From 4622ba923e55e12cb76081c8865b01fcb383a9d8 Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Mon, 5 Jun 2023 15:47:13 +0000 Subject: intel_idle: refactor state->enter manipulation into its own function Since the 6.4 kernel, the logic for updating a state's enter method based on "environmental conditions" (command line options, cpu sidechannel workarounds etc etc) has gotten pretty complex. This patch refactors this into a seperate small, self contained function (no behavior changes) for improved readability and to make future changes to this logic easier to do and understand. Signed-off-by: Arjan van de Ven Signed-off-by: Rafael J. Wysocki --- drivers/idle/intel_idle.c | 50 ++++++++++++++++++++++++++--------------------- 1 file changed, 28 insertions(+), 22 deletions(-) (limited to 'drivers/idle/intel_idle.c') diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index aa2d19db2b1d..c351b21c0875 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -1839,6 +1839,32 @@ static bool __init intel_idle_verify_cstate(unsigned int mwait_hint) return true; } +static void state_update_enter_method(struct cpuidle_state *state, int cstate) +{ + if (state->flags & CPUIDLE_FLAG_INIT_XSTATE) { + /* + * Combining with XSTATE with IBRS or IRQ_ENABLE flags + * is not currently supported but this driver. + */ + WARN_ON_ONCE(state->flags & CPUIDLE_FLAG_IBRS); + WARN_ON_ONCE(state->flags & CPUIDLE_FLAG_IRQ_ENABLE); + state->enter = intel_idle_xstate; + } else if (cpu_feature_enabled(X86_FEATURE_KERNEL_IBRS) && + state->flags & CPUIDLE_FLAG_IBRS) { + /* + * IBRS mitigation requires that C-states are entered + * with interrupts disabled. + */ + WARN_ON_ONCE(state->flags & CPUIDLE_FLAG_IRQ_ENABLE); + state->enter = intel_idle_ibrs; + } else if (state->flags & CPUIDLE_FLAG_IRQ_ENABLE) { + state->enter = intel_idle_irq; + } else if (force_irq_on) { + pr_info("forced intel_idle_irq for state %d\n", cstate); + state->enter = intel_idle_irq; + } +} + static void __init intel_idle_init_cstates_icpu(struct cpuidle_driver *drv) { int cstate; @@ -1894,28 +1920,8 @@ static void __init intel_idle_init_cstates_icpu(struct cpuidle_driver *drv) drv->states[drv->state_count] = cpuidle_state_table[cstate]; state = &drv->states[drv->state_count]; - if (state->flags & CPUIDLE_FLAG_INIT_XSTATE) { - /* - * Combining with XSTATE with IBRS or IRQ_ENABLE flags - * is not currently supported but this driver. - */ - WARN_ON_ONCE(state->flags & CPUIDLE_FLAG_IBRS); - WARN_ON_ONCE(state->flags & CPUIDLE_FLAG_IRQ_ENABLE); - state->enter = intel_idle_xstate; - } else if (cpu_feature_enabled(X86_FEATURE_KERNEL_IBRS) && - state->flags & CPUIDLE_FLAG_IBRS) { - /* - * IBRS mitigation requires that C-states are entered - * with interrupts disabled. - */ - WARN_ON_ONCE(state->flags & CPUIDLE_FLAG_IRQ_ENABLE); - state->enter = intel_idle_ibrs; - } else if (state->flags & CPUIDLE_FLAG_IRQ_ENABLE) { - state->enter = intel_idle_irq; - } else if (force_irq_on) { - pr_info("forced intel_idle_irq for state %d\n", cstate); - state->enter = intel_idle_irq; - } + state_update_enter_method(state, cstate); + if ((disabled_states_mask & BIT(drv->state_count)) || ((icpu->use_acpi || force_use_acpi) && -- cgit v1.2.3 From 7826c069c8765969cfb7a364f8e0e663fc132b10 Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Mon, 5 Jun 2023 15:47:14 +0000 Subject: intel_idle: clean up the (new) state_update_enter_method function Now that the logic for state_update_enter_method() is in its own function, the long if .. else if .. else if .. else if chain can be simplified by just returning from the function at the various places. This does not change functionality, but it makes the logic much simpler to read or modify later. Signed-off-by: Arjan van de Ven Signed-off-by: Rafael J. Wysocki --- drivers/idle/intel_idle.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) (limited to 'drivers/idle/intel_idle.c') diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index c351b21c0875..256c2d42e350 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -1849,7 +1849,10 @@ static void state_update_enter_method(struct cpuidle_state *state, int cstate) WARN_ON_ONCE(state->flags & CPUIDLE_FLAG_IBRS); WARN_ON_ONCE(state->flags & CPUIDLE_FLAG_IRQ_ENABLE); state->enter = intel_idle_xstate; - } else if (cpu_feature_enabled(X86_FEATURE_KERNEL_IBRS) && + return; + } + + if (cpu_feature_enabled(X86_FEATURE_KERNEL_IBRS) && state->flags & CPUIDLE_FLAG_IBRS) { /* * IBRS mitigation requires that C-states are entered @@ -1857,9 +1860,15 @@ static void state_update_enter_method(struct cpuidle_state *state, int cstate) */ WARN_ON_ONCE(state->flags & CPUIDLE_FLAG_IRQ_ENABLE); state->enter = intel_idle_ibrs; - } else if (state->flags & CPUIDLE_FLAG_IRQ_ENABLE) { + return; + } + + if (state->flags & CPUIDLE_FLAG_IRQ_ENABLE) { state->enter = intel_idle_irq; - } else if (force_irq_on) { + return; + } + + if (force_irq_on) { pr_info("forced intel_idle_irq for state %d\n", cstate); state->enter = intel_idle_irq; } -- cgit v1.2.3 From 2f3d08f074b02aa449de27238fda72496c789034 Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Mon, 5 Jun 2023 15:47:15 +0000 Subject: intel_idle: Add support for using intel_idle in a VM guest using just hlt In a typical VM guest, the mwait instruction is not available, leaving only the 'hlt' instruction (which causes a VMEXIT to the host). So for this common case, intel_idle will detect the lack of mwait, and fail to initialize (after which another idle method would step in which will just use hlt always). Other (non-common) cases exist; the table below shows the before/after for these: +------------+--------------------------+-------------------------+ | Hypervisor | Idle method before patch | Idle method after patch | | exposes | | | +============+==========================+=========================+ | nothing | default_idle fallback | intel_idle VM table | | (common) | (straight "hlt") | | +------------+--------------------------+-------------------------+ | mwait | intel_idle mwait table | intel_idle mwait table | +------------+--------------------------+-------------------------+ | ACPI | ACPI C1 state ("hlt") | intel_idle VM table | +------------+--------------------------+-------------------------+ This is only applicable to CPUs known by intel_idle. For the bare metal case, unknown CPU models will use the ACPI tables (when available) to get estimates for latency and break even point for longer idle states. In guests, the common case is that ACPI tables are not available, but even when they are available, they can't and don't provide the latency information for the longer (mwait based) states. For this scenario (unknown CPU model), the default_idle mode (no ACPI) or ACPI C1 (ACPI avaible) will be used. By providing capability to do this with the intel_idle driver, we can do better than the fallback or ACPI table methods. While this current change only gets us to the existing behavior, later patches in this series will add new capabilities such as optimized TLB flushing. In order to do this, a simplified version of the initialization function for VM guests is created, and this will be called if the CPU is recognized, but mwait is not supported, and we're in a VM guest. One thing to note is that the max latency (and break even) of this C1 state is higher than the typical bare metal C1 state. Because hlt causes a vmexit, and the cost of vmexit + hypervisor overhead + vmenter is typically in the order of upto 5 microseconds... even if the hypervisor does not actually goes into a hardware power saving state. Signed-off-by: Arjan van de Ven [ rjw: Dropped redundant checks from should_verify_mwait() ] Signed-off-by: Rafael J. Wysocki --- drivers/idle/intel_idle.c | 117 +++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 116 insertions(+), 1 deletion(-) (limited to 'drivers/idle/intel_idle.c') diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index 256c2d42e350..a80e1f520293 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -199,6 +199,43 @@ static __cpuidle int intel_idle_xstate(struct cpuidle_device *dev, return __intel_idle(dev, drv, index); } +static __always_inline int __intel_idle_hlt(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int index) +{ + raw_safe_halt(); + raw_local_irq_disable(); + return index; +} + +/** + * intel_idle_hlt - Ask the processor to enter the given idle state using hlt. + * @dev: cpuidle device of the target CPU. + * @drv: cpuidle driver (assumed to point to intel_idle_driver). + * @index: Target idle state index. + * + * Use the HLT instruction to notify the processor that the CPU represented by + * @dev is idle and it can try to enter the idle state corresponding to @index. + * + * Must be called under local_irq_disable(). + */ +static __cpuidle int intel_idle_hlt(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int index) +{ + return __intel_idle_hlt(dev, drv, index); +} + +static __cpuidle int intel_idle_hlt_irq_on(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int index) +{ + int ret; + + raw_local_irq_enable(); + ret = __intel_idle_hlt(dev, drv, index); + raw_local_irq_disable(); + + return ret; +} + /** * intel_idle_s2idle - Ask the processor to enter the given idle state. * @dev: cpuidle device of the target CPU. @@ -1242,6 +1279,18 @@ static struct cpuidle_state snr_cstates[] __initdata = { .enter = NULL } }; +static struct cpuidle_state vmguest_cstates[] __initdata = { + { + .name = "C1", + .desc = "HLT", + .flags = MWAIT2flg(0x00) | CPUIDLE_FLAG_IRQ_ENABLE, + .exit_latency = 5, + .target_residency = 10, + .enter = &intel_idle_hlt, }, + { + .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, @@ -1841,6 +1890,16 @@ static bool __init intel_idle_verify_cstate(unsigned int mwait_hint) static void state_update_enter_method(struct cpuidle_state *state, int cstate) { + if (state->enter == intel_idle_hlt) { + if (force_irq_on) { + pr_info("forced intel_idle_irq for state %d\n", cstate); + state->enter = intel_idle_hlt_irq_on; + } + return; + } + if (state->enter == intel_idle_hlt_irq_on) + return; /* no update scenarios */ + if (state->flags & CPUIDLE_FLAG_INIT_XSTATE) { /* * Combining with XSTATE with IBRS or IRQ_ENABLE flags @@ -1874,6 +1933,21 @@ static void state_update_enter_method(struct cpuidle_state *state, int cstate) } } +/* + * For mwait based states, we want to verify the cpuid data to see if the state + * is actually supported by this specific CPU. + * For non-mwait based states, this check should be skipped. + */ +static bool should_verify_mwait(struct cpuidle_state *state) +{ + if (state->enter == intel_idle_hlt) + return false; + if (state->enter == intel_idle_hlt_irq_on) + return false; + + return true; +} + static void __init intel_idle_init_cstates_icpu(struct cpuidle_driver *drv) { int cstate; @@ -1922,7 +1996,7 @@ static void __init intel_idle_init_cstates_icpu(struct cpuidle_driver *drv) } mwait_hint = flg2MWAIT(cpuidle_state_table[cstate].flags); - if (!intel_idle_verify_cstate(mwait_hint)) + if (should_verify_mwait(&cpuidle_state_table[cstate]) && !intel_idle_verify_cstate(mwait_hint)) continue; /* Structure copy. */ @@ -2056,6 +2130,45 @@ static void __init intel_idle_cpuidle_devices_uninit(void) cpuidle_unregister_device(per_cpu_ptr(intel_idle_cpuidle_devices, i)); } +static int __init intel_idle_vminit(const struct x86_cpu_id *id) +{ + int retval; + + cpuidle_state_table = vmguest_cstates; + + icpu = (const struct idle_cpu *)id->driver_data; + + pr_debug("v" INTEL_IDLE_VERSION " model 0x%X\n", + boot_cpu_data.x86_model); + + intel_idle_cpuidle_devices = alloc_percpu(struct cpuidle_device); + if (!intel_idle_cpuidle_devices) + return -ENOMEM; + + intel_idle_cpuidle_driver_init(&intel_idle_driver); + + retval = cpuidle_register_driver(&intel_idle_driver); + if (retval) { + struct cpuidle_driver *drv = cpuidle_get_driver(); + printk(KERN_DEBUG pr_fmt("intel_idle yielding to %s\n"), + drv ? drv->name : "none"); + goto init_driver_fail; + } + + retval = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "idle/intel:online", + intel_idle_cpu_online, NULL); + if (retval < 0) + goto hp_setup_fail; + + return 0; +hp_setup_fail: + intel_idle_cpuidle_devices_uninit(); + cpuidle_unregister_driver(&intel_idle_driver); +init_driver_fail: + free_percpu(intel_idle_cpuidle_devices); + return retval; +} + static int __init intel_idle_init(void) { const struct x86_cpu_id *id; @@ -2074,6 +2187,8 @@ static int __init intel_idle_init(void) id = x86_match_cpu(intel_idle_ids); if (id) { if (!boot_cpu_has(X86_FEATURE_MWAIT)) { + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) + return intel_idle_vminit(id); pr_debug("Please enable MWAIT in BIOS SETUP\n"); return -ENODEV; } -- cgit v1.2.3 From 0fac214bb75ee64d7b9e6521d53f8251a4d324ea Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Tue, 20 Jun 2023 18:03:54 +0000 Subject: intel_idle: Add a "Long HLT" C1 state for the VM guest mode intel_idle will, for the bare metal case, usually have one or more deep power states that have the CPUIDLE_FLAG_TLB_FLUSHED flag set. When a state with this flag is selected by the cpuidle framework, it will also flush the TLBs as part of entering this state. The benefit of doing this is that the kernel does not need to wake the cpu out of this deep power state just to flush the TLBs... for which the latency can be very high due to the exit latency of deep power states. In a VM guest currently, this benefit of avoiding the wakeup does not exist, while the problem (long exit latency) is even more severe. Linux will need to wake up a vCPU (causing the host to either come out of a deep C state, or the VMM to have to deschedule something else to schedule the vCPU) which can take a very long time.. adding a lot of latency to tlb flush operations (including munmap and others). To solve this, add a "Long HLT" C state to the state table for the VM guest case that has the CPUIDLE_FLAG_TLB_FLUSHED flag set. The result of that is that for long idle periods (where the VMM is likely to do things that cause large latency) the cpuidle framework will flush the TLBs (and avoid the wakeups), while for short/quick idle durations, the existing behavior is retained. Now, there is still only "hlt" available in the guest, but for long idle, the host can go to a deeper state (say C6). There is a reasonable debate one can have to what to set for the exit_latency and break even point for this "Long HLT" state. The good news is that intel_idle has these values available for the underlying CPU (even when mwait is not exposed). The solution thus is to just use the latency and break even of the deepest state from the bare metal CPU. This is under the assumption that this is a pretty reasonable estimate of what the VMM would do to cause latency. Signed-off-by: Arjan van de Ven Signed-off-by: Rafael J. Wysocki --- drivers/idle/intel_idle.c | 55 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 55 insertions(+) (limited to 'drivers/idle/intel_idle.c') diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index a80e1f520293..34201d7ef33e 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -1287,6 +1287,13 @@ static struct cpuidle_state vmguest_cstates[] __initdata = { .exit_latency = 5, .target_residency = 10, .enter = &intel_idle_hlt, }, + { + .name = "C1L", + .desc = "Long HLT", + .flags = MWAIT2flg(0x00) | CPUIDLE_FLAG_TLB_FLUSHED, + .exit_latency = 5, + .target_residency = 200, + .enter = &intel_idle_hlt, }, { .enter = NULL } }; @@ -2130,6 +2137,45 @@ static void __init intel_idle_cpuidle_devices_uninit(void) cpuidle_unregister_device(per_cpu_ptr(intel_idle_cpuidle_devices, i)); } +/* + * Match up the latency and break even point of the bare metal (cpu based) + * states with the deepest VM available state. + * + * We only want to do this for the deepest state, the ones that has + * the TLB_FLUSHED flag set on the . + * + * All our short idle states are dominated by vmexit/vmenter latencies, + * not the underlying hardware latencies so we keep our values for these. + */ +static void matchup_vm_state_with_baremetal(void) +{ + int cstate; + + for (cstate = 0; cstate < CPUIDLE_STATE_MAX; ++cstate) { + int matching_cstate; + + if (intel_idle_max_cstate_reached(cstate)) + break; + + if (!cpuidle_state_table[cstate].enter) + break; + + if (!(cpuidle_state_table[cstate].flags & CPUIDLE_FLAG_TLB_FLUSHED)) + continue; + + for (matching_cstate = 0; matching_cstate < CPUIDLE_STATE_MAX; ++matching_cstate) { + if (!icpu->state_table[matching_cstate].enter) + break; + if (icpu->state_table[matching_cstate].exit_latency > cpuidle_state_table[cstate].exit_latency) { + cpuidle_state_table[cstate].exit_latency = icpu->state_table[matching_cstate].exit_latency; + cpuidle_state_table[cstate].target_residency = icpu->state_table[matching_cstate].target_residency; + } + } + + } +} + + static int __init intel_idle_vminit(const struct x86_cpu_id *id) { int retval; @@ -2145,6 +2191,15 @@ static int __init intel_idle_vminit(const struct x86_cpu_id *id) if (!intel_idle_cpuidle_devices) return -ENOMEM; + /* + * We don't know exactly what the host will do when we go idle, but as a worst estimate + * we can assume that the exit latency of the deepest host state will be hit for our + * deep (long duration) guest idle state. + * The same logic applies to the break even point for the long duration guest idle state. + * So lets copy these two properties from the table we found for the host CPU type. + */ + matchup_vm_state_with_baremetal(); + intel_idle_cpuidle_driver_init(&intel_idle_driver); retval = cpuidle_register_driver(&intel_idle_driver); -- cgit v1.2.3 From b2918089d5cb452e928ad9f86c5ee601c592cee3 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 27 Jun 2023 19:50:48 +0200 Subject: intel_idle: Add __init annotation to matchup_vm_state_with_baremetal() The caller of (recently added) matchup_vm_state_with_baremetal() is an __init function and it uses some __initdata data structures, so add the __init annotation to it for consistency. This addresses the following build warnings: WARNING: modpost: vmlinux: section mismatch in reference: matchup_vm_state_with_baremetal+0x51 (section: .text) -> intel_idle_max_cstate_reached (section: .init.text) WARNING: modpost: vmlinux: section mismatch in reference: matchup_vm_state_with_baremetal+0x62 (section: .text) -> cpuidle_state_table (section: .init.data) WARNING: modpost: vmlinux: section mismatch in reference: matchup_vm_state_with_baremetal+0x79 (section: .text) -> icpu (section: .init.data) Fixes: 0fac214bb75e ("intel_idle: Add a "Long HLT" C1 state for the VM guest mode") Reported-by: Randy Dunlap Signed-off-by: Rafael J. Wysocki Tested-by: Randy Dunlap # build-tested Reviewed-by: Randy Dunlap --- drivers/idle/intel_idle.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/idle/intel_idle.c') diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index 34201d7ef33e..b930036edbbe 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -2147,7 +2147,7 @@ static void __init intel_idle_cpuidle_devices_uninit(void) * All our short idle states are dominated by vmexit/vmenter latencies, * not the underlying hardware latencies so we keep our values for these. */ -static void matchup_vm_state_with_baremetal(void) +static void __init matchup_vm_state_with_baremetal(void) { int cstate; -- cgit v1.2.3