diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2022-03-22 14:39:12 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2022-03-22 14:39:12 -0700 |
| commit | 3fe2f7446f1e029b220f7f650df6d138f91651f2 (patch) | |
| tree | bc6f9adc91f9e4fd4d78f49f1188388ebfa90bcb | |
| parent | ebd326ce724d5b2e5274724e6d6a46a046e28203 (diff) | |
| parent | ffea9fb319360b9ead8befac6bb2db2b54fd53e6 (diff) | |
Merge tag 'sched-core-2022-03-22' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull scheduler updates from Ingo Molnar:
- Cleanups for SCHED_DEADLINE
- Tracing updates/fixes
- CPU Accounting fixes
- First wave of changes to optimize the overhead of the scheduler
build, from the fast-headers tree - including placeholder *_api.h
headers for later header split-ups.
- Preempt-dynamic using static_branch() for ARM64
- Isolation housekeeping mask rework; preperatory for further changes
- NUMA-balancing: deal with CPU-less nodes
- NUMA-balancing: tune systems that have multiple LLC cache domains per
node (eg. AMD)
- Updates to RSEQ UAPI in preparation for glibc usage
- Lots of RSEQ/selftests, for same
- Add Suren as PSI co-maintainer
* tag 'sched-core-2022-03-22' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (81 commits)
sched/headers: ARM needs asm/paravirt_api_clock.h too
sched/numa: Fix boot crash on arm64 systems
headers/prep: Fix header to build standalone: <linux/psi.h>
sched/headers: Only include <linux/entry-common.h> when CONFIG_GENERIC_ENTRY=y
cgroup: Fix suspicious rcu_dereference_check() usage warning
sched/preempt: Tell about PREEMPT_DYNAMIC on kernel headers
sched/topology: Remove redundant variable and fix incorrect type in build_sched_domains
sched/deadline,rt: Remove unused parameter from pick_next_[rt|dl]_entity()
sched/deadline,rt: Remove unused functions for !CONFIG_SMP
sched/deadline: Use __node_2_[pdl|dle]() and rb_first_cached() consistently
sched/deadline: Merge dl_task_can_attach() and dl_cpu_busy()
sched/deadline: Move bandwidth mgmt and reclaim functions into sched class source file
sched/deadline: Remove unused def_dl_bandwidth
sched/tracing: Report TASK_RTLOCK_WAIT tasks as TASK_UNINTERRUPTIBLE
sched/tracing: Don't re-read p->state when emitting sched_switch event
sched/rt: Plug rt_mutex_setprio() vs push_rt_task() race
sched/cpuacct: Remove redundant RCU read lock
sched/cpuacct: Optimize away RCU read lock
sched/cpuacct: Fix charge percpu cpuusage
sched/headers: Reorganize, clean up and optimize kernel/sched/sched.h dependencies
...
135 files changed, 2345 insertions, 1307 deletions
diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst index 5dd660aac0ae..2d1b8c1ea2e8 100644 --- a/Documentation/admin-guide/sysctl/kernel.rst +++ b/Documentation/admin-guide/sysctl/kernel.rst @@ -609,51 +609,7 @@ be migrated to a local memory node. The unmapping of pages and trapping faults incur additional overhead that ideally is offset by improved memory locality but there is no universal guarantee. If the target workload is already bound to NUMA nodes then this -feature should be disabled. Otherwise, if the system overhead from the -feature is too high then the rate the kernel samples for NUMA hinting -faults may be controlled by the `numa_balancing_scan_period_min_ms, -numa_balancing_scan_delay_ms, numa_balancing_scan_period_max_ms, -numa_balancing_scan_size_mb`_, and numa_balancing_settle_count sysctls. - - -numa_balancing_scan_period_min_ms, numa_balancing_scan_delay_ms, numa_balancing_scan_period_max_ms, numa_balancing_scan_size_mb -=============================================================================================================================== - - -Automatic NUMA balancing scans tasks address space and unmaps pages to -detect if pages are properly placed or if the data should be migrated to a -memory node local to where the task is running. Every "scan delay" the task -scans the next "scan size" number of pages in its address space. When the -end of the address space is reached the scanner restarts from the beginning. - -In combination, the "scan delay" and "scan size" determine the scan rate. -When "scan delay" decreases, the scan rate increases. The scan delay and -hence the scan rate of every task is adaptive and depends on historical -behaviour. If pages are properly placed then the scan delay increases, -otherwise the scan delay decreases. The "scan size" is not adaptive but -the higher the "scan size", the higher the scan rate. - -Higher scan rates incur higher system overhead as page faults must be -trapped and potentially data must be migrated. However, the higher the scan -rate, the more quickly a tasks memory is migrated to a local node if the -workload pattern changes and minimises performance impact due to remote -memory accesses. These sysctls control the thresholds for scan delays and -the number of pages scanned. - -``numa_balancing_scan_period_min_ms`` is the minimum time in milliseconds to -scan a tasks virtual memory. It effectively controls the maximum scanning -rate for each task. - -``numa_balancing_scan_delay_ms`` is the starting "scan delay" used for a task -when it initially forks. - -``numa_balancing_scan_period_max_ms`` is the maximum time in milliseconds to -scan a tasks virtual memory. It effectively controls the minimum scanning -rate for each task. - -``numa_balancing_scan_size_mb`` is how many megabytes worth of pages are -scanned for a given scan. - +feature should be disabled. oops_all_cpu_backtrace ====================== diff --git a/Documentation/scheduler/index.rst b/Documentation/scheduler/index.rst index 693eaac769a7..b430d856056a 100644 --- a/Documentation/scheduler/index.rst +++ b/Documentation/scheduler/index.rst @@ -18,6 +18,7 @@ Linux Scheduler sched-nice-design sched-rt-group sched-stats + sched-debug text_files diff --git a/Documentation/scheduler/sched-debug.rst b/Documentation/scheduler/sched-debug.rst new file mode 100644 index 000000000000..4d3d24f2a439 --- /dev/null +++ b/Documentation/scheduler/sched-debug.rst @@ -0,0 +1,54 @@ +================= +Scheduler debugfs +================= + +Booting a kernel with CONFIG_SCHED_DEBUG=y will give access to +scheduler specific debug files under /sys/kernel/debug/sched. Some of +those files are described below. + +numa_balancing +============== + +`numa_balancing` directory is used to hold files to control NUMA +balancing feature. If the system overhead from the feature is too +high then the rate the kernel samples for NUMA hinting faults may be +controlled by the `scan_period_min_ms, scan_delay_ms, +scan_period_max_ms, scan_size_mb` files. + + +scan_period_min_ms, scan_delay_ms, scan_period_max_ms, scan_size_mb +------------------------------------------------------------------- + +Automatic NUMA balancing scans tasks address space and unmaps pages to +detect if pages are properly placed or if the data should be migrated to a +memory node local to where the task is running. Every "scan delay" the task +scans the next "scan size" number of pages in its address space. When the +end of the address space is reached the scanner restarts from the beginning. + +In combination, the "scan delay" and "scan size" determine the scan rate. +When "scan delay" decreases, the scan rate increases. The scan delay and +hence the scan rate of every task is adaptive and depends on historical +behaviour. If pages are properly placed then the scan delay increases, +otherwise the scan delay decreases. The "scan size" is not adaptive but +the higher the "scan size", the higher the scan rate. + +Higher scan rates incur higher system overhead as page faults must be +trapped and potentially data must be migrated. However, the higher the scan +rate, the more quickly a tasks memory is migrated to a local node if the +workload pattern changes and minimises performance impact due to remote +memory accesses. These files control the thresholds for scan delays and +the number of pages scanned. + +``scan_period_min_ms`` is the minimum time in milliseconds to scan a +tasks virtual memory. It effectively controls the maximum scanning +rate for each task. + +``scan_delay_ms`` is the starting "scan delay" used for a task when it +initially forks. + +``scan_period_max_ms`` is the maximum time in milliseconds to scan a +tasks virtual memory. It effectively controls the minimum scanning +rate for each task. + +``scan_size_mb`` is how many megabytes worth of pages are scanned for +a given scan. diff --git a/MAINTAINERS b/MAINTAINERS index 37adcd621a02..11d1a9ad9f35 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -15566,6 +15566,7 @@ F: drivers/net/ppp/pptp.c PRESSURE STALL INFORMATION (PSI) M: Johannes Weiner <hannes@cmpxchg.org> +M: Suren Baghdasaryan <surenb@google.com> S: Maintained F: include/linux/psi* F: kernel/sched/psi.c diff --git a/arch/Kconfig b/arch/Kconfig index cabfac22f2fb..17709ac1030a 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -1293,12 +1293,41 @@ config HAVE_STATIC_CALL_INLINE config HAVE_PREEMPT_DYNAMIC bool + +config HAVE_PREEMPT_DYNAMIC_CALL + bool depends on HAVE_STATIC_CALL - depends on GENERIC_ENTRY + select HAVE_PREEMPT_DYNAMIC + help + An architecture should select this if it can handle the preemption + model being selected at boot time using static calls. + + Where an architecture selects HAVE_STATIC_CALL_INLINE, any call to a + preemption function will be patched directly. + + Where an architecture does not select HAVE_STATIC_CALL_INLINE, any + call to a preemption function will go through a trampoline, and the + trampoline will be patched. + + It is strongly advised to support inline static call to avoid any + overhead. + +config HAVE_PREEMPT_DYNAMIC_KEY + bool + depends on HAVE_ARCH_JUMP_LABEL && CC_HAS_ASM_GOTO + select HAVE_PREEMPT_DYNAMIC help - Select this if the architecture support boot time preempt setting - on top of static calls. It is strongly advised to support inline - static call to avoid any overhead. + An architecture should select this if it can handle the preemption + model being selected at boot time using static keys. + + Each preemption function will be given an early return based on a + static key. This should have slightly lower overhead than non-inline + static calls, as this effectively inlines each trampoline into the + start of its callee. This may avoid redundant work, and may + integrate better with CFI schemes. + + This will have greater overhead than using inline static calls as + the call to the preemption function cannot be entirely elided. config ARCH_WANT_LD_ORPHAN_WARN bool diff --git a/arch/arm/include/asm/paravirt_api_clock.h b/arch/arm/include/asm/paravirt_api_clock.h new file mode 100644 index 000000000000..65ac7cee0dad --- /dev/null +++ b/arch/arm/include/asm/paravirt_api_clock.h @@ -0,0 +1 @@ +#include <asm/paravirt.h> diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 8c54de0cf3d6..13aa8d955c46 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -194,6 +194,7 @@ config ARM64 select HAVE_PERF_EVENTS select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP + select HAVE_PREEMPT_DYNAMIC_KEY select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_POSIX_CPU_TIMERS_TASK_WORK select HAVE_FUNCTION_ARG_ACCESS_API diff --git a/arch/arm64/include/asm/paravirt_api_clock.h b/arch/arm64/include/asm/paravirt_api_clock.h new file mode 100644 index 000000000000..65ac7cee0dad --- /dev/null +++ b/arch/arm64/include/asm/paravirt_api_clock.h @@ -0,0 +1 @@ +#include <asm/paravirt.h> diff --git a/arch/arm64/include/asm/preempt.h b/arch/arm64/include/asm/preempt.h index e83f0982b99c..0159b625cc7f 100644 --- a/arch/arm64/include/asm/preempt.h +++ b/arch/arm64/include/asm/preempt.h @@ -2,6 +2,7 @@ #ifndef __ASM_PREEMPT_H #define __ASM_PREEMPT_H +#include <linux/jump_label.h> #include <linux/thread_info.h> #define PREEMPT_NEED_RESCHED BIT(32) @@ -80,10 +81,24 @@ static inline bool should_resched(int preempt_offset) } #ifdef CONFIG_PREEMPTION + void preempt_schedule(void); -#define __preempt_schedule() preempt_schedule() void preempt_schedule_notrace(void); -#define __preempt_schedule_notrace() preempt_schedule_notrace() + +#ifdef CONFIG_PREEMPT_DYNAMIC + +DECLARE_STATIC_KEY_TRUE(sk_dynamic_irqentry_exit_cond_resched); +void dynamic_preempt_schedule(void); +#define __preempt_schedule() dynamic_preempt_schedule() +void dynamic_preempt_schedule_notrace(void); +#define __preempt_schedule_notrace() dynamic_preempt_schedule_notrace() + +#else /* CONFIG_PREEMPT_DYNAMIC */ + +#define __preempt_schedule() preempt_schedule() +#define __preempt_schedule_notrace() preempt_schedule_notrace() + +#endif /* CONFIG_PREEMPT_DYNAMIC */ #endif /* CONFIG_PREEMPTION */ #endif /* __ASM_PREEMPT_H */ diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c index 7093b578e325..878c65aa7206 100644 --- a/arch/arm64/kernel/entry-common.c +++ b/arch/arm64/kernel/entry-common.c @@ -223,9 +223,26 @@ static void noinstr arm64_exit_el1_dbg(struct pt_regs *regs) lockdep_hardirqs_on(CALLER_ADDR0); } +#ifdef CONFIG_PREEMPT_DYNAMIC +DEFINE_STATIC_KEY_TRUE(sk_dynamic_irqentry_exit_cond_resched); +#define need_irq_preemption() \ + (static_branch_unlikely(&sk_dynamic_irqentry_exit_cond_resched)) +#else +#define need_irq_preemption() (IS_ENABLED(CONFIG_PREEMPTION)) +#endif + static void __sched arm64_preempt_schedule_irq(void) { - lockdep_assert_irqs_disabled(); + if (!need_irq_preemption()) + return; + + /* + * Note: thread_info::preempt_count includes both thread_info::count + * and thread_info::need_resched, and is not equivalent to + * preempt_count(). + */ + if (READ_ONCE(current_thread_info()->preempt_count) != 0) + return; /* * DAIF.DA are cleared at the start of IRQ/FIQ handling, and when GIC @@ -441,14 +458,7 @@ static __always_inline void __el1_irq(struct pt_regs *regs, do_interrupt_handler(regs, handler); irq_exit_rcu(); - /* - * Note: thread_info::preempt_count includes both thread_info::count - * and thread_info::need_resched, and is not equivalent to - * preempt_count(). - */ - if (IS_ENABLED(CONFIG_PREEMPTION) && - READ_ONCE(current_thread_info()->preempt_count) == 0) - arm64_preempt_schedule_irq(); + arm64_preempt_schedule_irq(); exit_to_kernel_mode(regs); } diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 327e045540fa..42a3a736436f 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -248,7 +248,7 @@ config X86 select HAVE_STACK_VALIDATION if X86_64 select HAVE_STATIC_CALL select HAVE_STATIC_CALL_INLINE if HAVE_STACK_VALIDATION - select HAVE_PREEMPT_DYNAMIC + select HAVE_PREEMPT_DYNAMIC_CALL select HAVE_RSEQ select HAVE_SYSCALL_TRACEPOINTS select HAVE_UNSTABLE_SCHED_CLOCK diff --git a/arch/x86/include/asm/paravirt_api_clock.h b/arch/x86/include/asm/paravirt_api_clock.h new file mode 100644 index 000000000000..65ac7cee0dad --- /dev/null +++ b/arch/x86/include/asm/paravirt_api_clock.h @@ -0,0 +1 @@ +#include <asm/paravirt.h> diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h index fe5efbcba824..5f6daea1ee24 100644 --- a/arch/x86/include/asm/preempt.h +++ b/arch/x86/include/asm/preempt.h @@ -108,16 +108,18 @@ static __always_inline bool should_resched(int preempt_offset) extern asmlinkage void preempt_schedule(void); extern asmlinkage void preempt_schedule_thunk(void); -#define __preempt_schedule_func preempt_schedule_thunk +#define preempt_schedule_dynamic_enabled preempt_schedule_thunk +#define preempt_schedule_dynamic_disabled NULL extern asmlinkage void preempt_schedule_notrace(void); extern asmlinkage void preempt_schedule_notrace_thunk(void); -#define __preempt_schedule_notrace_func preempt_schedule_notrace_thunk +#define preempt_schedule_notrace_dynamic_enabled preempt_schedule_notrace_thunk +#define preempt_schedule_notrace_dynamic_disabled NULL #ifdef CONFIG_PREEMPT_DYNAMIC -DECLARE_STATIC_CALL(preempt_schedule, __preempt_schedule_func); +DECLARE_STATIC_CALL(preempt_schedule, preempt_schedule_dynamic_enabled); #define __preempt_schedule() \ do { \ @@ -125,7 +127,7 @@ do { \ asm volatile ("call " STATIC_CALL_TRAMP_STR(preempt_schedule) : ASM_CALL_CONSTRAINT); \ } while (0) -DECLARE_STATIC_CALL(preempt_schedule_notrace, __preempt_schedule_notrace_func); +DECLARE_STATIC_CALL(preempt_schedule_notrace, preempt_schedule_notrace_dynamic_enabled); #define __preempt_schedule_notrace() \ do { \ diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c index 22911deacb6e..9ca008f9e9b1 100644 --- a/arch/x86/kernel/cpu/aperfmperf.c +++ b/arch/x86/kernel/cpu/aperfmperf.c @@ -91,7 +91,7 @@ unsigned int aperfmperf_get_khz(int cpu) if (!boot_cpu_has(X86_FEATURE_APERFMPERF)) return 0; - if (!housekeeping_cpu(cpu, HK_FLAG_MISC)) + if (!housekeeping_cpu(cpu, HK_TYPE_MISC)) return 0; if (rcu_is_idle_cpu(cpu)) @@ -114,7 +114,7 @@ void arch_freq_prepare_all(void) return; for_each_online_cpu(cpu) { - if (!housekeeping_cpu(cpu, HK_FLAG_MISC)) + if (!housekeeping_cpu(cpu, HK_TYPE_MISC)) continue; if (rcu_is_idle_cpu(cpu)) continue; /* Idle CPUs are completely uninteresting. */ @@ -136,7 +136,7 @@ unsigned int arch_freq_get_on_cpu(int cpu) if (!boot_cpu_has(X86_FEATURE_APERFMPERF)) return 0; - if (!housekeeping_cpu(cpu, HK_FLAG_MISC)) + if (!housekeeping_cpu(cpu, HK_TYPE_MISC)) return 0; if (aperfmperf_snapshot_cpu(cpu, ktime_get(), true)) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index eb8269a4c83c..6db3a506b402 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -8853,7 +8853,7 @@ int kvm_arch_init(void *opaque) } if (pi_inject_timer == -1) - pi_inject_timer = housekeeping_enabled(HK_FLAG_TIMER); + pi_inject_timer = housekeeping_enabled(HK_TYPE_TIMER); #ifdef CONFIG_X86_64 pvclock_gtod_register_notifier(&pvclock_gtod_notifier); diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index 5fc258073bc7..2ef23fce0860 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -275,7 +275,7 @@ static ssize_t print_cpus_isolated(struct device *dev, return -ENOMEM; cpumask_andnot(isolated, cpu_possible_mask, - housekeeping_cpumask(HK_FLAG_DOMAIN)); + housekeeping_cpumask(HK_TYPE_DOMAIN)); len = sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(isolated)); free_cpumask_var(isolated); diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index 415f7664b010..4ceeb75fc899 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -350,7 +350,6 @@ static int pci_call_probe(struct pci_driver *drv, struct pci_dev *dev, const struct pci_device_id *id) { int error, node, cpu; - int hk_flags = HK_FLAG_DOMAIN | HK_FLAG_WQ; struct drv_dev_and_id ddi = { drv, dev, id }; /* @@ -368,17 +367,29 @@ static int pci_call_probe(struct pci_driver *drv, struct pci_dev *dev, * device is probed from work_on_cpu() of the Physical device. */ if (node < 0 || node >= MAX_NUMNODES || !node_online(node) || - pci_physfn_is_probed(dev)) + pci_physfn_is_probed(dev)) { cpu = nr_cpu_ids; - else + } else { + cpumask_var_t wq_domain_mask; + + if (!zalloc_cpumask_var(&wq_domain_mask, GFP_KERNEL)) { + error = -ENOMEM; + goto out; + } + cpumask_and(wq_domain_mask, + housekeeping_cpumask(HK_TYPE_WQ), + housekeeping_cpumask(HK_TYPE_DOMAIN)); + cpu = cpumask_any_and(cpumask_of_node(node), - housekeeping_cpumask(hk_flags)); + wq_domain_mask); + free_cpumask_var(wq_domain_mask); + } if (cpu < nr_cpu_ids) error = work_on_cpu(cpu, local_pci_probe, &ddi); else error = local_pci_probe(&ddi); - +out: dev->is_probed = 0; cpu_hotplug_enable(); return error; diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 75c151413fda..0d1ada8968d7 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -450,6 +450,7 @@ extern struct mutex cgroup_mutex; extern spinlock_t css_set_lock; #define task_css_set_check(task, __c) \ rcu_dereference_check((task)->cgroups, \ + rcu_read_lock_sched_held() || \ lockdep_is_held(&cgroup_mutex) || \ lockdep_is_held(&css_set_lock) || \ ((task)->flags & PF_EXITING) || (__c)) @@ -791,11 +792,9 @@ static inline void cgroup_account_cputime(struct task_struct *task, cpuacct_charge(task, delta_exec); - rcu_read_lock(); cgrp = task_dfl_cgroup(task); if (cgroup_parent(cgrp)) __cgroup_account_cputime(cgrp, delta_exec); - rcu_read_unlock(); } static inline void cgroup_account_cputime_field(struct task_struct *task, @@ -806,11 +805,9 @@ static inline void cgroup_account_cputime_field(struct task_struct *task, cpuacct_account_field(task, index, delta_exec); - rcu_read_lock(); cgrp = task_dfl_cgroup(task); if (cgroup_parent(cgrp)) __cgroup_account_cputime_field(cgrp, index, delta_exec); - rcu_read_unlock(); } #else /* CONFIG_CGROUPS */ diff --git a/include/linux/cgroup_api.h b/include/linux/cgroup_api.h new file mode 100644 index 000000000000..d0cfe8025111 --- /dev/null +++ b/include/linux/cgroup_api.h @@ -0,0 +1 @@ +#include <linux/cgroup.h> diff --git a/include/linux/cpumask_api.h b/include/linux/cpumask_api.h new file mode 100644 index 000000000000..83bd3ebe82b0 --- /dev/null +++ b/include/linux/cpumask_api.h @@ -0,0 +1 @@ +#include <linux/cpumask.h> diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h index 2e2b8d6140ed..141952f4fee8 100644 --- a/include/linux/entry-common.h +++ b/include/linux/entry-common.h @@ -454,10 +454,21 @@ irqentry_state_t noinstr irqentry_enter(struct pt_regs *regs); * * Conditional reschedule with additional sanity checks. */ -void irqentry_exit_cond_resched(void); +void raw_irqentry_exit_cond_resched(void); #ifdef CONFIG_PREEMPT_DYNAMIC -DECLARE_STATIC_CALL(irqentry_exit_cond_resched, irqentry_exit_cond_resched); +#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL) +#define irqentry_exit_cond_resched_dynamic_enabled raw_irqentry_exit_cond_resched +#define irqentry_exit_cond_resched_dynamic_disabled NULL +DECLARE_STATIC_CALL(irqentry_exit_cond_resched, raw_irqentry_exit_cond_resched); +#define irqentry_exit_cond_resched() static_call(irqentry_exit_cond_resched)() +#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY) +DECLARE_STATIC_KEY_TRUE(sk_dynamic_irqentry_exit_cond_resched); +void dynamic_irqentry_exit_cond_resched(void); +#define irqentry_exit_cond_resched() dynamic_irqentry_exit_cond_resched() #endif +#else /* CONFIG_PREEMPT_DYNAMIC */ +#define irqentry_exit_cond_resched() raw_irqentry_exit_cond_resched() +#endif /* CONFIG_PREEMPT_DYNAMIC */ /** * irqentry_exit - Handle return from exception that used irqentry_enter() diff --git a/include/linux/fs_api.h b/include/linux/fs_api.h new file mode 100644 index 000000000000..83be38d6d413 --- /dev/null +++ b/include/linux/fs_api.h @@ -0,0 +1 @@ +#include <linux/fs.h> diff --git a/include/linux/gfp_api.h b/include/linux/gfp_api.h new file mode 100644 index 000000000000..5a05a2764a86 --- /dev/null +++ b/include/linux/gfp_api.h @@ -0,0 +1 @@ +#include <linux/gfp.h> diff --git a/include/linux/hashtable_api.h b/include/linux/hashtable_api.h new file mode 100644 index 000000000000..c268ac2c5c0e --- /dev/null +++ b/include/linux/hashtable_api.h @@ -0,0 +1 @@ +#include <linux/hashtable.h> diff --git a/include/linux/hrtimer_api.h b/include/linux/hrtimer_api.h new file mode 100644 index 000000000000..8d9700894468 --- /dev/null +++ b/include/linux/hrtimer_api.h @@ -0,0 +1 @@ +#include <linux/hrtimer.h> diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 33f47a996513..a890428bcc1a 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -99,7 +99,7 @@ struct user; extern int __cond_resched(void); # define might_resched() __cond_resched() -#elif defined(CONFIG_PREEMPT_DYNAMIC) +#elif defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL) extern int __cond_resched(void); @@ -110,6 +110,11 @@ static __always_inline void might_resched(void) static_call_mod(might_resched)(); } +#elif defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY) + +extern int dynamic_might_resched(void); +# define might_resched() dynamic_might_resched() + #else # define might_resched() do { } while (0) diff --git a/include/linux/kobject_api.h b/include/linux/kobject_api.h new file mode 100644 index 000000000000..6e36a054c2d6 --- /dev/null +++ b/include/linux/kobject_api.h @@ -0,0 +1 @@ +#include <linux/kobject.h> diff --git a/include/linux/kref_api.h b/include/linux/kref_api.h new file mode 100644 index 000000000000..d67e554721d2 --- /dev/null +++ b/include/linux/kref_api.h @@ -0,0 +1 @@ +#include <linux/kref.h> diff --git a/include/linux/ktime_api.h b/include/linux/ktime_api.h new file mode 100644 index 000000000000..f697d493960f --- /dev/null +++ b/include/linux/ktime_api.h @@ -0,0 +1 @@ +#include <linux/ktime.h> diff --git a/include/linux/llist_api.h b/include/linux/llist_api.h new file mode 100644 index 000000000000..625bec0393a1 --- /dev/null +++ b/include/linux/llist_api.h @@ -0,0 +1 @@ +#include <linux/llist.h> diff --git a/include/linux/lockdep_api.h b/include/linux/lockdep_api.h new file mode 100644 index 000000000000..907e66979ab2 --- /dev/null +++ b/include/linux/lockdep_api.h @@ -0,0 +1 @@ +#include <linux/lockdep.h> diff --git a/include/linux/mm_api.h b/include/linux/mm_api.h new file mode 100644 index 000000000000..a5ace2b198b8 --- /dev/null +++ b/include/linux/mm_api.h @@ -0,0 +1 @@ +#include <linux/mm.h> diff --git a/include/linux/mutex_api.h b/include/linux/mutex_api.h new file mode 100644 index 000000000000..85ab9491e13e --- /dev/null +++ b/include/linux/mutex_api.h @@ -0,0 +1 @@ +#include <linux/mutex.h> diff --git a/include/linux/perf_event_api.h b/include/linux/perf_event_api.h new file mode 100644 index 000000000000..c2fd6048b790 --- /dev/null +++ b/include/linux/perf_event_api.h @@ -0,0 +1 @@ +#include <linux/perf_event.h> diff --git a/include/linux/pgtable_api.h b/include/linux/pgtable_api.h new file mode 100644 index 000000000000..ff367a4ba8c4 --- /dev/null +++ b/include/linux/pgtable_api.h @@ -0,0 +1 @@ +#include <linux/pgtable.h> diff --git a/include/linux/psi.h b/include/linux/psi.h index 7f7d1d88c3bb..89784763d19e 100644 --- a/include/linux/psi.h +++ b/include/linux/psi.h @@ -6,6 +6,7 @@ #include <linux/psi_types.h> #include <linux/sched.h> #include <linux/poll.h> +#include <linux/cgroup-defs.h> struct seq_file; struct css_set; diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h index 1a3cef26d129..c7fe7c089718 100644 --- a/include/linux/psi_types.h +++ b/include/linux/psi_types.h @@ -141,6 +141,9 @@ struct psi_trigger { * events to one per window */ u64 last_event_time; + + /* Deferred event(s) from previous ratelimit window */ + bool pending_event; }; struct psi_group { diff --git a/include/linux/ptrace_api.h b/include/linux/ptrace_api.h new file mode 100644 index 000000000000..26e7d275ad8d --- /dev/null +++ b/include/linux/ptrace_api.h @@ -0,0 +1 @@ +#include <linux/ptrace.h> diff --git a/include/linux/rcuwait_api.h b/include/linux/rcuwait_api.h new file mode 100644 index 000000000000..f962e28544dd --- /dev/null +++ b/include/linux/rcuwait_api.h @@ -0,0 +1 @@ +#include <linux/rcuwait.h> diff --git a/include/linux/refcount_api.h b/include/linux/refcount_api.h new file mode 100644 index 000000000000..5f032589f568 --- /dev/null +++ b/include/linux/refcount_api.h @@ -0,0 +1 @@ +#include <linux/refcount.h> diff --git a/include/linux/sched.h b/include/linux/sched.h index aab75966396f..fee34a8a8fe8 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1626,19 +1626,32 @@ static inline pid_t task_pgrp_nr(struct task_struct *tsk) #define TASK_REPORT_IDLE (TASK_REPORT + 1) #define TASK_REPORT_MAX (TASK_REPORT_IDLE << 1) -static inline unsigned int task_state_index(struct task_struct *tsk) +static inline unsigned int __task_state_index(unsigned int tsk_state, + unsigned int tsk_exit_state) { - unsigned int tsk_state = READ_ONCE(tsk->__state); - unsigned int state = (tsk_state | tsk->exit_state) & TASK_REPORT; + unsigned int state = (tsk_state | tsk_exit_state) & TASK_REPORT; BUILD_BUG_ON_NOT_POWER_OF_2(TASK_REPORT_MAX); if (tsk_state == TASK_IDLE) state = TASK_REPORT_IDLE; + /* + * We're lying here, but rather than expose a completely new task state + * to userspace, we can make this appear as if the task has gone through + * a regular rt_mutex_lock() call. + */ + if (tsk_state == TASK_RTLOCK_WAIT) + state = TASK_UNINTERRUPTIBLE; + return fls(state); } +static inline unsigned int task_state_index(struct task_struct *tsk) +{ + return __task_state_index(READ_ONCE(tsk->__state), tsk->exit_state); +} + static inline char task_index_to_char(unsigned int state) { static const char state_char[] = "RSDTtXZPI"; @@ -2021,7 +2034,7 @@ static inline int test_tsk_need_resched(struct task_struct *tsk) #if !defined(CONFIG_PREEMPTION) || defined(CONFIG_PREEMPT_DYNAMIC) extern int __cond_resched(void); -#ifdef CONFIG_PREEMPT_DYNAMIC +#if defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL) DECLARE_STATIC_CALL(cond_resched, __cond_resched); @@ -2030,6 +2043,14 @@ static __always_inline int _cond_resched(void) return static_call_mod(cond_resched)(); } +#elif defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY) +extern int dynamic_cond_resched(void); + +static __always_inline int _cond_resched(void) +{ + return dynamic_cond_resched(); +} + #else static inline int _cond_resched(void) diff --git a/include/linux/sched/affinity.h b/include/linux/sched/affinity.h new file mode 100644 index 000000000000..227f5be81bcd --- /dev/null +++ b/include/linux/sched/affinity.h @@ -0,0 +1 @@ +#include <linux/sched.h> diff --git a/include/linux/sched/cond_resched.h b/include/linux/sched/cond_resched.h new file mode 100644 index 000000000000..227f5be81bcd --- /dev/null +++ b/include/linux/sched/cond_resched.h @@ -0,0 +1 @@ +#include <linux/sched.h> diff --git a/include/linux/sched/deadline.h b/include/linux/sched/deadline.h index 1aff00b65f3c..7c83d4d5a971 100644 --- a/include/linux/sched/deadline.h +++ b/include/linux/sched/deadline.h @@ -6,6 +6,8 @@ * NORMAL/BATCH tasks. */ +#include <linux/sched.h> + #define MAX_DL_PRIO 0 static inline int dl_prio(int prio) diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h index cc9f393e2a70..8c15abd67aed 100644 --- a/include/linux/sched/isolation.h +++ b/include/linux/sched/isolation.h @@ -5,54 +5,55 @@ #include <linux/init.h> #include <linux/tick.h> -enum hk_flags { - HK_FLAG_TIMER = 1, - HK_FLAG_RCU = (1 << 1), - HK_FLAG_MISC = (1 << 2), - HK_FLAG_SCHED = (1 << 3), - HK_FLAG_TICK = (1 << 4), - HK_FLAG_DOMAIN = (1 << 5), - HK_FLAG_WQ = (1 << 6), - HK_FLAG_MANAGED_IRQ = (1 << 7), - HK_FLAG_KTHREAD = (1 << 8), +enum hk_type { + HK_TYPE_TIMER, + HK_TYPE_RCU, + HK_TYPE_MISC, + HK_TYPE_SCHED, + HK_TYPE_TICK, + HK_TYPE_DOMAIN, + HK_TYPE_WQ, + HK_TYPE_MANAGED_IRQ, + HK_TYPE_KTHREAD, + HK_TYPE_MAX }; #ifdef CONFIG_CPU_ISOLATION DECLARE_STATIC_KEY_FALSE(housekeeping_overridden); -extern int housekeeping_any_cpu(enum hk_flags flags); -extern const struct cpumask *housekeeping_cpumask(enum hk_flags flags); -extern bool housekeeping_enabled(enum hk_flags flags); -extern void housekeeping_affine(struct task_struct *t, enum hk_flags flags); -extern bool housekeeping_test_cpu(int cpu, enum hk_flags flags); +extern int housekeeping_any_cpu(enum hk_type type); +extern const struct cpumask *housekeeping_cpumask(enum hk_type type); +extern bool housekeeping_enabled(enum hk_type type); +extern void housekeeping_affine(struct task_struct *t, enum hk_type type); +extern bool housekeeping_test_cpu(int cpu, enum hk_type type); extern void __init housekeeping_init(void); #else -static inline int housekeeping_any_cpu(enum hk_flags flags) +static inline int housekeeping_any_cpu(enum hk_type type) { return smp_processor_id(); } -static inline const struct cpumask *housekeeping_cpumask(enum hk_flags flags) +static inline const struct cpumask *housekeeping_cpumask(enum hk_type type) { return cpu_possible_mask; } -static inline bool housekeeping_enabled(enum hk_flags flags) +static inline bool housekeeping_enabled(enum hk_type type) { return false; } static inline void housekeeping_affine(struct task_struct *t, - enum hk_flags flags) { } + enum hk_type type) { } static inline void housekeeping_init(void) { } #endif /* CONFIG_CPU_ISOLATION */ -static inline bool housekeeping_cpu(int cpu, enum hk_flags flags) +static inline bool housekeeping_cpu(int cpu, enum hk_type type) { #ifdef CONFIG_CPU_ISOLATION if (static_branch_unlikely(&housekeeping_overridden)) - return housekeeping_test_cpu(cpu, flags); + return housekeeping_test_cpu(cpu, type); #endif return true; } diff --git a/include/linux/sched/posix-timers.h b/include/linux/sched/posix-timers.h new file mode 100644 index 000000000000..523a381d6c88 --- /dev/null +++ b/include/linux/sched/posix-timers.h @@ -0,0 +1 @@ +#include <linux/posix-timers.h> diff --git a/include/linux/sched/rseq_api.h b/include/linux/sched/rseq_api.h new file mode 100644 index 000000000000..cf2af72693e1 --- /dev/null +++ b/include/linux/sched/rseq_api.h @@ -0,0 +1 @@ +#include <linux/rseq.h> diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index c19dd5a2c05c..3f2b70f8d32c 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -45,10 +45,6 @@ extern unsigned int sysctl_sched_uclamp_util_min_rt_default; extern unsigned int sysctl_sched_cfs_bandwidth_slice; #endif -#ifdef CONFIG_SCHED_AUTOGROUP -extern unsigned int sysctl_sched_autogroup_enabled; -#endif - extern int sysctl_sched_rr_timeslice; extern int sched_rr_timeslice; diff --git a/include/linux/sched/task_flags.h b/include/linux/sched/task_flags.h new file mode 100644 index 000000000000..227f5be81bcd --- /dev/null +++ b/include/linux/sched/task_flags.h @@ -0,0 +1 @@ +#include <linux/sched.h> diff --git a/include/linux/sched/thread_info_api.h b/include/linux/sched/thread_info_api.h new file mode 100644 index 000000000000..2c60fbc16c08 --- /dev/null +++ b/include/linux/sched/thread_info_api.h @@ -0,0 +1 @@ +#include <linux/thread_info.h> diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 8054641c0a7b..56cffe42abbc 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -93,6 +93,7 @@ struct sched_domain { unsigned int busy_factor; /* less balancing by factor if busy */ unsigned int imbalance_pct; /* No balance until over watermark */ unsigned int cache_nice_tries; /* Leave cache hot tasks for # tries */ + unsigned int imb_numa_nr; /* Nr running tasks that allows a NUMA imbalance */ int nohz_idle; /* NOHZ IDLE status */ int flags; /* See SD_* */ diff --git a/include/linux/sched_clock.h b/include/linux/sched_clock.h index 835ee87ed792..cb41c5edb4d4 100644 --- a/include/linux/sched_clock.h +++ b/include/linux/sched_clock.h @@ -5,6 +5,8 @@ #ifndef LINUX_SCHED_CLOCK #define LINUX_SCHED_CLOCK +#include <linux/types.h> + #ifdef CONFIG_GENERIC_SCHED_CLOCK /** * struct clock_read_data - data required to read from sched_clock() diff --git a/include/linux/seqlock_api.h b/include/linux/seqlock_api.h new file mode 100644 index 000000000000..be91e7d3b826 --- /dev/null +++ b/include/linux/seqlock_api.h @@ -0,0 +1 @@ +#include <linux/seqlock.h> diff --git a/include/linux/softirq.h b/include/linux/softirq.h new file mode 100644 index 000000000000..c73d7dcb4cb5 --- /dev/null +++ b/include/linux/softirq.h @@ -0,0 +1 @@ +#include <linux/interrupt.h> diff --git a/include/linux/spinlock_api.h b/include/linux/spinlock_api.h new file mode 100644 index 000000000000..6338b27f98df --- /dev/null +++ b/include/linux/spinlock_api.h @@ -0,0 +1 @@ +#include <linux/spinlock.h> diff --git a/include/linux/swait_api.h b/include/linux/swait_api.h new file mode 100644 index 000000000000..1eeaaaaa5ea7 --- /dev/null +++ b/include/linux/swait_api.h @@ -0,0 +1 @@ +#include <linux/swait.h> diff --git a/include/linux/syscalls_api.h b/include/linux/syscalls_api.h new file mode 100644 index 000000000000..23e012b04db4 --- /dev/null +++ b/include/linux/syscalls_api.h @@ -0,0 +1 @@ +#include <linux/syscalls.h> diff --git a/include/linux/u64_stats_sync_api.h b/include/linux/u64_stats_sync_api.h new file mode 100644 index 000000000000..c72ca63da44b --- /dev/null +++ b/include/linux/u64_stats_sync_api.h @@ -0,0 +1 @@ +#include <linux/u64_stats_sync.h> diff --git a/include/linux/wait_api.h b/include/linux/wait_api.h new file mode 100644 index 000000000000..4e930548935a --- /dev/null +++ b/include/linux/wait_api.h @@ -0,0 +1 @@ +#include <linux/wait.h> diff --git a/include/linux/workqueue_api.h b/include/linux/workqueue_api.h new file mode 100644 index 000000000000..77debb5d2760 --- /dev/null +++ b/include/linux/workqueue_api.h @@ -0,0 +1 @@ +#include <linux/workqueue.h> diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h index 94640482cfe7..65e786756321 100644 --- a/include/trace/events/sched.h +++ b/include/trace/events/sched.h @@ -187,7 +187,9 @@ DEFINE_EVENT(sched_wakeup_template, sched_wakeup_new, TP_ARGS(p)); #ifdef CREATE_TRACE_POINTS -static inline long __trace_sched_switch_state(bool preempt, struct task_struct *p) +static inline long __trace_sched_switch_state(bool preempt, + unsigned int prev_state, + struct task_struct *p) { unsigned int state; @@ -208,7 +210,7 @@ static inline long __trace_sched_switch_state(bool preempt, struct task_struct * * it for left shift operation to get the correct task->state * mapping. */ - state = task_state_index(p); + state = __task_state_index(prev_state, p->exit_state); return state ? (1 << (state - 1)) : state; } @@ -220,10 +222,11 @@ static inline long __trace_sched_switch_state(bool preempt, struct task_struct * TRACE_EVENT(sched_switch, TP_PROTO(bool preempt, + unsigned int prev_state, struct task_struct *prev, struct task_struct *next), - TP_ARGS(preempt, prev, next), + TP_ARGS(preempt, prev_state, prev, next), TP_STRUCT__entry( __array( char, prev_comm, TASK_COMM_LEN ) @@ -239,7 +242,7 @@ TRACE_EVENT(sched_switch, memcpy(__entry->next_comm, next->comm, TASK_COMM_LEN); __entry->prev_pid = prev->pid; __entry->prev_prio = prev->prio; - __entry->prev_state = __trace_sched_switch_state(preempt, prev); + __entry->prev_state = __trace_sched_switch_state(preempt, prev_state, prev); memcpy(__entry->prev_comm, prev->comm, TASK_COMM_LEN); __entry->next_pid = next->pid; __entry->next_prio = next->prio; diff --git a/include/uapi/linux/rseq.h b/include/uapi/linux/rseq.h index 9a402fdb60e9..77ee207623a9 100644 --- a/include/uapi/linux/rseq.h +++ b/include/uapi/linux/rseq.h @@ -105,23 +105,11 @@ struct rseq { * Read and set by the kernel. Set by user-space with single-copy * atomicity semantics. This field should only be updated by the * thread which registered this data structure. Aligned on 64-bit. + * + * 32-bit architectures should update the low order bits of the + * rseq_cs field, leaving the high order bits initialized to 0. */ - union { - __u64 ptr64; -#ifdef __LP64__ - __u64 ptr; -#else - struct { -#if (defined(__BYTE_ORDER) && (__BYTE_ORDER == __BIG_ENDIAN)) || defined(__BIG_ENDIAN) - __u32 padding; /* Initialized to zero. */ - __u32 ptr32; -#else /* LITTLE */ - __u32 ptr32; - __u32 padding; /* Initialized to zero. */ -#endif /* ENDIAN */ - } ptr; -#endif - } rseq_cs; + __u64 rseq_cs; /* * Restartable sequences flags field. diff --git a/init/Makefile b/init/Makefile index 06326e304384..d82623d7fc8e 100644 --- a/init/Makefile +++ b/init/Makefile @@ -31,7 +31,8 @@ quiet_cmd_compile.h = CHK $@ cmd_compile.h = \ $(CONFIG_SHELL) $(srctree)/scripts/mkcompile_h $@ \ "$(UTS_MACHINE)" "$(CONFIG_SMP)" "$(CONFIG_PREEMPT_BUILD)" \ - "$(CONFIG_PREEMPT_RT)" "$(CONFIG_CC_VERSION_TEXT)" "$(LD)" + "$(CONFIG_PREEMPT_DYNAMIC)" "$(CONFIG_PREEMPT_RT)" \ + "$(CONFIG_CC_VERSION_TEXT)" "$(LD)" include/generated/compile.h: FORCE $(call cmd,compile.h) diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt index 5644abd5f8a8..8c6de5a9ecc4 100644 --- a/kernel/Kconfig.preempt +++ b/kernel/Kconfig.preempt @@ -96,8 +96,9 @@ config PREEMPTION config PREEMPT_DYNAMIC bool "Preemption behaviour defined on boot" depends on HAVE_PREEMPT_DYNAMIC && !PREEMPT_RT + select JUMP_LABEL if HAVE_PREEMPT_DYNAMIC_KEY select PREEMPT_BUILD - default y + default y if HAVE_PREEMPT_DYNAMIC_CALL help This option allows to define the preemption model on the kernel command line parameter and thus override the default preemption diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 5de18448016c..ef88cc366bb8 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -833,7 +833,7 @@ static int generate_sched_domains(cpumask_var_t **domains, update_domain_attr_tree(dattr, &top_cpuset); } cpumask_and(doms[0], top_cpuset.effective_cpus, - housekeeping_cpumask(HK_FLAG_DOMAIN)); + housekeeping_cpumask(HK_TYPE_DOMAIN)); goto done; } @@ -863,7 +863,7 @@ static int generate_sched_domains(cpumask_var_t **domains, if (!cpumask_empty(cp->cpus_allowed) && !(is_sched_load_balance(cp) && cpumask_intersects(cp->cpus_allowed, - housekeeping_cpumask(HK_FLAG_DOMAIN)))) + housekeeping_cpumask(HK_TYPE_DOMAIN)))) continue; if (root_load_balance && @@ -952,7 +952,7 @@ restart: if (apn == b->pn) { cpumask_or(dp, dp, b->effective_cpus); - cpumask_and(dp, dp, housekeeping_cpumask(HK_FLAG_DOMAIN)); + cpumask_and(dp, dp, housekeeping_cpumask(HK_TYPE_DOMAIN)); if (dattr) update_domain_attr_tree(dattr + nslot, b); diff --git a/kernel/cpu.c b/kernel/cpu.c index 238cba15449f..5797c2a7a93f 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -1489,8 +1489,8 @@ int freeze_secondary_cpus(int primary) cpu_maps_update_begin(); if (primary == -1) { primary = cpumask_first(cpu_online_mask); - if (!housekeeping_cpu(primary, HK_FLAG_TIMER)) - primary = housekeeping_any_cpu(HK_FLAG_TIMER); + if (!housekeeping_cpu(primary, HK_TYPE_TIMER)) + primary = housekeeping_any_cpu(HK_TYPE_TIMER); } else { if (!cpu_online(primary)) primary = cpumask_first(cpu_online_mask); diff --git a/kernel/entry/common.c b/kernel/entry/common.c index 0543a2c92f20..ed10a95a6b1d 100644 --- a/kernel/entry/common.c +++ b/kernel/entry/common.c @@ -3,6 +3,7 @@ #include <linux/context_tracking.h> #include <linux/entry-common.h> #include <linux/highmem.h> +#include <linux/jump_label.h> #include <linux/livepatch.h> #include <linux/audit.h> #include <linux/tick.h> @@ -394,7 +395,7 @@ noinstr irqentry_state_t irqentry_enter(struct pt_regs *regs) return ret; } -void irqentry_exit_cond_resched(void) +void raw_irqentry_exit_cond_resched(void) { if (!preempt_count()) { /* Sanity check RCU and thread stack */ @@ -406,7 +407,17 @@ void irqentry_exit_cond_resched(void) } } #ifdef CONFIG_PREEMPT_DYNAMIC -DEFINE_STATIC_CALL(irqentry_exit_cond_resched, irqentry_exit_cond_resched); +#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL) +DEFINE_STATIC_CALL(irqentry_exit_cond_resched, raw_irqentry_exit_cond_resched); +#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY) +DEFINE_STATIC_KEY_TRUE(sk_dynamic_irqentry_exit_cond_resched); +void dynamic_irqentry_exit_cond_resched(void) +{ + if (!static_key_unlikely(&sk_dynamic_irqentry_exit_cond_resched)) + return; + raw_irqentry_exit_cond_resched(); +} +#endif #endif noinstr void irqentry_exit(struct pt_regs *regs, irqentry_state_t state) @@ -434,13 +445,9 @@ noinstr void irqentry_exit(struct pt_regs *regs, irqentry_state_t state) } instrumentation_begin(); - if (IS_ENABLED(CONFIG_PREEMPTION)) { -#ifdef CONFIG_PREEMPT_DYNAMIC - static_call(irqentry_exit_cond_resched)(); -#else + if (IS_ENABLED(CONFIG_PREEMPTION)) irqentry_exit_cond_resched(); -#endif - } + /* Covers both tracing and lockdep */ trace_hardirqs_on(); instrumentation_end(); diff --git a/kernel/irq/cpuhotplug.c b/kernel/irq/cpuhotplug.c index 39a41c56ad4f..1ed2b1739363 100644 --- a/kernel/irq/cpuhotplug.c +++ b/kernel/irq/cpuhotplug.c @@ -176,10 +176,10 @@ static bool hk_should_isolate(struct irq_data *data, unsigned int cpu) { const struct cpumask *hk_mask; - if (!housekeeping_enabled(HK_FLAG_MANAGED_IRQ)) + if (!housekeeping_enabled(HK_TYPE_MANAGED_IRQ)) return false; - hk_mask = housekeeping_cpumask(HK_FLAG_MANAGED_IRQ); + hk_mask = housekeeping_cpumask(HK_TYPE_MANAGED_IRQ); if (cpumask_subset(irq_data_get_effective_affinity_mask(data), hk_mask)) return false; diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index f23ffd30385b..c03f71d5ec10 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -247,13 +247,13 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, * online. */ if (irqd_affinity_is_managed(data) && - housekeeping_enabled(HK_FLAG_MANAGED_IRQ)) { + housekeeping_enabled(HK_TYPE_MANAGED_IRQ)) { const struct cpumask *hk_mask, *prog_mask; static DEFINE_RAW_SPINLOCK(tmp_mask_lock); static struct cpumask tmp_mask; - hk_mask = housekeeping_cpumask(HK_FLAG_MANAGED_IRQ); + hk_mask = housekeeping_cpumask(HK_TYPE_MANAGED_IRQ); raw_spin_lock(&tmp_mask_lock); cpumask_and(&tmp_mask, mask, hk_mask); diff --git a/kernel/kthread.c b/kernel/kthread.c index 38c6dd822da8..d100d5a15b38 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -356,7 +356,7 @@ static int kthread(void *_create) * back to default in case they have been changed. */ sched_setscheduler_nocheck(current, SCHED_NORMAL, ¶m); - set_cpus_allowed_ptr(current, housekeeping_cpumask(HK_FLAG_KTHREAD)); + set_cpus_allowed_ptr(current, housekeeping_cpumask(HK_TYPE_KTHREAD)); /* OK, tell user we're spawned, wait for stop or wakeup */ __set_current_state(TASK_UNINTERRUPTIBLE); @@ -722,7 +722,7 @@ int kthreadd(void *unused) /* Setup a clean context for our children to inherit. */ set_task_comm(tsk, "kthreadd"); ignore_signals(tsk); - set_cpus_allowed_ptr(tsk, housekeeping_cpumask(HK_FLAG_KTHREAD)); + set_cpus_allowed_ptr(tsk, housekeeping_cpumask(HK_TYPE_KTHREAD)); set_mems_allowed(node_states[N_MEMORY]); current->flags |= PF_NOFREEZE; diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index ac17348187e4..99cf3a13954c 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -496,7 +496,7 @@ static int __noreturn rcu_tasks_kthread(void *arg) struct rcu_tasks *rtp = arg; /* Run on housekeeping CPUs by default. Sysadm can move if desired. */ - housekeeping_affine(current, HK_FLAG_RCU); + housekeeping_affine(current, HK_TYPE_RCU); WRITE_ONCE(rtp->kthread_ptr, current); // Let GPs start! /* diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 6082dd23408f..8360d86db1c0 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -1218,9 +1218,9 @@ static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu) if ((mask & leaf_node_cpu_bit(rnp, cpu)) && cpu != outgoingcpu) cpumask_set_cpu(cpu, cm); - cpumask_and(cm, cm, housekeeping_cpumask(HK_FLAG_RCU)); + cpumask_and(cm, cm, housekeeping_cpumask(HK_TYPE_RCU)); if (cpumask_empty(cm)) - cpumask_copy(cm, housekeeping_cpumask(HK_FLAG_RCU)); + cpumask_copy(cm, housekeeping_cpumask(HK_TYPE_RCU)); set_cpus_allowed_ptr(t, cm); mutex_unlock(&rnp->boost_kthread_mutex); free_cpumask_var(cm); @@ -1296,7 +1296,7 @@ static void rcu_bind_gp_kthread(void) { if (!tick_nohz_full_enabled()) return; - housekeeping_affine(current, HK_FLAG_RCU); + housekeeping_affine(current, HK_TYPE_RCU); } /* Record the current task on dyntick-idle entry. */ diff --git a/kernel/rseq.c b/kernel/rseq.c index 6d45ac3dae7f..97ac20b4f738 100644 --- a/kernel/rseq.c +++ b/kernel/rseq.c @@ -128,10 +128,10 @@ static int rseq_get_rseq_cs(struct task_struct *t, struct rseq_cs *rseq_cs) int ret; #ifdef CONFIG_64BIT - if (get_user(ptr, &t->rseq->rseq_cs.ptr64)) + if (get_user(ptr, &t->rseq->rseq_cs)) return -EFAULT; #else - if (copy_from_user(&ptr, &t->rseq->rseq_cs.ptr64, sizeof(ptr))) + if (copy_from_user(&ptr, &t->rseq->rseq_cs, sizeof(ptr))) return -EFAULT; #endif if (!ptr) { @@ -217,9 +217,9 @@ static int clear_rseq_cs(struct task_struct *t) * Set rseq_cs to NULL. */ #ifdef CONFIG_64BIT - return put_user(0UL, &t->rseq->rseq_cs.ptr64); + return put_user(0UL, &t->rseq->rseq_cs); #else - if (clear_user(&t->rseq->rseq_cs.ptr64, sizeof(t->rseq->rseq_cs.ptr64))) + if (clear_user(&t->rseq->rseq_cs, sizeof(t->rseq->rseq_cs))) return -EFAULT; return 0; #endif diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile index c83b37af155b..976092b7bd45 100644 --- a/kernel/sched/Makefile +++ b/kernel/sched/Makefile @@ -1,7 +1,4 @@ # SPDX-License-Identifier: GPL-2.0 -ifdef CONFIG_FUNCTION_TRACER -CFLAGS_REMOVE_clock.o = $(CC_FLAGS_FTRACE) -endif # The compilers are complaining about unused variables inside an if(0) scope # block. This is daft, shut them up. @@ -25,18 +22,13 @@ ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y) CFLAGS_core.o := $(PROFILING) -fno-omit-frame-pointer endif -obj-y += core.o loadavg.o clock.o cputime.o -obj-y += idle.o fair.o rt.o deadline.o -obj-y += wait.o wait_bit.o swait.o completion.o - -obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o topology.o stop_task.o pelt.o -obj-$(CONFIG_SCHED_AUTOGROUP) += autogroup.o -obj-$(CONFIG_SCHEDSTATS) += stats.o -obj-$(CONFIG_SCHED_DEBUG) += debug.o -obj-$(CONFIG_CGROUP_CPUACCT) += cpuacct.o -obj-$(CONFIG_CPU_FREQ) += cpufreq.o -obj-$(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) += cpufreq_schedutil.o -obj-$(CONFIG_MEMBARRIER) += membarrier.o -obj-$(CONFIG_CPU_ISOLATION) += isolation.o -obj-$(CONFIG_PSI) += psi.o -obj-$(CONFIG_SCHED_CORE) += core_sched.o +# +# Build efficiency: +# +# These compilation units have roughly the same size and complexity - so their +# build parallelizes well and finishes roughly at once: +# +obj-y += core.o +obj-y += fair.o +obj-y += build_policy.o +obj-y += build_utility.o diff --git a/kernel/sched/autogroup.c b/kernel/sched/autogroup.c index 8629b37d118e..16092b49ff6a 100644 --- a/kernel/sched/autogroup.c +++ b/kernel/sched/autogroup.c @@ -1,14 +1,35 @@ // SPDX-License-Identifier: GPL-2.0 + /* * Auto-group scheduling implementation: */ -#include <linux/nospec.h> -#include "sched.h" unsigned int __read_mostly sysctl_sched_autogroup_enabled = 1; static struct autogroup autogroup_default; static atomic_t autogroup_seq_nr; +#ifdef CONFIG_SYSCTL +static struct ctl_table sched_autogroup_sysctls[] = { + { + .procname = "sched_autogroup_enabled", + .data = &sysctl_sched_autogroup_enabled, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + {} +}; + +static void __init sched_autogroup_sysctl_init(void) +{ + register_sysctl_init("kernel", sched_autogroup_sysctls); +} +#else +#define sched_autogroup_sysctl_init() do { } while (0) +#endif + void __init autogroup_init(struct task_struct *init_task) { autogroup_default.tg = &root_task_group; @@ -198,6 +219,7 @@ void sched_autogroup_exit(struct signal_struct *sig) static int __init setup_autogroup(char *str) { sysctl_sched_autogroup_enabled = 0; + sched_autogroup_sysctl_init(); return 1; } diff --git a/kernel/sched/autogroup.h b/kernel/sched/autogroup.h index b96419974a1f..90d69f2c5eaf 100644 --- a/kernel/sched/autogroup.h +++ b/kernel/sched/autogroup.h @@ -1,4 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _KERNEL_SCHED_AUTOGROUP_H +#define _KERNEL_SCHED_AUTOGROUP_H + #ifdef CONFIG_SCHED_AUTOGROUP struct autogroup { @@ -27,6 +30,7 @@ extern bool task_wants_autogroup(struct task_struct *p, struct task_group *tg); static inline struct task_group * autogroup_task_group(struct task_struct *p, struct task_group *tg) { + extern unsigned int sysctl_sched_autogroup_enabled; int enabled = READ_ONCE(sysctl_sched_autogroup_enabled); if (enabled && task_wants_autogroup(p, tg)) @@ -58,3 +62,5 @@ static inline int autogroup_path(struct task_group *tg, char *buf, int buflen) } #endif /* CONFIG_SCHED_AUTOGROUP */ + +#endif /* _KERNEL_SCHED_AUTOGROUP_H */ diff --git a/kernel/sched/build_policy.c b/kernel/sched/build_policy.c new file mode 100644 index 000000000000..e0104b45029a --- /dev/null +++ b/kernel/sched/build_policy.c @@ -0,0 +1,52 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * These are the scheduling policy related scheduler files, built + * in a single compilation unit for build efficiency reasons. + * + * ( Incidentally, the size of the compilation unit is roughly + * comparable to core.c and fair.c, the other two big + * compilation units. This helps balance build time, while + * coalescing source files to amortize header inclusion + * cost. ) + * + * core.c and fair.c are built separately. + */ + +/* Headers: */ +#include <linux/sched/clock.h> +#include <linux/sched/cputime.h> +#include <linux/sched/posix-timers.h> +#include <linux/sched/rt.h> + +#include <linux/cpuidle.h> +#include <linux/jiffies.h> +#include <linux/livepatch.h> +#include <linux/psi.h> +#include <linux/seqlock_api.h> +#include <linux/slab.h> +#include <linux/suspend.h> +#include <linux/tsacct_kern.h> +#include <linux/vtime.h> + +#include <uapi/linux/sched/types.h> + +#include "sched.h" + +#include "autogroup.h" +#include "stats.h" +#include "pelt.h" + +/* Source code modules: */ + +#include "idle.c" + +#include "rt.c" + +#ifdef CONFIG_SMP +# include "cpudeadline.c" +# include "pelt.c" +#endif + +#include "cputime.c" +#include "deadline.c" + diff --git a/kernel/sched/build_utility.c b/kernel/sched/build_utility.c new file mode 100644 index 000000000000..eec0849b2aae --- /dev/null +++ b/kernel/sched/build_utility.c @@ -0,0 +1,109 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * These are various utility functions of the scheduler, + * built in a single compilation unit for build efficiency reasons. + * + * ( Incidentally, the size of the compilation unit is roughly + * comparable to core.c, fair.c, smp.c and policy.c, the other + * big compilation units. This helps balance build time, while + * coalescing source files to amortize header inclusion + * cost. ) + */ +#include <linux/sched/clock.h> +#include <linux/sched/cputime.h> +#include <linux/sched/debug.h> +#include <linux/sched/isolation.h> +#include <linux/sched/loadavg.h> +#include <linux/sched/mm.h> +#include <linux/sched/rseq_api.h> +#include <linux/sched/task_stack.h> + +#include <linux/cpufreq.h> +#include <linux/cpumask_api.h> +#include <linux/cpuset.h> +#include <linux/ctype.h> +#include <linux/debugfs.h> +#include <linux/energy_model.h> +#include <linux/hashtable_api.h> +#include <linux/irq.h> +#include <linux/kobject_api.h> +#include <linux/membarrier.h> +#include <linux/mempolicy.h> +#include <linux/nmi.h> +#include <linux/nospec.h> +#include <linux/proc_fs.h> +#include <linux/psi.h> +#include <linux/psi.h> +#include <linux/ptrace_api.h> +#include <linux/sched_clock.h> +#include <linux/security.h> +#include <linux/spinlock_api.h> +#include <linux/swait_api.h> +#include <linux/timex.h> +#include <linux/utsname.h> +#include <linux/wait_api.h> +#include <linux/workqueue_api.h> + +#include <uapi/linux/prctl.h> +#include <uapi/linux/sched/types.h> + +#include <asm/switch_to.h> + +#include "sched.h" +#include "sched-pelt.h" +#include "stats.h" +#include "autogroup.h" + +#include "clock.c" + +#ifdef CONFIG_CGROUP_CPUACCT +# include "cpuacct.c" +#endif + +#ifdef CONFIG_CPU_FREQ +# include "cpufreq.c" +#endif + +#ifdef CONFIG_CPU_FREQ_GOV_SCHEDUTIL +# include "cpufreq_schedutil.c" +#endif + +#ifdef CONFIG_SCHED_DEBUG +# include "debug.c" +#endif + +#ifdef CONFIG_SCHEDSTATS +# include "stats.c" +#endif + +#include "loadavg.c" +#include "completion.c" +#include "swait.c" +#include "wait_bit.c" +#include "wait.c" + +#ifdef CONFIG_SMP +# include "cpupri.c" +# include "stop_task.c" +# include "topology.c" +#endif + +#ifdef CONFIG_SCHED_CORE +# include "core_sched.c" +#endif + +#ifdef CONFIG_PSI +# include "psi.c" +#endif + +#ifdef CONFIG_MEMBARRIER +# include "membarrier.c" +#endif + +#ifdef CONFIG_CPU_ISOLATION +# include "isolation.c" +#endif + +#ifdef CONFIG_SCHED_AUTOGROUP +# include "autogroup.c" +#endif diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c index c2b2859ddd82..d9272d9061a3 100644 --- a/kernel/sched/clock.c +++ b/kernel/sched/clock.c @@ -53,15 +53,13 @@ * that is otherwise invisible (TSC gets stopped). * */ -#include "sched.h" -#include <linux/sched_clock.h> /* * Scheduler clock - returns current time in nanosec units. * This is default implementation. * Architectures and sub-architectures can override this. */ -unsigned long long __weak sched_clock(void) +notrace unsigned long long __weak sched_clock(void) { return (unsigned long long)(jiffies - INITIAL_JIFFIES) * (NSEC_PER_SEC / HZ); @@ -95,28 +93,28 @@ struct sched_clock_data { static DEFINE_PER_CPU_SHARED_ALIGNED(struct sched_clock_data, sched_clock_data); -static inline struct sched_clock_data *this_scd(void) +notrace static inline struct sched_clock_data *this_scd(void) { return this_cpu_ptr(&sched_clock_data); } -static inline struct sched_clock_data *cpu_sdc(int cpu) +notrace static inline struct sched_clock_data *cpu_sdc(int cpu) { return &per_cpu(sched_clock_data, cpu); } -int sched_clock_stable(void) +notrace int sched_clock_stable(void) { return static_branch_likely(&__sched_clock_stable); } -static void __scd_stamp(struct sched_clock_data *scd) +notrace static void __scd_stamp(struct sched_clock_data *scd) { scd->tick_gtod = ktime_get_ns(); scd->tick_raw = sched_clock(); } -static void __set_sched_clock_stable(void) +notrace static void __set_sched_clock_stable(void) { struct sched_clock_data *scd; @@ -151,7 +149,7 @@ static void __set_sched_clock_stable(void) * The only way to fully avoid random clock jumps is to boot with: * "tsc=unstable". */ -static void __sched_clock_work(struct work_struct *work) +notrace static void __sched_clock_work(struct work_struct *work) { struct sched_clock_data *scd; int cpu; @@ -177,7 +175,7 @@ static void __sched_clock_work(struct work_struct *work) static DECLARE_WORK(sched_clock_work, __sched_clock_work); -static void __clear_sched_clock_stable(void) +notrace static void __clear_sched_clock_stable(void) { if (!sched_clock_stable()) return; @@ -186,7 +184,7 @@ static void __clear_sched_clock_stable(void) schedule_work(&sched_clock_work); } -void clear_sched_clock_stable(void) +notrace void clear_sched_clock_stable(void) { __sched_clock_stable_early = 0; @@ -196,7 +194,7 @@ void clear_sched_clock_stable(void) __clear_sched_clock_stable(); } -static void __sched_clock_gtod_offset(void) +notrace static void __sched_clock_gtod_offset(void) { struct sched_clock_data *scd = this_scd(); @@ -246,12 +244,12 @@ late_initcall(sched_clock_init_late); * min, max except they take wrapping into account */ -static inline u64 wrap_min(u64 x, u64 y) +notrace static inline u64 wrap_min(u64 x, u64 y) { return (s64)(x - y) < 0 ? x : y; } -static inline u64 wrap_max(u64 x, u64 y) +notrace static inline u64 wrap_max(u64 x, u64 y) { return (s64)(x - y) > 0 ? x : y; } @@ -262,7 +260,7 @@ static inline u64 wrap_max(u64 x, u64 y) * - filter out backward motion * - use the GTOD tick value to create a window to filter crazy TSC values */ -static u64 sched_clock_local(struct sched_clock_data *scd) +notrace static u64 sched_clock_local(struct sched_clock_data *scd) { u64 now, clock, old_clock, min_clock, max_clock, gtod; s64 delta; @@ -295,7 +293,7 @@ again: return clock; } -static u64 sched_clock_remote(struct sched_clock_data *scd) +notrace static u64 sched_clock_remote(struct sched_clock_data *scd) { struct sched_clock_data *my_scd = this_scd(); u64 this_clock, remote_clock; @@ -362,7 +360,7 @@ again: * * See cpu_clock(). */ -u64 sched_clock_cpu(int cpu) +notrace u64 sched_clock_cpu(int cpu) { struct sched_clock_data *scd; u64 clock; @@ -386,7 +384,7 @@ u64 sched_clock_cpu(int cpu) } EXPORT_SYMBOL_GPL(sched_clock_cpu); -void sched_clock_tick(void) +notrace void sched_clock_tick(void) { struct sched_clock_data *scd; @@ -403,7 +401,7 @@ void sched_clock_tick(void) sched_clock_local(scd); } -void sched_clock_tick_stable(void) +notrace void sched_clock_tick_stable(void) { if (!sched_clock_stable()) return; @@ -423,7 +421,7 @@ void sched_clock_tick_stable(void) /* * We are going deep-idle (irqs are disabled): */ -void sched_clock_idle_sleep_event(void) +notrace void sched_clock_idle_sleep_event(void) { sched_clock_cpu(smp_processor_id()); } @@ -432,7 +430,7 @@ EXPORT_SYMBOL_GPL(sched_clock_idle_sleep_event); /* * We just idled; resync with ktime. */ -void sched_clock_idle_wakeup_event(void) +notrace void sched_clock_idle_wakeup_event(void) { unsigned long flags; @@ -458,7 +456,7 @@ void __init sched_clock_init(void) local_irq_enable(); } -u64 sched_clock_cpu(int cpu) +notrace u64 sched_clock_cpu(int cpu) { if (!static_branch_likely(&sched_clock_running)) return 0; @@ -476,7 +474,7 @@ u64 sched_clock_cpu(int cpu) * On bare metal this function should return the same as local_clock. * Architectures and sub-architectures can override this. */ -u64 __weak running_clock(void) +notrace u64 __weak running_clock(void) { return local_clock(); } diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c index a778554f9dad..35f15c26ed54 100644 --- a/kernel/sched/completion.c +++ b/kernel/sched/completion.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 + /* * Generic wait-for-completion handler; * @@ -11,7 +12,6 @@ * typically be used for exclusion which gives rise to priority inversion. * Waiting for completion is a typically sync point, but not an exclusion point. */ -#include "sched.h" /** * complete: - signals a single thread waiting on this completion diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 6c56ee848e2a..6dc68465116b 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -6,26 +6,90 @@ * * Copyright (C) 1991-2002 Linus Torvalds */ -#define CREATE_TRACE_POINTS -#include <trace/events/sched.h> -#undef CREATE_TRACE_POINTS - -#include "sched.h" +#include <linux/highmem.h> +#include <linux/hrtimer_api.h> +#include <linux/ktime_api.h> +#include <linux/sched/signal.h> +#include <linux/syscalls_api.h> +#include <linux/debug_locks.h> +#include <linux/prefetch.h> +#include <linux/capability.h> +#include <linux/pgtable_api.h> +#include <linux/wait_bit.h> +#include <linux/jiffies.h> +#include <linux/spinlock_api.h> +#include <linux/cpumask_api.h> +#include <linux/lockdep_api.h> +#include <linux/hardirq.h> +#include <linux/softirq.h> +#include <linux/refcount_api.h> +#include <linux/topology.h> +#include <linux/sched/clock.h> +#include <linux/sched/cond_resched.h> +#include <linux/sched/debug.h> +#include <linux/sched/isolation.h> +#include <linux/sched/loadavg.h> +#include <linux/sched/mm.h> +#include <linux/sched/nohz.h> +#include <linux/sched/rseq_api.h> +#include <linux/sched/rt.h> -#include <linux/nospec.h> #include <linux/blkdev.h> +#include <linux/context_tracking.h> +#include <linux/cpuset.h> +#include <linux/delayacct.h> +#include <linux/init_task.h> +#include <linux/interrupt.h> +#include <linux/ioprio.h> +#include <linux/kallsyms.h> #include <linux/kcov.h> +#include <linux/kprobes.h> +#include <linux/llist_api.h> +#include <linux/mmu_context.h> +#include <linux/mmzone.h> +#include <linux/mutex_api.h> +#include <linux/nmi.h> +#include <linux/nospec.h> +#include <linux/perf_event_api.h> +#include <linux/profile.h> +#include <linux/psi.h> +#include <linux/rcuwait_api.h> +#include <linux/sched/wake_q.h> #include <linux/scs.h> +#include <linux/slab.h> +#include <linux/syscalls.h> +#include <linux/vtime.h> +#include <linux/wait_api.h> +#include <linux/workqueue_api.h> + +#ifdef CONFIG_PREEMPT_DYNAMIC +# ifdef CONFIG_GENERIC_ENTRY +# include <linux/entry-common.h> +# endif +#endif + +#include <uapi/linux/sched/types.h> #include <asm/switch_to.h> #include <asm/tlb.h> -#include "../workqueue_internal.h" -#include "../../fs/io-wq.h" -#include "../smpboot.h" +#define CREATE_TRACE_POINTS +#include <linux/sched/rseq_api.h> +#include <trace/events/sched.h> +#undef CREATE_TRACE_POINTS + +#include "sched.h" +#include "stats.h" +#include "autogroup.h" +#include "autogroup.h" #include "pelt.h" #include "smp.h" +#include "stats.h" + +#include "../workqueue_internal.h" +#include "../../fs/io-wq.h" +#include "../smpboot.h" /* * Export tracepoints that act as a bare tracehook (ie: have no trace event @@ -36,6 +100,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_rt_tp); EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_dl_tp); EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_irq_tp); EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_se_tp); +EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_thermal_tp); EXPORT_TRACEPOINT_SYMBOL_GPL(sched_cpu_capacity_tp); EXPORT_TRACEPOINT_SYMBOL_GPL(sched_overutilized_tp); EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_cfs_tp); @@ -1024,13 +1089,13 @@ int get_nohz_timer_target(void) struct sched_domain *sd; const struct cpumask *hk_mask; - if (housekeeping_cpu(cpu, HK_FLAG_TIMER)) { + if (housekeeping_cpu(cpu, HK_TYPE_TIMER)) { if (!idle_cpu(cpu)) return cpu; default_cpu = cpu; } - hk_mask = housekeeping_cpumask(HK_FLAG_TIMER); + hk_mask = housekeeping_cpumask(HK_TYPE_TIMER); rcu_read_lock(); for_each_domain(cpu, sd) { @@ -1046,7 +1111,7 @@ int get_nohz_timer_target(void) } if (default_cpu == -1) - default_cpu = housekeeping_any_cpu(HK_FLAG_TIMER); + default_cpu = housekeeping_any_cpu(HK_TYPE_TIMER); cpu = default_cpu; unlock: rcu_read_unlock(); @@ -4834,7 +4899,7 @@ static struct rq *finish_task_switch(struct task_struct *prev) { struct rq *rq = this_rq(); struct mm_struct *mm = rq->prev_mm; - long prev_state; + unsigned int prev_state; /* * The previous task will have left us with a preempt_count of 2 @@ -5379,7 +5444,7 @@ static void sched_tick_start(int cpu) int os; struct tick_work *twork; - if (housekeeping_cpu(cpu, HK_FLAG_TICK)) + if (housekeeping_cpu(cpu, HK_TYPE_TICK)) return; WARN_ON_ONCE(!tick_work_cpu); @@ -5400,7 +5465,7 @@ static void sched_tick_stop(int cpu) struct tick_work *twork; int os; - if (housekeeping_cpu(cpu, HK_FLAG_TICK)) + if (housekeeping_cpu(cpu, HK_TYPE_TICK)) return; WARN_ON_ONCE(!tick_work_cpu); @@ -6298,7 +6363,7 @@ static void __sched notrace __schedule(unsigned int sched_mode) migrate_disable_switch(rq, prev); psi_sched_switch(prev, next, !task_on_rq_queued(prev)); - trace_sched_switch(sched_mode & SM_MASK_PREEMPT, prev, next); + trace_sched_switch(sched_mode & SM_MASK_PREEMPT, prev_state, prev, next); /* Also unlocks the rq: */ rq = context_switch(rq, prev, next, &rf); @@ -6490,17 +6555,31 @@ asmlinkage __visible void __sched notrace preempt_schedule(void) */ if (likely(!preemptible())) return; - preempt_schedule_common(); } NOKPROBE_SYMBOL(preempt_schedule); EXPORT_SYMBOL(preempt_schedule); #ifdef CONFIG_PREEMPT_DYNAMIC -DEFINE_STATIC_CALL(preempt_schedule, __preempt_schedule_func); +#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL) +#ifndef preempt_schedule_dynamic_enabled +#define preempt_schedule_dynamic_enabled preempt_schedule +#define preempt_schedule_dynamic_disabled NULL +#endif +DEFINE_STATIC_CALL(preempt_schedule, preempt_schedule_dynamic_enabled); EXPORT_STATIC_CALL_TRAMP(preempt_schedule); +#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY) +static DEFINE_STATIC_KEY_TRUE(sk_dynamic_preempt_schedule); +void __sched notrace dynamic_preempt_schedule(void) +{ + if (!static_branch_unlikely(&sk_dynamic_preempt_schedule)) + return; + preempt_schedule(); +} +NOKPROBE_SYMBOL(dynamic_preempt_schedule); +EXPORT_SYMBOL(dynamic_preempt_schedule); +#endif #endif - /** * preempt_schedule_notrace - preempt_schedule called by tracing @@ -6555,147 +6634,27 @@ asmlinkage __visible void __sched notrace preempt_schedule_notrace(void) EXPORT_SYMBOL_GPL(preempt_schedule_notrace); #ifdef CONFIG_PREEMPT_DYNAMIC -DEFINE_STATIC_CALL(preempt_schedule_notrace, __preempt_schedule_notrace_func); -EXPORT_STATIC_CALL_TRAMP(preempt_schedule_notrace); +#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL) +#ifndef preempt_schedule_notrace_dynamic_enabled +#define preempt_schedule_notrace_dynamic_enabled preempt_schedule_notrace +#define preempt_schedule_notrace_dynamic_disabled NULL #endif - -#endif /* CONFIG_PREEMPTION */ - -#ifdef CONFIG_PREEMPT_DYNAMIC - -#include <linux/entry-common.h> - -/* - * SC:cond_resched - * SC:might_resched - * SC:preempt_schedule - * SC:preempt_schedule_notrace - * SC:irqentry_exit_cond_resched - * - * - * NONE: - * cond_resched <- __cond_resched - * might_resched <- RET0 - * preempt_schedule <- NOP - * preempt_schedule_notrace <- NOP - * irqentry_exit_cond_resched <- NOP - * - * VOLUNTARY: - * cond_resched <- __cond_resched - * might_resched <- __cond_resched - * preempt_schedule <- NOP - * preempt_schedule_notrace <- NOP - * irqentry_exit_cond_resched <- NOP - * - * FULL: - * cond_resched <- RET0 - * might_resched <- RET0 - * preempt_schedule <- preempt_schedule - * preempt_schedule_notrace <- preempt_schedule_notrace - * irqentry_exit_cond_resched <- irqentry_exit_cond_resched - */ - -enum { - preempt_dynamic_undefined = -1, - preempt_dynamic_none, - preempt_dynamic_voluntary, - preempt_dynamic_full, -}; - -int preempt_dynamic_mode = preempt_dynamic_undefined; - -int sched_dynamic_mode(const char *str) -{ - if (!strcmp(str, "none")) - return preempt_dynamic_none; - - if (!strcmp(str, "voluntary")) - return preempt_dynamic_voluntary; - - if (!strcmp(str, "full")) - return preempt_dynamic_full; - - return -EINVAL; -} - -void sched_dynamic_update(int mode) -{ - /* - * Avoid {NONE,VOLUNTARY} -> FULL transitions from ever ending up in - * the ZERO state, which is invalid. - */ - static_call_update(cond_resched, __cond_resched); - static_call_update(might_resched, __cond_resched); - static_call_update(preempt_schedule, __preempt_schedule_func); - static_call_update(preempt_schedule_notrace, __preempt_schedule_notrace_func); - static_call_update(irqentry_exit_cond_resched, irqentry_exit_cond_resched); - - switch (mode) { - case preempt_dynamic_none: - static_call_update(cond_resched, __cond_resched); - static_call_update(might_resched, (void *)&__static_call_return0); - static_call_update(preempt_schedule, NULL); - static_call_update(preempt_schedule_notrace, NULL); - static_call_update(irqentry_exit_cond_resched, NULL); - pr_info("Dynamic Preempt: none\n"); - break; - - case preempt_dynamic_voluntary: - static_call_update(cond_resched, __cond_resched); - static_call_update(might_resched, __cond_resched); - static_call_update(preempt_schedule, NULL); - static_call_update(preempt_schedule_notrace, NULL); - static_call_update(irqentry_exit_cond_resched, NULL); - pr_info("Dynamic Preempt: voluntary\n"); - break; - - case preempt_dynamic_full: - static_call_update(cond_resched, (void *)&__static_call_return0); - static_call_update(might_resched, (void *)&__static_call_return0); - static_call_update(preempt_schedule, __preempt_schedule_func); - static_call_update(preempt_schedule_notrace, __preempt_schedule_notrace_func); - static_call_update(irqentry_exit_cond_resched, irqentry_exit_cond_resched); - pr_info("Dynamic Preempt: full\n"); - break; - } - - preempt_dynamic_mode = mode; -} - -static int __init setup_preempt_mode(char *str) -{ - int mode = sched_dynamic_mode(str); - if (mode < 0) { - pr_warn("Dynamic Preempt: unsupported mode: %s\n", str); - return 0; - } - - sched_dynamic_update(mode); - return 1; -} -__setup("preempt=", setup_preempt_mode); - -static void __init preempt_dynamic_init(void) +DEFINE_STATIC_CALL(preempt_schedule_notrace, preempt_schedule_notrace_dynamic_enabled); +EXPORT_STATIC_CALL_TRAMP(preempt_schedule_notrace); +#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY) +static DEFINE_STATIC_KEY_TRUE(sk_dynamic_preempt_schedule_notrace); +void __sched notrace dynamic_preempt_schedule_notrace(void) { - if (preempt_dynamic_mode == preempt_dynamic_undefined) { - if (IS_ENABLED(CONFIG_PREEMPT_NONE)) { - sched_dynamic_update(preempt_dynamic_none); - } else if (IS_ENABLED(CONFIG_PREEMPT_VOLUNTARY)) { - sched_dynamic_update(preempt_dynamic_voluntary); - } else { - /* Default static call setting, nothing to do */ - WARN_ON_ONCE(!IS_ENABLED(CONFIG_PREEMPT)); - preempt_dynamic_mode = preempt_dynamic_full; - pr_info("Dynamic Preempt: full\n"); - } - } + if (!static_branch_unlikely(&sk_dynamic_preempt_schedule_notrace)) + return; + preempt_schedule_notrace(); } +NOKPROBE_SYMBOL(dynamic_preempt_schedule_notrace); +EXPORT_SYMBOL(dynamic_preempt_schedule_notrace); +#endif +#endif -#else /* !CONFIG_PREEMPT_DYNAMIC */ - -static inline void preempt_dynamic_init(void) { } - -#endif /* #ifdef CONFIG_PREEMPT_DYNAMIC */ +#endif /* CONFIG_PREEMPTION */ /* * This is the entry point to schedule() from kernel preemption @@ -8202,11 +8161,35 @@ EXPORT_SYMBOL(__cond_resched); #endif #ifdef CONFIG_PREEMPT_DYNAMIC +#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL) +#define cond_resched_dynamic_enabled __cond_resched +#define cond_resched_dynamic_disabled ((void *)&__static_call_return0) DEFINE_STATIC_CALL_RET0(cond_resched, __cond_resched); EXPORT_STATIC_CALL_TRAMP(cond_resched); +#define might_resched_dynamic_enabled __cond_resched +#define might_resched_dynamic_disabled ((void *)&__static_call_return0) DEFINE_STATIC_CALL_RET0(might_resched, __cond_resched); EXPORT_STATIC_CALL_TRAMP(might_resched); +#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY) +static DEFINE_STATIC_KEY_FALSE(sk_dynamic_cond_resched); +int __sched dynamic_cond_resched(void) +{ + if (!static_branch_unlikely(&sk_dynamic_cond_resched)) + return 0; + return __cond_resched(); +} +EXPORT_SYMBOL(dynamic_cond_resched); + +static DEFINE_STATIC_KEY_FALSE(sk_dynamic_might_resched); +int __sched dynamic_might_resched(void) +{ + if (!static_branch_unlikely(&sk_dynamic_might_resched)) + return 0; + return __cond_resched(); +} +EXPORT_SYMBOL(dynamic_might_resched); +#endif #endif /* @@ -8271,6 +8254,154 @@ int __cond_resched_rwlock_write(rwlock_t *lock) } EXPORT_SYMBOL(__cond_resched_rwlock_write); +#ifdef CONFIG_PREEMPT_DYNAMIC + +#ifdef CONFIG_GENERIC_ENTRY +#include <linux/entry-common.h> +#endif + +/* + * SC:cond_resched + * SC:might_resched + * SC:preempt_schedule + * SC:preempt_schedule_notrace + * SC:irqentry_exit_cond_resched + * + * + * NONE: + * cond_resched <- __cond_resched + * might_resched <- RET0 + * preempt_schedule <- NOP + * preempt_schedule_notrace <- NOP + * irqentry_exit_cond_resched <- NOP + * + * VOLUNTARY: + * cond_resched <- __cond_resched + * might_resched <- __cond_resched + * preempt_schedule <- NOP + * preempt_schedule_notrace <- NOP + * irqentry_exit_cond_resched <- NOP + * + * FULL: + * cond_resched <- RET0 + * might_resched <- RET0 + * preempt_schedule <- preempt_schedule + * preempt_schedule_notrace <- preempt_schedule_notrace + * irqentry_exit_cond_resched <- irqentry_exit_cond_resched + */ + +enum { + preempt_dynamic_undefined = -1, + preempt_dynamic_none, + preempt_dynamic_voluntary, + preempt_dynamic_full, +}; + +int preempt_dynamic_mode = preempt_dynamic_undefined; + +int sched_dynamic_mode(const char *str) +{ + if (!strcmp(str, "none")) + return preempt_dynamic_none; + + if (!strcmp(str, "voluntary")) + return preempt_dynamic_voluntary; + + if (!strcmp(str, "full")) + return preempt_dynamic_full; + + return -EINVAL; +} + +#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL) +#define preempt_dynamic_enable(f) static_call_update(f, f##_dynamic_enabled) +#define preempt_dynamic_disable(f) static_call_update(f, f##_dynamic_disabled) +#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY) +#define preempt_dynamic_enable(f) static_key_enable(&sk_dynamic_##f.key) +#define preempt_dynamic_disable(f) static_key_disable(&sk_dynamic_##f.key) +#else +#error "Unsupported PREEMPT_DYNAMIC mechanism" +#endif + +void sched_dynamic_update(int mode) +{ + /* + * Avoid {NONE,VOLUNTARY} -> FULL transitions from ever ending up in + * the ZERO state, which is invalid. + */ + preempt_dynamic_enable(cond_resched); + preempt_dynamic_enable(might_resched); + preempt_dynamic_enable(preempt_schedule); + preempt_dynamic_enable(preempt_schedule_notrace); + preempt_dynamic_enable(irqentry_exit_cond_resched); + + switch (mode) { + case preempt_dynamic_none: + preempt_dynamic_enable(cond_resched); + preempt_dynamic_disable(might_resched); + preempt_dynamic_disable(preempt_schedule); + preempt_dynamic_disable(preempt_schedule_notrace); + preempt_dynamic_disable(irqentry_exit_cond_resched); + pr_info("Dynamic Preempt: none\n"); + break; + + case preempt_dynamic_voluntary: + preempt_dynamic_enable(cond_resched); + preempt_dynamic_enable(might_resched); + preempt_dynamic_disable(preempt_schedule); + preempt_dynamic_disable(preempt_schedule_notrace); + preempt_dynamic_disable(irqentry_exit_cond_resched); + pr_info("Dynamic Preempt: voluntary\n"); + break; + + case preempt_dynamic_full: + preempt_dynamic_disable(cond_resched); + preempt_dynamic_disable(might_resched); + preempt_dynamic_enable(preempt_schedule); + preempt_dynamic_enable(preempt_schedule_notrace); + preempt_dynamic_enable(irqentry_exit_cond_resched); + pr_info("Dynamic Preempt: full\n"); + break; + } + + preempt_dynamic_mode = mode; +} + +static int __init setup_preempt_mode(char *str) +{ + int mode = sched_dynamic_mode(str); + if (mode < 0) { + pr_warn("Dynamic Preempt: unsupported mode: %s\n", str); + return 0; + } + + sched_dynamic_update(mode); + return 1; +} +__setup("preempt=", setup_preempt_mode); + +static void __init preempt_dynamic_init(void) +{ + if (preempt_dynamic_mode == preempt_dynamic_undefined) { + if (IS_ENABLED(CONFIG_PREEMPT_NONE)) { + sched_dynamic_update(preempt_dynamic_none); + } else if (IS_ENABLED(CONFIG_PREEMPT_VOLUNTARY)) { + sched_dynamic_update(preempt_dynamic_voluntary); + } else { + /* Default static call setting, nothing to do */ + WARN_ON_ONCE(!IS_ENABLED(CONFIG_PREEMPT)); + preempt_dynamic_mode = preempt_dynamic_full; + pr_info("Dynamic Preempt: full\n"); + } + } +} + +#else /* !CONFIG_PREEMPT_DYNAMIC */ + +static inline void preempt_dynamic_init(void) { } + +#endif /* #ifdef CONFIG_PREEMPT_DYNAMIC */ + /** * yield - yield the current processor to other threads. * @@ -8706,7 +8837,7 @@ int cpuset_cpumask_can_shrink(const struct cpumask *cur, { int ret = 1; - if (!cpumask_weight(cur)) + if (cpumask_empty(cur)) return ret; ret = dl_cpuset_cpumask_can_shrink(cur, trial); @@ -8734,8 +8865,11 @@ int task_can_attach(struct task_struct *p, } if (dl_task(p) && !cpumask_intersects(task_rq(p)->rd->span, - cs_cpus_allowed)) - ret = dl_task_can_attach(p, cs_cpus_allowed); + cs_cpus_allowed)) { + int cpu = cpumask_any_and(cpu_active_mask, cs_cpus_allowed); + + ret = dl_cpu_busy(cpu, p); + } out: return ret; @@ -9019,8 +9153,10 @@ static void cpuset_cpu_active(void) static int cpuset_cpu_inactive(unsigned int cpu) { if (!cpuhp_tasks_frozen) { - if (dl_cpu_busy(cpu)) - return -EBUSY; + int ret = dl_cpu_busy(cpu, NULL); + + if (ret) + return ret; cpuset_update_active_cpus(); } else { num_cpus_frozen++; @@ -9050,6 +9186,7 @@ int sched_cpu_activate(unsigned int cpu) set_cpu_active(cpu, true); if (sched_smp_initialized) { + sched_update_numa(cpu, true); sched_domains_numa_masks_set(cpu); cpuset_cpu_active(); } @@ -9128,10 +9265,12 @@ int sched_cpu_deactivate(unsigned int cpu) if (!sched_smp_initialized) return 0; + sched_update_numa(cpu, false); ret = cpuset_cpu_inactive(cpu); if (ret) { balance_push_set(cpu, false); set_cpu_active(cpu, true); + sched_update_numa(cpu, true); return ret; } sched_domains_numa_masks_clear(cpu); @@ -9234,7 +9373,7 @@ int sched_cpu_dying(unsigned int cpu) void __init sched_init_smp(void) { - sched_init_numa(); + sched_init_numa(NUMA_NO_NODE); /* * There's no userspace yet to cause hotplug operations; hence all the @@ -9246,7 +9385,7 @@ void __init sched_init_smp(void) mutex_unlock(&sched_domains_mutex); /* Move init over to a non-isolated CPU */ - if (set_cpus_allowed_ptr(current, housekeeping_cpumask(HK_FLAG_DOMAIN)) < 0) + if (set_cpus_allowed_ptr(current, housekeeping_cpumask(HK_TYPE_DOMAIN)) < 0) BUG(); current->flags &= ~PF_NO_SETAFFINITY; sched_init_granularity(); @@ -9346,7 +9485,6 @@ void __init sched_init(void) #endif /* CONFIG_CPUMASK_OFFSTACK */ init_rt_bandwidth(&def_rt_bandwidth, global_rt_period(), global_rt_runtime()); - init_dl_bandwidth(&def_dl_bandwidth, global_rt_period(), global_rt_runtime()); #ifdef CONFIG_SMP init_defrootdomain(); diff --git a/kernel/sched/core_sched.c b/kernel/sched/core_sched.c index c8746a9a7ada..38a2cec21014 100644 --- a/kernel/sched/core_sched.c +++ b/kernel/sched/core_sched.c @@ -1,8 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only -#include <linux/prctl.h> -#include "sched.h" - /* * A simple wrapper around refcount. An allocated sched_core_cookie's * address is used to compute the cookie of the task. diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c index 3d06c5e4220d..0de9dda09949 100644 --- a/kernel/sched/cpuacct.c +++ b/kernel/sched/cpuacct.c @@ -1,12 +1,11 @@ // SPDX-License-Identifier: GPL-2.0 + /* * CPU accounting code for task groups. * * Based on the work by Paul Menage (menage@google.com) and Balbir Singh * (balbir@in.ibm.com). */ -#include <asm/irq_regs.h> -#include "sched.h" /* Time spent by the tasks of the CPU accounting group executing in ... */ enum cpuacct_stat_index { @@ -334,14 +333,13 @@ static struct cftype files[] = { */ void cpuacct_charge(struct task_struct *tsk, u64 cputime) { + unsigned int cpu = task_cpu(tsk); struct cpuacct *ca; - rcu_read_lock(); + lockdep_assert_rq_held(cpu_rq(cpu)); for (ca = task_ca(tsk); ca; ca = parent_ca(ca)) - __this_cpu_add(*ca->cpuusage, cputime); - - rcu_read_unlock(); + *per_cpu_ptr(ca->cpuusage, cpu) += cputime; } /* @@ -353,10 +351,8 @@ void cpuacct_account_field(struct task_struct *tsk, int index, u64 val) { struct cpuacct *ca; - rcu_read_lock(); for (ca = task_ca(tsk); ca != &root_cpuacct; ca = parent_ca(ca)) __this_cpu_add(ca->cpustat->cpustat[index], val); - rcu_read_unlock(); } struct cgroup_subsys cpuacct_cgrp_subsys = { diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c index ceb03d76c0cc..02d970a879ed 100644 --- a/kernel/sched/cpudeadline.c +++ b/kernel/sched/cpudeadline.c @@ -1,12 +1,11 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * kernel/sched/cpudl.c + * kernel/sched/cpudeadline.c * * Global CPU deadline management * * Author: Juri Lelli <j.lelli@sssup.it> */ -#include "sched.h" static inline int parent(int i) { diff --git a/kernel/sched/cpufreq.c b/kernel/sched/cpufreq.c index 7c2fe50fd76d..5252fb191fae 100644 --- a/kernel/sched/cpufreq.c +++ b/kernel/sched/cpufreq.c @@ -5,9 +5,6 @@ * Copyright (C) 2016, Intel Corporation * Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com> */ -#include <linux/cpufreq.h> - -#include "sched.h" DEFINE_PER_CPU(struct update_util_data __rcu *, cpufreq_update_util_data); diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index cffcd08f4ec8..3dbf351d12d5 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -6,13 +6,6 @@ * Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com> */ -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include "sched.h" - -#include <linux/sched/cpufreq.h> -#include <trace/events/power.h> - #define IOWAIT_BOOST_MIN (SCHED_CAPACITY_SCALE / 8) struct sugov_tunables { @@ -289,6 +282,7 @@ static void sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time) * into the same scale so we can compare. */ boost = (sg_cpu->iowait_boost * sg_cpu->max) >> SCHED_CAPACITY_SHIFT; + boost = uclamp_rq_util_with(cpu_rq(sg_cpu->cpu), boost, NULL); if (sg_cpu->util < boost) sg_cpu->util = boost; } @@ -348,8 +342,11 @@ static void sugov_update_single_freq(struct update_util_data *hook, u64 time, /* * Do not reduce the frequency if the CPU has not been idle * recently, as the reduction is likely to be premature then. + * + * Except when the rq is capped by uclamp_max. */ - if (sugov_cpu_is_busy(sg_cpu) && next_f < sg_policy->next_freq) { + if (!uclamp_rq_is_capped(cpu_rq(sg_cpu->cpu)) && + sugov_cpu_is_busy(sg_cpu) && next_f < sg_policy->next_freq) { next_f = sg_policy->next_freq; /* Restore cached freq as next_freq has changed */ @@ -395,8 +392,11 @@ static void sugov_update_single_perf(struct update_util_data *hook, u64 time, /* * Do not reduce the target performance level if the CPU has not been * idle recently, as the reduction is likely to be premature then. + * + * Except when the rq is capped by uclamp_max. */ - if (sugov_cpu_is_busy(sg_cpu) && sg_cpu->util < prev_util) + if (!uclamp_rq_is_capped(cpu_rq(sg_cpu->cpu)) && + sugov_cpu_is_busy(sg_cpu) && sg_cpu->util < prev_util) sg_cpu->util = prev_util; cpufreq_driver_adjust_perf(sg_cpu->cpu, map_util_perf(sg_cpu->bw_dl), diff --git a/kernel/sched/cpupri.c b/kernel/sched/cpupri.c index d583f2aa744e..fa9ce9d83683 100644 --- a/kernel/sched/cpupri.c +++ b/kernel/sched/cpupri.c @@ -22,7 +22,6 @@ * worst case complexity of O(min(101, nr_domcpus)), though the scenario that * yields the worst case search is fairly contrived. */ -#include "sched.h" /* * p->rt_priority p->prio newpri cpupri diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index b7ec42732b28..78a233d43757 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -2,7 +2,6 @@ /* * Simple CPU accounting cgroup controller */ -#include "sched.h" #ifdef CONFIG_IRQ_TIME_ACCOUNTING diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index d2c072b0ef01..fb4255ae0b2c 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -15,10 +15,6 @@ * Michael Trimarchi <michael@amarulasolutions.com>, * Fabio Checconi <fchecconi@gmail.com> */ -#include "sched.h" -#include "pelt.h" - -struct dl_bandwidth def_dl_bandwidth; static inline struct task_struct *dl_task_of(struct sched_dl_entity *dl_se) { @@ -130,6 +126,21 @@ static inline bool dl_bw_visited(int cpu, u64 gen) rd->visit_gen = gen; return false; } + +static inline +void __dl_update(struct dl_bw *dl_b, s64 bw) +{ + struct root_domain *rd = container_of(dl_b, struct root_domain, dl_bw); + int i; + + RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(), + "sched RCU must be held"); + for_each_cpu_and(i, rd->span, cpu_active_mask) { + struct rq *rq = cpu_rq(i); + + rq->dl.extra_bw += bw; + } +} #else static inline struct dl_bw *dl_bw_of(int i) { @@ -150,9 +161,38 @@ static inline bool dl_bw_visited(int cpu, u64 gen) { return false; } + +static inline +void __dl_update(struct dl_bw *dl_b, s64 bw) +{ + struct dl_rq *dl = container_of(dl_b, struct dl_rq, dl_bw); + + dl->extra_bw += bw; +} #endif static inline +void __dl_sub(struct dl_bw *dl_b, u64 tsk_bw, int cpus) +{ + dl_b->total_bw -= tsk_bw; + __dl_update(dl_b, (s32)tsk_bw / cpus); +} + +static inline +void __dl_add(struct dl_bw *dl_b, u64 tsk_bw, int cpus) +{ + dl_b->total_bw += tsk_bw; + __dl_update(dl_b, -((s32)tsk_bw / cpus)); +} + +static inline bool +__dl_overflow(struct dl_bw *dl_b, unsigned long cap, u64 old_bw, u64 new_bw) +{ + return dl_b->bw != -1 && + cap_scale(dl_b->bw, cap) < dl_b->total_bw - old_bw + new_bw; +} + +static inline void __add_running_bw(u64 dl_bw, struct dl_rq *dl_rq) { u64 old = dl_rq->running_bw; @@ -408,7 +448,7 @@ static inline int is_leftmost(struct task_struct *p, struct dl_rq *dl_rq) { struct sched_dl_entity *dl_se = &p->dl; - return dl_rq->root.rb_leftmost == &dl_se->rb_node; + return rb_first_cached(&dl_rq->root) == &dl_se->rb_node; } static void init_dl_rq_bw_ratio(struct dl_rq *dl_rq); @@ -423,12 +463,10 @@ void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime) void init_dl_bw(struct dl_bw *dl_b) { raw_spin_lock_init(&dl_b->lock); - raw_spin_lock(&def_dl_bandwidth.dl_runtime_lock); if (global_rt_runtime() == RUNTIME_INF) dl_b->bw = -1; else dl_b->bw = to_ratio(global_rt_period(), global_rt_runtime()); - raw_spin_unlock(&def_dl_bandwidth.dl_runtime_lock); dl_b->total_bw = 0; } @@ -683,15 +721,6 @@ void dec_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq) { } -static inline bool need_pull_dl_task(struct rq *rq, struct task_struct *prev) -{ - return false; -} - -static inline void pull_dl_task(struct rq *rq) -{ -} - static inline void deadline_queue_push_tasks(struct rq *rq) { } @@ -1393,6 +1422,9 @@ void init_dl_inactive_task_timer(struct sched_dl_entity *dl_se) timer->function = inactive_task_timer; } +#define __node_2_dle(node) \ + rb_entry((node), struct sched_dl_entity, rb_node) + #ifdef CONFIG_SMP static void inc_dl_deadline(struct dl_rq *dl_rq, u64 deadline) @@ -1422,10 +1454,9 @@ static void dec_dl_deadline(struct dl_rq *dl_rq, u64 deadline) cpudl_clear(&rq->rd->cpudl, rq->cpu); cpupri_set(&rq->rd->cpupri, rq->cpu, rq->rt.highest_prio.curr); } else { - struct rb_node *leftmost = dl_rq->root.rb_leftmost; - struct sched_dl_entity *entry; + struct rb_node *leftmost = rb_first_cached(&dl_rq->root); + struct sched_dl_entity *entry = __node_2_dle(leftmost); - entry = rb_entry(leftmost, struct sched_dl_entity, rb_node); dl_rq->earliest_dl.curr = entry->deadline; cpudl_set(&rq->rd->cpudl, rq->cpu, entry->deadline); } @@ -1466,9 +1497,6 @@ void dec_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq) dec_dl_migration(dl_se, dl_rq); } -#define __node_2_dle(node) \ - rb_entry((node), struct sched_dl_entity, rb_node) - static inline bool __dl_less(struct rb_node *a, const struct rb_node *b) { return dl_time_before(__node_2_dle(a)->deadline, __node_2_dle(b)->deadline); @@ -1931,15 +1959,14 @@ static void set_next_task_dl(struct rq *rq, struct task_struct *p, bool first) deadline_queue_push_tasks(rq); } -static struct sched_dl_entity *pick_next_dl_entity(struct rq *rq, - struct dl_rq *dl_rq) +static struct sched_dl_entity *pick_next_dl_entity(struct dl_rq *dl_rq) { struct rb_node *left = rb_first_cached(&dl_rq->root); if (!left) return NULL; - return rb_entry(left, struct sched_dl_entity, rb_node); + return __node_2_dle(left); } static struct task_struct *pick_task_dl(struct rq *rq) @@ -1951,7 +1978,7 @@ static struct task_struct *pick_task_dl(struct rq *rq) if (!sched_dl_runnable(rq)) return NULL; - dl_se = pick_next_dl_entity(rq, dl_rq); + dl_se = pick_next_dl_entity(dl_rq); BUG_ON(!dl_se); p = dl_task_of(dl_se); @@ -2034,15 +2061,17 @@ static int pick_dl_task(struct rq *rq, struct task_struct *p, int cpu) */ static struct task_struct *pick_earliest_pushable_dl_task(struct rq *rq, int cpu) { - struct rb_node *next_node = rq->dl.pushable_dl_tasks_root.rb_leftmost; struct task_struct *p = NULL; + struct rb_node *next_node; if (!has_pushable_dl_tasks(rq)) return NULL; + next_node = rb_first_cached(&rq->dl.pushable_dl_tasks_root); + next_node: if (next_node) { - p = rb_entry(next_node, struct task_struct, pushable_dl_tasks); + p = __node_2_pdl(next_node); if (pick_dl_task(rq, p, cpu)) return p; @@ -2208,8 +2237,7 @@ static struct task_struct *pick_next_pushable_dl_task(struct rq *rq) if (!has_pushable_dl_tasks(rq)) return NULL; - p = rb_entry(rq->dl.pushable_dl_tasks_root.rb_leftmost, - struct task_struct, pushable_dl_tasks); + p = __node_2_pdl(rb_first_cached(&rq->dl.pushable_dl_tasks_root)); BUG_ON(rq->cpu != task_cpu(p)); BUG_ON(task_current(rq, p)); @@ -2240,12 +2268,6 @@ static int push_dl_task(struct rq *rq) return 0; retry: - if (is_migration_disabled(next_task)) - return 0; - - if (WARN_ON(next_task == rq->curr)) - return 0; - /* * If next_task preempts rq->curr, and rq->curr * can move away, it makes sense to just reschedule @@ -2258,6 +2280,12 @@ retry: return 0; } + if (is_migration_disabled(next_task)) + return 0; + + if (WARN_ON(next_task == rq->curr)) + return 0; + /* We might release rq lock */ get_task_struct(next_task); @@ -2731,9 +2759,6 @@ void sched_dl_do_global(void) int cpu; unsigned long flags; - def_dl_bandwidth.dl_period = global_rt_period(); - def_dl_bandwidth.dl_runtime = global_rt_runtime(); - if (global_rt_runtime() != RUNTIME_INF) new_bw = to_ratio(global_rt_period(), global_rt_runtime()); @@ -2955,41 +2980,6 @@ bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr) } #ifdef CONFIG_SMP -int dl_task_can_attach(struct task_struct *p, const struct cpumask *cs_cpus_allowed) -{ - unsigned long flags, cap; - unsigned int dest_cpu; - struct dl_bw *dl_b; - bool overflow; - int ret; - - dest_cpu = cpumask_any_and(cpu_active_mask, cs_cpus_allowed); - - rcu_read_lock_sched(); - dl_b = dl_bw_of(dest_cpu); - raw_spin_lock_irqsave(&dl_b->lock, flags); - cap = dl_bw_capacity(dest_cpu); - overflow = __dl_overflow(dl_b, cap, 0, p->dl.dl_bw); - if (overflow) { - ret = -EBUSY; - } else { - /* - * We reserve space for this task in the destination - * root_domain, as we can't fail after this point. - * We will free resources in the source root_domain - * later on (see set_cpus_allowed_dl()). - */ - int cpus = dl_bw_cpus(dest_cpu); - - __dl_add(dl_b, p->dl.dl_bw, cpus); - ret = 0; - } - raw_spin_unlock_irqrestore(&dl_b->lock, flags); - rcu_read_unlock_sched(); - - return ret; -} - int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial) { @@ -3011,7 +3001,7 @@ int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur, return ret; } -bool dl_cpu_busy(unsigned int cpu) +int dl_cpu_busy(int cpu, struct task_struct *p) { unsigned long flags, cap; struct dl_bw *dl_b; @@ -3021,11 +3011,22 @@ bool dl_cpu_busy(unsigned int cpu) dl_b = dl_bw_of(cpu); raw_spin_lock_irqsave(&dl_b->lock, flags); cap = dl_bw_capacity(cpu); - overflow = __dl_overflow(dl_b, cap, 0, 0); + overflow = __dl_overflow(dl_b, cap, 0, p ? p->dl.dl_bw : 0); + + if (!overflow && p) { + /* + * We reserve space for this task in the destination + * root_domain, as we can't fail after this point. + * We will free resources in the source root_domain + * later on (see set_cpus_allowed_dl()). + */ + __dl_add(dl_b, p->dl.dl_bw, dl_bw_cpus(cpu)); + } + raw_spin_unlock_irqrestore(&dl_b->lock, flags); rcu_read_unlock_sched(); - return overflow; + return overflow ? -EBUSY : 0; } #endif diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index aa29211de1bf..bb3d63bdf4ae 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -6,7 +6,6 @@ * * Copyright(C) 2007, Red Hat, Inc., Ingo Molnar */ -#include "sched.h" /* * This allows printing both to /proc/sched_debug and @@ -931,25 +930,15 @@ void print_numa_stats(struct seq_file *m, int node, unsigned long tsf, static void sched_show_numa(struct task_struct *p, struct seq_file *m) { #ifdef CONFIG_NUMA_BALANCING - struct mempolicy *pol; - if (p->mm) P(mm->numa_scan_seq); - task_lock(p); - pol = p->mempolicy; - if (pol && !(pol->flags & MPOL_F_MORON)) - pol = NULL; - mpol_get(pol); - task_unlock(p); - P(numa_pages_migrated); P(numa_preferred_nid); P(total_numa_faults); SEQ_printf(m, "current_node=%d, numa_group_id=%d\n", task_node(p), task_numa_group_id(p)); show_numa_stats(p, m); - mpol_put(pol); #endif } diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 5146163bfabb..ee0664c9d291 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -20,7 +20,38 @@ * Adaptive scheduling granularity, math enhancements by Peter Zijlstra * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra */ +#include <linux/energy_model.h> +#include <linux/mmap_lock.h> +#include <linux/hugetlb_inline.h> +#include <linux/jiffies.h> +#include <linux/mm_api.h> +#include <linux/highmem.h> +#include <linux/spinlock_api.h> +#include <linux/cpumask_api.h> +#include <linux/lockdep_api.h> +#include <linux/softirq.h> +#include <linux/refcount_api.h> +#include <linux/topology.h> +#include <linux/sched/clock.h> +#include <linux/sched/cond_resched.h> +#include <linux/sched/cputime.h> +#include <linux/sched/isolation.h> + +#include <linux/cpuidle.h> +#include <linux/interrupt.h> +#include <linux/mempolicy.h> +#include <linux/mutex_api.h> +#include <linux/profile.h> +#include <linux/psi.h> +#include <linux/ratelimit.h> + +#include <asm/switch_to.h> + +#include <linux/sched/cond_resched.h> + #include "sched.h" +#include "stats.h" +#include "autogroup.h" /* * Targeted preemption latency for CPU-bound tasks: @@ -1259,10 +1290,10 @@ static bool numa_is_active_node(int nid, struct numa_group *ng) /* Handle placement on systems where not all nodes are directly connected. */ static unsigned long score_nearby_nodes(struct task_struct *p, int nid, - int maxdist, bool task) + int lim_dist, bool task) { unsigned long score = 0; - int node; + int node, max_dist; /* * All nodes are directly connected, and the same distance @@ -1271,6 +1302,8 @@ static unsigned long score_nearby_nodes(struct task_struct *p, int nid, if (sched_numa_topology_type == NUMA_DIRECT) return 0; + /* sched_max_numa_distance may be changed in parallel. */ + max_dist = READ_ONCE(sched_max_numa_distance); /* * This code is called for each node, introducing N^2 complexity, * which should be ok given the number of nodes rarely exceeds 8. @@ -1283,7 +1316,7 @@ static unsigned long score_nearby_nodes(struct task_struct *p, int nid, * The furthest away nodes in the system are not interesting * for placement; nid was already counted. */ - if (dist == sched_max_numa_distance || node == nid) + if (dist >= max_dist || node == nid) continue; /* @@ -1293,8 +1326,7 @@ static unsigned long score_nearby_nodes(struct task_struct *p, int nid, * "hoplimit", only nodes closer by than "hoplimit" are part * of each group. Skip other nodes. */ - if (sched_numa_topology_type == NUMA_BACKPLANE && - dist >= maxdist) + if (sched_numa_topology_type == NUMA_BACKPLANE && dist >= lim_dist) continue; /* Add up the faults from nearby nodes. */ @@ -1312,8 +1344,8 @@ static unsigned long score_nearby_nodes(struct task_struct *p, int nid, * This seems to result in good task placement. */ if (sched_numa_topology_type == NUMA_GLUELESS_MESH) { - faults *= (sched_max_numa_distance - dist); - faults /= (sched_max_numa_distance - LOCAL_DISTANCE); + faults *= (max_dist - dist); + faults /= (max_dist - LOCAL_DISTANCE); } score += faults; @@ -1489,6 +1521,7 @@ struct task_numa_env { int src_cpu, src_nid; int dst_cpu, dst_nid; + int imb_numa_nr; struct numa_stats src_stats, dst_stats; @@ -1503,7 +1536,7 @@ struct task_numa_env { static unsigned long cpu_load(struct rq *rq); static unsigned long cpu_runnable(struct rq *rq); static inline long adjust_numa_imbalance(int imbalance, - int dst_running, int dst_weight); + int dst_running, int imb_numa_nr); static inline enum numa_type numa_classify(unsigned int imbalance_pct, @@ -1884,7 +1917,7 @@ static void task_numa_find_cpu(struct task_numa_env *env, dst_running = env->dst_stats.nr_running + 1; imbalance = max(0, dst_running - src_running); imbalance = adjust_numa_imbalance(imbalance, dst_running, - env->dst_stats.weight); + env->imb_numa_nr); /* Use idle CPU if there is no imbalance */ if (!imbalance) { @@ -1949,8 +1982,10 @@ static int task_numa_migrate(struct task_struct *p) */ rcu_read_lock(); sd = rcu_dereference(per_cpu(sd_numa, env.src_cpu)); - if (sd) + if (sd) { env.imbalance_pct = 100 + (sd->imbalance_pct - 100) / 2; + env.imb_numa_nr = sd->imb_numa_nr; + } rcu_read_unlock(); /* @@ -1985,7 +2020,7 @@ static int task_numa_migrate(struct task_struct *p) */ ng = deref_curr_numa_group(p); if (env.best_cpu == -1 || (ng && ng->active_nodes > 1)) { - for_each_online_node(nid) { + for_each_node_state(nid, N_CPU) { if (nid == env.src_nid || nid == p->numa_preferred_nid) continue; @@ -2083,13 +2118,13 @@ static void numa_group_count_active_nodes(struct numa_group *numa_group) unsigned long faults, max_faults = 0; int nid, active_nodes = 0; - for_each_online_node(nid) { + for_each_node_state(nid, N_CPU) { faults = group_faults_cpu(numa_group, nid); if (faults > max_faults) max_faults = faults; } - for_each_online_node(nid) { + for_each_node_state(nid, N_CPU) { faults = group_faults_cpu(numa_group, nid); if (faults * ACTIVE_NODE_FRACTION > max_faults) active_nodes++; @@ -2243,7 +2278,7 @@ static int preferred_group_nid(struct task_struct *p, int nid) dist = sched_max_numa_distance; - for_each_online_node(node) { + for_each_node_state(node, N_CPU) { score = group_weight(p, node, dist); if (score > max_score) { max_score = score; @@ -2262,7 +2297,7 @@ static int preferred_group_nid(struct task_struct *p, int nid) * inside the highest scoring group of nodes. The nodemask tricks * keep the complexity of the search down. */ - nodes = node_online_map; + nodes = node_states[N_CPU]; for (dist = sched_max_numa_distance; dist > LOCAL_DISTANCE; dist--) { unsigned long max_faults = 0; nodemask_t max_group = NODE_MASK_NONE; @@ -2401,6 +2436,21 @@ static void task_numa_placement(struct task_struct *p) } } + /* Cannot migrate task to CPU-less node */ + if (max_nid != NUMA_NO_NODE && !node_state(max_nid, N_CPU)) { + int near_nid = max_nid; + int distance, near_distance = INT_MAX; + + for_each_node_state(nid, N_CPU) { + distance = node_distance(max_nid, nid); + if (distance < near_distance) { + near_nid = nid; + near_distance = distance; + } + } + max_nid = near_nid; + } + if (ng) { numa_group_count_active_nodes(ng); spin_unlock_irq(group_lock); @@ -2825,6 +2875,8 @@ void init_numa_balancing(unsigned long clone_flags, struct task_struct *p) /* Protect against double add, see task_tick_numa and task_numa_work */ p->numa_work.next = &p->numa_work; p->numa_faults = NULL; + p->numa_pages_migrated = 0; + p->total_numa_faults = 0; RCU_INIT_POINTER(p->numa_group, NULL); p->last_task_numa_placement = 0; p->last_sum_exec_runtime = 0; @@ -9040,9 +9092,9 @@ static bool update_pick_idlest(struct sched_group *idlest, * This is an approximation as the number of running tasks may not be * related to the number of busy CPUs due to sched_setaffinity. */ -static inline bool allow_numa_imbalance(int dst_running, int dst_weight) +static inline bool allow_numa_imbalance(int running, int imb_numa_nr) { - return (dst_running < (dst_weight >> 2)); + return running <= imb_numa_nr; } /* @@ -9176,12 +9228,13 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu) return idlest; #endif /* - * Otherwise, keep the task on this node to stay close - * its wakeup source and improve locality. If there is - * a real need of migration, periodic load balance will - * take care of it. + * Otherwise, keep the task close to the wakeup source + * and improve locality if the number of running tasks + * would remain below threshold where an imbalance is + * allowed. If there is a real need of migration, + * periodic load balance will take care of it. */ - if (allow_numa_imbalance(local_sgs.sum_nr_running, sd->span_weight)) + if (allow_numa_imbalance(local_sgs.sum_nr_running + 1, sd->imb_numa_nr)) return NULL; } @@ -9273,9 +9326,9 @@ next_group: #define NUMA_IMBALANCE_MIN 2 static inline long adjust_numa_imbalance(int imbalance, - int dst_running, int dst_weight) + int dst_running, int imb_numa_nr) { - if (!allow_numa_imbalance(dst_running, dst_weight)) + if (!allow_numa_imbalance(dst_running, imb_numa_nr)) return imbalance; /* @@ -9387,7 +9440,7 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s /* Consider allowing a small imbalance between NUMA groups */ if (env->sd->flags & SD_NUMA) { env->imbalance = adjust_numa_imbalance(env->imbalance, - busiest->sum_nr_running, busiest->group_weight); + local->sum_nr_running + 1, env->sd->imb_numa_nr); } return; @@ -10351,7 +10404,7 @@ static inline int on_null_domain(struct rq *rq) * - When one of the busy CPUs notice that there may be an idle rebalancing * needed, they will kick the idle load balancer, which then does idle * load balancing for all the idle CPUs. - * - HK_FLAG_MISC CPUs are used for this task, because HK_FLAG_SCHED not set + * - HK_TYPE_MISC CPUs are used for this task, because HK_TYPE_SCHED not set * anywhere yet. */ @@ -10360,7 +10413,7 @@ static inline int find_new_ilb(void) int ilb; const struct cpumask *hk_mask; - hk_mask = housekeeping_cpumask(HK_FLAG_MISC); + hk_mask = housekeeping_cpumask(HK_TYPE_MISC); for_each_cpu_and(ilb, nohz.idle_cpus_mask, hk_mask) { @@ -10376,7 +10429,7 @@ static inline int find_new_ilb(void) /* * Kick a CPU to do the nohz balancing, if it is time for it. We pick any - * idle CPU in the HK_FLAG_MISC housekeeping set (if there is one). + * idle CPU in the HK_TYPE_MISC housekeeping set (if there is one). */ static void kick_ilb(unsigned int flags) { @@ -10589,7 +10642,7 @@ void nohz_balance_enter_idle(int cpu) return; /* Spare idle load balancing on CPUs that don't want to be disturbed: */ - if (!housekeeping_cpu(cpu, HK_FLAG_SCHED)) + if (!housekeeping_cpu(cpu, HK_TYPE_SCHED)) return; /* @@ -10805,7 +10858,7 @@ static void nohz_newidle_balance(struct rq *this_rq) * This CPU doesn't want to be disturbed by scheduler * housekeeping */ - if (!housekeeping_cpu(this_cpu, HK_FLAG_SCHED)) + if (!housekeeping_cpu(this_cpu, HK_TYPE_SCHED)) return; /* Will wake up very soon. No time for doing anything else*/ diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index d17b0a5ce6ac..8f8b5020e76a 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -6,9 +6,6 @@ * (NOTE: these are not related to SCHED_IDLE batch scheduled * tasks which are handled in sched/fair.c ) */ -#include "sched.h" - -#include <trace/events/power.h> /* Linker adds these: start and end of __cpuidle functions */ extern char __cpuidle_text_start[], __cpuidle_text_end[]; diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c index 7f06eaf12818..373d42c707bc 100644 --- a/kernel/sched/isolation.c +++ b/kernel/sched/isolation.c @@ -7,136 +7,179 @@ * Copyright (C) 2017-2018 SUSE, Frederic Weisbecker * */ -#include "sched.h" + +enum hk_flags { + HK_FLAG_TIMER = BIT(HK_TYPE_TIMER), + HK_FLAG_RCU = BIT(HK_TYPE_RCU), + HK_FLAG_MISC = BIT(HK_TYPE_MISC), + HK_FLAG_SCHED = BIT(HK_TYPE_SCHED), + HK_FLAG_TICK = BIT(HK_TYPE_TICK), + HK_FLAG_DOMAIN = BIT(HK_TYPE_DOMAIN), + HK_FLAG_WQ = BIT(HK_TYPE_WQ), + HK_FLAG_MANAGED_IRQ = BIT(HK_TYPE_MANAGED_IRQ), + HK_FLAG_KTHREAD = BIT(HK_TYPE_KTHREAD), +}; DEFINE_STATIC_KEY_FALSE(housekeeping_overridden); EXPORT_SYMBOL_GPL(housekeeping_overridden); -static cpumask_var_t housekeeping_mask; -static unsigned int housekeeping_flags; -bool housekeeping_enabled(enum hk_flags flags) +struct housekeeping { + cpumask_var_t cpumasks[HK_TYPE_MAX]; + unsigned long flags; +}; + +static struct housekeeping housekeeping; + +bool housekeeping_enabled(enum hk_type type) { - return !!(housekeeping_flags & flags); + return !!(housekeeping.flags & BIT(type)); } EXPORT_SYMBOL_GPL(housekeeping_enabled); -int housekeeping_any_cpu(enum hk_flags flags) +int housekeeping_any_cpu(enum hk_type type) { int cpu; if (static_branch_unlikely(&housekeeping_overridden)) { - if (housekeeping_flags & flags) { - cpu = sched_numa_find_closest(housekeeping_mask, smp_processor_id()); + if (housekeeping.flags & BIT(type)) { + cpu = sched_numa_find_closest(housekeeping.cpumasks[type], smp_processor_id()); if (cpu < nr_cpu_ids) return cpu; - return cpumask_any_and(housekeeping_mask, cpu_online_mask); + return cpumask_any_and(housekeeping.cpumasks[type], cpu_online_mask); } } return smp_processor_id(); } EXPORT_SYMBOL_GPL(housekeeping_any_cpu); -const struct cpumask *housekeeping_cpumask(enum hk_flags flags) +const struct cpumask *housekeeping_cpumask(enum hk_type type) { if (static_branch_unlikely(&housekeeping_overridden)) - if (housekeeping_flags & flags) - return housekeeping_mask; + if (housekeeping.flags & BIT(type)) + return housekeeping.cpumasks[type]; return cpu_possible_mask; } EXPORT_SYMBOL_GPL(housekeeping_cpumask); -void housekeeping_affine(struct task_struct *t, enum hk_flags flags) +void housekeeping_affine(struct task_struct *t, enum hk_type type) { if (static_branch_unlikely(&housekeeping_overridden)) - if (housekeeping_flags & flags) - set_cpus_allowed_ptr(t, housekeeping_mask); + if (housekeeping.flags & BIT(type)) + set_cpus_allowed_ptr(t, housekeeping.cpumasks[type]); } EXPORT_SYMBOL_GPL(housekeeping_affine); -bool housekeeping_test_cpu(int cpu, enum hk_flags flags) +bool housekeeping_test_cpu(int cpu, enum hk_type type) { if (static_branch_unlikely(&housekeeping_overridden)) - if (housekeeping_flags & flags) - return cpumask_test_cpu(cpu, housekeeping_mask); + if (housekeeping.flags & BIT(type)) + return cpumask_test_cpu(cpu, housekeeping.cpumasks[type]); return true; } EXPORT_SYMBOL_GPL(housekeeping_test_cpu); void __init housekeeping_init(void) { - if (!housekeeping_flags) + enum hk_type type; + + if (!housekeeping.flags) return; static_branch_enable(&housekeeping_overridden); - if (housekeeping_flags & HK_FLAG_TICK) + if (housekeeping.flags & HK_FLAG_TICK) sched_tick_offload_init(); - /* We need at least one CPU to handle housekeeping work */ - WARN_ON_ONCE(cpumask_empty(housekeeping_mask)); + for_each_set_bit(type, &housekeeping.flags, HK_TYPE_MAX) { + /* We need at least one CPU to handle housekeeping work */ + WARN_ON_ONCE(cpumask_empty(housekeeping.cpumasks[type])); + } } -static int __init housekeeping_setup(char *str, enum hk_flags flags) +static void __init housekeeping_setup_type(enum hk_type type, + cpumask_var_t housekeeping_staging) { - cpumask_var_t non_housekeeping_mask; - cpumask_var_t tmp; + + alloc_bootmem_cpumask_var(&housekeeping.cpumasks[type]); + cpumask_copy(housekeeping.cpumasks[type], + housekeeping_staging); +} + +static int __init housekeeping_setup(char *str, unsigned long flags) +{ + cpumask_var_t non_housekeeping_mask, housekeeping_staging; + int err = 0; + + if ((flags & HK_FLAG_TICK) && !(housekeeping.flags & HK_FLAG_TICK)) { + if (!IS_ENABLED(CONFIG_NO_HZ_FULL)) { + pr_warn("Housekeeping: nohz unsupported." + " Build with CONFIG_NO_HZ_FULL\n"); + return 0; + } + } alloc_bootmem_cpumask_var(&non_housekeeping_mask); if (cpulist_parse(str, non_housekeeping_mask) < 0) { pr_warn("Housekeeping: nohz_full= or isolcpus= incorrect CPU range\n"); - free_bootmem_cpumask_var(non_housekeeping_mask); - return 0; + goto free_non_housekeeping_mask; } - alloc_bootmem_cpumask_var(&tmp); - if (!housekeeping_flags) { - alloc_bootmem_cpumask_var(&housekeeping_mask); - cpumask_andnot(housekeeping_mask, - cpu_possible_mask, non_housekeeping_mask); + alloc_bootmem_cpumask_var(&housekeeping_staging); + cpumask_andnot(housekeeping_staging, + cpu_possible_mask, non_housekeeping_mask); - cpumask_andnot(tmp, cpu_present_mask, non_housekeeping_mask); - if (cpumask_empty(tmp)) { + if (!cpumask_intersects(cpu_present_mask, housekeeping_staging)) { + __cpumask_set_cpu(smp_processor_id(), housekeeping_staging); + __cpumask_clear_cpu(smp_processor_id(), non_housekeeping_mask); + if (!housekeeping.flags) { pr_warn("Housekeeping: must include one present CPU, " "using boot CPU:%d\n", smp_processor_id()); - __cpumask_set_cpu(smp_processor_id(), housekeeping_mask); - __cpumask_clear_cpu(smp_processor_id(), non_housekeeping_mask); - } - } else { - cpumask_andnot(tmp, cpu_present_mask, non_housekeeping_mask); - if (cpumask_empty(tmp)) - __cpumask_clear_cpu(smp_processor_id(), non_housekeeping_mask); - cpumask_andnot(tmp, cpu_possible_mask, non_housekeeping_mask); - if (!cpumask_equal(tmp, housekeeping_mask)) { - pr_warn("Housekeeping: nohz_full= must match isolcpus=\n"); - free_bootmem_cpumask_var(tmp); - free_bootmem_cpumask_var(non_housekeeping_mask); - return 0; } } - free_bootmem_cpumask_var(tmp); - if ((flags & HK_FLAG_TICK) && !(housekeeping_flags & HK_FLAG_TICK)) { - if (IS_ENABLED(CONFIG_NO_HZ_FULL)) { - tick_nohz_full_setup(non_housekeeping_mask); - } else { - pr_warn("Housekeeping: nohz unsupported." - " Build with CONFIG_NO_HZ_FULL\n"); - free_bootmem_cpumask_var(non_housekeeping_mask); - return 0; + if (!housekeeping.flags) { + /* First setup call ("nohz_full=" or "isolcpus=") */ + enum hk_type type; + + for_each_set_bit(type, &flags, HK_TYPE_MAX) + housekeeping_setup_type(type, housekeeping_staging); + } else { + /* Second setup call ("nohz_full=" after "isolcpus=" or the reverse) */ + enum hk_type type; + unsigned long iter_flags = flags & housekeeping.flags; + + for_each_set_bit(type, &iter_flags, HK_TYPE_MAX) { + if (!cpumask_equal(housekeeping_staging, + housekeeping.cpumasks[type])) { + pr_warn("Housekeeping: nohz_full= must match isolcpus=\n"); + goto free_housekeeping_staging; + } } + + iter_flags = flags & ~housekeeping.flags; + + for_each_set_bit(type, &iter_flags, HK_TYPE_MAX) + housekeeping_setup_type(type, housekeeping_staging); } - housekeeping_flags |= flags; + if ((flags & HK_FLAG_TICK) && !(housekeeping.flags & HK_FLAG_TICK)) + tick_nohz_full_setup(non_housekeeping_mask); + + housekeeping.flags |= flags; + err = 1; +free_housekeeping_staging: + free_bootmem_cpumask_var(housekeeping_staging); +free_non_housekeeping_mask: free_bootmem_cpumask_var(non_housekeeping_mask); - return 1; + return err; } static int __init housekeeping_nohz_full_setup(char *str) { - unsigned int flags; + unsigned long flags; flags = HK_FLAG_TICK | HK_FLAG_WQ | HK_FLAG_TIMER | HK_FLAG_RCU | HK_FLAG_MISC | HK_FLAG_KTHREAD; @@ -147,7 +190,7 @@ __setup("nohz_full=", housekeeping_nohz_full_setup); static int __init housekeeping_isolcpus_setup(char *str) { - unsigned int flags = 0; + unsigned long flags = 0; bool illegal = false; char *par; int len; diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c index 954b229868d9..52c8f8226b0d 100644 --- a/kernel/sched/loadavg.c +++ b/kernel/sched/loadavg.c @@ -6,7 +6,6 @@ * figure. Its a silly number but people think its important. We go through * great pains to make it work on big machines and tickless kernels. */ -#include "sched.h" /* * Global load-average calculations diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c index 3d2825408e3a..0c5be7ebb1dc 100644 --- a/kernel/sched/membarrier.c +++ b/kernel/sched/membarrier.c @@ -4,7 +4,6 @@ * * membarrier system call */ -#include "sched.h" /* * For documentation purposes, here are some membarrier ordering diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c index a554e3bbab2b..0f310768260c 100644 --- a/kernel/sched/pelt.c +++ b/kernel/sched/pelt.c @@ -24,10 +24,6 @@ * Author: Vincent Guittot <vincent.guittot@linaro.org> */ -#include <linux/sched.h> -#include "sched.h" -#include "pelt.h" - /* * Approximate: * val * y^n, where y^32 ~= 0.5 (~1 scheduling period) diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index e14358178849..a4fa3aadfcba 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -137,21 +137,6 @@ * sampling of the aggregate task states would be. */ -#include "../workqueue_internal.h" -#include <linux/sched/loadavg.h> -#include <linux/seq_file.h> -#include <linux/proc_fs.h> -#include <linux/seqlock.h> -#include <linux/uaccess.h> -#include <linux/cgroup.h> -#include <linux/module.h> -#include <linux/sched.h> -#include <linux/ctype.h> -#include <linux/file.h> -#include <linux/poll.h> -#include <linux/psi.h> -#include "sched.h" - static int psi_bug __read_mostly; DEFINE_STATIC_KEY_FALSE(psi_disabled); @@ -523,7 +508,7 @@ static void init_triggers(struct psi_group *group, u64 now) static u64 update_triggers(struct psi_group *group, u64 now) { struct psi_trigger *t; - bool new_stall = false; + bool update_total = false; u64 *total = group->total[PSI_POLL]; /* @@ -532,24 +517,35 @@ static u64 update_triggers(struct psi_group *group, u64 now) */ list_for_each_entry(t, &group->triggers, node) { u64 growth; + bool new_stall; - /* Check for stall activity */ - if (group->polling_total[t->state] == total[t->state]) - continue; + new_stall = group->polling_total[t->state] != total[t->state]; + /* Check for stall activity or a previous threshold breach */ + if (!new_stall && !t->pending_event) + continue; /* - * Multiple triggers might be looking at the same state, - * remember to update group->polling_total[] once we've - * been through all of them. Also remember to extend the - * polling time if we see new stall activity. + * Check for new stall activity, as well as deferred + * events that occurred in the last window after the + * trigger had already fired (we want to ratelimit + * events without dropping any). */ - new_stall = true; - - /* Calculate growth since last update */ - growth = window_update(&t->win, now, total[t->state]); - if (growth < t->threshold) - continue; - + if (new_stall) { + /* + * Multiple triggers might be looking at the same state, + * remember to update group->polling_total[] once we've + * been through all of them. Also remember to extend the + * polling time if we see new stall activity. + */ + update_total = true; + + /* Calculate growth since last update */ + growth = window_update(&t->win, now, total[t->state]); + if (growth < t->threshold) + continue; + + t->pending_event = true; + } /* Limit event signaling to once per window */ if (now < t->last_event_time + t->win.size) continue; @@ -558,9 +554,11 @@ static u64 update_triggers(struct psi_group *group, u64 now) if (cmpxchg(&t->event, 0, 1) == 0) wake_up_interruptible(&t->event_wait); t->last_event_time = now; + /* Reset threshold breach flag once event got generated */ + t->pending_event = false; } - if (new_stall) + if (update_total) memcpy(group->polling_total, total, sizeof(group->polling_total)); @@ -1124,6 +1122,7 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group, t->event = 0; t->last_event_time = 0; init_waitqueue_head(&t->event_wait); + t->pending_event = false; mutex_lock(&group->trigger_lock); diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 7b4f4fbbb404..a32c46889af8 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -3,9 +3,6 @@ * Real-Time Scheduling Class (mapped to the SCHED_FIFO and SCHED_RR * policies) */ -#include "sched.h" - -#include "pelt.h" int sched_rr_timeslice = RR_TIMESLICE; int sysctl_sched_rr_timeslice = (MSEC_PER_SEC / HZ) * RR_TIMESLICE; @@ -271,8 +268,6 @@ int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent) #ifdef CONFIG_SMP -static void pull_rt_task(struct rq *this_rq); - static inline bool need_pull_rt_task(struct rq *rq, struct task_struct *prev) { /* Try to pull RT tasks here if we lower this rq's prio */ @@ -429,15 +424,6 @@ void dec_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) { } -static inline bool need_pull_rt_task(struct rq *rq, struct task_struct *prev) -{ - return false; -} - -static inline void pull_rt_task(struct rq *this_rq) -{ -} - static inline void rt_queue_push_tasks(struct rq *rq) { } @@ -1730,8 +1716,7 @@ static inline void set_next_task_rt(struct rq *rq, struct task_struct *p, bool f rt_queue_push_tasks(rq); } -static struct sched_rt_entity *pick_next_rt_entity(struct rq *rq, - struct rt_rq *rt_rq) +static struct sched_rt_entity *pick_next_rt_entity(struct rt_rq *rt_rq) { struct rt_prio_array *array = &rt_rq->active; struct sched_rt_entity *next = NULL; @@ -1753,7 +1738,7 @@ static struct task_struct *_pick_next_task_rt(struct rq *rq) struct rt_rq *rt_rq = &rq->rt; do { - rt_se = pick_next_rt_entity(rq, rt_rq); + rt_se = pick_next_rt_entity(rt_rq); BUG_ON(!rt_se); rt_rq = group_rt_rq(rt_se); } while (rt_rq); @@ -2026,6 +2011,16 @@ static int push_rt_task(struct rq *rq, bool pull) return 0; retry: + /* + * It's possible that the next_task slipped in of + * higher priority than current. If that's the case + * just reschedule current. + */ + if (unlikely(next_task->prio < rq->curr->prio)) { + resched_curr(rq); + return 0; + } + if (is_migration_disabled(next_task)) { struct task_struct *push_task = NULL; int cpu; @@ -2033,6 +2028,18 @@ retry: if (!pull || rq->push_busy) return 0; + /* + * Invoking find_lowest_rq() on anything but an RT task doesn't + * make sense. Per the above priority check, curr has to + * be of higher priority than next_task, so no need to + * reschedule when bailing out. + * + * Note that the stoppers are masqueraded as SCHED_FIFO + * (cf. sched_set_stop_task()), so we can't rely on rt_task(). + */ + if (rq->curr->sched_class != &rt_sched_class) + return 0; + cpu = find_lowest_rq(rq->curr); if (cpu == -1 || cpu == rq->cpu) return 0; @@ -2057,16 +2064,6 @@ retry: if (WARN_ON(next_task == rq->curr)) return 0; - /* - * It's possible that the next_task slipped in of - * higher priority than current. If that's the case - * just reschedule current. - */ - if (unlikely(next_task->prio < rq->curr->prio)) { - resched_curr(rq); - return 0; - } - /* We might release rq lock */ get_task_struct(next_task); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index de53be905739..58263f90c559 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -2,86 +2,98 @@ /* * Scheduler internal types and methods: */ -#include <linux/sched.h> +#ifndef _KERNEL_SCHED_SCHED_H +#define _KERNEL_SCHED_SCHED_H +#include <linux/sched/affinity.h> #include <linux/sched/autogroup.h> -#include <linux/sched/clock.h> -#include <linux/sched/coredump.h> #include <linux/sched/cpufreq.h> -#include <linux/sched/cputime.h> #include <linux/sched/deadline.h> -#include <linux/sched/debug.h> -#include <linux/sched/hotplug.h> -#include <linux/sched/idle.h> -#include <linux/sched/init.h> -#include <linux/sched/isolation.h> -#include <linux/sched/jobctl.h> +#include <linux/sched.h> #include <linux/sched/loadavg.h> #include <linux/sched/mm.h> -#include <linux/sched/nohz.h> -#include <linux/sched/numa_balancing.h> -#include <linux/sched/prio.h> -#include <linux/sched/rt.h> +#include <linux/sched/rseq_api.h> #include <linux/sched/signal.h> #include <linux/sched/smt.h> #include <linux/sched/stat.h> #include <linux/sched/sysctl.h> +#include <linux/sched/task_flags.h> #include <linux/sched/task.h> -#include <linux/sched/task_stack.h> #include <linux/sched/topology.h> -#include <linux/sched/user.h> -#include <linux/sched/wake_q.h> -#include <linux/sched/xacct.h> -#include <uapi/linux/sched/types.h> - -#include <linux/binfmts.h> -#include <linux/bitops.h> -#include <linux/compat.h> -#include <linux/context_tracking.h> +#include <linux/atomic.h> +#include <linux/bitmap.h> +#include <linux/bug.h> +#include <linux/capability.h> +#include <linux/cgroup_api.h> +#include <linux/cgroup.h> #include <linux/cpufreq.h> -#include <linux/cpuidle.h> -#include <linux/cpuset.h> +#include <linux/cpumask_api.h> #include <linux/ctype.h> -#include <linux/debugfs.h> -#include <linux/delayacct.h> -#include <linux/energy_model.h> -#include <linux/init_task.h> -#include <linux/kprobes.h> +#include <linux/file.h> +#include <linux/fs_api.h> +#include <linux/hrtimer_api.h> +#include <linux/interrupt.h> +#include <linux/irq_work.h> +#include <linux/jiffies.h> +#include <linux/kref_api.h> #include <linux/kthread.h> -#include <linux/membarrier.h> -#include <linux/migrate.h> -#include <linux/mmu_context.h> -#include <linux/nmi.h> +#include <linux/ktime_api.h> +#include <linux/lockdep_api.h> +#include <linux/lockdep.h> +#include <linux/minmax.h> +#include <linux/mm.h> +#include <linux/module.h> +#include <linux/mutex_api.h> +#include <linux/plist.h> +#include <linux/poll.h> #include <linux/proc_fs.h> -#include <linux/prefetch.h> #include <linux/profile.h> #include <linux/psi.h> -#include <linux/ratelimit.h> -#include <linux/rcupdate_wait.h> -#include <linux/security.h> +#include <linux/rcupdate.h> +#include <linux/seq_file.h> +#include <linux/seqlock.h> +#include <linux/softirq.h> +#include <linux/spinlock_api.h> +#include <linux/static_key.h> #include <linux/stop_machine.h> -#include <linux/suspend.h> -#include <linux/swait.h> +#include <linux/syscalls_api.h> #include <linux/syscalls.h> -#include <linux/task_work.h> -#include <linux/tsacct_kern.h> +#include <linux/tick.h> +#include <linux/topology.h> +#include <linux/types.h> +#include <linux/u64_stats_sync_api.h> +#include <linux/uaccess.h> +#include <linux/wait_api.h> +#include <linux/wait_bit.h> +#include <linux/workqueue_api.h> + +#include <trace/events/power.h> +#include <trace/events/sched.h> + +#include "../workqueue_internal.h" + +#ifdef CONFIG_CGROUP_SCHED +#include <linux/cgroup.h> +#include <linux/psi.h> +#endif -#include <asm/tlb.h> +#ifdef CONFIG_SCHED_DEBUG +# include <linux/static_key.h> +#endif #ifdef CONFIG_PARAVIRT # include <asm/paravirt.h> +# include <asm/paravirt_api_clock.h> #endif #include "cpupri.h" #include "cpudeadline.h" -#include <trace/events/sched.h> - #ifdef CONFIG_SCHED_DEBUG -# define SCHED_WARN_ON(x) WARN_ONCE(x, #x) +# define SCHED_WARN_ON(x) WARN_ONCE(x, #x) #else -# define SCHED_WARN_ON(x) ({ (void)(x), 0; }) +# define SCHED_WARN_ON(x) ({ (void)(x), 0; }) #endif struct rq; @@ -301,29 +313,6 @@ struct dl_bw { u64 total_bw; }; -static inline void __dl_update(struct dl_bw *dl_b, s64 bw); - -static inline -void __dl_sub(struct dl_bw *dl_b, u64 tsk_bw, int cpus) -{ - dl_b->total_bw -= tsk_bw; - __dl_update(dl_b, (s32)tsk_bw / cpus); -} - -static inline -void __dl_add(struct dl_bw *dl_b, u64 tsk_bw, int cpus) -{ - dl_b->total_bw += tsk_bw; - __dl_update(dl_b, -((s32)tsk_bw / cpus)); -} - -static inline bool __dl_overflow(struct dl_bw *dl_b, unsigned long cap, - u64 old_bw, u64 new_bw) -{ - return dl_b->bw != -1 && - cap_scale(dl_b->bw, cap) < dl_b->total_bw - old_bw + new_bw; -} - /* * Verify the fitness of task @p to run on @cpu taking into account the * CPU original capacity and the runtime/deadline ratio of the task. @@ -347,15 +336,11 @@ extern void __setparam_dl(struct task_struct *p, const struct sched_attr *attr); extern void __getparam_dl(struct task_struct *p, struct sched_attr *attr); extern bool __checkparam_dl(const struct sched_attr *attr); extern bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr); -extern int dl_task_can_attach(struct task_struct *p, const struct cpumask *cs_cpus_allowed); extern int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial); -extern bool dl_cpu_busy(unsigned int cpu); +extern int dl_cpu_busy(int cpu, struct task_struct *p); #ifdef CONFIG_CGROUP_SCHED -#include <linux/cgroup.h> -#include <linux/psi.h> - struct cfs_rq; struct rt_rq; @@ -1662,12 +1647,14 @@ enum numa_topology_type { extern enum numa_topology_type sched_numa_topology_type; extern int sched_max_numa_distance; extern bool find_numa_distance(int distance); -extern void sched_init_numa(void); +extern void sched_init_numa(int offline_node); +extern void sched_update_numa(int cpu, bool online); extern void sched_domains_numa_masks_set(unsigned int cpu); extern void sched_domains_numa_masks_clear(unsigned int cpu); extern int sched_numa_find_closest(const struct cpumask *cpus, int cpu); #else -static inline void sched_init_numa(void) { } +static inline void sched_init_numa(int offline_node) { } +static inline void sched_update_numa(int cpu, bool online) { } static inline void sched_domains_numa_masks_set(unsigned int cpu) { } static inline void sched_domains_numa_masks_clear(unsigned int cpu) { } static inline int sched_numa_find_closest(const struct cpumask *cpus, int cpu) @@ -1854,7 +1841,6 @@ static inline void flush_smp_call_function_from_idle(void) { } #endif #include "stats.h" -#include "autogroup.h" #if defined(CONFIG_SCHED_CORE) && defined(CONFIG_SCHEDSTATS) @@ -1950,7 +1936,6 @@ static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu) * Tunables that become constants when CONFIG_SCHED_DEBUG is off: */ #ifdef CONFIG_SCHED_DEBUG -# include <linux/static_key.h> # define const_debug __read_mostly #else # define const_debug const @@ -2331,7 +2316,6 @@ extern void resched_cpu(int cpu); extern struct rt_bandwidth def_rt_bandwidth; extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime); -extern struct dl_bandwidth def_dl_bandwidth; extern void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime); extern void init_dl_task_timer(struct sched_dl_entity *dl_se); extern void init_dl_inactive_task_timer(struct sched_dl_entity *dl_se); @@ -2747,32 +2731,6 @@ extern void nohz_run_idle_balance(int cpu); static inline void nohz_run_idle_balance(int cpu) { } #endif -#ifdef CONFIG_SMP -static inline -void __dl_update(struct dl_bw *dl_b, s64 bw) -{ - struct root_domain *rd = container_of(dl_b, struct root_domain, dl_bw); - int i; - - RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(), - "sched RCU must be held"); - for_each_cpu_and(i, rd->span, cpu_active_mask) { - struct rq *rq = cpu_rq(i); - - rq->dl.extra_bw += bw; - } -} -#else -static inline -void __dl_update(struct dl_bw *dl_b, s64 bw) -{ - struct dl_rq *dl = container_of(dl_b, struct dl_rq, dl_bw); - - dl->extra_bw += bw; -} -#endif - - #ifdef CONFIG_IRQ_TIME_ACCOUNTING struct irqtime { u64 total; @@ -2841,88 +2799,6 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {} #endif /* CONFIG_CPU_FREQ */ -#ifdef CONFIG_UCLAMP_TASK -unsigned long uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id); - -/** - * uclamp_rq_util_with - clamp @util with @rq and @p effective uclamp values. - * @rq: The rq to clamp against. Must not be NULL. - * @util: The util value to clamp. - * @p: The task to clamp against. Can be NULL if you want to clamp - * against @rq only. - * - * Clamps the passed @util to the max(@rq, @p) effective uclamp values. - * - * If sched_uclamp_used static key is disabled, then just return the util - * without any clamping since uclamp aggregation at the rq level in the fast - * path is disabled, rendering this operation a NOP. - * - * Use uclamp_eff_value() if you don't care about uclamp values at rq level. It - * will return the correct effective uclamp value of the task even if the - * static key is disabled. - */ -static __always_inline -unsigned long uclamp_rq_util_with(struct rq *rq, unsigned long util, - struct task_struct *p) -{ - unsigned long min_util = 0; - unsigned long max_util = 0; - - if (!static_branch_likely(&sched_uclamp_used)) - return util; - - if (p) { - min_util = uclamp_eff_value(p, UCLAMP_MIN); - max_util = uclamp_eff_value(p, UCLAMP_MAX); - - /* - * Ignore last runnable task's max clamp, as this task will - * reset it. Similarly, no need to read the rq's min clamp. - */ - if (rq->uclamp_flags & UCLAMP_FLAG_IDLE) - goto out; - } - - min_util = max_t(unsigned long, min_util, READ_ONCE(rq->uclamp[UCLAMP_MIN].value)); - max_util = max_t(unsigned long, max_util, READ_ONCE(rq->uclamp[UCLAMP_MAX].value)); -out: - /* - * Since CPU's {min,max}_util clamps are MAX aggregated considering - * RUNNABLE tasks with _different_ clamps, we can end up with an - * inversion. Fix it now when the clamps are applied. - */ - if (unlikely(min_util >= max_util)) - return min_util; - - return clamp(util, min_util, max_util); -} - -/* - * When uclamp is compiled in, the aggregation at rq level is 'turned off' - * by default in the fast path and only gets turned on once userspace performs - * an operation that requires it. - * - * Returns true if userspace opted-in to use uclamp and aggregation at rq level - * hence is active. - */ -static inline bool uclamp_is_used(void) -{ - return static_branch_likely(&sched_uclamp_used); -} -#else /* CONFIG_UCLAMP_TASK */ -static inline -unsigned long uclamp_rq_util_with(struct rq *rq, unsigned long util, - struct task_struct *p) -{ - return util; -} - -static inline bool uclamp_is_used(void) -{ - return false; -} -#endif /* CONFIG_UCLAMP_TASK */ - #ifdef arch_scale_freq_capacity # ifndef arch_scale_freq_invariant # define arch_scale_freq_invariant() true @@ -3020,6 +2896,105 @@ static inline unsigned long cpu_util_rt(struct rq *rq) } #endif +#ifdef CONFIG_UCLAMP_TASK +unsigned long uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id); + +/** + * uclamp_rq_util_with - clamp @util with @rq and @p effective uclamp values. + * @rq: The rq to clamp against. Must not be NULL. + * @util: The util value to clamp. + * @p: The task to clamp against. Can be NULL if you want to clamp + * against @rq only. + * + * Clamps the passed @util to the max(@rq, @p) effective uclamp values. + * + * If sched_uclamp_used static key is disabled, then just return the util + * without any clamping since uclamp aggregation at the rq level in the fast + * path is disabled, rendering this operation a NOP. + * + * Use uclamp_eff_value() if you don't care about uclamp values at rq level. It + * will return the correct effective uclamp value of the task even if the + * static key is disabled. + */ +static __always_inline +unsigned long uclamp_rq_util_with(struct rq *rq, unsigned long util, + struct task_struct *p) +{ + unsigned long min_util = 0; + unsigned long max_util = 0; + + if (!static_branch_likely(&sched_uclamp_used)) + return util; + + if (p) { + min_util = uclamp_eff_value(p, UCLAMP_MIN); + max_util = uclamp_eff_value(p, UCLAMP_MAX); + + /* + * Ignore last runnable task's max clamp, as this task will + * reset it. Similarly, no need to read the rq's min clamp. + */ + if (rq->uclamp_flags & UCLAMP_FLAG_IDLE) + goto out; + } + + min_util = max_t(unsigned long, min_util, READ_ONCE(rq->uclamp[UCLAMP_MIN].value)); + max_util = max_t(unsigned long, max_util, READ_ONCE(rq->uclamp[UCLAMP_MAX].value)); +out: + /* + * Since CPU's {min,max}_util clamps are MAX aggregated considering + * RUNNABLE tasks with _different_ clamps, we can end up with an + * inversion. Fix it now when the clamps are applied. + */ + if (unlikely(min_util >= max_util)) + return min_util; + + return clamp(util, min_util, max_util); +} + +/* Is the rq being capped/throttled by uclamp_max? */ +static inline bool uclamp_rq_is_capped(struct rq *rq) +{ + unsigned long rq_util; + unsigned long max_util; + + if (!static_branch_likely(&sched_uclamp_used)) + return false; + + rq_util = cpu_util_cfs(cpu_of(rq)) + cpu_util_rt(rq); + max_util = READ_ONCE(rq->uclamp[UCLAMP_MAX].value); + + return max_util != SCHED_CAPACITY_SCALE && rq_util >= max_util; +} + +/* + * When uclamp is compiled in, the aggregation at rq level is 'turned off' + * by default in the fast path and only gets turned on once userspace performs + * an operation that requires it. + * + * Returns true if userspace opted-in to use uclamp and aggregation at rq level + * hence is active. + */ +static inline bool uclamp_is_used(void) +{ + return static_branch_likely(&sched_uclamp_used); +} +#else /* CONFIG_UCLAMP_TASK */ +static inline +unsigned long uclamp_rq_util_with(struct rq *rq, unsigned long util, + struct task_struct *p) +{ + return util; +} + +static inline bool uclamp_rq_is_capped(struct rq *rq) { return false; } + +static inline bool uclamp_is_used(void) +{ + return false; +} +#endif /* CONFIG_UCLAMP_TASK */ + #ifdef CONFIG_HAVE_SCHED_AVG_IRQ static inline unsigned long cpu_util_irq(struct rq *rq) { @@ -3118,3 +3093,4 @@ extern int sched_dynamic_mode(const char *str); extern void sched_dynamic_update(int mode); #endif +#endif /* _KERNEL_SCHED_SCHED_H */ diff --git a/kernel/sched/stats.c b/kernel/sched/stats.c index 07dde2928c79..857f837f52cb 100644 --- a/kernel/sched/stats.c +++ b/kernel/sched/stats.c @@ -2,7 +2,6 @@ /* * /proc/schedstat implementation */ -#include "sched.h" void __update_stats_wait_start(struct rq *rq, struct task_struct *p, struct sched_statistics *stats) diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h index 3a3c826dd83a..baa839c1ba96 100644 --- a/kernel/sched/stats.h +++ b/kernel/sched/stats.h @@ -1,4 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _KERNEL_STATS_H +#define _KERNEL_STATS_H #ifdef CONFIG_SCHEDSTATS @@ -298,3 +300,5 @@ sched_info_switch(struct rq *rq, struct task_struct *prev, struct task_struct *n # define sched_info_dequeue(rq, t) do { } while (0) # define sched_info_switch(rq, t, next) do { } while (0) #endif /* CONFIG_SCHED_INFO */ + +#endif /* _KERNEL_STATS_H */ diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c index 0b165a25f22f..d04073a93eb4 100644 --- a/kernel/sched/stop_task.c +++ b/kernel/sched/stop_task.c @@ -7,7 +7,6 @@ * * See kernel/stop_machine.c */ -#include "sched.h" #ifdef CONFIG_SMP static int diff --git a/kernel/sched/swait.c b/kernel/sched/swait.c index e1c655f928c7..76b9b796e695 100644 --- a/kernel/sched/swait.c +++ b/kernel/sched/swait.c @@ -2,7 +2,6 @@ /* * <linux/swait.h> (simple wait queues ) implementation: */ -#include "sched.h" void __init_swait_queue_head(struct swait_queue_head *q, const char *name, struct lock_class_key *key) diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index d201a7052a29..810750e62118 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -2,7 +2,6 @@ /* * Scheduler topology setup/handling methods */ -#include "sched.h" DEFINE_MUTEX(sched_domains_mutex); @@ -74,7 +73,7 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, break; } - if (!cpumask_weight(sched_group_span(group))) { + if (cpumask_empty(sched_group_span(group))) { printk(KERN_CONT "\n"); printk(KERN_ERR "ERROR: empty group\n"); break; @@ -1366,7 +1365,7 @@ static void asym_cpu_capacity_scan(void) list_for_each_entry(entry, &asym_cap_list, link) cpumask_clear(cpu_capacity_span(entry)); - for_each_cpu_and(cpu, cpu_possible_mask, housekeeping_cpumask(HK_FLAG_DOMAIN)) + for_each_cpu_and(cpu, cpu_possible_mask, housekeeping_cpumask(HK_TYPE_DOMAIN)) asym_cpu_capacity_update_data(cpu); list_for_each_entry_safe(entry, next, &asym_cap_list, link) { @@ -1492,8 +1491,6 @@ static int sched_domains_curr_level; int sched_max_numa_distance; static int *sched_domains_numa_distance; static struct cpumask ***sched_domains_numa_masks; - -static unsigned long __read_mostly *sched_numa_onlined_nodes; #endif /* @@ -1651,6 +1648,7 @@ static struct sched_domain_topology_level default_topology[] = { static struct sched_domain_topology_level *sched_domain_topology = default_topology; +static struct sched_domain_topology_level *sched_domain_topology_saved; #define for_each_sd_topology(tl) \ for (tl = sched_domain_topology; tl->mask; tl++) @@ -1661,6 +1659,7 @@ void set_sched_topology(struct sched_domain_topology_level *tl) return; sched_domain_topology = tl; + sched_domain_topology_saved = NULL; } #ifdef CONFIG_NUMA @@ -1684,8 +1683,12 @@ static void sched_numa_warn(const char *str) for (i = 0; i < nr_node_ids; i++) { printk(KERN_WARNING " "); - for (j = 0; j < nr_node_ids; j++) - printk(KERN_CONT "%02d ", node_distance(i,j)); + for (j = 0; j < nr_node_ids; j++) { + if (!node_state(i, N_CPU) || !node_state(j, N_CPU)) + printk(KERN_CONT "(%02d) ", node_distance(i,j)); + else + printk(KERN_CONT " %02d ", node_distance(i,j)); + } printk(KERN_CONT "\n"); } printk(KERN_WARNING "\n"); @@ -1693,19 +1696,34 @@ static void sched_numa_warn(const char *str) bool find_numa_distance(int distance) { - int i; + bool found = false; + int i, *distances; if (distance == node_distance(0, 0)) return true; + rcu_read_lock(); + distances = rcu_dereference(sched_domains_numa_distance); + if (!distances) + goto unlock; for (i = 0; i < sched_domains_numa_levels; i++) { - if (sched_domains_numa_distance[i] == distance) - return true; + if (distances[i] == distance) { + found = true; + break; + } } +unlock: + rcu_read_unlock(); - return false; + return found; } +#define for_each_cpu_node_but(n, nbut) \ + for_each_node_state(n, N_CPU) \ + if (n == nbut) \ + continue; \ + else + /* * A system can have three types of NUMA topology: * NUMA_DIRECT: all nodes are directly connected, or not a NUMA system @@ -1725,7 +1743,7 @@ bool find_numa_distance(int distance) * there is an intermediary node C, which is < N hops away from both * nodes A and B, the system is a glueless mesh. */ -static void init_numa_topology_type(void) +static void init_numa_topology_type(int offline_node) { int a, b, c, n; @@ -1736,14 +1754,14 @@ static void init_numa_topology_type(void) return; } - for_each_online_node(a) { - for_each_online_node(b) { + for_each_cpu_node_but(a, offline_node) { + for_each_cpu_node_but(b, offline_node) { /* Find two nodes furthest removed from each other. */ if (node_distance(a, b) < n) continue; /* Is there an intermediary node between a and b? */ - for_each_online_node(c) { + for_each_cpu_node_but(c, offline_node) { if (node_distance(a, c) < n && node_distance(b, c) < n) { sched_numa_topology_type = @@ -1756,17 +1774,22 @@ static void init_numa_topology_type(void) return; } } + + pr_err("Failed to find a NUMA topology type, defaulting to DIRECT\n"); + sched_numa_topology_type = NUMA_DIRECT; } #define NR_DISTANCE_VALUES (1 << DISTANCE_BITS) -void sched_init_numa(void) +void sched_init_numa(int offline_node) { struct sched_domain_topology_level *tl; unsigned long *distance_map; int nr_levels = 0; int i, j; + int *distances; + struct cpumask ***masks; /* * O(nr_nodes^2) deduplicating selection sort -- in order to find the @@ -1777,12 +1800,13 @@ void sched_init_numa(void) return; bitmap_zero(distance_map, NR_DISTANCE_VALUES); - for (i = 0; i < nr_node_ids; i++) { - for (j = 0; j < nr_node_ids; j++) { + for_each_cpu_node_but(i, offline_node) { + for_each_cpu_node_but(j, offline_node) { int distance = node_distance(i, j); if (distance < LOCAL_DISTANCE || distance >= NR_DISTANCE_VALUES) { sched_numa_warn("Invalid distance value range"); + bitmap_free(distance_map); return; } @@ -1795,16 +1819,17 @@ void sched_init_numa(void) */ nr_levels = bitmap_weight(distance_map, NR_DISTANCE_VALUES); - sched_domains_numa_distance = kcalloc(nr_levels, sizeof(int), GFP_KERNEL); - if (!sched_domains_numa_distance) { + distances = kcalloc(nr_levels, sizeof(int), GFP_KERNEL); + if (!distances) { bitmap_free(distance_map); return; } for (i = 0, j = 0; i < nr_levels; i++, j++) { j = find_next_bit(distance_map, NR_DISTANCE_VALUES, j); - sched_domains_numa_distance[i] = j; + distances[i] = j; } + rcu_assign_pointer(sched_domains_numa_distance, distances); bitmap_free(distance_map); @@ -1826,8 +1851,8 @@ void sched_init_numa(void) */ sched_domains_numa_levels = 0; - sched_domains_numa_masks = kzalloc(sizeof(void *) * nr_levels, GFP_KERNEL); - if (!sched_domains_numa_masks) + masks = kzalloc(sizeof(void *) * nr_levels, GFP_KERNEL); + if (!masks) return; /* @@ -1835,31 +1860,20 @@ void sched_init_numa(void) * CPUs of nodes that are that many hops away from us. */ for (i = 0; i < nr_levels; i++) { - sched_domains_numa_masks[i] = - kzalloc(nr_node_ids * sizeof(void *), GFP_KERNEL); - if (!sched_domains_numa_masks[i]) + masks[i] = kzalloc(nr_node_ids * sizeof(void *), GFP_KERNEL); + if (!masks[i]) return; - for (j = 0; j < nr_node_ids; j++) { + for_each_cpu_node_but(j, offline_node) { struct cpumask *mask = kzalloc(cpumask_size(), GFP_KERNEL); int k; if (!mask) return; - sched_domains_numa_masks[i][j] = mask; - - for_each_node(k) { - /* - * Distance information can be unreliable for - * offline nodes, defer building the node - * masks to its bringup. - * This relies on all unique distance values - * still being visible at init time. - */ - if (!node_online(j)) - continue; + masks[i][j] = mask; + for_each_cpu_node_but(k, offline_node) { if (sched_debug() && (node_distance(j, k) != node_distance(k, j))) sched_numa_warn("Node-distance not symmetric"); @@ -1870,6 +1884,7 @@ void sched_init_numa(void) } } } + rcu_assign_pointer(sched_domains_numa_masks, masks); /* Compute default topology size */ for (i = 0; sched_domain_topology[i].mask; i++); @@ -1907,59 +1922,67 @@ void sched_init_numa(void) }; } + sched_domain_topology_saved = sched_domain_topology; sched_domain_topology = tl; sched_domains_numa_levels = nr_levels; - sched_max_numa_distance = sched_domains_numa_distance[nr_levels - 1]; + WRITE_ONCE(sched_max_numa_distance, sched_domains_numa_distance[nr_levels - 1]); - init_numa_topology_type(); - - sched_numa_onlined_nodes = bitmap_alloc(nr_node_ids, GFP_KERNEL); - if (!sched_numa_onlined_nodes) - return; - - bitmap_zero(sched_numa_onlined_nodes, nr_node_ids); - for_each_online_node(i) - bitmap_set(sched_numa_onlined_nodes, i, 1); + init_numa_topology_type(offline_node); } -static void __sched_domains_numa_masks_set(unsigned int node) -{ - int i, j; - - /* - * NUMA masks are not built for offline nodes in sched_init_numa(). - * Thus, when a CPU of a never-onlined-before node gets plugged in, - * adding that new CPU to the right NUMA masks is not sufficient: the - * masks of that CPU's node must also be updated. - */ - if (test_bit(node, sched_numa_onlined_nodes)) - return; - bitmap_set(sched_numa_onlined_nodes, node, 1); - - for (i = 0; i < sched_domains_numa_levels; i++) { - for (j = 0; j < nr_node_ids; j++) { - if (!node_online(j) || node == j) - continue; +static void sched_reset_numa(void) +{ + int nr_levels, *distances; + struct cpumask ***masks; - if (node_distance(j, node) > sched_domains_numa_distance[i]) + nr_levels = sched_domains_numa_levels; + sched_domains_numa_levels = 0; + sched_max_numa_distance = 0; + sched_numa_topology_type = NUMA_DIRECT; + distances = sched_domains_numa_distance; + rcu_assign_pointer(sched_domains_numa_distance, NULL); + masks = sched_domains_numa_masks; + rcu_assign_pointer(sched_domains_numa_masks, NULL); + if (distances || masks) { + int i, j; + + synchronize_rcu(); + kfree(distances); + for (i = 0; i < nr_levels && masks; i++) { + if (!masks[i]) continue; - - /* Add remote nodes in our masks */ - cpumask_or(sched_domains_numa_masks[i][node], - sched_domains_numa_masks[i][node], - sched_domains_numa_masks[0][j]); + for_each_node(j) + kfree(masks[i][j]); + kfree(masks[i]); } + kfree(masks); + } + if (sched_domain_topology_saved) { + kfree(sched_domain_topology); + sched_domain_topology = sched_domain_topology_saved; + sched_domain_topology_saved = NULL; } +} +/* + * Call with hotplug lock held + */ +void sched_update_numa(int cpu, bool online) +{ + int node; + + node = cpu_to_node(cpu); /* - * A new node has been brought up, potentially changing the topology - * classification. - * - * Note that this is racy vs any use of sched_numa_topology_type :/ + * Scheduler NUMA topology is updated when the first CPU of a + * node is onlined or the last CPU of a node is offlined. */ - init_numa_topology_type(); + if (cpumask_weight(cpumask_of_node(node)) != 1) + return; + + sched_reset_numa(); + sched_init_numa(online ? NUMA_NO_NODE : node); } void sched_domains_numa_masks_set(unsigned int cpu) @@ -1967,11 +1990,9 @@ void sched_domains_numa_masks_set(unsigned int cpu) int node = cpu_to_node(cpu); int i, j; - __sched_domains_numa_masks_set(node); - for (i = 0; i < sched_domains_numa_levels; i++) { for (j = 0; j < nr_node_ids; j++) { - if (!node_online(j)) + if (!node_state(j, N_CPU)) continue; /* Set ourselves in the remote node's masks */ @@ -1986,8 +2007,10 @@ void sched_domains_numa_masks_clear(unsigned int cpu) int i, j; for (i = 0; i < sched_domains_numa_levels; i++) { - for (j = 0; j < nr_node_ids; j++) - cpumask_clear_cpu(cpu, sched_domains_numa_masks[i][j]); + for (j = 0; j < nr_node_ids; j++) { + if (sched_domains_numa_masks[i][j]) + cpumask_clear_cpu(cpu, sched_domains_numa_masks[i][j]); + } } } @@ -2001,14 +2024,26 @@ void sched_domains_numa_masks_clear(unsigned int cpu) */ int sched_numa_find_closest(const struct cpumask *cpus, int cpu) { - int i, j = cpu_to_node(cpu); + int i, j = cpu_to_node(cpu), found = nr_cpu_ids; + struct cpumask ***masks; + rcu_read_lock(); + masks = rcu_dereference(sched_domains_numa_masks); + if (!masks) + goto unlock; for (i = 0; i < sched_domains_numa_levels; i++) { - cpu = cpumask_any_and(cpus, sched_domains_numa_masks[i][j]); - if (cpu < nr_cpu_ids) - return cpu; + if (!masks[i][j]) + break; + cpu = cpumask_any_and(cpus, masks[i][j]); + if (cpu < nr_cpu_ids) { + found = cpu; + break; + } } - return nr_cpu_ids; +unlock: + rcu_read_unlock(); + + return found; } #endif /* CONFIG_NUMA */ @@ -2242,6 +2277,57 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att } } + /* + * Calculate an allowed NUMA imbalance such that LLCs do not get + * imbalanced. + */ + for_each_cpu(i, cpu_map) { + unsigned int imb = 0; + unsigned int imb_span = 1; + + for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) { + struct sched_domain *child = sd->child; + + if (!(sd->flags & SD_SHARE_PKG_RESOURCES) && child && + (child->flags & SD_SHARE_PKG_RESOURCES)) { + struct sched_domain __rcu *top_p; + unsigned int nr_llcs; + + /* + * For a single LLC per node, allow an + * imbalance up to 25% of the node. This is an + * arbitrary cutoff based on SMT-2 to balance + * between memory bandwidth and avoiding + * premature sharing of HT resources and SMT-4 + * or SMT-8 *may* benefit from a different + * cutoff. + * + * For multiple LLCs, allow an imbalance + * until multiple tasks would share an LLC + * on one node while LLCs on another node + * remain idle. + */ + nr_llcs = sd->span_weight / child->span_weight; + if (nr_llcs == 1) + imb = sd->span_weight >> 2; + else + imb = nr_llcs; + sd->imb_numa_nr = imb; + + /* Set span based on the first NUMA domain. */ + top_p = sd->parent; + while (top_p && !(top_p->flags & SD_NUMA)) { + top_p = top_p->parent; + } + imb_span = top_p ? top_p->span_weight : sd->span_weight; + } else { + int factor = max(1U, (sd->span_weight / imb_span)); + + sd->imb_numa_nr = imb * factor; + } + } + } + /* Calculate CPU capacity for physical packages and nodes */ for (i = nr_cpumask_bits-1; i >= 0; i--) { if (!cpumask_test_cpu(i, cpu_map)) @@ -2351,7 +2437,7 @@ int sched_init_domains(const struct cpumask *cpu_map) doms_cur = alloc_sched_domains(ndoms_cur); if (!doms_cur) doms_cur = &fallback_doms; - cpumask_and(doms_cur[0], cpu_map, housekeeping_cpumask(HK_FLAG_DOMAIN)); + cpumask_and(doms_cur[0], cpu_map, housekeeping_cpumask(HK_TYPE_DOMAIN)); err = build_sched_domains(doms_cur[0], NULL); return err; @@ -2440,7 +2526,7 @@ void partition_sched_domains_locked(int ndoms_new, cpumask_var_t doms_new[], if (doms_new) { n = 1; cpumask_and(doms_new[0], cpu_active_mask, - housekeeping_cpumask(HK_FLAG_DOMAIN)); + housekeeping_cpumask(HK_TYPE_DOMAIN)); } } else { n = ndoms_new; @@ -2475,7 +2561,7 @@ match1: n = 0; doms_new = &fallback_doms; cpumask_and(doms_new[0], cpu_active_mask, - housekeeping_cpumask(HK_FLAG_DOMAIN)); + housekeeping_cpumask(HK_TYPE_DOMAIN)); } /* Build new domains: */ diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c index eca38107b32f..9860bb9a847c 100644 --- a/kernel/sched/wait.c +++ b/kernel/sched/wait.c @@ -4,7 +4,6 @@ * * (C) 2004 Nadia Yvette Chambers, Oracle */ -#include "sched.h" void __init_waitqueue_head(struct wait_queue_head *wq_head, const char *name, struct lock_class_key *key) { diff --git a/kernel/sched/wait_bit.c b/kernel/sched/wait_bit.c index 02ce292b9bc0..d4788f810b55 100644 --- a/kernel/sched/wait_bit.c +++ b/kernel/sched/wait_bit.c @@ -1,8 +1,8 @@ // SPDX-License-Identifier: GPL-2.0-only + /* * The implementation of the wait_bit*() and related waiting APIs: */ -#include "sched.h" #define WAIT_TABLE_BITS 8 #define WAIT_TABLE_SIZE (1 << WAIT_TABLE_BITS) diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 730ab56d9e92..5ec3494b829b 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1757,17 +1757,6 @@ static struct ctl_table kern_table[] = { .proc_handler = sysctl_sched_uclamp_handler, }, #endif -#ifdef CONFIG_SCHED_AUTOGROUP - { - .procname = "sched_autogroup_enabled", - .data = &sysctl_sched_autogroup_enabled, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, -#endif #ifdef CONFIG_CFS_BANDWIDTH { .procname = "sched_cfs_bandwidth_slice_us", diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c index 22061d38fc00..19028e072cdb 100644 --- a/kernel/trace/fgraph.c +++ b/kernel/trace/fgraph.c @@ -415,7 +415,9 @@ free: static void ftrace_graph_probe_sched_switch(void *ignore, bool preempt, - struct task_struct *prev, struct task_struct *next) + unsigned int prev_state, + struct task_struct *prev, + struct task_struct *next) { unsigned long long timestamp; int index; diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 6105b7036482..8b568f57cc24 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -7346,7 +7346,9 @@ ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops) static void ftrace_filter_pid_sched_switch_probe(void *data, bool preempt, - struct task_struct *prev, struct task_struct *next) + unsigned int prev_state, + struct task_struct *prev, + struct task_struct *next) { struct trace_array *tr = data; struct trace_pid_list *pid_list; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index f527ae807e77..da69519c4905 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -765,7 +765,9 @@ void trace_event_follow_fork(struct trace_array *tr, bool enable) static void event_filter_pid_sched_switch_probe_pre(void *data, bool preempt, - struct task_struct *prev, struct task_struct *next) + unsigned int prev_state, + struct task_struct *prev, + struct task_struct *next) { struct trace_array *tr = data; struct trace_pid_list *no_pid_list; @@ -789,7 +791,9 @@ event_filter_pid_sched_switch_probe_pre(void *data, bool preempt, static void event_filter_pid_sched_switch_probe_post(void *data, bool preempt, - struct task_struct *prev, struct task_struct *next) + unsigned int prev_state, + struct task_struct *prev, + struct task_struct *next) { struct trace_array *tr = data; struct trace_pid_list *no_pid_list; diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c index 5e3c62a08fc0..e9ae1f33a7f0 100644 --- a/kernel/trace/trace_osnoise.c +++ b/kernel/trace/trace_osnoise.c @@ -1167,7 +1167,9 @@ thread_exit(struct osnoise_variables *osn_var, struct task_struct *t) * used to record the beginning and to report the end of a thread noise window. */ static void -trace_sched_switch_callback(void *data, bool preempt, struct task_struct *p, +trace_sched_switch_callback(void *data, bool preempt, + unsigned int prev_state, + struct task_struct *p, struct task_struct *n) { struct osnoise_variables *osn_var = this_cpu_osn_var(); diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c index e304196d7c28..993b0ed10d8c 100644 --- a/kernel/trace/trace_sched_switch.c +++ b/kernel/trace/trace_sched_switch.c @@ -22,6 +22,7 @@ static DEFINE_MUTEX(sched_register_mutex); static void probe_sched_switch(void *ignore, bool preempt, + unsigned int prev_state, struct task_struct *prev, struct task_struct *next) { int flags; diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index 2402de520eca..46429f9a96fa 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -426,6 +426,7 @@ tracing_sched_wakeup_trace(struct trace_array *tr, static void notrace probe_wakeup_sched_switch(void *ignore, bool preempt, + unsigned int prev_state, struct task_struct *prev, struct task_struct *next) { struct trace_array_cpu *data; diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 99afb88d2e85..9166220457bc 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -848,7 +848,7 @@ void __init lockup_detector_init(void) pr_info("Disabling watchdog on nohz_full cores by default\n"); cpumask_copy(&watchdog_cpumask, - housekeeping_cpumask(HK_FLAG_TIMER)); + housekeeping_cpumask(HK_TYPE_TIMER)); if (!watchdog_nmi_probe()) nmi_watchdog_available = true; diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 33f1106b4f99..52e9abbb7759 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -6006,13 +6006,13 @@ static void __init wq_numa_init(void) void __init workqueue_init_early(void) { int std_nice[NR_STD_WORKER_POOLS] = { 0, HIGHPRI_NICE_LEVEL }; - int hk_flags = HK_FLAG_DOMAIN | HK_FLAG_WQ; int i, cpu; BUILD_BUG_ON(__alignof__(struct pool_workqueue) < __alignof__(long long)); BUG_ON(!alloc_cpumask_var(&wq_unbound_cpumask, GFP_KERNEL)); - cpumask_copy(wq_unbound_cpumask, housekeeping_cpumask(hk_flags)); + cpumask_copy(wq_unbound_cpumask, housekeeping_cpumask(HK_TYPE_WQ)); + cpumask_and(wq_unbound_cpumask, wq_unbound_cpumask, housekeeping_cpumask(HK_TYPE_DOMAIN)); pwq_cache = KMEM_CACHE(pool_workqueue, SLAB_PANIC); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index fbddf966206b..9cbc1c8289bc 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -823,7 +823,7 @@ static ssize_t store_rps_map(struct netdev_rx_queue *queue, { struct rps_map *old_map, *map; cpumask_var_t mask; - int err, cpu, i, hk_flags; + int err, cpu, i; static DEFINE_MUTEX(rps_map_mutex); if (!capable(CAP_NET_ADMIN)) @@ -839,8 +839,8 @@ static ssize_t store_rps_map(struct netdev_rx_queue *queue, } if (!cpumask_empty(mask)) { - hk_flags = HK_FLAG_DOMAIN | HK_FLAG_WQ; - cpumask_and(mask, mask, housekeeping_cpumask(hk_flags)); + cpumask_and(mask, mask, housekeeping_cpumask(HK_TYPE_DOMAIN)); + cpumask_and(mask, mask, housekeeping_cpumask(HK_TYPE_WQ)); if (cpumask_empty(mask)) { free_cpumask_var(mask); return -EINVAL; diff --git a/scripts/mkcompile_h b/scripts/mkcompile_h index 6a2a04d92f42..ca40a5258c87 100755 --- a/scripts/mkcompile_h +++ b/scripts/mkcompile_h @@ -5,9 +5,10 @@ TARGET=$1 ARCH=$2 SMP=$3 PREEMPT=$4 -PREEMPT_RT=$5 -CC_VERSION="$6" -LD=$7 +PREEMPT_DYNAMIC=$5 +PREEMPT_RT=$6 +CC_VERSION="$7" +LD=$8 # Do not expand names set -f @@ -41,8 +42,14 @@ fi UTS_VERSION="#$VERSION" CONFIG_FLAGS="" if [ -n "$SMP" ] ; then CONFIG_FLAGS="SMP"; fi -if [ -n "$PREEMPT" ] ; then CONFIG_FLAGS="$CONFIG_FLAGS PREEMPT"; fi -if [ -n "$PREEMPT_RT" ] ; then CONFIG_FLAGS="$CONFIG_FLAGS PREEMPT_RT"; fi + +if [ -n "$PREEMPT_RT" ] ; then + CONFIG_FLAGS="$CONFIG_FLAGS PREEMPT_RT" +elif [ -n "$PREEMPT_DYNAMIC" ] ; then + CONFIG_FLAGS="$CONFIG_FLAGS PREEMPT_DYNAMIC" +elif [ -n "$PREEMPT" ] ; then + CONFIG_FLAGS="$CONFIG_FLAGS PREEMPT" +fi # Truncate to maximum length UTS_LEN=64 diff --git a/tools/testing/selftests/rseq/Makefile b/tools/testing/selftests/rseq/Makefile index 2af9d39a9716..215e1067f037 100644 --- a/tools/testing/selftests/rseq/Makefile +++ b/tools/testing/selftests/rseq/Makefile @@ -6,7 +6,7 @@ endif CFLAGS += -O2 -Wall -g -I./ -I../../../../usr/include/ -L$(OUTPUT) -Wl,-rpath=./ \ $(CLANG_FLAGS) -LDLIBS += -lpthread +LDLIBS += -lpthread -ldl # Own dependencies because we only want to build against 1st prerequisite, but # still track changes to header files and depend on shared object. diff --git a/tools/testing/selftests/rseq/basic_percpu_ops_test.c b/tools/testing/selftests/rseq/basic_percpu_ops_test.c index b953a52ff706..517756afc2a4 100644 --- a/tools/testing/selftests/rseq/basic_percpu_ops_test.c +++ b/tools/testing/selftests/rseq/basic_percpu_ops_test.c @@ -167,7 +167,7 @@ struct percpu_list_node *this_cpu_list_pop(struct percpu_list *list, for (;;) { struct percpu_list_node *head; intptr_t *targetptr, expectnot, *load; - off_t offset; + long offset; int ret, cpu; cpu = rseq_cpu_start(); diff --git a/tools/testing/selftests/rseq/compiler.h b/tools/testing/selftests/rseq/compiler.h new file mode 100644 index 000000000000..876eb6a7f75b --- /dev/null +++ b/tools/testing/selftests/rseq/compiler.h @@ -0,0 +1,30 @@ +/* SPDX-License-Identifier: LGPL-2.1-only OR MIT */ +/* + * rseq/compiler.h + * + * Work-around asm goto compiler bugs. + * + * (C) Copyright 2021 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com> + */ + +#ifndef RSEQ_COMPILER_H +#define RSEQ_COMPILER_H + +/* + * gcc prior to 4.8.2 miscompiles asm goto. + * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58670 + * + * gcc prior to 8.1.0 miscompiles asm goto at O1. + * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=103908 + * + * clang prior to version 13.0.1 miscompiles asm goto at O2. + * https://github.com/llvm/llvm-project/issues/52735 + * + * Work around these issues by adding a volatile inline asm with + * memory clobber in the fallthrough after the asm goto and at each + * label target. Emit this for all compilers in case other similar + * issues are found in the future. + */ +#define rseq_after_asm_goto() asm volatile ("" : : : "memory") + +#endif /* RSEQ_COMPILER_H_ */ diff --git a/tools/testing/selftests/rseq/param_test.c b/tools/testing/selftests/rseq/param_test.c index 699ad5f93c34..da23c22d5882 100644 --- a/tools/testing/selftests/rseq/param_test.c +++ b/tools/testing/selftests/rseq/param_test.c @@ -161,7 +161,7 @@ unsigned int yield_mod_cnt, nr_abort; " cbnz " INJECT_ASM_REG ", 222b\n" \ "333:\n" -#elif __PPC__ +#elif defined(__PPC__) #define RSEQ_INJECT_INPUT \ , [loop_cnt_1]"m"(loop_cnt[1]) \ @@ -368,9 +368,7 @@ void *test_percpu_spinlock_thread(void *arg) abort(); reps = thread_data->reps; for (i = 0; i < reps; i++) { - int cpu = rseq_cpu_start(); - - cpu = rseq_this_cpu_lock(&data->lock); + int cpu = rseq_this_cpu_lock(&data->lock); data->c[cpu].count++; rseq_percpu_unlock(&data->lock, cpu); #ifndef BENCHMARK @@ -551,7 +549,7 @@ struct percpu_list_node *this_cpu_list_pop(struct percpu_list *list, for (;;) { struct percpu_list_node *head; intptr_t *targetptr, expectnot, *load; - off_t offset; + long offset; int ret; cpu = rseq_cpu_start(); diff --git a/tools/testing/selftests/rseq/rseq-abi.h b/tools/testing/selftests/rseq/rseq-abi.h new file mode 100644 index 000000000000..a8c44d9af71f --- /dev/null +++ b/tools/testing/selftests/rseq/rseq-abi.h @@ -0,0 +1,151 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ +#ifndef _RSEQ_ABI_H +#define _RSEQ_ABI_H + +/* + * rseq-abi.h + * + * Restartable sequences system call API + * + * Copyright (c) 2015-2022 Mathieu Desnoyers <mathieu.desnoyers@efficios.com> + */ + +#include <linux/types.h> +#include <asm/byteorder.h> + +enum rseq_abi_cpu_id_state { + RSEQ_ABI_CPU_ID_UNINITIALIZED = -1, + RSEQ_ABI_CPU_ID_REGISTRATION_FAILED = -2, +}; + +enum rseq_abi_flags { + RSEQ_ABI_FLAG_UNREGISTER = (1 << 0), +}; + +enum rseq_abi_cs_flags_bit { + RSEQ_ABI_CS_FLAG_NO_RESTART_ON_PREEMPT_BIT = 0, + RSEQ_ABI_CS_FLAG_NO_RESTART_ON_SIGNAL_BIT = 1, + RSEQ_ABI_CS_FLAG_NO_RESTART_ON_MIGRATE_BIT = 2, +}; + +enum rseq_abi_cs_flags { + RSEQ_ABI_CS_FLAG_NO_RESTART_ON_PREEMPT = + (1U << RSEQ_ABI_CS_FLAG_NO_RESTART_ON_PREEMPT_BIT), + RSEQ_ABI_CS_FLAG_NO_RESTART_ON_SIGNAL = + (1U << RSEQ_ABI_CS_FLAG_NO_RESTART_ON_SIGNAL_BIT), + RSEQ_ABI_CS_FLAG_NO_RESTART_ON_MIGRATE = + (1U << RSEQ_ABI_CS_FLAG_NO_RESTART_ON_MIGRATE_BIT), +}; + +/* + * struct rseq_abi_cs is aligned on 4 * 8 bytes to ensure it is always + * contained within a single cache-line. It is usually declared as + * link-time constant data. + */ +struct rseq_abi_cs { + /* Version of this structure. */ + __u32 version; + /* enum rseq_abi_cs_flags */ + __u32 flags; + __u64 start_ip; + /* Offset from start_ip. */ + __u64 post_commit_offset; + __u64 abort_ip; +} __attribute__((aligned(4 * sizeof(__u64)))); + +/* + * struct rseq_abi is aligned on 4 * 8 bytes to ensure it is always + * contained within a single cache-line. + * + * A single struct rseq_abi per thread is allowed. + */ +struct rseq_abi { + /* + * Restartable sequences cpu_id_start field. Updated by the + * kernel. Read by user-space with single-copy atomicity + * semantics. This field should only be read by the thread which + * registered this data structure. Aligned on 32-bit. Always + * contains a value in the range of possible CPUs, although the + * value may not be the actual current CPU (e.g. if rseq is not + * initialized). This CPU number value should always be compared + * against the value of the cpu_id field before performing a rseq + * commit or returning a value read from a data structure indexed + * using the cpu_id_start value. + */ + __u32 cpu_id_start; + /* + * Restartable sequences cpu_id field. Updated by the kernel. + * Read by user-space with single-copy atomicity semantics. This + * field should only be read by the thread which registered this + * data structure. Aligned on 32-bit. Values + * RSEQ_CPU_ID_UNINITIALIZED and RSEQ_CPU_ID_REGISTRATION_FAILED + * have a special semantic: the former means "rseq uninitialized", + * and latter means "rseq initialization failed". This value is + * meant to be read within rseq critical sections and compared + * with the cpu_id_start value previously read, before performing + * the commit instruction, or read and compared with the + * cpu_id_start value before returning a value loaded from a data + * structure indexed using the cpu_id_start value. + */ + __u32 cpu_id; + /* + * Restartable sequences rseq_cs field. + * + * Contains NULL when no critical section is active for the current + * thread, or holds a pointer to the currently active struct rseq_cs. + * + * Updated by user-space, which sets the address of the currently + * active rseq_cs at the beginning of assembly instruction sequence + * block, and set to NULL by the kernel when it restarts an assembly + * instruction sequence block, as well as when the kernel detects that + * it is preempting or delivering a signal outside of the range + * targeted by the rseq_cs. Also needs to be set to NULL by user-space + * before reclaiming memory that contains the targeted struct rseq_cs. + * + * Read and set by the kernel. Set by user-space with single-copy + * atomicity semantics. This field should only be updated by the + * thread which registered this data structure. Aligned on 64-bit. + */ + union { + __u64 ptr64; + + /* + * The "arch" field provides architecture accessor for + * the ptr field based on architecture pointer size and + * endianness. + */ + struct { +#ifdef __LP64__ + __u64 ptr; +#elif defined(__BYTE_ORDER) ? (__BYTE_ORDER == __BIG_ENDIAN) : defined(__BIG_ENDIAN) + __u32 padding; /* Initialized to zero. */ + __u32 ptr; +#else + __u32 ptr; + __u32 padding; /* Initialized to zero. */ +#endif + } arch; + } rseq_cs; + + /* + * Restartable sequences flags field. + * + * This field should only be updated by the thread which + * registered this data structure. Read by the kernel. + * Mainly used for single-stepping through rseq critical sections + * with debuggers. + * + * - RSEQ_ABI_CS_FLAG_NO_RESTART_ON_PREEMPT + * Inhibit instruction sequence block restart on preemption + * for this thread. + * - RSEQ_ABI_CS_FLAG_NO_RESTART_ON_SIGNAL + * Inhibit instruction sequence block restart on signal + * delivery for this thread. + * - RSEQ_ABI_CS_FLAG_NO_RESTART_ON_MIGRATE + * Inhibit instruction sequence block restart on migration for + * this thread. + */ + __u32 flags; +} __attribute__((aligned(4 * sizeof(__u64)))); + +#endif /* _RSEQ_ABI_H */ diff --git a/tools/testing/selftests/rseq/rseq-arm.h b/tools/testing/selftests/rseq/rseq-arm.h index 5943c816c07c..893a11eca9d5 100644 --- a/tools/testing/selftests/rseq/rseq-arm.h +++ b/tools/testing/selftests/rseq/rseq-arm.h @@ -147,14 +147,11 @@ do { \ teardown \ "b %l[" __rseq_str(cmpfail_label) "]\n\t" -#define rseq_workaround_gcc_asm_size_guess() __asm__ __volatile__("") - static inline __attribute__((always_inline)) int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) { RSEQ_INJECT_C(9) - rseq_workaround_gcc_asm_size_guess(); __asm__ __volatile__ goto ( RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */ RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail]) @@ -185,8 +182,8 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) "5:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), [v] "m" (*v), [expect] "r" (expect), [newv] "r" (newv) @@ -198,30 +195,31 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) , error1, error2 #endif ); - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); return 0; abort: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } static inline __attribute__((always_inline)) int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, - off_t voffp, intptr_t *load, int cpu) + long voffp, intptr_t *load, int cpu) { RSEQ_INJECT_C(9) - rseq_workaround_gcc_asm_size_guess(); __asm__ __volatile__ goto ( RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */ RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail]) @@ -255,8 +253,8 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, "5:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* final store input */ [v] "m" (*v), [expectnot] "r" (expectnot), @@ -270,19 +268,21 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, , error1, error2 #endif ); - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); return 0; abort: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -292,7 +292,6 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu) { RSEQ_INJECT_C(9) - rseq_workaround_gcc_asm_size_guess(); __asm__ __volatile__ goto ( RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */ #ifdef RSEQ_COMPARE_TWICE @@ -316,8 +315,8 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu) "5:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), [v] "m" (*v), [count] "Ir" (count) RSEQ_INJECT_INPUT @@ -328,14 +327,15 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu) , error1 #endif ); - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); return 0; abort: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); #endif } @@ -347,7 +347,6 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, { RSEQ_INJECT_C(9) - rseq_workaround_gcc_asm_size_guess(); __asm__ __volatile__ goto ( RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */ RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail]) @@ -381,8 +380,8 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, "5:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* try store input */ [v2] "m" (*v2), [newv2] "r" (newv2), @@ -398,19 +397,21 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, , error1, error2 #endif ); - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); return 0; abort: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -422,7 +423,6 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect, { RSEQ_INJECT_C(9) - rseq_workaround_gcc_asm_size_guess(); __asm__ __volatile__ goto ( RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */ RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail]) @@ -457,8 +457,8 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect, "5:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* try store input */ [v2] "m" (*v2), [newv2] "r" (newv2), @@ -474,19 +474,21 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect, , error1, error2 #endif ); - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); return 0; abort: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -498,7 +500,6 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, { RSEQ_INJECT_C(9) - rseq_workaround_gcc_asm_size_guess(); __asm__ __volatile__ goto ( RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */ RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail]) @@ -537,8 +538,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, "5:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* cmp2 input */ [v2] "m" (*v2), [expect2] "r" (expect2), @@ -554,21 +555,24 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, , error1, error2, error3 #endif ); - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); return 0; abort: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("1st expected value comparison failed"); error3: + rseq_after_asm_goto(); rseq_bug("2nd expected value comparison failed"); #endif } @@ -582,7 +586,6 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, RSEQ_INJECT_C(9) - rseq_workaround_gcc_asm_size_guess(); __asm__ __volatile__ goto ( RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */ RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail]) @@ -657,8 +660,8 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, "8:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* final store input */ [v] "m" (*v), [expect] "r" (expect), @@ -678,21 +681,21 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, , error1, error2 #endif ); - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); return 0; abort: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -706,7 +709,6 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect, RSEQ_INJECT_C(9) - rseq_workaround_gcc_asm_size_guess(); __asm__ __volatile__ goto ( RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */ RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail]) @@ -782,8 +784,8 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect, "8:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* final store input */ [v] "m" (*v), [expect] "r" (expect), @@ -803,21 +805,21 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect, , error1, error2 #endif ); - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); return 0; abort: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } diff --git a/tools/testing/selftests/rseq/rseq-arm64.h b/tools/testing/selftests/rseq/rseq-arm64.h index 200dae9e4208..cbe190a4d005 100644 --- a/tools/testing/selftests/rseq/rseq-arm64.h +++ b/tools/testing/selftests/rseq/rseq-arm64.h @@ -230,8 +230,8 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "Qo" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "Qo" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), [v] "Qo" (*v), [expect] "r" (expect), [newv] "r" (newv) @@ -242,24 +242,28 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) , error1, error2 #endif ); - + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } static inline __attribute__((always_inline)) int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, - off_t voffp, intptr_t *load, int cpu) + long voffp, intptr_t *load, int cpu) { RSEQ_INJECT_C(9) @@ -287,8 +291,8 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "Qo" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "Qo" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), [v] "Qo" (*v), [expectnot] "r" (expectnot), [load] "Qo" (*load), @@ -300,16 +304,21 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -337,8 +346,8 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu) RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "Qo" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "Qo" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), [v] "Qo" (*v), [count] "r" (count) RSEQ_INJECT_INPUT @@ -348,12 +357,15 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu) , error1 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); #endif } @@ -388,8 +400,8 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "Qo" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "Qo" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), [expect] "r" (expect), [v] "Qo" (*v), [newv] "r" (newv), @@ -402,17 +414,21 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, , error1, error2 #endif ); - + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -447,8 +463,8 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "Qo" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "Qo" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), [expect] "r" (expect), [v] "Qo" (*v), [newv] "r" (newv), @@ -461,17 +477,21 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect, , error1, error2 #endif ); - + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -508,8 +528,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "Qo" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "Qo" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), [v] "Qo" (*v), [expect] "r" (expect), [v2] "Qo" (*v2), @@ -522,19 +542,24 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, , error1, error2, error3 #endif ); - + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); error3: + rseq_after_asm_goto(); rseq_bug("2nd expected value comparison failed"); #endif } @@ -569,8 +594,8 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "Qo" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "Qo" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), [expect] "r" (expect), [v] "Qo" (*v), [newv] "r" (newv), @@ -584,17 +609,21 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, , error1, error2 #endif ); - + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -629,8 +658,8 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "Qo" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "Qo" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), [expect] "r" (expect), [v] "Qo" (*v), [newv] "r" (newv), @@ -644,17 +673,21 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect, , error1, error2 #endif ); - + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } diff --git a/tools/testing/selftests/rseq/rseq-generic-thread-pointer.h b/tools/testing/selftests/rseq/rseq-generic-thread-pointer.h new file mode 100644 index 000000000000..38c584661571 --- /dev/null +++ b/tools/testing/selftests/rseq/rseq-generic-thread-pointer.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: LGPL-2.1-only OR MIT */ +/* + * rseq-generic-thread-pointer.h + * + * (C) Copyright 2021 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com> + */ + +#ifndef _RSEQ_GENERIC_THREAD_POINTER +#define _RSEQ_GENERIC_THREAD_POINTER + +#ifdef __cplusplus +extern "C" { +#endif + +/* Use gcc builtin thread pointer. */ +static inline void *rseq_thread_pointer(void) +{ + return __builtin_thread_pointer(); +} + +#ifdef __cplusplus +} +#endif + +#endif diff --git a/tools/testing/selftests/rseq/rseq-mips.h b/tools/testing/selftests/rseq/rseq-mips.h index e989e7c14b09..878739fae2fd 100644 --- a/tools/testing/selftests/rseq/rseq-mips.h +++ b/tools/testing/selftests/rseq/rseq-mips.h @@ -154,14 +154,11 @@ do { \ teardown \ "b %l[" __rseq_str(cmpfail_label) "]\n\t" -#define rseq_workaround_gcc_asm_size_guess() __asm__ __volatile__("") - static inline __attribute__((always_inline)) int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) { RSEQ_INJECT_C(9) - rseq_workaround_gcc_asm_size_guess(); __asm__ __volatile__ goto ( RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */ RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail]) @@ -190,8 +187,8 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) "5:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), [v] "m" (*v), [expect] "r" (expect), [newv] "r" (newv) @@ -203,14 +200,11 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) , error1, error2 #endif ); - rseq_workaround_gcc_asm_size_guess(); return 0; abort: - rseq_workaround_gcc_asm_size_guess(); RSEQ_INJECT_FAILED return -1; cmpfail: - rseq_workaround_gcc_asm_size_guess(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: @@ -222,11 +216,10 @@ error2: static inline __attribute__((always_inline)) int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, - off_t voffp, intptr_t *load, int cpu) + long voffp, intptr_t *load, int cpu) { RSEQ_INJECT_C(9) - rseq_workaround_gcc_asm_size_guess(); __asm__ __volatile__ goto ( RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */ RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail]) @@ -258,8 +251,8 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, "5:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* final store input */ [v] "m" (*v), [expectnot] "r" (expectnot), @@ -273,14 +266,11 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, , error1, error2 #endif ); - rseq_workaround_gcc_asm_size_guess(); return 0; abort: - rseq_workaround_gcc_asm_size_guess(); RSEQ_INJECT_FAILED return -1; cmpfail: - rseq_workaround_gcc_asm_size_guess(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: @@ -295,7 +285,6 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu) { RSEQ_INJECT_C(9) - rseq_workaround_gcc_asm_size_guess(); __asm__ __volatile__ goto ( RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */ #ifdef RSEQ_COMPARE_TWICE @@ -319,8 +308,8 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu) "5:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), [v] "m" (*v), [count] "Ir" (count) RSEQ_INJECT_INPUT @@ -331,10 +320,8 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu) , error1 #endif ); - rseq_workaround_gcc_asm_size_guess(); return 0; abort: - rseq_workaround_gcc_asm_size_guess(); RSEQ_INJECT_FAILED return -1; #ifdef RSEQ_COMPARE_TWICE @@ -350,7 +337,6 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, { RSEQ_INJECT_C(9) - rseq_workaround_gcc_asm_size_guess(); __asm__ __volatile__ goto ( RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */ RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail]) @@ -382,8 +368,8 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, "5:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* try store input */ [v2] "m" (*v2), [newv2] "r" (newv2), @@ -399,14 +385,11 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, , error1, error2 #endif ); - rseq_workaround_gcc_asm_size_guess(); return 0; abort: - rseq_workaround_gcc_asm_size_guess(); RSEQ_INJECT_FAILED return -1; cmpfail: - rseq_workaround_gcc_asm_size_guess(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: @@ -423,7 +406,6 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect, { RSEQ_INJECT_C(9) - rseq_workaround_gcc_asm_size_guess(); __asm__ __volatile__ goto ( RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */ RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail]) @@ -456,8 +438,8 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect, "5:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* try store input */ [v2] "m" (*v2), [newv2] "r" (newv2), @@ -473,14 +455,11 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect, , error1, error2 #endif ); - rseq_workaround_gcc_asm_size_guess(); return 0; abort: - rseq_workaround_gcc_asm_size_guess(); RSEQ_INJECT_FAILED return -1; cmpfail: - rseq_workaround_gcc_asm_size_guess(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: @@ -497,7 +476,6 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, { RSEQ_INJECT_C(9) - rseq_workaround_gcc_asm_size_guess(); __asm__ __volatile__ goto ( RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */ RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail]) @@ -532,8 +510,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, "5:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* cmp2 input */ [v2] "m" (*v2), [expect2] "r" (expect2), @@ -549,14 +527,11 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, , error1, error2, error3 #endif ); - rseq_workaround_gcc_asm_size_guess(); return 0; abort: - rseq_workaround_gcc_asm_size_guess(); RSEQ_INJECT_FAILED return -1; cmpfail: - rseq_workaround_gcc_asm_size_guess(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: @@ -577,7 +552,6 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, RSEQ_INJECT_C(9) - rseq_workaround_gcc_asm_size_guess(); __asm__ __volatile__ goto ( RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */ RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail]) @@ -649,8 +623,8 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, "8:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* final store input */ [v] "m" (*v), [expect] "r" (expect), @@ -670,21 +644,16 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, , error1, error2 #endif ); - rseq_workaround_gcc_asm_size_guess(); return 0; abort: - rseq_workaround_gcc_asm_size_guess(); RSEQ_INJECT_FAILED return -1; cmpfail: - rseq_workaround_gcc_asm_size_guess(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: - rseq_workaround_gcc_asm_size_guess(); rseq_bug("cpu_id comparison failed"); error2: - rseq_workaround_gcc_asm_size_guess(); rseq_bug("expected value comparison failed"); #endif } @@ -698,7 +667,6 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect, RSEQ_INJECT_C(9) - rseq_workaround_gcc_asm_size_guess(); __asm__ __volatile__ goto ( RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */ RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail]) @@ -771,8 +739,8 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect, "8:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* final store input */ [v] "m" (*v), [expect] "r" (expect), @@ -792,21 +760,16 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect, , error1, error2 #endif ); - rseq_workaround_gcc_asm_size_guess(); return 0; abort: - rseq_workaround_gcc_asm_size_guess(); RSEQ_INJECT_FAILED return -1; cmpfail: - rseq_workaround_gcc_asm_size_guess(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: - rseq_workaround_gcc_asm_size_guess(); rseq_bug("cpu_id comparison failed"); error2: - rseq_workaround_gcc_asm_size_guess(); rseq_bug("expected value comparison failed"); #endif } diff --git a/tools/testing/selftests/rseq/rseq-ppc-thread-pointer.h b/tools/testing/selftests/rseq/rseq-ppc-thread-pointer.h new file mode 100644 index 000000000000..263eee84fb76 --- /dev/null +++ b/tools/testing/selftests/rseq/rseq-ppc-thread-pointer.h @@ -0,0 +1,30 @@ +/* SPDX-License-Identifier: LGPL-2.1-only OR MIT */ +/* + * rseq-ppc-thread-pointer.h + * + * (C) Copyright 2021 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com> + */ + +#ifndef _RSEQ_PPC_THREAD_POINTER +#define _RSEQ_PPC_THREAD_POINTER + +#ifdef __cplusplus +extern "C" { +#endif + +static inline void *rseq_thread_pointer(void) +{ +#ifdef __powerpc64__ + register void *__result asm ("r13"); +#else + register void *__result asm ("r2"); +#endif + asm ("" : "=r" (__result)); + return __result; +} + +#ifdef __cplusplus +} +#endif + +#endif diff --git a/tools/testing/selftests/rseq/rseq-ppc.h b/tools/testing/selftests/rseq/rseq-ppc.h index 76be90196fe4..bab8e0b9fb11 100644 --- a/tools/testing/selftests/rseq/rseq-ppc.h +++ b/tools/testing/selftests/rseq/rseq-ppc.h @@ -47,10 +47,13 @@ do { \ #ifdef __PPC64__ -#define STORE_WORD "std " -#define LOAD_WORD "ld " -#define LOADX_WORD "ldx " -#define CMP_WORD "cmpd " +#define RSEQ_STORE_LONG(arg) "std%U[" __rseq_str(arg) "]%X[" __rseq_str(arg) "] " /* To memory ("m" constraint) */ +#define RSEQ_STORE_INT(arg) "stw%U[" __rseq_str(arg) "]%X[" __rseq_str(arg) "] " /* To memory ("m" constraint) */ +#define RSEQ_LOAD_LONG(arg) "ld%U[" __rseq_str(arg) "]%X[" __rseq_str(arg) "] " /* From memory ("m" constraint) */ +#define RSEQ_LOAD_INT(arg) "lwz%U[" __rseq_str(arg) "]%X[" __rseq_str(arg) "] " /* From memory ("m" constraint) */ +#define RSEQ_LOADX_LONG "ldx " /* From base register ("b" constraint) */ +#define RSEQ_CMP_LONG "cmpd " +#define RSEQ_CMP_LONG_INT "cmpdi " #define __RSEQ_ASM_DEFINE_TABLE(label, version, flags, \ start_ip, post_commit_offset, abort_ip) \ @@ -89,10 +92,13 @@ do { \ #else /* #ifdef __PPC64__ */ -#define STORE_WORD "stw " -#define LOAD_WORD "lwz " -#define LOADX_WORD "lwzx " -#define CMP_WORD "cmpw " +#define RSEQ_STORE_LONG(arg) "stw%U[" __rseq_str(arg) "]%X[" __rseq_str(arg) "] " /* To memory ("m" constraint) */ +#define RSEQ_STORE_INT(arg) RSEQ_STORE_LONG(arg) /* To memory ("m" constraint) */ +#define RSEQ_LOAD_LONG(arg) "lwz%U[" __rseq_str(arg) "]%X[" __rseq_str(arg) "] " /* From memory ("m" constraint) */ +#define RSEQ_LOAD_INT(arg) RSEQ_LOAD_LONG(arg) /* From memory ("m" constraint) */ +#define RSEQ_LOADX_LONG "lwzx " /* From base register ("b" constraint) */ +#define RSEQ_CMP_LONG "cmpw " +#define RSEQ_CMP_LONG_INT "cmpwi " #define __RSEQ_ASM_DEFINE_TABLE(label, version, flags, \ start_ip, post_commit_offset, abort_ip) \ @@ -125,7 +131,7 @@ do { \ RSEQ_INJECT_ASM(1) \ "lis %%r17, (" __rseq_str(cs_label) ")@ha\n\t" \ "addi %%r17, %%r17, (" __rseq_str(cs_label) ")@l\n\t" \ - "stw %%r17, %[" __rseq_str(rseq_cs) "]\n\t" \ + RSEQ_STORE_INT(rseq_cs) "%%r17, %[" __rseq_str(rseq_cs) "]\n\t" \ __rseq_str(label) ":\n\t" #endif /* #ifdef __PPC64__ */ @@ -136,7 +142,7 @@ do { \ #define RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, label) \ RSEQ_INJECT_ASM(2) \ - "lwz %%r17, %[" __rseq_str(current_cpu_id) "]\n\t" \ + RSEQ_LOAD_INT(current_cpu_id) "%%r17, %[" __rseq_str(current_cpu_id) "]\n\t" \ "cmpw cr7, %[" __rseq_str(cpu_id) "], %%r17\n\t" \ "bne- cr7, " __rseq_str(label) "\n\t" @@ -153,25 +159,25 @@ do { \ * RSEQ_ASM_OP_* (else): doesn't have hard-code registers(unless cr7) */ #define RSEQ_ASM_OP_CMPEQ(var, expect, label) \ - LOAD_WORD "%%r17, %[" __rseq_str(var) "]\n\t" \ - CMP_WORD "cr7, %%r17, %[" __rseq_str(expect) "]\n\t" \ + RSEQ_LOAD_LONG(var) "%%r17, %[" __rseq_str(var) "]\n\t" \ + RSEQ_CMP_LONG "cr7, %%r17, %[" __rseq_str(expect) "]\n\t" \ "bne- cr7, " __rseq_str(label) "\n\t" #define RSEQ_ASM_OP_CMPNE(var, expectnot, label) \ - LOAD_WORD "%%r17, %[" __rseq_str(var) "]\n\t" \ - CMP_WORD "cr7, %%r17, %[" __rseq_str(expectnot) "]\n\t" \ + RSEQ_LOAD_LONG(var) "%%r17, %[" __rseq_str(var) "]\n\t" \ + RSEQ_CMP_LONG "cr7, %%r17, %[" __rseq_str(expectnot) "]\n\t" \ "beq- cr7, " __rseq_str(label) "\n\t" #define RSEQ_ASM_OP_STORE(value, var) \ - STORE_WORD "%[" __rseq_str(value) "], %[" __rseq_str(var) "]\n\t" + RSEQ_STORE_LONG(var) "%[" __rseq_str(value) "], %[" __rseq_str(var) "]\n\t" /* Load @var to r17 */ #define RSEQ_ASM_OP_R_LOAD(var) \ - LOAD_WORD "%%r17, %[" __rseq_str(var) "]\n\t" + RSEQ_LOAD_LONG(var) "%%r17, %[" __rseq_str(var) "]\n\t" /* Store r17 to @var */ #define RSEQ_ASM_OP_R_STORE(var) \ - STORE_WORD "%%r17, %[" __rseq_str(var) "]\n\t" + RSEQ_STORE_LONG(var) "%%r17, %[" __rseq_str(var) "]\n\t" /* Add @count to r17 */ #define RSEQ_ASM_OP_R_ADD(count) \ @@ -179,11 +185,11 @@ do { \ /* Load (r17 + voffp) to r17 */ #define RSEQ_ASM_OP_R_LOADX(voffp) \ - LOADX_WORD "%%r17, %[" __rseq_str(voffp) "], %%r17\n\t" + RSEQ_LOADX_LONG "%%r17, %[" __rseq_str(voffp) "], %%r17\n\t" /* TODO: implement a faster memcpy. */ #define RSEQ_ASM_OP_R_MEMCPY() \ - "cmpdi %%r19, 0\n\t" \ + RSEQ_CMP_LONG_INT "%%r19, 0\n\t" \ "beq 333f\n\t" \ "addi %%r20, %%r20, -1\n\t" \ "addi %%r21, %%r21, -1\n\t" \ @@ -191,16 +197,16 @@ do { \ "lbzu %%r18, 1(%%r20)\n\t" \ "stbu %%r18, 1(%%r21)\n\t" \ "addi %%r19, %%r19, -1\n\t" \ - "cmpdi %%r19, 0\n\t" \ + RSEQ_CMP_LONG_INT "%%r19, 0\n\t" \ "bne 222b\n\t" \ "333:\n\t" \ #define RSEQ_ASM_OP_R_FINAL_STORE(var, post_commit_label) \ - STORE_WORD "%%r17, %[" __rseq_str(var) "]\n\t" \ + RSEQ_STORE_LONG(var) "%%r17, %[" __rseq_str(var) "]\n\t" \ __rseq_str(post_commit_label) ":\n\t" #define RSEQ_ASM_OP_FINAL_STORE(value, var, post_commit_label) \ - STORE_WORD "%[" __rseq_str(value) "], %[" __rseq_str(var) "]\n\t" \ + RSEQ_STORE_LONG(var) "%[" __rseq_str(value) "], %[" __rseq_str(var) "]\n\t" \ __rseq_str(post_commit_label) ":\n\t" static inline __attribute__((always_inline)) @@ -235,8 +241,8 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), [v] "m" (*v), [expect] "r" (expect), [newv] "r" (newv) @@ -248,23 +254,28 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } static inline __attribute__((always_inline)) int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, - off_t voffp, intptr_t *load, int cpu) + long voffp, intptr_t *load, int cpu) { RSEQ_INJECT_C(9) @@ -301,8 +312,8 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* final store input */ [v] "m" (*v), [expectnot] "r" (expectnot), @@ -316,16 +327,21 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -359,8 +375,8 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu) RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* final store input */ [v] "m" (*v), [count] "r" (count) @@ -372,12 +388,15 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu) , error1 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); #endif } @@ -419,8 +438,8 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* try store input */ [v2] "m" (*v2), [newv2] "r" (newv2), @@ -436,16 +455,21 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -489,8 +513,8 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* try store input */ [v2] "m" (*v2), [newv2] "r" (newv2), @@ -506,16 +530,21 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect, , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -560,8 +589,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* cmp2 input */ [v2] "m" (*v2), [expect2] "r" (expect2), @@ -577,18 +606,24 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, , error1, error2, error3 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("1st expected value comparison failed"); error3: + rseq_after_asm_goto(); rseq_bug("2nd expected value comparison failed"); #endif } @@ -635,8 +670,8 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* final store input */ [v] "m" (*v), [expect] "r" (expect), @@ -653,16 +688,21 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -711,8 +751,8 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* final store input */ [v] "m" (*v), [expect] "r" (expect), @@ -729,23 +769,23 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect, , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } -#undef STORE_WORD -#undef LOAD_WORD -#undef LOADX_WORD -#undef CMP_WORD - #endif /* !RSEQ_SKIP_FASTPATH */ diff --git a/tools/testing/selftests/rseq/rseq-s390.h b/tools/testing/selftests/rseq/rseq-s390.h index 8ef94ad1cbb4..4e6dc5f0cb42 100644 --- a/tools/testing/selftests/rseq/rseq-s390.h +++ b/tools/testing/selftests/rseq/rseq-s390.h @@ -165,8 +165,8 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), [v] "m" (*v), [expect] "r" (expect), [newv] "r" (newv) @@ -178,16 +178,21 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -198,7 +203,7 @@ error2: */ static inline __attribute__((always_inline)) int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, - off_t voffp, intptr_t *load, int cpu) + long voffp, intptr_t *load, int cpu) { RSEQ_INJECT_C(9) @@ -233,8 +238,8 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* final store input */ [v] "m" (*v), [expectnot] "r" (expectnot), @@ -248,16 +253,21 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -288,8 +298,8 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu) RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* final store input */ [v] "m" (*v), [count] "r" (count) @@ -301,12 +311,15 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu) , error1 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); #endif } @@ -347,8 +360,8 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* try store input */ [v2] "m" (*v2), [newv2] "r" (newv2), @@ -364,16 +377,21 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -426,8 +444,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* cmp2 input */ [v2] "m" (*v2), [expect2] "r" (expect2), @@ -443,18 +461,24 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, , error1, error2, error3 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("1st expected value comparison failed"); error3: + rseq_after_asm_goto(); rseq_bug("2nd expected value comparison failed"); #endif } @@ -534,8 +558,8 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, #endif : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* final store input */ [v] "m" (*v), [expect] "r" (expect), @@ -555,16 +579,21 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } diff --git a/tools/testing/selftests/rseq/rseq-skip.h b/tools/testing/selftests/rseq/rseq-skip.h index 72750b5905a9..7b53dac1fcdd 100644 --- a/tools/testing/selftests/rseq/rseq-skip.h +++ b/tools/testing/selftests/rseq/rseq-skip.h @@ -13,7 +13,7 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) static inline __attribute__((always_inline)) int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, - off_t voffp, intptr_t *load, int cpu) + long voffp, intptr_t *load, int cpu) { return -1; } diff --git a/tools/testing/selftests/rseq/rseq-thread-pointer.h b/tools/testing/selftests/rseq/rseq-thread-pointer.h new file mode 100644 index 000000000000..977c25d758b2 --- /dev/null +++ b/tools/testing/selftests/rseq/rseq-thread-pointer.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: LGPL-2.1-only OR MIT */ +/* + * rseq-thread-pointer.h + * + * (C) Copyright 2021 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com> + */ + +#ifndef _RSEQ_THREAD_POINTER +#define _RSEQ_THREAD_POINTER + +#if defined(__x86_64__) || defined(__i386__) +#include "rseq-x86-thread-pointer.h" +#elif defined(__PPC__) +#include "rseq-ppc-thread-pointer.h" +#else +#include "rseq-generic-thread-pointer.h" +#endif + +#endif diff --git a/tools/testing/selftests/rseq/rseq-x86-thread-pointer.h b/tools/testing/selftests/rseq/rseq-x86-thread-pointer.h new file mode 100644 index 000000000000..d3133587d996 --- /dev/null +++ b/tools/testing/selftests/rseq/rseq-x86-thread-pointer.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: LGPL-2.1-only OR MIT */ +/* + * rseq-x86-thread-pointer.h + * + * (C) Copyright 2021 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com> + */ + +#ifndef _RSEQ_X86_THREAD_POINTER +#define _RSEQ_X86_THREAD_POINTER + +#include <features.h> + +#ifdef __cplusplus +extern "C" { +#endif + +#if __GNUC_PREREQ (11, 1) +static inline void *rseq_thread_pointer(void) +{ + return __builtin_thread_pointer(); +} +#else +static inline void *rseq_thread_pointer(void) +{ + void *__result; + +# ifdef __x86_64__ + __asm__ ("mov %%fs:0, %0" : "=r" (__result)); +# else + __asm__ ("mov %%gs:0, %0" : "=r" (__result)); +# endif + return __result; +} +#endif /* !GCC 11 */ + +#ifdef __cplusplus +} +#endif + +#endif diff --git a/tools/testing/selftests/rseq/rseq-x86.h b/tools/testing/selftests/rseq/rseq-x86.h index 640411518e46..bd01dc41ca13 100644 --- a/tools/testing/selftests/rseq/rseq-x86.h +++ b/tools/testing/selftests/rseq/rseq-x86.h @@ -28,6 +28,8 @@ #ifdef __x86_64__ +#define RSEQ_ASM_TP_SEGMENT %%fs + #define rseq_smp_mb() \ __asm__ __volatile__ ("lock; addl $0,-128(%%rsp)" ::: "memory", "cc") #define rseq_smp_rmb() rseq_barrier() @@ -123,14 +125,14 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2]) #endif /* Start rseq by storing table entry pointer into rseq_cs. */ - RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi])) - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f) + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f) RSEQ_INJECT_ASM(3) "cmpq %[v], %[expect]\n\t" "jnz %l[cmpfail]\n\t" RSEQ_INJECT_ASM(4) #ifdef RSEQ_COMPARE_TWICE - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1]) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1]) "cmpq %[v], %[expect]\n\t" "jnz %l[error2]\n\t" #endif @@ -141,7 +143,7 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_offset] "r" (rseq_offset), [v] "m" (*v), [expect] "r" (expect), [newv] "r" (newv) @@ -152,16 +154,21 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -172,7 +179,7 @@ error2: */ static inline __attribute__((always_inline)) int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, - off_t voffp, intptr_t *load, int cpu) + long voffp, intptr_t *load, int cpu) { RSEQ_INJECT_C(9) @@ -184,15 +191,15 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2]) #endif /* Start rseq by storing table entry pointer into rseq_cs. */ - RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi])) - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f) + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f) RSEQ_INJECT_ASM(3) "movq %[v], %%rbx\n\t" "cmpq %%rbx, %[expectnot]\n\t" "je %l[cmpfail]\n\t" RSEQ_INJECT_ASM(4) #ifdef RSEQ_COMPARE_TWICE - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1]) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1]) "movq %[v], %%rbx\n\t" "cmpq %%rbx, %[expectnot]\n\t" "je %l[error2]\n\t" @@ -207,7 +214,7 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_offset] "r" (rseq_offset), /* final store input */ [v] "m" (*v), [expectnot] "r" (expectnot), @@ -220,16 +227,21 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -245,11 +257,11 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu) RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1]) #endif /* Start rseq by storing table entry pointer into rseq_cs. */ - RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi])) - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f) + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f) RSEQ_INJECT_ASM(3) #ifdef RSEQ_COMPARE_TWICE - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1]) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1]) #endif /* final store */ "addq %[count], %[v]\n\t" @@ -258,7 +270,7 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu) RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_offset] "r" (rseq_offset), /* final store input */ [v] "m" (*v), [count] "er" (count) @@ -269,12 +281,15 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu) , error1 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); #endif } @@ -286,7 +301,7 @@ error1: * *pval += inc; */ static inline __attribute__((always_inline)) -int rseq_offset_deref_addv(intptr_t *ptr, off_t off, intptr_t inc, int cpu) +int rseq_offset_deref_addv(intptr_t *ptr, long off, intptr_t inc, int cpu) { RSEQ_INJECT_C(9) @@ -296,11 +311,11 @@ int rseq_offset_deref_addv(intptr_t *ptr, off_t off, intptr_t inc, int cpu) RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1]) #endif /* Start rseq by storing table entry pointer into rseq_cs. */ - RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi])) - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f) + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f) RSEQ_INJECT_ASM(3) #ifdef RSEQ_COMPARE_TWICE - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1]) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1]) #endif /* get p+v */ "movq %[ptr], %%rbx\n\t" @@ -314,7 +329,7 @@ int rseq_offset_deref_addv(intptr_t *ptr, off_t off, intptr_t inc, int cpu) RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_offset] "r" (rseq_offset), /* final store input */ [ptr] "m" (*ptr), [off] "er" (off), @@ -351,14 +366,14 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2]) #endif /* Start rseq by storing table entry pointer into rseq_cs. */ - RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi])) - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f) + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f) RSEQ_INJECT_ASM(3) "cmpq %[v], %[expect]\n\t" "jnz %l[cmpfail]\n\t" RSEQ_INJECT_ASM(4) #ifdef RSEQ_COMPARE_TWICE - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1]) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1]) "cmpq %[v], %[expect]\n\t" "jnz %l[error2]\n\t" #endif @@ -372,7 +387,7 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_offset] "r" (rseq_offset), /* try store input */ [v2] "m" (*v2), [newv2] "r" (newv2), @@ -387,16 +402,21 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -426,8 +446,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error3]) #endif /* Start rseq by storing table entry pointer into rseq_cs. */ - RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi])) - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f) + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f) RSEQ_INJECT_ASM(3) "cmpq %[v], %[expect]\n\t" "jnz %l[cmpfail]\n\t" @@ -436,7 +456,7 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, "jnz %l[cmpfail]\n\t" RSEQ_INJECT_ASM(5) #ifdef RSEQ_COMPARE_TWICE - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1]) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1]) "cmpq %[v], %[expect]\n\t" "jnz %l[error2]\n\t" "cmpq %[v2], %[expect2]\n\t" @@ -449,7 +469,7 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_offset] "r" (rseq_offset), /* cmp2 input */ [v2] "m" (*v2), [expect2] "r" (expect2), @@ -464,18 +484,24 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, , error1, error2, error3 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("1st expected value comparison failed"); error3: + rseq_after_asm_goto(); rseq_bug("2nd expected value comparison failed"); #endif } @@ -500,14 +526,14 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, "movq %[dst], %[rseq_scratch1]\n\t" "movq %[len], %[rseq_scratch2]\n\t" /* Start rseq by storing table entry pointer into rseq_cs. */ - RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi])) - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f) + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f) RSEQ_INJECT_ASM(3) "cmpq %[v], %[expect]\n\t" "jnz 5f\n\t" RSEQ_INJECT_ASM(4) #ifdef RSEQ_COMPARE_TWICE - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 6f) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 6f) "cmpq %[v], %[expect]\n\t" "jnz 7f\n\t" #endif @@ -555,7 +581,7 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, #endif : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_offset] "r" (rseq_offset), /* final store input */ [v] "m" (*v), [expect] "r" (expect), @@ -574,16 +600,21 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -600,7 +631,9 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect, #endif /* !RSEQ_SKIP_FASTPATH */ -#elif __i386__ +#elif defined(__i386__) + +#define RSEQ_ASM_TP_SEGMENT %%gs #define rseq_smp_mb() \ __asm__ __volatile__ ("lock; addl $0,-128(%%esp)" ::: "memory", "cc") @@ -701,14 +734,14 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2]) #endif /* Start rseq by storing table entry pointer into rseq_cs. */ - RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi])) - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f) + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f) RSEQ_INJECT_ASM(3) "cmpl %[v], %[expect]\n\t" "jnz %l[cmpfail]\n\t" RSEQ_INJECT_ASM(4) #ifdef RSEQ_COMPARE_TWICE - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1]) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1]) "cmpl %[v], %[expect]\n\t" "jnz %l[error2]\n\t" #endif @@ -719,7 +752,7 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_offset] "r" (rseq_offset), [v] "m" (*v), [expect] "r" (expect), [newv] "r" (newv) @@ -730,16 +763,21 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -750,7 +788,7 @@ error2: */ static inline __attribute__((always_inline)) int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, - off_t voffp, intptr_t *load, int cpu) + long voffp, intptr_t *load, int cpu) { RSEQ_INJECT_C(9) @@ -762,15 +800,15 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2]) #endif /* Start rseq by storing table entry pointer into rseq_cs. */ - RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi])) - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f) + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f) RSEQ_INJECT_ASM(3) "movl %[v], %%ebx\n\t" "cmpl %%ebx, %[expectnot]\n\t" "je %l[cmpfail]\n\t" RSEQ_INJECT_ASM(4) #ifdef RSEQ_COMPARE_TWICE - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1]) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1]) "movl %[v], %%ebx\n\t" "cmpl %%ebx, %[expectnot]\n\t" "je %l[error2]\n\t" @@ -785,7 +823,7 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_offset] "r" (rseq_offset), /* final store input */ [v] "m" (*v), [expectnot] "r" (expectnot), @@ -798,16 +836,21 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -823,11 +866,11 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu) RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1]) #endif /* Start rseq by storing table entry pointer into rseq_cs. */ - RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi])) - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f) + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f) RSEQ_INJECT_ASM(3) #ifdef RSEQ_COMPARE_TWICE - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1]) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1]) #endif /* final store */ "addl %[count], %[v]\n\t" @@ -836,7 +879,7 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu) RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_offset] "r" (rseq_offset), /* final store input */ [v] "m" (*v), [count] "ir" (count) @@ -847,12 +890,15 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu) , error1 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); #endif } @@ -872,14 +918,14 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2]) #endif /* Start rseq by storing table entry pointer into rseq_cs. */ - RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi])) - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f) + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f) RSEQ_INJECT_ASM(3) "cmpl %[v], %[expect]\n\t" "jnz %l[cmpfail]\n\t" RSEQ_INJECT_ASM(4) #ifdef RSEQ_COMPARE_TWICE - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1]) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1]) "cmpl %[v], %[expect]\n\t" "jnz %l[error2]\n\t" #endif @@ -894,7 +940,7 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_offset] "r" (rseq_offset), /* try store input */ [v2] "m" (*v2), [newv2] "m" (newv2), @@ -909,16 +955,21 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -938,15 +989,15 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2]) #endif /* Start rseq by storing table entry pointer into rseq_cs. */ - RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi])) - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f) + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f) RSEQ_INJECT_ASM(3) "movl %[expect], %%eax\n\t" "cmpl %[v], %%eax\n\t" "jnz %l[cmpfail]\n\t" RSEQ_INJECT_ASM(4) #ifdef RSEQ_COMPARE_TWICE - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1]) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1]) "movl %[expect], %%eax\n\t" "cmpl %[v], %%eax\n\t" "jnz %l[error2]\n\t" @@ -962,7 +1013,7 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_offset] "r" (rseq_offset), /* try store input */ [v2] "m" (*v2), [newv2] "r" (newv2), @@ -977,16 +1028,21 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect, , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif @@ -1008,8 +1064,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error3]) #endif /* Start rseq by storing table entry pointer into rseq_cs. */ - RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi])) - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f) + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f) RSEQ_INJECT_ASM(3) "cmpl %[v], %[expect]\n\t" "jnz %l[cmpfail]\n\t" @@ -1018,7 +1074,7 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, "jnz %l[cmpfail]\n\t" RSEQ_INJECT_ASM(5) #ifdef RSEQ_COMPARE_TWICE - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1]) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1]) "cmpl %[v], %[expect]\n\t" "jnz %l[error2]\n\t" "cmpl %[expect2], %[v2]\n\t" @@ -1032,7 +1088,7 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_offset] "r" (rseq_offset), /* cmp2 input */ [v2] "m" (*v2), [expect2] "r" (expect2), @@ -1047,18 +1103,24 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, , error1, error2, error3 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("1st expected value comparison failed"); error3: + rseq_after_asm_goto(); rseq_bug("2nd expected value comparison failed"); #endif } @@ -1084,15 +1146,15 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, "movl %[dst], %[rseq_scratch1]\n\t" "movl %[len], %[rseq_scratch2]\n\t" /* Start rseq by storing table entry pointer into rseq_cs. */ - RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi])) - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f) + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f) RSEQ_INJECT_ASM(3) "movl %[expect], %%eax\n\t" "cmpl %%eax, %[v]\n\t" "jnz 5f\n\t" RSEQ_INJECT_ASM(4) #ifdef RSEQ_COMPARE_TWICE - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 6f) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 6f) "movl %[expect], %%eax\n\t" "cmpl %%eax, %[v]\n\t" "jnz 7f\n\t" @@ -1142,7 +1204,7 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, #endif : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_offset] "r" (rseq_offset), /* final store input */ [v] "m" (*v), [expect] "m" (expect), @@ -1161,16 +1223,21 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -1196,15 +1263,15 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect, "movl %[dst], %[rseq_scratch1]\n\t" "movl %[len], %[rseq_scratch2]\n\t" /* Start rseq by storing table entry pointer into rseq_cs. */ - RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi])) - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f) + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f) RSEQ_INJECT_ASM(3) "movl %[expect], %%eax\n\t" "cmpl %%eax, %[v]\n\t" "jnz 5f\n\t" RSEQ_INJECT_ASM(4) #ifdef RSEQ_COMPARE_TWICE - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 6f) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 6f) "movl %[expect], %%eax\n\t" "cmpl %%eax, %[v]\n\t" "jnz 7f\n\t" @@ -1255,7 +1322,7 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect, #endif : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_offset] "r" (rseq_offset), /* final store input */ [v] "m" (*v), [expect] "m" (expect), @@ -1274,16 +1341,21 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect, , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } diff --git a/tools/testing/selftests/rseq/rseq.c b/tools/testing/selftests/rseq/rseq.c index fb440dfca158..986b9458efb2 100644 --- a/tools/testing/selftests/rseq/rseq.c +++ b/tools/testing/selftests/rseq/rseq.c @@ -26,130 +26,124 @@ #include <assert.h> #include <signal.h> #include <limits.h> +#include <dlfcn.h> +#include <stddef.h> #include "../kselftest.h" #include "rseq.h" -__thread volatile struct rseq __rseq_abi = { - .cpu_id = RSEQ_CPU_ID_UNINITIALIZED, -}; - -/* - * Shared with other libraries. This library may take rseq ownership if it is - * still 0 when executing the library constructor. Set to 1 by library - * constructor when handling rseq. Set to 0 in destructor if handling rseq. - */ -int __rseq_handled; - -/* Whether this library have ownership of rseq registration. */ -static int rseq_ownership; +static const ptrdiff_t *libc_rseq_offset_p; +static const unsigned int *libc_rseq_size_p; +static const unsigned int *libc_rseq_flags_p; -static __thread volatile uint32_t __rseq_refcount; +/* Offset from the thread pointer to the rseq area. */ +ptrdiff_t rseq_offset; -static void signal_off_save(sigset_t *oldset) -{ - sigset_t set; - int ret; +/* Size of the registered rseq area. 0 if the registration was + unsuccessful. */ +unsigned int rseq_size = -1U; - sigfillset(&set); - ret = pthread_sigmask(SIG_BLOCK, &set, oldset); - if (ret) - abort(); -} +/* Flags used during rseq registration. */ +unsigned int rseq_flags; -static void signal_restore(sigset_t oldset) -{ - int ret; +static int rseq_ownership; - ret = pthread_sigmask(SIG_SETMASK, &oldset, NULL); - if (ret) - abort(); -} +static +__thread struct rseq_abi __rseq_abi __attribute__((tls_model("initial-exec"))) = { + .cpu_id = RSEQ_ABI_CPU_ID_UNINITIALIZED, +}; -static int sys_rseq(volatile struct rseq *rseq_abi, uint32_t rseq_len, +static int sys_rseq(struct rseq_abi *rseq_abi, uint32_t rseq_len, int flags, uint32_t sig) { return syscall(__NR_rseq, rseq_abi, rseq_len, flags, sig); } -int rseq_register_current_thread(void) +int rseq_available(void) { - int rc, ret = 0; - sigset_t oldset; + int rc; - if (!rseq_ownership) + rc = sys_rseq(NULL, 0, 0, 0); + if (rc != -1) + abort(); + switch (errno) { + case ENOSYS: return 0; - signal_off_save(&oldset); - if (__rseq_refcount == UINT_MAX) { - ret = -1; - goto end; - } - if (__rseq_refcount++) - goto end; - rc = sys_rseq(&__rseq_abi, sizeof(struct rseq), 0, RSEQ_SIG); - if (!rc) { - assert(rseq_current_cpu_raw() >= 0); - goto end; + case EINVAL: + return 1; + default: + abort(); } - if (errno != EBUSY) - __rseq_abi.cpu_id = RSEQ_CPU_ID_REGISTRATION_FAILED; - ret = -1; - __rseq_refcount--; -end: - signal_restore(oldset); - return ret; } -int rseq_unregister_current_thread(void) +int rseq_register_current_thread(void) { - int rc, ret = 0; - sigset_t oldset; + int rc; - if (!rseq_ownership) + if (!rseq_ownership) { + /* Treat libc's ownership as a successful registration. */ return 0; - signal_off_save(&oldset); - if (!__rseq_refcount) { - ret = -1; - goto end; } - if (--__rseq_refcount) - goto end; - rc = sys_rseq(&__rseq_abi, sizeof(struct rseq), - RSEQ_FLAG_UNREGISTER, RSEQ_SIG); - if (!rc) - goto end; - __rseq_refcount = 1; - ret = -1; -end: - signal_restore(oldset); - return ret; + rc = sys_rseq(&__rseq_abi, sizeof(struct rseq_abi), 0, RSEQ_SIG); + if (rc) + return -1; + assert(rseq_current_cpu_raw() >= 0); + return 0; } -int32_t rseq_fallback_current_cpu(void) +int rseq_unregister_current_thread(void) { - int32_t cpu; + int rc; - cpu = sched_getcpu(); - if (cpu < 0) { - perror("sched_getcpu()"); - abort(); + if (!rseq_ownership) { + /* Treat libc's ownership as a successful unregistration. */ + return 0; } - return cpu; + rc = sys_rseq(&__rseq_abi, sizeof(struct rseq_abi), RSEQ_ABI_FLAG_UNREGISTER, RSEQ_SIG); + if (rc) + return -1; + return 0; } -void __attribute__((constructor)) rseq_init(void) +static __attribute__((constructor)) +void rseq_init(void) { - /* Check whether rseq is handled by another library. */ - if (__rseq_handled) + libc_rseq_offset_p = dlsym(RTLD_NEXT, "__rseq_offset"); + libc_rseq_size_p = dlsym(RTLD_NEXT, "__rseq_size"); + libc_rseq_flags_p = dlsym(RTLD_NEXT, "__rseq_flags"); + if (libc_rseq_size_p && libc_rseq_offset_p && libc_rseq_flags_p) { + /* rseq registration owned by glibc */ + rseq_offset = *libc_rseq_offset_p; + rseq_size = *libc_rseq_size_p; + rseq_flags = *libc_rseq_flags_p; + return; + } + if (!rseq_available()) return; - __rseq_handled = 1; rseq_ownership = 1; + rseq_offset = (void *)&__rseq_abi - rseq_thread_pointer(); + rseq_size = sizeof(struct rseq_abi); + rseq_flags = 0; } -void __attribute__((destructor)) rseq_fini(void) +static __attribute__((destructor)) +void rseq_exit(void) { if (!rseq_ownership) return; - __rseq_handled = 0; + rseq_offset = 0; + rseq_size = -1U; rseq_ownership = 0; } + +int32_t rseq_fallback_current_cpu(void) +{ + int32_t cpu; + + cpu = sched_getcpu(); + if (cpu < 0) { + perror("sched_getcpu()"); + abort(); + } + return cpu; +} diff --git a/tools/testing/selftests/rseq/rseq.h b/tools/testing/selftests/rseq/rseq.h index 3f63eb362b92..9d850b290c2e 100644 --- a/tools/testing/selftests/rseq/rseq.h +++ b/tools/testing/selftests/rseq/rseq.h @@ -16,7 +16,9 @@ #include <errno.h> #include <stdio.h> #include <stdlib.h> -#include <linux/rseq.h> +#include <stddef.h> +#include "rseq-abi.h" +#include "compiler.h" /* * Empty code injection macros, override when testing. @@ -43,8 +45,20 @@ #define RSEQ_INJECT_FAILED #endif -extern __thread volatile struct rseq __rseq_abi; -extern int __rseq_handled; +#include "rseq-thread-pointer.h" + +/* Offset from the thread pointer to the rseq area. */ +extern ptrdiff_t rseq_offset; +/* Size of the registered rseq area. 0 if the registration was + unsuccessful. */ +extern unsigned int rseq_size; +/* Flags used during rseq registration. */ +extern unsigned int rseq_flags; + +static inline struct rseq_abi *rseq_get_abi(void) +{ + return (struct rseq_abi *) ((uintptr_t) rseq_thread_pointer() + rseq_offset); +} #define rseq_likely(x) __builtin_expect(!!(x), 1) #define rseq_unlikely(x) __builtin_expect(!!(x), 0) @@ -108,7 +122,7 @@ int32_t rseq_fallback_current_cpu(void); */ static inline int32_t rseq_current_cpu_raw(void) { - return RSEQ_ACCESS_ONCE(__rseq_abi.cpu_id); + return RSEQ_ACCESS_ONCE(rseq_get_abi()->cpu_id); } /* @@ -124,7 +138,7 @@ static inline int32_t rseq_current_cpu_raw(void) */ static inline uint32_t rseq_cpu_start(void) { - return RSEQ_ACCESS_ONCE(__rseq_abi.cpu_id_start); + return RSEQ_ACCESS_ONCE(rseq_get_abi()->cpu_id_start); } static inline uint32_t rseq_current_cpu(void) @@ -139,11 +153,7 @@ static inline uint32_t rseq_current_cpu(void) static inline void rseq_clear_rseq_cs(void) { -#ifdef __LP64__ - __rseq_abi.rseq_cs.ptr = 0; -#else - __rseq_abi.rseq_cs.ptr.ptr32 = 0; -#endif + RSEQ_WRITE_ONCE(rseq_get_abi()->rseq_cs.arch.ptr, 0); } /* |