diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index d79335506ecd3c3f5aa3beabde8e0dd74cef10a3..47551ab73ca8a03ab60448adb8fe0d8cee9aed5d 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -37,7 +37,7 @@ */ /* un-comment DEBUG to enable pr_debug() statements */ -#define DEBUG +/* #define DEBUG */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -64,11 +64,17 @@ static struct cpuidle_driver intel_idle_driver = { /* intel_idle.max_cstate=0 disables driver */ static int max_cstate = CPUIDLE_STATE_MAX - 1; static unsigned int disabled_states_mask; +static unsigned int preferred_states_mask; static struct cpuidle_device __percpu *intel_idle_cpuidle_devices; static unsigned long auto_demotion_disable_flags; -static bool disable_promotion_to_c1e; + +static enum { + C1E_PROMOTION_PRESERVE, + C1E_PROMOTION_ENABLE, + C1E_PROMOTION_DISABLE +} c1e_promotion = C1E_PROMOTION_PRESERVE; struct idle_cpu { struct cpuidle_state *state_table; @@ -88,6 +94,12 @@ static struct cpuidle_state *cpuidle_state_table __initdata; static unsigned int mwait_substates __initdata; +/* + * Enable interrupts before entering the C-state. On some platforms and for + * some C-states, this may measurably decrease interrupt latency. + */ +#define CPUIDLE_FLAG_IRQ_ENABLE BIT(14) + /* * Enable this state by default even if the ACPI _CST does not list it. */ @@ -115,9 +127,6 @@ static unsigned int mwait_substates __initdata; * If the local APIC timer is not known to be reliable in the target idle state, * enable one-shot tick broadcasting for the target CPU before executing MWAIT. * - * Optionally call leave_mm() for the target CPU upfront to avoid wakeups due to - * flushing user TLBs. - * * Must be called under local_irq_disable(). */ static __cpuidle int intel_idle(struct cpuidle_device *dev, @@ -127,6 +136,9 @@ static __cpuidle int intel_idle(struct cpuidle_device *dev, unsigned long eax = flg2MWAIT(state->flags); unsigned long ecx = 1; /* break on interrupt flag */ + if (state->flags & CPUIDLE_FLAG_IRQ_ENABLE) + local_irq_enable(); + mwait_idle_with_hints(eax, ecx); return index; @@ -698,7 +710,7 @@ static struct cpuidle_state skx_cstates[] __initdata = { { .name = "C1", .desc = "MWAIT 0x00", - .flags = MWAIT2flg(0x00), + .flags = MWAIT2flg(0x00) | CPUIDLE_FLAG_IRQ_ENABLE, .exit_latency = 2, .target_residency = 2, .enter = &intel_idle, @@ -727,7 +739,7 @@ static struct cpuidle_state icx_cstates[] __initdata = { { .name = "C1", .desc = "MWAIT 0x00", - .flags = MWAIT2flg(0x00), + .flags = MWAIT2flg(0x00) | CPUIDLE_FLAG_IRQ_ENABLE, .exit_latency = 1, .target_residency = 1, .enter = &intel_idle, @@ -744,8 +756,48 @@ static struct cpuidle_state icx_cstates[] __initdata = { .name = "C6", .desc = "MWAIT 0x20", .flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED, - .exit_latency = 128, - .target_residency = 384, + .exit_latency = 170, + .target_residency = 600, + .enter = &intel_idle, + .enter_s2idle = intel_idle_s2idle, }, + { + .enter = NULL } +}; + +/* + * On Sapphire Rapids Xeon C1 has to be disabled if C1E is enabled, and vice + * versa. On SPR C1E is enabled only if "C1E promotion" bit is set in + * MSR_IA32_POWER_CTL. But in this case there effectively no C1, because C1 + * requests are promoted to C1E. If the "C1E promotion" bit is cleared, then + * both C1 and C1E requests end up with C1, so there is effectively no C1E. + * + * By default we enable C1 and disable C1E by marking it with + * 'CPUIDLE_FLAG_UNUSABLE'. + */ +static struct cpuidle_state spr_cstates[] __initdata = { + { + .name = "C1", + .desc = "MWAIT 0x00", + .flags = MWAIT2flg(0x00), + .exit_latency = 1, + .target_residency = 1, + .enter = &intel_idle, + .enter_s2idle = intel_idle_s2idle, }, + { + .name = "C1E", + .desc = "MWAIT 0x01", + .flags = MWAIT2flg(0x01) | CPUIDLE_FLAG_ALWAYS_ENABLE | + CPUIDLE_FLAG_UNUSABLE, + .exit_latency = 2, + .target_residency = 4, + .enter = &intel_idle, + .enter_s2idle = intel_idle_s2idle, }, + { + .name = "C6", + .desc = "MWAIT 0x20", + .flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED, + .exit_latency = 290, + .target_residency = 800, .enter = &intel_idle, .enter_s2idle = intel_idle_s2idle, }, { @@ -963,6 +1015,39 @@ static struct cpuidle_state dnv_cstates[] __initdata = { .enter = NULL } }; +/* + * Note, depending on HW and FW revision, SnowRidge SoC may or may not support + * C6, and this is indicated in the CPUID mwait leaf. + */ +static struct cpuidle_state snr_cstates[] __initdata = { + { + .name = "C1", + .desc = "MWAIT 0x00", + .flags = MWAIT2flg(0x00), + .exit_latency = 2, + .target_residency = 2, + .enter = &intel_idle, + .enter_s2idle = intel_idle_s2idle, }, + { + .name = "C1E", + .desc = "MWAIT 0x01", + .flags = MWAIT2flg(0x01) | CPUIDLE_FLAG_ALWAYS_ENABLE, + .exit_latency = 15, + .target_residency = 25, + .enter = &intel_idle, + .enter_s2idle = intel_idle_s2idle, }, + { + .name = "C6", + .desc = "MWAIT 0x20", + .flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED, + .exit_latency = 130, + .target_residency = 500, + .enter = &intel_idle, + .enter_s2idle = intel_idle_s2idle, }, + { + .enter = NULL } +}; + static const struct idle_cpu idle_cpu_nehalem __initconst = { .state_table = nehalem_cstates, .auto_demotion_disable_flags = NHM_C1_AUTO_DEMOTE | NHM_C3_AUTO_DEMOTE, @@ -1062,6 +1147,12 @@ static const struct idle_cpu idle_cpu_icx __initconst = { .use_acpi = true, }; +static const struct idle_cpu idle_cpu_spr __initconst = { + .state_table = spr_cstates, + .disable_promotion_to_c1e = true, + .use_acpi = true, +}; + static const struct idle_cpu idle_cpu_avn __initconst = { .state_table = avn_cstates, .disable_promotion_to_c1e = true, @@ -1084,6 +1175,12 @@ static const struct idle_cpu idle_cpu_dnv __initconst = { .use_acpi = true, }; +static const struct idle_cpu idle_cpu_snr __initconst = { + .state_table = snr_cstates, + .disable_promotion_to_c1e = true, + .use_acpi = true, +}; + static const struct x86_cpu_id intel_idle_ids[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(NEHALEM_EP, &idle_cpu_nhx), X86_MATCH_INTEL_FAM6_MODEL(NEHALEM, &idle_cpu_nehalem), @@ -1117,12 +1214,14 @@ static const struct x86_cpu_id intel_idle_ids[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE, &idle_cpu_skl), X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_X, &idle_cpu_skx), X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X, &idle_cpu_icx), + X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D, &idle_cpu_icx), + X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &idle_cpu_spr), X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNL, &idle_cpu_knl), X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNM, &idle_cpu_knl), X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT, &idle_cpu_bxt), X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT_PLUS, &idle_cpu_bxt), X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT_D, &idle_cpu_dnv), - X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D, &idle_cpu_dnv), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D, &idle_cpu_snr), {} }; @@ -1444,6 +1543,68 @@ static void __init sklh_idle_state_table_update(void) skl_cstates[6].flags |= CPUIDLE_FLAG_UNUSABLE; /* C9-SKL */ } +/** + * skx_idle_state_table_update - Adjust the Sky Lake/Cascade Lake + * idle states table. + */ +static void __init skx_idle_state_table_update(void) +{ + unsigned long long msr; + + rdmsrl(MSR_PKG_CST_CONFIG_CONTROL, msr); + + /* + * 000b: C0/C1 (no package C-state support) + * 001b: C2 + * 010b: C6 (non-retention) + * 011b: C6 (retention) + * 111b: No Package C state limits. + */ + if ((msr & 0x7) < 2) { + /* + * Uses the CC6 + PC0 latency and 3 times of + * latency for target_residency if the PC6 + * is disabled in BIOS. This is consistent + * with how intel_idle driver uses _CST + * to set the target_residency. + */ + skx_cstates[2].exit_latency = 92; + skx_cstates[2].target_residency = 276; + } +} + +/** + * spr_idle_state_table_update - Adjust Sapphire Rapids idle states table. + */ +static void __init spr_idle_state_table_update(void) +{ + unsigned long long msr; + + /* Check if user prefers C1E over C1. */ + if ((preferred_states_mask & BIT(2)) && + !(preferred_states_mask & BIT(1))) { + /* Disable C1 and enable C1E. */ + spr_cstates[0].flags |= CPUIDLE_FLAG_UNUSABLE; + spr_cstates[1].flags &= ~CPUIDLE_FLAG_UNUSABLE; + + /* Enable C1E using the "C1E promotion" bit. */ + c1e_promotion = C1E_PROMOTION_ENABLE; + } + + /* + * By default, the C6 state assumes the worst-case scenario of package + * C6. However, if PC6 is disabled, we update the numbers to match + * core C6. + */ + rdmsrl(MSR_PKG_CST_CONFIG_CONTROL, msr); + + /* Limit value 2 and above allow for PC6. */ + if ((msr & 0x7) < 2) { + spr_cstates[2].exit_latency = 190; + spr_cstates[2].target_residency = 600; + } +} + static bool __init intel_idle_verify_cstate(unsigned int mwait_hint) { unsigned int mwait_cstate = MWAIT_HINT2CSTATE(mwait_hint) + 1; @@ -1475,6 +1636,12 @@ static void __init intel_idle_init_cstates_icpu(struct cpuidle_driver *drv) case INTEL_FAM6_SKYLAKE: sklh_idle_state_table_update(); break; + case INTEL_FAM6_SKYLAKE_X: + skx_idle_state_table_update(); + break; + case INTEL_FAM6_SAPPHIRERAPIDS_X: + spr_idle_state_table_update(); + break; } for (cstate = 0; cstate < CPUIDLE_STATE_MAX; ++cstate) { @@ -1547,6 +1714,15 @@ static void auto_demotion_disable(void) wrmsrl(MSR_PKG_CST_CONFIG_CONTROL, msr_bits); } +static void c1e_promotion_enable(void) +{ + unsigned long long msr_bits; + + rdmsrl(MSR_IA32_POWER_CTL, msr_bits); + msr_bits |= 0x2; + wrmsrl(MSR_IA32_POWER_CTL, msr_bits); +} + static void c1e_promotion_disable(void) { unsigned long long msr_bits; @@ -1578,7 +1754,9 @@ static int intel_idle_cpu_init(unsigned int cpu) if (auto_demotion_disable_flags) auto_demotion_disable(); - if (disable_promotion_to_c1e) + if (c1e_promotion == C1E_PROMOTION_ENABLE) + c1e_promotion_enable(); + else if (c1e_promotion == C1E_PROMOTION_DISABLE) c1e_promotion_disable(); return 0; @@ -1657,7 +1835,8 @@ static int __init intel_idle_init(void) if (icpu) { cpuidle_state_table = icpu->state_table; auto_demotion_disable_flags = icpu->auto_demotion_disable_flags; - disable_promotion_to_c1e = icpu->disable_promotion_to_c1e; + if (icpu->disable_promotion_to_c1e) + c1e_promotion = C1E_PROMOTION_DISABLE; if (icpu->use_acpi || force_use_acpi) intel_idle_acpi_cst_extract(); } else if (!intel_idle_acpi_cst_extract()) { @@ -1716,3 +1895,14 @@ module_param(max_cstate, int, 0444); */ module_param_named(states_off, disabled_states_mask, uint, 0444); MODULE_PARM_DESC(states_off, "Mask of disabled idle states"); +/* + * Some platforms come with mutually exclusive C-states, so that if one is + * enabled, the other C-states must not be used. Example: C1 and C1E on + * Sapphire Rapids platform. This parameter allows for selecting the + * preferred C-states among the groups of mutually exclusive C-states - the + * selected C-states will be registered, the other C-states from the mutually + * exclusive group won't be registered. If the platform has no mutually + * exclusive C-states, this parameter has no effect. + */ +module_param_named(preferred_cstates, preferred_states_mask, uint, 0444); +MODULE_PARM_DESC(preferred_cstates, "Mask of preferred idle states");