 UTC|newest]
Thread overview: 11+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-07-27 10:03 [PATCH v6 0/6] Add support for FORM2 associativity Aneesh Kumar K.V
2021-07-27 10:03 ` [PATCH v6 1/6] powerpc/pseries: rename min_common_depth to primary_domain_index Aneesh Kumar K.V
2021-07-27 10:03 ` [PATCH v6 2/6] powerpc/pseries: Rename TYPE1_AFFINITY to FORM1_AFFINITY Aneesh Kumar K.V
2021-07-27 10:03 ` [PATCH v6 3/6] powerpc/pseries: Consolidate different NUMA distance update code paths Aneesh Kumar K.V
2021-08-06 6:37 ` David Gibson [this message]
2021-07-27 10:03 ` [PATCH v6 4/6] powerpc/pseries: Add a helper for form1 cpu distance Aneesh Kumar K.V
2021-07-27 10:03 ` [PATCH v6 5/6] powerpc/pseries: Add support for FORM2 associativity Aneesh Kumar K.V
2021-07-27 10:03 ` [PATCH v6 6/6] powerpc/pseries: Consolidate form1 distance initialization into a helper Aneesh Kumar K.V
2021-08-06 6:47 ` David Gibson
2021-08-06 16:23 ` Aneesh Kumar K.V
2021-08-09 3:27 ` David Gibson
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=YQzYu8KpqV2L/rIW@yekko \
--to=david@gibson.dropbear.id.au \
--cc=aneesh.kumar@linux.ibm.com \
--cc=danielhb413@gmail.com \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=nathanl@linux.ibm.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).