From 1b908debf53ff3cf0e43e0fa51e7319a23518e6c Mon Sep 17 00:00:00 2001 From: Tony Luck Date: Wed, 1 Nov 2023 14:26:15 -0700 Subject: x86/resctrl: Fix unused variable warning in cache_alloc_hsw_probe() In a "W=1" build gcc throws a warning: arch/x86/kernel/cpu/resctrl/core.c: In function ‘cache_alloc_hsw_probe’: arch/x86/kernel/cpu/resctrl/core.c:139:16: warning: variable ‘h’ set but not used Switch from wrmsr_safe() to wrmsrl_safe(), and from rdmsr() to rdmsrl() using a single u64 argument for the MSR value instead of the pair of u32 for the high and low halves. Signed-off-by: Tony Luck Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Babu Moger Acked-by: Reinette Chatre Link: https://lore.kernel.org/r/ZULCd/TGJL9Dmncf@agluck-desk3 --- arch/x86/kernel/cpu/resctrl/core.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index 19e0681f0435..d29ebe345de6 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -136,15 +136,15 @@ static inline void cache_alloc_hsw_probe(void) { struct rdt_hw_resource *hw_res = &rdt_resources_all[RDT_RESOURCE_L3]; struct rdt_resource *r = &hw_res->r_resctrl; - u32 l, h, max_cbm = BIT_MASK(20) - 1; + u64 max_cbm = BIT_ULL_MASK(20) - 1, l3_cbm_0; - if (wrmsr_safe(MSR_IA32_L3_CBM_BASE, max_cbm, 0)) + if (wrmsrl_safe(MSR_IA32_L3_CBM_BASE, max_cbm)) return; - rdmsr(MSR_IA32_L3_CBM_BASE, l, h); + rdmsrl(MSR_IA32_L3_CBM_BASE, l3_cbm_0); /* If all the bits were set in MSR, return success */ - if (l != max_cbm) + if (l3_cbm_0 != max_cbm) return; hw_res->num_closid = 4; -- cgit v1.2.3 From 0976783bb123f30981bc1e7a14d9626a6f63aeac Mon Sep 17 00:00:00 2001 From: Babu Moger Date: Mon, 15 Jan 2024 16:52:27 -0600 Subject: x86/resctrl: Remove hard-coded memory bandwidth limit The QOS Memory Bandwidth Enforcement Limit is reported by CPUID_Fn80000020_EAX_x01 and CPUID_Fn80000020_EAX_x02: Bits Description 31:0 BW_LEN: Size of the QOS Memory Bandwidth Enforcement Limit. Newer processors can support higher bandwidth limit than the current hard-coded value. Remove latter and detect using CPUID instead. Also, update the register variables eax and edx to match the AMD CPUID definition. The CPUID details are documented in the Processor Programming Reference (PPR) Vol 1.1 for AMD Family 19h Model 11h B1 - 55901 Rev 0.25 in the Link tag below. Fixes: 4d05bf71f157 ("x86/resctrl: Introduce AMD QOS feature") Signed-off-by: Babu Moger Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Reinette Chatre Link: https://bugzilla.kernel.org/show_bug.cgi?id=206537 Link: https://lore.kernel.org/r/c26a8ca79d399ed076cf8bf2e9fbc58048808289.1705359148.git.babu.moger@amd.com --- arch/x86/kernel/cpu/resctrl/core.c | 10 ++++------ arch/x86/kernel/cpu/resctrl/internal.h | 1 - 2 files changed, 4 insertions(+), 7 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index d29ebe345de6..aa9810a64258 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -231,9 +231,7 @@ static bool __get_mem_config_intel(struct rdt_resource *r) static bool __rdt_get_mem_config_amd(struct rdt_resource *r) { struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); - union cpuid_0x10_3_eax eax; - union cpuid_0x10_x_edx edx; - u32 ebx, ecx, subleaf; + u32 eax, ebx, ecx, edx, subleaf; /* * Query CPUID_Fn80000020_EDX_x01 for MBA and @@ -241,9 +239,9 @@ static bool __rdt_get_mem_config_amd(struct rdt_resource *r) */ subleaf = (r->rid == RDT_RESOURCE_SMBA) ? 2 : 1; - cpuid_count(0x80000020, subleaf, &eax.full, &ebx, &ecx, &edx.full); - hw_res->num_closid = edx.split.cos_max + 1; - r->default_ctrl = MAX_MBA_BW_AMD; + cpuid_count(0x80000020, subleaf, &eax, &ebx, &ecx, &edx); + hw_res->num_closid = edx + 1; + r->default_ctrl = 1 << eax; /* AMD does not use delay */ r->membw.delay_linear = false; diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index a4f1aa15f0a2..d2979748fae4 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -18,7 +18,6 @@ #define MBM_OVERFLOW_INTERVAL 1000 #define MAX_MBA_BW 100u #define MBA_IS_LINEAR 0x4 -#define MAX_MBA_BW_AMD 0x800 #define MBM_CNTR_WIDTH_OFFSET_AMD 20 #define RMID_VAL_ERROR BIT_ULL(63) -- cgit v1.2.3 From 54e35eb8611cce5550d3d7689679b1a91c864f28 Mon Sep 17 00:00:00 2001 From: Babu Moger Date: Mon, 15 Jan 2024 16:52:28 -0600 Subject: x86/resctrl: Read supported bandwidth sources from CPUID If the BMEC (Bandwidth Monitoring Event Configuration) feature is supported, the bandwidth events can be configured. The maximum supported bandwidth bitmask can be read from CPUID: CPUID_Fn80000020_ECX_x03 [Platform QoS Monitoring Bandwidth Event Configuration] Bits Description 31:7 Reserved 6:0 Identifies the bandwidth sources that can be tracked. While at it, move the mask checking to mon_config_write() before iterating over all the domains. Also, print the valid bitmask when the user tries to configure invalid event configuration value. The CPUID details are documented in the Processor Programming Reference (PPR) Vol 1.1 for AMD Family 19h Model 11h B1 - 55901 Rev 0.25 in the Link tag. Fixes: dc2a3e857981 ("x86/resctrl: Add interface to read mbm_total_bytes_config") Signed-off-by: Babu Moger Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Reinette Chatre Link: https://bugzilla.kernel.org/show_bug.cgi?id=206537 Link: https://lore.kernel.org/r/669896fa512c7451319fa5ca2fdb6f7e015b5635.1705359148.git.babu.moger@amd.com --- arch/x86/kernel/cpu/resctrl/internal.h | 3 +++ arch/x86/kernel/cpu/resctrl/monitor.c | 6 ++++++ arch/x86/kernel/cpu/resctrl/rdtgroup.c | 14 ++++++++------ 3 files changed, 17 insertions(+), 6 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index d2979748fae4..e3dc35a00a19 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -394,6 +394,8 @@ struct rdt_parse_data { * @msr_update: Function pointer to update QOS MSRs * @mon_scale: cqm counter * mon_scale = occupancy in bytes * @mbm_width: Monitor width, to detect and correct for overflow. + * @mbm_cfg_mask: Bandwidth sources that can be tracked when Bandwidth + * Monitoring Event Configuration (BMEC) is supported. * @cdp_enabled: CDP state of this resource * * Members of this structure are either private to the architecture @@ -408,6 +410,7 @@ struct rdt_hw_resource { struct rdt_resource *r); unsigned int mon_scale; unsigned int mbm_width; + unsigned int mbm_cfg_mask; bool cdp_enabled; }; diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index f136ac046851..acca577e2b06 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -813,6 +813,12 @@ int __init rdt_get_mon_l3_config(struct rdt_resource *r) return ret; if (rdt_cpu_has(X86_FEATURE_BMEC)) { + u32 eax, ebx, ecx, edx; + + /* Detect list of bandwidth sources that can be tracked */ + cpuid_count(0x80000020, 3, &eax, &ebx, &ecx, &edx); + hw_res->mbm_cfg_mask = ecx & MAX_EVT_CONFIG_BITS; + if (rdt_cpu_has(X86_FEATURE_CQM_MBM_TOTAL)) { mbm_total_event.configurable = true; mbm_config_rftype_init("mbm_total_bytes_config"); diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 69a1de92384a..2b69e560b05f 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -1620,12 +1620,6 @@ static int mbm_config_write_domain(struct rdt_resource *r, struct mon_config_info mon_info = {0}; int ret = 0; - /* mon_config cannot be more than the supported set of events */ - if (val > MAX_EVT_CONFIG_BITS) { - rdt_last_cmd_puts("Invalid event configuration\n"); - return -EINVAL; - } - /* * Read the current config value first. If both are the same then * no need to write it again. @@ -1663,6 +1657,7 @@ out: static int mon_config_write(struct rdt_resource *r, char *tok, u32 evtid) { + struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); char *dom_str = NULL, *id_str; unsigned long dom_id, val; struct rdt_domain *d; @@ -1686,6 +1681,13 @@ next: return -EINVAL; } + /* Value from user cannot be more than the supported set of events */ + if ((val & hw_res->mbm_cfg_mask) != val) { + rdt_last_cmd_printf("Invalid event configuration: max valid mask is 0x%02x\n", + hw_res->mbm_cfg_mask); + return -EINVAL; + } + list_for_each_entry(d, &r->domains, list) { if (d->id == dom_id) { ret = mbm_config_write_domain(r, d, evtid, val); -- cgit v1.2.3 From c2427e70c1630d98966375fffc2b713ab9768a94 Mon Sep 17 00:00:00 2001 From: Tony Luck Date: Mon, 22 Jan 2024 10:08:07 -0800 Subject: x86/resctrl: Implement new mba_MBps throttling heuristic The mba_MBps feedback loop increases throttling when a group is using more bandwidth than the target set by the user in the schemata file, and decreases throttling when below target. To avoid possibly stepping throttling up and down on every poll a flag "delta_comp" is set whenever throttling is changed to indicate that the actual change in bandwidth should be recorded on the next poll in "delta_bw". Throttling is only reduced if the current bandwidth plus delta_bw is below the user target. This algorithm works well if the workload has steady bandwidth needs. But it can go badly wrong if the workload moves to a different phase just as the throttling level changed. E.g. if the workload becomes essentially idle right as throttling level is increased, the value calculated for delta_bw will be more or less the old bandwidth level. If the workload then resumes, Linux may never reduce throttling because current bandwidth plus delta_bw is above the target set by the user. Implement a simpler heuristic by assuming that in the worst case the currently measured bandwidth is being controlled by the current level of throttling. Compute how much it may increase if throttling is relaxed to the next higher level. If that is still below the user target, then it is ok to reduce the amount of throttling. Fixes: ba0f26d8529c ("x86/intel_rdt/mba_sc: Prepare for feedback loop") Reported-by: Xiaochen Shen Signed-off-by: Tony Luck Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Reinette Chatre Tested-by: Xiaochen Shen Link: https://lore.kernel.org/r/20240122180807.70518-1-tony.luck@intel.com --- arch/x86/kernel/cpu/resctrl/internal.h | 4 ---- arch/x86/kernel/cpu/resctrl/monitor.c | 42 ++++++++-------------------------- 2 files changed, 10 insertions(+), 36 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index e3dc35a00a19..52e7e7deee10 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -295,14 +295,10 @@ struct rftype { * struct mbm_state - status for each MBM counter in each domain * @prev_bw_bytes: Previous bytes value read for bandwidth calculation * @prev_bw: The most recent bandwidth in MBps - * @delta_bw: Difference between the current and previous bandwidth - * @delta_comp: Indicates whether to compute the delta_bw */ struct mbm_state { u64 prev_bw_bytes; u32 prev_bw; - u32 delta_bw; - bool delta_comp; }; /** diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index acca577e2b06..3a6c069614eb 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -440,9 +440,6 @@ static void mbm_bw_count(u32 rmid, struct rmid_read *rr) cur_bw = bytes / SZ_1M; - if (m->delta_comp) - m->delta_bw = abs(cur_bw - m->prev_bw); - m->delta_comp = false; m->prev_bw = cur_bw; } @@ -520,11 +517,11 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm) { u32 closid, rmid, cur_msr_val, new_msr_val; struct mbm_state *pmbm_data, *cmbm_data; - u32 cur_bw, delta_bw, user_bw; struct rdt_resource *r_mba; struct rdt_domain *dom_mba; struct list_head *head; struct rdtgroup *entry; + u32 cur_bw, user_bw; if (!is_mbm_local_enabled()) return; @@ -543,7 +540,6 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm) cur_bw = pmbm_data->prev_bw; user_bw = dom_mba->mbps_val[closid]; - delta_bw = pmbm_data->delta_bw; /* MBA resource doesn't support CDP */ cur_msr_val = resctrl_arch_get_config(r_mba, dom_mba, closid, CDP_NONE); @@ -555,49 +551,31 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm) list_for_each_entry(entry, head, mon.crdtgrp_list) { cmbm_data = &dom_mbm->mbm_local[entry->mon.rmid]; cur_bw += cmbm_data->prev_bw; - delta_bw += cmbm_data->delta_bw; } /* * Scale up/down the bandwidth linearly for the ctrl group. The * bandwidth step is the bandwidth granularity specified by the * hardware. - * - * The delta_bw is used when increasing the bandwidth so that we - * dont alternately increase and decrease the control values - * continuously. - * - * For ex: consider cur_bw = 90MBps, user_bw = 100MBps and if - * bandwidth step is 20MBps(> user_bw - cur_bw), we would keep - * switching between 90 and 110 continuously if we only check - * cur_bw < user_bw. + * Always increase throttling if current bandwidth is above the + * target set by user. + * But avoid thrashing up and down on every poll by checking + * whether a decrease in throttling is likely to push the group + * back over target. E.g. if currently throttling to 30% of bandwidth + * on a system with 10% granularity steps, check whether moving to + * 40% would go past the limit by multiplying current bandwidth by + * "(30 + 10) / 30". */ if (cur_msr_val > r_mba->membw.min_bw && user_bw < cur_bw) { new_msr_val = cur_msr_val - r_mba->membw.bw_gran; } else if (cur_msr_val < MAX_MBA_BW && - (user_bw > (cur_bw + delta_bw))) { + (user_bw > (cur_bw * (cur_msr_val + r_mba->membw.min_bw) / cur_msr_val))) { new_msr_val = cur_msr_val + r_mba->membw.bw_gran; } else { return; } resctrl_arch_update_one(r_mba, dom_mba, closid, CDP_NONE, new_msr_val); - - /* - * Delta values are updated dynamically package wise for each - * rdtgrp every time the throttle MSR changes value. - * - * This is because (1)the increase in bandwidth is not perfectly - * linear and only "approximately" linear even when the hardware - * says it is linear.(2)Also since MBA is a core specific - * mechanism, the delta values vary based on number of cores used - * by the rdtgrp. - */ - pmbm_data->delta_comp = true; - list_for_each_entry(entry, head, mon.crdtgrp_list) { - cmbm_data = &dom_mbm->mbm_local[entry->mon.rmid]; - cmbm_data->delta_comp = true; - } } static void mbm_update(struct rdt_resource *r, struct rdt_domain *d, int rmid) -- cgit v1.2.3 From fc747eebef734563cf68a512f57937c8f231834a Mon Sep 17 00:00:00 2001 From: Babu Moger Date: Wed, 24 Jan 2024 11:52:56 -0600 Subject: x86/resctrl: Remove redundant variable in mbm_config_write_domain() The kernel test robot reported the following warning after commit 54e35eb8611c ("x86/resctrl: Read supported bandwidth sources from CPUID"). even though the issue is present even in the original commit 92bd5a139033 ("x86/resctrl: Add interface to write mbm_total_bytes_config") which added this function. The reported warning is: $ make C=1 CHECK=scripts/coccicheck arch/x86/kernel/cpu/resctrl/rdtgroup.o ... arch/x86/kernel/cpu/resctrl/rdtgroup.c:1621:5-8: Unneeded variable: "ret". Return "0" on line 1655 Remove the local variable 'ret'. [ bp: Massage commit message, make mbm_config_write_domain() void. ] Fixes: 92bd5a139033 ("x86/resctrl: Add interface to write mbm_total_bytes_config") Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202401241810.jbd8Ipa1-lkp@intel.com/ Signed-off-by: Babu Moger Signed-off-by: Borislav Petkov (AMD) Acked-by: Reinette Chatre Link: https://lore.kernel.org/r/202401241810.jbd8Ipa1-lkp@intel.com --- arch/x86/kernel/cpu/resctrl/rdtgroup.c | 15 ++++----------- 1 file changed, 4 insertions(+), 11 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 2b69e560b05f..aa24343f1d23 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -1614,11 +1614,10 @@ static void mon_event_config_write(void *info) wrmsr(MSR_IA32_EVT_CFG_BASE + index, mon_info->mon_config, 0); } -static int mbm_config_write_domain(struct rdt_resource *r, - struct rdt_domain *d, u32 evtid, u32 val) +static void mbm_config_write_domain(struct rdt_resource *r, + struct rdt_domain *d, u32 evtid, u32 val) { struct mon_config_info mon_info = {0}; - int ret = 0; /* * Read the current config value first. If both are the same then @@ -1627,7 +1626,7 @@ static int mbm_config_write_domain(struct rdt_resource *r, mon_info.evtid = evtid; mondata_config_read(d, &mon_info); if (mon_info.mon_config == val) - goto out; + return; mon_info.mon_config = val; @@ -1650,9 +1649,6 @@ static int mbm_config_write_domain(struct rdt_resource *r, * mbm_local and mbm_total counts for all the RMIDs. */ resctrl_arch_reset_rmid_all(r, d); - -out: - return ret; } static int mon_config_write(struct rdt_resource *r, char *tok, u32 evtid) @@ -1661,7 +1657,6 @@ static int mon_config_write(struct rdt_resource *r, char *tok, u32 evtid) char *dom_str = NULL, *id_str; unsigned long dom_id, val; struct rdt_domain *d; - int ret = 0; next: if (!tok || tok[0] == '\0') @@ -1690,9 +1685,7 @@ next: list_for_each_entry(d, &r->domains, list) { if (d->id == dom_id) { - ret = mbm_config_write_domain(r, d, evtid, val); - if (ret) - return -EINVAL; + mbm_config_write_domain(r, d, evtid, val); goto next; } } -- cgit v1.2.3 From 3f7b07380d58cfbb6a2d3aa672dcc76c0f4b0745 Mon Sep 17 00:00:00 2001 From: James Morse Date: Tue, 13 Feb 2024 18:44:16 +0000 Subject: x86/resctrl: Free rmid_ptrs from resctrl_exit() rmid_ptrs[] is allocated from dom_data_init() but never free()d. While the exit text ends up in the linker script's DISCARD section, the direction of travel is for resctrl to be/have loadable modules. Add resctrl_put_mon_l3_config() to cleanup any memory allocated by rdt_get_mon_l3_config(). There is no reason to backport this to a stable kernel. Signed-off-by: James Morse Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Babu Moger Reviewed-by: Reinette Chatre Tested-by: Babu Moger Tested-by: Carl Worth # arm64 Link: https://lore.kernel.org/r/20240213184438.16675-3-james.morse@arm.com Signed-off-by: Borislav Petkov (AMD) --- arch/x86/kernel/cpu/resctrl/core.c | 6 ++++++ arch/x86/kernel/cpu/resctrl/internal.h | 1 + arch/x86/kernel/cpu/resctrl/monitor.c | 15 +++++++++++++++ 3 files changed, 22 insertions(+) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index aa9810a64258..9641c42d0f85 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -990,8 +990,14 @@ late_initcall(resctrl_late_init); static void __exit resctrl_exit(void) { + struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; + cpuhp_remove_state(rdt_online); + rdtgroup_exit(); + + if (r->mon_capable) + rdt_put_mon_l3_config(); } __exitcall(resctrl_exit); diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index 52e7e7deee10..61c763604fc9 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -544,6 +544,7 @@ void closid_free(int closid); int alloc_rmid(void); void free_rmid(u32 rmid); int rdt_get_mon_l3_config(struct rdt_resource *r); +void __exit rdt_put_mon_l3_config(void); bool __init rdt_cpu_has(int flag); void mon_event_count(void *info); int rdtgroup_mondata_show(struct seq_file *m, void *arg); diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index 3a6c069614eb..3a73db0579d8 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -719,6 +719,16 @@ static int dom_data_init(struct rdt_resource *r) return 0; } +static void __exit dom_data_exit(void) +{ + mutex_lock(&rdtgroup_mutex); + + kfree(rmid_ptrs); + rmid_ptrs = NULL; + + mutex_unlock(&rdtgroup_mutex); +} + static struct mon_evt llc_occupancy_event = { .name = "llc_occupancy", .evtid = QOS_L3_OCCUP_EVENT_ID, @@ -814,6 +824,11 @@ int __init rdt_get_mon_l3_config(struct rdt_resource *r) return 0; } +void __exit rdt_put_mon_l3_config(void) +{ + dom_data_exit(); +} + void __init intel_rdt_mbm_apply_quirk(void) { int cf_index; -- cgit v1.2.3 From b1de313979af99dc0f999656fc99bbcb52559a38 Mon Sep 17 00:00:00 2001 From: James Morse Date: Tue, 13 Feb 2024 18:44:17 +0000 Subject: x86/resctrl: Create helper for RMID allocation and mondata dir creation When monitoring is supported, each monitor and control group is allocated an RMID. For control groups, rdtgroup_mkdir_ctrl_mon() later goes on to allocate the CLOSID. MPAM's equivalent of RMID are not an independent number, so can't be allocated until the CLOSID is known. An RMID allocation for one CLOSID may fail, whereas another may succeed depending on how many monitor groups a control group has. The RMID allocation needs to move to be after the CLOSID has been allocated. Move the RMID allocation and mondata dir creation to a helper. Signed-off-by: James Morse Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Shaopeng Tan Reviewed-by: Ilpo Järvinen Reviewed-by: Reinette Chatre Reviewed-by: Babu Moger Tested-by: Peter Newman Tested-by: Shaopeng Tan Tested-by: Babu Moger Tested-by: Carl Worth # arm64 Link: https://lore.kernel.org/r/20240213184438.16675-4-james.morse@arm.com Signed-off-by: Borislav Petkov (AMD) --- arch/x86/kernel/cpu/resctrl/rdtgroup.c | 42 ++++++++++++++++++++++------------ 1 file changed, 27 insertions(+), 15 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index aa24343f1d23..4ea5a871be49 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -3288,6 +3288,30 @@ out: return ret; } +static int mkdir_rdt_prepare_rmid_alloc(struct rdtgroup *rdtgrp) +{ + int ret; + + if (!rdt_mon_capable) + return 0; + + ret = alloc_rmid(); + if (ret < 0) { + rdt_last_cmd_puts("Out of RMIDs\n"); + return ret; + } + rdtgrp->mon.rmid = ret; + + ret = mkdir_mondata_all(rdtgrp->kn, rdtgrp, &rdtgrp->mon.mon_data_kn); + if (ret) { + rdt_last_cmd_puts("kernfs subdir error\n"); + free_rmid(rdtgrp->mon.rmid); + return ret; + } + + return 0; +} + static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, const char *name, umode_t mode, enum rdt_group_type rtype, struct rdtgroup **r) @@ -3360,20 +3384,10 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, goto out_destroy; } - if (rdt_mon_capable) { - ret = alloc_rmid(); - if (ret < 0) { - rdt_last_cmd_puts("Out of RMIDs\n"); - goto out_destroy; - } - rdtgrp->mon.rmid = ret; + ret = mkdir_rdt_prepare_rmid_alloc(rdtgrp); + if (ret) + goto out_destroy; - ret = mkdir_mondata_all(kn, rdtgrp, &rdtgrp->mon.mon_data_kn); - if (ret) { - rdt_last_cmd_puts("kernfs subdir error\n"); - goto out_idfree; - } - } kernfs_activate(kn); /* @@ -3381,8 +3395,6 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, */ return 0; -out_idfree: - free_rmid(rdtgrp->mon.rmid); out_destroy: kernfs_put(rdtgrp->kn); kernfs_remove(rdtgrp->kn); -- cgit v1.2.3 From 311639e9512bb3af2abae32be9322b8a9b30eaa1 Mon Sep 17 00:00:00 2001 From: James Morse Date: Tue, 13 Feb 2024 18:44:18 +0000 Subject: x86/resctrl: Move RMID allocation out of mkdir_rdt_prepare() RMIDs are allocated for each monitor or control group directory, because each of these needs its own RMID. For control groups, rdtgroup_mkdir_ctrl_mon() later goes on to allocate the CLOSID. MPAM's equivalent of RMID is not an independent number, so can't be allocated until the CLOSID is known. An RMID allocation for one CLOSID may fail, whereas another may succeed depending on how many monitor groups a control group has. The RMID allocation needs to move to be after the CLOSID has been allocated. Move the RMID allocation out of mkdir_rdt_prepare() to occur in its caller, after the mkdir_rdt_prepare() call. This allows the RMID allocator to know the CLOSID. Signed-off-by: James Morse Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Shaopeng Tan Reviewed-by: Reinette Chatre Reviewed-by: Babu Moger Tested-by: Shaopeng Tan Tested-by: Peter Newman Tested-by: Babu Moger Tested-by: Carl Worth # arm64 Link: https://lore.kernel.org/r/20240213184438.16675-5-james.morse@arm.com Signed-off-by: Borislav Petkov (AMD) --- arch/x86/kernel/cpu/resctrl/rdtgroup.c | 35 +++++++++++++++++++++++++--------- 1 file changed, 26 insertions(+), 9 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 4ea5a871be49..f455a10b74ab 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -3312,6 +3312,12 @@ static int mkdir_rdt_prepare_rmid_alloc(struct rdtgroup *rdtgrp) return 0; } +static void mkdir_rdt_prepare_rmid_free(struct rdtgroup *rgrp) +{ + if (rdt_mon_capable) + free_rmid(rgrp->mon.rmid); +} + static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, const char *name, umode_t mode, enum rdt_group_type rtype, struct rdtgroup **r) @@ -3384,12 +3390,6 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, goto out_destroy; } - ret = mkdir_rdt_prepare_rmid_alloc(rdtgrp); - if (ret) - goto out_destroy; - - kernfs_activate(kn); - /* * The caller unlocks the parent_kn upon success. */ @@ -3408,7 +3408,6 @@ out_unlock: static void mkdir_rdt_prepare_clean(struct rdtgroup *rgrp) { kernfs_remove(rgrp->kn); - free_rmid(rgrp->mon.rmid); rdtgroup_remove(rgrp); } @@ -3430,12 +3429,21 @@ static int rdtgroup_mkdir_mon(struct kernfs_node *parent_kn, prgrp = rdtgrp->mon.parent; rdtgrp->closid = prgrp->closid; + ret = mkdir_rdt_prepare_rmid_alloc(rdtgrp); + if (ret) { + mkdir_rdt_prepare_clean(rdtgrp); + goto out_unlock; + } + + kernfs_activate(rdtgrp->kn); + /* * Add the rdtgrp to the list of rdtgrps the parent * ctrl_mon group has to track. */ list_add_tail(&rdtgrp->mon.crdtgrp_list, &prgrp->mon.crdtgrp_list); +out_unlock: rdtgroup_kn_unlock(parent_kn); return ret; } @@ -3466,9 +3474,16 @@ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn, ret = 0; rdtgrp->closid = closid; + + ret = mkdir_rdt_prepare_rmid_alloc(rdtgrp); + if (ret) + goto out_closid_free; + + kernfs_activate(rdtgrp->kn); + ret = rdtgroup_init_alloc(rdtgrp); if (ret < 0) - goto out_id_free; + goto out_rmid_free; list_add(&rdtgrp->rdtgroup_list, &rdt_all_groups); @@ -3488,7 +3503,9 @@ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn, out_del_list: list_del(&rdtgrp->rdtgroup_list); -out_id_free: +out_rmid_free: + mkdir_rdt_prepare_rmid_free(rdtgrp); +out_closid_free: closid_free(closid); out_common_fail: mkdir_rdt_prepare_clean(rdtgrp); -- cgit v1.2.3 From 40fc735b78f0c81cea7d1c511cfd83892cb4d679 Mon Sep 17 00:00:00 2001 From: James Morse Date: Tue, 13 Feb 2024 18:44:19 +0000 Subject: x86/resctrl: Track the closid with the rmid x86's RMID are independent of the CLOSID. An RMID can be allocated, used and freed without considering the CLOSID. MPAM's equivalent feature is PMG, which is not an independent number, it extends the CLOSID/PARTID space. For MPAM, only PMG-bits worth of 'RMID' can be allocated for a single CLOSID. i.e. if there is 1 bit of PMG space, then each CLOSID can have two monitor groups. To allow resctrl to disambiguate RMID values for different CLOSID, everything in resctrl that keeps an RMID value needs to know the CLOSID too. This will always be ignored on x86. Signed-off-by: James Morse Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Shaopeng Tan Reviewed-by: Xin Hao Reviewed-by: Reinette Chatre Tested-by: Shaopeng Tan Tested-by: Peter Newman Tested-by: Babu Moger Tested-by: Carl Worth # arm64 Link: https://lore.kernel.org/r/20240213184438.16675-6-james.morse@arm.com Signed-off-by: Borislav Petkov (AMD) --- arch/x86/include/asm/resctrl.h | 7 +++ arch/x86/kernel/cpu/resctrl/internal.h | 2 +- arch/x86/kernel/cpu/resctrl/monitor.c | 73 ++++++++++++++++++++----------- arch/x86/kernel/cpu/resctrl/pseudo_lock.c | 4 +- arch/x86/kernel/cpu/resctrl/rdtgroup.c | 12 ++--- include/linux/resctrl.h | 16 ++++++- 6 files changed, 77 insertions(+), 37 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/resctrl.h b/arch/x86/include/asm/resctrl.h index 255a78d9d906..cc6e1bce7b1a 100644 --- a/arch/x86/include/asm/resctrl.h +++ b/arch/x86/include/asm/resctrl.h @@ -7,6 +7,13 @@ #include #include +/* + * This value can never be a valid CLOSID, and is used when mapping a + * (closid, rmid) pair to an index and back. On x86 only the RMID is + * needed. The index is a software defined value. + */ +#define X86_RESCTRL_EMPTY_CLOSID ((u32)~0) + /** * struct resctrl_pqr_state - State cache for the PQR MSR * @cur_rmid: The cached Resource Monitoring ID diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index 61c763604fc9..ae0e3338abc4 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -542,7 +542,7 @@ struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r); int closids_supported(void); void closid_free(int closid); int alloc_rmid(void); -void free_rmid(u32 rmid); +void free_rmid(u32 closid, u32 rmid); int rdt_get_mon_l3_config(struct rdt_resource *r); void __exit rdt_put_mon_l3_config(void); bool __init rdt_cpu_has(int flag); diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index 3a73db0579d8..3dad4134d2c9 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -24,7 +24,20 @@ #include "internal.h" +/** + * struct rmid_entry - dirty tracking for all RMID. + * @closid: The CLOSID for this entry. + * @rmid: The RMID for this entry. + * @busy: The number of domains with cached data using this RMID. + * @list: Member of the rmid_free_lru list when busy == 0. + * + * Depending on the architecture the correct monitor is accessed using + * both @closid and @rmid, or @rmid only. + * + * Take the rdtgroup_mutex when accessing. + */ struct rmid_entry { + u32 closid; u32 rmid; int busy; struct list_head list; @@ -136,7 +149,7 @@ static inline u64 get_corrected_mbm_count(u32 rmid, unsigned long val) return val; } -static inline struct rmid_entry *__rmid_entry(u32 rmid) +static inline struct rmid_entry *__rmid_entry(u32 closid, u32 rmid) { struct rmid_entry *entry; @@ -190,7 +203,8 @@ static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_domain *hw_dom, } void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d, - u32 rmid, enum resctrl_event_id eventid) + u32 unused, u32 rmid, + enum resctrl_event_id eventid) { struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d); struct arch_mbm_state *am; @@ -230,7 +244,8 @@ static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width) } int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d, - u32 rmid, enum resctrl_event_id eventid, u64 *val) + u32 unused, u32 rmid, enum resctrl_event_id eventid, + u64 *val) { struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d); @@ -285,9 +300,9 @@ void __check_limbo(struct rdt_domain *d, bool force_free) if (nrmid >= r->num_rmid) break; - entry = __rmid_entry(nrmid); + entry = __rmid_entry(X86_RESCTRL_EMPTY_CLOSID, nrmid);// temporary - if (resctrl_arch_rmid_read(r, d, entry->rmid, + if (resctrl_arch_rmid_read(r, d, entry->closid, entry->rmid, QOS_L3_OCCUP_EVENT_ID, &val)) { rmid_dirty = true; } else { @@ -342,7 +357,8 @@ static void add_rmid_to_limbo(struct rmid_entry *entry) cpu = get_cpu(); list_for_each_entry(d, &r->domains, list) { if (cpumask_test_cpu(cpu, &d->cpu_mask)) { - err = resctrl_arch_rmid_read(r, d, entry->rmid, + err = resctrl_arch_rmid_read(r, d, entry->closid, + entry->rmid, QOS_L3_OCCUP_EVENT_ID, &val); if (err || val <= resctrl_rmid_realloc_threshold) @@ -366,7 +382,7 @@ static void add_rmid_to_limbo(struct rmid_entry *entry) list_add_tail(&entry->list, &rmid_free_lru); } -void free_rmid(u32 rmid) +void free_rmid(u32 closid, u32 rmid) { struct rmid_entry *entry; @@ -375,7 +391,7 @@ void free_rmid(u32 rmid) lockdep_assert_held(&rdtgroup_mutex); - entry = __rmid_entry(rmid); + entry = __rmid_entry(closid, rmid); if (is_llc_occupancy_enabled()) add_rmid_to_limbo(entry); @@ -383,8 +399,8 @@ void free_rmid(u32 rmid) list_add_tail(&entry->list, &rmid_free_lru); } -static struct mbm_state *get_mbm_state(struct rdt_domain *d, u32 rmid, - enum resctrl_event_id evtid) +static struct mbm_state *get_mbm_state(struct rdt_domain *d, u32 closid, + u32 rmid, enum resctrl_event_id evtid) { switch (evtid) { case QOS_L3_MBM_TOTAL_EVENT_ID: @@ -396,20 +412,21 @@ static struct mbm_state *get_mbm_state(struct rdt_domain *d, u32 rmid, } } -static int __mon_event_count(u32 rmid, struct rmid_read *rr) +static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr) { struct mbm_state *m; u64 tval = 0; if (rr->first) { - resctrl_arch_reset_rmid(rr->r, rr->d, rmid, rr->evtid); - m = get_mbm_state(rr->d, rmid, rr->evtid); + resctrl_arch_reset_rmid(rr->r, rr->d, closid, rmid, rr->evtid); + m = get_mbm_state(rr->d, closid, rmid, rr->evtid); if (m) memset(m, 0, sizeof(struct mbm_state)); return 0; } - rr->err = resctrl_arch_rmid_read(rr->r, rr->d, rmid, rr->evtid, &tval); + rr->err = resctrl_arch_rmid_read(rr->r, rr->d, closid, rmid, rr->evtid, + &tval); if (rr->err) return rr->err; @@ -421,6 +438,7 @@ static int __mon_event_count(u32 rmid, struct rmid_read *rr) /* * mbm_bw_count() - Update bw count from values previously read by * __mon_event_count(). + * @closid: The closid used to identify the cached mbm_state. * @rmid: The rmid used to identify the cached mbm_state. * @rr: The struct rmid_read populated by __mon_event_count(). * @@ -429,7 +447,7 @@ static int __mon_event_count(u32 rmid, struct rmid_read *rr) * __mon_event_count() is compared with the chunks value from the previous * invocation. This must be called once per second to maintain values in MBps. */ -static void mbm_bw_count(u32 rmid, struct rmid_read *rr) +static void mbm_bw_count(u32 closid, u32 rmid, struct rmid_read *rr) { struct mbm_state *m = &rr->d->mbm_local[rmid]; u64 cur_bw, bytes, cur_bytes; @@ -456,7 +474,7 @@ void mon_event_count(void *info) rdtgrp = rr->rgrp; - ret = __mon_event_count(rdtgrp->mon.rmid, rr); + ret = __mon_event_count(rdtgrp->closid, rdtgrp->mon.rmid, rr); /* * For Ctrl groups read data from child monitor groups and @@ -467,7 +485,8 @@ void mon_event_count(void *info) if (rdtgrp->type == RDTCTRL_GROUP) { list_for_each_entry(entry, head, mon.crdtgrp_list) { - if (__mon_event_count(entry->mon.rmid, rr) == 0) + if (__mon_event_count(entry->closid, entry->mon.rmid, + rr) == 0) ret = 0; } } @@ -578,7 +597,8 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm) resctrl_arch_update_one(r_mba, dom_mba, closid, CDP_NONE, new_msr_val); } -static void mbm_update(struct rdt_resource *r, struct rdt_domain *d, int rmid) +static void mbm_update(struct rdt_resource *r, struct rdt_domain *d, + u32 closid, u32 rmid) { struct rmid_read rr; @@ -593,12 +613,12 @@ static void mbm_update(struct rdt_resource *r, struct rdt_domain *d, int rmid) if (is_mbm_total_enabled()) { rr.evtid = QOS_L3_MBM_TOTAL_EVENT_ID; rr.val = 0; - __mon_event_count(rmid, &rr); + __mon_event_count(closid, rmid, &rr); } if (is_mbm_local_enabled()) { rr.evtid = QOS_L3_MBM_LOCAL_EVENT_ID; rr.val = 0; - __mon_event_count(rmid, &rr); + __mon_event_count(closid, rmid, &rr); /* * Call the MBA software controller only for the @@ -606,7 +626,7 @@ static void mbm_update(struct rdt_resource *r, struct rdt_domain *d, int rmid) * the software controller explicitly. */ if (is_mba_sc(NULL)) - mbm_bw_count(rmid, &rr); + mbm_bw_count(closid, rmid, &rr); } } @@ -663,11 +683,11 @@ void mbm_handle_overflow(struct work_struct *work) d = container_of(work, struct rdt_domain, mbm_over.work); list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) { - mbm_update(r, d, prgrp->mon.rmid); + mbm_update(r, d, prgrp->closid, prgrp->mon.rmid); head = &prgrp->mon.crdtgrp_list; list_for_each_entry(crgrp, head, mon.crdtgrp_list) - mbm_update(r, d, crgrp->mon.rmid); + mbm_update(r, d, crgrp->closid, crgrp->mon.rmid); if (is_mba_sc(NULL)) update_mba_bw(prgrp, d); @@ -710,10 +730,11 @@ static int dom_data_init(struct rdt_resource *r) } /* - * RMID 0 is special and is always allocated. It's used for all - * tasks that are not monitored. + * RESCTRL_RESERVED_CLOSID and RESCTRL_RESERVED_RMID are special and + * are always allocated. These are used for the rdtgroup_default + * control group, which will be setup later in rdtgroup_init(). */ - entry = __rmid_entry(0); + entry = __rmid_entry(RESCTRL_RESERVED_CLOSID, RESCTRL_RESERVED_RMID); list_del(&entry->list); return 0; diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c index 8f559eeae08e..65bee6f11015 100644 --- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c +++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c @@ -752,7 +752,7 @@ int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp) * anymore when this group would be used for pseudo-locking. This * is safe to call on platforms not capable of monitoring. */ - free_rmid(rdtgrp->mon.rmid); + free_rmid(rdtgrp->closid, rdtgrp->mon.rmid); ret = 0; goto out; @@ -787,7 +787,7 @@ int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp) ret = rdtgroup_locksetup_user_restore(rdtgrp); if (ret) { - free_rmid(rdtgrp->mon.rmid); + free_rmid(rdtgrp->closid, rdtgrp->mon.rmid); return ret; } diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index f455a10b74ab..ad7da7254f4d 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -2837,7 +2837,7 @@ static void free_all_child_rdtgrp(struct rdtgroup *rdtgrp) head = &rdtgrp->mon.crdtgrp_list; list_for_each_entry_safe(sentry, stmp, head, mon.crdtgrp_list) { - free_rmid(sentry->mon.rmid); + free_rmid(sentry->closid, sentry->mon.rmid); list_del(&sentry->mon.crdtgrp_list); if (atomic_read(&sentry->waitcount) != 0) @@ -2877,7 +2877,7 @@ static void rmdir_all_sub(void) cpumask_or(&rdtgroup_default.cpu_mask, &rdtgroup_default.cpu_mask, &rdtgrp->cpu_mask); - free_rmid(rdtgrp->mon.rmid); + free_rmid(rdtgrp->closid, rdtgrp->mon.rmid); kernfs_remove(rdtgrp->kn); list_del(&rdtgrp->rdtgroup_list); @@ -3305,7 +3305,7 @@ static int mkdir_rdt_prepare_rmid_alloc(struct rdtgroup *rdtgrp) ret = mkdir_mondata_all(rdtgrp->kn, rdtgrp, &rdtgrp->mon.mon_data_kn); if (ret) { rdt_last_cmd_puts("kernfs subdir error\n"); - free_rmid(rdtgrp->mon.rmid); + free_rmid(rdtgrp->closid, rdtgrp->mon.rmid); return ret; } @@ -3315,7 +3315,7 @@ static int mkdir_rdt_prepare_rmid_alloc(struct rdtgroup *rdtgrp) static void mkdir_rdt_prepare_rmid_free(struct rdtgroup *rgrp) { if (rdt_mon_capable) - free_rmid(rgrp->mon.rmid); + free_rmid(rgrp->closid, rgrp->mon.rmid); } static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, @@ -3574,7 +3574,7 @@ static int rdtgroup_rmdir_mon(struct rdtgroup *rdtgrp, cpumask_var_t tmpmask) update_closid_rmid(tmpmask, NULL); rdtgrp->flags = RDT_DELETED; - free_rmid(rdtgrp->mon.rmid); + free_rmid(rdtgrp->closid, rdtgrp->mon.rmid); /* * Remove the rdtgrp from the parent ctrl_mon group's list @@ -3620,8 +3620,8 @@ static int rdtgroup_rmdir_ctrl(struct rdtgroup *rdtgrp, cpumask_var_t tmpmask) cpumask_or(tmpmask, tmpmask, &rdtgrp->cpu_mask); update_closid_rmid(tmpmask, NULL); + free_rmid(rdtgrp->closid, rdtgrp->mon.rmid); closid_free(rdtgrp->closid); - free_rmid(rdtgrp->mon.rmid); rdtgroup_ctrl_remove(rdtgrp); diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index 66942d7fba7f..bd4ec22b5a96 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -6,6 +6,10 @@ #include #include +/* CLOSID, RMID value used by the default control group */ +#define RESCTRL_RESERVED_CLOSID 0 +#define RESCTRL_RESERVED_RMID 0 + #ifdef CONFIG_PROC_CPU_RESCTRL int proc_resctrl_show(struct seq_file *m, @@ -225,6 +229,9 @@ void resctrl_offline_domain(struct rdt_resource *r, struct rdt_domain *d); * for this resource and domain. * @r: resource that the counter should be read from. * @d: domain that the counter should be read from. + * @closid: closid that matches the rmid. Depending on the architecture, the + * counter may match traffic of both @closid and @rmid, or @rmid + * only. * @rmid: rmid of the counter to read. * @eventid: eventid to read, e.g. L3 occupancy. * @val: result of the counter read in bytes. @@ -235,20 +242,25 @@ void resctrl_offline_domain(struct rdt_resource *r, struct rdt_domain *d); * 0 on success, or -EIO, -EINVAL etc on error. */ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d, - u32 rmid, enum resctrl_event_id eventid, u64 *val); + u32 closid, u32 rmid, enum resctrl_event_id eventid, + u64 *val); + /** * resctrl_arch_reset_rmid() - Reset any private state associated with rmid * and eventid. * @r: The domain's resource. * @d: The rmid's domain. + * @closid: closid that matches the rmid. Depending on the architecture, the + * counter may match traffic of both @closid and @rmid, or @rmid only. * @rmid: The rmid whose counter values should be reset. * @eventid: The eventid whose counter values should be reset. * * This can be called from any CPU. */ void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d, - u32 rmid, enum resctrl_event_id eventid); + u32 closid, u32 rmid, + enum resctrl_event_id eventid); /** * resctrl_arch_reset_rmid_all() - Reset all private state associated with -- cgit v1.2.3 From 6791e0ea30711b937d5cb6e2b17f59a2a2af5386 Mon Sep 17 00:00:00 2001 From: James Morse Date: Tue, 13 Feb 2024 18:44:20 +0000 Subject: x86/resctrl: Access per-rmid structures by index x86 systems identify traffic using the CLOSID and RMID. The CLOSID is used to lookup the control policy, the RMID is used for monitoring. For x86 these are independent numbers. Arm's MPAM has equivalent features PARTID and PMG, where the PARTID is used to lookup the control policy. The PMG in contrast is a small number of bits that are used to subdivide PARTID when monitoring. The cache-occupancy monitors require the PARTID to be specified when monitoring. This means MPAM's PMG field is not unique. There are multiple PMG-0, one per allocated CLOSID/PARTID. If PMG is treated as equivalent to RMID, it cannot be allocated as an independent number. Bitmaps like rmid_busy_llc need to be sized by the number of unique entries for this resource. Treat the combined CLOSID and RMID as an index, and provide architecture helpers to pack and unpack an index. This makes the MPAM values unique. The domain's rmid_busy_llc and rmid_ptrs[] are then sized by index, as are domain mbm_local[] and mbm_total[]. x86 can ignore the CLOSID field when packing and unpacking an index, and report as many indexes as RMID. Signed-off-by: James Morse Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Shaopeng Tan Reviewed-by: Babu Moger Reviewed-by: Reinette Chatre Tested-by: Shaopeng Tan Tested-by: Peter Newman Tested-by: Babu Moger Tested-by: Carl Worth # arm64 Link: https://lore.kernel.org/r/20240213184438.16675-7-james.morse@arm.com Signed-off-by: Borislav Petkov (AMD) --- arch/x86/include/asm/resctrl.h | 17 ++++++ arch/x86/kernel/cpu/resctrl/core.c | 13 ++--- arch/x86/kernel/cpu/resctrl/internal.h | 4 +- arch/x86/kernel/cpu/resctrl/monitor.c | 98 +++++++++++++++++++++++----------- arch/x86/kernel/cpu/resctrl/rdtgroup.c | 13 ++--- 5 files changed, 100 insertions(+), 45 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/resctrl.h b/arch/x86/include/asm/resctrl.h index cc6e1bce7b1a..db4c84dde2d5 100644 --- a/arch/x86/include/asm/resctrl.h +++ b/arch/x86/include/asm/resctrl.h @@ -101,6 +101,23 @@ static inline void resctrl_sched_in(struct task_struct *tsk) __resctrl_sched_in(tsk); } +static inline u32 resctrl_arch_system_num_rmid_idx(void) +{ + /* RMID are independent numbers for x86. num_rmid_idx == num_rmid */ + return boot_cpu_data.x86_cache_max_rmid + 1; +} + +static inline void resctrl_arch_rmid_idx_decode(u32 idx, u32 *closid, u32 *rmid) +{ + *rmid = idx; + *closid = X86_RESCTRL_EMPTY_CLOSID; +} + +static inline u32 resctrl_arch_rmid_idx_encode(u32 ignored, u32 rmid) +{ + return rmid; +} + void resctrl_cpu_detect(struct cpuinfo_x86 *c); #else diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index 9641c42d0f85..d1dc80a21ea9 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -587,7 +587,7 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r) mbm_setup_overflow_handler(d, 0); } if (is_llc_occupancy_enabled() && cpu == d->cqm_work_cpu && - has_busy_rmid(r, d)) { + has_busy_rmid(d)) { cancel_delayed_work(&d->cqm_limbo); cqm_setup_limbo_handler(d, 0); } @@ -598,11 +598,12 @@ static void clear_closid_rmid(int cpu) { struct resctrl_pqr_state *state = this_cpu_ptr(&pqr_state); - state->default_closid = 0; - state->default_rmid = 0; - state->cur_closid = 0; - state->cur_rmid = 0; - wrmsr(MSR_IA32_PQR_ASSOC, 0, 0); + state->default_closid = RESCTRL_RESERVED_CLOSID; + state->default_rmid = RESCTRL_RESERVED_RMID; + state->cur_closid = RESCTRL_RESERVED_CLOSID; + state->cur_rmid = RESCTRL_RESERVED_RMID; + wrmsr(MSR_IA32_PQR_ASSOC, RESCTRL_RESERVED_RMID, + RESCTRL_RESERVED_CLOSID); } static int resctrl_online_cpu(unsigned int cpu) diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index ae0e3338abc4..cbba782acd0c 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -8,6 +8,8 @@ #include #include +#include + #define L3_QOS_CDP_ENABLE 0x01ULL #define L2_QOS_CDP_ENABLE 0x01ULL @@ -558,7 +560,7 @@ void __init intel_rdt_mbm_apply_quirk(void); bool is_mba_sc(struct rdt_resource *r); void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms); void cqm_handle_limbo(struct work_struct *work); -bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d); +bool has_busy_rmid(struct rdt_domain *d); void __check_limbo(struct rdt_domain *d, bool force_free); void rdt_domain_reconfigure_cdp(struct rdt_resource *r); void __init thread_throttle_mode_init(void); diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index 3dad4134d2c9..bc5ceef143ab 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -149,12 +149,29 @@ static inline u64 get_corrected_mbm_count(u32 rmid, unsigned long val) return val; } -static inline struct rmid_entry *__rmid_entry(u32 closid, u32 rmid) +/* + * x86 and arm64 differ in their handling of monitoring. + * x86's RMID are independent numbers, there is only one source of traffic + * with an RMID value of '1'. + * arm64's PMG extends the PARTID/CLOSID space, there are multiple sources of + * traffic with a PMG value of '1', one for each CLOSID, meaning the RMID + * value is no longer unique. + * To account for this, resctrl uses an index. On x86 this is just the RMID, + * on arm64 it encodes the CLOSID and RMID. This gives a unique number. + * + * The domain's rmid_busy_llc and rmid_ptrs[] are sized by index. The arch code + * must accept an attempt to read every index. + */ +static inline struct rmid_entry *__rmid_entry(u32 idx) { struct rmid_entry *entry; + u32 closid, rmid; + + entry = &rmid_ptrs[idx]; + resctrl_arch_rmid_idx_decode(idx, &closid, &rmid); - entry = &rmid_ptrs[rmid]; - WARN_ON(entry->rmid != rmid); + WARN_ON_ONCE(entry->closid != closid); + WARN_ON_ONCE(entry->rmid != rmid); return entry; } @@ -284,8 +301,9 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d, void __check_limbo(struct rdt_domain *d, bool force_free) { struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; + u32 idx_limit = resctrl_arch_system_num_rmid_idx(); struct rmid_entry *entry; - u32 crmid = 1, nrmid; + u32 idx, cur_idx = 1; bool rmid_dirty; u64 val = 0; @@ -296,12 +314,11 @@ void __check_limbo(struct rdt_domain *d, bool force_free) * RMID and move it to the free list when the counter reaches 0. */ for (;;) { - nrmid = find_next_bit(d->rmid_busy_llc, r->num_rmid, crmid); - if (nrmid >= r->num_rmid) + idx = find_next_bit(d->rmid_busy_llc, idx_limit, cur_idx); + if (idx >= idx_limit) break; - entry = __rmid_entry(X86_RESCTRL_EMPTY_CLOSID, nrmid);// temporary - + entry = __rmid_entry(idx); if (resctrl_arch_rmid_read(r, d, entry->closid, entry->rmid, QOS_L3_OCCUP_EVENT_ID, &val)) { rmid_dirty = true; @@ -310,19 +327,21 @@ void __check_limbo(struct rdt_domain *d, bool force_free) } if (force_free || !rmid_dirty) { - clear_bit(entry->rmid, d->rmid_busy_llc); + clear_bit(idx, d->rmid_busy_llc); if (!--entry->busy) { rmid_limbo_count--; list_add_tail(&entry->list, &rmid_free_lru); } } - crmid = nrmid + 1; + cur_idx = idx + 1; } } -bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d) +bool has_busy_rmid(struct rdt_domain *d) { - return find_first_bit(d->rmid_busy_llc, r->num_rmid) != r->num_rmid; + u32 idx_limit = resctrl_arch_system_num_rmid_idx(); + + return find_first_bit(d->rmid_busy_llc, idx_limit) != idx_limit; } /* @@ -352,6 +371,9 @@ static void add_rmid_to_limbo(struct rmid_entry *entry) struct rdt_domain *d; int cpu, err; u64 val = 0; + u32 idx; + + idx = resctrl_arch_rmid_idx_encode(entry->closid, entry->rmid); entry->busy = 0; cpu = get_cpu(); @@ -369,9 +391,9 @@ static void add_rmid_to_limbo(struct rmid_entry *entry) * For the first limbo RMID in the domain, * setup up the limbo worker. */ - if (!has_busy_rmid(r, d)) + if (!has_busy_rmid(d)) cqm_setup_limbo_handler(d, CQM_LIMBOCHECK_INTERVAL); - set_bit(entry->rmid, d->rmid_busy_llc); + set_bit(idx, d->rmid_busy_llc); entry->busy++; } put_cpu(); @@ -384,14 +406,21 @@ static void add_rmid_to_limbo(struct rmid_entry *entry) void free_rmid(u32 closid, u32 rmid) { + u32 idx = resctrl_arch_rmid_idx_encode(closid, rmid); struct rmid_entry *entry; - if (!rmid) - return; - lockdep_assert_held(&rdtgroup_mutex); - entry = __rmid_entry(closid, rmid); + /* + * Do not allow the default rmid to be free'd. Comparing by index + * allows architectures that ignore the closid parameter to avoid an + * unnecessary check. + */ + if (idx == resctrl_arch_rmid_idx_encode(RESCTRL_RESERVED_CLOSID, + RESCTRL_RESERVED_RMID)) + return; + + entry = __rmid_entry(idx); if (is_llc_occupancy_enabled()) add_rmid_to_limbo(entry); @@ -402,11 +431,13 @@ void free_rmid(u32 closid, u32 rmid) static struct mbm_state *get_mbm_state(struct rdt_domain *d, u32 closid, u32 rmid, enum resctrl_event_id evtid) { + u32 idx = resctrl_arch_rmid_idx_encode(closid, rmid); + switch (evtid) { case QOS_L3_MBM_TOTAL_EVENT_ID: - return &d->mbm_total[rmid]; + return &d->mbm_total[idx]; case QOS_L3_MBM_LOCAL_EVENT_ID: - return &d->mbm_local[rmid]; + return &d->mbm_local[idx]; default: return NULL; } @@ -449,7 +480,8 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr) */ static void mbm_bw_count(u32 closid, u32 rmid, struct rmid_read *rr) { - struct mbm_state *m = &rr->d->mbm_local[rmid]; + u32 idx = resctrl_arch_rmid_idx_encode(closid, rmid); + struct mbm_state *m = &rr->d->mbm_local[idx]; u64 cur_bw, bytes, cur_bytes; cur_bytes = rr->val; @@ -538,9 +570,9 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm) struct mbm_state *pmbm_data, *cmbm_data; struct rdt_resource *r_mba; struct rdt_domain *dom_mba; + u32 cur_bw, user_bw, idx; struct list_head *head; struct rdtgroup *entry; - u32 cur_bw, user_bw; if (!is_mbm_local_enabled()) return; @@ -549,7 +581,8 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm) closid = rgrp->closid; rmid = rgrp->mon.rmid; - pmbm_data = &dom_mbm->mbm_local[rmid]; + idx = resctrl_arch_rmid_idx_encode(closid, rmid); + pmbm_data = &dom_mbm->mbm_local[idx]; dom_mba = get_domain_from_cpu(smp_processor_id(), r_mba); if (!dom_mba) { @@ -638,17 +671,15 @@ void cqm_handle_limbo(struct work_struct *work) { unsigned long delay = msecs_to_jiffies(CQM_LIMBOCHECK_INTERVAL); int cpu = smp_processor_id(); - struct rdt_resource *r; struct rdt_domain *d; mutex_lock(&rdtgroup_mutex); - r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; d = container_of(work, struct rdt_domain, cqm_limbo.work); __check_limbo(d, false); - if (has_busy_rmid(r, d)) + if (has_busy_rmid(d)) schedule_delayed_work_on(cpu, &d->cqm_limbo, delay); mutex_unlock(&rdtgroup_mutex); @@ -713,19 +744,20 @@ void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms) static int dom_data_init(struct rdt_resource *r) { + u32 idx_limit = resctrl_arch_system_num_rmid_idx(); struct rmid_entry *entry = NULL; - int i, nr_rmids; + u32 idx; + int i; - nr_rmids = r->num_rmid; - rmid_ptrs = kcalloc(nr_rmids, sizeof(struct rmid_entry), GFP_KERNEL); + rmid_ptrs = kcalloc(idx_limit, sizeof(struct rmid_entry), GFP_KERNEL); if (!rmid_ptrs) return -ENOMEM; - for (i = 0; i < nr_rmids; i++) { + for (i = 0; i < idx_limit; i++) { entry = &rmid_ptrs[i]; INIT_LIST_HEAD(&entry->list); - entry->rmid = i; + resctrl_arch_rmid_idx_decode(i, &entry->closid, &entry->rmid); list_add_tail(&entry->list, &rmid_free_lru); } @@ -734,7 +766,9 @@ static int dom_data_init(struct rdt_resource *r) * are always allocated. These are used for the rdtgroup_default * control group, which will be setup later in rdtgroup_init(). */ - entry = __rmid_entry(RESCTRL_RESERVED_CLOSID, RESCTRL_RESERVED_RMID); + idx = resctrl_arch_rmid_idx_encode(RESCTRL_RESERVED_CLOSID, + RESCTRL_RESERVED_RMID); + entry = __rmid_entry(idx); list_del(&entry->list); return 0; diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index ad7da7254f4d..a7dbc0e7e559 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -3853,8 +3853,8 @@ static void __init rdtgroup_setup_default(void) { mutex_lock(&rdtgroup_mutex); - rdtgroup_default.closid = 0; - rdtgroup_default.mon.rmid = 0; + rdtgroup_default.closid = RESCTRL_RESERVED_CLOSID; + rdtgroup_default.mon.rmid = RESCTRL_RESERVED_RMID; rdtgroup_default.type = RDTCTRL_GROUP; INIT_LIST_HEAD(&rdtgroup_default.mon.crdtgrp_list); @@ -3889,7 +3889,7 @@ void resctrl_offline_domain(struct rdt_resource *r, struct rdt_domain *d) if (is_mbm_enabled()) cancel_delayed_work(&d->mbm_over); - if (is_llc_occupancy_enabled() && has_busy_rmid(r, d)) { + if (is_llc_occupancy_enabled() && has_busy_rmid(d)) { /* * When a package is going down, forcefully * decrement rmid->ebusy. There is no way to know @@ -3907,16 +3907,17 @@ void resctrl_offline_domain(struct rdt_resource *r, struct rdt_domain *d) static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d) { + u32 idx_limit = resctrl_arch_system_num_rmid_idx(); size_t tsize; if (is_llc_occupancy_enabled()) { - d->rmid_busy_llc = bitmap_zalloc(r->num_rmid, GFP_KERNEL); + d->rmid_busy_llc = bitmap_zalloc(idx_limit, GFP_KERNEL); if (!d->rmid_busy_llc) return -ENOMEM; } if (is_mbm_total_enabled()) { tsize = sizeof(*d->mbm_total); - d->mbm_total = kcalloc(r->num_rmid, tsize, GFP_KERNEL); + d->mbm_total = kcalloc(idx_limit, tsize, GFP_KERNEL); if (!d->mbm_total) { bitmap_free(d->rmid_busy_llc); return -ENOMEM; @@ -3924,7 +3925,7 @@ static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d) } if (is_mbm_local_enabled()) { tsize = sizeof(*d->mbm_local); - d->mbm_local = kcalloc(r->num_rmid, tsize, GFP_KERNEL); + d->mbm_local = kcalloc(idx_limit, tsize, GFP_KERNEL); if (!d->mbm_local) { bitmap_free(d->rmid_busy_llc); kfree(d->mbm_total); -- cgit v1.2.3 From c4c0376eefe185b790d89ca8016b7f837ebf25da Mon Sep 17 00:00:00 2001 From: James Morse Date: Tue, 13 Feb 2024 18:44:21 +0000 Subject: x86/resctrl: Allow RMID allocation to be scoped by CLOSID MPAMs RMID values are not unique unless the CLOSID is considered as well. alloc_rmid() expects the RMID to be an independent number. Pass the CLOSID in to alloc_rmid(). Use this to compare indexes when allocating. If the CLOSID is not relevant to the index, this ends up comparing the free RMID with itself, and the first free entry will be used. With MPAM the CLOSID is included in the index, so this becomes a walk of the free RMID entries, until one that matches the supplied CLOSID is found. Signed-off-by: James Morse Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Shaopeng Tan Reviewed-by: Reinette Chatre Reviewed-by: Babu Moger Tested-by: Shaopeng Tan Tested-by: Peter Newman Tested-by: Babu Moger Tested-by: Carl Worth # arm64 Link: https://lore.kernel.org/r/20240213184438.16675-8-james.morse@arm.com Signed-off-by: Borislav Petkov (AMD) --- arch/x86/kernel/cpu/resctrl/internal.h | 2 +- arch/x86/kernel/cpu/resctrl/monitor.c | 43 ++++++++++++++++++++++++------- arch/x86/kernel/cpu/resctrl/pseudo_lock.c | 2 +- arch/x86/kernel/cpu/resctrl/rdtgroup.c | 2 +- 4 files changed, 37 insertions(+), 12 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index cbba782acd0c..872ba1a34103 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -543,7 +543,7 @@ void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp); struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r); int closids_supported(void); void closid_free(int closid); -int alloc_rmid(void); +int alloc_rmid(u32 closid); void free_rmid(u32 closid, u32 rmid); int rdt_get_mon_l3_config(struct rdt_resource *r); void __exit rdt_put_mon_l3_config(void); diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index bc5ceef143ab..c49f2e89ef29 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -344,24 +344,49 @@ bool has_busy_rmid(struct rdt_domain *d) return find_first_bit(d->rmid_busy_llc, idx_limit) != idx_limit; } +static struct rmid_entry *resctrl_find_free_rmid(u32 closid) +{ + struct rmid_entry *itr; + u32 itr_idx, cmp_idx; + + if (list_empty(&rmid_free_lru)) + return rmid_limbo_count ? ERR_PTR(-EBUSY) : ERR_PTR(-ENOSPC); + + list_for_each_entry(itr, &rmid_free_lru, list) { + /* + * Get the index of this free RMID, and the index it would need + * to be if it were used with this CLOSID. + * If the CLOSID is irrelevant on this architecture, the two + * index values are always the same on every entry and thus the + * very first entry will be returned. + */ + itr_idx = resctrl_arch_rmid_idx_encode(itr->closid, itr->rmid); + cmp_idx = resctrl_arch_rmid_idx_encode(closid, itr->rmid); + + if (itr_idx == cmp_idx) + return itr; + } + + return ERR_PTR(-ENOSPC); +} + /* - * As of now the RMIDs allocation is global. - * However we keep track of which packages the RMIDs - * are used to optimize the limbo list management. + * For MPAM the RMID value is not unique, and has to be considered with + * the CLOSID. The (CLOSID, RMID) pair is allocated on all domains, which + * allows all domains to be managed by a single free list. + * Each domain also has a rmid_busy_llc to reduce the work of the limbo handler. */ -int alloc_rmid(void) +int alloc_rmid(u32 closid) { struct rmid_entry *entry; lockdep_assert_held(&rdtgroup_mutex); - if (list_empty(&rmid_free_lru)) - return rmid_limbo_count ? -EBUSY : -ENOSPC; + entry = resctrl_find_free_rmid(closid); + if (IS_ERR(entry)) + return PTR_ERR(entry); - entry = list_first_entry(&rmid_free_lru, - struct rmid_entry, list); list_del(&entry->list); - return entry->rmid; } diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c index 65bee6f11015..d8f44113ed1f 100644 --- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c +++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c @@ -777,7 +777,7 @@ int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp) int ret; if (rdt_mon_capable) { - ret = alloc_rmid(); + ret = alloc_rmid(rdtgrp->closid); if (ret < 0) { rdt_last_cmd_puts("Out of RMIDs\n"); return ret; diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index a7dbc0e7e559..dcffd1c4a476 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -3295,7 +3295,7 @@ static int mkdir_rdt_prepare_rmid_alloc(struct rdtgroup *rdtgrp) if (!rdt_mon_capable) return 0; - ret = alloc_rmid(); + ret = alloc_rmid(rdtgrp->closid); if (ret < 0) { rdt_last_cmd_puts("Out of RMIDs\n"); return ret; -- cgit v1.2.3 From b30a55df60c35df09b9ef08dfb0a0cbb543abe81 Mon Sep 17 00:00:00 2001 From: James Morse Date: Tue, 13 Feb 2024 18:44:22 +0000 Subject: x86/resctrl: Track the number of dirty RMID a CLOSID has MPAM's PMG bits extend its PARTID space, meaning the same PMG value can be used for different control groups. This means once a CLOSID is allocated, all its monitoring ids may still be dirty, and held in limbo. Keep track of the number of RMID held in limbo each CLOSID has. This will allow a future helper to find the 'cleanest' CLOSID when allocating. The array is only needed when CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID is defined. This will never be the case on x86. Signed-off-by: James Morse Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Shaopeng Tan Reviewed-by: Reinette Chatre Reviewed-by: Babu Moger Tested-by: Shaopeng Tan Tested-by: Peter Newman Tested-by: Babu Moger Tested-by: Carl Worth # arm64 Link: https://lore.kernel.org/r/20240213184438.16675-9-james.morse@arm.com Signed-off-by: Borislav Petkov (AMD) --- arch/x86/kernel/cpu/resctrl/monitor.c | 75 ++++++++++++++++++++++++++++++----- 1 file changed, 65 insertions(+), 10 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index c49f2e89ef29..13b0c8d14f3d 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -50,6 +50,13 @@ struct rmid_entry { */ static LIST_HEAD(rmid_free_lru); +/* + * @closid_num_dirty_rmid The number of dirty RMID each CLOSID has. + * Only allocated when CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID is defined. + * Indexed by CLOSID. Protected by rdtgroup_mutex. + */ +static u32 *closid_num_dirty_rmid; + /* * @rmid_limbo_count - count of currently unused but (potentially) * dirty RMIDs. @@ -292,6 +299,17 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d, return 0; } +static void limbo_release_entry(struct rmid_entry *entry) +{ + lockdep_assert_held(&rdtgroup_mutex); + + rmid_limbo_count--; + list_add_tail(&entry->list, &rmid_free_lru); + + if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) + closid_num_dirty_rmid[entry->closid]--; +} + /* * Check the RMIDs that are marked as busy for this domain. If the * reported LLC occupancy is below the threshold clear the busy bit and @@ -328,10 +346,8 @@ void __check_limbo(struct rdt_domain *d, bool force_free) if (force_free || !rmid_dirty) { clear_bit(idx, d->rmid_busy_llc); - if (!--entry->busy) { - rmid_limbo_count--; - list_add_tail(&entry->list, &rmid_free_lru); - } + if (!--entry->busy) + limbo_release_entry(entry); } cur_idx = idx + 1; } @@ -398,6 +414,8 @@ static void add_rmid_to_limbo(struct rmid_entry *entry) u64 val = 0; u32 idx; + lockdep_assert_held(&rdtgroup_mutex); + idx = resctrl_arch_rmid_idx_encode(entry->closid, entry->rmid); entry->busy = 0; @@ -423,10 +441,13 @@ static void add_rmid_to_limbo(struct rmid_entry *entry) } put_cpu(); - if (entry->busy) + if (entry->busy) { rmid_limbo_count++; - else + if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) + closid_num_dirty_rmid[entry->closid]++; + } else { list_add_tail(&entry->list, &rmid_free_lru); + } } void free_rmid(u32 closid, u32 rmid) @@ -770,13 +791,39 @@ void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms) static int dom_data_init(struct rdt_resource *r) { u32 idx_limit = resctrl_arch_system_num_rmid_idx(); + u32 num_closid = resctrl_arch_get_num_closid(r); struct rmid_entry *entry = NULL; + int err = 0, i; u32 idx; - int i; + + mutex_lock(&rdtgroup_mutex); + if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) { + u32 *tmp; + + /* + * If the architecture hasn't provided a sanitised value here, + * this may result in larger arrays than necessary. Resctrl will + * use a smaller system wide value based on the resources in + * use. + */ + tmp = kcalloc(num_closid, sizeof(*tmp), GFP_KERNEL); + if (!tmp) { + err = -ENOMEM; + goto out_unlock; + } + + closid_num_dirty_rmid = tmp; + } rmid_ptrs = kcalloc(idx_limit, sizeof(struct rmid_entry), GFP_KERNEL); - if (!rmid_ptrs) - return -ENOMEM; + if (!rmid_ptrs) { + if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) { + kfree(closid_num_dirty_rmid); + closid_num_dirty_rmid = NULL; + } + err = -ENOMEM; + goto out_unlock; + } for (i = 0; i < idx_limit; i++) { entry = &rmid_ptrs[i]; @@ -796,13 +843,21 @@ static int dom_data_init(struct rdt_resource *r) entry = __rmid_entry(idx); list_del(&entry->list); - return 0; +out_unlock: + mutex_unlock(&rdtgroup_mutex); + + return err; } static void __exit dom_data_exit(void) { mutex_lock(&rdtgroup_mutex); + if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) { + kfree(closid_num_dirty_rmid); + closid_num_dirty_rmid = NULL; + } + kfree(rmid_ptrs); rmid_ptrs = NULL; -- cgit v1.2.3 From 5d920b6881f2249be3a028ce0a7f31c5cc61b1ee Mon Sep 17 00:00:00 2001 From: James Morse Date: Tue, 13 Feb 2024 18:44:23 +0000 Subject: x86/resctrl: Use __set_bit()/__clear_bit() instead of open coding The resctrl CLOSID allocator uses a single 32bit word to track which CLOSID are free. The setting and clearing of bits is open coded. Convert the existing open coded bit manipulations of closid_free_map to use __set_bit() and friends. These don't need to be atomic as this list is protected by the mutex. Signed-off-by: James Morse Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Shaopeng Tan Reviewed-by: Reinette Chatre Reviewed-by: Babu Moger Tested-by: Shaopeng Tan Tested-by: Peter Newman Tested-by: Babu Moger Tested-by: Carl Worth # arm64 Link: https://lore.kernel.org/r/20240213184438.16675-10-james.morse@arm.com Signed-off-by: Borislav Petkov (AMD) --- arch/x86/kernel/cpu/resctrl/rdtgroup.c | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index dcffd1c4a476..bc6e0f83c847 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -111,7 +111,7 @@ void rdt_staged_configs_clear(void) * - Our choices on how to configure each resource become progressively more * limited as the number of resources grows. */ -static int closid_free_map; +static unsigned long closid_free_map; static int closid_free_map_len; int closids_supported(void) @@ -130,8 +130,8 @@ static void closid_init(void) closid_free_map = BIT_MASK(rdt_min_closid) - 1; - /* CLOSID 0 is always reserved for the default group */ - closid_free_map &= ~1; + /* RESCTRL_RESERVED_CLOSID is always reserved for the default group */ + __clear_bit(RESCTRL_RESERVED_CLOSID, &closid_free_map); closid_free_map_len = rdt_min_closid; } @@ -139,17 +139,21 @@ static int closid_alloc(void) { u32 closid = ffs(closid_free_map); + lockdep_assert_held(&rdtgroup_mutex); + if (closid == 0) return -ENOSPC; closid--; - closid_free_map &= ~(1 << closid); + __clear_bit(closid, &closid_free_map); return closid; } void closid_free(int closid) { - closid_free_map |= 1 << closid; + lockdep_assert_held(&rdtgroup_mutex); + + __set_bit(closid, &closid_free_map); } /** @@ -161,7 +165,9 @@ void closid_free(int closid) */ static bool closid_allocated(unsigned int closid) { - return (closid_free_map & (1 << closid)) == 0; + lockdep_assert_held(&rdtgroup_mutex); + + return !test_bit(closid, &closid_free_map); } /** -- cgit v1.2.3 From 6eac36bb9eb0349c983313c71692c19d50b56878 Mon Sep 17 00:00:00 2001 From: James Morse Date: Tue, 13 Feb 2024 18:44:24 +0000 Subject: x86/resctrl: Allocate the cleanest CLOSID by searching closid_num_dirty_rmid MPAM's PMG bits extend its PARTID space, meaning the same PMG value can be used for different control groups. This means once a CLOSID is allocated, all its monitoring ids may still be dirty, and held in limbo. Instead of allocating the first free CLOSID, on architectures where CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID is enabled, search closid_num_dirty_rmid[] to find the cleanest CLOSID. The CLOSID found is returned to closid_alloc() for the free list to be updated. Signed-off-by: James Morse Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Shaopeng Tan Reviewed-by: Reinette Chatre Reviewed-by: Babu Moger Tested-by: Shaopeng Tan Tested-by: Peter Newman Tested-by: Babu Moger Tested-by: Carl Worth # arm64 Link: https://lore.kernel.org/r/20240213184438.16675-11-james.morse@arm.com Signed-off-by: Borislav Petkov (AMD) --- arch/x86/kernel/cpu/resctrl/internal.h | 2 ++ arch/x86/kernel/cpu/resctrl/monitor.c | 45 ++++++++++++++++++++++++++++++++++ arch/x86/kernel/cpu/resctrl/rdtgroup.c | 19 ++++++++++---- 3 files changed, 61 insertions(+), 5 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index 872ba1a34103..b7b9d9230bef 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -566,5 +566,7 @@ void rdt_domain_reconfigure_cdp(struct rdt_resource *r); void __init thread_throttle_mode_init(void); void __init mbm_config_rftype_init(const char *config); void rdt_staged_configs_clear(void); +bool closid_allocated(unsigned int closid); +int resctrl_find_cleanest_closid(void); #endif /* _ASM_X86_RESCTRL_INTERNAL_H */ diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index 13b0c8d14f3d..101f1b112d17 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -386,6 +386,51 @@ static struct rmid_entry *resctrl_find_free_rmid(u32 closid) return ERR_PTR(-ENOSPC); } +/** + * resctrl_find_cleanest_closid() - Find a CLOSID where all the associated + * RMID are clean, or the CLOSID that has + * the most clean RMID. + * + * MPAM's equivalent of RMID are per-CLOSID, meaning a freshly allocated CLOSID + * may not be able to allocate clean RMID. To avoid this the allocator will + * choose the CLOSID with the most clean RMID. + * + * When the CLOSID and RMID are independent numbers, the first free CLOSID will + * be returned. + */ +int resctrl_find_cleanest_closid(void) +{ + u32 cleanest_closid = ~0; + int i = 0; + + lockdep_assert_held(&rdtgroup_mutex); + + if (!IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) + return -EIO; + + for (i = 0; i < closids_supported(); i++) { + int num_dirty; + + if (closid_allocated(i)) + continue; + + num_dirty = closid_num_dirty_rmid[i]; + if (num_dirty == 0) + return i; + + if (cleanest_closid == ~0) + cleanest_closid = i; + + if (num_dirty < closid_num_dirty_rmid[cleanest_closid]) + cleanest_closid = i; + } + + if (cleanest_closid == ~0) + return -ENOSPC; + + return cleanest_closid; +} + /* * For MPAM the RMID value is not unique, and has to be considered with * the CLOSID. The (CLOSID, RMID) pair is allocated on all domains, which diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index bc6e0f83c847..8fc46204a6cc 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -137,13 +137,22 @@ static void closid_init(void) static int closid_alloc(void) { - u32 closid = ffs(closid_free_map); + int cleanest_closid; + u32 closid; lockdep_assert_held(&rdtgroup_mutex); - if (closid == 0) - return -ENOSPC; - closid--; + if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) { + cleanest_closid = resctrl_find_cleanest_closid(); + if (cleanest_closid < 0) + return cleanest_closid; + closid = cleanest_closid; + } else { + closid = ffs(closid_free_map); + if (closid == 0) + return -ENOSPC; + closid--; + } __clear_bit(closid, &closid_free_map); return closid; @@ -163,7 +172,7 @@ void closid_free(int closid) * Return: true if @closid is currently associated with a resource group, * false if @closid is free */ -static bool closid_allocated(unsigned int closid) +bool closid_allocated(unsigned int closid) { lockdep_assert_held(&rdtgroup_mutex); -- cgit v1.2.3 From 6eca639d8340b569ff78ffd753796e83ef7075ae Mon Sep 17 00:00:00 2001 From: James Morse Date: Tue, 13 Feb 2024 18:44:25 +0000 Subject: x86/resctrl: Move CLOSID/RMID matching and setting to use helpers When switching tasks, the CLOSID and RMID that the new task should use are stored in struct task_struct. For x86 the CLOSID known by resctrl, the value in task_struct, and the value written to the CPU register are all the same thing. MPAM's CPU interface has two different PARTIDs - one for data accesses the other for instruction fetch. Storing resctrl's CLOSID value in struct task_struct implies the arch code knows whether resctrl is using CDP. Move the matching and setting of the struct task_struct properties to use helpers. This allows arm64 to store the hardware format of the register, instead of having to convert it each time. __rdtgroup_move_task()s use of READ_ONCE()/WRITE_ONCE() ensures torn values aren't seen as another CPU may schedule the task being moved while the value is being changed. MPAM has an additional corner-case here as the PMG bits extend the PARTID space. If the scheduler sees a new-CLOSID but old-RMID, the task will dirty an RMID that the limbo code is not watching causing an inaccurate count. x86's RMID are independent values, so the limbo code will still be watching the old-RMID in this circumstance. To avoid this, arm64 needs both the CLOSID/RMID WRITE_ONCE()d together. Both values must be provided together. Because MPAM's RMID values are not unique, the CLOSID must be provided when matching the RMID. Signed-off-by: James Morse Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Shaopeng Tan Reviewed-by: Reinette Chatre Reviewed-by: Babu Moger Tested-by: Shaopeng Tan Tested-by: Peter Newman Tested-by: Babu Moger Tested-by: Carl Worth # arm64 Link: https://lore.kernel.org/r/20240213184438.16675-12-james.morse@arm.com Signed-off-by: Borislav Petkov (AMD) --- arch/x86/include/asm/resctrl.h | 18 ++++++++++ arch/x86/kernel/cpu/resctrl/rdtgroup.c | 62 +++++++++++++++++++++------------- 2 files changed, 56 insertions(+), 24 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/resctrl.h b/arch/x86/include/asm/resctrl.h index db4c84dde2d5..1d274dbabc44 100644 --- a/arch/x86/include/asm/resctrl.h +++ b/arch/x86/include/asm/resctrl.h @@ -95,6 +95,24 @@ static inline unsigned int resctrl_arch_round_mon_val(unsigned int val) return val * scale; } +static inline void resctrl_arch_set_closid_rmid(struct task_struct *tsk, + u32 closid, u32 rmid) +{ + WRITE_ONCE(tsk->closid, closid); + WRITE_ONCE(tsk->rmid, rmid); +} + +static inline bool resctrl_arch_match_closid(struct task_struct *tsk, u32 closid) +{ + return READ_ONCE(tsk->closid) == closid; +} + +static inline bool resctrl_arch_match_rmid(struct task_struct *tsk, u32 ignored, + u32 rmid) +{ + return READ_ONCE(tsk->rmid) == rmid; +} + static inline void resctrl_sched_in(struct task_struct *tsk) { if (static_branch_likely(&rdt_enable_key)) diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 8fc46204a6cc..e42cbdf8f6a3 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -102,7 +102,7 @@ void rdt_staged_configs_clear(void) * * Using a global CLOSID across all resources has some advantages and * some drawbacks: - * + We can simply set "current->closid" to assign a task to a resource + * + We can simply set current's closid to assign a task to a resource * group. * + Context switch code can avoid extra memory references deciding which * CLOSID to load into the PQR_ASSOC MSR @@ -574,14 +574,26 @@ static void update_task_closid_rmid(struct task_struct *t) _update_task_closid_rmid(t); } +static bool task_in_rdtgroup(struct task_struct *tsk, struct rdtgroup *rdtgrp) +{ + u32 closid, rmid = rdtgrp->mon.rmid; + + if (rdtgrp->type == RDTCTRL_GROUP) + closid = rdtgrp->closid; + else if (rdtgrp->type == RDTMON_GROUP) + closid = rdtgrp->mon.parent->closid; + else + return false; + + return resctrl_arch_match_closid(tsk, closid) && + resctrl_arch_match_rmid(tsk, closid, rmid); +} + static int __rdtgroup_move_task(struct task_struct *tsk, struct rdtgroup *rdtgrp) { /* If the task is already in rdtgrp, no need to move the task. */ - if ((rdtgrp->type == RDTCTRL_GROUP && tsk->closid == rdtgrp->closid && - tsk->rmid == rdtgrp->mon.rmid) || - (rdtgrp->type == RDTMON_GROUP && tsk->rmid == rdtgrp->mon.rmid && - tsk->closid == rdtgrp->mon.parent->closid)) + if (task_in_rdtgroup(tsk, rdtgrp)) return 0; /* @@ -592,19 +604,19 @@ static int __rdtgroup_move_task(struct task_struct *tsk, * For monitor groups, can move the tasks only from * their parent CTRL group. */ - - if (rdtgrp->type == RDTCTRL_GROUP) { - WRITE_ONCE(tsk->closid, rdtgrp->closid); - WRITE_ONCE(tsk->rmid, rdtgrp->mon.rmid); - } else if (rdtgrp->type == RDTMON_GROUP) { - if (rdtgrp->mon.parent->closid == tsk->closid) { - WRITE_ONCE(tsk->rmid, rdtgrp->mon.rmid); - } else { - rdt_last_cmd_puts("Can't move task to different control group\n"); - return -EINVAL; - } + if (rdtgrp->type == RDTMON_GROUP && + !resctrl_arch_match_closid(tsk, rdtgrp->mon.parent->closid)) { + rdt_last_cmd_puts("Can't move task to different control group\n"); + return -EINVAL; } + if (rdtgrp->type == RDTMON_GROUP) + resctrl_arch_set_closid_rmid(tsk, rdtgrp->mon.parent->closid, + rdtgrp->mon.rmid); + else + resctrl_arch_set_closid_rmid(tsk, rdtgrp->closid, + rdtgrp->mon.rmid); + /* * Ensure the task's closid and rmid are written before determining if * the task is current that will decide if it will be interrupted. @@ -626,14 +638,15 @@ static int __rdtgroup_move_task(struct task_struct *tsk, static bool is_closid_match(struct task_struct *t, struct rdtgroup *r) { - return (rdt_alloc_capable && - (r->type == RDTCTRL_GROUP) && (t->closid == r->closid)); + return (rdt_alloc_capable && (r->type == RDTCTRL_GROUP) && + resctrl_arch_match_closid(t, r->closid)); } static bool is_rmid_match(struct task_struct *t, struct rdtgroup *r) { - return (rdt_mon_capable && - (r->type == RDTMON_GROUP) && (t->rmid == r->mon.rmid)); + return (rdt_mon_capable && (r->type == RDTMON_GROUP) && + resctrl_arch_match_rmid(t, r->mon.parent->closid, + r->mon.rmid)); } /** @@ -884,7 +897,7 @@ int proc_resctrl_show(struct seq_file *s, struct pid_namespace *ns, rdtg->mode != RDT_MODE_EXCLUSIVE) continue; - if (rdtg->closid != tsk->closid) + if (!resctrl_arch_match_closid(tsk, rdtg->closid)) continue; seq_printf(s, "res:%s%s\n", (rdtg == &rdtgroup_default) ? "/" : "", @@ -892,7 +905,8 @@ int proc_resctrl_show(struct seq_file *s, struct pid_namespace *ns, seq_puts(s, "mon:"); list_for_each_entry(crg, &rdtg->mon.crdtgrp_list, mon.crdtgrp_list) { - if (tsk->rmid != crg->mon.rmid) + if (!resctrl_arch_match_rmid(tsk, crg->mon.parent->closid, + crg->mon.rmid)) continue; seq_printf(s, "%s", crg->kn->name); break; @@ -2820,8 +2834,8 @@ static void rdt_move_group_tasks(struct rdtgroup *from, struct rdtgroup *to, for_each_process_thread(p, t) { if (!from || is_closid_match(t, from) || is_rmid_match(t, from)) { - WRITE_ONCE(t->closid, to->closid); - WRITE_ONCE(t->rmid, to->mon.rmid); + resctrl_arch_set_closid_rmid(t, to->closid, + to->mon.rmid); /* * Order the closid/rmid stores above before the loads -- cgit v1.2.3 From a4846aaf39455fe69fce3522b385319383666eef Mon Sep 17 00:00:00 2001 From: James Morse Date: Tue, 13 Feb 2024 18:44:26 +0000 Subject: x86/resctrl: Add cpumask_any_housekeeping() for limbo/overflow The limbo and overflow code picks a CPU to use from the domain's list of online CPUs. Work is then scheduled on these CPUs to maintain the limbo list and any counters that may overflow. cpumask_any() may pick a CPU that is marked nohz_full, which will either penalise the work that CPU was dedicated to, or delay the processing of limbo list or counters that may overflow. Perhaps indefinitely. Delaying the overflow handling will skew the bandwidth values calculated by mba_sc, which expects to be called once a second. Add cpumask_any_housekeeping() as a replacement for cpumask_any() that prefers housekeeping CPUs. This helper will still return a nohz_full CPU if that is the only option. The CPU to use is re-evaluated each time the limbo/overflow work runs. This ensures the work will move off a nohz_full CPU once a housekeeping CPU is available. Signed-off-by: James Morse Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Shaopeng Tan Reviewed-by: Reinette Chatre Reviewed-by: Babu Moger Tested-by: Shaopeng Tan Tested-by: Peter Newman Tested-by: Babu Moger Tested-by: Carl Worth # arm64 Link: https://lore.kernel.org/r/20240213184438.16675-13-james.morse@arm.com Signed-off-by: Borislav Petkov (AMD) --- arch/x86/kernel/cpu/resctrl/internal.h | 24 ++++++++++++++++++++++++ arch/x86/kernel/cpu/resctrl/monitor.c | 20 +++++++++++++------- 2 files changed, 37 insertions(+), 7 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index b7b9d9230bef..81f5de916db8 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -7,6 +7,7 @@ #include #include #include +#include #include @@ -55,6 +56,29 @@ /* Max event bits supported */ #define MAX_EVT_CONFIG_BITS GENMASK(6, 0) +/** + * cpumask_any_housekeeping() - Choose any CPU in @mask, preferring those that + * aren't marked nohz_full + * @mask: The mask to pick a CPU from. + * + * Returns a CPU in @mask. If there are housekeeping CPUs that don't use + * nohz_full, these are preferred. + */ +static inline unsigned int cpumask_any_housekeeping(const struct cpumask *mask) +{ + unsigned int cpu, hk_cpu; + + cpu = cpumask_any(mask); + if (!tick_nohz_full_cpu(cpu)) + return cpu; + + hk_cpu = cpumask_nth_andnot(0, mask, tick_nohz_full_mask); + if (hk_cpu < nr_cpu_ids) + cpu = hk_cpu; + + return cpu; +} + struct rdt_fs_context { struct kernfs_fs_context kfc; bool enable_cdpl2; diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index 101f1b112d17..38f85e53ca93 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -761,7 +761,6 @@ static void mbm_update(struct rdt_resource *r, struct rdt_domain *d, void cqm_handle_limbo(struct work_struct *work) { unsigned long delay = msecs_to_jiffies(CQM_LIMBOCHECK_INTERVAL); - int cpu = smp_processor_id(); struct rdt_domain *d; mutex_lock(&rdtgroup_mutex); @@ -770,8 +769,11 @@ void cqm_handle_limbo(struct work_struct *work) __check_limbo(d, false); - if (has_busy_rmid(d)) - schedule_delayed_work_on(cpu, &d->cqm_limbo, delay); + if (has_busy_rmid(d)) { + d->cqm_work_cpu = cpumask_any_housekeeping(&d->cpu_mask); + schedule_delayed_work_on(d->cqm_work_cpu, &d->cqm_limbo, + delay); + } mutex_unlock(&rdtgroup_mutex); } @@ -781,7 +783,7 @@ void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms) unsigned long delay = msecs_to_jiffies(delay_ms); int cpu; - cpu = cpumask_any(&dom->cpu_mask); + cpu = cpumask_any_housekeeping(&dom->cpu_mask); dom->cqm_work_cpu = cpu; schedule_delayed_work_on(cpu, &dom->cqm_limbo, delay); @@ -791,7 +793,6 @@ void mbm_handle_overflow(struct work_struct *work) { unsigned long delay = msecs_to_jiffies(MBM_OVERFLOW_INTERVAL); struct rdtgroup *prgrp, *crgrp; - int cpu = smp_processor_id(); struct list_head *head; struct rdt_resource *r; struct rdt_domain *d; @@ -815,7 +816,12 @@ void mbm_handle_overflow(struct work_struct *work) update_mba_bw(prgrp, d); } - schedule_delayed_work_on(cpu, &d->mbm_over, delay); + /* + * Re-check for housekeeping CPUs. This allows the overflow handler to + * move off a nohz_full CPU quickly. + */ + d->mbm_work_cpu = cpumask_any_housekeeping(&d->cpu_mask); + schedule_delayed_work_on(d->mbm_work_cpu, &d->mbm_over, delay); out_unlock: mutex_unlock(&rdtgroup_mutex); @@ -828,7 +834,7 @@ void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms) if (!static_branch_likely(&rdt_mon_enable_key)) return; - cpu = cpumask_any(&dom->cpu_mask); + cpu = cpumask_any_housekeeping(&dom->cpu_mask); dom->mbm_work_cpu = cpu; schedule_delayed_work_on(cpu, &dom->mbm_over, delay); } -- cgit v1.2.3 From 09909e098113bed99c9f63e1df89073e92c69891 Mon Sep 17 00:00:00 2001 From: James Morse Date: Tue, 13 Feb 2024 18:44:27 +0000 Subject: x86/resctrl: Queue mon_event_read() instead of sending an IPI Intel is blessed with an abundance of monitors, one per RMID, that can be read from any CPU in the domain. MPAMs monitors reside in the MMIO MSC, the number implemented is up to the manufacturer. This means when there are fewer monitors than needed, they need to be allocated and freed. MPAM's CSU monitors are used to back the 'llc_occupancy' monitor file. The CSU counter is allowed to return 'not ready' for a small number of micro-seconds after programming. To allow one CSU hardware monitor to be used for multiple control or monitor groups, the CPU accessing the monitor needs to be able to block when configuring and reading the counter. Worse, the domain may be broken up into slices, and the MMIO accesses for each slice may need performing from different CPUs. These two details mean MPAMs monitor code needs to be able to sleep, and IPI another CPU in the domain to read from a resource that has been sliced. mon_event_read() already invokes mon_event_count() via IPI, which means this isn't possible. On systems using nohz-full, some CPUs need to be interrupted to run kernel work as they otherwise stay in user-space running realtime workloads. Interrupting these CPUs should be avoided, and scheduling work on them may never complete. Change mon_event_read() to pick a housekeeping CPU, (one that is not using nohz_full) and schedule mon_event_count() and wait. If all the CPUs in a domain are using nohz-full, then an IPI is used as the fallback. This function is only used in response to a user-space filesystem request (not the timing sensitive overflow code). This allows MPAM to hide the slice behaviour from resctrl, and to keep the monitor-allocation in monitor.c. When the IPI fallback is used on machines where MPAM needs to make an access on multiple CPUs, the counter read will always fail. Signed-off-by: James Morse Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Shaopeng Tan Reviewed-by: Peter Newman Reviewed-by: Reinette Chatre Reviewed-by: Babu Moger Tested-by: Shaopeng Tan Tested-by: Peter Newman Tested-by: Babu Moger Tested-by: Carl Worth # arm64 Link: https://lore.kernel.org/r/20240213184438.16675-14-james.morse@arm.com Signed-off-by: Borislav Petkov (AMD) --- arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 26 ++++++++++++++++++++++++-- arch/x86/kernel/cpu/resctrl/monitor.c | 2 +- 2 files changed, 25 insertions(+), 3 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c index beccb0e87ba7..e933e1cdb1c9 100644 --- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c +++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c @@ -19,6 +19,8 @@ #include #include #include +#include + #include "internal.h" /* @@ -522,12 +524,21 @@ int rdtgroup_schemata_show(struct kernfs_open_file *of, return ret; } +static int smp_mon_event_count(void *arg) +{ + mon_event_count(arg); + + return 0; +} + void mon_event_read(struct rmid_read *rr, struct rdt_resource *r, struct rdt_domain *d, struct rdtgroup *rdtgrp, int evtid, int first) { + int cpu; + /* - * setup the parameters to send to the IPI to read the data. + * Setup the parameters to pass to mon_event_count() to read the data. */ rr->rgrp = rdtgrp; rr->evtid = evtid; @@ -536,7 +547,18 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r, rr->val = 0; rr->first = first; - smp_call_function_any(&d->cpu_mask, mon_event_count, rr, 1); + cpu = cpumask_any_housekeeping(&d->cpu_mask); + + /* + * cpumask_any_housekeeping() prefers housekeeping CPUs, but + * are all the CPUs nohz_full? If yes, pick a CPU to IPI. + * MPAM's resctrl_arch_rmid_read() is unable to read the + * counters on some platforms if its called in IRQ context. + */ + if (tick_nohz_full_cpu(cpu)) + smp_call_function_any(&d->cpu_mask, mon_event_count, rr, 1); + else + smp_call_on_cpu(cpu, smp_mon_event_count, rr, false); } int rdtgroup_mondata_show(struct seq_file *m, void *arg) diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index 38f85e53ca93..fd060ef86f38 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -585,7 +585,7 @@ static void mbm_bw_count(u32 closid, u32 rmid, struct rmid_read *rr) } /* - * This is called via IPI to read the CQM/MBM counters + * This is scheduled by mon_event_read() to read the CQM/MBM counters * on a domain. */ void mon_event_count(void *info) -- cgit v1.2.3 From 6fde1424f29b151b9dc8c660eecf4d1645facea5 Mon Sep 17 00:00:00 2001 From: James Morse Date: Tue, 13 Feb 2024 18:44:28 +0000 Subject: x86/resctrl: Allow resctrl_arch_rmid_read() to sleep MPAM's cache occupancy counters can take a little while to settle once the monitor has been configured. The maximum settling time is described to the driver via a firmware table. The value could be large enough that it makes sense to sleep. To avoid exposing this to resctrl, it should be hidden behind MPAM's resctrl_arch_rmid_read(). resctrl_arch_rmid_read() may be called via IPI meaning it is unable to sleep. In this case, it should return an error if it needs to sleep. This will only affect MPAM platforms where the cache occupancy counter isn't available immediately, nohz_full is in use, and there are no housekeeping CPUs in the necessary domain. There are three callers of resctrl_arch_rmid_read(): __mon_event_count() and __check_limbo() are both called from a non-migrateable context. mon_event_read() invokes __mon_event_count() using smp_call_on_cpu(), which adds work to the target CPUs workqueue. rdtgroup_mutex() is held, meaning this cannot race with the resctrl cpuhp callback. __check_limbo() is invoked via schedule_delayed_work_on() also adds work to a per-cpu workqueue. The remaining call is add_rmid_to_limbo() which is called in response to a user-space syscall that frees an RMID. This opportunistically reads the LLC occupancy counter on the current domain to see if the RMID is over the dirty threshold. This has to disable preemption to avoid reading the wrong domain's value. Disabling preemption here prevents resctrl_arch_rmid_read() from sleeping. add_rmid_to_limbo() walks each domain, but only reads the counter on one domain. If the system has more than one domain, the RMID will always be added to the limbo list. If the RMIDs usage was not over the threshold, it will be removed from the list when __check_limbo() runs. Make this the default behaviour. Free RMIDs are always added to the limbo list for each domain. The user visible effect of this is that a clean RMID is not available for re-allocation immediately after 'rmdir()' completes. This behaviour was never portable as it never happened on a machine with multiple domains. Removing this path allows resctrl_arch_rmid_read() to sleep if its called with interrupts unmasked. Document this is the expected behaviour, and add a might_sleep() annotation to catch changes that won't work on arm64. Signed-off-by: James Morse Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Shaopeng Tan Reviewed-by: Reinette Chatre Reviewed-by: Babu Moger Tested-by: Shaopeng Tan Tested-by: Peter Newman Tested-by: Babu Moger Tested-by: Carl Worth # arm64 Link: https://lore.kernel.org/r/20240213184438.16675-15-james.morse@arm.com Signed-off-by: Borislav Petkov (AMD) --- arch/x86/kernel/cpu/resctrl/monitor.c | 25 +++++-------------------- include/linux/resctrl.h | 23 ++++++++++++++++++++++- 2 files changed, 27 insertions(+), 21 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index fd060ef86f38..e8aeff6673ea 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -277,6 +277,8 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d, u64 msr_val, chunks; int ret; + resctrl_arch_rmid_read_context_check(); + if (!cpumask_test_cpu(smp_processor_id(), &d->cpu_mask)) return -EINVAL; @@ -455,8 +457,6 @@ static void add_rmid_to_limbo(struct rmid_entry *entry) { struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; struct rdt_domain *d; - int cpu, err; - u64 val = 0; u32 idx; lockdep_assert_held(&rdtgroup_mutex); @@ -464,17 +464,7 @@ static void add_rmid_to_limbo(struct rmid_entry *entry) idx = resctrl_arch_rmid_idx_encode(entry->closid, entry->rmid); entry->busy = 0; - cpu = get_cpu(); list_for_each_entry(d, &r->domains, list) { - if (cpumask_test_cpu(cpu, &d->cpu_mask)) { - err = resctrl_arch_rmid_read(r, d, entry->closid, - entry->rmid, - QOS_L3_OCCUP_EVENT_ID, - &val); - if (err || val <= resctrl_rmid_realloc_threshold) - continue; - } - /* * For the first limbo RMID in the domain, * setup up the limbo worker. @@ -484,15 +474,10 @@ static void add_rmid_to_limbo(struct rmid_entry *entry) set_bit(idx, d->rmid_busy_llc); entry->busy++; } - put_cpu(); - if (entry->busy) { - rmid_limbo_count++; - if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) - closid_num_dirty_rmid[entry->closid]++; - } else { - list_add_tail(&entry->list, &rmid_free_lru); - } + rmid_limbo_count++; + if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) + closid_num_dirty_rmid[entry->closid]++; } void free_rmid(u32 closid, u32 rmid) diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index bd4ec22b5a96..8649fc84aac2 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -236,7 +236,12 @@ void resctrl_offline_domain(struct rdt_resource *r, struct rdt_domain *d); * @eventid: eventid to read, e.g. L3 occupancy. * @val: result of the counter read in bytes. * - * Call from process context on a CPU that belongs to domain @d. + * Some architectures need to sleep when first programming some of the counters. + * (specifically: arm64's MPAM cache occupancy counters can return 'not ready' + * for a short period of time). Call from a non-migrateable process context on + * a CPU that belongs to domain @d. e.g. use smp_call_on_cpu() or + * schedule_work_on(). This function can be called with interrupts masked, + * e.g. using smp_call_function_any(), but may consistently return an error. * * Return: * 0 on success, or -EIO, -EINVAL etc on error. @@ -245,6 +250,22 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d, u32 closid, u32 rmid, enum resctrl_event_id eventid, u64 *val); +/** + * resctrl_arch_rmid_read_context_check() - warn about invalid contexts + * + * When built with CONFIG_DEBUG_ATOMIC_SLEEP generate a warning when + * resctrl_arch_rmid_read() is called with preemption disabled. + * + * The contract with resctrl_arch_rmid_read() is that if interrupts + * are unmasked, it can sleep. This allows NOHZ_FULL systems to use an + * IPI, (and fail if the call needed to sleep), while most of the time + * the work is scheduled, allowing the call to sleep. + */ +static inline void resctrl_arch_rmid_read_context_check(void) +{ + if (!irqs_disabled()) + might_sleep(); +} /** * resctrl_arch_reset_rmid() - Reset any private state associated with rmid -- cgit v1.2.3 From e557999f80a5ee4ec812f594ab42bb76c3ec4eb2 Mon Sep 17 00:00:00 2001 From: James Morse Date: Tue, 13 Feb 2024 18:44:29 +0000 Subject: x86/resctrl: Allow arch to allocate memory needed in resctrl_arch_rmid_read() Depending on the number of monitors available, Arm's MPAM may need to allocate a monitor prior to reading the counter value. Allocating a contended resource may involve sleeping. __check_limbo() and mon_event_count() each make multiple calls to resctrl_arch_rmid_read(), to avoid extra work on contended systems, the allocation should be valid for multiple invocations of resctrl_arch_rmid_read(). The memory or hardware allocated is not specific to a domain. Add arch hooks for this allocation, which need calling before resctrl_arch_rmid_read(). The allocated monitor is passed to resctrl_arch_rmid_read(), then freed again afterwards. The helper can be called on any CPU, and can sleep. Signed-off-by: James Morse Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Shaopeng Tan Reviewed-by: Reinette Chatre Reviewed-by: Babu Moger Tested-by: Shaopeng Tan Tested-by: Peter Newman Tested-by: Babu Moger Tested-by: Carl Worth # arm64 Link: https://lore.kernel.org/r/20240213184438.16675-16-james.morse@arm.com Signed-off-by: Borislav Petkov (AMD) --- arch/x86/include/asm/resctrl.h | 11 ++++++++++ arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 7 +++++++ arch/x86/kernel/cpu/resctrl/internal.h | 1 + arch/x86/kernel/cpu/resctrl/monitor.c | 35 ++++++++++++++++++++++++++++--- include/linux/resctrl.h | 5 ++++- 5 files changed, 55 insertions(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/resctrl.h b/arch/x86/include/asm/resctrl.h index 1d274dbabc44..29c4cc343787 100644 --- a/arch/x86/include/asm/resctrl.h +++ b/arch/x86/include/asm/resctrl.h @@ -136,6 +136,17 @@ static inline u32 resctrl_arch_rmid_idx_encode(u32 ignored, u32 rmid) return rmid; } +/* x86 can always read an rmid, nothing needs allocating */ +struct rdt_resource; +static inline void *resctrl_arch_mon_ctx_alloc(struct rdt_resource *r, int evtid) +{ + might_sleep(); + return NULL; +}; + +static inline void resctrl_arch_mon_ctx_free(struct rdt_resource *r, int evtid, + void *ctx) { }; + void resctrl_cpu_detect(struct cpuinfo_x86 *c); #else diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c index e933e1cdb1c9..52fa0e14cb86 100644 --- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c +++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c @@ -546,6 +546,11 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r, rr->d = d; rr->val = 0; rr->first = first; + rr->arch_mon_ctx = resctrl_arch_mon_ctx_alloc(r, evtid); + if (IS_ERR(rr->arch_mon_ctx)) { + rr->err = -EINVAL; + return; + } cpu = cpumask_any_housekeeping(&d->cpu_mask); @@ -559,6 +564,8 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r, smp_call_function_any(&d->cpu_mask, mon_event_count, rr, 1); else smp_call_on_cpu(cpu, smp_mon_event_count, rr, false); + + resctrl_arch_mon_ctx_free(r, evtid, rr->arch_mon_ctx); } int rdtgroup_mondata_show(struct seq_file *m, void *arg) diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index 81f5de916db8..e089d1a1a055 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -137,6 +137,7 @@ struct rmid_read { bool first; int err; u64 val; + void *arch_mon_ctx; }; extern bool rdt_alloc_capable; diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index e8aeff6673ea..9b503e6ac490 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -269,7 +269,7 @@ static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width) int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d, u32 unused, u32 rmid, enum resctrl_event_id eventid, - u64 *val) + u64 *val, void *ignored) { struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d); @@ -324,9 +324,17 @@ void __check_limbo(struct rdt_domain *d, bool force_free) u32 idx_limit = resctrl_arch_system_num_rmid_idx(); struct rmid_entry *entry; u32 idx, cur_idx = 1; + void *arch_mon_ctx; bool rmid_dirty; u64 val = 0; + arch_mon_ctx = resctrl_arch_mon_ctx_alloc(r, QOS_L3_OCCUP_EVENT_ID); + if (IS_ERR(arch_mon_ctx)) { + pr_warn_ratelimited("Failed to allocate monitor context: %ld", + PTR_ERR(arch_mon_ctx)); + return; + } + /* * Skip RMID 0 and start from RMID 1 and check all the RMIDs that * are marked as busy for occupancy < threshold. If the occupancy @@ -340,7 +348,8 @@ void __check_limbo(struct rdt_domain *d, bool force_free) entry = __rmid_entry(idx); if (resctrl_arch_rmid_read(r, d, entry->closid, entry->rmid, - QOS_L3_OCCUP_EVENT_ID, &val)) { + QOS_L3_OCCUP_EVENT_ID, &val, + arch_mon_ctx)) { rmid_dirty = true; } else { rmid_dirty = (val >= resctrl_rmid_realloc_threshold); @@ -353,6 +362,8 @@ void __check_limbo(struct rdt_domain *d, bool force_free) } cur_idx = idx + 1; } + + resctrl_arch_mon_ctx_free(r, QOS_L3_OCCUP_EVENT_ID, arch_mon_ctx); } bool has_busy_rmid(struct rdt_domain *d) @@ -533,7 +544,7 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr) } rr->err = resctrl_arch_rmid_read(rr->r, rr->d, closid, rmid, rr->evtid, - &tval); + &tval, rr->arch_mon_ctx); if (rr->err) return rr->err; @@ -722,11 +733,27 @@ static void mbm_update(struct rdt_resource *r, struct rdt_domain *d, if (is_mbm_total_enabled()) { rr.evtid = QOS_L3_MBM_TOTAL_EVENT_ID; rr.val = 0; + rr.arch_mon_ctx = resctrl_arch_mon_ctx_alloc(rr.r, rr.evtid); + if (IS_ERR(rr.arch_mon_ctx)) { + pr_warn_ratelimited("Failed to allocate monitor context: %ld", + PTR_ERR(rr.arch_mon_ctx)); + return; + } + __mon_event_count(closid, rmid, &rr); + + resctrl_arch_mon_ctx_free(rr.r, rr.evtid, rr.arch_mon_ctx); } if (is_mbm_local_enabled()) { rr.evtid = QOS_L3_MBM_LOCAL_EVENT_ID; rr.val = 0; + rr.arch_mon_ctx = resctrl_arch_mon_ctx_alloc(rr.r, rr.evtid); + if (IS_ERR(rr.arch_mon_ctx)) { + pr_warn_ratelimited("Failed to allocate monitor context: %ld", + PTR_ERR(rr.arch_mon_ctx)); + return; + } + __mon_event_count(closid, rmid, &rr); /* @@ -736,6 +763,8 @@ static void mbm_update(struct rdt_resource *r, struct rdt_domain *d, */ if (is_mba_sc(NULL)) mbm_bw_count(closid, rmid, &rr); + + resctrl_arch_mon_ctx_free(rr.r, rr.evtid, rr.arch_mon_ctx); } } diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index 8649fc84aac2..bf460c912bf5 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -235,6 +235,9 @@ void resctrl_offline_domain(struct rdt_resource *r, struct rdt_domain *d); * @rmid: rmid of the counter to read. * @eventid: eventid to read, e.g. L3 occupancy. * @val: result of the counter read in bytes. + * @arch_mon_ctx: An architecture specific value from + * resctrl_arch_mon_ctx_alloc(), for MPAM this identifies + * the hardware monitor allocated for this read request. * * Some architectures need to sleep when first programming some of the counters. * (specifically: arm64's MPAM cache occupancy counters can return 'not ready' @@ -248,7 +251,7 @@ void resctrl_offline_domain(struct rdt_resource *r, struct rdt_domain *d); */ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d, u32 closid, u32 rmid, enum resctrl_event_id eventid, - u64 *val); + u64 *val, void *arch_mon_ctx); /** * resctrl_arch_rmid_read_context_check() - warn about invalid contexts -- cgit v1.2.3 From 13e5769debf09588543db83836c524148873929f Mon Sep 17 00:00:00 2001 From: James Morse Date: Tue, 13 Feb 2024 18:44:30 +0000 Subject: x86/resctrl: Make resctrl_mounted checks explicit The rdt_enable_key is switched when resctrl is mounted, and used to prevent a second mount of the filesystem. It also enables the architecture's context switch code. This requires another architecture to have the same set of static keys, as resctrl depends on them too. The existing users of these static keys are implicitly also checking if the filesystem is mounted. Make the resctrl_mounted checks explicit: resctrl can keep track of whether it has been mounted once. This doesn't need to be combined with whether the arch code is context switching the CLOSID. rdt_mon_enable_key is never used just to test that resctrl is mounted, but does also have this implication. Add a resctrl_mounted to all uses of rdt_mon_enable_key. This will allow the static key changing to be moved behind resctrl_arch_ calls. Signed-off-by: James Morse Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Shaopeng Tan Reviewed-by: Reinette Chatre Reviewed-by: Babu Moger Tested-by: Shaopeng Tan Tested-by: Peter Newman Tested-by: Babu Moger Tested-by: Carl Worth # arm64 Link: https://lore.kernel.org/r/20240213184438.16675-17-james.morse@arm.com Signed-off-by: Borislav Petkov (AMD) --- arch/x86/kernel/cpu/resctrl/internal.h | 1 + arch/x86/kernel/cpu/resctrl/monitor.c | 12 ++++++++++-- arch/x86/kernel/cpu/resctrl/rdtgroup.c | 23 +++++++++++++++++------ 3 files changed, 28 insertions(+), 8 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index e089d1a1a055..9bfda6963794 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -144,6 +144,7 @@ extern bool rdt_alloc_capable; extern bool rdt_mon_capable; extern unsigned int rdt_mon_features; extern struct list_head resctrl_schema_all; +extern bool resctrl_mounted; enum rdt_group_type { RDTCTRL_GROUP = 0, diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index 9b503e6ac490..d5d8a58d96f2 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -813,7 +813,11 @@ void mbm_handle_overflow(struct work_struct *work) mutex_lock(&rdtgroup_mutex); - if (!static_branch_likely(&rdt_mon_enable_key)) + /* + * If the filesystem has been unmounted this work no longer needs to + * run. + */ + if (!resctrl_mounted || !static_branch_likely(&rdt_mon_enable_key)) goto out_unlock; r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; @@ -846,7 +850,11 @@ void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms) unsigned long delay = msecs_to_jiffies(delay_ms); int cpu; - if (!static_branch_likely(&rdt_mon_enable_key)) + /* + * When a domain comes online there is no guarantee the filesystem is + * mounted. If not, there is no need to catch counter overflow. + */ + if (!resctrl_mounted || !static_branch_likely(&rdt_mon_enable_key)) return; cpu = cpumask_any_housekeeping(&dom->cpu_mask); dom->mbm_work_cpu = cpu; diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index e42cbdf8f6a3..857fbbc3c839 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -42,6 +42,9 @@ LIST_HEAD(rdt_all_groups); /* list of entries for the schemata file */ LIST_HEAD(resctrl_schema_all); +/* The filesystem can only be mounted once. */ +bool resctrl_mounted; + /* Kernel fs node for "info" directory under root */ static struct kernfs_node *kn_info; @@ -881,7 +884,7 @@ int proc_resctrl_show(struct seq_file *s, struct pid_namespace *ns, mutex_lock(&rdtgroup_mutex); /* Return empty if resctrl has not been mounted. */ - if (!static_branch_unlikely(&rdt_enable_key)) { + if (!resctrl_mounted) { seq_puts(s, "res:\nmon:\n"); goto unlock; } @@ -2608,7 +2611,7 @@ static int rdt_get_tree(struct fs_context *fc) /* * resctrl file system can only be mounted once. */ - if (static_branch_unlikely(&rdt_enable_key)) { + if (resctrl_mounted) { ret = -EBUSY; goto out; } @@ -2669,8 +2672,10 @@ static int rdt_get_tree(struct fs_context *fc) if (rdt_mon_capable) static_branch_enable_cpuslocked(&rdt_mon_enable_key); - if (rdt_alloc_capable || rdt_mon_capable) + if (rdt_alloc_capable || rdt_mon_capable) { static_branch_enable_cpuslocked(&rdt_enable_key); + resctrl_mounted = true; + } if (is_mbm_enabled()) { r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; @@ -2944,6 +2949,7 @@ static void rdt_kill_sb(struct super_block *sb) static_branch_disable_cpuslocked(&rdt_alloc_enable_key); static_branch_disable_cpuslocked(&rdt_mon_enable_key); static_branch_disable_cpuslocked(&rdt_enable_key); + resctrl_mounted = false; kernfs_kill_sb(sb); mutex_unlock(&rdtgroup_mutex); cpus_read_unlock(); @@ -3913,7 +3919,7 @@ void resctrl_offline_domain(struct rdt_resource *r, struct rdt_domain *d) * If resctrl is mounted, remove all the * per domain monitor data directories. */ - if (static_branch_unlikely(&rdt_mon_enable_key)) + if (resctrl_mounted && static_branch_unlikely(&rdt_mon_enable_key)) rmdir_mondata_subdir_allrdtgrp(r, d->id); if (is_mbm_enabled()) @@ -3990,8 +3996,13 @@ int resctrl_online_domain(struct rdt_resource *r, struct rdt_domain *d) if (is_llc_occupancy_enabled()) INIT_DELAYED_WORK(&d->cqm_limbo, cqm_handle_limbo); - /* If resctrl is mounted, add per domain monitor data directories. */ - if (static_branch_unlikely(&rdt_mon_enable_key)) + /* + * If the filesystem is not mounted then only the default resource group + * exists. Creation of its directories is deferred until mount time + * by rdt_get_tree() calling mkdir_mondata_all(). + * If resctrl is mounted, add per domain monitor data directories. + */ + if (resctrl_mounted && static_branch_unlikely(&rdt_mon_enable_key)) mkdir_mondata_subdir_allrdtgrp(r, d); return 0; -- cgit v1.2.3 From 5db6a4a75c95f6967d57906ba7b82756d1985d63 Mon Sep 17 00:00:00 2001 From: James Morse Date: Tue, 13 Feb 2024 18:44:31 +0000 Subject: x86/resctrl: Move alloc/mon static keys into helpers resctrl enables three static keys depending on the features it has enabled. Another architecture's context switch code may look different, any static keys that control it should be buried behind helpers. Move the alloc/mon logic into arch-specific helpers as a preparatory step for making the rdt_enable_key's status something the arch code decides. This means other architectures don't have to mirror the static keys. Signed-off-by: James Morse Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Shaopeng Tan Reviewed-by: Reinette Chatre Reviewed-by: Babu Moger Tested-by: Shaopeng Tan Tested-by: Peter Newman Tested-by: Babu Moger Tested-by: Carl Worth # arm64 Link: https://lore.kernel.org/r/20240213184438.16675-18-james.morse@arm.com Signed-off-by: Borislav Petkov (AMD) --- arch/x86/include/asm/resctrl.h | 20 ++++++++++++++++++++ arch/x86/kernel/cpu/resctrl/internal.h | 5 ----- arch/x86/kernel/cpu/resctrl/rdtgroup.c | 8 ++++---- 3 files changed, 24 insertions(+), 9 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/resctrl.h b/arch/x86/include/asm/resctrl.h index 29c4cc343787..3c9137b6ad4f 100644 --- a/arch/x86/include/asm/resctrl.h +++ b/arch/x86/include/asm/resctrl.h @@ -42,6 +42,26 @@ DECLARE_STATIC_KEY_FALSE(rdt_enable_key); DECLARE_STATIC_KEY_FALSE(rdt_alloc_enable_key); DECLARE_STATIC_KEY_FALSE(rdt_mon_enable_key); +static inline void resctrl_arch_enable_alloc(void) +{ + static_branch_enable_cpuslocked(&rdt_alloc_enable_key); +} + +static inline void resctrl_arch_disable_alloc(void) +{ + static_branch_disable_cpuslocked(&rdt_alloc_enable_key); +} + +static inline void resctrl_arch_enable_mon(void) +{ + static_branch_enable_cpuslocked(&rdt_mon_enable_key); +} + +static inline void resctrl_arch_disable_mon(void) +{ + static_branch_disable_cpuslocked(&rdt_mon_enable_key); +} + /* * __resctrl_sched_in() - Writes the task's CLOSid/RMID to IA32_PQR_MSR * diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index 9bfda6963794..78580855139d 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -94,9 +94,6 @@ static inline struct rdt_fs_context *rdt_fc2context(struct fs_context *fc) return container_of(kfc, struct rdt_fs_context, kfc); } -DECLARE_STATIC_KEY_FALSE(rdt_enable_key); -DECLARE_STATIC_KEY_FALSE(rdt_mon_enable_key); - /** * struct mon_evt - Entry in the event list of a resource * @evtid: event id @@ -452,8 +449,6 @@ extern struct mutex rdtgroup_mutex; extern struct rdt_hw_resource rdt_resources_all[]; extern struct rdtgroup rdtgroup_default; -DECLARE_STATIC_KEY_FALSE(rdt_alloc_enable_key); - extern struct dentry *debugfs_resctrl; enum resctrl_res_level { diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 857fbbc3c839..231207f09e04 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -2668,9 +2668,9 @@ static int rdt_get_tree(struct fs_context *fc) goto out_psl; if (rdt_alloc_capable) - static_branch_enable_cpuslocked(&rdt_alloc_enable_key); + resctrl_arch_enable_alloc(); if (rdt_mon_capable) - static_branch_enable_cpuslocked(&rdt_mon_enable_key); + resctrl_arch_enable_mon(); if (rdt_alloc_capable || rdt_mon_capable) { static_branch_enable_cpuslocked(&rdt_enable_key); @@ -2946,8 +2946,8 @@ static void rdt_kill_sb(struct super_block *sb) rdtgroup_default.mode = RDT_MODE_SHAREABLE; schemata_list_destroy(); rdtgroup_destroy_root(); - static_branch_disable_cpuslocked(&rdt_alloc_enable_key); - static_branch_disable_cpuslocked(&rdt_mon_enable_key); + resctrl_arch_disable_alloc(); + resctrl_arch_disable_mon(); static_branch_disable_cpuslocked(&rdt_enable_key); resctrl_mounted = false; kernfs_kill_sb(sb); -- cgit v1.2.3 From 0a2f4d9b548c5b1e2e3fcfa966f5d47b1cacff01 Mon Sep 17 00:00:00 2001 From: James Morse Date: Tue, 13 Feb 2024 18:44:32 +0000 Subject: x86/resctrl: Make rdt_enable_key the arch's decision to switch rdt_enable_key is switched when resctrl is mounted. It was also previously used to prevent a second mount of the filesystem. Any other architecture that wants to support resctrl has to provide identical static keys. Now that there are helpers for enabling and disabling the alloc/mon keys, resctrl doesn't need to switch this extra key, it can be done by the arch code. Use the static-key increment and decrement helpers, and change resctrl to ensure the calls are balanced. Signed-off-by: James Morse Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Shaopeng Tan Reviewed-by: Reinette Chatre Reviewed-by: Babu Moger Tested-by: Shaopeng Tan Tested-by: Peter Newman Tested-by: Babu Moger Tested-by: Carl Worth # arm64 Link: https://lore.kernel.org/r/20240213184438.16675-19-james.morse@arm.com Signed-off-by: Borislav Petkov (AMD) --- arch/x86/include/asm/resctrl.h | 4 ++++ arch/x86/kernel/cpu/resctrl/rdtgroup.c | 11 +++++------ 2 files changed, 9 insertions(+), 6 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/resctrl.h b/arch/x86/include/asm/resctrl.h index 3c9137b6ad4f..b74aa34dc9e8 100644 --- a/arch/x86/include/asm/resctrl.h +++ b/arch/x86/include/asm/resctrl.h @@ -45,21 +45,25 @@ DECLARE_STATIC_KEY_FALSE(rdt_mon_enable_key); static inline void resctrl_arch_enable_alloc(void) { static_branch_enable_cpuslocked(&rdt_alloc_enable_key); + static_branch_inc_cpuslocked(&rdt_enable_key); } static inline void resctrl_arch_disable_alloc(void) { static_branch_disable_cpuslocked(&rdt_alloc_enable_key); + static_branch_dec_cpuslocked(&rdt_enable_key); } static inline void resctrl_arch_enable_mon(void) { static_branch_enable_cpuslocked(&rdt_mon_enable_key); + static_branch_inc_cpuslocked(&rdt_enable_key); } static inline void resctrl_arch_disable_mon(void) { static_branch_disable_cpuslocked(&rdt_mon_enable_key); + static_branch_dec_cpuslocked(&rdt_enable_key); } /* diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 231207f09e04..7e57ac9d81f7 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -2672,10 +2672,8 @@ static int rdt_get_tree(struct fs_context *fc) if (rdt_mon_capable) resctrl_arch_enable_mon(); - if (rdt_alloc_capable || rdt_mon_capable) { - static_branch_enable_cpuslocked(&rdt_enable_key); + if (rdt_alloc_capable || rdt_mon_capable) resctrl_mounted = true; - } if (is_mbm_enabled()) { r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; @@ -2946,9 +2944,10 @@ static void rdt_kill_sb(struct super_block *sb) rdtgroup_default.mode = RDT_MODE_SHAREABLE; schemata_list_destroy(); rdtgroup_destroy_root(); - resctrl_arch_disable_alloc(); - resctrl_arch_disable_mon(); - static_branch_disable_cpuslocked(&rdt_enable_key); + if (rdt_alloc_capable) + resctrl_arch_disable_alloc(); + if (rdt_mon_capable) + resctrl_arch_disable_mon(); resctrl_mounted = false; kernfs_kill_sb(sb); mutex_unlock(&rdtgroup_mutex); -- cgit v1.2.3 From 30017b60706c2ba72a0a4da7d5ef8f5fa95a2f01 Mon Sep 17 00:00:00 2001 From: James Morse Date: Tue, 13 Feb 2024 18:44:33 +0000 Subject: x86/resctrl: Add helpers for system wide mon/alloc capable resctrl reads rdt_alloc_capable or rdt_mon_capable to determine whether any of the resources support the corresponding features. resctrl also uses the static keys that affect the architecture's context-switch code to determine the same thing. This forces another architecture to have the same static keys. As the static key is enabled based on the capable flag, and none of the filesystem uses of these are in the scheduler path, move the capable flags behind helpers, and use these in the filesystem code instead of the static key. After this change, only the architecture code manages and uses the static keys to ensure __resctrl_sched_in() does not need runtime checks. This avoids multiple architectures having to define the same static keys. Cases where the static key implicitly tested if the resctrl filesystem was mounted all have an explicit check now. Signed-off-by: James Morse Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Shaopeng Tan Reviewed-by: Reinette Chatre Reviewed-by: Babu Moger Tested-by: Shaopeng Tan Tested-by: Peter Newman Tested-by: Babu Moger Tested-by: Carl Worth # arm64 Link: https://lore.kernel.org/r/20240213184438.16675-20-james.morse@arm.com Signed-off-by: Borislav Petkov (AMD) --- arch/x86/include/asm/resctrl.h | 13 +++++++++++ arch/x86/kernel/cpu/resctrl/internal.h | 2 -- arch/x86/kernel/cpu/resctrl/monitor.c | 4 ++-- arch/x86/kernel/cpu/resctrl/pseudo_lock.c | 6 ++--- arch/x86/kernel/cpu/resctrl/rdtgroup.c | 38 +++++++++++++++---------------- 5 files changed, 37 insertions(+), 26 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/resctrl.h b/arch/x86/include/asm/resctrl.h index b74aa34dc9e8..12dbd2588ca7 100644 --- a/arch/x86/include/asm/resctrl.h +++ b/arch/x86/include/asm/resctrl.h @@ -38,10 +38,18 @@ struct resctrl_pqr_state { DECLARE_PER_CPU(struct resctrl_pqr_state, pqr_state); +extern bool rdt_alloc_capable; +extern bool rdt_mon_capable; + DECLARE_STATIC_KEY_FALSE(rdt_enable_key); DECLARE_STATIC_KEY_FALSE(rdt_alloc_enable_key); DECLARE_STATIC_KEY_FALSE(rdt_mon_enable_key); +static inline bool resctrl_arch_alloc_capable(void) +{ + return rdt_alloc_capable; +} + static inline void resctrl_arch_enable_alloc(void) { static_branch_enable_cpuslocked(&rdt_alloc_enable_key); @@ -54,6 +62,11 @@ static inline void resctrl_arch_disable_alloc(void) static_branch_dec_cpuslocked(&rdt_enable_key); } +static inline bool resctrl_arch_mon_capable(void) +{ + return rdt_mon_capable; +} + static inline void resctrl_arch_enable_mon(void) { static_branch_enable_cpuslocked(&rdt_mon_enable_key); diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index 78580855139d..3ee855c37447 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -137,8 +137,6 @@ struct rmid_read { void *arch_mon_ctx; }; -extern bool rdt_alloc_capable; -extern bool rdt_mon_capable; extern unsigned int rdt_mon_features; extern struct list_head resctrl_schema_all; extern bool resctrl_mounted; diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index d5d8a58d96f2..92d7ba674003 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -817,7 +817,7 @@ void mbm_handle_overflow(struct work_struct *work) * If the filesystem has been unmounted this work no longer needs to * run. */ - if (!resctrl_mounted || !static_branch_likely(&rdt_mon_enable_key)) + if (!resctrl_mounted || !resctrl_arch_mon_capable()) goto out_unlock; r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; @@ -854,7 +854,7 @@ void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms) * When a domain comes online there is no guarantee the filesystem is * mounted. If not, there is no need to catch counter overflow. */ - if (!resctrl_mounted || !static_branch_likely(&rdt_mon_enable_key)) + if (!resctrl_mounted || !resctrl_arch_mon_capable()) return; cpu = cpumask_any_housekeeping(&dom->cpu_mask); dom->mbm_work_cpu = cpu; diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c index d8f44113ed1f..8056bed033cc 100644 --- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c +++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c @@ -581,7 +581,7 @@ static int rdtgroup_locksetup_user_restrict(struct rdtgroup *rdtgrp) if (ret) goto err_cpus; - if (rdt_mon_capable) { + if (resctrl_arch_mon_capable()) { ret = rdtgroup_kn_mode_restrict(rdtgrp, "mon_groups"); if (ret) goto err_cpus_list; @@ -628,7 +628,7 @@ static int rdtgroup_locksetup_user_restore(struct rdtgroup *rdtgrp) if (ret) goto err_cpus; - if (rdt_mon_capable) { + if (resctrl_arch_mon_capable()) { ret = rdtgroup_kn_mode_restore(rdtgrp, "mon_groups", 0777); if (ret) goto err_cpus_list; @@ -776,7 +776,7 @@ int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp) { int ret; - if (rdt_mon_capable) { + if (resctrl_arch_mon_capable()) { ret = alloc_rmid(rdtgrp->closid); if (ret < 0) { rdt_last_cmd_puts("Out of RMIDs\n"); diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 7e57ac9d81f7..ed5fc677a99d 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -641,13 +641,13 @@ static int __rdtgroup_move_task(struct task_struct *tsk, static bool is_closid_match(struct task_struct *t, struct rdtgroup *r) { - return (rdt_alloc_capable && (r->type == RDTCTRL_GROUP) && + return (resctrl_arch_alloc_capable() && (r->type == RDTCTRL_GROUP) && resctrl_arch_match_closid(t, r->closid)); } static bool is_rmid_match(struct task_struct *t, struct rdtgroup *r) { - return (rdt_mon_capable && (r->type == RDTMON_GROUP) && + return (resctrl_arch_mon_capable() && (r->type == RDTMON_GROUP) && resctrl_arch_match_rmid(t, r->mon.parent->closid, r->mon.rmid)); } @@ -2632,7 +2632,7 @@ static int rdt_get_tree(struct fs_context *fc) closid_init(); - if (rdt_mon_capable) + if (resctrl_arch_mon_capable()) flags |= RFTYPE_MON; ret = rdtgroup_add_files(rdtgroup_default.kn, flags); @@ -2645,7 +2645,7 @@ static int rdt_get_tree(struct fs_context *fc) if (ret < 0) goto out_schemata_free; - if (rdt_mon_capable) { + if (resctrl_arch_mon_capable()) { ret = mongroup_create_dir(rdtgroup_default.kn, &rdtgroup_default, "mon_groups", &kn_mongrp); @@ -2667,12 +2667,12 @@ static int rdt_get_tree(struct fs_context *fc) if (ret < 0) goto out_psl; - if (rdt_alloc_capable) + if (resctrl_arch_alloc_capable()) resctrl_arch_enable_alloc(); - if (rdt_mon_capable) + if (resctrl_arch_mon_capable()) resctrl_arch_enable_mon(); - if (rdt_alloc_capable || rdt_mon_capable) + if (resctrl_arch_alloc_capable() || resctrl_arch_mon_capable()) resctrl_mounted = true; if (is_mbm_enabled()) { @@ -2686,10 +2686,10 @@ static int rdt_get_tree(struct fs_context *fc) out_psl: rdt_pseudo_lock_release(); out_mondata: - if (rdt_mon_capable) + if (resctrl_arch_mon_capable()) kernfs_remove(kn_mondata); out_mongrp: - if (rdt_mon_capable) + if (resctrl_arch_mon_capable()) kernfs_remove(kn_mongrp); out_info: kernfs_remove(kn_info); @@ -2944,9 +2944,9 @@ static void rdt_kill_sb(struct super_block *sb) rdtgroup_default.mode = RDT_MODE_SHAREABLE; schemata_list_destroy(); rdtgroup_destroy_root(); - if (rdt_alloc_capable) + if (resctrl_arch_alloc_capable()) resctrl_arch_disable_alloc(); - if (rdt_mon_capable) + if (resctrl_arch_mon_capable()) resctrl_arch_disable_mon(); resctrl_mounted = false; kernfs_kill_sb(sb); @@ -3326,7 +3326,7 @@ static int mkdir_rdt_prepare_rmid_alloc(struct rdtgroup *rdtgrp) { int ret; - if (!rdt_mon_capable) + if (!resctrl_arch_mon_capable()) return 0; ret = alloc_rmid(rdtgrp->closid); @@ -3348,7 +3348,7 @@ static int mkdir_rdt_prepare_rmid_alloc(struct rdtgroup *rdtgrp) static void mkdir_rdt_prepare_rmid_free(struct rdtgroup *rgrp) { - if (rdt_mon_capable) + if (resctrl_arch_mon_capable()) free_rmid(rgrp->closid, rgrp->mon.rmid); } @@ -3412,7 +3412,7 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, if (rtype == RDTCTRL_GROUP) { files = RFTYPE_BASE | RFTYPE_CTRL; - if (rdt_mon_capable) + if (resctrl_arch_mon_capable()) files |= RFTYPE_MON; } else { files = RFTYPE_BASE | RFTYPE_MON; @@ -3521,7 +3521,7 @@ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn, list_add(&rdtgrp->rdtgroup_list, &rdt_all_groups); - if (rdt_mon_capable) { + if (resctrl_arch_mon_capable()) { /* * Create an empty mon_groups directory to hold the subset * of tasks and cpus to monitor. @@ -3576,14 +3576,14 @@ static int rdtgroup_mkdir(struct kernfs_node *parent_kn, const char *name, * allocation is supported, add a control and monitoring * subdirectory */ - if (rdt_alloc_capable && parent_kn == rdtgroup_default.kn) + if (resctrl_arch_alloc_capable() && parent_kn == rdtgroup_default.kn) return rdtgroup_mkdir_ctrl_mon(parent_kn, name, mode); /* * If RDT monitoring is supported and the parent directory is a valid * "mon_groups" directory, add a monitoring subdirectory. */ - if (rdt_mon_capable && is_mon_groups(parent_kn, name)) + if (resctrl_arch_mon_capable() && is_mon_groups(parent_kn, name)) return rdtgroup_mkdir_mon(parent_kn, name, mode); return -EPERM; @@ -3918,7 +3918,7 @@ void resctrl_offline_domain(struct rdt_resource *r, struct rdt_domain *d) * If resctrl is mounted, remove all the * per domain monitor data directories. */ - if (resctrl_mounted && static_branch_unlikely(&rdt_mon_enable_key)) + if (resctrl_mounted && resctrl_arch_mon_capable()) rmdir_mondata_subdir_allrdtgrp(r, d->id); if (is_mbm_enabled()) @@ -4001,7 +4001,7 @@ int resctrl_online_domain(struct rdt_resource *r, struct rdt_domain *d) * by rdt_get_tree() calling mkdir_mondata_all(). * If resctrl is mounted, add per domain monitor data directories. */ - if (resctrl_mounted && static_branch_unlikely(&rdt_mon_enable_key)) + if (resctrl_mounted && resctrl_arch_mon_capable()) mkdir_mondata_subdir_allrdtgrp(r, d); return 0; -- cgit v1.2.3 From 1b3e50ce7f5001f1e0edaf7d6abea43b264db7ee Mon Sep 17 00:00:00 2001 From: James Morse Date: Tue, 13 Feb 2024 18:44:34 +0000 Subject: x86/resctrl: Add CPU online callback for resctrl work The resctrl architecture specific code may need to create a domain when a CPU comes online, it also needs to reset the CPUs PQR_ASSOC register. The resctrl filesystem code needs to update the rdtgroup_default CPU mask when CPUs are brought online. Currently, this is all done in one function, resctrl_online_cpu(). It will need to be split into architecture and filesystem parts before resctrl can be moved to /fs/. Pull the rdtgroup_default update work out as a filesystem specific cpu_online helper. resctrl_online_cpu() is the obvious name for this, which means the version in core.c needs renaming. resctrl_online_cpu() is called by the arch code once it has done the work to add the new CPU to any domains. In future patches, resctrl_online_cpu() will take the rdtgroup_mutex itself. Signed-off-by: James Morse Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Shaopeng Tan Reviewed-by: Reinette Chatre Reviewed-by: Babu Moger Tested-by: Shaopeng Tan Tested-by: Peter Newman Tested-by: Babu Moger Tested-by: Carl Worth # arm64 Link: https://lore.kernel.org/r/20240213184438.16675-21-james.morse@arm.com Signed-off-by: Borislav Petkov (AMD) --- arch/x86/kernel/cpu/resctrl/core.c | 8 ++++---- arch/x86/kernel/cpu/resctrl/rdtgroup.c | 8 ++++++++ include/linux/resctrl.h | 1 + 3 files changed, 13 insertions(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index d1dc80a21ea9..4627d447bc3d 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -606,16 +606,16 @@ static void clear_closid_rmid(int cpu) RESCTRL_RESERVED_CLOSID); } -static int resctrl_online_cpu(unsigned int cpu) +static int resctrl_arch_online_cpu(unsigned int cpu) { struct rdt_resource *r; mutex_lock(&rdtgroup_mutex); for_each_capable_rdt_resource(r) domain_add_cpu(cpu, r); - /* The cpu is set in default rdtgroup after online. */ - cpumask_set_cpu(cpu, &rdtgroup_default.cpu_mask); clear_closid_rmid(cpu); + + resctrl_online_cpu(cpu); mutex_unlock(&rdtgroup_mutex); return 0; @@ -967,7 +967,7 @@ static int __init resctrl_late_init(void) state = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/resctrl/cat:online:", - resctrl_online_cpu, resctrl_offline_cpu); + resctrl_arch_online_cpu, resctrl_offline_cpu); if (state < 0) return state; diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index ed5fc677a99d..38d3b19a3aca 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -4007,6 +4007,14 @@ int resctrl_online_domain(struct rdt_resource *r, struct rdt_domain *d) return 0; } +void resctrl_online_cpu(unsigned int cpu) +{ + lockdep_assert_held(&rdtgroup_mutex); + + /* The CPU is set in default rdtgroup after online. */ + cpumask_set_cpu(cpu, &rdtgroup_default.cpu_mask); +} + /* * rdtgroup_init - rdtgroup initialization * diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index bf460c912bf5..4c4bad3c34e4 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -223,6 +223,7 @@ u32 resctrl_arch_get_config(struct rdt_resource *r, struct rdt_domain *d, u32 closid, enum resctrl_conf_type type); int resctrl_online_domain(struct rdt_resource *r, struct rdt_domain *d); void resctrl_offline_domain(struct rdt_resource *r, struct rdt_domain *d); +void resctrl_online_cpu(unsigned int cpu); /** * resctrl_arch_rmid_read() - Read the eventid counter corresponding to rmid -- cgit v1.2.3 From 978fcca954cb52249babbc14e53de53c88dd6433 Mon Sep 17 00:00:00 2001 From: James Morse Date: Tue, 13 Feb 2024 18:44:35 +0000 Subject: x86/resctrl: Allow overflow/limbo handlers to be scheduled on any-but CPU When a CPU is taken offline resctrl may need to move the overflow or limbo handlers to run on a different CPU. Once the offline callbacks have been split, cqm_setup_limbo_handler() will be called while the CPU that is going offline is still present in the CPU mask. Pass the CPU to exclude to cqm_setup_limbo_handler() and mbm_setup_overflow_handler(). These functions can use a variant of cpumask_any_but() when selecting the CPU. -1 is used to indicate no CPUs need excluding. Signed-off-by: James Morse Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Shaopeng Tan Reviewed-by: Babu Moger Reviewed-by: Reinette Chatre Tested-by: Shaopeng Tan Tested-by: Peter Newman Tested-by: Babu Moger Tested-by: Carl Worth # arm64 Link: https://lore.kernel.org/r/20240213184438.16675-22-james.morse@arm.com Signed-off-by: Borislav Petkov (AMD) --- arch/x86/kernel/cpu/resctrl/core.c | 8 ++++-- arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 2 +- arch/x86/kernel/cpu/resctrl/internal.h | 33 ++++++++++++++++++------ arch/x86/kernel/cpu/resctrl/monitor.c | 42 ++++++++++++++++++++++++------- arch/x86/kernel/cpu/resctrl/rdtgroup.c | 6 +++-- include/linux/resctrl.h | 2 ++ 6 files changed, 72 insertions(+), 21 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index 4627d447bc3d..55322ba629da 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -584,12 +584,16 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r) if (r == &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl) { if (is_mbm_enabled() && cpu == d->mbm_work_cpu) { cancel_delayed_work(&d->mbm_over); - mbm_setup_overflow_handler(d, 0); + /* + * temporary: exclude_cpu=-1 as this CPU has already + * been removed by cpumask_clear_cpu()d + */ + mbm_setup_overflow_handler(d, 0, RESCTRL_PICK_ANY_CPU); } if (is_llc_occupancy_enabled() && cpu == d->cqm_work_cpu && has_busy_rmid(d)) { cancel_delayed_work(&d->cqm_limbo); - cqm_setup_limbo_handler(d, 0); + cqm_setup_limbo_handler(d, 0, RESCTRL_PICK_ANY_CPU); } } } diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c index 52fa0e14cb86..20b02d6f02c1 100644 --- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c +++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c @@ -552,7 +552,7 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r, return; } - cpu = cpumask_any_housekeeping(&d->cpu_mask); + cpu = cpumask_any_housekeeping(&d->cpu_mask, RESCTRL_PICK_ANY_CPU); /* * cpumask_any_housekeeping() prefers housekeeping CPUs, but diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index 3ee855c37447..c99f26ebe7a6 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -60,19 +60,36 @@ * cpumask_any_housekeeping() - Choose any CPU in @mask, preferring those that * aren't marked nohz_full * @mask: The mask to pick a CPU from. + * @exclude_cpu:The CPU to avoid picking. * - * Returns a CPU in @mask. If there are housekeeping CPUs that don't use - * nohz_full, these are preferred. + * Returns a CPU from @mask, but not @exclude_cpu. If there are housekeeping + * CPUs that don't use nohz_full, these are preferred. Pass + * RESCTRL_PICK_ANY_CPU to avoid excluding any CPUs. + * + * When a CPU is excluded, returns >= nr_cpu_ids if no CPUs are available. */ -static inline unsigned int cpumask_any_housekeeping(const struct cpumask *mask) +static inline unsigned int +cpumask_any_housekeeping(const struct cpumask *mask, int exclude_cpu) { unsigned int cpu, hk_cpu; - cpu = cpumask_any(mask); - if (!tick_nohz_full_cpu(cpu)) + if (exclude_cpu == RESCTRL_PICK_ANY_CPU) + cpu = cpumask_any(mask); + else + cpu = cpumask_any_but(mask, exclude_cpu); + + if (!IS_ENABLED(CONFIG_NO_HZ_FULL)) return cpu; + /* If the CPU picked isn't marked nohz_full nothing more needs doing. */ + if (cpu < nr_cpu_ids && !tick_nohz_full_cpu(cpu)) + return cpu; + + /* Try to find a CPU that isn't nohz_full to use in preference */ hk_cpu = cpumask_nth_andnot(0, mask, tick_nohz_full_mask); + if (hk_cpu == exclude_cpu) + hk_cpu = cpumask_nth_andnot(1, mask, tick_nohz_full_mask); + if (hk_cpu < nr_cpu_ids) cpu = hk_cpu; @@ -573,11 +590,13 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r, struct rdt_domain *d, struct rdtgroup *rdtgrp, int evtid, int first); void mbm_setup_overflow_handler(struct rdt_domain *dom, - unsigned long delay_ms); + unsigned long delay_ms, + int exclude_cpu); void mbm_handle_overflow(struct work_struct *work); void __init intel_rdt_mbm_apply_quirk(void); bool is_mba_sc(struct rdt_resource *r); -void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms); +void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms, + int exclude_cpu); void cqm_handle_limbo(struct work_struct *work); bool has_busy_rmid(struct rdt_domain *d); void __check_limbo(struct rdt_domain *d, bool force_free); diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index 92d7ba674003..67edd4c440f0 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -481,7 +481,8 @@ static void add_rmid_to_limbo(struct rmid_entry *entry) * setup up the limbo worker. */ if (!has_busy_rmid(d)) - cqm_setup_limbo_handler(d, CQM_LIMBOCHECK_INTERVAL); + cqm_setup_limbo_handler(d, CQM_LIMBOCHECK_INTERVAL, + RESCTRL_PICK_ANY_CPU); set_bit(idx, d->rmid_busy_llc); entry->busy++; } @@ -784,7 +785,8 @@ void cqm_handle_limbo(struct work_struct *work) __check_limbo(d, false); if (has_busy_rmid(d)) { - d->cqm_work_cpu = cpumask_any_housekeeping(&d->cpu_mask); + d->cqm_work_cpu = cpumask_any_housekeeping(&d->cpu_mask, + RESCTRL_PICK_ANY_CPU); schedule_delayed_work_on(d->cqm_work_cpu, &d->cqm_limbo, delay); } @@ -792,15 +794,25 @@ void cqm_handle_limbo(struct work_struct *work) mutex_unlock(&rdtgroup_mutex); } -void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms) +/** + * cqm_setup_limbo_handler() - Schedule the limbo handler to run for this + * domain. + * @dom: The domain the limbo handler should run for. + * @delay_ms: How far in the future the handler should run. + * @exclude_cpu: Which CPU the handler should not run on, + * RESCTRL_PICK_ANY_CPU to pick any CPU. + */ +void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms, + int exclude_cpu) { unsigned long delay = msecs_to_jiffies(delay_ms); int cpu; - cpu = cpumask_any_housekeeping(&dom->cpu_mask); + cpu = cpumask_any_housekeeping(&dom->cpu_mask, exclude_cpu); dom->cqm_work_cpu = cpu; - schedule_delayed_work_on(cpu, &dom->cqm_limbo, delay); + if (cpu < nr_cpu_ids) + schedule_delayed_work_on(cpu, &dom->cqm_limbo, delay); } void mbm_handle_overflow(struct work_struct *work) @@ -838,14 +850,24 @@ void mbm_handle_overflow(struct work_struct *work) * Re-check for housekeeping CPUs. This allows the overflow handler to * move off a nohz_full CPU quickly. */ - d->mbm_work_cpu = cpumask_any_housekeeping(&d->cpu_mask); + d->mbm_work_cpu = cpumask_any_housekeeping(&d->cpu_mask, + RESCTRL_PICK_ANY_CPU); schedule_delayed_work_on(d->mbm_work_cpu, &d->mbm_over, delay); out_unlock: mutex_unlock(&rdtgroup_mutex); } -void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms) +/** + * mbm_setup_overflow_handler() - Schedule the overflow handler to run for this + * domain. + * @dom: The domain the overflow handler should run for. + * @delay_ms: How far in the future the handler should run. + * @exclude_cpu: Which CPU the handler should not run on, + * RESCTRL_PICK_ANY_CPU to pick any CPU. + */ +void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms, + int exclude_cpu) { unsigned long delay = msecs_to_jiffies(delay_ms); int cpu; @@ -856,9 +878,11 @@ void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms) */ if (!resctrl_mounted || !resctrl_arch_mon_capable()) return; - cpu = cpumask_any_housekeeping(&dom->cpu_mask); + cpu = cpumask_any_housekeeping(&dom->cpu_mask, exclude_cpu); dom->mbm_work_cpu = cpu; - schedule_delayed_work_on(cpu, &dom->mbm_over, delay); + + if (cpu < nr_cpu_ids) + schedule_delayed_work_on(cpu, &dom->mbm_over, delay); } static int dom_data_init(struct rdt_resource *r) diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 38d3b19a3aca..f5688c79d94f 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -2678,7 +2678,8 @@ static int rdt_get_tree(struct fs_context *fc) if (is_mbm_enabled()) { r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; list_for_each_entry(dom, &r->domains, list) - mbm_setup_overflow_handler(dom, MBM_OVERFLOW_INTERVAL); + mbm_setup_overflow_handler(dom, MBM_OVERFLOW_INTERVAL, + RESCTRL_PICK_ANY_CPU); } goto out; @@ -3989,7 +3990,8 @@ int resctrl_online_domain(struct rdt_resource *r, struct rdt_domain *d) if (is_mbm_enabled()) { INIT_DELAYED_WORK(&d->mbm_over, mbm_handle_overflow); - mbm_setup_overflow_handler(d, MBM_OVERFLOW_INTERVAL); + mbm_setup_overflow_handler(d, MBM_OVERFLOW_INTERVAL, + RESCTRL_PICK_ANY_CPU); } if (is_llc_occupancy_enabled()) diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index 4c4bad3c34e4..ccbbbe5d18d3 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -10,6 +10,8 @@ #define RESCTRL_RESERVED_CLOSID 0 #define RESCTRL_RESERVED_RMID 0 +#define RESCTRL_PICK_ANY_CPU -1 + #ifdef CONFIG_PROC_CPU_RESCTRL int proc_resctrl_show(struct seq_file *m, -- cgit v1.2.3 From 258c91e84fedc789353a35ad91d827a9111d3cbd Mon Sep 17 00:00:00 2001 From: James Morse Date: Tue, 13 Feb 2024 18:44:36 +0000 Subject: x86/resctrl: Add CPU offline callback for resctrl work The resctrl architecture specific code may need to free a domain when a CPU goes offline, it also needs to reset the CPUs PQR_ASSOC register. Amongst other things, the resctrl filesystem code needs to clear this CPU from the cpu_mask of any control and monitor groups. Currently, this is all done in core.c and called from resctrl_offline_cpu(), making the split between architecture and filesystem code unclear. Move the filesystem work to remove the CPU from the control and monitor groups into a filesystem helper called resctrl_offline_cpu(), and rename the one in core.c resctrl_arch_offline_cpu(). Signed-off-by: James Morse Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Shaopeng Tan Reviewed-by: Reinette Chatre Reviewed-by: Babu Moger Tested-by: Shaopeng Tan Tested-by: Peter Newman Tested-by: Babu Moger Tested-by: Carl Worth # arm64 Link: https://lore.kernel.org/r/20240213184438.16675-23-james.morse@arm.com Signed-off-by: Borislav Petkov (AMD) --- arch/x86/kernel/cpu/resctrl/core.c | 25 +++++-------------------- arch/x86/kernel/cpu/resctrl/rdtgroup.c | 24 ++++++++++++++++++++++++ include/linux/resctrl.h | 1 + 3 files changed, 30 insertions(+), 20 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index 55322ba629da..4aedefa22f61 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -625,31 +625,15 @@ static int resctrl_arch_online_cpu(unsigned int cpu) return 0; } -static void clear_childcpus(struct rdtgroup *r, unsigned int cpu) +static int resctrl_arch_offline_cpu(unsigned int cpu) { - struct rdtgroup *cr; - - list_for_each_entry(cr, &r->mon.crdtgrp_list, mon.crdtgrp_list) { - if (cpumask_test_and_clear_cpu(cpu, &cr->cpu_mask)) { - break; - } - } -} - -static int resctrl_offline_cpu(unsigned int cpu) -{ - struct rdtgroup *rdtgrp; struct rdt_resource *r; mutex_lock(&rdtgroup_mutex); + resctrl_offline_cpu(cpu); + for_each_capable_rdt_resource(r) domain_remove_cpu(cpu, r); - list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) { - if (cpumask_test_and_clear_cpu(cpu, &rdtgrp->cpu_mask)) { - clear_childcpus(rdtgrp, cpu); - break; - } - } clear_closid_rmid(cpu); mutex_unlock(&rdtgroup_mutex); @@ -971,7 +955,8 @@ static int __init resctrl_late_init(void) state = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/resctrl/cat:online:", - resctrl_arch_online_cpu, resctrl_offline_cpu); + resctrl_arch_online_cpu, + resctrl_arch_offline_cpu); if (state < 0) return state; diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index f5688c79d94f..5bd3d8fb3f67 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -4017,6 +4017,30 @@ void resctrl_online_cpu(unsigned int cpu) cpumask_set_cpu(cpu, &rdtgroup_default.cpu_mask); } +static void clear_childcpus(struct rdtgroup *r, unsigned int cpu) +{ + struct rdtgroup *cr; + + list_for_each_entry(cr, &r->mon.crdtgrp_list, mon.crdtgrp_list) { + if (cpumask_test_and_clear_cpu(cpu, &cr->cpu_mask)) + break; + } +} + +void resctrl_offline_cpu(unsigned int cpu) +{ + struct rdtgroup *rdtgrp; + + lockdep_assert_held(&rdtgroup_mutex); + + list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) { + if (cpumask_test_and_clear_cpu(cpu, &rdtgrp->cpu_mask)) { + clear_childcpus(rdtgrp, cpu); + break; + } + } +} + /* * rdtgroup_init - rdtgroup initialization * diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index ccbbbe5d18d3..270ff1d5c051 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -226,6 +226,7 @@ u32 resctrl_arch_get_config(struct rdt_resource *r, struct rdt_domain *d, int resctrl_online_domain(struct rdt_resource *r, struct rdt_domain *d); void resctrl_offline_domain(struct rdt_resource *r, struct rdt_domain *d); void resctrl_online_cpu(unsigned int cpu); +void resctrl_offline_cpu(unsigned int cpu); /** * resctrl_arch_rmid_read() - Read the eventid counter corresponding to rmid -- cgit v1.2.3 From eeff1d4f118bdf0870227fee5a770f03056e3adc Mon Sep 17 00:00:00 2001 From: James Morse Date: Tue, 13 Feb 2024 18:44:37 +0000 Subject: x86/resctrl: Move domain helper migration into resctrl_offline_cpu() When a CPU is taken offline the resctrl filesystem code needs to check if it was the CPU nominated to perform the periodic overflow and limbo work. If so, another CPU needs to be chosen to do this work. This is currently done in core.c, mixed in with the code that removes the CPU from the domain's mask, and potentially free()s the domain. Move the migration of the overflow and limbo helpers into the filesystem code, into resctrl_offline_cpu(). As resctrl_offline_cpu() runs before the architecture code has removed the CPU from the domain mask, the callers need to be told which CPU is being removed, to avoid picking it as the new CPU. This uses the exclude_cpu feature previously added. Signed-off-by: James Morse Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Shaopeng Tan Reviewed-by: Reinette Chatre Reviewed-by: Babu Moger Tested-by: Shaopeng Tan Tested-by: Peter Newman Tested-by: Babu Moger Tested-by: Carl Worth # arm64 Link: https://lore.kernel.org/r/20240213184438.16675-24-james.morse@arm.com Signed-off-by: Borislav Petkov (AMD) --- arch/x86/kernel/cpu/resctrl/core.c | 16 ---------------- arch/x86/kernel/cpu/resctrl/rdtgroup.c | 18 ++++++++++++++++++ 2 files changed, 18 insertions(+), 16 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index 4aedefa22f61..b03a6c658ae5 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -580,22 +580,6 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r) return; } - - if (r == &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl) { - if (is_mbm_enabled() && cpu == d->mbm_work_cpu) { - cancel_delayed_work(&d->mbm_over); - /* - * temporary: exclude_cpu=-1 as this CPU has already - * been removed by cpumask_clear_cpu()d - */ - mbm_setup_overflow_handler(d, 0, RESCTRL_PICK_ANY_CPU); - } - if (is_llc_occupancy_enabled() && cpu == d->cqm_work_cpu && - has_busy_rmid(d)) { - cancel_delayed_work(&d->cqm_limbo); - cqm_setup_limbo_handler(d, 0, RESCTRL_PICK_ANY_CPU); - } - } } static void clear_closid_rmid(int cpu) diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 5bd3d8fb3f67..777e9f680332 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -4029,7 +4029,9 @@ static void clear_childcpus(struct rdtgroup *r, unsigned int cpu) void resctrl_offline_cpu(unsigned int cpu) { + struct rdt_resource *l3 = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; struct rdtgroup *rdtgrp; + struct rdt_domain *d; lockdep_assert_held(&rdtgroup_mutex); @@ -4039,6 +4041,22 @@ void resctrl_offline_cpu(unsigned int cpu) break; } } + + if (!l3->mon_capable) + return; + + d = get_domain_from_cpu(cpu, l3); + if (d) { + if (is_mbm_enabled() && cpu == d->mbm_work_cpu) { + cancel_delayed_work(&d->mbm_over); + mbm_setup_overflow_handler(d, 0, cpu); + } + if (is_llc_occupancy_enabled() && cpu == d->cqm_work_cpu && + has_busy_rmid(d)) { + cancel_delayed_work(&d->cqm_limbo); + cqm_setup_limbo_handler(d, 0, cpu); + } + } } /* -- cgit v1.2.3 From fb700810d30b9eb333a7bf447012e1158e35c62f Mon Sep 17 00:00:00 2001 From: James Morse Date: Tue, 13 Feb 2024 18:44:38 +0000 Subject: x86/resctrl: Separate arch and fs resctrl locks resctrl has one mutex that is taken by the architecture-specific code, and the filesystem parts. The two interact via cpuhp, where the architecture code updates the domain list. Filesystem handlers that walk the domains list should not run concurrently with the cpuhp callback modifying the list. Exposing a lock from the filesystem code means the interface is not cleanly defined, and creates the possibility of cross-architecture lock ordering headaches. The interaction only exists so that certain filesystem paths are serialised against CPU hotplug. The CPU hotplug code already has a mechanism to do this using cpus_read_lock(). MPAM's monitors have an overflow interrupt, so it needs to be possible to walk the domains list in irq context. RCU is ideal for this, but some paths need to be able to sleep to allocate memory. Because resctrl_{on,off}line_cpu() take the rdtgroup_mutex as part of a cpuhp callback, cpus_read_lock() must always be taken first. rdtgroup_schemata_write() already does this. Most of the filesystem code's domain list walkers are currently protected by the rdtgroup_mutex taken in rdtgroup_kn_lock_live(). The exceptions are rdt_bit_usage_show() and the mon_config helpers which take the lock directly. Make the domain list protected by RCU. An architecture-specific lock prevents concurrent writers. rdt_bit_usage_show() could walk the domain list using RCU, but to keep all the filesystem operations the same, this is changed to call cpus_read_lock(). The mon_config helpers send multiple IPIs, take the cpus_read_lock() in these cases. The other filesystem list walkers need to be able to sleep. Add cpus_read_lock() to rdtgroup_kn_lock_live() so that the cpuhp callbacks can't be invoked when file system operations are occurring. Add lockdep_assert_cpus_held() in the cases where the rdtgroup_kn_lock_live() call isn't obvious. Resctrl's domain online/offline calls now need to take the rdtgroup_mutex themselves. [ bp: Fold in a build fix: https://lore.kernel.org/r/87zfvwieli.ffs@tglx ] Signed-off-by: James Morse Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Shaopeng Tan Reviewed-by: Reinette Chatre Reviewed-by: Babu Moger Tested-by: Shaopeng Tan Tested-by: Peter Newman Tested-by: Babu Moger Tested-by: Carl Worth # arm64 Link: https://lore.kernel.org/r/20240213184438.16675-25-james.morse@arm.com Signed-off-by: Borislav Petkov (AMD) --- arch/x86/kernel/cpu/resctrl/core.c | 44 +++++++++++++++----- arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 15 +++++-- arch/x86/kernel/cpu/resctrl/monitor.c | 8 ++++ arch/x86/kernel/cpu/resctrl/pseudo_lock.c | 3 ++ arch/x86/kernel/cpu/resctrl/rdtgroup.c | 68 ++++++++++++++++++++++++------- include/linux/resctrl.h | 2 +- 6 files changed, 112 insertions(+), 28 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index b03a6c658ae5..8a4ef4f5bddc 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -16,6 +16,7 @@ #define pr_fmt(fmt) "resctrl: " fmt +#include #include #include #include @@ -25,8 +26,15 @@ #include #include "internal.h" -/* Mutex to protect rdtgroup access. */ -DEFINE_MUTEX(rdtgroup_mutex); +/* + * rdt_domain structures are kfree()d when their last CPU goes offline, + * and allocated when the first CPU in a new domain comes online. + * The rdt_resource's domain list is updated when this happens. Readers of + * the domain list must either take cpus_read_lock(), or rely on an RCU + * read-side critical section, to avoid observing concurrent modification. + * All writers take this mutex: + */ +static DEFINE_MUTEX(domain_list_lock); /* * The cached resctrl_pqr_state is strictly per CPU and can never be @@ -354,6 +362,15 @@ struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r) { struct rdt_domain *d; + /* + * Walking r->domains, ensure it can't race with cpuhp. + * Because this is called via IPI by rdt_ctrl_update(), assertions + * about locks this thread holds will lead to false positives. Check + * someone is holding the CPUs lock. + */ + if (IS_ENABLED(CONFIG_HOTPLUG_CPU) && IS_ENABLED(CONFIG_LOCKDEP)) + WARN_ON_ONCE(!lockdep_is_cpus_held()); + list_for_each_entry(d, &r->domains, list) { /* Find the domain that contains this CPU */ if (cpumask_test_cpu(cpu, &d->cpu_mask)) @@ -510,6 +527,8 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r) struct rdt_domain *d; int err; + lockdep_assert_held(&domain_list_lock); + d = rdt_find_domain(r, id, &add_pos); if (IS_ERR(d)) { pr_warn("Couldn't find cache id for CPU %d\n", cpu); @@ -543,11 +562,12 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r) return; } - list_add_tail(&d->list, add_pos); + list_add_tail_rcu(&d->list, add_pos); err = resctrl_online_domain(r, d); if (err) { - list_del(&d->list); + list_del_rcu(&d->list); + synchronize_rcu(); domain_free(hw_dom); } } @@ -558,6 +578,8 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r) struct rdt_hw_domain *hw_dom; struct rdt_domain *d; + lockdep_assert_held(&domain_list_lock); + d = rdt_find_domain(r, id, NULL); if (IS_ERR_OR_NULL(d)) { pr_warn("Couldn't find cache id for CPU %d\n", cpu); @@ -568,7 +590,8 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r) cpumask_clear_cpu(cpu, &d->cpu_mask); if (cpumask_empty(&d->cpu_mask)) { resctrl_offline_domain(r, d); - list_del(&d->list); + list_del_rcu(&d->list); + synchronize_rcu(); /* * rdt_domain "d" is going to be freed below, so clear @@ -598,13 +621,13 @@ static int resctrl_arch_online_cpu(unsigned int cpu) { struct rdt_resource *r; - mutex_lock(&rdtgroup_mutex); + mutex_lock(&domain_list_lock); for_each_capable_rdt_resource(r) domain_add_cpu(cpu, r); - clear_closid_rmid(cpu); + mutex_unlock(&domain_list_lock); + clear_closid_rmid(cpu); resctrl_online_cpu(cpu); - mutex_unlock(&rdtgroup_mutex); return 0; } @@ -613,13 +636,14 @@ static int resctrl_arch_offline_cpu(unsigned int cpu) { struct rdt_resource *r; - mutex_lock(&rdtgroup_mutex); resctrl_offline_cpu(cpu); + mutex_lock(&domain_list_lock); for_each_capable_rdt_resource(r) domain_remove_cpu(cpu, r); + mutex_unlock(&domain_list_lock); + clear_closid_rmid(cpu); - mutex_unlock(&rdtgroup_mutex); return 0; } diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c index 20b02d6f02c1..7997b47743a2 100644 --- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c +++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c @@ -212,6 +212,9 @@ static int parse_line(char *line, struct resctrl_schema *s, struct rdt_domain *d; unsigned long dom_id; + /* Walking r->domains, ensure it can't race with cpuhp */ + lockdep_assert_cpus_held(); + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP && (r->rid == RDT_RESOURCE_MBA || r->rid == RDT_RESOURCE_SMBA)) { rdt_last_cmd_puts("Cannot pseudo-lock MBA resource\n"); @@ -316,6 +319,9 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid) struct rdt_domain *d; u32 idx; + /* Walking r->domains, ensure it can't race with cpuhp */ + lockdep_assert_cpus_held(); + if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL)) return -ENOMEM; @@ -381,11 +387,9 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, return -EINVAL; buf[nbytes - 1] = '\0'; - cpus_read_lock(); rdtgrp = rdtgroup_kn_lock_live(of->kn); if (!rdtgrp) { rdtgroup_kn_unlock(of->kn); - cpus_read_unlock(); return -ENOENT; } rdt_last_cmd_clear(); @@ -447,7 +451,6 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, out: rdt_staged_configs_clear(); rdtgroup_kn_unlock(of->kn); - cpus_read_unlock(); return ret ?: nbytes; } @@ -467,6 +470,9 @@ static void show_doms(struct seq_file *s, struct resctrl_schema *schema, int clo bool sep = false; u32 ctrl_val; + /* Walking r->domains, ensure it can't race with cpuhp */ + lockdep_assert_cpus_held(); + seq_printf(s, "%*s:", max_name_width, schema->name); list_for_each_entry(dom, &r->domains, list) { if (sep) @@ -537,6 +543,9 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r, { int cpu; + /* When picking a CPU from cpu_mask, ensure it can't race with cpuhp */ + lockdep_assert_cpus_held(); + /* * Setup the parameters to pass to mon_event_count() to read the data. */ diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index 67edd4c440f0..c34a35ec0f03 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -15,6 +15,7 @@ * Software Developer Manual June 2016, volume 3, section 17.17. */ +#include #include #include #include @@ -472,6 +473,9 @@ static void add_rmid_to_limbo(struct rmid_entry *entry) lockdep_assert_held(&rdtgroup_mutex); + /* Walking r->domains, ensure it can't race with cpuhp */ + lockdep_assert_cpus_held(); + idx = resctrl_arch_rmid_idx_encode(entry->closid, entry->rmid); entry->busy = 0; @@ -778,6 +782,7 @@ void cqm_handle_limbo(struct work_struct *work) unsigned long delay = msecs_to_jiffies(CQM_LIMBOCHECK_INTERVAL); struct rdt_domain *d; + cpus_read_lock(); mutex_lock(&rdtgroup_mutex); d = container_of(work, struct rdt_domain, cqm_limbo.work); @@ -792,6 +797,7 @@ void cqm_handle_limbo(struct work_struct *work) } mutex_unlock(&rdtgroup_mutex); + cpus_read_unlock(); } /** @@ -823,6 +829,7 @@ void mbm_handle_overflow(struct work_struct *work) struct rdt_resource *r; struct rdt_domain *d; + cpus_read_lock(); mutex_lock(&rdtgroup_mutex); /* @@ -856,6 +863,7 @@ void mbm_handle_overflow(struct work_struct *work) out_unlock: mutex_unlock(&rdtgroup_mutex); + cpus_read_unlock(); } /** diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c index 8056bed033cc..884b88e25141 100644 --- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c +++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c @@ -844,6 +844,9 @@ bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d) struct rdt_domain *d_i; bool ret = false; + /* Walking r->domains, ensure it can't race with cpuhp */ + lockdep_assert_cpus_held(); + if (!zalloc_cpumask_var(&cpu_with_psl, GFP_KERNEL)) return true; diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 777e9f680332..011e17efb1a6 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -35,6 +35,10 @@ DEFINE_STATIC_KEY_FALSE(rdt_enable_key); DEFINE_STATIC_KEY_FALSE(rdt_mon_enable_key); DEFINE_STATIC_KEY_FALSE(rdt_alloc_enable_key); + +/* Mutex to protect rdtgroup access. */ +DEFINE_MUTEX(rdtgroup_mutex); + static struct kernfs_root *rdt_root; struct rdtgroup rdtgroup_default; LIST_HEAD(rdt_all_groups); @@ -1014,6 +1018,7 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of, bool sep = false; u32 ctrl_val; + cpus_read_lock(); mutex_lock(&rdtgroup_mutex); hw_shareable = r->cache.shareable_bits; list_for_each_entry(dom, &r->domains, list) { @@ -1074,6 +1079,7 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of, } seq_putc(seq, '\n'); mutex_unlock(&rdtgroup_mutex); + cpus_read_unlock(); return 0; } @@ -1329,6 +1335,9 @@ static bool rdtgroup_mode_test_exclusive(struct rdtgroup *rdtgrp) struct rdt_domain *d; u32 ctrl; + /* Walking r->domains, ensure it can't race with cpuhp */ + lockdep_assert_cpus_held(); + list_for_each_entry(s, &resctrl_schema_all, list) { r = s->res; if (r->rid == RDT_RESOURCE_MBA || r->rid == RDT_RESOURCE_SMBA) @@ -1593,6 +1602,7 @@ static int mbm_config_show(struct seq_file *s, struct rdt_resource *r, u32 evtid struct rdt_domain *dom; bool sep = false; + cpus_read_lock(); mutex_lock(&rdtgroup_mutex); list_for_each_entry(dom, &r->domains, list) { @@ -1609,6 +1619,7 @@ static int mbm_config_show(struct seq_file *s, struct rdt_resource *r, u32 evtid seq_puts(s, "\n"); mutex_unlock(&rdtgroup_mutex); + cpus_read_unlock(); return 0; } @@ -1690,6 +1701,9 @@ static int mon_config_write(struct rdt_resource *r, char *tok, u32 evtid) unsigned long dom_id, val; struct rdt_domain *d; + /* Walking r->domains, ensure it can't race with cpuhp */ + lockdep_assert_cpus_held(); + next: if (!tok || tok[0] == '\0') return 0; @@ -1736,6 +1750,7 @@ static ssize_t mbm_total_bytes_config_write(struct kernfs_open_file *of, if (nbytes == 0 || buf[nbytes - 1] != '\n') return -EINVAL; + cpus_read_lock(); mutex_lock(&rdtgroup_mutex); rdt_last_cmd_clear(); @@ -1745,6 +1760,7 @@ static ssize_t mbm_total_bytes_config_write(struct kernfs_open_file *of, ret = mon_config_write(r, buf, QOS_L3_MBM_TOTAL_EVENT_ID); mutex_unlock(&rdtgroup_mutex); + cpus_read_unlock(); return ret ?: nbytes; } @@ -1760,6 +1776,7 @@ static ssize_t mbm_local_bytes_config_write(struct kernfs_open_file *of, if (nbytes == 0 || buf[nbytes - 1] != '\n') return -EINVAL; + cpus_read_lock(); mutex_lock(&rdtgroup_mutex); rdt_last_cmd_clear(); @@ -1769,6 +1786,7 @@ static ssize_t mbm_local_bytes_config_write(struct kernfs_open_file *of, ret = mon_config_write(r, buf, QOS_L3_MBM_LOCAL_EVENT_ID); mutex_unlock(&rdtgroup_mutex); + cpus_read_unlock(); return ret ?: nbytes; } @@ -2245,6 +2263,9 @@ static int set_cache_qos_cfg(int level, bool enable) struct rdt_domain *d; int cpu; + /* Walking r->domains, ensure it can't race with cpuhp */ + lockdep_assert_cpus_held(); + if (level == RDT_RESOURCE_L3) update = l3_qos_cfg_update; else if (level == RDT_RESOURCE_L2) @@ -2444,6 +2465,7 @@ struct rdtgroup *rdtgroup_kn_lock_live(struct kernfs_node *kn) rdtgroup_kn_get(rdtgrp, kn); + cpus_read_lock(); mutex_lock(&rdtgroup_mutex); /* Was this group deleted while we waited? */ @@ -2461,6 +2483,8 @@ void rdtgroup_kn_unlock(struct kernfs_node *kn) return; mutex_unlock(&rdtgroup_mutex); + cpus_read_unlock(); + rdtgroup_kn_put(rdtgrp, kn); } @@ -2793,6 +2817,9 @@ static int reset_all_ctrls(struct rdt_resource *r) struct rdt_domain *d; int i; + /* Walking r->domains, ensure it can't race with cpuhp */ + lockdep_assert_cpus_held(); + if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL)) return -ENOMEM; @@ -3077,6 +3104,9 @@ static int mkdir_mondata_subdir_alldom(struct kernfs_node *parent_kn, struct rdt_domain *dom; int ret; + /* Walking r->domains, ensure it can't race with cpuhp */ + lockdep_assert_cpus_held(); + list_for_each_entry(dom, &r->domains, list) { ret = mkdir_mondata_subdir(parent_kn, dom, r, prgrp); if (ret) @@ -3907,13 +3937,13 @@ static void domain_destroy_mon_state(struct rdt_domain *d) void resctrl_offline_domain(struct rdt_resource *r, struct rdt_domain *d) { - lockdep_assert_held(&rdtgroup_mutex); + mutex_lock(&rdtgroup_mutex); if (supports_mba_mbps() && r->rid == RDT_RESOURCE_MBA) mba_sc_domain_destroy(r, d); if (!r->mon_capable) - return; + goto out_unlock; /* * If resctrl is mounted, remove all the @@ -3938,6 +3968,9 @@ void resctrl_offline_domain(struct rdt_resource *r, struct rdt_domain *d) } domain_destroy_mon_state(d); + +out_unlock: + mutex_unlock(&rdtgroup_mutex); } static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d) @@ -3973,20 +4006,22 @@ static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d) int resctrl_online_domain(struct rdt_resource *r, struct rdt_domain *d) { - int err; + int err = 0; - lockdep_assert_held(&rdtgroup_mutex); + mutex_lock(&rdtgroup_mutex); - if (supports_mba_mbps() && r->rid == RDT_RESOURCE_MBA) + if (supports_mba_mbps() && r->rid == RDT_RESOURCE_MBA) { /* RDT_RESOURCE_MBA is never mon_capable */ - return mba_sc_domain_allocate(r, d); + err = mba_sc_domain_allocate(r, d); + goto out_unlock; + } if (!r->mon_capable) - return 0; + goto out_unlock; err = domain_setup_mon_state(r, d); if (err) - return err; + goto out_unlock; if (is_mbm_enabled()) { INIT_DELAYED_WORK(&d->mbm_over, mbm_handle_overflow); @@ -4006,15 +4041,18 @@ int resctrl_online_domain(struct rdt_resource *r, struct rdt_domain *d) if (resctrl_mounted && resctrl_arch_mon_capable()) mkdir_mondata_subdir_allrdtgrp(r, d); - return 0; +out_unlock: + mutex_unlock(&rdtgroup_mutex); + + return err; } void resctrl_online_cpu(unsigned int cpu) { - lockdep_assert_held(&rdtgroup_mutex); - + mutex_lock(&rdtgroup_mutex); /* The CPU is set in default rdtgroup after online. */ cpumask_set_cpu(cpu, &rdtgroup_default.cpu_mask); + mutex_unlock(&rdtgroup_mutex); } static void clear_childcpus(struct rdtgroup *r, unsigned int cpu) @@ -4033,8 +4071,7 @@ void resctrl_offline_cpu(unsigned int cpu) struct rdtgroup *rdtgrp; struct rdt_domain *d; - lockdep_assert_held(&rdtgroup_mutex); - + mutex_lock(&rdtgroup_mutex); list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) { if (cpumask_test_and_clear_cpu(cpu, &rdtgrp->cpu_mask)) { clear_childcpus(rdtgrp, cpu); @@ -4043,7 +4080,7 @@ void resctrl_offline_cpu(unsigned int cpu) } if (!l3->mon_capable) - return; + goto out_unlock; d = get_domain_from_cpu(cpu, l3); if (d) { @@ -4057,6 +4094,9 @@ void resctrl_offline_cpu(unsigned int cpu) cqm_setup_limbo_handler(d, 0, cpu); } } + +out_unlock: + mutex_unlock(&rdtgroup_mutex); } /* diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index 270ff1d5c051..a365f67131ec 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -159,7 +159,7 @@ struct resctrl_schema; * @cache_level: Which cache level defines scope of this resource * @cache: Cache allocation related data * @membw: If the component has bandwidth controls, their properties. - * @domains: All domains for this resource + * @domains: RCU list of all domains for this resource * @name: Name to use in "schemata" file. * @data_width: Character width of data when displaying * @default_ctrl: Specifies default cache cbm or memory B/W percent. -- cgit v1.2.3 From c0d848fcb09d80a5f48b99f85e448185125ef59f Mon Sep 17 00:00:00 2001 From: James Morse Date: Wed, 21 Feb 2024 12:23:06 +0000 Subject: x86/resctrl: Remove lockdep annotation that triggers false positive get_domain_from_cpu() walks a list of domains to find the one that contains the specified CPU. This needs to be protected against races with CPU hotplug when the list is modified. It has recently gained a lockdep annotation to check this. The lockdep annotation causes false positives when called via IPI as the lock is held, but by another process. Remove it. [ bp: Refresh it ontop of x86/cache. ] Fixes: fb700810d30b ("x86/resctrl: Separate arch and fs resctrl locks") Reported-by: Tony Luck Signed-off-by: James Morse Signed-off-by: Borislav Petkov (AMD) Link: https://lore.kernel.org/all/ZdUSwOM9UUNpw84Y@agluck-desk3 --- arch/x86/kernel/cpu/resctrl/core.c | 9 --------- 1 file changed, 9 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index 8a4ef4f5bddc..83e40341583e 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -362,15 +362,6 @@ struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r) { struct rdt_domain *d; - /* - * Walking r->domains, ensure it can't race with cpuhp. - * Because this is called via IPI by rdt_ctrl_update(), assertions - * about locks this thread holds will lead to false positives. Check - * someone is holding the CPUs lock. - */ - if (IS_ENABLED(CONFIG_HOTPLUG_CPU) && IS_ENABLED(CONFIG_LOCKDEP)) - WARN_ON_ONCE(!lockdep_is_cpus_held()); - list_for_each_entry(d, &r->domains, list) { /* Find the domain that contains this CPU */ if (cpumask_test_cpu(cpu, &d->cpu_mask)) -- cgit v1.2.3