Hi Reinette, On 8/16/24 17:33, Reinette Chatre wrote: > Hi Babu, > > On 8/6/24 3:00 PM, Babu Moger wrote: >> Introduce the interface to assign MBM events in ABMC mode. >> >> Events can be enabled or disabled by writing to file >> /sys/fs/resctrl/info/L3_MON/mbm_control >> >> Format is similar to the list format with addition of opcode for the >> assignment operation. >> "<CTRL_MON group>/<MON group>/<domain_id><opcode><flags>" >> >> Format for specific type of groups: >> >> * Default CTRL_MON group: >> "//<domain_id><opcode><flags>" >> >> * Non-default CTRL_MON group: >> "<CTRL_MON group>//<domain_id><opcode><flags>" >> >> * Child MON group of default CTRL_MON group: >> "/<MON group>/<domain_id><opcode><flags>" >> >> * Child MON group of non-default CTRL_MON group: >> "<CTRL_MON group>/<MON group>/<domain_id><opcode><flags>" >> >> Domain_id '*' will apply the flags on all the domains. >> >> Opcode can be one of the following: >> >> = Update the assignment to match the flags >> + assign a MBM event >> - unassign a MBM event >> >> Assignment flags can be one of the following: >> t MBM total event >> l MBM local event >> tl Both total and local MBM events >> _ None of the MBM events. Valid only with '=' opcode. > > (please note comments in this area of cover letter) Ok. Yes. Will test differrent cobminations of flags(like _lt etc..). > >> >> Signed-off-by: Babu Moger <babu.moger@xxxxxxx> >> --- >> v6: Added support assign all if domain id is '*' >> Fixed the allocation of counter id if it not assigned already. >> >> v5: Interface name changed from mbm_assign_control to mbm_control. >> Fixed opcode and flags combination. >> '=_" is valid. >> "-_" amd "+_" is not valid. >> Minor message update. >> Renamed the function with prefix - rdtgroup_. >> Corrected few documentation mistakes. >> Rebase related changes after SNC support. >> >> v4: Added domain specific assignments. Fixed the opcode parsing. >> >> v3: New patch. >> Addresses the feedback to provide the global assignment interface. >> >> https://lore.kernel.org/lkml/c73f444b-83a1-4e9a-95d3-54c5165ee782@xxxxxxxxx/ >> --- >> Documentation/arch/x86/resctrl.rst | 94 +++++++- >> arch/x86/kernel/cpu/resctrl/internal.h | 7 + >> arch/x86/kernel/cpu/resctrl/rdtgroup.c | 315 ++++++++++++++++++++++++- >> 3 files changed, 414 insertions(+), 2 deletions(-) >> >> diff --git a/Documentation/arch/x86/resctrl.rst >> b/Documentation/arch/x86/resctrl.rst >> index 113c22ba6db3..ae3b17b7cefe 100644 >> --- a/Documentation/arch/x86/resctrl.rst >> +++ b/Documentation/arch/x86/resctrl.rst >> @@ -346,7 +346,7 @@ with the following files: >> t MBM total event is enabled. >> l MBM local event is enabled. >> tl Both total and local MBM events are enabled. >> - _ None of the MBM events are enabled. >> + _ None of the MBM events are enabled. Only works with opcode '=' >> for write. >> Examples: >> :: >> @@ -365,6 +365,98 @@ with the following files: >> enabled on domain 0 and 1. >> + Assignment state can be updated by writing to the interface. >> + >> + Format is similar to the list format with addition of opcode for the >> + assignment operation. >> + >> + "<CTRL_MON group>/<MON group>/<domain_id><opcode><flags>" >> + >> + Format for each type of groups: >> + >> + * Default CTRL_MON group: >> + "//<domain_id><opcode><flags>" >> + >> + * Non-default CTRL_MON group: >> + "<CTRL_MON group>//<domain_id><opcode><flags>" >> + >> + * Child MON group of default CTRL_MON group: >> + "/<MON group>/<domain_id><opcode><flags>" >> + >> + * Child MON group of non-default CTRL_MON group: >> + "<CTRL_MON group>/<MON group>/<domain_id><opcode><flags>" >> + >> + Domain_id '*' wil apply the flags on all the domains. >> + >> + Opcode can be one of the following: >> + :: >> + >> + = Update the assignment to match the MBM event. >> + + Assign a MBM event. > > "Assign a new MBM event without impacting existing assignments."? Sure. > >> + - Unassign a MBM event. > > (similar) Sure. > >> + >> + Examples: >> + :: >> + >> + Initial group status: >> + # cat /sys/fs/resctrl/info/L3_MON/mbm_control >> + non_default_ctrl_mon_grp//0=tl;1=tl; >> + non_default_ctrl_mon_grp/child_non_default_mon_grp/0=tl;1=tl; >> + //0=tl;1=tl; >> + /child_default_mon_grp/0=tl;1=tl; >> + >> + To update the default group to assign only total MBM event on >> domain 0: >> + # echo "//0=t" > /sys/fs/resctrl/info/L3_MON/mbm_control >> + >> + Assignment status after the update: >> + # cat /sys/fs/resctrl/info/L3_MON/mbm_control >> + non_default_ctrl_mon_grp//0=tl;1=tl; >> + non_default_ctrl_mon_grp/child_non_default_mon_grp/0=tl;1=tl; >> + //0=t;1=tl; >> + /child_default_mon_grp/0=tl;1=tl; >> + >> + To update the MON group child_default_mon_grp to remove total MBM >> event on domain 1: >> + # echo "/child_default_mon_grp/1-t" > >> /sys/fs/resctrl/info/L3_MON/mbm_control >> + >> + Assignment status after the update: >> + $ cat /sys/fs/resctrl/info/L3_MON/mbm_control >> + non_default_ctrl_mon_grp//0=tl;1=tl; >> + non_default_ctrl_mon_grp/child_non_default_mon_grp/0=tl;1=tl; >> + //0=t;1=tl; >> + /child_default_mon_grp/0=tl;1=l; >> + >> + To update the MON group >> non_default_ctrl_mon_grp/child_non_default_mon_grp to >> + unassign both local and total MBM events on domain 1: >> + # echo "non_default_ctrl_mon_grp/child_non_default_mon_grp/1=_" > >> + /sys/fs/resctrl/info/L3_MON/mbm_control >> + >> + Assignment status after the update: >> + non_default_ctrl_mon_grp//0=tl;1=tl; >> + non_default_ctrl_mon_grp/child_non_default_mon_grp/0=tl;1=_; >> + //0=t;1=tl; >> + /child_default_mon_grp/0=tl;1=l; >> + >> + To update the default group to add a local MBM event domain 0. >> + # echo "//0+l" > /sys/fs/resctrl/info/L3_MON/mbm_control >> + >> + Assignment status after the update: >> + # cat /sys/fs/resctrl/info/L3_MON/mbm_control >> + non_default_ctrl_mon_grp//0=tl;1=tl; >> + non_default_ctrl_mon_grp/child_non_default_mon_grp/0=tl;1=_; >> + //0=tl;1=tl; >> + /child_default_mon_grp/0=tl;1=l; >> + >> + To update the non default CTRL_MON group non_default_ctrl_mon_grp >> to unassign all >> + the MBM events on all the domains. >> + # echo "non_default_ctrl_mon_grp//*=_" > >> /sys/fs/resctrl/info/L3_MON/mbm_control >> + >> + Assignment status after the update: >> + #cat /sys/fs/resctrl/info/L3_MON/mbm_control >> + non_default_ctrl_mon_grp//0=_;1=_; >> + non_default_ctrl_mon_grp/child_non_default_mon_grp/0=tl;1=_; >> + //0=tl;1=tl; >> + /child_default_mon_grp/0=tl;1=l; >> + >> "max_threshold_occupancy": >> Read/write file provides the largest value (in >> bytes) at which a previously used LLC_occupancy >> diff --git a/arch/x86/kernel/cpu/resctrl/internal.h >> b/arch/x86/kernel/cpu/resctrl/internal.h >> index ba3012f8f940..5af225b4a497 100644 >> --- a/arch/x86/kernel/cpu/resctrl/internal.h >> +++ b/arch/x86/kernel/cpu/resctrl/internal.h >> @@ -46,6 +46,13 @@ >> #define MON_CNTR_UNSET U32_MAX >> +/* >> + * Assignment flags for ABMC feature > > (this is resctrl fs code) Ok. > >> + */ >> +#define ASSIGN_NONE 0 >> +#define ASSIGN_TOTAL BIT(QOS_L3_MBM_TOTAL_EVENT_ID) >> +#define ASSIGN_LOCAL BIT(QOS_L3_MBM_LOCAL_EVENT_ID) >> + >> /** >> * cpumask_any_housekeeping() - Choose any CPU in @mask, preferring >> those that >> * aren't marked nohz_full >> diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c >> b/arch/x86/kernel/cpu/resctrl/rdtgroup.c >> index d7aadca5e4ab..8567fb3a6274 100644 >> --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c >> +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c >> @@ -1034,6 +1034,318 @@ static int rdtgroup_mbm_control_show(struct >> kernfs_open_file *of, >> return 0; >> } >> +/* >> + * Update the assign states for the domain. >> + * >> + * If this is a new assignment for the group then allocate a counter >> and update >> + * the assignment else just update the assign state >> + */ >> +static int rdtgroup_assign_update(struct rdtgroup *rdtgrp, enum >> resctrl_event_id evtid, >> + struct rdt_mon_domain *d) >> +{ >> + int ret, index; >> + >> + index = mon_event_config_index_get(evtid); >> + if (index == INVALID_CONFIG_INDEX) >> + return -EINVAL; > > (wrong spacing ... see checkpatch.pl) ok > >> + >> + if (rdtgrp->mon.cntr_id[index] == MON_CNTR_UNSET) { >> + ret = rdtgroup_alloc_cntr(rdtgrp, index); >> + if (ret < 0) >> + goto out_done; >> + } >> + >> + /* Update the state on all domains if d == NULL */ >> + if (d == NULL) { > > if (!d) ... (checkpatch) ok. > >> + ret = rdtgroup_assign_cntr(rdtgrp, evtid); >> + } else { >> + ret = resctrl_arch_assign_cntr(d, evtid, rdtgrp->mon.rmid, >> + rdtgrp->mon.cntr_id[index], >> + rdtgrp->closid, 1); >> + if (!ret) >> + set_bit(rdtgrp->mon.cntr_id[index], d->mbm_cntr_map); >> + } >> + >> +out_done: >> + return ret; >> +} > > Please merge this with almost identical rdtgroup_assign_cntr() Yes. Sure. > >> + >> +/* >> + * Update the unassign state for the domain. >> + * >> + * Free the counter if it is unassigned on all the domains else just >> + * update the unassign state >> + */ >> +static int rdtgroup_unassign_update(struct rdtgroup *rdtgrp, enum >> resctrl_event_id evtid, >> + struct rdt_mon_domain *d) >> +{ >> + struct rdt_resource *r = >> &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; >> + int ret = 0, index; >> + >> + index = mon_event_config_index_get(evtid); >> + if (index == INVALID_CONFIG_INDEX) >> + return -EINVAL; > > (wrong spacing ... see checkpatch.pl) Sure. > >> + >> + if (rdtgrp->mon.cntr_id[index] == MON_CNTR_UNSET) >> + goto out_done; >> + >> + if (d == NULL) { > > if (!d) > >> + ret = rdtgroup_unassign_cntr(rdtgrp, evtid); >> + } else { >> + ret = resctrl_arch_assign_cntr(d, evtid, rdtgrp->mon.rmid, >> + rdtgrp->mon.cntr_id[index], >> + rdtgrp->closid, 0); >> + if (!ret) { >> + clear_bit(rdtgrp->mon.cntr_id[index], d->mbm_cntr_map); >> + rdtgroup_free_cntr(r, rdtgrp, index); >> + } >> + } >> + >> +out_done: >> + return ret; >> +} > > Please merge this with almost identical rdtgroup_unassign_cntr() Sure. > >> + >> +static int rdtgroup_str_to_mon_state(char *flag) >> +{ >> + int i, mon_state = 0; >> + >> + for (i = 0; i < strlen(flag); i++) { >> + switch (*(flag + i)) { >> + case 't': >> + mon_state |= ASSIGN_TOTAL; >> + break; >> + case 'l': >> + mon_state |= ASSIGN_LOCAL; >> + break; >> + case '_': >> + mon_state = ASSIGN_NONE; >> + break; > > It looks like this supports flags like "_lt", treating it as assigning > both local and total. I expect this should remove all flags instead? This is a cobination of flags. "_lt" This will assign both local and total. "lt_" This with remove both the flags. It seems alright to me. Do you want me to change the bahaviour here? > >> + default: >> + break; >> + } >> + } >> + >> + return mon_state; >> +} > > hmmm ... so you removed assigning mon_state to ASSIGN_NONE from default, > but that did not change what this function returns since ASSIGN_NONE is 0 > and mon_state is initialized to 0. Unknown flags should cause error so > that it is possible to add flags in the future. Above prevents us from > ever adding new flags. May be I am missing something here. How about this? enum { ASSIGN_NONE = 0, ASSIGN_TOTAL, ASSIGN_LOCAL, ASSIGN_INVALID, }; static int rdtgroup_str_to_mon_state(char *flag) { int i, mon_state = ASSIGN_NONE; for (i = 0; i < strlen(flag); i++) { switch (*(flag + i)) { case 't': mon_state |= ASSIGN_TOTAL; break; case 'l': mon_state |= ASSIGN_LOCAL; break; case '_': mon_state = ASSIGN_NONE; break; default: mon_state = ASSIGN_INVALID; goto out_done; } } :out_done: return mon_state; } Then handle the ASSIGN_INVALID from the caller. Is that what you think? > >> + >> +static struct rdtgroup *rdtgroup_find_grp(enum rdt_group_type rtype, >> char *p_grp, char *c_grp) > > rdtgroup_find_grp() -> rdtgroup_find_grp_by_name()? > >> +{ >> + struct rdtgroup *rdtg, *crg; >> + >> + if (rtype == RDTCTRL_GROUP && *p_grp == '\0') { >> + return &rdtgroup_default; >> + } else if (rtype == RDTCTRL_GROUP) { >> + list_for_each_entry(rdtg, &rdt_all_groups, rdtgroup_list) >> + if (!strcmp(p_grp, rdtg->kn->name)) >> + return rdtg; >> + } else if (rtype == RDTMON_GROUP) { >> + list_for_each_entry(rdtg, &rdt_all_groups, rdtgroup_list) { >> + if (!strcmp(p_grp, rdtg->kn->name)) { >> + list_for_each_entry(crg, &rdtg->mon.crdtgrp_list, >> + mon.crdtgrp_list) { >> + if (!strcmp(c_grp, crg->kn->name)) >> + return crg; >> + } >> + } >> + } >> + } >> + >> + return NULL; >> +} >> + >> +static int rdtgroup_process_flags(struct rdt_resource *r, >> + enum rdt_group_type rtype, >> + char *p_grp, char *c_grp, char *tok) >> +{ >> + int op, mon_state, assign_state, unassign_state; >> + char *dom_str, *id_str, *op_str; >> + struct rdt_mon_domain *d; >> + struct rdtgroup *rdtgrp; >> + unsigned long dom_id; >> + int ret, found = 0; >> + >> + rdtgrp = rdtgroup_find_grp(rtype, p_grp, c_grp); >> + >> + if (!rdtgrp) { >> + rdt_last_cmd_puts("Not a valid resctrl group\n"); >> + return -EINVAL; >> + } >> + >> +next: >> + if (!tok || tok[0] == '\0') >> + return 0; >> + >> + /* Start processing the strings for each domain */ >> + dom_str = strim(strsep(&tok, ";")); >> + >> + op_str = strpbrk(dom_str, "=+-"); >> + >> + if (op_str) { >> + op = *op_str; >> + } else { >> + rdt_last_cmd_puts("Missing operation =, +, -, _ character\n"); >> + return -EINVAL; >> + } >> + >> + id_str = strsep(&dom_str, "=+-"); >> + >> + /* Check for domain id '*' which means all domains */ >> + if (id_str && *id_str == '*') { >> + d = NULL; >> + goto check_state; >> + } else if (!id_str || kstrtoul(id_str, 10, &dom_id)) { >> + rdt_last_cmd_puts("Missing domain id\n"); >> + return -EINVAL; >> + } >> + >> + /* Verify if the dom_id is valid */ >> + list_for_each_entry(d, &r->mon_domains, hdr.list) { >> + if (d->hdr.id == dom_id) { >> + found = 1; >> + break; >> + } >> + } >> + >> + if (!found) { >> + rdt_last_cmd_printf("Invalid domain id %ld\n", dom_id); >> + return -EINVAL; >> + } >> + >> +check_state: >> + mon_state = rdtgroup_str_to_mon_state(dom_str); > > Function should return error and exit here. No. This is case to skip checking for domain when '*' is passed to apply assignment to all the domains. > >> + >> + assign_state = 0; >> + unassign_state = 0; >> + >> + switch (op) { >> + case '+': >> + if (mon_state == ASSIGN_NONE) { >> + rdt_last_cmd_puts("Invalid assign opcode\n"); >> + goto out_fail; >> + } >> + assign_state = mon_state; >> + break; >> + case '-': >> + if (mon_state == ASSIGN_NONE) { >> + rdt_last_cmd_puts("Invalid assign opcode\n"); >> + goto out_fail; >> + } >> + unassign_state = mon_state; >> + break; >> + case '=': >> + assign_state = mon_state; >> + unassign_state = (ASSIGN_TOTAL | ASSIGN_LOCAL) & ~assign_state; >> + break; >> + default: >> + break; >> + } >> + >> + if (assign_state & ASSIGN_TOTAL) { >> + ret = rdtgroup_assign_update(rdtgrp, QOS_L3_MBM_TOTAL_EVENT_ID, >> d); >> + if (ret) >> + goto out_fail; >> + } > > Should unassign occur before assign so that unassign can make counters > available for > assign that follows? Yes. It works. Just tested it. > >> + >> + if (assign_state & ASSIGN_LOCAL) { >> + ret = rdtgroup_assign_update(rdtgrp, QOS_L3_MBM_LOCAL_EVENT_ID, >> d); >> + if (ret) >> + goto out_fail; >> + } >> + >> + if (unassign_state & ASSIGN_TOTAL) { >> + ret = rdtgroup_unassign_update(rdtgrp, >> QOS_L3_MBM_TOTAL_EVENT_ID, d); >> + if (ret) >> + goto out_fail; >> + } >> + >> + if (unassign_state & ASSIGN_LOCAL) { >> + ret = rdtgroup_unassign_update(rdtgrp, >> QOS_L3_MBM_LOCAL_EVENT_ID, d); >> + if (ret) >> + goto out_fail; >> + } >> + >> + goto next; >> + >> +out_fail: >> + >> + return -EINVAL; >> +} >> + >> +static ssize_t rdtgroup_mbm_control_write(struct kernfs_open_file *of, >> + char *buf, size_t nbytes, >> + loff_t off) >> +{ >> + struct rdt_resource *r = of->kn->parent->priv; >> + char *token, *cmon_grp, *mon_grp; >> + int ret; >> + >> + if (!resctrl_arch_get_abmc_enabled()) >> + return -EINVAL; > > This needs to be protected by mutex. Sure. > >> + >> + /* Valid input requires a trailing newline */ >> + if (nbytes == 0 || buf[nbytes - 1] != '\n') >> + return -EINVAL; >> + >> + buf[nbytes - 1] = '\0'; >> + >> + cpus_read_lock(); >> + mutex_lock(&rdtgroup_mutex); >> + rdt_last_cmd_clear(); >> + >> + while ((token = strsep(&buf, "\n")) != NULL) { >> + if (strstr(token, "//")) { >> + /* >> + * The CTRL_MON group processing: >> + * default CTRL_MON group: "//<flags>" >> + * non-default CTRL_MON group: "<CTRL_MON group>//flags" >> + * The CTRL_MON group will be empty string if it is a >> + * default group. >> + */ >> + cmon_grp = strsep(&token, "//"); >> + >> + /* >> + * strsep returns empty string for contiguous delimiters. >> + * Make sure check for two consecutive delimiters and >> + * advance the token. >> + */ >> + mon_grp = strsep(&token, "//"); >> + if (*mon_grp != '\0') { >> + rdt_last_cmd_printf("Invalid CTRL_MON group format >> %s\n", token); >> + ret = -EINVAL; >> + break; >> + } >> + >> + ret = rdtgroup_process_flags(r, RDTCTRL_GROUP, cmon_grp, >> mon_grp, token); >> + if (ret) >> + break; >> + } else if (strstr(token, "/")) { >> + /* >> + * MON group processing: >> + * MON_GROUP inside default CTRL_MON group: "/<MON >> group>/<flags>" >> + * MON_GROUP within CTRL_MON group: "<CTRL_MON group>/<MON >> group>/<flags>" >> + */ >> + cmon_grp = strsep(&token, "/"); > > Isn't strsep(&token, "//") the same as strsep(&token, "/")? It looks like > these two big branches > can be merged. Sure. Will check this. > >> + >> + /* Extract the MON_GROUP. It cannot be empty string */ >> + mon_grp = strsep(&token, "/"); >> + if (*mon_grp == '\0') { >> + rdt_last_cmd_printf("Invalid MON_GROUP format %s\n", >> token); >> + ret = -EINVAL; >> + break; >> + } >> + >> + ret = rdtgroup_process_flags(r, RDTMON_GROUP, cmon_grp, >> mon_grp, token); >> + if (ret) >> + break; >> + } >> + } >> + >> + mutex_unlock(&rdtgroup_mutex); >> + cpus_read_unlock(); >> + >> + return ret ?: nbytes; >> +} >> + >> #ifdef CONFIG_PROC_CPU_RESCTRL >> /* >> @@ -2277,9 +2589,10 @@ static struct rftype res_common_files[] = { >> }, >> { >> .name = "mbm_control", >> - .mode = 0444, >> + .mode = 0644, >> .kf_ops = &rdtgroup_kf_single_ops, >> .seq_show = rdtgroup_mbm_control_show, >> + .write = rdtgroup_mbm_control_write, >> }, >> { >> .name = "cpus_list", > > Reinette > -- Thanks Babu Moger
