diff options
| author | Ingo Molnar <mingo@kernel.org> | 2025-04-11 11:13:27 +0200 |
|---|---|---|
| committer | Ingo Molnar <mingo@kernel.org> | 2025-04-11 11:13:27 +0200 |
| commit | 9f13acb2406a3aed90c6738b3a2f1c0e43118cbd (patch) | |
| tree | cf37d241e85bf8fea4d13cb8d64ad6602c745b72 /arch/x86/kernel | |
| parent | x86/cacheinfo: Properly parse CPUID(0x80000006) L2/L3 associativity (diff) | |
| parent | Linux 6.15-rc1 (diff) | |
| download | linux-9f13acb2406a3aed90c6738b3a2f1c0e43118cbd.tar.gz linux-9f13acb2406a3aed90c6738b3a2f1c0e43118cbd.zip | |
Merge tag 'v6.15-rc1' into x86/cpu, to refresh the branch with upstream changes
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'arch/x86/kernel')
30 files changed, 900 insertions, 753 deletions
diff --git a/arch/x86/kernel/acpi/cppc.c b/arch/x86/kernel/acpi/cppc.c index d745dd586303..77bfb846490c 100644 --- a/arch/x86/kernel/acpi/cppc.c +++ b/arch/x86/kernel/acpi/cppc.c @@ -4,6 +4,8 @@ * Copyright (c) 2016, Intel Corporation. */ +#include <linux/bitfield.h> + #include <acpi/cppc_acpi.h> #include <asm/msr.h> #include <asm/processor.h> @@ -149,7 +151,7 @@ int amd_get_highest_perf(unsigned int cpu, u32 *highest_perf) if (ret) goto out; - val = AMD_CPPC_HIGHEST_PERF(val); + val = FIELD_GET(AMD_CPPC_HIGHEST_PERF_MASK, val); } else { ret = cppc_get_highest_perf(cpu, &val); if (ret) diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 736f62812f5c..fee42a73d64a 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -799,7 +799,7 @@ int __init arch_early_irq_init(void) x86_vector_domain = irq_domain_create_tree(fn, &x86_vector_domain_ops, NULL); BUG_ON(x86_vector_domain == NULL); - irq_set_default_host(x86_vector_domain); + irq_set_default_domain(x86_vector_domain); BUG_ON(!alloc_cpumask_var(&vector_searchmask, GFP_KERNEL)); @@ -888,8 +888,109 @@ static int apic_set_affinity(struct irq_data *irqd, return err ? err : IRQ_SET_MASK_OK; } +static void free_moved_vector(struct apic_chip_data *apicd) +{ + unsigned int vector = apicd->prev_vector; + unsigned int cpu = apicd->prev_cpu; + bool managed = apicd->is_managed; + + /* + * Managed interrupts are usually not migrated away + * from an online CPU, but CPU isolation 'managed_irq' + * can make that happen. + * 1) Activation does not take the isolation into account + * to keep the code simple + * 2) Migration away from an isolated CPU can happen when + * a non-isolated CPU which is in the calculated + * affinity mask comes online. + */ + trace_vector_free_moved(apicd->irq, cpu, vector, managed); + irq_matrix_free(vector_matrix, cpu, vector, managed); + per_cpu(vector_irq, cpu)[vector] = VECTOR_UNUSED; + hlist_del_init(&apicd->clist); + apicd->prev_vector = 0; + apicd->move_in_progress = 0; +} + +/* + * Called from fixup_irqs() with @desc->lock held and interrupts disabled. + */ +static void apic_force_complete_move(struct irq_data *irqd) +{ + unsigned int cpu = smp_processor_id(); + struct apic_chip_data *apicd; + unsigned int vector; + + guard(raw_spinlock)(&vector_lock); + apicd = apic_chip_data(irqd); + if (!apicd) + return; + + /* + * If prev_vector is empty or the descriptor is neither currently + * nor previously on the outgoing CPU no action required. + */ + vector = apicd->prev_vector; + if (!vector || (apicd->cpu != cpu && apicd->prev_cpu != cpu)) + return; + + /* + * This is tricky. If the cleanup of the old vector has not been + * done yet, then the following setaffinity call will fail with + * -EBUSY. This can leave the interrupt in a stale state. + * + * All CPUs are stuck in stop machine with interrupts disabled so + * calling __irq_complete_move() would be completely pointless. + * + * 1) The interrupt is in move_in_progress state. That means that we + * have not seen an interrupt since the io_apic was reprogrammed to + * the new vector. + * + * 2) The interrupt has fired on the new vector, but the cleanup IPIs + * have not been processed yet. + */ + if (apicd->move_in_progress) { + /* + * In theory there is a race: + * + * set_ioapic(new_vector) <-- Interrupt is raised before update + * is effective, i.e. it's raised on + * the old vector. + * + * So if the target cpu cannot handle that interrupt before + * the old vector is cleaned up, we get a spurious interrupt + * and in the worst case the ioapic irq line becomes stale. + * + * But in case of cpu hotplug this should be a non issue + * because if the affinity update happens right before all + * cpus rendezvous in stop machine, there is no way that the + * interrupt can be blocked on the target cpu because all cpus + * loops first with interrupts enabled in stop machine, so the + * old vector is not yet cleaned up when the interrupt fires. + * + * So the only way to run into this issue is if the delivery + * of the interrupt on the apic/system bus would be delayed + * beyond the point where the target cpu disables interrupts + * in stop machine. I doubt that it can happen, but at least + * there is a theoretical chance. Virtualization might be + * able to expose this, but AFAICT the IOAPIC emulation is not + * as stupid as the real hardware. + * + * Anyway, there is nothing we can do about that at this point + * w/o refactoring the whole fixup_irq() business completely. + * We print at least the irq number and the old vector number, + * so we have the necessary information when a problem in that + * area arises. + */ + pr_warn("IRQ fixup: irq %d move in progress, old vector %d\n", + irqd->irq, vector); + } + free_moved_vector(apicd); +} + #else -# define apic_set_affinity NULL +# define apic_set_affinity NULL +# define apic_force_complete_move NULL #endif static int apic_retrigger_irq(struct irq_data *irqd) @@ -923,39 +1024,16 @@ static void x86_vector_msi_compose_msg(struct irq_data *data, } static struct irq_chip lapic_controller = { - .name = "APIC", - .irq_ack = apic_ack_edge, - .irq_set_affinity = apic_set_affinity, - .irq_compose_msi_msg = x86_vector_msi_compose_msg, - .irq_retrigger = apic_retrigger_irq, + .name = "APIC", + .irq_ack = apic_ack_edge, + .irq_set_affinity = apic_set_affinity, + .irq_compose_msi_msg = x86_vector_msi_compose_msg, + .irq_force_complete_move = apic_force_complete_move, + .irq_retrigger = apic_retrigger_irq, }; #ifdef CONFIG_SMP -static void free_moved_vector(struct apic_chip_data *apicd) -{ - unsigned int vector = apicd->prev_vector; - unsigned int cpu = apicd->prev_cpu; - bool managed = apicd->is_managed; - - /* - * Managed interrupts are usually not migrated away - * from an online CPU, but CPU isolation 'managed_irq' - * can make that happen. - * 1) Activation does not take the isolation into account - * to keep the code simple - * 2) Migration away from an isolated CPU can happen when - * a non-isolated CPU which is in the calculated - * affinity mask comes online. - */ - trace_vector_free_moved(apicd->irq, cpu, vector, managed); - irq_matrix_free(vector_matrix, cpu, vector, managed); - per_cpu(vector_irq, cpu)[vector] = VECTOR_UNUSED; - hlist_del_init(&apicd->clist); - apicd->prev_vector = 0; - apicd->move_in_progress = 0; -} - static void __vector_cleanup(struct vector_cleanup *cl, bool check_irr) { struct apic_chip_data *apicd; @@ -1068,99 +1146,6 @@ void irq_complete_move(struct irq_cfg *cfg) __vector_schedule_cleanup(apicd); } -/* - * Called from fixup_irqs() with @desc->lock held and interrupts disabled. - */ -void irq_force_complete_move(struct irq_desc *desc) -{ - unsigned int cpu = smp_processor_id(); - struct apic_chip_data *apicd; - struct irq_data *irqd; - unsigned int vector; - - /* - * The function is called for all descriptors regardless of which - * irqdomain they belong to. For example if an IRQ is provided by - * an irq_chip as part of a GPIO driver, the chip data for that - * descriptor is specific to the irq_chip in question. - * - * Check first that the chip_data is what we expect - * (apic_chip_data) before touching it any further. - */ - irqd = irq_domain_get_irq_data(x86_vector_domain, - irq_desc_get_irq(desc)); - if (!irqd) - return; - - raw_spin_lock(&vector_lock); - apicd = apic_chip_data(irqd); - if (!apicd) - goto unlock; - - /* - * If prev_vector is empty or the descriptor is neither currently - * nor previously on the outgoing CPU no action required. - */ - vector = apicd->prev_vector; - if (!vector || (apicd->cpu != cpu && apicd->prev_cpu != cpu)) - goto unlock; - - /* - * This is tricky. If the cleanup of the old vector has not been - * done yet, then the following setaffinity call will fail with - * -EBUSY. This can leave the interrupt in a stale state. - * - * All CPUs are stuck in stop machine with interrupts disabled so - * calling __irq_complete_move() would be completely pointless. - * - * 1) The interrupt is in move_in_progress state. That means that we - * have not seen an interrupt since the io_apic was reprogrammed to - * the new vector. - * - * 2) The interrupt has fired on the new vector, but the cleanup IPIs - * have not been processed yet. - */ - if (apicd->move_in_progress) { - /* - * In theory there is a race: - * - * set_ioapic(new_vector) <-- Interrupt is raised before update - * is effective, i.e. it's raised on - * the old vector. - * - * So if the target cpu cannot handle that interrupt before - * the old vector is cleaned up, we get a spurious interrupt - * and in the worst case the ioapic irq line becomes stale. - * - * But in case of cpu hotplug this should be a non issue - * because if the affinity update happens right before all - * cpus rendezvous in stop machine, there is no way that the - * interrupt can be blocked on the target cpu because all cpus - * loops first with interrupts enabled in stop machine, so the - * old vector is not yet cleaned up when the interrupt fires. - * - * So the only way to run into this issue is if the delivery - * of the interrupt on the apic/system bus would be delayed - * beyond the point where the target cpu disables interrupts - * in stop machine. I doubt that it can happen, but at least - * there is a theoretical chance. Virtualization might be - * able to expose this, but AFAICT the IOAPIC emulation is not - * as stupid as the real hardware. - * - * Anyway, there is nothing we can do about that at this point - * w/o refactoring the whole fixup_irq() business completely. - * We print at least the irq number and the old vector number, - * so we have the necessary information when a problem in that - * area arises. - */ - pr_warn("IRQ fixup: irq %d move in progress, old vector %d\n", - irqd->irq, vector); - } - free_moved_vector(apicd); -unlock: - raw_spin_unlock(&vector_lock); -} - #ifdef CONFIG_HOTPLUG_CPU /* * Note, this is not accurate accounting, but at least good enough to diff --git a/arch/x86/kernel/callthunks.c b/arch/x86/kernel/callthunks.c index 25ae54250112..d86d7d6e750c 100644 --- a/arch/x86/kernel/callthunks.c +++ b/arch/x86/kernel/callthunks.c @@ -98,11 +98,10 @@ static inline bool within_module_coretext(void *addr) #ifdef CONFIG_MODULES struct module *mod; - preempt_disable(); + guard(rcu)(); mod = __module_address((unsigned long)addr); if (mod && within_module_core((unsigned long)addr, mod)) ret = true; - preempt_enable(); #endif return ret; } diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c index f642de2ebdac..6cf31a1649c4 100644 --- a/arch/x86/kernel/cpu/aperfmperf.c +++ b/arch/x86/kernel/cpu/aperfmperf.c @@ -498,7 +498,7 @@ void arch_scale_freq_tick(void) */ #define MAX_SAMPLE_AGE ((unsigned long)HZ / 50) -unsigned int arch_freq_get_on_cpu(int cpu) +int arch_freq_get_on_cpu(int cpu) { struct aperfmperf *s = per_cpu_ptr(&cpu_samples, cpu); unsigned int seq, freq; diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index a5d0998d7604..4386aa6c69e1 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -113,6 +113,10 @@ DEFINE_STATIC_KEY_FALSE(switch_mm_cond_ibpb); /* Control unconditional IBPB in switch_mm() */ DEFINE_STATIC_KEY_FALSE(switch_mm_always_ibpb); +/* Control IBPB on vCPU load */ +DEFINE_STATIC_KEY_FALSE(switch_vcpu_ibpb); +EXPORT_SYMBOL_GPL(switch_vcpu_ibpb); + /* Control MDS CPU buffer clear before idling (halt, mwait) */ DEFINE_STATIC_KEY_FALSE(mds_idle_clear); EXPORT_SYMBOL_GPL(mds_idle_clear); @@ -234,7 +238,7 @@ static void x86_amd_ssb_disable(void) /* Default mitigation for MDS-affected CPUs */ static enum mds_mitigations mds_mitigation __ro_after_init = - IS_ENABLED(CONFIG_MITIGATION_MDS) ? MDS_MITIGATION_FULL : MDS_MITIGATION_OFF; + IS_ENABLED(CONFIG_MITIGATION_MDS) ? MDS_MITIGATION_AUTO : MDS_MITIGATION_OFF; static bool mds_nosmt __ro_after_init = false; static const char * const mds_strings[] = { @@ -243,6 +247,40 @@ static const char * const mds_strings[] = { [MDS_MITIGATION_VMWERV] = "Vulnerable: Clear CPU buffers attempted, no microcode", }; +enum taa_mitigations { + TAA_MITIGATION_OFF, + TAA_MITIGATION_AUTO, + TAA_MITIGATION_UCODE_NEEDED, + TAA_MITIGATION_VERW, + TAA_MITIGATION_TSX_DISABLED, +}; + +/* Default mitigation for TAA-affected CPUs */ +static enum taa_mitigations taa_mitigation __ro_after_init = + IS_ENABLED(CONFIG_MITIGATION_TAA) ? TAA_MITIGATION_AUTO : TAA_MITIGATION_OFF; + +enum mmio_mitigations { + MMIO_MITIGATION_OFF, + MMIO_MITIGATION_AUTO, + MMIO_MITIGATION_UCODE_NEEDED, + MMIO_MITIGATION_VERW, +}; + +/* Default mitigation for Processor MMIO Stale Data vulnerabilities */ +static enum mmio_mitigations mmio_mitigation __ro_after_init = + IS_ENABLED(CONFIG_MITIGATION_MMIO_STALE_DATA) ? MMIO_MITIGATION_AUTO : MMIO_MITIGATION_OFF; + +enum rfds_mitigations { + RFDS_MITIGATION_OFF, + RFDS_MITIGATION_AUTO, + RFDS_MITIGATION_VERW, + RFDS_MITIGATION_UCODE_NEEDED, +}; + +/* Default mitigation for Register File Data Sampling */ +static enum rfds_mitigations rfds_mitigation __ro_after_init = + IS_ENABLED(CONFIG_MITIGATION_RFDS) ? RFDS_MITIGATION_AUTO : RFDS_MITIGATION_OFF; + static void __init mds_select_mitigation(void) { if (!boot_cpu_has_bug(X86_BUG_MDS) || cpu_mitigations_off()) { @@ -250,6 +288,9 @@ static void __init mds_select_mitigation(void) return; } + if (mds_mitigation == MDS_MITIGATION_AUTO) + mds_mitigation = MDS_MITIGATION_FULL; + if (mds_mitigation == MDS_MITIGATION_FULL) { if (!boot_cpu_has(X86_FEATURE_MD_CLEAR)) mds_mitigation = MDS_MITIGATION_VMWERV; @@ -286,16 +327,6 @@ early_param("mds", mds_cmdline); #undef pr_fmt #define pr_fmt(fmt) "TAA: " fmt -enum taa_mitigations { - TAA_MITIGATION_OFF, - TAA_MITIGATION_UCODE_NEEDED, - TAA_MITIGATION_VERW, - TAA_MITIGATION_TSX_DISABLED, -}; - -/* Default mitigation for TAA-affected CPUs */ -static enum taa_mitigations taa_mitigation __ro_after_init = - IS_ENABLED(CONFIG_MITIGATION_TAA) ? TAA_MITIGATION_VERW : TAA_MITIGATION_OFF; static bool taa_nosmt __ro_after_init; static const char * const taa_strings[] = { @@ -386,15 +417,6 @@ early_param("tsx_async_abort", tsx_async_abort_parse_cmdline); #undef pr_fmt #define pr_fmt(fmt) "MMIO Stale Data: " fmt -enum mmio_mitigations { - MMIO_MITIGATION_OFF, - MMIO_MITIGATION_UCODE_NEEDED, - MMIO_MITIGATION_VERW, -}; - -/* Default mitigation for Processor MMIO Stale Data vulnerabilities */ -static enum mmio_mitigations mmio_mitigation __ro_after_init = - IS_ENABLED(CONFIG_MITIGATION_MMIO_STALE_DATA) ? MMIO_MITIGATION_VERW : MMIO_MITIGATION_OFF; static bool mmio_nosmt __ro_after_init = false; static const char * const mmio_strings[] = { @@ -483,16 +505,6 @@ early_param("mmio_stale_data", mmio_stale_data_parse_cmdline); #undef pr_fmt #define pr_fmt(fmt) "Register File Data Sampling: " fmt -enum rfds_mitigations { - RFDS_MITIGATION_OFF, - RFDS_MITIGATION_VERW, - RFDS_MITIGATION_UCODE_NEEDED, -}; - -/* Default mitigation for Register File Data Sampling */ -static enum rfds_mitigations rfds_mitigation __ro_after_init = - IS_ENABLED(CONFIG_MITIGATION_RFDS) ? RFDS_MITIGATION_VERW : RFDS_MITIGATION_OFF; - static const char * const rfds_strings[] = { [RFDS_MITIGATION_OFF] = "Vulnerable", [RFDS_MITIGATION_VERW] = "Mitigation: Clear Register File", @@ -508,6 +520,9 @@ static void __init rfds_select_mitigation(void) if (rfds_mitigation == RFDS_MITIGATION_OFF) return; + if (rfds_mitigation == RFDS_MITIGATION_AUTO) + rfds_mitigation = RFDS_MITIGATION_VERW; + if (x86_arch_cap_msr & ARCH_CAP_RFDS_CLEAR) setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF); else @@ -1293,9 +1308,13 @@ static __ro_after_init enum spectre_v2_mitigation_cmd spectre_v2_cmd; static enum spectre_v2_user_cmd __init spectre_v2_parse_user_cmdline(void) { + enum spectre_v2_user_cmd mode; char arg[20]; int ret, i; + mode = IS_ENABLED(CONFIG_MITIGATION_SPECTRE_V2) ? + SPECTRE_V2_USER_CMD_AUTO : SPECTRE_V2_USER_CMD_NONE; + switch (spectre_v2_cmd) { case SPECTRE_V2_CMD_NONE: return SPECTRE_V2_USER_CMD_NONE; @@ -1308,7 +1327,7 @@ spectre_v2_parse_user_cmdline(void) ret = cmdline_find_option(boot_command_line, "spectre_v2_user", arg, sizeof(arg)); if (ret < 0) - return SPECTRE_V2_USER_CMD_AUTO; + return mode; for (i = 0; i < ARRAY_SIZE(v2_user_options); i++) { if (match_option(arg, ret, v2_user_options[i].option)) { @@ -1318,8 +1337,8 @@ spectre_v2_parse_user_cmdline(void) } } - pr_err("Unknown user space protection option (%s). Switching to AUTO select\n", arg); - return SPECTRE_V2_USER_CMD_AUTO; + pr_err("Unknown user space protection option (%s). Switching to default\n", arg); + return mode; } static inline bool spectre_v2_in_ibrs_mode(enum spectre_v2_mitigation mode) @@ -1331,16 +1350,11 @@ static void __init spectre_v2_user_select_mitigation(void) { enum spectre_v2_user_mitigation mode = SPECTRE_V2_USER_NONE; - bool smt_possible = IS_ENABLED(CONFIG_SMP); enum spectre_v2_user_cmd cmd; if (!boot_cpu_has(X86_FEATURE_IBPB) && !boot_cpu_has(X86_FEATURE_STIBP)) return; - if (cpu_smt_control == CPU_SMT_FORCE_DISABLED || - cpu_smt_control == CPU_SMT_NOT_SUPPORTED) - smt_possible = false; - cmd = spectre_v2_parse_user_cmdline(); switch (cmd) { case SPECTRE_V2_USER_CMD_NONE: @@ -1364,7 +1378,7 @@ spectre_v2_user_select_mitigation(void) /* Initialize Indirect Branch Prediction Barrier */ if (boot_cpu_has(X86_FEATURE_IBPB)) { - setup_force_cpu_cap(X86_FEATURE_USE_IBPB); + static_branch_enable(&switch_vcpu_ibpb); spectre_v2_user_ibpb = mode; switch (cmd) { @@ -1401,7 +1415,7 @@ spectre_v2_user_select_mitigation(void) * so allow for STIBP to be selected in those cases. */ if (!boot_cpu_has(X86_FEATURE_STIBP) || - !smt_possible || + !cpu_smt_possible() || (spectre_v2_in_eibrs_mode(spectre_v2_enabled) && !boot_cpu_has(X86_FEATURE_AUTOIBRS))) return; @@ -1973,6 +1987,7 @@ void cpu_bugs_smt_update(void) switch (mds_mitigation) { case MDS_MITIGATION_FULL: + case MDS_MITIGATION_AUTO: case MDS_MITIGATION_VMWERV: if (sched_smt_active() && !boot_cpu_has(X86_BUG_MSBDS_ONLY)) pr_warn_once(MDS_MSG_SMT); @@ -1984,6 +1999,7 @@ void cpu_bugs_smt_update(void) switch (taa_mitigation) { case TAA_MITIGATION_VERW: + case TAA_MITIGATION_AUTO: case TAA_MITIGATION_UCODE_NEEDED: if (sched_smt_active()) pr_warn_once(TAA_MSG_SMT); @@ -1995,6 +2011,7 @@ void cpu_bugs_smt_update(void) switch (mmio_mitigation) { case MMIO_MITIGATION_VERW: + case MMIO_MITIGATION_AUTO: case MMIO_MITIGATION_UCODE_NEEDED: if (sched_smt_active()) pr_warn_once(MMIO_MSG_SMT); @@ -2522,6 +2539,7 @@ enum srso_mitigation { SRSO_MITIGATION_SAFE_RET, SRSO_MITIGATION_IBPB, SRSO_MITIGATION_IBPB_ON_VMEXIT, + SRSO_MITIGATION_BP_SPEC_REDUCE, }; enum srso_mitigation_cmd { @@ -2539,7 +2557,8 @@ static const char * const srso_strings[] = { [SRSO_MITIGATION_MICROCODE] = "Vulnerable: Microcode, no safe RET", [SRSO_MITIGATION_SAFE_RET] = "Mitigation: Safe RET", [SRSO_MITIGATION_IBPB] = "Mitigation: IBPB", - [SRSO_MITIGATION_IBPB_ON_VMEXIT] = "Mitigation: IBPB on VMEXIT only" + [SRSO_MITIGATION_IBPB_ON_VMEXIT] = "Mitigation: IBPB on VMEXIT only", + [SRSO_MITIGATION_BP_SPEC_REDUCE] = "Mitigation: Reduced Speculation" }; static enum srso_mitigation srso_mitigation __ro_after_init = SRSO_MITIGATION_NONE; @@ -2578,7 +2597,7 @@ static void __init srso_select_mitigation(void) srso_cmd == SRSO_CMD_OFF) { if (boot_cpu_has(X86_FEATURE_SBPB)) x86_pred_cmd = PRED_CMD_SBPB; - return; + goto out; } if (has_microcode) { @@ -2590,7 +2609,7 @@ static void __init srso_select_mitigation(void) */ if (boot_cpu_data.x86 < 0x19 && !cpu_smt_possible()) { setup_force_cpu_cap(X86_FEATURE_SRSO_NO); - return; + goto out; } if (retbleed_mitigation == RETBLEED_MITIGATION_IBPB) { @@ -2670,6 +2689,12 @@ static void __init srso_select_mitigation(void) ibpb_on_vmexit: case SRSO_CMD_IBPB_ON_VMEXIT: + if (boot_cpu_has(X86_FEATURE_SRSO_BP_SPEC_REDUCE)) { + pr_notice("Reducing speculation to address VM/HV SRSO attack vector.\n"); + srso_mitigation = SRSO_MITIGATION_BP_SPEC_REDUCE; + break; + } + if (IS_ENABLED(CONFIG_MITIGATION_IBPB_ENTRY)) { if (has_microcode) { setup_force_cpu_cap(X86_FEATURE_IBPB_ON_VMEXIT); @@ -2691,7 +2716,15 @@ ibpb_on_vmexit: } out: - pr_info("%s\n", srso_strings[srso_mitigation]); + /* + * Clear the feature flag if this mitigation is not selected as that + * feature flag controls the BpSpecReduce MSR bit toggling in KVM. + */ + if (srso_mitigation != SRSO_MITIGATION_BP_SPEC_REDUCE) + setup_clear_cpu_cap(X86_FEATURE_SRSO_BP_SPEC_REDUCE); + + if (srso_mitigation != SRSO_MITIGATION_NONE) + pr_info("%s\n", srso_strings[srso_mitigation]); } #undef pr_fmt diff --git a/arch/x86/kernel/cpu/bus_lock.c b/arch/x86/kernel/cpu/bus_lock.c index 97222efb4d2a..237faf7e700c 100644 --- a/arch/x86/kernel/cpu/bus_lock.c +++ b/arch/x86/kernel/cpu/bus_lock.c @@ -201,6 +201,26 @@ static void __split_lock_reenable(struct work_struct *work) static DEFINE_PER_CPU(struct delayed_work, sl_reenable); /* + * Per-CPU delayed_work can't be statically initialized properly because + * the struct address is unknown. Thus per-CPU delayed_work structures + * have to be initialized during kernel initialization and after calling + * setup_per_cpu_areas(). + */ +static int __init setup_split_lock_delayed_work(void) +{ + unsigned int cpu; + + for_each_possible_cpu(cpu) { + struct delayed_work *work = per_cpu_ptr(&sl_reenable, cpu); + + INIT_DELAYED_WORK(work, __split_lock_reenable); + } + + return 0; +} +pure_initcall(setup_split_lock_delayed_work); + +/* * If a CPU goes offline with pending delayed work to re-enable split lock * detection then the delayed work will be executed on some other CPU. That * handles releasing the buslock_sem, but because it executes on a @@ -219,15 +239,16 @@ static int splitlock_cpu_offline(unsigned int cpu) static void split_lock_warn(unsigned long ip) { - struct delayed_work *work = NULL; + struct delayed_work *work; int cpu; + unsigned int saved_sld_mitigate = READ_ONCE(sysctl_sld_mitigate); if (!current->reported_split_lock) pr_warn_ratelimited("#AC: %s/%d took a split_lock trap at address: 0x%lx\n", current->comm, current->pid, ip); current->reported_split_lock = 1; - if (sysctl_sld_mitigate) { + if (saved_sld_mitigate) { /* * misery factor #1: * sleep 10ms before trying to execute split lock. @@ -240,18 +261,10 @@ static void split_lock_warn(unsigned long ip) */ if (down_interruptible(&buslock_sem) == -EINTR) return; - work = &sl_reenable_unlock; } cpu = get_cpu(); - - if (!work) { - work = this_cpu_ptr(&sl_reenable); - /* Deferred initialization of per-CPU struct */ - if (!work->work.func) - INIT_DELAYED_WORK(work, __split_lock_reenable); - } - + work = saved_sld_mitigate ? &sl_reenable_unlock : per_cpu_ptr(&sl_reenable, cpu); schedule_delayed_work_on(cpu, work, 2); /* Disable split lock detection on this CPU to make progress */ diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 73565168fc19..12126adbc3a9 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1332,8 +1332,10 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) setup_force_cpu_bug(X86_BUG_SPECTRE_V1); - if (!cpu_matches(cpu_vuln_whitelist, NO_SPECTRE_V2)) + if (!cpu_matches(cpu_vuln_whitelist, NO_SPECTRE_V2)) { setup_force_cpu_bug(X86_BUG_SPECTRE_V2); + setup_force_cpu_bug(X86_BUG_SPECTRE_V2_USER); + } if (!cpu_matches(cpu_vuln_whitelist, NO_SSB) && !(x86_arch_cap_msr & ARCH_CAP_SSB_NO) && diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index e5d814703406..a6493f60b3f2 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -514,6 +514,25 @@ static void init_intel_misc_features(struct cpuinfo_x86 *c) wrmsrl(MSR_MISC_FEATURES_ENABLES, msr); } +/* + * This is a list of Intel CPUs that are known to suffer from downclocking when + * ZMM registers (512-bit vectors) are used. On these CPUs, when the kernel + * executes SIMD-optimized code such as cryptography functions or CRCs, it + * should prefer 256-bit (YMM) code to 512-bit (ZMM) code. + */ +static const struct x86_cpu_id zmm_exclusion_list[] = { + X86_MATCH_VFM(INTEL_SKYLAKE_X, 0), + X86_MATCH_VFM(INTEL_ICELAKE_X, 0), + X86_MATCH_VFM(INTEL_ICELAKE_D, 0), + X86_MATCH_VFM(INTEL_ICELAKE, 0), + X86_MATCH_VFM(INTEL_ICELAKE_L, 0), + X86_MATCH_VFM(INTEL_ICELAKE_NNPI, 0), + X86_MATCH_VFM(INTEL_TIGERLAKE_L, 0), + X86_MATCH_VFM(INTEL_TIGERLAKE, 0), + /* Allow Rocket Lake and later, and Sapphire Rapids and later. */ + {}, +}; + static void init_intel(struct cpuinfo_x86 *c) { early_init_intel(c); @@ -592,6 +611,9 @@ static void init_intel(struct cpuinfo_x86 *c) } #endif + if (x86_match_cpu(zmm_exclusion_list)) + set_cpu_cap(c, X86_FEATURE_PREFER_YMM); + /* Work around errata */ srat_detect_node(c); diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 0dc00c9894c7..f6fd71b64b66 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -584,6 +584,28 @@ bool mce_is_correctable(struct mce *m) } EXPORT_SYMBOL_GPL(mce_is_correctable); +/* + * Notify the user(s) about new machine check events. + * Can be called from interrupt context, but not from machine check/NMI + * context. + */ +static bool mce_notify_irq(void) +{ + /* Not more than two messages every minute */ + static DEFINE_RATELIMIT_STATE(ratelimit, 60*HZ, 2); + + if (test_and_clear_bit(0, &mce_need_notify)) { + mce_work_trigger(); + + if (__ratelimit(&ratelimit)) + pr_info(HW_ERR "Machine check events logged\n"); + + return true; + } + + return false; +} + static int mce_early_notifier(struct notifier_block *nb, unsigned long val, void *data) { @@ -1764,36 +1786,14 @@ void mce_timer_kick(bool storm) __this_cpu_write(mce_next_interval, check_interval * HZ); } -/* Must not be called in IRQ context where del_timer_sync() can deadlock */ +/* Must not be called in IRQ context where timer_delete_sync() can deadlock */ static void mce_timer_delete_all(void) { int cpu; for_each_online_cpu(cpu) - del_timer_sync(&per_cpu(mce_timer, cpu)); -} - -/* - * Notify the user(s) about new machine check events. - * Can be called from interrupt context, but not from machine check/NMI - * context. - */ -bool mce_notify_irq(void) -{ - /* Not more than two messages every minute */ - static DEFINE_RATELIMIT_STATE(ratelimit, 60*HZ, 2); - - if (test_and_clear_bit(0, &mce_need_notify)) { - mce_work_trigger(); - - if (__ratelimit(&ratelimit)) - pr_info(HW_ERR "Machine check events logged\n"); - - return true; - } - return false; + timer_delete_sync(&per_cpu(mce_timer, cpu)); } -EXPORT_SYMBOL_GPL(mce_notify_irq); static void __mcheck_cpu_mce_banks_init(void) { @@ -2820,7 +2820,7 @@ static int mce_cpu_pre_down(unsigned int cpu) struct timer_list *t = this_cpu_ptr(&mce_timer); mce_disable_cpu(); - del_timer_sync(t); + timer_delete_sync(t); mce_threshold_remove_device(cpu); mce_device_remove(cpu); return 0; diff --git a/arch/x86/kernel/cpu/mce/inject.c b/arch/x86/kernel/cpu/mce/inject.c index 313fe682db33..06e3cf7229ce 100644 --- a/arch/x86/kernel/cpu/mce/inject.c +++ b/arch/x86/kernel/cpu/mce/inject.c @@ -229,7 +229,6 @@ static int raise_local(void) } else if (m->status) { pr_info("Starting machine check poll CPU %d\n", cpu); raise_poll(m); - mce_notify_irq(); pr_info("Machine check poll done on CPU %d\n", cpu); } else m->finished = 0; diff --git a/arch/x86/kernel/cpu/mce/severity.c b/arch/x86/kernel/cpu/mce/severity.c index dac4d64dfb2a..2235a7477436 100644 --- a/arch/x86/kernel/cpu/mce/severity.c +++ b/arch/x86/kernel/cpu/mce/severity.c @@ -300,13 +300,12 @@ static noinstr int error_context(struct mce *m, struct pt_regs *regs) copy_user = is_copy_from_user(regs); instrumentation_end(); - switch (fixup_type) { - case EX_TYPE_UACCESS: - if (!copy_user) - return IN_KERNEL; - m->kflags |= MCE_IN_KERNEL_COPYIN; - fallthrough; + if (copy_user) { + m->kflags |= MCE_IN_KERNEL_COPYIN | MCE_IN_KERNEL_RECOV; + return IN_KERNEL_RECOV; + } + switch (fixup_type) { case EX_TYPE_FAULT_MCE_SAFE: case EX_TYPE_DEFAULT_MCE_SAFE: m->kflags |= MCE_IN_KERNEL_RECOV; diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 138689b8e1d8..b61028cf5c8a 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -600,7 +600,7 @@ static bool __apply_microcode_amd(struct microcode_amd *mc, u32 *cur_rev, unsigned long p_addr = (unsigned long)&mc->hdr.data_code; if (!verify_sha256_digest(mc->hdr.patch_id, *cur_rev, (const u8 *)p_addr, psize)) - return -1; + return false; native_wrmsrl(MSR_AMD64_PATCH_LOADER, p_addr); diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index f285757618fc..3e2533954675 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -33,8 +33,6 @@ #include <asm/numa.h> #include <asm/svm.h> -/* Is Linux running as the root partition? */ -bool hv_root_partition; /* Is Linux running on nested Microsoft Hypervisor */ bool hv_nested; struct ms_hyperv_info ms_hyperv; @@ -109,6 +107,7 @@ void hv_set_msr(unsigned int reg, u64 value) } EXPORT_SYMBOL_GPL(hv_set_msr); +static void (*mshv_handler)(void); static void (*vmbus_handler)(void); static void (*hv_stimer0_handler)(void); static void (*hv_kexec_handler)(void); @@ -119,6 +118,9 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_hyperv_callback) struct pt_regs *old_regs = set_irq_regs(regs); inc_irq_stat(irq_hv_callback_count); + if (mshv_handler) + mshv_handler(); + if (vmbus_handler) vmbus_handler(); @@ -128,6 +130,11 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_hyperv_callback) set_irq_regs(old_regs); } +void hv_setup_mshv_handler(void (*handler)(void)) +{ + mshv_handler = handler; +} + void hv_setup_vmbus_handler(void (*handler)(void)) { vmbus_handler = handler; @@ -422,6 +429,7 @@ int hv_get_hypervisor_version(union hv_hypervisor_version_info *info) return 0; } +EXPORT_SYMBOL_GPL(hv_get_hypervisor_version); static void __init ms_hyperv_init_platform(void) { @@ -436,13 +444,15 @@ static void __init ms_hyperv_init_platform(void) */ ms_hyperv.features = cpuid_eax(HYPERV_CPUID_FEATURES); ms_hyperv.priv_high = cpuid_ebx(HYPERV_CPUID_FEATURES); + ms_hyperv.ext_features = cpuid_ecx(HYPERV_CPUID_FEATURES); ms_hyperv.misc_features = cpuid_edx(HYPERV_CPUID_FEATURES); ms_hyperv.hints = cpuid_eax(HYPERV_CPUID_ENLIGHTMENT_INFO); hv_max_functions_eax = cpuid_eax(HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS); - pr_info("Hyper-V: privilege flags low 0x%x, high 0x%x, hints 0x%x, misc 0x%x\n", - ms_hyperv.features, ms_hyperv.priv_high, ms_hyperv.hints, + pr_info("Hyper-V: privilege flags low %#x, high %#x, ext %#x, hints %#x, misc %#x\n", + ms_hyperv.features, ms_hyperv.priv_high, + ms_hyperv.ext_features, ms_hyperv.hints, ms_hyperv.misc_features); ms_hyperv.max_vp_index = cpuid_eax(HYPERV_CPUID_IMPLEMENT_LIMITS); @@ -451,25 +461,7 @@ static void __init ms_hyperv_init_platform(void) pr_debug("Hyper-V: max %u virtual processors, %u logical processors\n", ms_hyperv.max_vp_index, ms_hyperv.max_lp_index); - /* - * Check CPU management privilege. - * - * To mirror what Windows does we should extract CPU management - * features and use the ReservedIdentityBit to detect if Linux is the - * root partition. But that requires negotiating CPU management - * interface (a process to be finalized). For now, use the privilege - * flag as the indicator for running as root. - * - * Hyper-V should never specify running as root and as a Confidential - * VM. But to protect against a compromised/malicious Hyper-V trying - * to exploit root behavior to expose Confidential VM memory, ignore - * the root partition setting if also a Confidential VM. - */ - if ((ms_hyperv.priv_high & HV_CPU_MANAGEMENT) && - !(ms_hyperv.priv_high & HV_ISOLATION)) { - hv_root_partition = true; - pr_info("Hyper-V: running as root partition\n"); - } + hv_identify_partition_type(); if (ms_hyperv.hints & HV_X64_HYPERV_NESTED) { hv_nested = true; @@ -618,7 +610,7 @@ static void __init ms_hyperv_init_platform(void) # ifdef CONFIG_SMP smp_ops.smp_prepare_boot_cpu = hv_smp_prepare_boot_cpu; - if (hv_root_partition || + if (hv_root_partition() || (!ms_hyperv.paravisor_present && hv_isolation_type_snp())) smp_ops.smp_prepare_cpus = hv_smp_prepare_cpus; # endif diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c index 41ed01f46bd9..6571d432cbe3 100644 --- a/arch/x86/kernel/cpu/proc.c +++ b/arch/x86/kernel/cpu/proc.c @@ -86,9 +86,12 @@ static int show_cpuinfo(struct seq_file *m, void *v) seq_printf(m, "microcode\t: 0x%x\n", c->microcode); if (cpu_has(c, X86_FEATURE_TSC)) { - unsigned int freq = arch_freq_get_on_cpu(cpu); + int freq = arch_freq_get_on_cpu(cpu); - seq_printf(m, "cpu MHz\t\t: %u.%03u\n", freq / 1000, (freq % 1000)); + if (freq < 0) + seq_puts(m, "cpu MHz\t\t: Unknown\n"); + else + seq_printf(m, "cpu MHz\t\t: %u.%03u\n", freq / 1000, (freq % 1000)); } /* Cache size */ diff --git a/arch/x86/kernel/cpu/resctrl/Makefile b/arch/x86/kernel/cpu/resctrl/Makefile index 4a06c37b9cf1..0c13b0befd8a 100644 --- a/arch/x86/kernel/cpu/resctrl/Makefile +++ b/arch/x86/kernel/cpu/resctrl/Makefile @@ -1,4 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -obj-$(CONFIG_X86_CPU_RESCTRL) += core.o rdtgroup.o monitor.o -obj-$(CONFIG_X86_CPU_RESCTRL) += ctrlmondata.o pseudo_lock.o +obj-$(CONFIG_X86_CPU_RESCTRL) += core.o rdtgroup.o monitor.o +obj-$(CONFIG_X86_CPU_RESCTRL) += ctrlmondata.o +obj-$(CONFIG_RESCTRL_FS_PSEUDO_LOCK) += pseudo_lock.o CFLAGS_pseudo_lock.o = -I$(src) diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index 3d1735ed8d1f..cf29681d01e0 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -44,12 +44,6 @@ static DEFINE_MUTEX(domain_list_lock); DEFINE_PER_CPU(struct resctrl_pqr_state, pqr_state); /* - * Used to store the max resource name width and max resource data width - * to display the schemata in a tabular format - */ -int max_name_width, max_data_width; - -/* * Global boolean for rdt_alloc which is true if any * resource allocation is enabled. */ @@ -62,7 +56,7 @@ static void mba_wrmsr_amd(struct msr_param *m); #define ctrl_domain_init(id) LIST_HEAD_INIT(rdt_resources_all[id].r_resctrl.ctrl_domains) #define mon_domain_init(id) LIST_HEAD_INIT(rdt_resources_all[id].r_resctrl.mon_domains) -struct rdt_hw_resource rdt_resources_all[] = { +struct rdt_hw_resource rdt_resources_all[RDT_NUM_RESOURCES] = { [RDT_RESOURCE_L3] = { .r_resctrl = { @@ -72,9 +66,7 @@ struct rdt_hw_resource rdt_resources_all[] = { .mon_scope = RESCTRL_L3_CACHE, .ctrl_domains = ctrl_domain_init(RDT_RESOURCE_L3), .mon_domains = mon_domain_init(RDT_RESOURCE_L3), - .parse_ctrlval = parse_cbm, - .format_str = "%d=%0*x", - .fflags = RFTYPE_RES_CACHE, + .schema_fmt = RESCTRL_SCHEMA_BITMAP, }, .msr_base = MSR_IA32_L3_CBM_BASE, .msr_update = cat_wrmsr, @@ -86,9 +78,7 @@ struct rdt_hw_resource rdt_resources_all[] = { .name = "L2", .ctrl_scope = RESCTRL_L2_CACHE, .ctrl_domains = ctrl_domain_init(RDT_RESOURCE_L2), - .parse_ctrlval = parse_cbm, - .format_str = "%d=%0*x", - .fflags = RFTYPE_RES_CACHE, + .schema_fmt = RESCTRL_SCHEMA_BITMAP, }, .msr_base = MSR_IA32_L2_CBM_BASE, .msr_update = cat_wrmsr, @@ -100,9 +90,7 @@ struct rdt_hw_resource rdt_resources_all[] = { .name = "MB", .ctrl_scope = RESCTRL_L3_CACHE, .ctrl_domains = ctrl_domain_init(RDT_RESOURCE_MBA), - .parse_ctrlval = parse_bw, - .format_str = "%d=%*u", - .fflags = RFTYPE_RES_MB, + .schema_fmt = RESCTRL_SCHEMA_RANGE, }, }, [RDT_RESOURCE_SMBA] = @@ -112,9 +100,7 @@ struct rdt_hw_resource rdt_resources_all[] = { .name = "SMBA", .ctrl_scope = RESCTRL_L3_CACHE, .ctrl_domains = ctrl_domain_init(RDT_RESOURCE_SMBA), - .parse_ctrlval = parse_bw, - .format_str = "%d=%*u", - .fflags = RFTYPE_RES_MB, + .schema_fmt = RESCTRL_SCHEMA_RANGE, }, }, }; @@ -127,6 +113,14 @@ u32 resctrl_arch_system_num_rmid_idx(void) return r->num_rmid; } +struct rdt_resource *resctrl_arch_get_resource(enum resctrl_res_level l) +{ + if (l >= RDT_NUM_RESOURCES) + return NULL; + + return &rdt_resources_all[l].r_resctrl; +} + /* * cache_alloc_hsw_probe() - Have to probe for Intel haswell server CPUs * as they do not have CPUID enumeration support for Cache allocation. @@ -161,7 +155,6 @@ static inline void cache_alloc_hsw_probe(void) return; hw_res->num_closid = 4; - r->default_ctrl = max_cbm; r->cache.cbm_len = 20; r->cache.shareable_bits = 0xc0000; r->cache.min_cbm_bits = 2; @@ -174,7 +167,7 @@ static inline void cache_alloc_hsw_probe(void) bool is_mba_sc(struct rdt_resource *r) { if (!r) - return rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl.membw.mba_sc; + r = resctrl_arch_get_resource(RDT_RESOURCE_MBA); /* * The software controller support is only applicable to MBA resource. @@ -217,7 +210,7 @@ static __init bool __get_mem_config_intel(struct rdt_resource *r) cpuid_count(0x00000010, 3, &eax.full, &ebx, &ecx, &edx.full); hw_res->num_closid = edx.split.cos_max + 1; max_delay = eax.split.max_delay + 1; - r->default_ctrl = MAX_MBA_BW; + r->membw.max_bw = MAX_MBA_BW; r->membw.arch_needs_linear = true; if (ecx & MBA_IS_LINEAR) { r->membw.delay_linear = true; @@ -228,16 +221,12 @@ static __init bool __get_mem_config_intel(struct rdt_resource *r) return false; r->membw.arch_needs_linear = false; } - r->data_width = 3; if (boot_cpu_has(X86_FEATURE_PER_THREAD_MBA)) r->membw.throttle_mode = THREAD_THROTTLE_PER_THREAD; else r->membw.throttle_mode = THREAD_THROTTLE_MAX; - resctrl_file_fflags_init("thread_throttle_mode", - RFTYPE_CTRL_INFO | RFTYPE_RES_MB); - r->alloc_capable = true; return true; @@ -256,7 +245,7 @@ static __init bool __rdt_get_mem_config_amd(struct rdt_resource *r) cpuid_count(0x80000020, subleaf, &eax, &ebx, &ecx, &edx); hw_res->num_closid = edx + 1; - r->default_ctrl = 1 << eax; + r->membw.max_bw = 1 << eax; /* AMD does not use delay */ r->membw.delay_linear = false; @@ -269,8 +258,6 @@ static __init bool __rdt_get_mem_config_amd(struct rdt_resource *r) r->membw.throttle_mode = THREAD_THROTTLE_UNDEFINED; r->membw.min_bw = 0; r->membw.bw_gran = 1; - /* Max value is 2048, Data width should be 4 in decimal */ - r->data_width = 4; r->alloc_capable = true; @@ -283,14 +270,13 @@ static void rdt_get_cache_alloc_cfg(int idx, struct rdt_resource *r) union cpuid_0x10_1_eax eax; union cpuid_0x10_x_ecx ecx; union cpuid_0x10_x_edx edx; - u32 ebx; + u32 ebx, default_ctrl; cpuid_count(0x00000010, idx, &eax.full, &ebx, &ecx.full, &edx.full); hw_res->num_closid = edx.split.cos_max + 1; r->cache.cbm_len = eax.split.cbm_len + 1; - r->default_ctrl = BIT_MASK(eax.split.cbm_len + 1) - 1; - r->cache.shareable_bits = ebx & r->default_ctrl; - r->data_width = (r->cache.cbm_len + 3) / 4; + default_ctrl = BIT_MASK(eax.split.cbm_len + 1) - 1; + r->cache.shareable_bits = ebx & default_ctrl; if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) r->cache.arch_has_sparse_bitmasks = ecx.split.noncont; r->alloc_capable = true; @@ -337,7 +323,7 @@ static u32 delay_bw_map(unsigned long bw, struct rdt_resource *r) return MAX_MBA_BW - bw; pr_warn_once("Non Linear delay-bw map not supported but queried\n"); - return r->default_ctrl; + return MAX_MBA_BW; } static void mba_wrmsr_intel(struct msr_param *m) @@ -361,36 +347,6 @@ static void cat_wrmsr(struct msr_param *m) wrmsrl(hw_res->msr_base + i, hw_dom->ctrl_val[i]); } -struct rdt_ctrl_domain *get_ctrl_domain_from_cpu(int cpu, struct rdt_resource *r) -{ - struct rdt_ctrl_domain *d; - - lockdep_assert_cpus_held(); - - list_for_each_entry(d, &r->ctrl_domains, hdr.list) { - /* Find the domain that contains this CPU */ - if (cpumask_test_cpu(cpu, &d->hdr.cpu_mask)) - return d; - } - - return NULL; -} - -struct rdt_mon_domain *get_mon_domain_from_cpu(int cpu, struct rdt_resource *r) -{ - struct rdt_mon_domain *d; - - lockdep_assert_cpus_held(); - - list_for_each_entry(d, &r->mon_domains, hdr.list) { - /* Find the domain that contains this CPU */ - if (cpumask_test_cpu(cpu, &d->hdr.cpu_mask)) - return d; - } - - return NULL; -} - u32 resctrl_arch_get_num_closid(struct rdt_resource *r) { return resctrl_to_arch_res(r)->num_closid; @@ -405,36 +361,6 @@ void rdt_ctrl_update(void *arg) hw_res->msr_update(m); } -/* - * rdt_find_domain - Search for a domain id in a resource domain list. - * - * Search the domain list to find the domain id. If the domain id is - * found, return the domain. NULL otherwise. If the domain id is not - * found (and NULL returned) then the first domain with id bigger than - * the input id can be returned to the caller via @pos. - */ -struct rdt_domain_hdr *rdt_find_domain(struct list_head *h, int id, - struct list_head **pos) -{ - struct rdt_domain_hdr *d; - struct list_head *l; - - list_for_each(l, h) { - d = list_entry(l, struct rdt_domain_hdr, list); - /* When id is found, return its domain. */ - if (id == d->id) - return d; - /* Stop searching when finding id's position in sorted list. */ - if (id < d->id) - break; - } - - if (pos) - *pos = l; - - return NULL; -} - static void setup_default_ctrlval(struct rdt_resource *r, u32 *dc) { struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); @@ -446,7 +372,7 @@ static void setup_default_ctrlval(struct rdt_resource *r, u32 *dc) * For Memory Allocation: Set b/w requested to 100% */ for (i = 0; i < hw_res->num_closid; i++, dc++) - *dc = r->default_ctrl; + *dc = resctrl_get_default_ctrl(r); } static void ctrl_domain_free(struct rdt_hw_ctrl_domain *hw_dom) @@ -494,13 +420,13 @@ static int arch_domain_mbm_alloc(u32 num_rmid, struct rdt_hw_mon_domain *hw_dom) { size_t tsize; - if (is_mbm_total_enabled()) { + if (resctrl_arch_is_mbm_total_enabled()) { tsize = sizeof(*hw_dom->arch_mbm_total); hw_dom->arch_mbm_total = kcalloc(num_rmid, tsize, GFP_KERNEL); if (!hw_dom->arch_mbm_total) return -ENOMEM; } - if (is_mbm_local_enabled()) { + if (resctrl_arch_is_mbm_local_enabled()) { tsize = sizeof(*hw_dom->arch_mbm_local); hw_dom->arch_mbm_local = kcalloc(num_rmid, tsize, GFP_KERNEL); if (!hw_dom->arch_mbm_local) { @@ -545,7 +471,7 @@ static void domain_add_cpu_ctrl(int cpu, struct rdt_resource *r) return; } - hdr = rdt_find_domain(&r->ctrl_domains, id, &add_pos); + hdr = resctrl_find_domain(&r->ctrl_domains, id, &add_pos); if (hdr) { if (WARN_ON_ONCE(hdr->type != RESCTRL_CTRL_DOMAIN)) return; @@ -600,7 +526,7 @@ static void domain_add_cpu_mon(int cpu, struct rdt_resource *r) return; } - hdr = rdt_find_domain(&r->mon_domains, id, &add_pos); + hdr = resctrl_find_domain(&r->mon_domains, id, &add_pos); if (hdr) { if (WARN_ON_ONCE(hdr->type != RESCTRL_MON_DOMAIN)) return; @@ -665,7 +591,7 @@ static void domain_remove_cpu_ctrl(int cpu, struct rdt_resource *r) return; } - hdr = rdt_find_domain(&r->ctrl_domains, id, NULL); + hdr = resctrl_find_domain(&r->ctrl_domains, id, NULL); if (!hdr) { pr_warn("Can't find control domain for id=%d for CPU %d for resource %s\n", id, cpu, r->name); @@ -711,7 +637,7 @@ static void domain_remove_cpu_mon(int cpu, struct rdt_resource *r) return; } - hdr = rdt_find_domain(&r->mon_domains, id, NULL); + hdr = resctrl_find_domain(&r->mon_domains, id, NULL); if (!hdr) { pr_warn("Can't find monitor domain for id=%d for CPU %d for resource %s\n", id, cpu, r->name); @@ -786,20 +712,6 @@ static int resctrl_arch_offline_cpu(unsigned int cpu) return 0; } -/* - * Choose a width for the resource name and resource data based on the - * resource that has widest name and cbm. - */ -static __init void rdt_init_padding(void) -{ - struct rdt_resource *r; - - for_each_alloc_capable_rdt_resource(r) { - if (r->data_width > max_data_width) - max_data_width = r->data_width; - } -} - enum { RDT_FLAG_CMT, RDT_FLAG_MBM_TOTAL, @@ -885,6 +797,21 @@ bool __init rdt_cpu_has(int flag) return ret; } +__init bool resctrl_arch_is_evt_configurable(enum resctrl_event_id evt) +{ + if (!rdt_cpu_has(X86_FEATURE_BMEC)) + return false; + + switch (evt) { + case QOS_L3_MBM_TOTAL_EVENT_ID: + return rdt_cpu_has(X86_FEATURE_CQM_MBM_TOTAL); + case QOS_L3_MBM_LOCAL_EVENT_ID: + return rdt_cpu_has(X86_FEATURE_CQM_MBM_LOCAL); + default: + return false; + } +} + static __init bool get_mem_config(void) { struct rdt_hw_resource *hw_res = &rdt_resources_all[RDT_RESOURCE_MBA]; @@ -963,11 +890,6 @@ static __init bool get_rdt_mon_resources(void) if (!rdt_mon_features) return false; - if (is_mbm_local_enabled()) - mba_mbps_default_event = QOS_L3_MBM_LOCAL_EVENT_ID; - else if (is_mbm_total_enabled()) - mba_mbps_default_event = QOS_L3_MBM_TOTAL_EVENT_ID; - return !rdt_get_mon_l3_config(r); } @@ -1086,7 +1008,7 @@ void resctrl_cpu_detect(struct cpuinfo_x86 *c) } } -static int __init resctrl_late_init(void) +static int __init resctrl_arch_late_init(void) { struct rdt_resource *r; int state, ret; @@ -1102,8 +1024,6 @@ static int __init resctrl_late_init(void) if (!get_rdt_resources()) return -ENODEV; - rdt_init_padding(); - state = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/resctrl/cat:online:", resctrl_arch_online_cpu, @@ -1111,7 +1031,7 @@ static int __init resctrl_late_init(void) if (state < 0) return state; - ret = rdtgroup_init(); + ret = resctrl_init(); if (ret) { cpuhp_remove_state(state); return ret; @@ -1127,18 +1047,13 @@ static int __init resctrl_late_init(void) return 0; } -late_initcall(resctrl_late_init); +late_initcall(resctrl_arch_late_init); -static void __exit resctrl_exit(void) +static void __exit resctrl_arch_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(); + resctrl_exit(); } -__exitcall(resctrl_exit); +__exitcall(resctrl_arch_exit); diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c index 536351159cc2..0a0ac5f6112e 100644 --- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c +++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c @@ -23,6 +23,15 @@ #include "internal.h" +struct rdt_parse_data { + struct rdtgroup *rdtgrp; + char *buf; +}; + +typedef int (ctrlval_parser_t)(struct rdt_parse_data *data, + struct resctrl_schema *s, + struct rdt_ctrl_domain *d); + /* * Check whether MBA bandwidth percentage value is correct. The value is * checked against the minimum and max bandwidth values specified by the @@ -54,9 +63,9 @@ static bool bw_validate(char *buf, u32 *data, struct rdt_resource *r) return true; } - if (bw < r->membw.min_bw || bw > r->default_ctrl) { + if (bw < r->membw.min_bw || bw > r->membw.max_bw) { rdt_last_cmd_printf("MB value %u out of range [%d,%d]\n", - bw, r->membw.min_bw, r->default_ctrl); + bw, r->membw.min_bw, r->membw.max_bw); return false; } @@ -64,8 +73,8 @@ static bool bw_validate(char *buf, u32 *data, struct rdt_resource *r) return true; } -int parse_bw(struct rdt_parse_data *data, struct resctrl_schema *s, - struct rdt_ctrl_domain *d) +static int parse_bw(struct rdt_parse_data *data, struct resctrl_schema *s, + struct rdt_ctrl_domain *d) { struct resctrl_staged_config *cfg; u32 closid = data->rdtgrp->closid; @@ -104,8 +113,9 @@ int parse_bw(struct rdt_parse_data *data, struct resctrl_schema *s, */ static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r) { - unsigned long first_bit, zero_bit, val; + u32 supported_bits = BIT_MASK(r->cache.cbm_len) - 1; unsigned int cbm_len = r->cache.cbm_len; + unsigned long first_bit, zero_bit, val; int ret; ret = kstrtoul(buf, 16, &val); @@ -114,7 +124,7 @@ static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r) return false; } - if ((r->cache.min_cbm_bits > 0 && val == 0) || val > r->default_ctrl) { + if ((r->cache.min_cbm_bits > 0 && val == 0) || val > supported_bits) { rdt_last_cmd_puts("Mask out of range\n"); return false; } @@ -143,8 +153,8 @@ static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r) * Read one cache bit mask (hex). Check that it is valid for the current * resource type. */ -int parse_cbm(struct rdt_parse_data *data, struct resctrl_schema *s, - struct rdt_ctrl_domain *d) +static int parse_cbm(struct rdt_parse_data *data, struct resctrl_schema *s, + struct rdt_ctrl_domain *d) { struct rdtgroup *rdtgrp = data->rdtgrp; struct resctrl_staged_config *cfg; @@ -210,6 +220,7 @@ static int parse_line(char *line, struct resctrl_schema *s, struct rdtgroup *rdtgrp) { enum resctrl_conf_type t = s->conf_type; + ctrlval_parser_t *parse_ctrlval = NULL; struct resctrl_staged_config *cfg; struct rdt_resource *r = s->res; struct rdt_parse_data data; @@ -220,6 +231,18 @@ static int parse_line(char *line, struct resctrl_schema *s, /* Walking r->domains, ensure it can't race with cpuhp */ lockdep_assert_cpus_held(); + switch (r->schema_fmt) { + case RESCTRL_SCHEMA_BITMAP: + parse_ctrlval = &parse_cbm; + break; + case RESCTRL_SCHEMA_RANGE: + parse_ctrlval = &parse_bw; + break; + } + + if (WARN_ON_ONCE(!parse_ctrlval)) + return -EINVAL; + 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"); @@ -240,7 +263,7 @@ next: if (d->hdr.id == dom_id) { data.buf = dom; data.rdtgrp = rdtgrp; - if (r->parse_ctrlval(&data, s, d)) + if (parse_ctrlval(&data, s, d)) return -EINVAL; if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { cfg = &d->staged_config[t]; @@ -264,25 +287,12 @@ next: return -EINVAL; } -static u32 get_config_index(u32 closid, enum resctrl_conf_type type) -{ - switch (type) { - default: - case CDP_NONE: - return closid; - case CDP_CODE: - return closid * 2 + 1; - case CDP_DATA: - return closid * 2; - } -} - int resctrl_arch_update_one(struct rdt_resource *r, struct rdt_ctrl_domain *d, u32 closid, enum resctrl_conf_type t, u32 cfg_val) { struct rdt_hw_ctrl_domain *hw_dom = resctrl_to_arch_ctrl_dom(d); struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); - u32 idx = get_config_index(closid, t); + u32 idx = resctrl_get_config_index(closid, t); struct msr_param msr_param; if (!cpumask_test_cpu(smp_processor_id(), &d->hdr.cpu_mask)) @@ -319,7 +329,7 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid) if (!cfg->have_new_ctrl) continue; - idx = get_config_index(closid, t); + idx = resctrl_get_config_index(closid, t); if (cfg->new_ctrl == hw_dom->ctrl_val[idx]) continue; hw_dom->ctrl_val[idx] = cfg->new_ctrl; @@ -439,7 +449,7 @@ u32 resctrl_arch_get_config(struct rdt_resource *r, struct rdt_ctrl_domain *d, u32 closid, enum resctrl_conf_type type) { struct rdt_hw_ctrl_domain *hw_dom = resctrl_to_arch_ctrl_dom(d); - u32 idx = get_config_index(closid, type); + u32 idx = resctrl_get_config_index(closid, type); return hw_dom->ctrl_val[idx]; } @@ -465,8 +475,7 @@ static void show_doms(struct seq_file *s, struct resctrl_schema *schema, int clo ctrl_val = resctrl_arch_get_config(r, dom, closid, schema->conf_type); - seq_printf(s, r->format_str, dom->hdr.id, max_data_width, - ctrl_val); + seq_printf(s, schema->fmt_str, dom->hdr.id, ctrl_val); sep = true; } seq_puts(s, "\n"); @@ -537,12 +546,12 @@ ssize_t rdtgroup_mba_mbps_event_write(struct kernfs_open_file *of, rdt_last_cmd_clear(); if (!strcmp(buf, "mbm_local_bytes")) { - if (is_mbm_local_enabled()) + if (resctrl_arch_is_mbm_local_enabled()) rdtgrp->mba_mbps_event = QOS_L3_MBM_LOCAL_EVENT_ID; else ret = -EINVAL; } else if (!strcmp(buf, "mbm_total_bytes")) { - if (is_mbm_total_enabled()) + if (resctrl_arch_is_mbm_total_enabled()) rdtgrp->mba_mbps_event = QOS_L3_MBM_TOTAL_EVENT_ID; else ret = -EINVAL; @@ -588,6 +597,28 @@ int rdtgroup_mba_mbps_event_show(struct kernfs_open_file *of, return ret; } +struct rdt_domain_hdr *resctrl_find_domain(struct list_head *h, int id, + struct list_head **pos) +{ + struct rdt_domain_hdr *d; + struct list_head *l; + + list_for_each(l, h) { + d = list_entry(l, struct rdt_domain_hdr, list); + /* When id is found, return its domain. */ + if (id == d->id) + return d; + /* Stop searching when finding id's position in sorted list. */ + if (id < d->id) + break; + } + + if (pos) + *pos = l; + + return NULL; +} + void mon_event_read(struct rmid_read *rr, struct rdt_resource *r, struct rdt_mon_domain *d, struct rdtgroup *rdtgrp, cpumask_t *cpumask, int evtid, int first) @@ -649,7 +680,7 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg) resid = md.u.rid; domid = md.u.domid; evtid = md.u.evtid; - r = &rdt_resources_all[resid].r_resctrl; + r = resctrl_arch_get_resource(resid); if (md.u.sum) { /* @@ -673,7 +704,7 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg) * This file provides data from a single domain. Search * the resource to find the domain with "domid". */ - hdr = rdt_find_domain(&r->mon_domains, domid, NULL); + hdr = resctrl_find_domain(&r->mon_domains, domid, NULL); if (!hdr || WARN_ON_ONCE(hdr->type != RESCTRL_MON_DOMAIN)) { ret = -ENOENT; goto out; diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index 20c898f09b7e..eaae99602b61 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -32,30 +32,6 @@ */ #define MBM_CNTR_WIDTH_OFFSET_MAX (62 - MBM_CNTR_WIDTH_BASE) -/* Reads to Local DRAM Memory */ -#define READS_TO_LOCAL_MEM BIT(0) - -/* Reads to Remote DRAM Memory */ -#define READS_TO_REMOTE_MEM BIT(1) - -/* Non-Temporal Writes to Local Memory */ -#define NON_TEMP_WRITE_TO_LOCAL_MEM BIT(2) - -/* Non-Temporal Writes to Remote Memory */ -#define NON_TEMP_WRITE_TO_REMOTE_MEM BIT(3) - -/* Reads to Local Memory the system identifies as "Slow Memory" */ -#define READS_TO_LOCAL_S_MEM BIT(4) - -/* Reads to Remote Memory the system identifies as "Slow Memory" */ -#define READS_TO_REMOTE_S_MEM BIT(5) - -/* Dirty Victims to All Types of Memory */ -#define DIRTY_VICTIMS_TO_ALL_MEM BIT(6) - -/* 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 @@ -180,7 +156,6 @@ struct rmid_read { void *arch_mon_ctx; }; -extern unsigned int rdt_mon_features; extern struct list_head resctrl_schema_all; extern bool resctrl_mounted; @@ -234,43 +209,6 @@ struct mongroup { }; /** - * struct pseudo_lock_region - pseudo-lock region information - * @s: Resctrl schema for the resource to which this - * pseudo-locked region belongs - * @d: RDT domain to which this pseudo-locked region - * belongs - * @cbm: bitmask of the pseudo-locked region - * @lock_thread_wq: waitqueue used to wait on the pseudo-locking thread - * completion - * @thread_done: variable used by waitqueue to test if pseudo-locking - * thread completed - * @cpu: core associated with the cache on which the setup code - * will be run - * @line_size: size of the cache lines - * @size: size of pseudo-locked region in bytes - * @kmem: the kernel memory associated with pseudo-locked region - * @minor: minor number of character device associated with this - * region - * @debugfs_dir: pointer to this region's directory in the debugfs - * filesystem - * @pm_reqs: Power management QoS requests related to this region - */ -struct pseudo_lock_region { - struct resctrl_schema *s; - struct rdt_ctrl_domain *d; - u32 cbm; - wait_queue_head_t lock_thread_wq; - int thread_done; - int cpu; - unsigned int line_size; - unsigned int size; - void *kmem; - unsigned int minor; - struct dentry *debugfs_dir; - struct list_head pm_reqs; -}; - -/** * struct rdtgroup - store rdtgroup's data in resctrl file system. * @kn: kernfs node * @rdtgroup_list: linked list for all rdtgroups @@ -326,10 +264,7 @@ struct rdtgroup { /* List of all resource groups */ extern struct list_head rdt_all_groups; -extern int max_name_width, max_data_width; - -int __init rdtgroup_init(void); -void __exit rdtgroup_exit(void); +extern int max_name_width; /** * struct rftype - describe each file in the resctrl file system @@ -433,37 +368,6 @@ struct msr_param { u32 high; }; -static inline bool is_llc_occupancy_enabled(void) -{ - return (rdt_mon_features & (1 << QOS_L3_OCCUP_EVENT_ID)); -} - -static inline bool is_mbm_total_enabled(void) -{ - return (rdt_mon_features & (1 << QOS_L3_MBM_TOTAL_EVENT_ID)); -} - -static inline bool is_mbm_local_enabled(void) -{ - return (rdt_mon_features & (1 << QOS_L3_MBM_LOCAL_EVENT_ID)); -} - -static inline bool is_mbm_enabled(void) -{ - return (is_mbm_total_enabled() || is_mbm_local_enabled()); -} - -static inline bool is_mbm_event(int e) -{ - return (e >= QOS_L3_MBM_TOTAL_EVENT_ID && - e <= QOS_L3_MBM_LOCAL_EVENT_ID); -} - -struct rdt_parse_data { - struct rdtgroup *rdtgrp; - char *buf; -}; - /** * struct rdt_hw_resource - arch private attributes of a resctrl resource * @r_resctrl: Attributes of the resource used directly by resctrl. @@ -476,8 +380,6 @@ 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 @@ -491,7 +393,6 @@ struct rdt_hw_resource { void (*msr_update)(struct msr_param *m); unsigned int mon_scale; unsigned int mbm_width; - unsigned int mbm_cfg_mask; bool cdp_enabled; }; @@ -500,36 +401,18 @@ static inline struct rdt_hw_resource *resctrl_to_arch_res(struct rdt_resource *r return container_of(r, struct rdt_hw_resource, r_resctrl); } -int parse_cbm(struct rdt_parse_data *data, struct resctrl_schema *s, - struct rdt_ctrl_domain *d); -int parse_bw(struct rdt_parse_data *data, struct resctrl_schema *s, - struct rdt_ctrl_domain *d); - extern struct mutex rdtgroup_mutex; +static inline const char *rdt_kn_name(const struct kernfs_node *kn) +{ + return rcu_dereference_check(kn->name, lockdep_is_held(&rdtgroup_mutex)); +} + extern struct rdt_hw_resource rdt_resources_all[]; extern struct rdtgroup rdtgroup_default; extern struct dentry *debugfs_resctrl; extern enum resctrl_event_id mba_mbps_default_event; -enum resctrl_res_level { - RDT_RESOURCE_L3, - RDT_RESOURCE_L2, - RDT_RESOURCE_MBA, - RDT_RESOURCE_SMBA, - - /* Must be the last */ - RDT_NUM_RESOURCES, -}; - -static inline struct rdt_resource *resctrl_inc(struct rdt_resource *res) -{ - struct rdt_hw_resource *hw_res = resctrl_to_arch_res(res); - - hw_res++; - return &hw_res->r_resctrl; -} - static inline bool resctrl_arch_get_cdp_enabled(enum resctrl_res_level l) { return rdt_resources_all[l].cdp_enabled; @@ -539,27 +422,6 @@ int resctrl_arch_set_cdp_enabled(enum resctrl_res_level l, bool enable); void arch_mon_domain_online(struct rdt_resource *r, struct rdt_mon_domain *d); -/* - * To return the common struct rdt_resource, which is contained in struct - * rdt_hw_resource, walk the resctrl member of struct rdt_hw_resource. - */ -#define for_each_rdt_resource(r) \ - for (r = &rdt_resources_all[0].r_resctrl; \ - r <= &rdt_resources_all[RDT_NUM_RESOURCES - 1].r_resctrl; \ - r = resctrl_inc(r)) - -#define for_each_capable_rdt_resource(r) \ - for_each_rdt_resource(r) \ - if (r->alloc_capable || r->mon_capable) - -#define for_each_alloc_capable_rdt_resource(r) \ - for_each_rdt_resource(r) \ - if (r->alloc_capable) - -#define for_each_mon_capable_rdt_resource(r) \ - for_each_rdt_resource(r) \ - if (r->mon_capable) - /* CPUID.(EAX=10H, ECX=ResID=1).EAX */ union cpuid_0x10_1_eax { struct { @@ -604,8 +466,6 @@ void rdtgroup_kn_unlock(struct kernfs_node *kn); int rdtgroup_kn_mode_restrict(struct rdtgroup *r, const char *name); int rdtgroup_kn_mode_restore(struct rdtgroup *r, const char *name, umode_t mask); -struct rdt_domain_hdr *rdt_find_domain(struct list_head *h, int id, - struct list_head **pos); ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off); int rdtgroup_schemata_show(struct kernfs_open_file *of, @@ -620,28 +480,19 @@ unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, struct rdt_ctrl_domain unsigned long cbm); enum rdtgrp_mode rdtgroup_mode_by_closid(int closid); int rdtgroup_tasks_assigned(struct rdtgroup *r); -int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp); -int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp); -bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_ctrl_domain *d, unsigned long cbm); -bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_ctrl_domain *d); -int rdt_pseudo_lock_init(void); -void rdt_pseudo_lock_release(void); -int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp); -void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp); -struct rdt_ctrl_domain *get_ctrl_domain_from_cpu(int cpu, struct rdt_resource *r); -struct rdt_mon_domain *get_mon_domain_from_cpu(int cpu, struct rdt_resource *r); int closids_supported(void); void closid_free(int closid); 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); +void resctrl_mon_resource_exit(void); bool __init rdt_cpu_has(int flag); void mon_event_count(void *info); int rdtgroup_mondata_show(struct seq_file *m, void *arg); void mon_event_read(struct rmid_read *rr, struct rdt_resource *r, struct rdt_mon_domain *d, struct rdtgroup *rdtgrp, cpumask_t *cpumask, int evtid, int first); +int __init resctrl_mon_resource_init(void); void mbm_setup_overflow_handler(struct rdt_mon_domain *dom, unsigned long delay_ms, int exclude_cpu); @@ -658,4 +509,45 @@ void resctrl_file_fflags_init(const char *config, unsigned long fflags); void rdt_staged_configs_clear(void); bool closid_allocated(unsigned int closid); int resctrl_find_cleanest_closid(void); + +#ifdef CONFIG_RESCTRL_FS_PSEUDO_LOCK +int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp); +int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp); +bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_ctrl_domain *d, unsigned long cbm); +bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_ctrl_domain *d); +int rdt_pseudo_lock_init(void); +void rdt_pseudo_lock_release(void); +int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp); +void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp); +#else +static inline int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp) +{ + return -EOPNOTSUPP; +} + +static inline int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp) +{ + return -EOPNOTSUPP; +} + +static inline bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_ctrl_domain *d, unsigned long cbm) +{ + return false; +} + +static inline bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_ctrl_domain *d) +{ + return false; +} + +static inline int rdt_pseudo_lock_init(void) { return 0; } +static inline void rdt_pseudo_lock_release(void) { } +static inline int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp) +{ + return -EOPNOTSUPP; +} + +static inline void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp) { } +#endif /* CONFIG_RESCTRL_FS_PSEUDO_LOCK */ + #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 94a1d9780461..a93ed7d2a160 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -295,11 +295,11 @@ void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_mon_domain * { struct rdt_hw_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d); - if (is_mbm_total_enabled()) + if (resctrl_arch_is_mbm_total_enabled()) memset(hw_dom->arch_mbm_total, 0, sizeof(*hw_dom->arch_mbm_total) * r->num_rmid); - if (is_mbm_local_enabled()) + if (resctrl_arch_is_mbm_local_enabled()) memset(hw_dom->arch_mbm_local, 0, sizeof(*hw_dom->arch_mbm_local) * r->num_rmid); } @@ -365,7 +365,7 @@ static void limbo_release_entry(struct rmid_entry *entry) */ void __check_limbo(struct rdt_mon_domain *d, bool force_free) { - struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; + struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_L3); u32 idx_limit = resctrl_arch_system_num_rmid_idx(); struct rmid_entry *entry; u32 idx, cur_idx = 1; @@ -521,7 +521,7 @@ int alloc_rmid(u32 closid) static void add_rmid_to_limbo(struct rmid_entry *entry) { - struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; + struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_L3); struct rdt_mon_domain *d; u32 idx; @@ -569,7 +569,7 @@ void free_rmid(u32 closid, u32 rmid) entry = __rmid_entry(idx); - if (is_llc_occupancy_enabled()) + if (resctrl_arch_is_llc_occupancy_enabled()) add_rmid_to_limbo(entry); else list_add_tail(&entry->list, &rmid_free_lru); @@ -718,6 +718,22 @@ void mon_event_count(void *info) rr->err = 0; } +static struct rdt_ctrl_domain *get_ctrl_domain_from_cpu(int cpu, + struct rdt_resource *r) +{ + struct rdt_ctrl_domain *d; + + lockdep_assert_cpus_held(); + + list_for_each_entry(d, &r->ctrl_domains, hdr.list) { + /* Find the domain that contains this CPU */ + if (cpumask_test_cpu(cpu, &d->hdr.cpu_mask)) + return d; + } + + return NULL; +} + /* * Feedback loop for MBA software controller (mba_sc) * @@ -761,7 +777,7 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_mon_domain *dom_mbm) struct rdtgroup *entry; u32 cur_bw, user_bw; - r_mba = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl; + r_mba = resctrl_arch_get_resource(RDT_RESOURCE_MBA); evt_id = rgrp->mba_mbps_event; closid = rgrp->closid; @@ -852,10 +868,10 @@ static void mbm_update(struct rdt_resource *r, struct rdt_mon_domain *d, * This is protected from concurrent reads from user as both * the user and overflow handler hold the global mutex. */ - if (is_mbm_total_enabled()) + if (resctrl_arch_is_mbm_total_enabled()) mbm_update_one_event(r, d, closid, rmid, QOS_L3_MBM_TOTAL_EVENT_ID); - if (is_mbm_local_enabled()) + if (resctrl_arch_is_mbm_local_enabled()) mbm_update_one_event(r, d, closid, rmid, QOS_L3_MBM_LOCAL_EVENT_ID); } @@ -925,7 +941,7 @@ void mbm_handle_overflow(struct work_struct *work) if (!resctrl_mounted || !resctrl_arch_mon_capable()) goto out_unlock; - r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; + r = resctrl_arch_get_resource(RDT_RESOURCE_L3); d = container_of(work, struct rdt_mon_domain, mbm_over.work); list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) { @@ -1027,7 +1043,7 @@ static int dom_data_init(struct rdt_resource *r) /* * 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(). + * control group, which will be setup later in resctrl_init(). */ idx = resctrl_arch_rmid_idx_encode(RESCTRL_RESERVED_CLOSID, RESCTRL_RESERVED_RMID); @@ -1040,10 +1056,13 @@ out_unlock: return err; } -static void __exit dom_data_exit(void) +static void dom_data_exit(struct rdt_resource *r) { mutex_lock(&rdtgroup_mutex); + if (!r->mon_capable) + goto out_unlock; + if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) { kfree(closid_num_dirty_rmid); closid_num_dirty_rmid = NULL; @@ -1052,6 +1071,7 @@ static void __exit dom_data_exit(void) kfree(rmid_ptrs); rmid_ptrs = NULL; +out_unlock: mutex_unlock(&rdtgroup_mutex); } @@ -1081,11 +1101,11 @@ static void l3_mon_evt_init(struct rdt_resource *r) { INIT_LIST_HEAD(&r->evt_list); - if (is_llc_occupancy_enabled()) + if (resctrl_arch_is_llc_occupancy_enabled()) list_add_tail(&llc_occupancy_event.list, &r->evt_list); - if (is_mbm_total_enabled()) + if (resctrl_arch_is_mbm_total_enabled()) list_add_tail(&mbm_total_event.list, &r->evt_list); - if (is_mbm_local_enabled()) + if (resctrl_arch_is_mbm_local_enabled()) list_add_tail(&mbm_local_event.list, &r->evt_list); } @@ -1172,12 +1192,56 @@ static __init int snc_get_config(void) return ret; } +/** + * resctrl_mon_resource_init() - Initialise global monitoring structures. + * + * Allocate and initialise global monitor resources that do not belong to a + * specific domain. i.e. the rmid_ptrs[] used for the limbo and free lists. + * Called once during boot after the struct rdt_resource's have been configured + * but before the filesystem is mounted. + * Resctrl's cpuhp callbacks may be called before this point to bring a domain + * online. + * + * Returns 0 for success, or -ENOMEM. + */ +int __init resctrl_mon_resource_init(void) +{ + struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_L3); + int ret; + + if (!r->mon_capable) + return 0; + + ret = dom_data_init(r); + if (ret) + return ret; + + l3_mon_evt_init(r); + + if (resctrl_arch_is_evt_configurable(QOS_L3_MBM_TOTAL_EVENT_ID)) { + mbm_total_event.configurable = true; + resctrl_file_fflags_init("mbm_total_bytes_config", + RFTYPE_MON_INFO | RFTYPE_RES_CACHE); + } + if (resctrl_arch_is_evt_configurable(QOS_L3_MBM_LOCAL_EVENT_ID)) { + mbm_local_event.configurable = true; + resctrl_file_fflags_init("mbm_local_bytes_config", + RFTYPE_MON_INFO | RFTYPE_RES_CACHE); + } + + if (resctrl_arch_is_mbm_local_enabled()) + mba_mbps_default_event = QOS_L3_MBM_LOCAL_EVENT_ID; + else if (resctrl_arch_is_mbm_total_enabled()) + mba_mbps_default_event = QOS_L3_MBM_TOTAL_EVENT_ID; + + return 0; +} + int __init rdt_get_mon_l3_config(struct rdt_resource *r) { unsigned int mbm_offset = boot_cpu_data.x86_cache_mbm_width_offset; struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); unsigned int threshold; - int ret; snc_nodes_per_l3_cache = snc_get_config(); @@ -1207,39 +1271,24 @@ int __init rdt_get_mon_l3_config(struct rdt_resource *r) */ resctrl_rmid_realloc_threshold = resctrl_arch_round_mon_val(threshold); - ret = dom_data_init(r); - if (ret) - 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; - resctrl_file_fflags_init("mbm_total_bytes_config", - RFTYPE_MON_INFO | RFTYPE_RES_CACHE); - } - if (rdt_cpu_has(X86_FEATURE_CQM_MBM_LOCAL)) { - mbm_local_event.configurable = true; - resctrl_file_fflags_init("mbm_local_bytes_config", - RFTYPE_MON_INFO | RFTYPE_RES_CACHE); - } + r->mbm_cfg_mask = ecx & MAX_EVT_CONFIG_BITS; } - l3_mon_evt_init(r); - r->mon_capable = true; return 0; } -void __exit rdt_put_mon_l3_config(void) +void resctrl_mon_resource_exit(void) { - dom_data_exit(); + struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_L3); + + dom_data_exit(r); } void __init intel_rdt_mbm_apply_quirk(void) diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c index 42cc162f7fc9..92ea1472bde9 100644 --- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c +++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c @@ -52,7 +52,8 @@ static char *pseudo_lock_devnode(const struct device *dev, umode_t *mode) rdtgrp = dev_get_drvdata(dev); if (mode) *mode = 0600; - return kasprintf(GFP_KERNEL, "pseudo_lock/%s", rdtgrp->kn->name); + guard(mutex)(&rdtgroup_mutex); + return kasprintf(GFP_KERNEL, "pseudo_lock/%s", rdt_kn_name(rdtgrp->kn)); } static const struct class pseudo_lock_class = { @@ -61,7 +62,8 @@ static const struct class pseudo_lock_class = { }; /** - * get_prefetch_disable_bits - prefetch disable bits of supported platforms + * resctrl_arch_get_prefetch_disable_bits - prefetch disable bits of supported + * platforms * @void: It takes no parameters. * * Capture the list of platforms that have been validated to support @@ -75,14 +77,16 @@ static const struct class pseudo_lock_class = { * in the SDM. * * When adding a platform here also add support for its cache events to - * measure_cycles_perf_fn() + * resctrl_arch_measure_l*_residency() * * Return: * If platform is supported, the bits to disable hardware prefetchers, 0 * if platform is not supported. */ -static u64 get_prefetch_disable_bits(void) +u64 resctrl_arch_get_prefetch_disable_bits(void) { + prefetch_disable_bits = 0; + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL || boot_cpu_data.x86 != 6) return 0; @@ -98,7 +102,8 @@ static u64 get_prefetch_disable_bits(void) * 3 DCU IP Prefetcher Disable (R/W) * 63:4 Reserved */ - return 0xF; + prefetch_disable_bits = 0xF; + break; case INTEL_ATOM_GOLDMONT: case INTEL_ATOM_GOLDMONT_PLUS: /* @@ -109,10 +114,11 @@ static u64 get_prefetch_disable_bits(void) * 2 DCU Hardware Prefetcher Disable (R/W) * 63:3 Reserved */ - return 0x5; + prefetch_disable_bits = 0x5; + break; } - return 0; + return prefetch_disable_bits; } /** @@ -408,8 +414,8 @@ static void pseudo_lock_free(struct rdtgroup *rdtgrp) } /** - * pseudo_lock_fn - Load kernel memory into cache - * @_rdtgrp: resource group to which pseudo-lock region belongs + * resctrl_arch_pseudo_lock_fn - Load kernel memory into cache + * @_plr: the pseudo-lock region descriptor * * This is the core pseudo-locking flow. * @@ -426,10 +432,9 @@ static void pseudo_lock_free(struct rdtgroup *rdtgrp) * * Return: 0. Waiter on waitqueue will be woken on completion. */ -static int pseudo_lock_fn(void *_rdtgrp) +int resctrl_arch_pseudo_lock_fn(void *_plr) { - struct rdtgroup *rdtgrp = _rdtgrp; - struct pseudo_lock_region *plr = rdtgrp->plr; + struct pseudo_lock_region *plr = _plr; u32 rmid_p, closid_p; unsigned long i; u64 saved_msr; @@ -489,7 +494,8 @@ static int pseudo_lock_fn(void *_rdtgrp) * pseudo-locked followed by reading of kernel memory to load it * into the cache. */ - __wrmsr(MSR_IA32_PQR_ASSOC, rmid_p, rdtgrp->closid); + __wrmsr(MSR_IA32_PQR_ASSOC, rmid_p, plr->closid); + /* * Cache was flushed earlier. Now access kernel memory to read it * into cache region associated with just activated plr->closid. @@ -712,8 +718,7 @@ int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp) * Not knowing the bits to disable prefetching implies that this * platform does not support Cache Pseudo-Locking. */ - prefetch_disable_bits = get_prefetch_disable_bits(); - if (prefetch_disable_bits == 0) { + if (resctrl_arch_get_prefetch_disable_bits() == 0) { rdt_last_cmd_puts("Pseudo-locking not supported\n"); return -EINVAL; } @@ -872,7 +877,8 @@ bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_ctrl_domain *d) } /** - * measure_cycles_lat_fn - Measure cycle latency to read pseudo-locked memory + * resctrl_arch_measure_cycles_lat_fn - Measure cycle latency to read + * pseudo-locked memory * @_plr: pseudo-lock region to measure * * There is no deterministic way to test if a memory region is cached. One @@ -885,7 +891,7 @@ bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_ctrl_domain *d) * * Return: 0. Waiter on waitqueue will be woken on completion. */ -static int measure_cycles_lat_fn(void *_plr) +int resctrl_arch_measure_cycles_lat_fn(void *_plr) { struct pseudo_lock_region *plr = _plr; u32 saved_low, saved_high; @@ -1069,7 +1075,7 @@ out: return 0; } -static int measure_l2_residency(void *_plr) +int resctrl_arch_measure_l2_residency(void *_plr) { struct pseudo_lock_region *plr = _plr; struct residency_counts counts = {0}; @@ -1107,7 +1113,7 @@ out: return 0; } -static int measure_l3_residency(void *_plr) +int resctrl_arch_measure_l3_residency(void *_plr) { struct pseudo_lock_region *plr = _plr; struct residency_counts counts = {0}; @@ -1205,14 +1211,14 @@ static int pseudo_lock_measure_cycles(struct rdtgroup *rdtgrp, int sel) plr->cpu = cpu; if (sel == 1) - thread = kthread_run_on_cpu(measure_cycles_lat_fn, plr, - cpu, "pseudo_lock_measure/%u"); + thread = kthread_run_on_cpu(resctrl_arch_measure_cycles_lat_fn, + plr, cpu, "pseudo_lock_measure/%u"); else if (sel == 2) - thread = kthread_run_on_cpu(measure_l2_residency, plr, - cpu, "pseudo_lock_measure/%u"); + thread = kthread_run_on_cpu(resctrl_arch_measure_l2_residency, + plr, cpu, "pseudo_lock_measure/%u"); else if (sel == 3) - thread = kthread_run_on_cpu(measure_l3_residency, plr, - cpu, "pseudo_lock_measure/%u"); + thread = kthread_run_on_cpu(resctrl_arch_measure_l3_residency, + plr, cpu, "pseudo_lock_measure/%u"); else goto out; @@ -1293,6 +1299,7 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp) struct task_struct *thread; unsigned int new_minor; struct device *dev; + char *kn_name __free(kfree) = NULL; int ret; ret = pseudo_lock_region_alloc(plr); @@ -1304,10 +1311,15 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp) ret = -EINVAL; goto out_region; } + kn_name = kstrdup(rdt_kn_name(rdtgrp->kn), GFP_KERNEL); + if (!kn_name) { + ret = -ENOMEM; + goto out_cstates; + } plr->thread_done = 0; - thread = kthread_run_on_cpu(pseudo_lock_fn, rdtgrp, + thread = kthread_run_on_cpu(resctrl_arch_pseudo_lock_fn, plr, plr->cpu, "pseudo_lock/%u"); if (IS_ERR(thread)) { ret = PTR_ERR(thread); @@ -1348,8 +1360,7 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp) mutex_unlock(&rdtgroup_mutex); if (!IS_ERR_OR_NULL(debugfs_resctrl)) { - plr->debugfs_dir = debugfs_create_dir(rdtgrp->kn->name, - debugfs_resctrl); + plr->debugfs_dir = debugfs_create_dir(kn_name, debugfs_resctrl); if (!IS_ERR_OR_NULL(plr->debugfs_dir)) debugfs_create_file("pseudo_lock_measure", 0200, plr->debugfs_dir, rdtgrp, @@ -1358,7 +1369,7 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp) dev = device_create(&pseudo_lock_class, NULL, MKDEV(pseudo_lock_major, new_minor), - rdtgrp, "%s", rdtgrp->kn->name); + rdtgrp, "%s", kn_name); mutex_lock(&rdtgroup_mutex); diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 6419e04d8a7b..93ec829015f1 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -57,6 +57,12 @@ static struct kernfs_node *kn_mongrp; /* Kernel fs node for "mon_data" directory under root */ static struct kernfs_node *kn_mondata; +/* + * Used to store the max resource name width to display the schemata names in + * a tabular format. + */ +int max_name_width; + static struct seq_buf last_cmd_status; static char last_cmd_status_buf[512]; @@ -111,6 +117,18 @@ void rdt_staged_configs_clear(void) } } +static bool resctrl_is_mbm_enabled(void) +{ + return (resctrl_arch_is_mbm_total_enabled() || + resctrl_arch_is_mbm_local_enabled()); +} + +static bool resctrl_is_mbm_event(int e) +{ + return (e >= QOS_L3_MBM_TOTAL_EVENT_ID && + e <= QOS_L3_MBM_LOCAL_EVENT_ID); +} + /* * Trivial allocator for CLOSIDs. Since h/w only supports a small number, * we can keep a bitmap of free CLOSIDs in a single integer. @@ -157,7 +175,8 @@ static int closid_alloc(void) lockdep_assert_held(&rdtgroup_mutex); - if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) { + if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID) && + resctrl_arch_is_llc_occupancy_enabled()) { cleanest_closid = resctrl_find_cleanest_closid(); if (cleanest_closid < 0) return cleanest_closid; @@ -348,13 +367,13 @@ static int rdtgroup_cpus_show(struct kernfs_open_file *of, * from update_closid_rmid() is protected against __switch_to() because * preemption is disabled. */ -static void update_cpu_closid_rmid(void *info) +void resctrl_arch_sync_cpu_closid_rmid(void *info) { - struct rdtgroup *r = info; + struct resctrl_cpu_defaults *r = info; if (r) { this_cpu_write(pqr_state.default_closid, r->closid); - this_cpu_write(pqr_state.default_rmid, r->mon.rmid); + this_cpu_write(pqr_state.default_rmid, r->rmid); } /* @@ -369,11 +388,20 @@ static void update_cpu_closid_rmid(void *info) * Update the PGR_ASSOC MSR on all cpus in @cpu_mask, * * Per task closids/rmids must have been set up before calling this function. + * @r may be NULL. */ static void update_closid_rmid(const struct cpumask *cpu_mask, struct rdtgroup *r) { - on_each_cpu_mask(cpu_mask, update_cpu_closid_rmid, r, 1); + struct resctrl_cpu_defaults defaults, *p = NULL; + + if (r) { + defaults.closid = r->closid; + defaults.rmid = r->mon.rmid; + p = &defaults; + } + + on_each_cpu_mask(cpu_mask, resctrl_arch_sync_cpu_closid_rmid, p, 1); } static int cpus_mon_write(struct rdtgroup *rdtgrp, cpumask_var_t newmask, @@ -916,14 +944,14 @@ int proc_resctrl_show(struct seq_file *s, struct pid_namespace *ns, continue; seq_printf(s, "res:%s%s\n", (rdtg == &rdtgroup_default) ? "/" : "", - rdtg->kn->name); + rdt_kn_name(rdtg->kn)); seq_puts(s, "mon:"); list_for_each_entry(crg, &rdtg->mon.crdtgrp_list, mon.crdtgrp_list) { if (!resctrl_arch_match_rmid(tsk, crg->mon.parent->closid, crg->mon.rmid)) continue; - seq_printf(s, "%s", crg->kn->name); + seq_printf(s, "%s", rdt_kn_name(crg->kn)); break; } seq_putc(s, '\n'); @@ -956,10 +984,20 @@ static int rdt_last_cmd_status_show(struct kernfs_open_file *of, return 0; } +static void *rdt_kn_parent_priv(struct kernfs_node *kn) +{ + /* + * The parent pointer is only valid within RCU section since it can be + * replaced. + */ + guard(rcu)(); + return rcu_dereference(kn->__parent)->priv; +} + static int rdt_num_closids_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { - struct resctrl_schema *s = of->kn->parent->priv; + struct resctrl_schema *s = rdt_kn_parent_priv(of->kn); seq_printf(seq, "%u\n", s->num_closid); return 0; @@ -968,17 +1006,17 @@ static int rdt_num_closids_show(struct kernfs_open_file *of, static int rdt_default_ctrl_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { - struct resctrl_schema *s = of->kn->parent->priv; + struct resctrl_schema *s = rdt_kn_parent_priv(of->kn); struct rdt_resource *r = s->res; - seq_printf(seq, "%x\n", r->default_ctrl); + seq_printf(seq, "%x\n", resctrl_get_default_ctrl(r)); return 0; } static int rdt_min_cbm_bits_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { - struct resctrl_schema *s = of->kn->parent->priv; + struct resctrl_schema *s = rdt_kn_parent_priv(of->kn); struct rdt_resource *r = s->res; seq_printf(seq, "%u\n", r->cache.min_cbm_bits); @@ -988,7 +1026,7 @@ static int rdt_min_cbm_bits_show(struct kernfs_open_file *of, static int rdt_shareable_bits_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { - struct resctrl_schema *s = of->kn->parent->priv; + struct resctrl_schema *s = rdt_kn_parent_priv(of->kn); struct rdt_resource *r = s->res; seq_printf(seq, "%x\n", r->cache.shareable_bits); @@ -1012,7 +1050,7 @@ static int rdt_shareable_bits_show(struct kernfs_open_file *of, static int rdt_bit_usage_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { - struct resctrl_schema *s = of->kn->parent->priv; + struct resctrl_schema *s = rdt_kn_parent_priv(of->kn); /* * Use unsigned long even though only 32 bits are used to ensure * test_bit() is used safely. @@ -1094,7 +1132,7 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of, static int rdt_min_bw_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { - struct resctrl_schema *s = of->kn->parent->priv; + struct resctrl_schema *s = rdt_kn_parent_priv(of->kn); struct rdt_resource *r = s->res; seq_printf(seq, "%u\n", r->membw.min_bw); @@ -1104,7 +1142,7 @@ static int rdt_min_bw_show(struct kernfs_open_file *of, static int rdt_num_rmids_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { - struct rdt_resource *r = of->kn->parent->priv; + struct rdt_resource *r = rdt_kn_parent_priv(of->kn); seq_printf(seq, "%d\n", r->num_rmid); @@ -1114,7 +1152,7 @@ static int rdt_num_rmids_show(struct kernfs_open_file *of, static int rdt_mon_features_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { - struct rdt_resource *r = of->kn->parent->priv; + struct rdt_resource *r = rdt_kn_parent_priv(of->kn); struct mon_evt *mevt; list_for_each_entry(mevt, &r->evt_list, list) { @@ -1129,7 +1167,7 @@ static int rdt_mon_features_show(struct kernfs_open_file *of, static int rdt_bw_gran_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { - struct resctrl_schema *s = of->kn->parent->priv; + struct resctrl_schema *s = rdt_kn_parent_priv(of->kn); struct rdt_resource *r = s->res; seq_printf(seq, "%u\n", r->membw.bw_gran); @@ -1139,7 +1177,7 @@ static int rdt_bw_gran_show(struct kernfs_open_file *of, static int rdt_delay_linear_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { - struct resctrl_schema *s = of->kn->parent->priv; + struct resctrl_schema *s = rdt_kn_parent_priv(of->kn); struct rdt_resource *r = s->res; seq_printf(seq, "%u\n", r->membw.delay_linear); @@ -1157,13 +1195,22 @@ static int max_threshold_occ_show(struct kernfs_open_file *of, static int rdt_thread_throttle_mode_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { - struct resctrl_schema *s = of->kn->parent->priv; + struct resctrl_schema *s = rdt_kn_parent_priv(of->kn); struct rdt_resource *r = s->res; - if (r->membw.throttle_mode == THREAD_THROTTLE_PER_THREAD) + switch (r->membw.throttle_mode) { + case THREAD_THROTTLE_PER_THREAD: seq_puts(seq, "per-thread\n"); - else + return 0; + case THREAD_THROTTLE_MAX: seq_puts(seq, "max\n"); + return 0; + case THREAD_THROTTLE_UNDEFINED: + seq_puts(seq, "undefined\n"); + return 0; + } + + WARN_ON_ONCE(1); return 0; } @@ -1222,7 +1269,7 @@ static enum resctrl_conf_type resctrl_peer_type(enum resctrl_conf_type my_type) static int rdt_has_sparse_bitmasks_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { - struct resctrl_schema *s = of->kn->parent->priv; + struct resctrl_schema *s = rdt_kn_parent_priv(of->kn); struct rdt_resource *r = s->res; seq_printf(seq, "%u\n", r->cache.arch_has_sparse_bitmasks); @@ -1425,7 +1472,8 @@ static ssize_t rdtgroup_mode_write(struct kernfs_open_file *of, goto out; } rdtgrp->mode = RDT_MODE_EXCLUSIVE; - } else if (!strcmp(buf, "pseudo-locksetup")) { + } else if (IS_ENABLED(CONFIG_RESCTRL_FS_PSEUDO_LOCK) && + !strcmp(buf, "pseudo-locksetup")) { ret = rdtgroup_locksetup_enter(rdtgrp); if (ret) goto out; @@ -1552,11 +1600,6 @@ out: return ret; } -struct mon_config_info { - u32 evtid; - u32 mon_config; -}; - #define INVALID_CONFIG_INDEX UINT_MAX /** @@ -1581,31 +1624,32 @@ static inline unsigned int mon_event_config_index_get(u32 evtid) } } -static void mon_event_config_read(void *info) +void resctrl_arch_mon_event_config_read(void *_config_info) { - struct mon_config_info *mon_info = info; + struct resctrl_mon_config_info *config_info = _config_info; unsigned int index; u64 msrval; - index = mon_event_config_index_get(mon_info->evtid); + index = mon_event_config_index_get(config_info->evtid); if (index == INVALID_CONFIG_INDEX) { - pr_warn_once("Invalid event id %d\n", mon_info->evtid); + pr_warn_once("Invalid event id %d\n", config_info->evtid); return; } rdmsrl(MSR_IA32_EVT_CFG_BASE + index, msrval); /* Report only the valid event configuration bits */ - mon_info->mon_config = msrval & MAX_EVT_CONFIG_BITS; + config_info->mon_config = msrval & MAX_EVT_CONFIG_BITS; } -static void mondata_config_read(struct rdt_mon_domain *d, struct mon_config_info *mon_info) +static void mondata_config_read(struct resctrl_mon_config_info *mon_info) { - smp_call_function_any(&d->hdr.cpu_mask, mon_event_config_read, mon_info, 1); + smp_call_function_any(&mon_info->d->hdr.cpu_mask, + resctrl_arch_mon_event_config_read, mon_info, 1); } static int mbm_config_show(struct seq_file *s, struct rdt_resource *r, u32 evtid) { - struct mon_config_info mon_info; + struct resctrl_mon_config_info mon_info; struct rdt_mon_domain *dom; bool sep = false; @@ -1616,9 +1660,11 @@ static int mbm_config_show(struct seq_file *s, struct rdt_resource *r, u32 evtid if (sep) seq_puts(s, ";"); - memset(&mon_info, 0, sizeof(struct mon_config_info)); + memset(&mon_info, 0, sizeof(struct resctrl_mon_config_info)); + mon_info.r = r; + mon_info.d = dom; mon_info.evtid = evtid; - mondata_config_read(dom, &mon_info); + mondata_config_read(&mon_info); seq_printf(s, "%d=0x%02x", dom->hdr.id, mon_info.mon_config); sep = true; @@ -1634,7 +1680,7 @@ static int mbm_config_show(struct seq_file *s, struct rdt_resource *r, u32 evtid static int mbm_total_bytes_config_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { - struct rdt_resource *r = of->kn->parent->priv; + struct rdt_resource *r = rdt_kn_parent_priv(of->kn); mbm_config_show(seq, r, QOS_L3_MBM_TOTAL_EVENT_ID); @@ -1644,37 +1690,39 @@ static int mbm_total_bytes_config_show(struct kernfs_open_file *of, static int mbm_local_bytes_config_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { - struct rdt_resource *r = of->kn->parent->priv; + struct rdt_resource *r = rdt_kn_parent_priv(of->kn); mbm_config_show(seq, r, QOS_L3_MBM_LOCAL_EVENT_ID); return 0; } -static void mon_event_config_write(void *info) +void resctrl_arch_mon_event_config_write(void *_config_info) { - struct mon_config_info *mon_info = info; + struct resctrl_mon_config_info *config_info = _config_info; unsigned int index; - index = mon_event_config_index_get(mon_info->evtid); + index = mon_event_config_index_get(config_info->evtid); if (index == INVALID_CONFIG_INDEX) { - pr_warn_once("Invalid event id %d\n", mon_info->evtid); + pr_warn_once("Invalid event id %d\n", config_info->evtid); return; } - wrmsr(MSR_IA32_EVT_CFG_BASE + index, mon_info->mon_config, 0); + wrmsr(MSR_IA32_EVT_CFG_BASE + index, config_info->mon_config, 0); } static void mbm_config_write_domain(struct rdt_resource *r, struct rdt_mon_domain *d, u32 evtid, u32 val) { - struct mon_config_info mon_info = {0}; + struct resctrl_mon_config_info mon_info = {0}; /* * Read the current config value first. If both are the same then * no need to write it again. */ + mon_info.r = r; + mon_info.d = d; mon_info.evtid = evtid; - mondata_config_read(d, &mon_info); + mondata_config_read(&mon_info); if (mon_info.mon_config == val) return; @@ -1686,7 +1734,7 @@ static void mbm_config_write_domain(struct rdt_resource *r, * are scoped at the domain level. Writing any of these MSRs * on one CPU is observed by all the CPUs in the domain. */ - smp_call_function_any(&d->hdr.cpu_mask, mon_event_config_write, + smp_call_function_any(&d->hdr.cpu_mask, resctrl_arch_mon_event_config_write, &mon_info, 1); /* @@ -1703,7 +1751,6 @@ static void mbm_config_write_domain(struct rdt_resource *r, 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_mon_domain *d; @@ -1730,9 +1777,9 @@ next: } /* Value from user cannot be more than the supported set of events */ - if ((val & hw_res->mbm_cfg_mask) != val) { + if ((val & r->mbm_cfg_mask) != val) { rdt_last_cmd_printf("Invalid event configuration: max valid mask is 0x%02x\n", - hw_res->mbm_cfg_mask); + r->mbm_cfg_mask); return -EINVAL; } @@ -1750,7 +1797,7 @@ static ssize_t mbm_total_bytes_config_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { - struct rdt_resource *r = of->kn->parent->priv; + struct rdt_resource *r = rdt_kn_parent_priv(of->kn); int ret; /* Valid input requires a trailing newline */ @@ -1776,7 +1823,7 @@ static ssize_t mbm_local_bytes_config_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { - struct rdt_resource *r = of->kn->parent->priv; + struct rdt_resource *r = rdt_kn_parent_priv(of->kn); int ret; /* Valid input requires a trailing newline */ @@ -2036,6 +2083,28 @@ static struct rftype *rdtgroup_get_rftype_by_name(const char *name) return NULL; } +static void thread_throttle_mode_init(void) +{ + enum membw_throttle_mode throttle_mode = THREAD_THROTTLE_UNDEFINED; + struct rdt_resource *r_mba, *r_smba; + + r_mba = resctrl_arch_get_resource(RDT_RESOURCE_MBA); + if (r_mba->alloc_capable && + r_mba->membw.throttle_mode != THREAD_THROTTLE_UNDEFINED) + throttle_mode = r_mba->membw.throttle_mode; + + r_smba = resctrl_arch_get_resource(RDT_RESOURCE_SMBA); + if (r_smba->alloc_capable && + r_smba->membw.throttle_mode != THREAD_THROTTLE_UNDEFINED) + throttle_mode = r_smba->membw.throttle_mode; + + if (throttle_mode == THREAD_THROTTLE_UNDEFINED) + return; + + resctrl_file_fflags_init("thread_throttle_mode", + RFTYPE_CTRL_INFO | RFTYPE_RES_MB); +} + void resctrl_file_fflags_init(const char *config, unsigned long fflags) { struct rftype *rft; @@ -2164,6 +2233,20 @@ static int rdtgroup_mkdir_info_resdir(void *priv, char *name, return ret; } +static unsigned long fflags_from_resource(struct rdt_resource *r) +{ + switch (r->rid) { + case RDT_RESOURCE_L3: + case RDT_RESOURCE_L2: + return RFTYPE_RES_CACHE; + case RDT_RESOURCE_MBA: + case RDT_RESOURCE_SMBA: + return RFTYPE_RES_MB; + } + + return WARN_ON_ONCE(1); +} + static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn) { struct resctrl_schema *s; @@ -2184,14 +2267,14 @@ static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn) /* loop over enabled controls, these are all alloc_capable */ list_for_each_entry(s, &resctrl_schema_all, list) { r = s->res; - fflags = r->fflags | RFTYPE_CTRL_INFO; + fflags = fflags_from_resource(r) | RFTYPE_CTRL_INFO; ret = rdtgroup_mkdir_info_resdir(s, s->name, fflags); if (ret) goto out_destroy; } for_each_mon_capable_rdt_resource(r) { - fflags = r->fflags | RFTYPE_MON_INFO; + fflags = fflags_from_resource(r) | RFTYPE_MON_INFO; sprintf(name, "%s_MON", r->name); ret = rdtgroup_mkdir_info_resdir(r, name, fflags); if (ret) @@ -2255,7 +2338,7 @@ static void l2_qos_cfg_update(void *arg) static inline bool is_mba_linear(void) { - return rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl.membw.delay_linear; + return resctrl_arch_get_resource(RDT_RESOURCE_MBA)->membw.delay_linear; } static int set_cache_qos_cfg(int level, bool enable) @@ -2345,10 +2428,10 @@ static void mba_sc_domain_destroy(struct rdt_resource *r, */ static bool supports_mba_mbps(void) { - struct rdt_resource *rmbm = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; - struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl; + struct rdt_resource *rmbm = resctrl_arch_get_resource(RDT_RESOURCE_L3); + struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_MBA); - return (is_mbm_enabled() && + return (resctrl_is_mbm_enabled() && r->alloc_capable && is_mba_linear() && r->ctrl_scope == rmbm->mon_scope); } @@ -2359,7 +2442,7 @@ static bool supports_mba_mbps(void) */ static int set_mba_sc(bool mba_sc) { - struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl; + struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_MBA); u32 num_closid = resctrl_arch_get_num_closid(r); struct rdt_ctrl_domain *d; unsigned long fflags; @@ -2440,12 +2523,13 @@ static struct rdtgroup *kernfs_to_rdtgroup(struct kernfs_node *kn) * resource. "info" and its subdirectories don't * have rdtgroup structures, so return NULL here. */ - if (kn == kn_info || kn->parent == kn_info) + if (kn == kn_info || + rcu_access_pointer(kn->__parent) == kn_info) return NULL; else return kn->priv; } else { - return kn->parent->priv; + return rdt_kn_parent_priv(kn); } } @@ -2596,6 +2680,20 @@ static int schemata_list_add(struct rdt_resource *r, enum resctrl_conf_type type if (cl > max_name_width) max_name_width = cl; + switch (r->schema_fmt) { + case RESCTRL_SCHEMA_BITMAP: + s->fmt_str = "%d=%x"; + break; + case RESCTRL_SCHEMA_RANGE: + s->fmt_str = "%d=%u"; + break; + } + + if (WARN_ON_ONCE(!s->fmt_str)) { + kfree(s); + return -EINVAL; + } + INIT_LIST_HEAD(&s->list); list_add(&s->list, &resctrl_schema_all); @@ -2712,8 +2810,8 @@ static int rdt_get_tree(struct fs_context *fc) if (resctrl_arch_alloc_capable() || resctrl_arch_mon_capable()) resctrl_mounted = true; - if (is_mbm_enabled()) { - r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; + if (resctrl_is_mbm_enabled()) { + r = resctrl_arch_get_resource(RDT_RESOURCE_L3); list_for_each_entry(dom, &r->mon_domains, hdr.list) mbm_setup_overflow_handler(dom, MBM_OVERFLOW_INTERVAL, RESCTRL_PICK_ANY_CPU); @@ -2823,7 +2921,7 @@ static int rdt_init_fs_context(struct fs_context *fc) return 0; } -static int reset_all_ctrls(struct rdt_resource *r) +void resctrl_arch_reset_all_ctrls(struct rdt_resource *r) { struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); struct rdt_hw_ctrl_domain *hw_dom; @@ -2847,12 +2945,12 @@ static int reset_all_ctrls(struct rdt_resource *r) hw_dom = resctrl_to_arch_ctrl_dom(d); for (i = 0; i < hw_res->num_closid; i++) - hw_dom->ctrl_val[i] = r->default_ctrl; + hw_dom->ctrl_val[i] = resctrl_get_default_ctrl(r); msr_param.dom = d; smp_call_function_any(&d->hdr.cpu_mask, rdt_ctrl_update, &msr_param, 1); } - return 0; + return; } /* @@ -2971,9 +3069,10 @@ static void rdt_kill_sb(struct super_block *sb) rdt_disable_ctx(); - /*Put everything back to default values. */ + /* Put everything back to default values. */ for_each_alloc_capable_rdt_resource(r) - reset_all_ctrls(r); + resctrl_arch_reset_all_ctrls(r); + rmdir_all_sub(); rdt_pseudo_lock_release(); rdtgroup_default.mode = RDT_MODE_SHAREABLE; @@ -3080,7 +3179,7 @@ static int mon_add_all_files(struct kernfs_node *kn, struct rdt_mon_domain *d, if (ret) return ret; - if (!do_sum && is_mbm_event(mevt->evtid)) + if (!do_sum && resctrl_is_mbm_event(mevt->evtid)) mon_event_read(&rr, r, d, prgrp, &d->hdr.cpu_mask, mevt->evtid, true); } @@ -3382,7 +3481,7 @@ static void rdtgroup_init_mba(struct rdt_resource *r, u32 closid) } cfg = &d->staged_config[CDP_NONE]; - cfg->new_ctrl = r->default_ctrl; + cfg->new_ctrl = resctrl_get_default_ctrl(r); cfg->have_new_ctrl = true; } } @@ -3664,7 +3763,7 @@ out_unlock: */ static bool is_mon_groups(struct kernfs_node *kn, const char *name) { - return (!strcmp(kn->name, "mon_groups") && + return (!strcmp(rdt_kn_name(kn), "mon_groups") && strcmp(name, "mon_groups")); } @@ -3696,14 +3795,21 @@ static int rdtgroup_mkdir(struct kernfs_node *parent_kn, const char *name, static int rdtgroup_rmdir_mon(struct rdtgroup *rdtgrp, cpumask_var_t tmpmask) { struct rdtgroup *prdtgrp = rdtgrp->mon.parent; + u32 closid, rmid; int cpu; /* Give any tasks back to the parent group */ rdt_move_group_tasks(rdtgrp, prdtgrp, tmpmask); - /* Update per cpu rmid of the moved CPUs first */ + /* + * Update per cpu closid/rmid of the moved CPUs first. + * Note: the closid will not change, but the arch code still needs it. + */ + closid = prdtgrp->closid; + rmid = prdtgrp->mon.rmid; for_each_cpu(cpu, &rdtgrp->cpu_mask) - per_cpu(pqr_state.default_rmid, cpu) = prdtgrp->mon.rmid; + resctrl_arch_set_cpu_default_closid_rmid(cpu, closid, rmid); + /* * Update the MSR on moved CPUs and CPUs which have moved * task running on them. @@ -3736,6 +3842,7 @@ static int rdtgroup_ctrl_remove(struct rdtgroup *rdtgrp) static int rdtgroup_rmdir_ctrl(struct rdtgroup *rdtgrp, cpumask_var_t tmpmask) { + u32 closid, rmid; int cpu; /* Give any tasks back to the default group */ @@ -3746,10 +3853,10 @@ static int rdtgroup_rmdir_ctrl(struct rdtgroup *rdtgrp, cpumask_var_t tmpmask) &rdtgroup_default.cpu_mask, &rdtgrp->cpu_mask); /* Update per cpu closid and rmid of the moved CPUs first */ - for_each_cpu(cpu, &rdtgrp->cpu_mask) { - per_cpu(pqr_state.default_closid, cpu) = rdtgroup_default.closid; - per_cpu(pqr_state.default_rmid, cpu) = rdtgroup_default.mon.rmid; - } + closid = rdtgroup_default.closid; + rmid = rdtgroup_default.mon.rmid; + for_each_cpu(cpu, &rdtgrp->cpu_mask) + resctrl_arch_set_cpu_default_closid_rmid(cpu, closid, rmid); /* * Update the MSR on moved CPUs and CPUs which have moved @@ -3771,9 +3878,18 @@ static int rdtgroup_rmdir_ctrl(struct rdtgroup *rdtgrp, cpumask_var_t tmpmask) return 0; } +static struct kernfs_node *rdt_kn_parent(struct kernfs_node *kn) +{ + /* + * Valid within the RCU section it was obtained or while rdtgroup_mutex + * is held. + */ + return rcu_dereference_check(kn->__parent, lockdep_is_held(&rdtgroup_mutex)); +} + static int rdtgroup_rmdir(struct kernfs_node *kn) { - struct kernfs_node *parent_kn = kn->parent; + struct kernfs_node *parent_kn; struct rdtgroup *rdtgrp; cpumask_var_t tmpmask; int ret = 0; @@ -3786,6 +3902,7 @@ static int rdtgroup_rmdir(struct kernfs_node *kn) ret = -EPERM; goto out; } + parent_kn = rdt_kn_parent(kn); /* * If the rdtgroup is a ctrl_mon group and parent directory @@ -3803,7 +3920,7 @@ static int rdtgroup_rmdir(struct kernfs_node *kn) ret = rdtgroup_rmdir_ctrl(rdtgrp, tmpmask); } } else if (rdtgrp->type == RDTMON_GROUP && - is_mon_groups(parent_kn, kn->name)) { + is_mon_groups(parent_kn, rdt_kn_name(kn))) { ret = rdtgroup_rmdir_mon(rdtgrp, tmpmask); } else { ret = -EPERM; @@ -3854,6 +3971,7 @@ static void mongrp_reparent(struct rdtgroup *rdtgrp, static int rdtgroup_rename(struct kernfs_node *kn, struct kernfs_node *new_parent, const char *new_name) { + struct kernfs_node *kn_parent; struct rdtgroup *new_prdtgrp; struct rdtgroup *rdtgrp; cpumask_var_t tmpmask; @@ -3888,8 +4006,9 @@ static int rdtgroup_rename(struct kernfs_node *kn, goto out; } - if (rdtgrp->type != RDTMON_GROUP || !kn->parent || - !is_mon_groups(kn->parent, kn->name)) { + kn_parent = rdt_kn_parent(kn); + if (rdtgrp->type != RDTMON_GROUP || !kn_parent || + !is_mon_groups(kn_parent, rdt_kn_name(kn))) { rdt_last_cmd_puts("Source must be a MON group\n"); ret = -EPERM; goto out; @@ -3950,7 +4069,7 @@ static int rdtgroup_show_options(struct seq_file *seq, struct kernfs_root *kf) if (resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L2)) seq_puts(seq, ",cdpl2"); - if (is_mba_sc(&rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl)) + if (is_mba_sc(resctrl_arch_get_resource(RDT_RESOURCE_MBA))) seq_puts(seq, ",mba_MBps"); if (resctrl_debug) @@ -4029,9 +4148,9 @@ void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d if (resctrl_mounted && resctrl_arch_mon_capable()) rmdir_mondata_subdir_allrdtgrp(r, d); - if (is_mbm_enabled()) + if (resctrl_is_mbm_enabled()) cancel_delayed_work(&d->mbm_over); - if (is_llc_occupancy_enabled() && has_busy_rmid(d)) { + if (resctrl_arch_is_llc_occupancy_enabled() && has_busy_rmid(d)) { /* * When a package is going down, forcefully * decrement rmid->ebusy. There is no way to know @@ -4049,17 +4168,30 @@ void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d mutex_unlock(&rdtgroup_mutex); } +/** + * domain_setup_mon_state() - Initialise domain monitoring structures. + * @r: The resource for the newly online domain. + * @d: The newly online domain. + * + * Allocate monitor resources that belong to this domain. + * Called when the first CPU of a domain comes online, regardless of whether + * the filesystem is mounted. + * During boot this may be called before global allocations have been made by + * resctrl_mon_resource_init(). + * + * Returns 0 for success, or -ENOMEM. + */ static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_mon_domain *d) { u32 idx_limit = resctrl_arch_system_num_rmid_idx(); size_t tsize; - if (is_llc_occupancy_enabled()) { + if (resctrl_arch_is_llc_occupancy_enabled()) { d->rmid_busy_llc = bitmap_zalloc(idx_limit, GFP_KERNEL); if (!d->rmid_busy_llc) return -ENOMEM; } - if (is_mbm_total_enabled()) { + if (resctrl_arch_is_mbm_total_enabled()) { tsize = sizeof(*d->mbm_total); d->mbm_total = kcalloc(idx_limit, tsize, GFP_KERNEL); if (!d->mbm_total) { @@ -4067,7 +4199,7 @@ static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_mon_domain return -ENOMEM; } } - if (is_mbm_local_enabled()) { + if (resctrl_arch_is_mbm_local_enabled()) { tsize = sizeof(*d->mbm_local); d->mbm_local = kcalloc(idx_limit, tsize, GFP_KERNEL); if (!d->mbm_local) { @@ -4106,13 +4238,13 @@ int resctrl_online_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d) if (err) goto out_unlock; - if (is_mbm_enabled()) { + if (resctrl_is_mbm_enabled()) { INIT_DELAYED_WORK(&d->mbm_over, mbm_handle_overflow); mbm_setup_overflow_handler(d, MBM_OVERFLOW_INTERVAL, RESCTRL_PICK_ANY_CPU); } - if (is_llc_occupancy_enabled()) + if (resctrl_arch_is_llc_occupancy_enabled()) INIT_DELAYED_WORK(&d->cqm_limbo, cqm_handle_limbo); /* @@ -4148,9 +4280,25 @@ static void clear_childcpus(struct rdtgroup *r, unsigned int cpu) } } +static struct rdt_mon_domain *get_mon_domain_from_cpu(int cpu, + struct rdt_resource *r) +{ + struct rdt_mon_domain *d; + + lockdep_assert_cpus_held(); + + list_for_each_entry(d, &r->mon_domains, hdr.list) { + /* Find the domain that contains this CPU */ + if (cpumask_test_cpu(cpu, &d->hdr.cpu_mask)) + return d; + } + + return NULL; +} + void resctrl_offline_cpu(unsigned int cpu) { - struct rdt_resource *l3 = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; + struct rdt_resource *l3 = resctrl_arch_get_resource(RDT_RESOURCE_L3); struct rdt_mon_domain *d; struct rdtgroup *rdtgrp; @@ -4167,12 +4315,12 @@ void resctrl_offline_cpu(unsigned int cpu) d = get_mon_domain_from_cpu(cpu, l3); if (d) { - if (is_mbm_enabled() && cpu == d->mbm_work_cpu) { + if (resctrl_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)) { + if (resctrl_arch_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); } @@ -4183,14 +4331,14 @@ out_unlock: } /* - * rdtgroup_init - rdtgroup initialization + * resctrl_init - resctrl filesystem initialization * * Setup resctrl file system including set up root, create mount point, - * register rdtgroup filesystem, and initialize files under root directory. + * register resctrl filesystem, and initialize files under root directory. * * Return: 0 on success or -errno */ -int __init rdtgroup_init(void) +int __init resctrl_init(void) { int ret = 0; @@ -4199,10 +4347,18 @@ int __init rdtgroup_init(void) rdtgroup_setup_default(); - ret = sysfs_create_mount_point(fs_kobj, "resctrl"); + thread_throttle_mode_init(); + + ret = resctrl_mon_resource_init(); if (ret) return ret; + ret = sysfs_create_mount_point(fs_kobj, "resctrl"); + if (ret) { + resctrl_mon_resource_exit(); + return ret; + } + ret = register_filesystem(&rdt_fs_type); if (ret) goto cleanup_mountpoint; @@ -4234,13 +4390,16 @@ int __init rdtgroup_init(void) cleanup_mountpoint: sysfs_remove_mount_point(fs_kobj, "resctrl"); + resctrl_mon_resource_exit(); return ret; } -void __exit rdtgroup_exit(void) +void __exit resctrl_exit(void) { debugfs_remove_recursive(debugfs_resctrl); unregister_filesystem(&rdt_fs_type); sysfs_remove_mount_point(fs_kobj, "resctrl"); + + resctrl_mon_resource_exit(); } diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 91639d1e4ec2..c6fefd4585f8 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -195,6 +195,7 @@ static void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, printk("%sCall Trace:\n", log_lvl); unwind_start(&state, task, regs, stack); + stack = stack ?: get_stack_pointer(task, regs); regs = unwind_get_entry_regs(&state, &partial); /* @@ -213,9 +214,7 @@ static void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, * - hardirq stack * - entry stack */ - for (stack = stack ?: get_stack_pointer(task, regs); - stack; - stack = stack_info.next_sp) { + for (; stack; stack = stack_info.next_sp) { const char *stack_name; stack = PTR_ALIGN(stack, sizeof(long)); diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c index fc1714bad045..611f27e3890c 100644 --- a/arch/x86/kernel/early_printk.c +++ b/arch/x86/kernel/early_printk.c @@ -190,7 +190,6 @@ static __init void early_serial_init(char *s) early_serial_hw_init(divisor); } -#ifdef CONFIG_PCI static __noendbr void mem32_serial_out(unsigned long addr, int offset, int value) { u32 __iomem *vaddr = (u32 __iomem *)addr; @@ -208,6 +207,45 @@ static __noendbr unsigned int mem32_serial_in(unsigned long addr, int offset) ANNOTATE_NOENDBR_SYM(mem32_serial_in); /* + * early_mmio_serial_init() - Initialize MMIO-based early serial console. + * @s: MMIO-based serial specification. + */ +static __init void early_mmio_serial_init(char *s) +{ + unsigned long baudrate; + unsigned long membase; + char *e; + + if (*s == ',') + s++; + + if (!strncmp(s, "0x", 2)) { + /* NB: only 32-bit addresses are supported. */ + membase = simple_strtoul(s, &e, 16); + early_serial_base = (unsigned long)early_ioremap(membase, PAGE_SIZE); + + static_call_update(serial_in, mem32_serial_in); + static_call_update(serial_out, mem32_serial_out); + + s += strcspn(s, ","); + if (*s == ',') + s++; + } + + if (!strncmp(s, "nocfg", 5)) { + baudrate = 0; + } else { + baudrate = simple_strtoul(s, &e, 0); + if (baudrate == 0 || s == e) + baudrate = DEFAULT_BAUD; + } + + if (baudrate) + early_serial_hw_init(115200 / baudrate); +} + +#ifdef CONFIG_PCI +/* * early_pci_serial_init() * * This function is invoked when the early_printk param starts with "pciserial" @@ -351,6 +389,11 @@ static int __init setup_early_printk(char *buf) keep = (strstr(buf, "keep") != NULL); while (*buf != '\0') { + if (!strncmp(buf, "mmio", 4)) { + early_mmio_serial_init(buf + 4); + early_console_register(&early_serial_console, keep); + buf += 4; + } if (!strncmp(buf, "serial", 6)) { buf += 6; early_serial_init(buf); diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index 1b734a9ff088..91d6341f281f 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -508,7 +508,7 @@ static inline void fpstate_init_fstate(struct fpstate *fpstate) /* * Used in two places: * 1) Early boot to setup init_fpstate for non XSAVE systems - * 2) fpu_init_fpstate_user() which is invoked from KVM + * 2) fpu_alloc_guest_fpstate() which is invoked from KVM */ void fpstate_init_user(struct fpstate *fpstate) { diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index 9c9faa1634fb..102641fd2172 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -655,7 +655,7 @@ void kgdb_arch_late(void) if (breakinfo[i].pev) continue; breakinfo[i].pev = register_wide_hw_breakpoint(&attr, NULL, NULL); - if (IS_ERR((void * __force)breakinfo[i].pev)) { + if (IS_ERR_PCPU(breakinfo[i].pev)) { printk(KERN_ERR "kgdb: Could not allocate hw" "breakpoints\nDisabling the kernel debugger\n"); breakinfo[i].pev = NULL; diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 97925632c28e..1ccd05d8999f 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -75,6 +75,11 @@ void paravirt_set_sched_clock(u64 (*func)(void)) static_call_update(pv_sched_clock, func); } +static noinstr void pv_native_safe_halt(void) +{ + native_safe_halt(); +} + #ifdef CONFIG_PARAVIRT_XXL static noinstr void pv_native_write_cr2(unsigned long val) { @@ -100,11 +105,6 @@ static noinstr void pv_native_set_debugreg(int regno, unsigned long val) { native_set_debugreg(regno, val); } - -static noinstr void pv_native_safe_halt(void) -{ - native_safe_halt(); -} #endif struct pv_info pv_info = { @@ -161,9 +161,11 @@ struct paravirt_patch_template pv_ops = { .irq.save_fl = __PV_IS_CALLEE_SAVE(pv_native_save_fl), .irq.irq_disable = __PV_IS_CALLEE_SAVE(pv_native_irq_disable), .irq.irq_enable = __PV_IS_CALLEE_SAVE(pv_native_irq_enable), +#endif /* CONFIG_PARAVIRT_XXL */ + + /* Irq HLT ops. */ .irq.safe_halt = pv_native_safe_halt, .irq.halt = native_halt, -#endif /* CONFIG_PARAVIRT_XXL */ /* Mmu ops. */ .mmu.flush_tlb_user = native_flush_tlb_local, diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 91f6ff618852..962c3ce39323 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -939,7 +939,7 @@ void __init select_idle_routine(void) static_call_update(x86_idle, mwait_idle); } else if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) { pr_info("using TDX aware idle routine\n"); - static_call_update(x86_idle, tdx_safe_halt); + static_call_update(x86_idle, tdx_halt); } else { static_call_update(x86_idle, default_idle); } diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index c7164a8de983..9d2a13b37833 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -578,14 +578,13 @@ static void __init memblock_x86_reserve_range_setup_data(void) static void __init arch_reserve_crashkernel(void) { unsigned long long crash_base, crash_size, low_size = 0; - char *cmdline = boot_command_line; bool high = false; int ret; if (!IS_ENABLED(CONFIG_CRASH_RESERVE)) return; - ret = parse_crashkernel(cmdline, memblock_phys_mem_size(), + ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(), &crash_size, &crash_base, &low_size, &high); if (ret) @@ -596,8 +595,7 @@ static void __init arch_reserve_crashkernel(void) return; } - reserve_crashkernel_generic(cmdline, crash_size, crash_base, - low_size, high); + reserve_crashkernel_generic(crash_size, crash_base, low_size, high); } static struct resource standard_io_resources[] = { @@ -1031,8 +1029,6 @@ void __init setup_arch(char **cmdline_p) max_low_pfn = e820__end_of_low_ram_pfn(); else max_low_pfn = max_pfn; - - high_memory = (void *)__va(max_pfn * PAGE_SIZE - 1) + 1; #endif /* Find and reserve MPTABLE area */ @@ -1166,8 +1162,10 @@ void __init setup_arch(char **cmdline_p) initmem_init(); dma_contiguous_reserve(max_pfn_mapped << PAGE_SHIFT); - if (boot_cpu_has(X86_FEATURE_GBPAGES)) + if (boot_cpu_has(X86_FEATURE_GBPAGES)) { hugetlb_cma_reserve(PUD_SHIFT - PAGE_SHIFT); + hugetlb_bootmem_alloc(); + } /* * Reserve memory for crash kernel after SRAT is parsed so that it diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c index 9e51242ed125..a59c72e77645 100644 --- a/arch/x86/kernel/static_call.c +++ b/arch/x86/kernel/static_call.c @@ -158,7 +158,7 @@ void arch_static_call_transform(void *site, void *tramp, void *func, bool tail) { mutex_lock(&text_mutex); - if (tramp) { + if (tramp && !site) { __static_call_validate(tramp, true, true); __static_call_transform(tramp, __sc_insn(!func, true), func, false); } diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index d4705a348a80..977ee75e047c 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -476,7 +476,7 @@ bool unwind_next_frame(struct unwind_state *state) return false; /* Don't let modules unload while we're reading their ORC data. */ - preempt_disable(); + guard(rcu)(); /* End-of-stack check for user tasks: */ if (state->regs && user_mode(state->regs)) @@ -669,14 +669,12 @@ bool unwind_next_frame(struct unwind_state *state) goto err; } - preempt_enable(); return true; err: state->error = true; the_end: - preempt_enable(); state->stack_info.type = STACK_TYPE_UNKNOWN; return false; } |