Hi Tony, On 10/20/2023 2:30 PM, Tony Luck wrote: > Resctrl assumes that control and monitor operations on a resource are > performed at the same scope. > > Prepare for systems that use different scope (specifically L3 scope for > cache control and NODE scope for cache occupancy and memory bandwidth > monitoring). The first paragraph is a generalization of all resources but then the second paragraph only mentions L3. In preparation for readers seeing that only L3 resource's monitoring scope initialized it may help to be specific here that resctrl only supports monitoring on L3. > Create separate domain lists for control and monitor operations. Please do note that an upcoming change changes the domain list locking. I expect the transition to go smoothly with the locking and list type translating to both lists so just sharing for your information in case you are now aware: https://lore.kernel.org/lkml/20231025180345.28061-25-james.morse@xxxxxxx/ > > Note that errors during initialization of either control or monitor > functions on a domain would previously result in that domain being > excluded from both control and monitor operations. Now the domains are > allocated independently it is no longer required to disable both control > and monitor operations if either fail. > > Signed-off-by: Tony Luck <tony.luck@xxxxxxxxx> > --- ... > @@ -356,7 +359,7 @@ struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r) > { > struct rdt_domain *d; > > - list_for_each_entry(d, &r->domains, hdr.list) { > + list_for_each_entry(d, &r->ctrl_domains, hdr.list) { > /* Find the domain that contains this CPU */ > if (cpumask_test_cpu(cpu, &d->cpu_mask)) > return d; This appears to silently turn a generic "get_domain_from_cpu()" into code that assumes control domain. This works for now for the existing users but can trip up future changes. I think this would be better renamed to get_ctrl_domain_from_cpu() or something better. > @@ -388,29 +391,39 @@ void rdt_ctrl_update(void *arg) > } > > /* > - * rdt_find_domain - Find a domain in a resource that matches input resource id > + * rdt_find_domain - Find a domain in one of a resource domain lists. The above does not sound right. "one of a resource domain lists" -> "a resource domain list" or "one of the resource domain lists" or ? > * > - * Search resource r's domain list to find the resource id. If the resource > - * id is found in a domain, return the domain. Otherwise, if requested by > - * caller, return the first domain whose id is bigger than the input id. > + * Search the list to find the resource id. If the resource id is found > + * in a domain, return the domain. Otherwise, if requested by caller, > + * return the first domain whose id is bigger than the input id. The above does not sound right. First there is "Search the list to find the resource id." The resource id is not involved in this code, do you mean "domain id"? Also later "If the resource id is found in a domain," what does that mean here? > * The domain list is sorted by id in ascending order. > + * > + * If an existing domain in the resource r's domain list matches the cpu's > + * resource id, add the cpu in the domain. domain id? > + * > + * Otherwise, caller will allocate a new domain and insert into the right position > + * in the domain list sorted by id in ascending order. > + * > + * The order in the domain list is visible to users when we print entries > + * in the schemata file and schemata input is validated to have the same order > + * as this list. Please document what the caller does at the caller. Also, please always use "CPU", not "cpu". Finally, please do not impersonate code (no "we"). I understand you are copying original comments, no need to propagate these issues. > */ > -struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id, > - struct list_head **pos) > +struct rdt_domain_hdr *rdt_find_domain(struct list_head *h, int id, > + struct list_head **pos) > { > - struct rdt_domain *d; > + struct rdt_domain_hdr *d; > struct list_head *l; > > if (id < 0) > return ERR_PTR(-ENODEV); > > - list_for_each(l, &r->domains) { > - d = list_entry(l, struct rdt_domain, hdr.list); > + list_for_each(l, h) { > + d = list_entry(l, struct rdt_domain_hdr, list); > /* When id is found, return its domain. */ > - if (id == d->hdr.id) > + if (id == d->id) > return d; > /* Stop searching when finding id's position in sorted list. */ > - if (id < d->hdr.id) > + if (id < d->id) > break; > } > > @@ -504,39 +517,33 @@ static int get_domain_id_from_scope(int cpu, enum resctrl_scope scope) > return -EINVAL; > } > > -/* > - * domain_add_cpu - Add a cpu to a resource's domain list. > - * > - * If an existing domain in the resource r's domain list matches the cpu's > - * resource id, add the cpu in the domain. > - * > - * Otherwise, a new domain is allocated and inserted into the right position > - * in the domain list sorted by id in ascending order. > - * > - * The order in the domain list is visible to users when we print entries > - * in the schemata file and schemata input is validated to have the same order > - * as this list. > - */ > -static void domain_add_cpu(int cpu, struct rdt_resource *r) > +static void domain_add_cpu_ctrl(int cpu, struct rdt_resource *r) > { > - int id = get_domain_id_from_scope(cpu, r->scope); > + int id = get_domain_id_from_scope(cpu, r->ctrl_scope); > struct list_head *add_pos = NULL; > struct rdt_hw_domain *hw_dom; > + struct rdt_domain_hdr *hdr; > struct rdt_domain *d; > int err; > > if (id < 0) { > - pr_warn_once("Can't find domain id for CPU:%d scope:%d for resource %s\n", > - cpu, r->scope, r->name); > + pr_warn_once("Can't find control domain id for CPU:%d scope:%d for resource %s\n", > + cpu, r->ctrl_scope, r->name); > return; > } > - d = rdt_find_domain(r, id, &add_pos); > - if (IS_ERR(d)) { > - pr_warn("Couldn't find cache id for CPU %d\n", cpu); > + > + hdr = rdt_find_domain(&r->ctrl_domains, id, &add_pos); > + if (IS_ERR(hdr)) { > + pr_warn("Couldn't find control scope id=%d for CPU %d\n", id, cpu); How can the failure in the error message be encountered at this point? > return; > } > > - if (d) { > + if (hdr) { > + if (WARN_ON_ONCE(hdr->type != RESCTRL_CTRL_DOMAIN)) > + return; > + > + d = container_of(hdr, struct rdt_domain, hdr); > + > cpumask_set_cpu(cpu, &d->cpu_mask); > if (r->cache.arch_has_per_cpu_cfg) > rdt_domain_reconfigure_cdp(r); > @@ -549,48 +556,115 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r) > > d = &hw_dom->d_resctrl; > d->hdr.id = id; > + d->hdr.type = RESCTRL_CTRL_DOMAIN; > cpumask_set_cpu(cpu, &d->cpu_mask); > > rdt_domain_reconfigure_cdp(r); > > - if (r->alloc_capable && domain_setup_ctrlval(r, d)) { > + if (domain_setup_ctrlval(r, d)) { > + domain_free(hw_dom); > + return; > + } > + > + list_add_tail(&d->hdr.list, add_pos); > + > + err = resctrl_online_ctrl_domain(r, d); > + if (err) { > + list_del(&d->hdr.list); > domain_free(hw_dom); > + } > +} > + > +static void domain_add_cpu_mon(int cpu, struct rdt_resource *r) > +{ > + int id = get_domain_id_from_scope(cpu, r->mon_scope); > + struct list_head *add_pos = NULL; > + struct rdt_hw_domain *hw_dom; > + struct rdt_domain_hdr *hdr; > + struct rdt_domain *d; > + int err; > + > + if (id < 0) { > + pr_warn_once("Can't find monitor domain id for CPU:%d scope:%d for resource %s\n", > + cpu, r->mon_scope, r->name); > + return; > + } > + > + hdr = rdt_find_domain(&r->mon_domains, id, &add_pos); > + if (IS_ERR(hdr)) { > + pr_warn("Couldn't find monitor scope id=%d for CPU %d\n", id, cpu); > + return; > + } > + > + if (hdr) { > + if (WARN_ON_ONCE(hdr->type != RESCTRL_MON_DOMAIN)) > + return; > + > + d = container_of(hdr, struct rdt_domain, hdr); > + > + cpumask_set_cpu(cpu, &d->cpu_mask); > return; > } > > - if (r->mon_capable && arch_domain_mbm_alloc(r->num_rmid, hw_dom)) { > + hw_dom = kzalloc_node(sizeof(*hw_dom), GFP_KERNEL, cpu_to_node(cpu)); > + if (!hw_dom) > + return; > + > + d = &hw_dom->d_resctrl; > + d->hdr.id = id; > + d->hdr.type = RESCTRL_MON_DOMAIN; > + cpumask_set_cpu(cpu, &d->cpu_mask); > + > + if (arch_domain_mbm_alloc(r->num_rmid, hw_dom)) { > domain_free(hw_dom); > return; > } > > list_add_tail(&d->hdr.list, add_pos); > > - err = resctrl_online_domain(r, d); > + err = resctrl_online_mon_domain(r, d); > if (err) { > list_del(&d->hdr.list); > domain_free(hw_dom); > } > } > > -static void domain_remove_cpu(int cpu, struct rdt_resource *r) > +/* > + * domain_add_cpu - Add a cpu to either/both resource's domain lists. cpu -> CPU (please check all changelog and comments) > + */ > +static void domain_add_cpu(int cpu, struct rdt_resource *r) > +{ > + if (r->alloc_capable) > + domain_add_cpu_ctrl(cpu, r); > + if (r->mon_capable) > + domain_add_cpu_mon(cpu, r); > +} > + > @@ -3914,18 +3916,22 @@ static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d) > return 0; > } > > -int resctrl_online_domain(struct rdt_resource *r, struct rdt_domain *d) > +int resctrl_online_ctrl_domain(struct rdt_resource *r, struct rdt_domain *d) > { > - int err; > - > lockdep_assert_held(&rdtgroup_mutex); > > if (supports_mba_mbps() && r->rid == RDT_RESOURCE_MBA) > /* RDT_RESOURCE_MBA is never mon_capable */ This comment was used to justify the early exit based on later "if (!r->mon_capable)" test. With the test removed this comment becomes unnecessary. Reinette
