diff options
400 files changed, 9645 insertions, 2119 deletions
diff --git a/Documentation/driver-api/libata.rst b/Documentation/driver-api/libata.rst index 4adc056f7635..70e180e6b93d 100644 --- a/Documentation/driver-api/libata.rst +++ b/Documentation/driver-api/libata.rst @@ -118,8 +118,7 @@ PIO data read/write All bmdma-style drivers must implement this hook. This is the low-level operation that actually copies the data bytes during a PIO data transfer. Typically the driver will choose one of -:c:func:`ata_sff_data_xfer_noirq`, :c:func:`ata_sff_data_xfer`, or -:c:func:`ata_sff_data_xfer32`. +:c:func:`ata_sff_data_xfer`, or :c:func:`ata_sff_data_xfer32`. ATA command execute ~~~~~~~~~~~~~~~~~~~ diff --git a/arch/Kconfig b/arch/Kconfig index a18371a36e03..c43f4b71c028 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -20,6 +20,7 @@ config OPROFILE tristate "OProfile system profiling" depends on PROFILING depends on HAVE_OPROFILE + depends on !PREEMPT_RT_FULL select RING_BUFFER select RING_BUFFER_ALLOW_SWAP help diff --git a/arch/alpha/include/asm/spinlock_types.h b/arch/alpha/include/asm/spinlock_types.h index 1d5716bc060b..6883bc952d22 100644 --- a/arch/alpha/include/asm/spinlock_types.h +++ b/arch/alpha/include/asm/spinlock_types.h @@ -2,10 +2,6 @@ #ifndef _ALPHA_SPINLOCK_TYPES_H #define _ALPHA_SPINLOCK_TYPES_H -#ifndef __LINUX_SPINLOCK_TYPES_H -# error "please don't include this file directly" -#endif - typedef struct { volatile unsigned int lock; } arch_spinlock_t; diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 45a6cf925eec..2b8c658bcc5a 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -50,7 +50,7 @@ config ARM select HARDIRQS_SW_RESEND select HAVE_ARCH_AUDITSYSCALL if (AEABI && !OABI_COMPAT) select HAVE_ARCH_BITREVERSE if (CPU_32v7M || CPU_32v7) && !CPU_32v6 - select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU + select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU && !PREEMPT_RT_BASE select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32 && MMU select HAVE_ARCH_MMAP_RND_BITS if MMU select HAVE_ARCH_SECCOMP_FILTER if (AEABI && !OABI_COMPAT) @@ -89,6 +89,7 @@ config ARM select HAVE_PERF_EVENTS select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP + select HAVE_PREEMPT_LAZY select HAVE_RCU_TABLE_FREE if (SMP && ARM_LPAE) select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_RSEQ @@ -2170,7 +2171,7 @@ config NEON config KERNEL_MODE_NEON bool "Support for NEON in kernel mode" - depends on NEON && AEABI + depends on NEON && AEABI && !PREEMPT_RT_BASE help Say Y to include support for NEON in kernel mode. diff --git a/arch/arm/configs/at91_dt_defconfig b/arch/arm/configs/at91_dt_defconfig index e4b1be66b3f5..f4b253bd05ed 100644 --- a/arch/arm/configs/at91_dt_defconfig +++ b/arch/arm/configs/at91_dt_defconfig @@ -19,6 +19,7 @@ CONFIG_ARCH_MULTI_V5=y CONFIG_ARCH_AT91=y CONFIG_SOC_AT91RM9200=y CONFIG_SOC_AT91SAM9=y +# CONFIG_ATMEL_CLOCKSOURCE_PIT is not set CONFIG_AEABI=y CONFIG_UACCESS_WITH_MEMCPY=y CONFIG_ZBOOT_ROM_TEXT=0x0 @@ -64,7 +65,6 @@ CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_COUNT=4 CONFIG_BLK_DEV_RAM_SIZE=8192 -CONFIG_ATMEL_TCLIB=y CONFIG_ATMEL_SSC=y CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y diff --git a/arch/arm/configs/sama5_defconfig b/arch/arm/configs/sama5_defconfig index 2080025556b5..be92871ab155 100644 --- a/arch/arm/configs/sama5_defconfig +++ b/arch/arm/configs/sama5_defconfig @@ -20,6 +20,7 @@ CONFIG_ARCH_AT91=y CONFIG_SOC_SAMA5D2=y CONFIG_SOC_SAMA5D3=y CONFIG_SOC_SAMA5D4=y +# CONFIG_ATMEL_CLOCKSOURCE_PIT is not set CONFIG_AEABI=y CONFIG_UACCESS_WITH_MEMCPY=y CONFIG_ZBOOT_ROM_TEXT=0x0 @@ -75,7 +76,6 @@ CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_COUNT=4 CONFIG_BLK_DEV_RAM_SIZE=8192 -CONFIG_ATMEL_TCLIB=y CONFIG_ATMEL_SSC=y CONFIG_EEPROM_AT24=y CONFIG_SCSI=y diff --git a/arch/arm/include/asm/irq.h b/arch/arm/include/asm/irq.h index 2de321e89b94..0edd36f372e5 100644 --- a/arch/arm/include/asm/irq.h +++ b/arch/arm/include/asm/irq.h @@ -23,6 +23,8 @@ #endif #ifndef __ASSEMBLY__ +#include <linux/cpumask.h> + struct irqaction; struct pt_regs; diff --git a/arch/arm/include/asm/spinlock_types.h b/arch/arm/include/asm/spinlock_types.h index 5976958647fe..a37c0803954b 100644 --- a/arch/arm/include/asm/spinlock_types.h +++ b/arch/arm/include/asm/spinlock_types.h @@ -2,10 +2,6 @@ #ifndef __ASM_SPINLOCK_TYPES_H #define __ASM_SPINLOCK_TYPES_H -#ifndef __LINUX_SPINLOCK_TYPES_H -# error "please don't include this file directly" -#endif - #define TICKET_SHIFT 16 typedef struct { diff --git a/arch/arm/include/asm/switch_to.h b/arch/arm/include/asm/switch_to.h index d3e937dcee4d..6ab96a2ce1f8 100644 --- a/arch/arm/include/asm/switch_to.h +++ b/arch/arm/include/asm/switch_to.h @@ -4,6 +4,13 @@ #include <linux/thread_info.h> +#if defined CONFIG_PREEMPT_RT_FULL && defined CONFIG_HIGHMEM +void switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p); +#else +static inline void +switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p) { } +#endif + /* * For v7 SMP cores running a preemptible kernel we may be pre-empted * during a TLB maintenance operation, so execute an inner-shareable dsb @@ -26,6 +33,7 @@ extern struct task_struct *__switch_to(struct task_struct *, struct thread_info #define switch_to(prev,next,last) \ do { \ __complete_pending_tlbi(); \ + switch_kmaps(prev, next); \ last = __switch_to(prev,task_thread_info(prev), task_thread_info(next)); \ } while (0) diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h index 479d12c0f745..7fdfaea463ea 100644 --- a/arch/arm/include/asm/thread_info.h +++ b/arch/arm/include/asm/thread_info.h @@ -49,6 +49,7 @@ struct cpu_context_save { struct thread_info { unsigned long flags; /* low level flags */ int preempt_count; /* 0 => preemptable, <0 => bug */ + int preempt_lazy_count; /* 0 => preemptable, <0 => bug */ mm_segment_t addr_limit; /* address limit */ struct task_struct *task; /* main task structure */ __u32 cpu; /* cpu */ @@ -139,7 +140,8 @@ extern int vfp_restore_user_hwstate(struct user_vfp __user *, #define TIF_SYSCALL_TRACE 4 /* syscall trace active */ #define TIF_SYSCALL_AUDIT 5 /* syscall auditing active */ #define TIF_SYSCALL_TRACEPOINT 6 /* syscall tracepoint instrumentation */ -#define TIF_SECCOMP 7 /* seccomp syscall filtering active */ +#define TIF_SECCOMP 8 /* seccomp syscall filtering active */ +#define TIF_NEED_RESCHED_LAZY 7 #define TIF_NOHZ 12 /* in adaptive nohz mode */ #define TIF_USING_IWMMXT 17 @@ -149,6 +151,7 @@ extern int vfp_restore_user_hwstate(struct user_vfp __user *, #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) #define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME) +#define _TIF_NEED_RESCHED_LAZY (1 << TIF_NEED_RESCHED_LAZY) #define _TIF_UPROBE (1 << TIF_UPROBE) #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) @@ -164,7 +167,8 @@ extern int vfp_restore_user_hwstate(struct user_vfp __user *, * Change these and you break ASM code in entry-common.S */ #define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \ - _TIF_NOTIFY_RESUME | _TIF_UPROBE) + _TIF_NOTIFY_RESUME | _TIF_UPROBE | \ + _TIF_NEED_RESCHED_LAZY) #endif /* __KERNEL__ */ #endif /* __ASM_ARM_THREAD_INFO_H */ diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c index 974d8d7d1bcd..d54deed3481b 100644 --- a/arch/arm/kernel/asm-offsets.c +++ b/arch/arm/kernel/asm-offsets.c @@ -67,6 +67,7 @@ int main(void) BLANK(); DEFINE(TI_FLAGS, offsetof(struct thread_info, flags)); DEFINE(TI_PREEMPT, offsetof(struct thread_info, preempt_count)); + DEFINE(TI_PREEMPT_LAZY, offsetof(struct thread_info, preempt_lazy_count)); DEFINE(TI_ADDR_LIMIT, offsetof(struct thread_info, addr_limit)); DEFINE(TI_TASK, offsetof(struct thread_info, task)); DEFINE(TI_CPU, offsetof(struct thread_info, cpu)); diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index 179a9f6bd1e3..2b386b87e46b 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -216,11 +216,18 @@ __irq_svc: #ifdef CONFIG_PREEMPT ldr r8, [tsk, #TI_PREEMPT] @ get preempt count - ldr r0, [tsk, #TI_FLAGS] @ get flags teq r8, #0 @ if preempt count != 0 + bne 1f @ return from exeption + ldr r0, [tsk, #TI_FLAGS] @ get flags + tst r0, #_TIF_NEED_RESCHED @ if NEED_RESCHED is set + blne svc_preempt @ preempt! + + ldr r8, [tsk, #TI_PREEMPT_LAZY] @ get preempt lazy count + teq r8, #0 @ if preempt lazy count != 0 movne r0, #0 @ force flags to 0 - tst r0, #_TIF_NEED_RESCHED + tst r0, #_TIF_NEED_RESCHED_LAZY blne svc_preempt +1: #endif svc_exit r5, irq = 1 @ return from exception @@ -235,8 +242,14 @@ svc_preempt: 1: bl preempt_schedule_irq @ irq en/disable is done inside ldr r0, [tsk, #TI_FLAGS] @ get new tasks TI_FLAGS tst r0, #_TIF_NEED_RESCHED + bne 1b + tst r0, #_TIF_NEED_RESCHED_LAZY reteq r8 @ go again - b 1b + ldr r0, [tsk, #TI_PREEMPT_LAZY] @ get preempt lazy count + teq r0, #0 @ if preempt lazy count != 0 + beq 1b + ret r8 @ go again + #endif __und_fault: diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S index 4a30d60c9504..8f4b3bf5b126 100644 --- a/arch/arm/kernel/entry-common.S +++ b/arch/arm/kernel/entry-common.S @@ -56,7 +56,9 @@ __ret_fast_syscall: cmp r2, #TASK_SIZE blne addr_limit_check_failed ldr r1, [tsk, #TI_FLAGS] @ re-check for syscall tracing - tst r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK + tst r1, #((_TIF_SYSCALL_WORK | _TIF_WORK_MASK) & ~_TIF_SECCOMP) + bne fast_work_pending + tst r1, #_TIF_SECCOMP bne fast_work_pending @@ -93,8 +95,11 @@ __ret_fast_syscall: cmp r2, #TASK_SIZE blne addr_limit_check_failed ldr r1, [tsk, #TI_FLAGS] @ re-check for syscall tracing - tst r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK + tst r1, #((_TIF_SYSCALL_WORK | _TIF_WORK_MASK) & ~_TIF_SECCOMP) + bne do_slower_path + tst r1, #_TIF_SECCOMP beq no_work_pending +do_slower_path: UNWIND(.fnend ) ENDPROC(ret_fast_syscall) diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index d9c299133111..12c83dc81287 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -324,6 +324,30 @@ unsigned long arch_randomize_brk(struct mm_struct *mm) } #ifdef CONFIG_MMU +/* + * CONFIG_SPLIT_PTLOCK_CPUS results in a page->ptl lock. If the lock is not + * initialized by pgtable_page_ctor() then a coredump of the vector page will + * fail. + */ +static int __init vectors_user_mapping_init_page(void) +{ + struct page *page; + unsigned long addr = 0xffff0000; + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + + pgd = pgd_offset_k(addr); + pud = pud_offset(pgd, addr); + pmd = pmd_offset(pud, addr); + page = pmd_page(*(pmd)); + + pgtable_page_ctor(page); + + return 0; +} +late_initcall(vectors_user_mapping_init_page); + #ifdef CONFIG_KUSER_HELPERS /* * The vectors page is always readable from user space for the diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c index 55a11de43219..a5e48e612bd8 100644 --- a/arch/arm/kernel/signal.c +++ b/arch/arm/kernel/signal.c @@ -652,7 +652,8 @@ do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall) */ trace_hardirqs_off(); do { - if (likely(thread_flags & _TIF_NEED_RESCHED)) { + if (likely(thread_flags & (_TIF_NEED_RESCHED | + _TIF_NEED_RESCHED_LAZY))) { schedule(); } else { if (unlikely(!user_mode(regs))) diff --git a/arch/arm/mach-at91/Kconfig b/arch/arm/mach-at91/Kconfig index 1254bf9d91b4..64f18cd220b9 100644 --- a/arch/arm/mach-at91/Kconfig +++ b/arch/arm/mach-at91/Kconfig @@ -106,6 +106,31 @@ config SOC_AT91SAM9 AT91SAM9X35 AT91SAM9XE +comment "Clocksource driver selection" + +config ATMEL_CLOCKSOURCE_PIT + bool "Periodic Interval Timer (PIT) support" + depends on SOC_AT91SAM9 || SOC_SAMA5 + default SOC_AT91SAM9 || SOC_SAMA5 + select ATMEL_PIT + help + Select this to get a clocksource based on the Atmel Periodic Interval + Timer. It has a relatively low resolution and the TC Block clocksource + should be preferred. + +config ATMEL_CLOCKSOURCE_TCB + bool "Timer Counter Blocks (TCB) support" + depends on SOC_AT91RM9200 || SOC_AT91SAM9 || SOC_SAMA5 || COMPILE_TEST + default SOC_AT91RM9200 || SOC_AT91SAM9 || SOC_SAMA5 + depends on !ATMEL_TCLIB + select ATMEL_ARM_TCB_CLKSRC + help + Select this to get a high precision clocksource based on a + TC block with a 5+ MHz base clock rate. + On platforms with 16-bit counters, two timer channels are combined + to make a single 32-bit timer. + It can also be used as a clock event device supporting oneshot mode. + config HAVE_AT91_UTMI bool diff --git a/arch/arm/mach-exynos/platsmp.c b/arch/arm/mach-exynos/platsmp.c index 6a1e682371b3..17dca0ff336e 100644 --- a/arch/arm/mach-exynos/platsmp.c +++ b/arch/arm/mach-exynos/platsmp.c @@ -239,7 +239,7 @@ static void write_pen_release(int val) sync_cache_w(&pen_release); } -static DEFINE_SPINLOCK(boot_lock); +static DEFINE_RAW_SPINLOCK(boot_lock); static void exynos_secondary_init(unsigned int cpu) { @@ -252,8 +252,8 @@ static void exynos_secondary_init(unsigned int cpu) /* * Synchronise with the boot thread. */ - spin_lock(&boot_lock); - spin_unlock(&boot_lock); + raw_spin_lock(&boot_lock); + raw_spin_unlock(&boot_lock); } int exynos_set_boot_addr(u32 core_id, unsigned long boot_addr) @@ -317,7 +317,7 @@ static int exynos_boot_secondary(unsigned int cpu, struct task_struct *idle) * Set synchronisation state between this boot processor * and the secondary one */ - spin_lock(&boot_lock); + raw_spin_lock(&boot_lock); /* * The secondary processor is waiting to be released from @@ -344,7 +344,7 @@ static int exynos_boot_secondary(unsigned int cpu, struct task_struct *idle) if (timeout == 0) { printk(KERN_ERR "cpu1 power enable failed"); - spin_unlock(&boot_lock); + raw_spin_unlock(&boot_lock); return -ETIMEDOUT; } } @@ -390,7 +390,7 @@ static int exynos_boot_secondary(unsigned int cpu, struct task_struct *idle) * calibrations, then wait for it to finish */ fail: - spin_unlock(&boot_lock); + raw_spin_unlock(&boot_lock); return pen_release != -1 ? ret : 0; } diff --git a/arch/arm/mach-hisi/platmcpm.c b/arch/arm/mach-hisi/platmcpm.c index f66815c3dd07..00524abd963f 100644 --- a/arch/arm/mach-hisi/platmcpm.c +++ b/arch/arm/mach-hisi/platmcpm.c @@ -61,7 +61,7 @@ static void __iomem *sysctrl, *fabric; static int hip04_cpu_table[HIP04_MAX_CLUSTERS][HIP04_MAX_CPUS_PER_CLUSTER]; -static DEFINE_SPINLOCK(boot_lock); +static DEFINE_RAW_SPINLOCK(boot_lock); static u32 fabric_phys_addr; /* * [0]: bootwrapper physical address @@ -113,7 +113,7 @@ static int hip04_boot_secondary(unsigned int l_cpu, struct task_struct *idle) if (cluster >= HIP04_MAX_CLUSTERS || cpu >= HIP04_MAX_CPUS_PER_CLUSTER) return -EINVAL; - spin_lock_irq(&boot_lock); + raw_spin_lock_irq(&boot_lock); if (hip04_cpu_table[cluster][cpu]) goto out; @@ -147,7 +147,7 @@ static int hip04_boot_secondary(unsigned int l_cpu, struct task_struct *idle) out: hip04_cpu_table[cluster][cpu]++; - spin_unlock_irq(&boot_lock); + raw_spin_unlock_irq(&boot_lock); return 0; } @@ -162,11 +162,11 @@ static void hip04_cpu_die(unsigned int l_cpu) cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0); cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1); - spin_lock(&boot_lock); + raw_spin_lock(&boot_lock); hip04_cpu_table[cluster][cpu]--; if (hip04_cpu_table[cluster][cpu] == 1) { /* A power_up request went ahead of us. */ - spin_unlock(&boot_lock); + raw_spin_unlock(&boot_lock); return; } else if (hip04_cpu_table[cluster][cpu] > 1) { pr_err("Cluster %d CPU%d boots multiple times\n", cluster, cpu); @@ -174,7 +174,7 @@ static void hip04_cpu_die(unsigned int l_cpu) } last_man = hip04_cluster_is_down(cluster); - spin_unlock(&boot_lock); + raw_spin_unlock(&boot_lock); if (last_man) { /* Since it's Cortex A15, disable L2 prefetching. */ asm volatile( @@ -203,7 +203,7 @@ static int hip04_cpu_kill(unsigned int l_cpu) cpu >= HIP04_MAX_CPUS_PER_CLUSTER); count = TIMEOUT_MSEC / POLL_MSEC; - spin_lock_irq(&boot_lock); + raw_spin_lock_irq(&boot_lock); for (tries = 0; tries < count; tries++) { if (hip04_cpu_table[cluster][cpu]) goto err; @@ -211,10 +211,10 @@ static int hip04_cpu_kill(unsigned int l_cpu) data = readl_relaxed(sysctrl + SC_CPU_RESET_STATUS(cluster)); if (data & CORE_WFI_STATUS(cpu)) break; - spin_unlock_irq(&boot_lock); + raw_spin_unlock_irq(&boot_lock); /* Wait for clean L2 when the whole cluster is down. */ msleep(POLL_MSEC); - spin_lock_irq(&boot_lock); + raw_spin_lock_irq(&boot_lock); } if (tries >= count) goto err; @@ -231,10 +231,10 @@ static int hip04_cpu_kill(unsigned int l_cpu) goto err; if (hip04_cluster_is_down(cluster)) hip04_set_snoop_filter(cluster, 0); - spin_unlock_irq(&boot_lock); + raw_spin_unlock_irq(&boot_lock); return 1; err: - spin_unlock_irq(&boot_lock); + raw_spin_unlock_irq(&boot_lock); return 0; } #endif diff --git a/arch/arm/mach-omap2/omap-smp.c b/arch/arm/mach-omap2/omap-smp.c index 1c73694c871a..ac4d2f030b87 100644 --- a/arch/arm/mach-omap2/omap-smp.c +++ b/arch/arm/mach-omap2/omap-smp.c @@ -69,7 +69,7 @@ static const struct omap_smp_config omap5_cfg __initconst = { .startup_addr = omap5_secondary_startup, }; -static DEFINE_SPINLOCK(boot_lock); +static DEFINE_RAW_SPINLOCK(boot_lock); void __iomem *omap4_get_scu_base(void) { @@ -177,8 +177,8 @@ static void omap4_secondary_init(unsigned int cpu) /* * Synchronise with the boot thread. */ - spin_lock(&boot_lock); - spin_unlock(&boot_lock); + raw_spin_lock(&boot_lock); + raw_spin_unlock(&boot_lock); } static int omap4_boot_secondary(unsigned int cpu, struct task_struct *idle) @@ -191,7 +191,7 @@ static int omap4_boot_secondary(unsigned int cpu, struct task_struct *idle) * Set synchronisation state between this boot processor * and the secondary one */ - spin_lock(&boot_lock); + raw_spin_lock(&boot_lock); /* * Update the AuxCoreBoot0 with boot state for secondary core. @@ -270,7 +270,7 @@ static int omap4_boot_secondary(unsigned int cpu, struct task_struct *idle) * Now the secondary core is starting up let it run its * calibrations, then wait for it to finish */ - spin_unlock(&boot_lock); + raw_spin_unlock(&boot_lock); return 0; } diff --git a/arch/arm/mach-prima2/platsmp.c b/arch/arm/mach-prima2/platsmp.c index 75ef5d4be554..c17c86e5d860 100644 --- a/arch/arm/mach-prima2/platsmp.c +++ b/arch/arm/mach-prima2/platsmp.c @@ -22,7 +22,7 @@ static void __iomem *clk_base; -static DEFINE_SPINLOCK(boot_lock); +static DEFINE_RAW_SPINLOCK(boot_lock); static void sirfsoc_secondary_init(unsigned int cpu) { @@ -36,8 +36,8 @@ static void sirfsoc_secondary_init(unsigned int cpu) /* * Synchronise with the boot thread. */ - spin_lock(&boot_lock); - spin_unlock(&boot_lock); + raw_spin_lock(&boot_lock); + raw_spin_unlock(&boot_lock); } static const struct of_device_id clk_ids[] = { @@ -75,7 +75,7 @@ static int sirfsoc_boot_secondary(unsigned int cpu, struct task_struct *idle) /* make sure write buffer is drained */ mb(); - spin_lock(&boot_lock); + raw_spin_lock(&boot_lock); /* * The secondary processor is waiting to be released from @@ -107,7 +107,7 @@ static int sirfsoc_boot_secondary(unsigned int cpu, struct task_struct *idle) * now the secondary core is starting up let it run its * calibrations, then wait for it to finish */ - spin_unlock(&boot_lock); + raw_spin_unlock(&boot_lock); return pen_release != -1 ? -ENOSYS : 0; } diff --git a/arch/arm/mach-qcom/platsmp.c b/arch/arm/mach-qcom/platsmp.c index 5494c9e0c909..e8ce157d3548 100644 --- a/arch/arm/mach-qcom/platsmp.c +++ b/arch/arm/mach-qcom/platsmp.c @@ -46,7 +46,7 @@ extern void secondary_startup_arm(void); -static DEFINE_SPINLOCK(boot_lock); +static DEFINE_RAW_SPINLOCK(boot_lock); #ifdef CONFIG_HOTPLUG_CPU static void qcom_cpu_die(unsigned int cpu) @@ -60,8 +60,8 @@ static void qcom_secondary_init(unsigned int cpu) /* * Synchronise with the boot thread. */ - spin_lock(&boot_lock); - spin_unlock(&boot_lock); + raw_spin_lock(&boot_lock); + raw_spin_unlock(&boot_lock); } static int scss_release_secondary(unsigned int cpu) @@ -284,7 +284,7 @@ static int qcom_boot_secondary(unsigned int cpu, int (*func)(unsigned int)) * set synchronisation state between this boot processor * and the secondary one */ - spin_lock(&boot_lock); + raw_spin_lock(&boot_lock); /* * Send the secondary CPU a soft interrupt, thereby causing @@ -297,7 +297,7 @@ static int qcom_boot_secondary(unsigned int cpu, int (*func)(unsigned int)) * now the secondary core is starting up let it run its * calibrations, then wait for it to finish */ - spin_unlock(&boot_lock); + raw_spin_unlock(&boot_lock); return ret; } diff --git a/arch/arm/mach-spear/platsmp.c b/arch/arm/mach-spear/platsmp.c index 39038a03836a..6da5c93872bf 100644 --- a/arch/arm/mach-spear/platsmp.c +++ b/arch/arm/mach-spear/platsmp.c @@ -32,7 +32,7 @@ static void write_pen_release(int val) sync_cache_w(&pen_release); } -static DEFINE_SPINLOCK(boot_lock); +static DEFINE_RAW_SPINLOCK(boot_lock); static void __iomem *scu_base = IOMEM(VA_SCU_BASE); @@ -47,8 +47,8 @@ static void spear13xx_secondary_init(unsigned int cpu) /* * Synchronise with the boot thread. */ - spin_lock(&boot_lock); - spin_unlock(&boot_lock); + raw_spin_lock(&boot_lock); + raw_spin_unlock(&boot_lock); } static int spear13xx_boot_secondary(unsigned int cpu, struct task_struct *idle) @@ -59,7 +59,7 @@ static int spear13xx_boot_secondary(unsigned int cpu, struct task_struct *idle) * set synchronisation state between this boot processor * and the secondary one */ - spin_lock(&boot_lock); + raw_spin_lock(&boot_lock); /* * The secondary processor is waiting to be released from @@ -84,7 +84,7 @@ static int spear13xx_boot_secondary(unsigned int cpu, struct task_struct *idle) * now the secondary core is starting up let it run its * calibrations, then wait for it to finish */ - spin_unlock(&boot_lock); + raw_spin_unlock(&boot_lock); return pen_release != -1 ? -ENOSYS : 0; } diff --git a/arch/arm/mach-sti/platsmp.c b/arch/arm/mach-sti/platsmp.c index 231f19e17436..a3419b7003e6 100644 --- a/arch/arm/mach-sti/platsmp.c +++ b/arch/arm/mach-sti/platsmp.c @@ -35,7 +35,7 @@ static void write_pen_release(int val) sync_cache_w(&pen_release); } -static DEFINE_SPINLOCK(boot_lock); +static DEFINE_RAW_SPINLOCK(boot_lock); static void sti_secondary_init(unsigned int cpu) { @@ -48,8 +48,8 @@ static void sti_secondary_init(unsigned int cpu) /* * Synchronise with the boot thread. */ - spin_lock(&boot_lock); - spin_unlock(&boot_lock); + raw_spin_lock(&boot_lock); + raw_spin_unlock(&boot_lock); } static int sti_boot_secondary(unsigned int cpu, struct task_struct *idle) @@ -60,7 +60,7 @@ static int sti_boot_secondary(unsigned int cpu, struct task_struct *idle) * set synchronisation state between this boot processor * and the secondary one */ - spin_lock(&boot_lock); + raw_spin_lock(&boot_lock); /* * The secondary processor is waiting to be released from @@ -91,7 +91,7 @@ static int sti_boot_secondary(unsigned int cpu, struct task_struct *idle) * now the secondary core is starting up let it run its * calibrations, then wait for it to finish */ - spin_unlock(&boot_lock); + raw_spin_unlock(&boot_lock); return pen_release != -1 ? -ENOSYS : 0; } diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index 5376744107c1..4b13cfdf8ed6 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -438,6 +438,9 @@ do_translation_fault(unsigned long addr, unsigned int fsr, if (addr < TASK_SIZE) return do_page_fault(addr, fsr, regs); + if (interrupts_enabled(regs)) + local_irq_enable(); + if (user_mode(regs)) goto bad_area; @@ -514,6 +517,9 @@ do_translation_fault(unsigned long addr, unsigned int fsr, static int do_sect_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs) { + if (interrupts_enabled(regs)) + local_irq_enable(); + do_bad_area(addr, fsr, regs); return 0; } diff --git a/arch/arm/mm/highmem.c b/arch/arm/mm/highmem.c index d02f8187b1cc..542692dbd40a 100644 --- a/arch/arm/mm/highmem.c +++ b/arch/arm/mm/highmem.c @@ -34,6 +34,11 @@ static inline pte_t get_fixmap_pte(unsigned long vaddr) return *ptep; } +static unsigned int fixmap_idx(int type) +{ + return FIX_KMAP_BEGIN + type + KM_TYPE_NR * smp_processor_id(); +} + void *kmap(struct page *page) { might_sleep(); @@ -54,12 +59,13 @@ EXPORT_SYMBOL(kunmap); void *kmap_atomic(struct page *page) { + pte_t pte = mk_pte(page, kmap_prot); unsigned int idx; unsigned long vaddr; void *kmap; int type; - preempt_disable(); + preempt_disable_nort(); pagefault_disable(); if (!PageHighMem(page)) return page_address(page); @@ -79,7 +85,7 @@ void *kmap_atomic(struct page *page) type = kmap_atomic_idx_push(); - idx = FIX_KMAP_BEGIN + type + KM_TYPE_NR * smp_processor_id(); + idx = fixmap_idx(type); vaddr = __fix_to_virt(idx); #ifdef CONFIG_DEBUG_HIGHMEM /* @@ -93,7 +99,10 @@ void *kmap_atomic(struct page *page) * in place, so the contained TLB flush ensures the TLB is updated * with the new mapping. */ - set_fixmap_pte(idx, mk_pte(page, kmap_prot)); +#ifdef CONFIG_PREEMPT_RT_FULL + current->kmap_pte[type] = pte; +#endif + set_fixmap_pte(idx, pte); return (void *)vaddr; } @@ -106,44 +115,75 @@ void __kunmap_atomic(void *kvaddr) if (kvaddr >= (void *)FIXADDR_START) { type = kmap_atomic_idx(); - idx = FIX_KMAP_BEGIN + type + KM_TYPE_NR * smp_processor_id(); + idx = fixmap_idx(type); if (cache_is_vivt()) __cpuc_flush_dcache_area((void *)vaddr, PAGE_SIZE); +#ifdef CONFIG_PREEMPT_RT_FULL + current->kmap_pte[type] = __pte(0); +#endif #ifdef CONFIG_DEBUG_HIGHMEM BUG_ON(vaddr != __fix_to_virt(idx)); - set_fixmap_pte(idx, __pte(0)); #else (void) idx; /* to kill a warning */ #endif + set_fixmap_pte(idx, __pte(0)); kmap_atomic_idx_pop(); } else if (vaddr >= PKMAP_ADDR(0) && vaddr < PKMAP_ADDR(LAST_PKMAP)) { /* this address was obtained through kmap_high_get() */ kunmap_high(pte_page(pkmap_page_table[PKMAP_NR(vaddr)])); } pagefault_enable(); - preempt_enable(); + preempt_enable_nort(); } EXPORT_SYMBOL(__kunmap_atomic); void *kmap_atomic_pfn(unsigned long pfn) { + pte_t pte = pfn_pte(pfn, kmap_prot); unsigned long vaddr; int idx, type; struct page *page = pfn_to_page(pfn); - preempt_disable(); + preempt_disable_nort(); pagefault_disable(); if (!PageHighMem(page)) return page_address(page); type = kmap_atomic_idx_push(); - idx = FIX_KMAP_BEGIN + type + KM_TYPE_NR * smp_processor_id(); + idx = fixmap_idx(type); vaddr = __fix_to_virt(idx); #ifdef CONFIG_DEBUG_HIGHMEM BUG_ON(!pte_none(get_fixmap_pte(vaddr))); #endif - set_fixmap_pte(idx, pfn_pte(pfn, kmap_prot)); +#ifdef CONFIG_PREEMPT_RT_FULL + current->kmap_pte[type] = pte; +#endif + set_fixmap_pte(idx, pte); return (void *)vaddr; } +#if defined CONFIG_PREEMPT_RT_FULL +void switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p) +{ + int i; + + /* + * Clear @prev's kmap_atomic mappings + */ + for (i = 0; i < prev_p->kmap_idx; i++) { + int idx = fixmap_idx(i); + + set_fixmap_pte(idx, __pte(0)); + } + /* + * Restore @next_p's kmap_atomic mappings + */ + for (i = 0; i < next_p->kmap_idx; i++) { + int idx = fixmap_idx(i); + + if (!pte_none(next_p->kmap_pte[i])) + set_fixmap_pte(idx, next_p->kmap_pte[i]); + } +} +#endif diff --git a/arch/arm/plat-versatile/platsmp.c b/arch/arm/plat-versatile/platsmp.c index c2366510187a..6b60f582b738 100644 --- a/arch/arm/plat-versatile/platsmp.c +++ b/arch/arm/plat-versatile/platsmp.c @@ -32,7 +32,7 @@ static void write_pen_release(int val) sync_cache_w(&pen_release); } -static DEFINE_SPINLOCK(boot_lock); +static DEFINE_RAW_SPINLOCK(boot_lock); void versatile_secondary_init(unsigned int cpu) { @@ -45,8 +45,8 @@ void versatile_secondary_init(unsigned int cpu) /* * Synchronise with the boot thread. */ - spin_lock(&boot_lock); - spin_unlock(&boot_lock); + raw_spin_lock(&boot_lock); + raw_spin_unlock(&boot_lock); } int versatile_boot_secondary(unsigned int cpu, struct task_struct *idle) @@ -57,7 +57,7 @@ int versatile_boot_secondary(unsigned int cpu, struct task_struct *idle) * Set synchronisation state between this boot processor * and the secondary one */ - spin_lock(&boot_lock); + raw_spin_lock(&boot_lock); /* * This is really belt and braces; we hold unintended secondary @@ -87,7 +87,7 @@ int versatile_boot_secondary(unsigned int cpu, struct task_struct *idle) * now the secondary core is starting up let it run its * calibrations, then wait for it to finish */ - spin_unlock(&boot_lock); + raw_spin_unlock(&boot_lock); return pen_release != -1 ? -ENOSYS : 0; } diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 3eb034189cf8..4a7e133bf1eb 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -125,6 +125,7 @@ config ARM64 select HAVE_PERF_EVENTS select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP + select HAVE_PREEMPT_LAZY select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_RCU_TABLE_FREE select HAVE_STACKPROTECTOR diff --git a/arch/arm64/crypto/Kconfig b/arch/arm64/crypto/Kconfig index d51944ff9f91..0d4b3f0cfba6 100644 --- a/arch/arm64/crypto/Kconfig +++ b/arch/arm64/crypto/Kconfig @@ -19,43 +19,43 @@ config CRYPTO_SHA512_ARM64 config CRYPTO_SHA1_ARM64_CE tristate "SHA-1 digest algorithm (ARMv8 Crypto Extensions)" - depends on KERNEL_MODE_NEON + depends on KERNEL_MODE_NEON && !PREEMPT_RT_BASE select CRYPTO_HASH select CRYPTO_SHA1 config CRYPTO_SHA2_ARM64_CE tristate "SHA-224/SHA-256 digest algorithm (ARMv8 Crypto Extensions)" - depends on KERNEL_MODE_NEON + depends on KERNEL_MODE_NEON && !PREEMPT_RT_BASE select CRYPTO_HASH select CRYPTO_SHA256_ARM64 config CRYPTO_SHA512_ARM64_CE tristate "SHA-384/SHA-512 digest algorithm (ARMv8 Crypto Extensions)" - depends on KERNEL_MODE_NEON + depends on KERNEL_MODE_NEON && !PREEMPT_RT_BASE select CRYPTO_HASH select CRYPTO_SHA512_ARM64 config CRYPTO_SHA3_ARM64 tristate "SHA3 digest algorithm (ARMv8.2 Crypto Extensions)" - depends on KERNEL_MODE_NEON + depends on KERNEL_MODE_NEON && !PREEMPT_RT_BASE select CRYPTO_HASH select CRYPTO_SHA3 config CRYPTO_SM3_ARM64_CE tristate "SM3 digest algorithm (ARMv8.2 Crypto Extensions)" - depends on KERNEL_MODE_NEON + depends on KERNEL_MODE_NEON && !PREEMPT_RT_BASE select CRYPTO_HASH select CRYPTO_SM3 config CRYPTO_SM4_ARM64_CE tristate "SM4 symmetric cipher (ARMv8.2 Crypto Extensions)" - depends on KERNEL_MODE_NEON + depends on KERNEL_MODE_NEON && !PREEMPT_RT_BASE select CRYPTO_ALGAPI select CRYPTO_SM4 config CRYPTO_GHASH_ARM64_CE tristate "GHASH/AES-GCM using ARMv8 Crypto Extensions" - depends on KERNEL_MODE_NEON + depends on KERNEL_MODE_NEON && !PREEMPT_RT_BASE select CRYPTO_HASH select CRYPTO_GF128MUL select CRYPTO_AES @@ -63,7 +63,7 @@ config CRYPTO_GHASH_ARM64_CE config CRYPTO_CRCT10DIF_ARM64_CE tristate "CRCT10DIF digest algorithm using PMULL instructions" - depends on KERNEL_MODE_NEON && CRC_T10DIF + depends on KERNEL_MODE_NEON && CRC_T10DIF && !PREEMPT_RT_BASE select CRYPTO_HASH config CRYPTO_CRC32_ARM64_CE @@ -77,13 +77,13 @@ config CRYPTO_AES_ARM64 config CRYPTO_AES_ARM64_CE tristate "AES core cipher using ARMv8 Crypto Extensions" - depends on ARM64 && KERNEL_MODE_NEON + depends on ARM64 && KERNEL_MODE_NEON && !PREEMPT_RT_BASE select CRYPTO_ALGAPI select CRYPTO_AES_ARM64 config CRYPTO_AES_ARM64_CE_CCM tristate "AES in CCM mode using ARMv8 Crypto Extensions" - depends on ARM64 && KERNEL_MODE_NEON + depends on ARM64 && KERNEL_MODE_NEON && !PREEMPT_RT_BASE select CRYPTO_ALGAPI select CRYPTO_AES_ARM64_CE select CRYPTO_AES_ARM64 @@ -91,7 +91,7 @@ config CRYPTO_AES_ARM64_CE_CCM config CRYPTO_AES_ARM64_CE_BLK tristate "AES in ECB/CBC/CTR/XTS modes using ARMv8 Crypto Extensions" - depends on KERNEL_MODE_NEON + depends on KERNEL_MODE_NEON && !PREEMPT_RT_BASE select CRYPTO_BLKCIPHER select CRYPTO_AES_ARM64_CE select CRYPTO_AES_ARM64 @@ -99,7 +99,7 @@ config CRYPTO_AES_ARM64_CE_BLK config CRYPTO_AES_ARM64_NEON_BLK tristate "AES in ECB/CBC/CTR/XTS modes using NEON instructions" - depends on KERNEL_MODE_NEON + depends on KERNEL_MODE_NEON && !PREEMPT_RT_BASE select CRYPTO_BLKCIPHER select CRYPTO_AES_ARM64 select CRYPTO_AES @@ -107,13 +107,13 @@ config CRYPTO_AES_ARM64_NEON_BLK config CRYPTO_CHACHA20_NEON tristate "NEON accelerated ChaCha20 symmetric cipher" - depends on KERNEL_MODE_NEON + depends on KERNEL_MODE_NEON && !PREEMPT_RT_BASE select CRYPTO_BLKCIPHER select CRYPTO_CHACHA20 config CRYPTO_AES_ARM64_BS tristate "AES in ECB/CBC/CTR/XTS modes using bit-sliced NEON algorithm" - depends on KERNEL_MODE_NEON + depends on KERNEL_MODE_NEON && !PREEMPT_RT_BASE select CRYPTO_BLKCIPHER select CRYPTO_AES_ARM64_NEON_BLK select CRYPTO_AES_ARM64 diff --git a/arch/arm64/crypto/crc32-ce-glue.c b/arch/arm64/crypto/crc32-ce-glue.c index 34b4e3d46aab..ae055cdad8cf 100644 --- a/arch/arm64/crypto/crc32-ce-glue.c +++ b/arch/arm64/crypto/crc32-ce-glue.c @@ -208,7 +208,8 @@ static struct shash_alg crc32_pmull_algs[] = { { static int __init crc32_pmull_mod_init(void) { - if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) && (elf_hwcap & HWCAP_PMULL)) { + if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) && + !IS_ENABLED(CONFIG_PREEMPT_RT_BASE) && (elf_hwcap & HWCAP_PMULL)) { crc32_pmull_algs[0].update = crc32_pmull_update; crc32_pmull_algs[1].update = crc32c_pmull_update; diff --git a/arch/arm64/include/asm/alternative.h b/arch/arm64/include/asm/alternative.h index 4b650ec1d7dd..f561ea0ac645 100644 --- a/arch/arm64/include/asm/alternative.h +++ b/arch/arm64/include/asm/alternative.h @@ -35,6 +35,12 @@ void apply_alternatives_module(void *start, size_t length); static inline void apply_alternatives_module(void *start, size_t length) { } #endif +#ifdef CONFIG_KVM_ARM_HOST +void kvm_compute_layout(void); +#else +static inline void kvm_compute_layout(void) { } +#endif + #define ALTINSTR_ENTRY(feature,cb) \ " .word 661b - .\n" /* label */ \ " .if " __stringify(cb) " == 0\n" \ diff --git a/arch/arm64/include/asm/spinlock_types.h b/arch/arm64/include/asm/spinlock_types.h index 6b856012c51b..be584db25d51 100644 --- a/arch/arm64/include/asm/spinlock_types.h +++ b/arch/arm64/include/asm/spinlock_types.h @@ -16,10 +16,6 @@ #ifndef __ASM_SPINLOCK_TYPES_H #define __ASM_SPINLOCK_TYPES_H -#if !defined(__LINUX_SPINLOCK_TYPES_H) && !defined(__ASM_SPINLOCK_H) -# error "please don't include this file directly" -#endif - #include <linux/types.h> #define TICKET_SHIFT 16 diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h index cb2c10a8f0a8..f1820f7318b6 100644 --- a/arch/arm64/include/asm/thread_info.h +++ b/arch/arm64/include/asm/thread_info.h @@ -43,6 +43,7 @@ struct thread_info { u64 ttbr0; /* saved TTBR0_EL1 */ #endif int preempt_count; /* 0 => preemptable, <0 => bug */ + int preempt_lazy_count; /* 0 => preemptable, <0 => bug */ }; #define thread_saved_pc(tsk) \ @@ -76,6 +77,7 @@ void arch_release_task_struct(struct task_struct *tsk); #define TIF_FOREIGN_FPSTATE 3 /* CPU's FP state is not current's */ #define TIF_UPROBE 4 /* uprobe breakpoint or singlestep */ #define TIF_FSCHECK 5 /* Check FS is USER_DS on return */ +#define TIF_NEED_RESCHED_LAZY 6 #define TIF_NOHZ 7 #define TIF_SYSCALL_TRACE 8 #define TIF_SYSCALL_AUDIT 9 @@ -94,6 +96,7 @@ void arch_release_task_struct(struct task_struct *tsk); #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) #define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME) #define _TIF_FOREIGN_FPSTATE (1 << TIF_FOREIGN_FPSTATE) +#define _TIF_NEED_RESCHED_LAZY (1 << TIF_NEED_RESCHED_LAZY) #define _TIF_NOHZ (1 << TIF_NOHZ) #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) @@ -106,8 +109,9 @@ void arch_release_task_struct(struct task_struct *tsk); #define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \ _TIF_NOTIFY_RESUME | _TIF_FOREIGN_FPSTATE | \ - _TIF_UPROBE | _TIF_FSCHECK) + _TIF_UPROBE | _TIF_FSCHECK | _TIF_NEED_RESCHED_LAZY) +#define _TIF_NEED_RESCHED_MASK (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY) #define _TIF_SYSCALL_WORK (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \ _TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP | \ _TIF_NOHZ) diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c index 36fb069fd049..ea3dd7b09e04 100644 --- a/arch/arm64/kernel/alternative.c +++ b/arch/arm64/kernel/alternative.c @@ -224,6 +224,7 @@ static int __apply_alternatives_multi_stop(void *unused) void __init apply_alternatives_all(void) { /* better not try code patching on a live SMP system */ + kvm_compute_layout(); stop_machine(__apply_alternatives_multi_stop, NULL, cpu_online_mask); } diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index 92fba851ce53..844c71bc865b 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -41,6 +41,7 @@ int main(void) BLANK(); DEFINE(TSK_TI_FLAGS, offsetof(struct task_struct, thread_info.flags)); DEFINE(TSK_TI_PREEMPT, offsetof(struct task_struct, thread_info.preempt_count)); + DEFINE(TSK_TI_PREEMPT_LAZY, offsetof(struct task_struct, thread_info.preempt_lazy_count)); DEFINE(TSK_TI_ADDR_LIMIT, offsetof(struct task_struct, thread_info.addr_limit)); #ifdef CONFIG_ARM64_SW_TTBR0_PAN DEFINE(TSK_TI_TTBR0, offsetof(struct task_struct, thread_info.ttbr0)); diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index b0db91eefbde..85ad8f844dc9 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -633,11 +633,16 @@ el1_irq: #ifdef CONFIG_PREEMPT ldr w24, [tsk, #TSK_TI_PREEMPT] // get preempt count - cbnz w24, 1f // preempt count != 0 + cbnz w24, 2f // preempt count != 0 ldr x0, [tsk, #TSK_TI_FLAGS] // get flags - tbz x0, #TIF_NEED_RESCHED, 1f // needs rescheduling? - bl el1_preempt + tbnz x0, #TIF_NEED_RESCHED, 1f // needs rescheduling? + + ldr w24, [tsk, #TSK_TI_PREEMPT_LAZY] // get preempt lazy count + cbnz w24, 2f // preempt lazy count != 0 + tbz x0, #TIF_NEED_RESCHED_LAZY, 2f // needs rescheduling? 1: + bl el1_preempt +2: #endif #ifdef CONFIG_TRACE_IRQFLAGS bl trace_hardirqs_on @@ -651,6 +656,7 @@ el1_preempt: 1: bl preempt_schedule_irq // irq en/disable is done inside ldr x0, [tsk, #TSK_TI_FLAGS] // get new tasks TI_FLAGS tbnz x0, #TIF_NEED_RESCHED, 1b // needs rescheduling? + tbnz x0, #TIF_NEED_RESCHED_LAZY, 1b // needs rescheduling? ret x24 #endif diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 84c68b14f1b2..8f0a5993ba66 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -159,6 +159,16 @@ static void sve_free(struct task_struct *task) __sve_free(task); } +static void *sve_free_atomic(struct task_struct *task) +{ + void *sve_state = task->thread.sve_state; + + WARN_ON(test_tsk_thread_flag(task, TIF_SVE)); + + task->thread.sve_state = NULL; + return sve_state; +} + static void change_cpacr(u64 val, u64 mask) { u64 cpacr = read_sysreg(CPACR_EL1); @@ -566,6 +576,7 @@ int sve_set_vector_length(struct task_struct *task, * non-SVE thread. */ if (task == current) { + preempt_disable(); local_bh_disable(); fpsimd_save(); @@ -576,8 +587,10 @@ int sve_set_vector_length(struct task_struct *task, if (test_and_clear_tsk_thread_flag(task, TIF_SVE)) sve_to_fpsimd(task); - if (task == current) + if (task == current) { local_bh_enable(); + preempt_enable(); + } /* * Force reallocation of task SVE state to the correct size @@ -832,6 +845,7 @@ asmlinkage void do_sve_acc(unsigned int esr, struct pt_regs *regs) sve_alloc(current); + preempt_disable(); local_bh_disable(); fpsimd_save(); @@ -845,6 +859,7 @@ asmlinkage void do_sve_acc(unsigned int esr, struct pt_regs *regs) WARN_ON(1); /* SVE access shouldn't have trapped */ local_bh_enable(); + preempt_enable(); } /* @@ -911,10 +926,12 @@ void fpsimd_thread_switch(struct task_struct *next) void fpsimd_flush_thread(void) { int vl, supported_vl; + void *mem = NULL; if (!system_supports_fpsimd()) return; + preempt_disable(); local_bh_disable(); memset(¤t->thread.uw.fpsimd_state, 0, @@ -923,7 +940,7 @@ void fpsimd_flush_thread(void) if (system_supports_sve()) { clear_thread_flag(TIF_SVE); - sve_free(current); + mem = sve_free_atomic(current); /* * Reset the task vector length as required. @@ -959,6 +976,8 @@ void fpsimd_flush_thread(void) set_thread_flag(TIF_FOREIGN_FPSTATE); local_bh_enable(); + preempt_enable(); + kfree(mem); } /* @@ -970,9 +989,11 @@ void fpsimd_preserve_current_state(void) if (!system_supports_fpsimd()) return; + preempt_disable(); local_bh_disable(); fpsimd_save(); local_bh_enable(); + preempt_enable(); } /* @@ -1030,6 +1051,7 @@ void fpsimd_restore_current_state(void) if (!system_supports_fpsimd()) return; + preempt_disable(); local_bh_disable(); if (test_and_clear_thread_flag(TIF_FOREIGN_FPSTATE)) { @@ -1038,6 +1060,7 @@ void fpsimd_restore_current_state(void) } local_bh_enable(); + preempt_enable(); } /* @@ -1050,6 +1073,7 @@ void fpsimd_update_current_state(struct user_fpsimd_state const *state) if (!system_supports_fpsimd()) return; + preempt_disable(); local_bh_disable(); current->thread.uw.fpsimd_state = *state; @@ -1062,6 +1086,7 @@ void fpsimd_update_current_state(struct user_fpsimd_state const *state) clear_thread_flag(TIF_FOREIGN_FPSTATE); local_bh_enable(); + preempt_enable(); } /* @@ -1107,6 +1132,7 @@ void kernel_neon_begin(void) BUG_ON(!may_use_simd()); + preempt_disable(); local_bh_disable(); __this_cpu_write(kernel_neon_busy, true); @@ -1120,6 +1146,7 @@ void kernel_neon_begin(void) preempt_disable(); local_bh_enable(); + preempt_enable(); } EXPORT_SYMBOL(kernel_neon_begin); diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index 511af13e8d8f..fb48b87826ed 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -923,7 +923,7 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, /* Check valid user FS if needed */ addr_limit_user_check(); - if (thread_flags & _TIF_NEED_RESCHED) { + if (thread_flags & _TIF_NEED_RESCHED_MASK) { /* Unmask Debug and SError for the next task */ local_daif_restore(DAIF_PROCCTX_NOIRQ); diff --git a/arch/arm64/kvm/va_layout.c b/arch/arm64/kvm/va_layout.c index c712a7376bc1..792da0e125de 100644 --- a/arch/arm64/kvm/va_layout.c +++ b/arch/arm64/kvm/va_layout.c @@ -33,7 +33,7 @@ static u8 tag_lsb; static u64 tag_val; static u64 va_mask; -static void compute_layout(void) +__init void kvm_compute_layout(void) { phys_addr_t idmap_addr = __pa_symbol(__hyp_idmap_text_start); u64 hyp_va_msb; @@ -121,8 +121,6 @@ void __init kvm_update_va_mask(struct alt_instr *alt, BUG_ON(nr_inst != 5); - if (!has_vhe() && !va_mask) - compute_layout(); for (i = 0; i < nr_inst; i++) { u32 rd, rn, insn, oinsn; @@ -167,9 +165,6 @@ void kvm_patch_vector_branch(struct alt_instr *alt, return; } - if (!va_mask) - compute_layout(); - /* * Compute HYP VA by using the same computation as kern_hyp_va() */ diff --git a/arch/hexagon/include/asm/spinlock_types.h b/arch/hexagon/include/asm/spinlock_types.h index 7a906b5214a4..d8f596fec022 100644 --- a/arch/hexagon/include/asm/spinlock_types.h +++ b/arch/hexagon/include/asm/spinlock_types.h @@ -21,10 +21,6 @@ #ifndef _ASM_SPINLOCK_TYPES_H #define _ASM_SPINLOCK_TYPES_H -#ifndef __LINUX_SPINLOCK_TYPES_H -# error "please don't include this file directly" -#endif - typedef struct { volatile unsigned int lock; } arch_spinlock_t; diff --git a/arch/ia64/include/asm/spinlock_types.h b/arch/ia64/include/asm/spinlock_types.h index 6e345fefcdca..681408d6816f 100644 --- a/arch/ia64/include/asm/spinlock_types.h +++ b/arch/ia64/include/asm/spinlock_types.h @@ -2,10 +2,6 @@ #ifndef _ASM_IA64_SPINLOCK_TYPES_H #define _ASM_IA64_SPINLOCK_TYPES_H -#ifndef __LINUX_SPINLOCK_TYPES_H -# error "please don't include this file directly" -#endif - typedef struct { volatile unsigned int lock; } arch_spinlock_t; diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c index 6115464d5f03..f09e34c8409c 100644 --- a/arch/ia64/kernel/mca.c +++ b/arch/ia64/kernel/mca.c @@ -1824,7 +1824,7 @@ format_mca_init_stack(void *mca_data, unsigned long offset, ti->cpu = cpu; p->stack = ti; p->state = TASK_UNINTERRUPTIBLE; - cpumask_set_cpu(cpu, &p->cpus_allowed); + cpumask_set_cpu(cpu, &p->cpus_mask); INIT_LIST_HEAD(&p->tasks); p->parent = p->real_parent = p->group_leader = p; INIT_LIST_HEAD(&p->children); diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 818107118507..bd154497a4b2 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -2522,7 +2522,7 @@ config MIPS_CRC_SUPPORT # config HIGHMEM bool "High Memory Support" - depends on 32BIT && CPU_SUPPORTS_HIGHMEM && SYS_SUPPORTS_HIGHMEM && !CPU_MIPS32_3_5_EVA + depends on 32BIT && CPU_SUPPORTS_HIGHMEM && SYS_SUPPORTS_HIGHMEM && !CPU_MIPS32_3_5_EVA && !PREEMPT_RT_FULL config CPU_SUPPORTS_HIGHMEM bool diff --git a/arch/mips/include/asm/switch_to.h b/arch/mips/include/asm/switch_to.h index e610473d61b8..1428b4febbc9 100644 --- a/arch/mips/include/asm/switch_to.h +++ b/arch/mips/include/asm/switch_to.h @@ -42,7 +42,7 @@ extern struct task_struct *ll_task; * inline to try to keep the overhead down. If we have been forced to run on * a "CPU" with an FPU because of a previous high level of FP computation, * but did not actually use the FPU during the most recent time-slice (CU1 - * isn't set), we undo the restriction on cpus_allowed. + * isn't set), we undo the restriction on cpus_mask. * * We're not calling set_cpus_allowed() here, because we have no need to * force prompt migration - we're already switching the current CPU to a @@ -57,7 +57,7 @@ do { \ test_ti_thread_flag(__prev_ti, TIF_FPUBOUND) && \ (!(KSTK_STATUS(prev) & ST0_CU1))) { \ clear_ti_thread_flag(__prev_ti, TIF_FPUBOUND); \ - prev->cpus_allowed = prev->thread.user_cpus_allowed; \ + prev->cpus_mask = prev->thread.user_cpus_allowed; \ } \ next->thread.emulated_fp = 0; \ } while(0) diff --git a/arch/mips/kernel/mips-mt-fpaff.c b/arch/mips/kernel/mips-mt-fpaff.c index a7c0f97e4b0d..1a08428eedcf 100644 --- a/arch/mips/kernel/mips-mt-fpaff.c +++ b/arch/mips/kernel/mips-mt-fpaff.c @@ -177,7 +177,7 @@ asmlinkage long mipsmt_sys_sched_getaffinity(pid_t pid, unsigned int len, if (retval) goto out_unlock; - cpumask_or(&allowed, &p->thread.user_cpus_allowed, &p->cpus_allowed); + cpumask_or(&allowed, &p->thread.user_cpus_allowed, p->cpus_ptr); cpumask_and(&mask, &allowed, cpu_active_mask); out_unlock: diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index 8d505a21396e..a86468a49e1e 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -1176,12 +1176,12 @@ static void mt_ase_fp_affinity(void) * restricted the allowed set to exclude any CPUs with FPUs, * we'll skip the procedure. */ - if (cpumask_intersects(¤t->cpus_allowed, &mt_fpu_cpumask)) { + if (cpumask_intersects(¤t->cpus_mask, &mt_fpu_cpumask)) { cpumask_t tmask; current->thread.user_cpus_allowed - = current->cpus_allowed; - cpumask_and(&tmask, ¤t->cpus_allowed, + = current->cpus_mask; + cpumask_and(&tmask, ¤t->cpus_mask, &mt_fpu_cpumask); set_cpus_allowed_ptr(current, &tmask); set_thread_flag(TIF_FPUBOUND); diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 709a0fb05536..04de824c73c6 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -105,10 +105,11 @@ config LOCKDEP_SUPPORT config RWSEM_GENERIC_SPINLOCK bool + default y if PREEMPT_RT_FULL config RWSEM_XCHGADD_ALGORITHM bool - default y + default y if !PREEMPT_RT_FULL config GENERIC_LOCKBREAK bool @@ -214,6 +215,7 @@ config PPC select HAVE_HARDLOCKUP_DETECTOR_PERF if PERF_EVENTS && HAVE_PERF_EVENTS_NMI && !HAVE_HARDLOCKUP_DETECTOR_ARCH select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP + select HAVE_PREEMPT_LAZY select HAVE_RCU_TABLE_FREE if SMP select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_RELIABLE_STACKTRACE if PPC64 && CPU_LITTLE_ENDIAN @@ -399,7 +401,7 @@ menu "Kernel options" config HIGHMEM bool "High memory support" - depends on PPC32 + depends on PPC32 && !PREEMPT_RT_FULL source kernel/Kconfig.hz source kernel/Kconfig.preempt diff --git a/arch/powerpc/include/asm/spinlock_types.h b/arch/powerpc/include/asm/spinlock_types.h index 87adaf13b7e8..7305cb6a53e4 100644 --- a/arch/powerpc/include/asm/spinlock_types.h +++ b/arch/powerpc/include/asm/spinlock_types.h @@ -2,10 +2,6 @@ #ifndef _ASM_POWERPC_SPINLOCK_TYPES_H #define _ASM_POWERPC_SPINLOCK_TYPES_H -#ifndef __LINUX_SPINLOCK_TYPES_H -# error "please don't include this file directly" -#endif - typedef struct { volatile unsigned int slock; } arch_spinlock_t; diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h index f308dfeb2746..15c2c0925b6c 100644 --- a/arch/powerpc/include/asm/thread_info.h +++ b/arch/powerpc/include/asm/thread_info.h @@ -36,6 +36,8 @@ struct thread_info { int cpu; /* cpu we're on */ int preempt_count; /* 0 => preemptable, <0 => BUG */ + int preempt_lazy_count; /* 0 => preemptable, + <0 => BUG */ unsigned long local_flags; /* private flags for thread */ #ifdef CONFIG_LIVEPATCH unsigned long *livepatch_sp; @@ -80,7 +82,7 @@ extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src #define TIF_SIGPENDING 1 /* signal pending */ #define TIF_NEED_RESCHED 2 /* rescheduling necessary */ #define TIF_FSCHECK 3 /* Check FS is USER_DS on return */ -#define TIF_32BIT 4 /* 32 bit binary */ +#define TIF_NEED_RESCHED_LAZY 4 /* lazy rescheduling necessary */ #define TIF_RESTORE_TM 5 /* need to restore TM FP/VEC/VSX */ #define TIF_PATCH_PENDING 6 /* pending live patching update */ #define TIF_SYSCALL_AUDIT 7 /* syscall auditing active */ @@ -99,6 +101,7 @@ extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src #define TIF_ELF2ABI 18 /* function descriptors must die! */ #endif #define TIF_POLLING_NRFLAG 19 /* true if poll_idle() is polling TIF_NEED_RESCHED */ +#define TIF_32BIT 20 /* 32 bit binary */ /* as above, but as bit values */ #define _TIF_SYSCALL_TRACE (1<<TIF_SYSCALL_TRACE) @@ -118,6 +121,7 @@ extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src #define _TIF_SYSCALL_TRACEPOINT (1<<TIF_SYSCALL_TRACEPOINT) #define _TIF_EMULATE_STACK_STORE (1<<TIF_EMULATE_STACK_STORE) #define _TIF_NOHZ (1<<TIF_NOHZ) +#define _TIF_NEED_RESCHED_LAZY (1<<TIF_NEED_RESCHED_LAZY) #define _TIF_FSCHECK (1<<TIF_FSCHECK) #define _TIF_SYSCALL_DOTRACE (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \ _TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT | \ @@ -126,8 +130,9 @@ extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src #define _TIF_USER_WORK_MASK (_TIF_SIGPENDING | _TIF_NEED_RESCHED | \ _TIF_NOTIFY_RESUME | _TIF_UPROBE | \ _TIF_RESTORE_TM | _TIF_PATCH_PENDING | \ - _TIF_FSCHECK) + _TIF_FSCHECK | _TIF_NEED_RESCHED_LAZY) #define _TIF_PERSYSCALL_MASK (_TIF_RESTOREALL|_TIF_NOERROR) +#define _TIF_NEED_RESCHED_MASK (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY) /* Bits in local_flags */ /* Don't move TLF_NAPPING without adjusting the code in entry_32.S */ diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 0a0544335950..13faf1055b81 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -156,6 +156,7 @@ int main(void) OFFSET(TI_FLAGS, thread_info, flags); OFFSET(TI_LOCAL_FLAGS, thread_info, local_flags); OFFSET(TI_PREEMPT, thread_info, preempt_count); + OFFSET(TI_PREEMPT_LAZY, thread_info, preempt_lazy_count); OFFSET(TI_TASK, thread_info, task); OFFSET(TI_CPU, thread_info, cpu); diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index 5e7a46f25b00..bd175d11d5a9 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -886,7 +886,14 @@ resume_kernel: cmpwi 0,r0,0 /* if non-zero, just restore regs and return */ bne restore andi. r8,r8,_TIF_NEED_RESCHED + bne+ 1f + lwz r0,TI_PREEMPT_LAZY(r9) + cmpwi 0,r0,0 /* if non-zero, just restore regs and return */ + bne restore + lwz r0,TI_FLAGS(r9) + andi. r0,r0,_TIF_NEED_RESCHED_LAZY beq+ restore +1: lwz r3,_MSR(r1) andi. r0,r3,MSR_EE /* interrupts off? */ beq restore /* don't schedule if so */ @@ -897,11 +904,11 @@ resume_kernel: */ bl trace_hardirqs_off #endif -1: bl preempt_schedule_irq +2: bl preempt_schedule_irq CURRENT_THREAD_INFO(r9, r1) lwz r3,TI_FLAGS(r9) - andi. r0,r3,_TIF_NEED_RESCHED - bne- 1b + andi. r0,r3,_TIF_NEED_RESCHED_MASK + bne- 2b #ifdef CONFIG_TRACE_IRQFLAGS /* And now, to properly rebalance the above, we tell lockdep they * are being turned back on, which will happen when we return @@ -1230,7 +1237,7 @@ global_dbcr0: #endif /* !(CONFIG_4xx || CONFIG_BOOKE) */ do_work: /* r10 contains MSR_KERNEL here */ - andi. r0,r9,_TIF_NEED_RESCHED + andi. r0,r9,_TIF_NEED_RESCHED_MASK beq do_user_signal do_resched: /* r10 contains MSR_KERNEL here */ @@ -1251,7 +1258,7 @@ recheck: MTMSRD(r10) /* disable interrupts */ CURRENT_THREAD_INFO(r9, r1) lwz r9,TI_FLAGS(r9) - andi. r0,r9,_TIF_NEED_RESCHED + andi. r0,r9,_TIF_NEED_RESCHED_MASK bne- do_resched andi. r0,r9,_TIF_USER_WORK_MASK beq restore_user diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 88f5930bba2a..05df11e9ebb2 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -174,7 +174,7 @@ system_call: /* label this so stack traces look sane */ * based on caller's run-mode / personality. */ ld r11,SYS_CALL_TABLE@toc(2) - andi. r10,r10,_TIF_32BIT + andis. r10,r10,_TIF_32BIT@h beq 15f addi r11,r11,8 /* use 32-bit syscall entries */ clrldi r3,r3,32 @@ -766,7 +766,7 @@ _GLOBAL(ret_from_except_lite) bl restore_math b restore #endif -1: andi. r0,r4,_TIF_NEED_RESCHED +1: andi. r0,r4,_TIF_NEED_RESCHED_MASK beq 2f bl restore_interrupts SCHEDULE_USER @@ -828,10 +828,18 @@ resume_kernel: #ifdef CONFIG_PREEMPT /* Check if we need to preempt */ + lwz r8,TI_PREEMPT(r9) + cmpwi 0,r8,0 /* if non-zero, just restore regs and return */ + bne restore andi. r0,r4,_TIF_NEED_RESCHED + bne+ check_count + + andi. r0,r4,_TIF_NEED_RESCHED_LAZY beq+ restore + lwz r8,TI_PREEMPT_LAZY(r9) + /* Check that preempt_count() == 0 and interrupts are enabled */ - lwz r8,TI_PREEMPT(r9) +check_count: cmpwi cr0,r8,0 bne restore ld r0,SOFTE(r1) @@ -848,7 +856,7 @@ resume_kernel: /* Re-test flags and eventually loop */ CURRENT_THREAD_INFO(r9, r1) ld r4,TI_FLAGS(r9) - andi. r0,r4,_TIF_NEED_RESCHED + andi. r0,r4,_TIF_NEED_RESCHED_MASK bne 1b /* diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 0682fef1f385..b66d7c3953c6 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -745,6 +745,7 @@ void irq_ctx_init(void) } } +#ifndef CONFIG_PREEMPT_RT_FULL void do_softirq_own_stack(void) { struct thread_info *curtp, *irqtp; @@ -762,6 +763,7 @@ void do_softirq_own_stack(void) if (irqtp->flags) set_bits(irqtp->flags, &curtp->flags); } +#endif irq_hw_number_t virq_to_hw(unsigned int virq) { diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index 3f7a9a2d2435..1795359d27b6 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -41,6 +41,7 @@ * We store the saved ksp_limit in the unused part * of the STACK_FRAME_OVERHEAD */ +#ifndef CONFIG_PREEMPT_RT_FULL _GLOBAL(call_do_softirq) mflr r0 stw r0,4(r1) @@ -57,6 +58,7 @@ _GLOBAL(call_do_softirq) stw r10,THREAD+KSP_LIMIT(r2) mtlr r0 blr +#endif /* * void call_do_irq(struct pt_regs *regs, struct thread_info *irqtp); diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index fa267e94090a..b541e80c5b48 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -31,6 +31,7 @@ .text +#ifndef CONFIG_PREEMPT_RT_FULL _GLOBAL(call_do_softirq) mflr r0 std r0,16(r1) @@ -41,6 +42,7 @@ _GLOBAL(call_do_softirq) ld r0,16(r1) mtlr r0 blr +#endif _GLOBAL(call_do_irq) mflr r0 diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig index 68a0e9d5b440..6f4d5d7615af 100644 --- a/arch/powerpc/kvm/Kconfig +++ b/arch/powerpc/kvm/Kconfig @@ -178,6 +178,7 @@ config KVM_E500MC config KVM_MPIC bool "KVM in-kernel MPIC emulation" depends on KVM && E500 + depends on !PREEMPT_RT_FULL select HAVE_KVM_IRQCHIP select HAVE_KVM_IRQFD select HAVE_KVM_IRQ_ROUTING diff --git a/arch/powerpc/platforms/cell/spufs/sched.c b/arch/powerpc/platforms/cell/spufs/sched.c index c9ef3c532169..cb10249b1125 100644 --- a/arch/powerpc/platforms/cell/spufs/sched.c +++ b/arch/powerpc/platforms/cell/spufs/sched.c @@ -141,7 +141,7 @@ void __spu_update_sched_info(struct spu_context *ctx) * runqueue. The context will be rescheduled on the proper node * if it is timesliced or preempted. */ - cpumask_copy(&ctx->cpus_allowed, ¤t->cpus_allowed); + cpumask_copy(&ctx->cpus_allowed, current->cpus_ptr); /* Save the current cpu id for spu interrupt routing. */ ctx->last_ran = raw_smp_processor_id(); diff --git a/arch/powerpc/platforms/ps3/device-init.c b/arch/powerpc/platforms/ps3/device-init.c index e7075aaff1bb..1fedb067389f 100644 --- a/arch/powerpc/platforms/ps3/device-init.c +++ b/arch/powerpc/platforms/ps3/device-init.c @@ -752,7 +752,7 @@ static int ps3_notification_read_write(struct ps3_notification_device *dev, } pr_debug("%s:%u: notification %s issued\n", __func__, __LINE__, op); - res = wait_event_interruptible(dev->done.wait, + res = swait_event_interruptible(dev->done.wait, dev->done.done || kthread_should_stop()); if (kthread_should_stop()) res = -EINTR; diff --git a/arch/s390/include/asm/spinlock_types.h b/arch/s390/include/asm/spinlock_types.h index cfed272e4fd5..8e28e8176ec8 100644 --- a/arch/s390/include/asm/spinlock_types.h +++ b/arch/s390/include/asm/spinlock_types.h @@ -2,10 +2,6 @@ #ifndef __ASM_SPINLOCK_TYPES_H #define __ASM_SPINLOCK_TYPES_H -#ifndef __LINUX_SPINLOCK_TYPES_H -# error "please don't include this file directly" -#endif - typedef struct { int lock; } __attribute__ ((aligned (4))) arch_spinlock_t; diff --git a/arch/sh/include/asm/spinlock_types.h b/arch/sh/include/asm/spinlock_types.h index e82369f286a2..22ca9a98bbb8 100644 --- a/arch/sh/include/asm/spinlock_types.h +++ b/arch/sh/include/asm/spinlock_types.h @@ -2,10 +2,6 @@ #ifndef __ASM_SH_SPINLOCK_TYPES_H #define __ASM_SH_SPINLOCK_TYPES_H -#ifndef __LINUX_SPINLOCK_TYPES_H -# error "please don't include this file directly" -#endif - typedef struct { volatile unsigned int lock; } arch_spinlock_t; diff --git a/arch/sh/kernel/irq.c b/arch/sh/kernel/irq.c index 5717c7cbdd97..66dd399b2007 100644 --- a/arch/sh/kernel/irq.c +++ b/arch/sh/kernel/irq.c @@ -148,6 +148,7 @@ void irq_ctx_exit(int cpu) hardirq_ctx[cpu] = NULL; } +#ifndef CONFIG_PREEMPT_RT_FULL void do_softirq_own_stack(void) { struct thread_info *curctx; @@ -175,6 +176,7 @@ void do_softirq_own_stack(void) "r5", "r6", "r7", "r8", "r9", "r15", "t", "pr" ); } +#endif #else static inline void handle_one_irq(unsigned int irq) { diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c index 713670e6d13d..5dfc715343f9 100644 --- a/arch/sparc/kernel/irq_64.c +++ b/arch/sparc/kernel/irq_64.c @@ -854,6 +854,7 @@ void __irq_entry handler_irq(int pil, struct pt_regs *regs) set_irq_regs(old_regs); } +#ifndef CONFIG_PREEMPT_RT_FULL void do_softirq_own_stack(void) { void *orig_sp, *sp = softirq_stack[smp_processor_id()]; @@ -868,6 +869,7 @@ void do_softirq_own_stack(void) __asm__ __volatile__("mov %0, %%sp" : : "r" (orig_sp)); } +#endif #ifdef CONFIG_HOTPLUG_CPU void fixup_irqs(void) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 9558de7c0aaf..aa3ce0e62045 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -178,6 +178,7 @@ config X86 select HAVE_HARDLOCKUP_DETECTOR_PERF if PERF_EVENTS && HAVE_PERF_EVENTS_NMI select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP + select HAVE_PREEMPT_LAZY select HAVE_RCU_TABLE_FREE select HAVE_RCU_TABLE_INVALIDATE if HAVE_RCU_TABLE_FREE select HAVE_REGS_AND_STACK_ACCESS_API @@ -262,8 +263,11 @@ config ARCH_MAY_HAVE_PC_FDC def_bool y depends on ISA_DMA_API +config RWSEM_GENERIC_SPINLOCK + def_bool PREEMPT_RT_FULL + config RWSEM_XCHGADD_ALGORITHM - def_bool y + def_bool !RWSEM_GENERIC_SPINLOCK && !PREEMPT_RT_FULL config GENERIC_CALIBRATE_DELAY def_bool y @@ -936,7 +940,7 @@ config CALGARY_IOMMU_ENABLED_BY_DEFAULT config MAXSMP bool "Enable Maximum number of SMP Processors and NUMA Nodes" depends on X86_64 && SMP && DEBUG_KERNEL - select CPUMASK_OFFSTACK + select CPUMASK_OFFSTACK if !PREEMPT_RT_FULL ---help--- Enable maximum number of CPUS and NUMA Nodes for this architecture. If unsure, say N. diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c index 917f25e4d0a8..58d8c03fc32d 100644 --- a/arch/x86/crypto/aesni-intel_glue.c +++ b/arch/x86/crypto/aesni-intel_glue.c @@ -434,14 +434,14 @@ static int ecb_encrypt(struct skcipher_request *req) err = skcipher_walk_virt(&walk, req, true); - kernel_fpu_begin(); while ((nbytes = walk.nbytes)) { + kernel_fpu_begin(); aesni_ecb_enc(ctx, walk.dst.virt.addr, walk.src.virt.addr, nbytes & AES_BLOCK_MASK); + kernel_fpu_end(); nbytes &= AES_BLOCK_SIZE - 1; err = skcipher_walk_done(&walk, nbytes); } - kernel_fpu_end(); return err; } @@ -456,14 +456,14 @@ static int ecb_decrypt(struct skcipher_request *req) err = skcipher_walk_virt(&walk, req, true); - kernel_fpu_begin(); while ((nbytes = walk.nbytes)) { + kernel_fpu_begin(); aesni_ecb_dec(ctx, walk.dst.virt.addr, walk.src.virt.addr, nbytes & AES_BLOCK_MASK); + kernel_fpu_end(); nbytes &= AES_BLOCK_SIZE - 1; err = skcipher_walk_done(&walk, nbytes); } - kernel_fpu_end(); return err; } @@ -478,14 +478,14 @@ static int cbc_encrypt(struct skcipher_request *req) err = skcipher_walk_virt(&walk, req, true); - kernel_fpu_begin(); while ((nbytes = walk.nbytes)) { + kernel_fpu_begin(); aesni_cbc_enc(ctx, walk.dst.virt.addr, walk.src.virt.addr, nbytes & AES_BLOCK_MASK, walk.iv); + kernel_fpu_end(); nbytes &= AES_BLOCK_SIZE - 1; err = skcipher_walk_done(&walk, nbytes); } - kernel_fpu_end(); return err; } @@ -500,14 +500,14 @@ static int cbc_decrypt(struct skcipher_request *req) err = skcipher_walk_virt(&walk, req, true); - kernel_fpu_begin(); while ((nbytes = walk.nbytes)) { + kernel_fpu_begin(); aesni_cbc_dec(ctx, walk.dst.virt.addr, walk.src.virt.addr, nbytes & AES_BLOCK_MASK, walk.iv); + kernel_fpu_end(); nbytes &= AES_BLOCK_SIZE - 1; err = skcipher_walk_done(&walk, nbytes); } - kernel_fpu_end(); return err; } @@ -557,18 +557,20 @@ static int ctr_crypt(struct skcipher_request *req) err = skcipher_walk_virt(&walk, req, true); - kernel_fpu_begin(); while ((nbytes = walk.nbytes) >= AES_BLOCK_SIZE) { + kernel_fpu_begin(); aesni_ctr_enc_tfm(ctx, walk.dst.virt.addr, walk.src.virt.addr, nbytes & AES_BLOCK_MASK, walk.iv); + kernel_fpu_end(); nbytes &= AES_BLOCK_SIZE - 1; err = skcipher_walk_done(&walk, nbytes); } if (walk.nbytes) { + kernel_fpu_begin(); ctr_crypt_final(ctx, &walk); + kernel_fpu_end(); err = skcipher_walk_done(&walk, 0); } - kernel_fpu_end(); return err; } diff --git a/arch/x86/crypto/cast5_avx_glue.c b/arch/x86/crypto/cast5_avx_glue.c index 41034745d6a2..d4bf7fc02ee7 100644 --- a/arch/x86/crypto/cast5_avx_glue.c +++ b/arch/x86/crypto/cast5_avx_glue.c @@ -61,7 +61,7 @@ static inline void cast5_fpu_end(bool fpu_enabled) static int ecb_crypt(struct skcipher_request *req, bool enc) { - bool fpu_enabled = false; + bool fpu_enabled; struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); struct cast5_ctx *ctx = crypto_skcipher_ctx(tfm); struct skcipher_walk walk; @@ -76,7 +76,7 @@ static int ecb_crypt(struct skcipher_request *req, bool enc) u8 *wsrc = walk.src.virt.addr; u8 *wdst = walk.dst.virt.addr; - fpu_enabled = cast5_fpu_begin(fpu_enabled, &walk, nbytes); + fpu_enabled = cast5_fpu_begin(false, &walk, nbytes); /* Process multi-block batch */ if (nbytes >= bsize * CAST5_PARALLEL_BLOCKS) { @@ -105,10 +105,9 @@ static int ecb_crypt(struct skcipher_request *req, bool enc) } while (nbytes >= bsize); done: + cast5_fpu_end(fpu_enabled); err = skcipher_walk_done(&walk, nbytes); } - - cast5_fpu_end(fpu_enabled); return err; } @@ -212,7 +211,7 @@ static int cbc_decrypt(struct skcipher_request *req) { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); struct cast5_ctx *ctx = crypto_skcipher_ctx(tfm); - bool fpu_enabled = false; + bool fpu_enabled; struct skcipher_walk walk; unsigned int nbytes; int err; @@ -220,12 +219,11 @@ static int cbc_decrypt(struct skcipher_request *req) err = skcipher_walk_virt(&walk, req, false); while ((nbytes = walk.nbytes)) { - fpu_enabled = cast5_fpu_begin(fpu_enabled, &walk, nbytes); + fpu_enabled = cast5_fpu_begin(false, &walk, nbytes); nbytes = __cbc_decrypt(ctx, &walk); + cast5_fpu_end(fpu_enabled); err = skcipher_walk_done(&walk, nbytes); } - - cast5_fpu_end(fpu_enabled); return err; } @@ -292,7 +290,7 @@ static int ctr_crypt(struct skcipher_request *req) { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); struct cast5_ctx *ctx = crypto_skcipher_ctx(tfm); - bool fpu_enabled = false; + bool fpu_enabled; struct skcipher_walk walk; unsigned int nbytes; int err; @@ -300,13 +298,12 @@ static int ctr_crypt(struct skcipher_request *req) err = skcipher_walk_virt(&walk, req, false); while ((nbytes = walk.nbytes) >= CAST5_BLOCK_SIZE) { - fpu_enabled = cast5_fpu_begin(fpu_enabled, &walk, nbytes); + fpu_enabled = cast5_fpu_begin(false, &walk, nbytes); nbytes = __ctr_crypt(&walk, ctx); + cast5_fpu_end(fpu_enabled); err = skcipher_walk_done(&walk, nbytes); } - cast5_fpu_end(fpu_enabled); - if (walk.nbytes) { ctr_crypt_final(&walk, ctx); err = skcipher_walk_done(&walk, 0); diff --git a/arch/x86/crypto/chacha20_glue.c b/arch/x86/crypto/chacha20_glue.c index dce7c5d39c2f..6194160b7fbc 100644 --- a/arch/x86/crypto/chacha20_glue.c +++ b/arch/x86/crypto/chacha20_glue.c @@ -81,23 +81,24 @@ static int chacha20_simd(struct skcipher_request *req) crypto_chacha20_init(state, ctx, walk.iv); - kernel_fpu_begin(); - while (walk.nbytes >= CHACHA20_BLOCK_SIZE) { + kernel_fpu_begin(); + chacha20_dosimd(state, walk.dst.virt.addr, walk.src.virt.addr, rounddown(walk.nbytes, CHACHA20_BLOCK_SIZE)); + kernel_fpu_end(); err = skcipher_walk_done(&walk, walk.nbytes % CHACHA20_BLOCK_SIZE); } if (walk.nbytes) { + kernel_fpu_begin(); chacha20_dosimd(state, walk.dst.virt.addr, walk.src.virt.addr, walk.nbytes); + kernel_fpu_end(); err = skcipher_walk_done(&walk, 0); } - kernel_fpu_end(); - return err; } diff --git a/arch/x86/crypto/glue_helper.c b/arch/x86/crypto/glue_helper.c index a78ef99a9981..dac489a1c4da 100644 --- a/arch/x86/crypto/glue_helper.c +++ b/arch/x86/crypto/glue_helper.c @@ -38,7 +38,7 @@ int glue_ecb_req_128bit(const struct common_glue_ctx *gctx, void *ctx = crypto_skcipher_ctx(crypto_skcipher_reqtfm(req)); const unsigned int bsize = 128 / 8; struct skcipher_walk walk; - bool fpu_enabled = false; + bool fpu_enabled; unsigned int nbytes; int err; @@ -51,7 +51,7 @@ int glue_ecb_req_128bit(const struct common_glue_ctx *gctx, unsigned int i; fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit, - &walk, fpu_enabled, nbytes); + &walk, false, nbytes); for (i = 0; i < gctx->num_funcs; i++) { func_bytes = bsize * gctx->funcs[i].num_blocks; @@ -69,10 +69,9 @@ int glue_ecb_req_128bit(const struct common_glue_ctx *gctx, if (nbytes < bsize) break; } + glue_fpu_end(fpu_enabled); err = skcipher_walk_done(&walk, nbytes); } - - glue_fpu_end(fpu_enabled); return err; } EXPORT_SYMBOL_GPL(glue_ecb_req_128bit); @@ -115,7 +114,7 @@ int glue_cbc_decrypt_req_128bit(const struct common_glue_ctx *gctx, void *ctx = crypto_skcipher_ctx(crypto_skcipher_reqtfm(req)); const unsigned int bsize = 128 / 8; struct skcipher_walk walk; - bool fpu_enabled = false; + bool fpu_enabled; unsigned int nbytes; int err; @@ -129,7 +128,7 @@ int glue_cbc_decrypt_req_128bit(const struct common_glue_ctx *gctx, u128 last_iv; fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit, - &walk, fpu_enabled, nbytes); + &walk, false, nbytes); /* Start of the last block. */ src += nbytes / bsize - 1; dst += nbytes / bsize - 1; @@ -161,10 +160,10 @@ int glue_cbc_decrypt_req_128bit(const struct common_glue_ctx *gctx, done: u128_xor(dst, dst, (u128 *)walk.iv); *(u128 *)walk.iv = last_iv; + glue_fpu_end(fpu_enabled); err = skcipher_walk_done(&walk, nbytes); } - glue_fpu_end(fpu_enabled); return err; } EXPORT_SYMBOL_GPL(glue_cbc_decrypt_req_128bit); @@ -175,7 +174,7 @@ int glue_ctr_req_128bit(const struct common_glue_ctx *gctx, void *ctx = crypto_skcipher_ctx(crypto_skcipher_reqtfm(req)); const unsigned int bsize = 128 / 8; struct skcipher_walk walk; - bool fpu_enabled = false; + bool fpu_enabled; unsigned int nbytes; int err; @@ -189,7 +188,7 @@ int glue_ctr_req_128bit(const struct common_glue_ctx *gctx, le128 ctrblk; fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit, - &walk, fpu_enabled, nbytes); + &walk, false, nbytes); be128_to_le128(&ctrblk, (be128 *)walk.iv); @@ -213,11 +212,10 @@ int glue_ctr_req_128bit(const struct common_glue_ctx *gctx, } le128_to_be128((be128 *)walk.iv, &ctrblk); + glue_fpu_end(fpu_enabled); err = skcipher_walk_done(&walk, nbytes); } - glue_fpu_end(fpu_enabled); - if (nbytes) { le128 ctrblk; u128 tmp; @@ -278,7 +276,7 @@ int glue_xts_req_128bit(const struct common_glue_ctx *gctx, { const unsigned int bsize = 128 / 8; struct skcipher_walk walk; - bool fpu_enabled = false; + bool fpu_enabled; unsigned int nbytes; int err; @@ -289,21 +287,24 @@ int glue_xts_req_128bit(const struct common_glue_ctx *gctx, /* set minimum length to bsize, for tweak_fn */ fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit, - &walk, fpu_enabled, + &walk, false, nbytes < bsize ? bsize : nbytes); /* calculate first value of T */ tweak_fn(tweak_ctx, walk.iv, walk.iv); while (nbytes) { + fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit, + &walk, fpu_enabled, + nbytes < bsize ? bsize : nbytes); nbytes = __glue_xts_req_128bit(gctx, crypt_ctx, &walk); + glue_fpu_end(fpu_enabled); + fpu_enabled = false; err = skcipher_walk_done(&walk, nbytes); nbytes = walk.nbytes; } - glue_fpu_end(fpu_enabled); - return err; } EXPORT_SYMBOL_GPL(glue_xts_req_128bit); diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index 8353348ddeaf..3b5e41d9b29d 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -134,7 +134,7 @@ static long syscall_trace_enter(struct pt_regs *regs) #define EXIT_TO_USERMODE_LOOP_FLAGS \ (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_UPROBE | \ - _TIF_NEED_RESCHED | _TIF_USER_RETURN_NOTIFY | _TIF_PATCH_PENDING) + _TIF_NEED_RESCHED_MASK | _TIF_USER_RETURN_NOTIFY | _TIF_PATCH_PENDING) static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags) { @@ -149,9 +149,16 @@ static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags) /* We have work to do. */ local_irq_enable(); - if (cached_flags & _TIF_NEED_RESCHED) + if (cached_flags & _TIF_NEED_RESCHED_MASK) schedule(); +#ifdef ARCH_RT_DELAYS_SIGNAL_SEND + if (unlikely(current->forced_info.si_signo)) { + struct task_struct *t = current; + force_sig_info(t->forced_info.si_signo, &t->forced_info, t); + t->forced_info.si_signo = 0; + } +#endif if (cached_flags & _TIF_UPROBE) uprobe_notify_resume(regs); diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 476b48531646..598cabdb71c9 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -352,8 +352,25 @@ END(ret_from_exception) ENTRY(resume_kernel) DISABLE_INTERRUPTS(CLBR_ANY) .Lneed_resched: + # preempt count == 0 + NEED_RS set? cmpl $0, PER_CPU_VAR(__preempt_count) +#ifndef CONFIG_PREEMPT_LAZY jnz restore_all +#else + jz test_int_off + + # atleast preempt count == 0 ? + cmpl $_PREEMPT_ENABLED,PER_CPU_VAR(__preempt_count) + jne restore_all + + movl PER_CPU_VAR(current_task), %ebp + cmpl $0,TASK_TI_preempt_lazy_count(%ebp) # non-zero preempt_lazy_count ? + jnz restore_all + + testl $_TIF_NEED_RESCHED_LAZY, TASK_TI_flags(%ebp) + jz restore_all +test_int_off: +#endif testl $X86_EFLAGS_IF, PT_EFLAGS(%esp) # interrupts off (exception path) ? jz restore_all call preempt_schedule_irq diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index d7753fb25bc6..08aee2c69de3 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -709,7 +709,23 @@ retint_kernel: btl $9, EFLAGS(%rsp) /* were interrupts off? */ jnc 1f 0: cmpl $0, PER_CPU_VAR(__preempt_count) +#ifndef CONFIG_PREEMPT_LAZY jnz 1f +#else + jz do_preempt_schedule_irq + + # atleast preempt count == 0 ? + cmpl $_PREEMPT_ENABLED,PER_CPU_VAR(__preempt_count) + jnz 1f + + movq PER_CPU_VAR(current_task), %rcx + cmpl $0, TASK_TI_preempt_lazy_count(%rcx) + jnz 1f + + bt $TIF_NEED_RESCHED_LAZY,TASK_TI_flags(%rcx) + jnc 1f +do_preempt_schedule_irq: +#endif call preempt_schedule_irq jmp 0b 1: @@ -1060,6 +1076,7 @@ bad_gs: jmp 2b .previous +#ifndef CONFIG_PREEMPT_RT_FULL /* Call softirq on interrupt stack. Interrupts are off. */ ENTRY(do_softirq_own_stack) pushq %rbp @@ -1070,6 +1087,7 @@ ENTRY(do_softirq_own_stack) leaveq ret ENDPROC(do_softirq_own_stack) +#endif #ifdef CONFIG_XEN idtentry hypervisor_callback xen_do_hypervisor_callback has_error_code=0 diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h index b56d504af654..e51c7094075d 100644 --- a/arch/x86/include/asm/fpu/api.h +++ b/arch/x86/include/asm/fpu/api.h @@ -20,6 +20,7 @@ */ extern void kernel_fpu_begin(void); extern void kernel_fpu_end(void); +extern void kernel_fpu_resched(void); extern bool irq_fpu_usable(void); /* diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h index 7f2dbd91fc74..22992c837795 100644 --- a/arch/x86/include/asm/preempt.h +++ b/arch/x86/include/asm/preempt.h @@ -86,17 +86,46 @@ static __always_inline void __preempt_count_sub(int val) * a decrement which hits zero means we have no preempt_count and should * reschedule. */ -static __always_inline bool __preempt_count_dec_and_test(void) +static __always_inline bool ____preempt_count_dec_and_test(void) { GEN_UNARY_RMWcc("decl", __preempt_count, __percpu_arg(0), e); } +static __always_inline bool __preempt_count_dec_and_test(void) +{ + if (____preempt_count_dec_and_test()) + return true; +#ifdef CONFIG_PREEMPT_LAZY + if (current_thread_info()->preempt_lazy_count) + return false; + return test_thread_flag(TIF_NEED_RESCHED_LAZY); +#else + return false; +#endif +} + /* * Returns true when we need to resched and can (barring IRQ state). */ static __always_inline bool should_resched(int preempt_offset) { +#ifdef CONFIG_PREEMPT_LAZY + u32 tmp; + + tmp = raw_cpu_read_4(__preempt_count); + if (tmp == preempt_offset) + return true; + + /* preempt count == 0 ? */ + tmp &= ~PREEMPT_NEED_RESCHED; + if (tmp) + return false; + if (current_thread_info()->preempt_lazy_count) + return false; + return test_thread_flag(TIF_NEED_RESCHED_LAZY); +#else return unlikely(raw_cpu_read_4(__preempt_count) == preempt_offset); +#endif } #ifdef CONFIG_PREEMPT diff --git a/arch/x86/include/asm/signal.h b/arch/x86/include/asm/signal.h index 5f9012ff52ed..39117e57caf2 100644 --- a/arch/x86/include/asm/signal.h +++ b/arch/x86/include/asm/signal.h @@ -28,6 +28,19 @@ typedef struct { #define SA_IA32_ABI 0x02000000u #define SA_X32_ABI 0x01000000u +/* + * Because some traps use the IST stack, we must keep preemption + * disabled while calling do_trap(), but do_trap() may call + * force_sig_info() which will grab the signal spin_locks for the + * task, which in PREEMPT_RT_FULL are mutexes. By defining + * ARCH_RT_DELAYS_SIGNAL_SEND the force_sig_info() will set + * TIF_NOTIFY_RESUME and set up the signal to be sent on exit of the + * trap. + */ +#if defined(CONFIG_PREEMPT_RT_FULL) +#define ARCH_RT_DELAYS_SIGNAL_SEND +#endif + #ifndef CONFIG_COMPAT typedef sigset_t compat_sigset_t; #endif diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h index 8ec97a62c245..7bc85841fc56 100644 --- a/arch/x86/include/asm/stackprotector.h +++ b/arch/x86/include/asm/stackprotector.h @@ -60,7 +60,7 @@ */ static __always_inline void boot_init_stack_canary(void) { - u64 canary; + u64 uninitialized_var(canary); u64 tsc; #ifdef CONFIG_X86_64 @@ -71,8 +71,14 @@ static __always_inline void boot_init_stack_canary(void) * of randomness. The TSC only matters for very early init, * there it already has some randomness on most systems. Later * on during the bootup the random pool has true entropy too. + * For preempt-rt we need to weaken the randomness a bit, as + * we can't call into the random generator from atomic context + * due to locking constraints. We just leave canary + * uninitialized and use the TSC based randomness on top of it. */ +#ifndef CONFIG_PREEMPT_RT_FULL get_random_bytes(&canary, sizeof(canary)); +#endif tsc = rdtsc(); canary += tsc + (tsc << 32UL); canary &= CANARY_MASK; diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 82b73b75d67c..428595b19602 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -56,17 +56,24 @@ struct task_struct; struct thread_info { unsigned long flags; /* low level flags */ u32 status; /* thread synchronous flags */ + int preempt_lazy_count; /* 0 => lazy preemptable + <0 => BUG */ }; #define INIT_THREAD_INFO(tsk) \ { \ .flags = 0, \ + .preempt_lazy_count = 0, \ } #else /* !__ASSEMBLY__ */ #include <asm/asm-offsets.h> +#define GET_THREAD_INFO(reg) \ + _ASM_MOV PER_CPU_VAR(cpu_current_top_of_stack),reg ; \ + _ASM_SUB $(THREAD_SIZE),reg ; + #endif /* @@ -88,6 +95,7 @@ struct thread_info { #define TIF_USER_RETURN_NOTIFY 11 /* notify kernel of userspace return */ #define TIF_UPROBE 12 /* breakpointed or singlestepping */ #define TIF_PATCH_PENDING 13 /* pending live patching update */ +#define TIF_NEED_RESCHED_LAZY 14 /* lazy rescheduling necessary */ #define TIF_NOCPUID 15 /* CPUID is not accessible in userland */ #define TIF_NOTSC 16 /* TSC is not accessible in userland */ #define TIF_IA32 17 /* IA32 compatibility process */ @@ -117,6 +125,7 @@ struct thread_info { #define _TIF_USER_RETURN_NOTIFY (1 << TIF_USER_RETURN_NOTIFY) #define _TIF_UPROBE (1 << TIF_UPROBE) #define _TIF_PATCH_PENDING (1 << TIF_PATCH_PENDING) +#define _TIF_NEED_RESCHED_LAZY (1 << TIF_NEED_RESCHED_LAZY) #define _TIF_NOCPUID (1 << TIF_NOCPUID) #define _TIF_NOTSC (1 << TIF_NOTSC) #define _TIF_IA32 (1 << TIF_IA32) @@ -165,6 +174,8 @@ struct thread_info { #define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW|_TIF_USER_RETURN_NOTIFY) #define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW) +#define _TIF_NEED_RESCHED_MASK (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY) + #define STACK_WARN (THREAD_SIZE/8) /* diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index ff0d14cd9e82..c2bd6e0433f8 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1722,19 +1722,20 @@ static bool io_apic_level_ack_pending(struct mp_chip_data *data) return false; } -static inline bool ioapic_irqd_mask(struct irq_data *data) +static inline bool ioapic_prepare_move(struct irq_data *data) { /* If we are moving the irq we need to mask it */ if (unlikely(irqd_is_setaffinity_pending(data))) { - mask_ioapic_irq(data); + if (!irqd_irq_masked(data)) + mask_ioapic_irq(data); return true; } return false; } -static inline void ioapic_irqd_unmask(struct irq_data *data, bool masked) +static inline void ioapic_finish_move(struct irq_data *data, bool moveit) { - if (unlikely(masked)) { + if (unlikely(moveit)) { /* Only migrate the irq if the ack has been received. * * On rare occasions the broadcast level triggered ack gets @@ -1763,15 +1764,17 @@ static inline void ioapic_irqd_unmask(struct irq_data *data, bool masked) */ if (!io_apic_level_ack_pending(data->chip_data)) irq_move_masked_irq(data); - unmask_ioapic_irq(data); + /* If the irq is masked in the core, leave it */ + if (!irqd_irq_masked(data)) + unmask_ioapic_irq(data); } } #else -static inline bool ioapic_irqd_mask(struct irq_data *data) +static inline bool ioapic_prepare_move(struct irq_data *data) { return false; } -static inline void ioapic_irqd_unmask(struct irq_data *data, bool masked) +static inline void ioapic_finish_move(struct irq_data *data, bool moveit) { } #endif @@ -1780,11 +1783,11 @@ static void ioapic_ack_level(struct irq_data *irq_data) { struct irq_cfg *cfg = irqd_cfg(irq_data); unsigned long v; - bool masked; + bool moveit; int i; irq_complete_move(cfg); - masked = ioapic_irqd_mask(irq_data); + moveit = ioapic_prepare_move(irq_data); /* * It appears there is an erratum which affects at least version 0x11 @@ -1839,7 +1842,7 @@ static void ioapic_ack_level(struct irq_data *irq_data) eoi_ioapic_pin(cfg->vector, irq_data->chip_data); } - ioapic_irqd_unmask(irq_data, masked); + ioapic_finish_move(irq_data, moveit); } static void ioapic_ir_ack_level(struct irq_data *irq_data) diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index dcb008c320fe..b63b1e9557be 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -38,6 +38,7 @@ void common(void) { BLANK(); OFFSET(TASK_TI_flags, task_struct, thread_info.flags); + OFFSET(TASK_TI_preempt_lazy_count, task_struct, thread_info.preempt_lazy_count); OFFSET(TASK_addr_limit, task_struct, thread.addr_limit); BLANK(); @@ -94,6 +95,7 @@ void common(void) { BLANK(); DEFINE(PTREGS_SIZE, sizeof(struct pt_regs)); + DEFINE(_PREEMPT_ENABLED, PREEMPT_ENABLED); /* TLB state for the entry code */ OFFSET(TLB_STATE_user_pcid_flush_mask, tlb_state, user_pcid_flush_mask); diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index 2e5003fef51a..768c53767bb2 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -136,6 +136,18 @@ void kernel_fpu_end(void) } EXPORT_SYMBOL_GPL(kernel_fpu_end); +void kernel_fpu_resched(void) +{ + WARN_ON_FPU(!this_cpu_read(in_kernel_fpu)); + + if (should_resched(PREEMPT_OFFSET)) { + kernel_fpu_end(); + cond_resched(); + kernel_fpu_begin(); + } +} +EXPORT_SYMBOL_GPL(kernel_fpu_resched); + /* * Save the FPU state (mark it for reload if necessary): * diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index 95600a99ae93..9192d76085ba 100644 --- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -130,6 +130,7 @@ void irq_ctx_init(int cpu) cpu, per_cpu(hardirq_stack, cpu), per_cpu(softirq_stack, cpu)); } +#ifndef CONFIG_PREEMPT_RT_FULL void do_softirq_own_stack(void) { struct irq_stack *irqstk; @@ -146,6 +147,7 @@ void do_softirq_own_stack(void) call_on_stack(__do_softirq, isp); } +#endif bool handle_irq(struct irq_desc *desc, struct pt_regs *regs) { diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index ebd937d3ea3f..7c53f4da8064 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -38,6 +38,7 @@ #include <linux/io.h> #include <linux/kdebug.h> #include <linux/syscalls.h> +#include <linux/highmem.h> #include <asm/pgtable.h> #include <asm/ldt.h> @@ -205,6 +206,35 @@ start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp) } EXPORT_SYMBOL_GPL(start_thread); +#ifdef CONFIG_PREEMPT_RT_FULL +static void switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p) +{ + int i; + + /* + * Clear @prev's kmap_atomic mappings + */ + for (i = 0; i < prev_p->kmap_idx; i++) { + int idx = i + KM_TYPE_NR * smp_processor_id(); + pte_t *ptep = kmap_pte - idx; + + kpte_clear_flush(ptep, __fix_to_virt(FIX_KMAP_BEGIN + idx)); + } + /* + * Restore @next_p's kmap_atomic mappings + */ + for (i = 0; i < next_p->kmap_idx; i++) { + int idx = i + KM_TYPE_NR * smp_processor_id(); + + if (!pte_none(next_p->kmap_pte[i])) + set_pte(kmap_pte - idx, next_p->kmap_pte[i]); + } +} +#else +static inline void +switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p) { } +#endif + /* * switch_to(x,y) should switch tasks from x to y. @@ -274,6 +304,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) switch_to_extra(prev_p, next_p); + switch_kmaps(prev_p, next_p); + /* * Leave lazy mode, flushing any hypercalls made here. * This must be done before restoring TLS segments so diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index e1994ca59323..fe63b0a3039d 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -2194,7 +2194,7 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu) apic->vcpu = vcpu; hrtimer_init(&apic->lapic_timer.timer, CLOCK_MONOTONIC, - HRTIMER_MODE_ABS_PINNED); + HRTIMER_MODE_ABS_PINNED_HARD); apic->lapic_timer.timer.function = apic_timer_fn; /* diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 3aac2ce63462..7584e7015da3 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -6657,6 +6657,13 @@ int kvm_arch_init(void *opaque) goto out; } +#ifdef CONFIG_PREEMPT_RT_FULL + if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) { + printk(KERN_ERR "RT requires X86_FEATURE_CONSTANT_TSC\n"); + return -EOPNOTSUPP; + } +#endif + r = kvm_mmu_module_init(); if (r) goto out_free_percpu; diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c index 6d18b70ed5a9..f752724c22e8 100644 --- a/arch/x86/mm/highmem_32.c +++ b/arch/x86/mm/highmem_32.c @@ -32,10 +32,11 @@ EXPORT_SYMBOL(kunmap); */ void *kmap_atomic_prot(struct page *page, pgprot_t prot) { + pte_t pte = mk_pte(page, prot); unsigned long vaddr; int idx, type; - preempt_disable(); + preempt_disable_nort(); pagefault_disable(); if (!PageHighMem(page)) @@ -45,7 +46,10 @@ void *kmap_atomic_prot(struct page *page, pgprot_t prot) idx = type + KM_TYPE_NR*smp_processor_id(); vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); BUG_ON(!pte_none(*(kmap_pte-idx))); - set_pte(kmap_pte-idx, mk_pte(page, prot)); +#ifdef CONFIG_PREEMPT_RT_FULL + current->kmap_pte[type] = pte; +#endif + set_pte(kmap_pte-idx, pte); arch_flush_lazy_mmu_mode(); return (void *)vaddr; @@ -88,6 +92,9 @@ void __kunmap_atomic(void *kvaddr) * is a bad idea also, in case the page changes cacheability * attributes or becomes a protected page in a hypervisor. */ +#ifdef CONFIG_PREEMPT_RT_FULL + current->kmap_pte[type] = __pte(0); +#endif kpte_clear_flush(kmap_pte-idx, vaddr); kmap_atomic_idx_pop(); arch_flush_lazy_mmu_mode(); @@ -100,7 +107,7 @@ void __kunmap_atomic(void *kvaddr) #endif pagefault_enable(); - preempt_enable(); + preempt_enable_nort(); } EXPORT_SYMBOL(__kunmap_atomic); diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c index b3294d36769d..c0ec8d430c02 100644 --- a/arch/x86/mm/iomap_32.c +++ b/arch/x86/mm/iomap_32.c @@ -59,6 +59,7 @@ EXPORT_SYMBOL_GPL(iomap_free); void *kmap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot) { + pte_t pte = pfn_pte(pfn, prot); unsigned long vaddr; int idx, type; @@ -68,7 +69,12 @@ void *kmap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot) type = kmap_atomic_idx_push(); idx = type + KM_TYPE_NR * smp_processor_id(); vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); - set_pte(kmap_pte - idx, pfn_pte(pfn, prot)); + WARN_ON(!pte_none(*(kmap_pte - idx))); + +#ifdef CONFIG_PREEMPT_RT_FULL + current->kmap_pte[type] = pte; +#endif + set_pte(kmap_pte - idx, pte); arch_flush_lazy_mmu_mode(); return (void *)vaddr; @@ -119,6 +125,9 @@ iounmap_atomic(void __iomem *kvaddr) * is a bad idea also, in case the page changes cacheability * attributes or becomes a protected page in a hypervisor. */ +#ifdef CONFIG_PREEMPT_RT_FULL + current->kmap_pte[type] = __pte(0); +#endif kpte_clear_flush(kmap_pte-idx, vaddr); kmap_atomic_idx_pop(); } diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 5f2eb3231607..7b36c1032a4f 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -619,18 +619,16 @@ void __init efi_dump_pagetable(void) /* * Makes the calling thread switch to/from efi_mm context. Can be used - * for SetVirtualAddressMap() i.e. current->active_mm == init_mm as well - * as during efi runtime calls i.e current->active_mm == current_mm. - * We are not mm_dropping()/mm_grabbing() any mm, because we are not - * losing/creating any references. + * in a kernel thread and user context. Preemption needs to remain disabled + * while the EFI-mm is borrowed. mmgrab()/mmdrop() is not used because the mm + * can not change under us. + * It should be ensured that there are no concurent calls to this function. */ void efi_switch_mm(struct mm_struct *mm) { - task_lock(current); efi_scratch.prev_mm = current->active_mm; current->active_mm = mm; switch_mm(efi_scratch.prev_mm, mm, NULL); - task_unlock(current); } #ifdef CONFIG_EFI_MIXED diff --git a/arch/xtensa/include/asm/spinlock_types.h b/arch/xtensa/include/asm/spinlock_types.h index bb1fe6c1816e..8a22f1e7b6c9 100644 --- a/arch/xtensa/include/asm/spinlock_types.h +++ b/arch/xtensa/include/asm/spinlock_types.h @@ -2,10 +2,6 @@ #ifndef __ASM_SPINLOCK_TYPES_H #define __ASM_SPINLOCK_TYPES_H -#ifndef __LINUX_SPINLOCK_TYPES_H -# error "please don't include this file directly" -#endif - typedef struct { volatile unsigned int slock; } arch_spinlock_t; diff --git a/block/blk-core.c b/block/blk-core.c index 7d4bf916546c..e342ab04fb24 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -189,6 +189,9 @@ void blk_rq_init(struct request_queue *q, struct request *rq) INIT_LIST_HEAD(&rq->queuelist); INIT_LIST_HEAD(&rq->timeout_list); +#ifdef CONFIG_PREEMPT_RT_FULL + INIT_WORK(&rq->work, __blk_mq_complete_request_remote_work); +#endif rq->cpu = -1; rq->q = q; rq->__sector = (sector_t) -1; @@ -965,12 +968,21 @@ void blk_queue_exit(struct request_queue *q) percpu_ref_put(&q->q_usage_counter); } +static void blk_queue_usage_counter_release_swork(struct swork_event *sev) +{ + struct request_queue *q = + container_of(sev, struct request_queue, mq_pcpu_wake); + + wake_up_all(&q->mq_freeze_wq); +} + static void blk_queue_usage_counter_release(struct percpu_ref *ref) { struct request_queue *q = container_of(ref, struct request_queue, q_usage_counter); - wake_up_all(&q->mq_freeze_wq); + if (wq_has_sleeper(&q->mq_freeze_wq)) + swork_queue(&q->mq_pcpu_wake); } static void blk_rq_timed_out_timer(struct timer_list *t) @@ -1068,6 +1080,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id, queue_flag_set_unlocked(QUEUE_FLAG_BYPASS, q); init_waitqueue_head(&q->mq_freeze_wq); + INIT_SWORK(&q->mq_pcpu_wake, blk_queue_usage_counter_release_swork); /* * Init percpu_ref in atomic mode so that it's faster to shutdown. @@ -3957,6 +3970,8 @@ int __init blk_dev_init(void) if (!kblockd_workqueue) panic("Failed to create kblockd\n"); + BUG_ON(swork_get()); + request_cachep = kmem_cache_create("blkdev_requests", sizeof(struct request), 0, SLAB_PANIC, NULL); diff --git a/block/blk-ioc.c b/block/blk-ioc.c index f23311e4b201..ca9ea624f159 100644 --- a/block/blk-ioc.c +++ b/block/blk-ioc.c @@ -9,6 +9,7 @@ #include <linux/blkdev.h> #include <linux/slab.h> #include <linux/sched/task.h> +#include <linux/delay.h> #include "blk.h" @@ -118,7 +119,7 @@ static void ioc_release_fn(struct work_struct *work) spin_unlock(q->queue_lock); } else { spin_unlock_irqrestore(&ioc->lock, flags); - cpu_relax(); + cpu_chill(); spin_lock_irqsave_nested(&ioc->lock, flags, 1); } } @@ -202,7 +203,7 @@ retry: spin_unlock(icq->q->queue_lock); } else { spin_unlock_irqrestore(&ioc->lock, flags); - cpu_relax(); + cpu_chill(); goto retry; } } diff --git a/block/blk-mq.c b/block/blk-mq.c index 5f1493fc9c7f..e8041b1add07 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -320,6 +320,9 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data, rq->extra_len = 0; rq->__deadline = 0; +#ifdef CONFIG_PREEMPT_RT_FULL + INIT_WORK(&rq->work, __blk_mq_complete_request_remote_work); +#endif INIT_LIST_HEAD(&rq->timeout_list); rq->timeout = 0; @@ -547,12 +550,24 @@ void blk_mq_end_request(struct request *rq, blk_status_t error) } EXPORT_SYMBOL(blk_mq_end_request); +#ifdef CONFIG_PREEMPT_RT_FULL + +void __blk_mq_complete_request_remote_work(struct work_struct *work) +{ + struct request *rq = container_of(work, struct request, work); + + rq->q->softirq_done_fn(rq); +} + +#else + static void __blk_mq_complete_request_remote(void *data) { struct request *rq = data; rq->q->softirq_done_fn(rq); } +#endif static void __blk_mq_complete_request(struct request *rq) { @@ -570,19 +585,27 @@ static void __blk_mq_complete_request(struct request *rq) return; } - cpu = get_cpu(); + cpu = get_cpu_light(); if (!test_bit(QUEUE_FLAG_SAME_FORCE, &rq->q->queue_flags)) shared = cpus_share_cache(cpu, ctx->cpu); if (cpu != ctx->cpu && !shared && cpu_online(ctx->cpu)) { +#ifdef CONFIG_PREEMPT_RT_FULL + /* + * We could force QUEUE_FLAG_SAME_FORCE then we would not get in + * here. But we could try to invoke it one the CPU like this. + */ + schedule_work_on(ctx->cpu, &rq->work); +#else rq->csd.func = __blk_mq_complete_request_remote; rq->csd.info = rq; rq->csd.flags = 0; smp_call_function_single_async(ctx->cpu, &rq->csd); +#endif } else { rq->q->softirq_done_fn(rq); } - put_cpu(); + put_cpu_light(); } static void hctx_unlock(struct blk_mq_hw_ctx *hctx, int srcu_idx) @@ -1336,14 +1359,14 @@ static void __blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async, return; if (!async && !(hctx->flags & BLK_MQ_F_BLOCKING)) { - int cpu = get_cpu(); + int cpu = get_cpu_light(); if (cpumask_test_cpu(cpu, hctx->cpumask)) { __blk_mq_run_hw_queue(hctx); - put_cpu(); + put_cpu_light(); return; } - put_cpu(); + put_cpu_light(); } kblockd_mod_delayed_work_on(blk_mq_hctx_next_cpu(hctx), &hctx->run_work, @@ -2996,10 +3019,9 @@ static bool blk_mq_poll_hybrid_sleep(struct request_queue *q, kt = nsecs; mode = HRTIMER_MODE_REL; - hrtimer_init_on_stack(&hs.timer, CLOCK_MONOTONIC, mode); + hrtimer_init_sleeper_on_stack(&hs, CLOCK_MONOTONIC, mode, current); hrtimer_set_expires(&hs.timer, kt); - hrtimer_init_sleeper(&hs, current); do { if (blk_mq_rq_state(rq) == MQ_RQ_COMPLETE) break; diff --git a/block/blk-mq.h b/block/blk-mq.h index 89231e439b2f..1c2007b0a366 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -112,12 +112,12 @@ static inline struct blk_mq_ctx *__blk_mq_get_ctx(struct request_queue *q, */ static inline struct blk_mq_ctx *blk_mq_get_ctx(struct request_queue *q) { - return __blk_mq_get_ctx(q, get_cpu()); + return __blk_mq_get_ctx(q, get_cpu_light()); } static inline void blk_mq_put_ctx(struct blk_mq_ctx *ctx) { - put_cpu(); + put_cpu_light(); } struct blk_mq_alloc_data { diff --git a/block/blk-softirq.c b/block/blk-softirq.c index 15c1f5e12eb8..1628277885a1 100644 --- a/block/blk-softirq.c +++ b/block/blk-softirq.c @@ -53,6 +53,7 @@ static void trigger_softirq(void *data) raise_softirq_irqoff(BLOCK_SOFTIRQ); local_irq_restore(flags); + preempt_check_resched_rt(); } /* @@ -91,6 +92,7 @@ static int blk_softirq_cpu_dead(unsigned int cpu) this_cpu_ptr(&blk_cpu_done)); raise_softirq_irqoff(BLOCK_SOFTIRQ); local_irq_enable(); + preempt_check_resched_rt(); return 0; } @@ -143,6 +145,7 @@ do_local: goto do_local; local_irq_restore(flags); + preempt_check_resched_rt(); } EXPORT_SYMBOL(__blk_complete_request); diff --git a/crypto/cryptd.c b/crypto/cryptd.c index addca7bae33f..8ad657cddc0a 100644 --- a/crypto/cryptd.c +++ b/crypto/cryptd.c @@ -39,6 +39,7 @@ MODULE_PARM_DESC(cryptd_max_cpu_qlen, "Set cryptd Max queue depth"); struct cryptd_cpu_queue { struct crypto_queue queue; struct work_struct work; + spinlock_t qlock; }; struct cryptd_queue { @@ -117,6 +118,7 @@ static int cryptd_init_queue(struct cryptd_queue *queue, cpu_queue = per_cpu_ptr(queue->cpu_queue, cpu); crypto_init_queue(&cpu_queue->queue, max_cpu_qlen); INIT_WORK(&cpu_queue->work, cryptd_queue_worker); + spin_lock_init(&cpu_queue->qlock); } pr_info("cryptd: max_cpu_qlen set to %d\n", max_cpu_qlen); return 0; @@ -141,8 +143,10 @@ static int cryptd_enqueue_request(struct cryptd_queue *queue, struct cryptd_cpu_queue *cpu_queue; atomic_t *refcnt; - cpu = get_cpu(); - cpu_queue = this_cpu_ptr(queue->cpu_queue); + cpu_queue = raw_cpu_ptr(queue->cpu_queue); + spin_lock_bh(&cpu_queue->qlock); + cpu = smp_processor_id(); + err = crypto_enqueue_request(&cpu_queue->queue, request); refcnt = crypto_tfm_ctx(request->tfm); @@ -158,7 +162,7 @@ static int cryptd_enqueue_request(struct cryptd_queue *queue, atomic_inc(refcnt); out_put_cpu: - put_cpu(); + spin_unlock_bh(&cpu_queue->qlock); return err; } @@ -174,16 +178,11 @@ static void cryptd_queue_worker(struct work_struct *work) cpu_queue = container_of(work, struct cryptd_cpu_queue, work); /* * Only handle one request at a time to avoid hogging crypto workqueue. - * preempt_disable/enable is used to prevent being preempted by - * cryptd_enqueue_request(). local_bh_disable/enable is used to prevent - * cryptd_enqueue_request() being accessed from software interrupts. */ - local_bh_disable(); - preempt_disable(); + spin_lock_bh(&cpu_queue->qlock); backlog = crypto_get_backlog(&cpu_queue->queue); req = crypto_dequeue_request(&cpu_queue->queue); - preempt_enable(); - local_bh_enable(); + spin_unlock_bh(&cpu_queue->qlock); if (!req) return; diff --git a/crypto/scompress.c b/crypto/scompress.c index 968bbcf65c94..c2f0077e0801 100644 --- a/crypto/scompress.c +++ b/crypto/scompress.c @@ -24,6 +24,7 @@ #include <linux/cryptouser.h> #include <net/netlink.h> #include <linux/scatterlist.h> +#include <linux/locallock.h> #include <crypto/scatterwalk.h> #include <crypto/internal/acompress.h> #include <crypto/internal/scompress.h> @@ -34,6 +35,7 @@ static void * __percpu *scomp_src_scratches; static void * __percpu *scomp_dst_scratches; static int scomp_scratch_users; static DEFINE_MUTEX(scomp_lock); +static DEFINE_LOCAL_IRQ_LOCK(scomp_scratches_lock); #ifdef CONFIG_NET static int crypto_scomp_report(struct sk_buff *skb, struct crypto_alg *alg) @@ -146,7 +148,7 @@ static int scomp_acomp_comp_decomp(struct acomp_req *req, int dir) void **tfm_ctx = acomp_tfm_ctx(tfm); struct crypto_scomp *scomp = *tfm_ctx; void **ctx = acomp_request_ctx(req); - const int cpu = get_cpu(); + const int cpu = local_lock_cpu(scomp_scratches_lock); u8 *scratch_src = *per_cpu_ptr(scomp_src_scratches, cpu); u8 *scratch_dst = *per_cpu_ptr(scomp_dst_scratches, cpu); int ret; @@ -181,7 +183,7 @@ static int scomp_acomp_comp_decomp(struct acomp_req *req, int dir) 1); } out: - put_cpu(); + local_unlock_cpu(scomp_scratches_lock); return ret; } diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c index cc2f2e35f4c2..c5ea0fc635e5 100644 --- a/drivers/ata/libata-sff.c +++ b/drivers/ata/libata-sff.c @@ -658,36 +658,6 @@ unsigned int ata_sff_data_xfer32(struct ata_queued_cmd *qc, unsigned char *buf, EXPORT_SYMBOL_GPL(ata_sff_data_xfer32); /** - * ata_sff_data_xfer_noirq - Transfer data by PIO - * @qc: queued command - * @buf: data buffer - * @buflen: buffer length - * @rw: read/write - * - * Transfer data from/to the device data register by PIO. Do the - * transfer with interrupts disabled. - * - * LOCKING: - * Inherited from caller. - * - * RETURNS: - * Bytes consumed. - */ -unsigned int ata_sff_data_xfer_noirq(struct ata_queued_cmd *qc, unsigned char *buf, - unsigned int buflen, int rw) -{ - unsigned long flags; - unsigned int consumed; - - local_irq_save(flags); - consumed = ata_sff_data_xfer32(qc, buf, buflen, rw); - local_irq_restore(flags); - - return consumed; -} -EXPORT_SYMBOL_GPL(ata_sff_data_xfer_noirq); - -/** * ata_pio_sector - Transfer a sector of data. * @qc: Command on going * diff --git a/drivers/ata/pata_cmd640.c b/drivers/ata/pata_cmd640.c index c47caa807fa9..e3532eda7b05 100644 --- a/drivers/ata/pata_cmd640.c +++ b/drivers/ata/pata_cmd640.c @@ -178,7 +178,7 @@ static struct scsi_host_template cmd640_sht = { static struct ata_port_operations cmd640_port_ops = { .inherits = &ata_sff_port_ops, /* In theory xfer_noirq is not needed once we kill the prefetcher */ - .sff_data_xfer = ata_sff_data_xfer_noirq, + .sff_data_xfer = ata_sff_data_xfer32, .sff_irq_check = cmd640_sff_irq_check, .qc_issue = cmd640_qc_issue, .cable_detect = ata_cable_40wire, diff --git a/drivers/ata/pata_icside.c b/drivers/ata/pata_icside.c index 188f2f2eb21f..c272f2cbb47c 100644 --- a/drivers/ata/pata_icside.c +++ b/drivers/ata/pata_icside.c @@ -324,7 +324,7 @@ static struct ata_port_operations pata_icside_port_ops = { .inherits = &ata_bmdma_port_ops, /* no need to build any PRD tables for DMA */ .qc_prep = ata_noop_qc_prep, - .sff_data_xfer = ata_sff_data_xfer_noirq, + .sff_data_xfer = ata_sff_data_xfer32, .bmdma_setup = pata_icside_bmdma_setup, .bmdma_start = pata_icside_bmdma_start, .bmdma_stop = pata_icside_bmdma_stop, diff --git a/drivers/ata/pata_imx.c b/drivers/ata/pata_imx.c index d4caa23f5a88..108101325efd 100644 --- a/drivers/ata/pata_imx.c +++ b/drivers/ata/pata_imx.c @@ -102,7 +102,7 @@ static struct scsi_host_template pata_imx_sht = { static struct ata_port_operations pata_imx_port_ops = { .inherits = &ata_sff_port_ops, - .sff_data_xfer = ata_sff_data_xfer_noirq, + .sff_data_xfer = ata_sff_data_xfer32, .cable_detect = ata_cable_unknown, .set_piomode = pata_imx_set_piomode, }; diff --git a/drivers/ata/pata_legacy.c b/drivers/ata/pata_legacy.c index 53828b6c3044..8ea4b8431fc8 100644 --- a/drivers/ata/pata_legacy.c +++ b/drivers/ata/pata_legacy.c @@ -246,12 +246,12 @@ static const struct ata_port_operations legacy_base_port_ops = { static struct ata_port_operations simple_port_ops = { .inherits = &legacy_base_port_ops, - .sff_data_xfer = ata_sff_data_xfer_noirq, + .sff_data_xfer = ata_sff_data_xfer32, }; static struct ata_port_operations legacy_port_ops = { .inherits = &legacy_base_port_ops, - .sff_data_xfer = ata_sff_data_xfer_noirq, + .sff_data_xfer = ata_sff_data_xfer32, .set_mode = legacy_set_mode, }; @@ -341,7 +341,7 @@ static unsigned int pdc_data_xfer_vlb(struct ata_queued_cmd *qc, } local_irq_restore(flags); } else - buflen = ata_sff_data_xfer_noirq(qc, buf, buflen, rw); + buflen = ata_sff_data_xfer32(qc, buf, buflen, rw); return buflen; } diff --git a/drivers/ata/pata_palmld.c b/drivers/ata/pata_palmld.c index 8c0d7d736b7a..d071ab6864a8 100644 --- a/drivers/ata/pata_palmld.c +++ b/drivers/ata/pata_palmld.c @@ -44,7 +44,7 @@ static struct scsi_host_template palmld_sht = { static struct ata_port_operations palmld_port_ops = { .inherits = &ata_sff_port_ops, - .sff_data_xfer = ata_sff_data_xfer_noirq, + .sff_data_xfer = ata_sff_data_xfer32, .cable_detect = ata_cable_40wire, }; diff --git a/drivers/ata/pata_pcmcia.c b/drivers/ata/pata_pcmcia.c index a541eacc5e95..9b0e6c72e3f9 100644 --- a/drivers/ata/pata_pcmcia.c +++ b/drivers/ata/pata_pcmcia.c @@ -151,7 +151,7 @@ static struct scsi_host_template pcmcia_sht = { static struct ata_port_operations pcmcia_port_ops = { .inherits = &ata_sff_port_ops, - .sff_data_xfer = ata_sff_data_xfer_noirq, + .sff_data_xfer = ata_sff_data_xfer32, .cable_detect = ata_cable_40wire, .set_mode = pcmcia_set_mode, }; diff --git a/drivers/ata/pata_platform.c b/drivers/ata/pata_platform.c index c503ded87bb8..d6f8f5406442 100644 --- a/drivers/ata/pata_platform.c +++ b/drivers/ata/pata_platform.c @@ -49,7 +49,7 @@ static struct scsi_host_template pata_platform_sht = { static struct ata_port_operations pata_platform_port_ops = { .inherits = &ata_sff_port_ops, - .sff_data_xfer = ata_sff_data_xfer_noirq, + .sff_data_xfer = ata_sff_data_xfer32, .cable_detect = ata_cable_unknown, .set_mode = pata_platform_set_mode, }; diff --git a/drivers/ata/pata_via.c b/drivers/ata/pata_via.c index 1ca6bcab369f..fd19f1ce83aa 100644 --- a/drivers/ata/pata_via.c +++ b/drivers/ata/pata_via.c @@ -471,7 +471,7 @@ static struct ata_port_operations via_port_ops = { static struct ata_port_operations via_port_ops_noirq = { .inherits = &via_port_ops, - .sff_data_xfer = ata_sff_data_xfer_noirq, + .sff_data_xfer = ata_sff_data_xfer32, }; /** diff --git a/drivers/block/zram/zcomp.c b/drivers/block/zram/zcomp.c index 4ed0a78fdc09..eece02262000 100644 --- a/drivers/block/zram/zcomp.c +++ b/drivers/block/zram/zcomp.c @@ -116,12 +116,20 @@ ssize_t zcomp_available_show(const char *comp, char *buf) struct zcomp_strm *zcomp_stream_get(struct zcomp *comp) { - return *get_cpu_ptr(comp->stream); + struct zcomp_strm *zstrm; + + zstrm = *get_local_ptr(comp->stream); + spin_lock(&zstrm->zcomp_lock); + return zstrm; } void zcomp_stream_put(struct zcomp *comp) { - put_cpu_ptr(comp->stream); + struct zcomp_strm *zstrm; + + zstrm = *this_cpu_ptr(comp->stream); + spin_unlock(&zstrm->zcomp_lock); + put_local_ptr(zstrm); } int zcomp_compress(struct zcomp_strm *zstrm, @@ -171,6 +179,7 @@ int zcomp_cpu_up_prepare(unsigned int cpu, struct hlist_node *node) pr_err("Can't allocate a compression stream\n"); return -ENOMEM; } + spin_lock_init(&zstrm->zcomp_lock); *per_cpu_ptr(comp->stream, cpu) = zstrm; return 0; } diff --git a/drivers/block/zram/zcomp.h b/drivers/block/zram/zcomp.h index 41c1002a7d7d..d424eafcbf8e 100644 --- a/drivers/block/zram/zcomp.h +++ b/drivers/block/zram/zcomp.h @@ -14,6 +14,7 @@ struct zcomp_strm { /* compression/decompression buffer */ void *buffer; struct crypto_comp *tfm; + spinlock_t zcomp_lock; }; /* dynamic per-device compression frontend */ diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 5fa4faaa9d81..5d77b6123918 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -53,6 +53,40 @@ static size_t huge_class_size; static void zram_free_page(struct zram *zram, size_t index); +#ifdef CONFIG_PREEMPT_RT_BASE +static void zram_meta_init_table_locks(struct zram *zram, size_t num_pages) +{ + size_t index; + + for (index = 0; index < num_pages; index++) + spin_lock_init(&zram->table[index].lock); +} + +static int zram_slot_trylock(struct zram *zram, u32 index) +{ + int ret; + + ret = spin_trylock(&zram->table[index].lock); + if (ret) + __set_bit(ZRAM_LOCK, &zram->table[index].value); + return ret; +} + +static void zram_slot_lock(struct zram *zram, u32 index) +{ + spin_lock(&zram->table[index].lock); + __set_bit(ZRAM_LOCK, &zram->table[index].value); +} + +static void zram_slot_unlock(struct zram *zram, u32 index) +{ + __clear_bit(ZRAM_LOCK, &zram->table[index].value); + spin_unlock(&zram->table[index].lock); +} + +#else +static void zram_meta_init_table_locks(struct zram *zram, size_t num_pages) { } + static int zram_slot_trylock(struct zram *zram, u32 index) { return bit_spin_trylock(ZRAM_LOCK, &zram->table[index].value); @@ -67,6 +101,7 @@ static void zram_slot_unlock(struct zram *zram, u32 index) { bit_spin_unlock(ZRAM_LOCK, &zram->table[index].value); } +#endif static inline bool init_done(struct zram *zram) { @@ -901,6 +936,8 @@ static DEVICE_ATTR_RO(io_stat); static DEVICE_ATTR_RO(mm_stat); static DEVICE_ATTR_RO(debug_stat); + + static void zram_meta_free(struct zram *zram, u64 disksize) { size_t num_pages = disksize >> PAGE_SHIFT; @@ -931,6 +968,7 @@ static bool zram_meta_alloc(struct zram *zram, u64 disksize) if (!huge_class_size) huge_class_size = zs_huge_class_size(zram->mem_pool); + zram_meta_init_table_locks(zram, num_pages); return true; } @@ -989,6 +1027,7 @@ static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index, unsigned long handle; unsigned int size; void *src, *dst; + struct zcomp_strm *zstrm; if (zram_wb_enabled(zram)) { zram_slot_lock(zram, index); @@ -1023,6 +1062,7 @@ static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index, size = zram_get_obj_size(zram, index); + zstrm = zcomp_stream_get(zram->comp); src = zs_map_object(zram->mem_pool, handle, ZS_MM_RO); if (size == PAGE_SIZE) { dst = kmap_atomic(page); @@ -1030,14 +1070,13 @@ static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index, kunmap_atomic(dst); ret = 0; } else { - struct zcomp_strm *zstrm = zcomp_stream_get(zram->comp); dst = kmap_atomic(page); ret = zcomp_decompress(zstrm, src, size, dst); kunmap_atomic(dst); - zcomp_stream_put(zram->comp); } zs_unmap_object(zram->mem_pool, handle); + zcomp_stream_put(zram->comp); zram_slot_unlock(zram, index); /* Should NEVER happen. Return bio error if it does. */ diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h index d1095dfdffa8..144e91061df8 100644 --- a/drivers/block/zram/zram_drv.h +++ b/drivers/block/zram/zram_drv.h @@ -61,6 +61,9 @@ struct zram_table_entry { unsigned long element; }; unsigned long value; +#ifdef CONFIG_PREEMPT_RT_BASE + spinlock_t lock; +#endif #ifdef CONFIG_ZRAM_MEMORY_TRACKING ktime_t ac_time; #endif diff --git a/drivers/char/random.c b/drivers/char/random.c index 13c69a681659..093e819ac254 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -265,6 +265,7 @@ #include <linux/syscalls.h> #include <linux/completion.h> #include <linux/uuid.h> +#include <linux/locallock.h> #include <crypto/chacha20.h> #include <asm/processor.h> @@ -1122,8 +1123,6 @@ static void add_timer_randomness(struct timer_rand_state *state, unsigned num) } sample; long delta, delta2, delta3; - preempt_disable(); - sample.jiffies = jiffies; sample.cycles = random_get_entropy(); sample.num = num; @@ -1161,8 +1160,6 @@ static void add_timer_randomness(struct timer_rand_state *state, unsigned num) * and limit entropy entimate to 12 bits. */ credit_entropy_bits(r, min_t(int, fls(delta>>1), 11)); - - preempt_enable(); } void add_input_randomness(unsigned int type, unsigned int code, @@ -1219,28 +1216,27 @@ static __u32 get_reg(struct fast_pool *f, struct pt_regs *regs) return *ptr; } -void add_interrupt_randomness(int irq, int irq_flags) +void add_interrupt_randomness(int irq, int irq_flags, __u64 ip) { struct entropy_store *r; struct fast_pool *fast_pool = this_cpu_ptr(&irq_randomness); - struct pt_regs *regs = get_irq_regs(); unsigned long now = jiffies; cycles_t cycles = random_get_entropy(); __u32 c_high, j_high; - __u64 ip; unsigned long seed; int credit = 0; if (cycles == 0) - cycles = get_reg(fast_pool, regs); + cycles = get_reg(fast_pool, NULL); c_high = (sizeof(cycles) > 4) ? cycles >> 32 : 0; j_high = (sizeof(now) > 4) ? now >> 32 : 0; fast_pool->pool[0] ^= cycles ^ j_high ^ irq; fast_pool->pool[1] ^= now ^ c_high; - ip = regs ? instruction_pointer(regs) : _RET_IP_; + if (!ip) + ip = _RET_IP_; fast_pool->pool[2] ^= ip; fast_pool->pool[3] ^= (sizeof(ip) > 4) ? ip >> 32 : - get_reg(fast_pool, regs); + get_reg(fast_pool, NULL); fast_mix(fast_pool); add_interrupt_bench(cycles); diff --git a/drivers/char/tpm/tpm_tis.c b/drivers/char/tpm/tpm_tis.c index f08949a5f678..9fefcfcae593 100644 --- a/drivers/char/tpm/tpm_tis.c +++ b/drivers/char/tpm/tpm_tis.c @@ -53,6 +53,31 @@ static inline struct tpm_tis_tcg_phy *to_tpm_tis_tcg_phy(struct tpm_tis_data *da return container_of(data, struct tpm_tis_tcg_phy, priv); } +#ifdef CONFIG_PREEMPT_RT_FULL +/* + * Flushes previous write operations to chip so that a subsequent + * ioread*()s won't stall a cpu. + */ +static inline void tpm_tis_flush(void __iomem *iobase) +{ + ioread8(iobase + TPM_ACCESS(0)); +} +#else +#define tpm_tis_flush(iobase) do { } while (0) +#endif + +static inline void tpm_tis_iowrite8(u8 b, void __iomem *iobase, u32 addr) +{ + iowrite8(b, iobase + addr); + tpm_tis_flush(iobase); +} + +static inline void tpm_tis_iowrite32(u32 b, void __iomem *iobase, u32 addr) +{ + iowrite32(b, iobase + addr); + tpm_tis_flush(iobase); +} + static bool interrupts = true; module_param(interrupts, bool, 0444); MODULE_PARM_DESC(interrupts, "Enable interrupts"); @@ -150,7 +175,7 @@ static int tpm_tcg_write_bytes(struct tpm_tis_data *data, u32 addr, u16 len, struct tpm_tis_tcg_phy *phy = to_tpm_tis_tcg_phy(data); while (len--) - iowrite8(*value++, phy->iobase + addr); + tpm_tis_iowrite8(*value++, phy->iobase, addr); return 0; } @@ -177,7 +202,7 @@ static int tpm_tcg_write32(struct tpm_tis_data *data, u32 addr, u32 value) { struct tpm_tis_tcg_phy *phy = to_tpm_tis_tcg_phy(data); - iowrite32(value, phy->iobase + addr); + tpm_tis_iowrite32(value, phy->iobase, addr); return 0; } diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig index 88b93f704e59..6a9cab1aea33 100644 --- a/drivers/clocksource/Kconfig +++ b/drivers/clocksource/Kconfig @@ -404,8 +404,11 @@ config ARMV7M_SYSTICK This options enables support for the ARMv7M system timer unit config ATMEL_PIT + bool "Microchip ARM Periodic Interval Timer (PIT)" if COMPILE_TEST select TIMER_OF if OF - def_bool SOC_AT91SAM9 || SOC_SAMA5 + help + This enables build of clocksource and clockevent driver for + the integrated PIT in Microchip ARM SoCs. config ATMEL_ST bool "Atmel ST timer support" if COMPILE_TEST @@ -415,6 +418,14 @@ config ATMEL_ST help Support for the Atmel ST timer. +config ATMEL_ARM_TCB_CLKSRC + bool "Microchip ARM TC Block" if COMPILE_TEST + select REGMAP_MMIO + depends on GENERIC_CLOCKEVENTS + help + This enables build of clocksource and clockevent driver for + the integrated Timer Counter Blocks in Microchip ARM SoCs. + config CLKSRC_EXYNOS_MCT bool "Exynos multi core timer driver" if COMPILE_TEST depends on ARM || ARM64 diff --git a/drivers/clocksource/Makefile b/drivers/clocksource/Makefile index 00caf37e52f9..6991348aa24a 100644 --- a/drivers/clocksource/Makefile +++ b/drivers/clocksource/Makefile @@ -3,7 +3,8 @@ obj-$(CONFIG_TIMER_OF) += timer-of.o obj-$(CONFIG_TIMER_PROBE) += timer-probe.o obj-$(CONFIG_ATMEL_PIT) += timer-atmel-pit.o obj-$(CONFIG_ATMEL_ST) += timer-atmel-st.o -obj-$(CONFIG_ATMEL_TCB_CLKSRC) += tcb_clksrc.o +obj-$(CONFIG_ATMEL_TCB_CLKSRC) += tcb_clksrc.o +obj-$(CONFIG_ATMEL_ARM_TCB_CLKSRC) += timer-atmel-tcb.o obj-$(CONFIG_X86_PM_TIMER) += acpi_pm.o obj-$(CONFIG_SCx200HR_TIMER) += scx200_hrt.o obj-$(CONFIG_CS5535_CLOCK_EVENT_SRC) += cs5535-clockevt.o diff --git a/drivers/clocksource/tcb_clksrc.c b/drivers/clocksource/tcb_clksrc.c index 43f4d5c4d6fa..ba15242a6066 100644 --- a/drivers/clocksource/tcb_clksrc.c +++ b/drivers/clocksource/tcb_clksrc.c @@ -25,8 +25,7 @@ * this 32 bit free-running counter. the second channel is not used. * * - The third channel may be used to provide a 16-bit clockevent - * source, used in either periodic or oneshot mode. This runs - * at 32 KiHZ, and can handle delays of up to two seconds. + * source, used in either periodic or oneshot mode. * * A boot clocksource and clockevent source are also currently needed, * unless the relevant platforms (ARM/AT91, AVR32/AT32) are changed so @@ -126,6 +125,8 @@ static struct clocksource clksrc = { struct tc_clkevt_device { struct clock_event_device clkevt; struct clk *clk; + bool clk_enabled; + u32 freq; void __iomem *regs; }; @@ -134,15 +135,26 @@ static struct tc_clkevt_device *to_tc_clkevt(struct clock_event_device *clkevt) return container_of(clkevt, struct tc_clkevt_device, clkevt); } -/* For now, we always use the 32K clock ... this optimizes for NO_HZ, - * because using one of the divided clocks would usually mean the - * tick rate can never be less than several dozen Hz (vs 0.5 Hz). - * - * A divided clock could be good for high resolution timers, since - * 30.5 usec resolution can seem "low". - */ static u32 timer_clock; +static void tc_clk_disable(struct clock_event_device *d) +{ + struct tc_clkevt_device *tcd = to_tc_clkevt(d); + + clk_disable(tcd->clk); + tcd->clk_enabled = false; +} + +static void tc_clk_enable(struct clock_event_device *d) +{ + struct tc_clkevt_device *tcd = to_tc_clkevt(d); + + if (tcd->clk_enabled) + return; + clk_enable(tcd->clk); + tcd->clk_enabled = true; +} + static int tc_shutdown(struct clock_event_device *d) { struct tc_clkevt_device *tcd = to_tc_clkevt(d); @@ -150,8 +162,14 @@ static int tc_shutdown(struct clock_event_device *d) writel(0xff, regs + ATMEL_TC_REG(2, IDR)); writel(ATMEL_TC_CLKDIS, regs + ATMEL_TC_REG(2, CCR)); + return 0; +} + +static int tc_shutdown_clk_off(struct clock_event_device *d) +{ + tc_shutdown(d); if (!clockevent_state_detached(d)) - clk_disable(tcd->clk); + tc_clk_disable(d); return 0; } @@ -164,9 +182,9 @@ static int tc_set_oneshot(struct clock_event_device *d) if (clockevent_state_oneshot(d) || clockevent_state_periodic(d)) tc_shutdown(d); - clk_enable(tcd->clk); + tc_clk_enable(d); - /* slow clock, count up to RC, then irq and stop */ + /* count up to RC, then irq and stop */ writel(timer_clock | ATMEL_TC_CPCSTOP | ATMEL_TC_WAVE | ATMEL_TC_WAVESEL_UP_AUTO, regs + ATMEL_TC_REG(2, CMR)); writel(ATMEL_TC_CPCS, regs + ATMEL_TC_REG(2, IER)); @@ -186,12 +204,12 @@ static int tc_set_periodic(struct clock_event_device *d) /* By not making the gentime core emulate periodic mode on top * of oneshot, we get lower overhead and improved accuracy. */ - clk_enable(tcd->clk); + tc_clk_enable(d); - /* slow clock, count up to RC, then irq and restart */ + /* count up to RC, then irq and restart */ writel(timer_clock | ATMEL_TC_WAVE | ATMEL_TC_WAVESEL_UP_AUTO, regs + ATMEL_TC_REG(2, CMR)); - writel((32768 + HZ / 2) / HZ, tcaddr + ATMEL_TC_REG(2, RC)); + writel((tcd->freq + HZ / 2) / HZ, tcaddr + ATMEL_TC_REG(2, RC)); /* Enable clock and interrupts on RC compare */ writel(ATMEL_TC_CPCS, regs + ATMEL_TC_REG(2, IER)); @@ -218,9 +236,13 @@ static struct tc_clkevt_device clkevt = { .features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT, /* Should be lower than at91rm9200's system timer */ +#ifdef CONFIG_ATMEL_TCB_CLKSRC_USE_SLOW_CLOCK .rating = 125, +#else + .rating = 200, +#endif .set_next_event = tc_next_event, - .set_state_shutdown = tc_shutdown, + .set_state_shutdown = tc_shutdown_clk_off, .set_state_periodic = tc_set_periodic, .set_state_oneshot = tc_set_oneshot, }, @@ -240,8 +262,9 @@ static irqreturn_t ch2_irq(int irq, void *handle) return IRQ_NONE; } -static int __init setup_clkevents(struct atmel_tc *tc, int clk32k_divisor_idx) +static int __init setup_clkevents(struct atmel_tc *tc, int divisor_idx) { + unsigned divisor = atmel_tc_divisors[divisor_idx]; int ret; struct clk *t2_clk = tc->clk[2]; int irq = tc->irq[2]; @@ -262,7 +285,11 @@ static int __init setup_clkevents(struct atmel_tc *tc, int clk32k_divisor_idx) clkevt.regs = tc->regs; clkevt.clk = t2_clk; - timer_clock = clk32k_divisor_idx; + timer_clock = divisor_idx; + if (!divisor) + clkevt.freq = 32768; + else + clkevt.freq = clk_get_rate(t2_clk) / divisor; clkevt.clkevt.cpumask = cpumask_of(0); @@ -273,7 +300,7 @@ static int __init setup_clkevents(struct atmel_tc *tc, int clk32k_divisor_idx) return ret; } - clockevents_config_and_register(&clkevt.clkevt, 32768, 1, 0xffff); + clockevents_config_and_register(&clkevt.clkevt, clkevt.freq, 1, 0xffff); return ret; } @@ -410,7 +437,11 @@ static int __init tcb_clksrc_init(void) goto err_disable_t1; /* channel 2: periodic and oneshot timer support */ +#ifdef CONFIG_ATMEL_TCB_CLKSRC_USE_SLOW_CLOCK ret = setup_clkevents(tc, clk32k_divisor_idx); +#else + ret = setup_clkevents(tc, best_divisor_idx); +#endif if (ret) goto err_unregister_clksrc; diff --git a/drivers/clocksource/timer-atmel-tcb.c b/drivers/clocksource/timer-atmel-tcb.c new file mode 100644 index 000000000000..bbbacf8c46b0 --- /dev/null +++ b/drivers/clocksource/timer-atmel-tcb.c @@ -0,0 +1,608 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/clk.h> +#include <linux/clockchips.h> +#include <linux/clocksource.h> +#include <linux/interrupt.h> +#include <linux/kernel.h> +#include <linux/mfd/syscon.h> +#include <linux/of_address.h> +#include <linux/of_irq.h> +#include <linux/regmap.h> +#include <linux/sched_clock.h> +#include <soc/at91/atmel_tcb.h> + +static struct atmel_tcb_clksrc { + struct clocksource clksrc; + struct clock_event_device clkevt; + struct regmap *regmap; + void __iomem *base; + struct clk *clk[2]; + char name[20]; + int channels[2]; + int bits; + int irq; + struct { + u32 cmr; + u32 imr; + u32 rc; + bool clken; + } cache[2]; + u32 bmr_cache; + bool registered; +} tc = { + .clksrc = { + .rating = 200, + .mask = CLOCKSOURCE_MASK(32), + .flags = CLOCK_SOURCE_IS_CONTINUOUS, + }, + .clkevt = { + .features = CLOCK_EVT_FEAT_ONESHOT, + /* Should be lower than at91rm9200's system timer */ + .rating = 125, + }, +}; + +static struct tc_clkevt_device { + struct clock_event_device clkevt; + struct regmap *regmap; + void __iomem *base; + struct clk *slow_clk; + struct clk *clk; + char name[20]; + int channel; + int irq; + struct { + u32 cmr; + u32 imr; + u32 rc; + bool clken; + } cache; + bool registered; +} tce = { + .clkevt = { + .features = CLOCK_EVT_FEAT_PERIODIC | + CLOCK_EVT_FEAT_ONESHOT, + /* + * Should be lower than at91rm9200's system timer + * but higher than tc.clkevt.rating + */ + .rating = 140, + }, +}; + +/* + * Clockevent device using its own channel + */ +static int tc_clkevt2_shutdown(struct clock_event_device *d) +{ + writel(0xff, tce.base + ATMEL_TC_IDR(tce.channel)); + writel(ATMEL_TC_CCR_CLKDIS, tce.base + ATMEL_TC_CCR(tce.channel)); + if (!clockevent_state_detached(d)) + clk_disable(tce.clk); + + return 0; +} + +/* For now, we always use the 32K clock ... this optimizes for NO_HZ, + * because using one of the divided clocks would usually mean the + * tick rate can never be less than several dozen Hz (vs 0.5 Hz). + * + * A divided clock could be good for high resolution timers, since + * 30.5 usec resolution can seem "low". + */ +static int tc_clkevt2_set_oneshot(struct clock_event_device *d) +{ + if (clockevent_state_oneshot(d) || clockevent_state_periodic(d)) + tc_clkevt2_shutdown(d); + + clk_enable(tce.clk); + + /* slow clock, count up to RC, then irq and stop */ + writel(ATMEL_TC_CMR_TCLK(4) | ATMEL_TC_CMR_CPCSTOP | + ATMEL_TC_CMR_WAVE | ATMEL_TC_CMR_WAVESEL_UPRC, + tce.base + ATMEL_TC_CMR(tce.channel)); + writel(ATMEL_TC_CPCS, tce.base + ATMEL_TC_IER(tce.channel)); + + return 0; +} + +static int tc_clkevt2_set_periodic(struct clock_event_device *d) +{ + if (clockevent_state_oneshot(d) || clockevent_state_periodic(d)) + tc_clkevt2_shutdown(d); + + /* By not making the gentime core emulate periodic mode on top + * of oneshot, we get lower overhead and improved accuracy. + */ + clk_enable(tce.clk); + + /* slow clock, count up to RC, then irq and restart */ + writel(ATMEL_TC_CMR_TCLK(4) | ATMEL_TC_CMR_WAVE | + ATMEL_TC_CMR_WAVESEL_UPRC, + tce.base + ATMEL_TC_CMR(tce.channel)); + writel((32768 + HZ / 2) / HZ, tce.base + ATMEL_TC_RC(tce.channel)); + + /* Enable clock and interrupts on RC compare */ + writel(ATMEL_TC_CPCS, tce.base + ATMEL_TC_IER(tce.channel)); + writel(ATMEL_TC_CCR_CLKEN | ATMEL_TC_CCR_SWTRG, + tce.base + ATMEL_TC_CCR(tce.channel)); + + return 0; +} + +static int tc_clkevt2_next_event(unsigned long delta, + struct clock_event_device *d) +{ + writel(delta, tce.base + ATMEL_TC_RC(tce.channel)); + writel(ATMEL_TC_CCR_CLKEN | ATMEL_TC_CCR_SWTRG, + tce.base + ATMEL_TC_CCR(tce.channel)); + + return 0; +} + +static irqreturn_t tc_clkevt2_irq(int irq, void *handle) +{ + unsigned int sr; + + sr = readl(tce.base + ATMEL_TC_SR(tce.channel)); + if (sr & ATMEL_TC_CPCS) { + tce.clkevt.event_handler(&tce.clkevt); + return IRQ_HANDLED; + } + + return IRQ_NONE; +} + +static void tc_clkevt2_suspend(struct clock_event_device *d) +{ + tce.cache.cmr = readl(tce.base + ATMEL_TC_CMR(tce.channel)); + tce.cache.imr = readl(tce.base + ATMEL_TC_IMR(tce.channel)); + tce.cache.rc = readl(tce.base + ATMEL_TC_RC(tce.channel)); + tce.cache.clken = !!(readl(tce.base + ATMEL_TC_SR(tce.channel)) & + ATMEL_TC_CLKSTA); +} + +static void tc_clkevt2_resume(struct clock_event_device *d) +{ + /* Restore registers for the channel, RA and RB are not used */ + writel(tce.cache.cmr, tc.base + ATMEL_TC_CMR(tce.channel)); + writel(tce.cache.rc, tc.base + ATMEL_TC_RC(tce.channel)); + writel(0, tc.base + ATMEL_TC_RA(tce.channel)); + writel(0, tc.base + ATMEL_TC_RB(tce.channel)); + /* Disable all the interrupts */ + writel(0xff, tc.base + ATMEL_TC_IDR(tce.channel)); + /* Reenable interrupts that were enabled before suspending */ + writel(tce.cache.imr, tc.base + ATMEL_TC_IER(tce.channel)); + + /* Start the clock if it was used */ + if (tce.cache.clken) + writel(ATMEL_TC_CCR_CLKEN | ATMEL_TC_CCR_SWTRG, + tc.base + ATMEL_TC_CCR(tce.channel)); +} + +static int __init tc_clkevt_register(struct device_node *node, + struct regmap *regmap, void __iomem *base, + int channel, int irq, int bits) +{ + int ret; + + tce.regmap = regmap; + tce.base = base; + tce.channel = channel; + tce.irq = irq; + + tce.slow_clk = of_clk_get_by_name(node->parent, "slow_clk"); + if (IS_ERR(tce.slow_clk)) + return PTR_ERR(tce.slow_clk); + + ret = clk_prepare_enable(tce.slow_clk); + if (ret) + return ret; + + tce.clk = tcb_clk_get(node, tce.channel); + if (IS_ERR(tce.clk)) { + ret = PTR_ERR(tce.clk); + goto err_slow; + } + + snprintf(tce.name, sizeof(tce.name), "%s:%d", + kbasename(node->parent->full_name), channel); + tce.clkevt.cpumask = cpumask_of(0); + tce.clkevt.name = tce.name; + tce.clkevt.set_next_event = tc_clkevt2_next_event, + tce.clkevt.set_state_shutdown = tc_clkevt2_shutdown, + tce.clkevt.set_state_periodic = tc_clkevt2_set_periodic, + tce.clkevt.set_state_oneshot = tc_clkevt2_set_oneshot, + tce.clkevt.suspend = tc_clkevt2_suspend, + tce.clkevt.resume = tc_clkevt2_resume, + + /* try to enable clk to avoid future errors in mode change */ + ret = clk_prepare_enable(tce.clk); + if (ret) + goto err_slow; + clk_disable(tce.clk); + + clockevents_config_and_register(&tce.clkevt, 32768, 1, BIT(bits) - 1); + + ret = request_irq(tce.irq, tc_clkevt2_irq, IRQF_TIMER | IRQF_SHARED, + tce.clkevt.name, &tce); + if (ret) + goto err_clk; + + tce.registered = true; + + return 0; + +err_clk: + clk_unprepare(tce.clk); +err_slow: + clk_disable_unprepare(tce.slow_clk); + + return ret; +} + +/* + * Clocksource and clockevent using the same channel(s) + */ +static u64 tc_get_cycles(struct clocksource *cs) +{ + u32 lower, upper; + + do { + upper = readl_relaxed(tc.base + ATMEL_TC_CV(tc.channels[1])); + lower = readl_relaxed(tc.base + ATMEL_TC_CV(tc.channels[0])); + } while (upper != readl_relaxed(tc.base + ATMEL_TC_CV(tc.channels[1]))); + + return (upper << 16) | lower; +} + +static u64 tc_get_cycles32(struct clocksource *cs) +{ + return readl_relaxed(tc.base + ATMEL_TC_CV(tc.channels[0])); +} + +static u64 notrace tc_sched_clock_read(void) +{ + return tc_get_cycles(&tc.clksrc); +} + +static u64 notrace tc_sched_clock_read32(void) +{ + return tc_get_cycles32(&tc.clksrc); +} + +static int tcb_clkevt_next_event(unsigned long delta, + struct clock_event_device *d) +{ + u32 old, next, cur; + + + old = readl(tc.base + ATMEL_TC_CV(tc.channels[0])); + next = old + delta; + writel(next, tc.base + ATMEL_TC_RC(tc.channels[0])); + cur = readl(tc.base + ATMEL_TC_CV(tc.channels[0])); + + /* check whether the delta elapsed while setting the register */ + if ((next < old && cur < old && cur > next) || + (next > old && (cur < old || cur > next))) { + /* + * Clear the CPCS bit in the status register to avoid + * generating a spurious interrupt next time a valid + * timer event is configured. + */ + old = readl(tc.base + ATMEL_TC_SR(tc.channels[0])); + return -ETIME; + } + + writel(ATMEL_TC_CPCS, tc.base + ATMEL_TC_IER(tc.channels[0])); + + return 0; +} + +static irqreturn_t tc_clkevt_irq(int irq, void *handle) +{ + unsigned int sr; + + sr = readl(tc.base + ATMEL_TC_SR(tc.channels[0])); + if (sr & ATMEL_TC_CPCS) { + tc.clkevt.event_handler(&tc.clkevt); + return IRQ_HANDLED; + } + + return IRQ_NONE; +} + +static int tcb_clkevt_oneshot(struct clock_event_device *dev) +{ + if (clockevent_state_oneshot(dev)) + return 0; + + /* + * Because both clockevent devices may share the same IRQ, we don't want + * the less likely one to stay requested + */ + return request_irq(tc.irq, tc_clkevt_irq, IRQF_TIMER | IRQF_SHARED, + tc.name, &tc); +} + +static int tcb_clkevt_shutdown(struct clock_event_device *dev) +{ + writel(0xff, tc.base + ATMEL_TC_IDR(tc.channels[0])); + if (tc.bits == 16) + writel(0xff, tc.base + ATMEL_TC_IDR(tc.channels[1])); + + if (!clockevent_state_detached(dev)) + free_irq(tc.irq, &tc); + + return 0; +} + +static void __init tcb_setup_dual_chan(struct atmel_tcb_clksrc *tc, + int mck_divisor_idx) +{ + /* first channel: waveform mode, input mclk/8, clock TIOA on overflow */ + writel(mck_divisor_idx /* likely divide-by-8 */ + | ATMEL_TC_CMR_WAVE + | ATMEL_TC_CMR_WAVESEL_UP /* free-run */ + | ATMEL_TC_CMR_ACPA(SET) /* TIOA rises at 0 */ + | ATMEL_TC_CMR_ACPC(CLEAR), /* (duty cycle 50%) */ + tc->base + ATMEL_TC_CMR(tc->channels[0])); + writel(0x0000, tc->base + ATMEL_TC_RA(tc->channels[0])); + writel(0x8000, tc->base + ATMEL_TC_RC(tc->channels[0])); + writel(0xff, tc->base + ATMEL_TC_IDR(tc->channels[0])); /* no irqs */ + writel(ATMEL_TC_CCR_CLKEN, tc->base + ATMEL_TC_CCR(tc->channels[0])); + + /* second channel: waveform mode, input TIOA */ + writel(ATMEL_TC_CMR_XC(tc->channels[1]) /* input: TIOA */ + | ATMEL_TC_CMR_WAVE + | ATMEL_TC_CMR_WAVESEL_UP, /* free-run */ + tc->base + ATMEL_TC_CMR(tc->channels[1])); + writel(0xff, tc->base + ATMEL_TC_IDR(tc->channels[1])); /* no irqs */ + writel(ATMEL_TC_CCR_CLKEN, tc->base + ATMEL_TC_CCR(tc->channels[1])); + + /* chain both channel, we assume the previous channel */ + regmap_write(tc->regmap, ATMEL_TC_BMR, + ATMEL_TC_BMR_TCXC(1 + tc->channels[1], tc->channels[1])); + /* then reset all the timers */ + regmap_write(tc->regmap, ATMEL_TC_BCR, ATMEL_TC_BCR_SYNC); +} + +static void __init tcb_setup_single_chan(struct atmel_tcb_clksrc *tc, + int mck_divisor_idx) +{ + /* channel 0: waveform mode, input mclk/8 */ + writel(mck_divisor_idx /* likely divide-by-8 */ + | ATMEL_TC_CMR_WAVE + | ATMEL_TC_CMR_WAVESEL_UP, /* free-run */ + tc->base + ATMEL_TC_CMR(tc->channels[0])); + writel(0xff, tc->base + ATMEL_TC_IDR(tc->channels[0])); /* no irqs */ + writel(ATMEL_TC_CCR_CLKEN, tc->base + ATMEL_TC_CCR(tc->channels[0])); + + /* then reset all the timers */ + regmap_write(tc->regmap, ATMEL_TC_BCR, ATMEL_TC_BCR_SYNC); +} + +static void tc_clksrc_suspend(struct clocksource *cs) +{ + int i; + + for (i = 0; i < 1 + (tc.bits == 16); i++) { + tc.cache[i].cmr = readl(tc.base + ATMEL_TC_CMR(tc.channels[i])); + tc.cache[i].imr = readl(tc.base + ATMEL_TC_IMR(tc.channels[i])); + tc.cache[i].rc = readl(tc.base + ATMEL_TC_RC(tc.channels[i])); + tc.cache[i].clken = !!(readl(tc.base + + ATMEL_TC_SR(tc.channels[i])) & + ATMEL_TC_CLKSTA); + } + + if (tc.bits == 16) + regmap_read(tc.regmap, ATMEL_TC_BMR, &tc.bmr_cache); +} + +static void tc_clksrc_resume(struct clocksource *cs) +{ + int i; + + for (i = 0; i < 1 + (tc.bits == 16); i++) { + /* Restore registers for the channel, RA and RB are not used */ + writel(tc.cache[i].cmr, tc.base + ATMEL_TC_CMR(tc.channels[i])); + writel(tc.cache[i].rc, tc.base + ATMEL_TC_RC(tc.channels[i])); + writel(0, tc.base + ATMEL_TC_RA(tc.channels[i])); + writel(0, tc.base + ATMEL_TC_RB(tc.channels[i])); + /* Disable all the interrupts */ + writel(0xff, tc.base + ATMEL_TC_IDR(tc.channels[i])); + /* Reenable interrupts that were enabled before suspending */ + writel(tc.cache[i].imr, tc.base + ATMEL_TC_IER(tc.channels[i])); + + /* Start the clock if it was used */ + if (tc.cache[i].clken) + writel(ATMEL_TC_CCR_CLKEN, tc.base + + ATMEL_TC_CCR(tc.channels[i])); + } + + /* in case of dual channel, chain channels */ + if (tc.bits == 16) + regmap_write(tc.regmap, ATMEL_TC_BMR, tc.bmr_cache); + /* Finally, trigger all the channels*/ + regmap_write(tc.regmap, ATMEL_TC_BCR, ATMEL_TC_BCR_SYNC); +} + +static int __init tcb_clksrc_register(struct device_node *node, + struct regmap *regmap, void __iomem *base, + int channel, int channel1, int irq, + int bits) +{ + u32 rate, divided_rate = 0; + int best_divisor_idx = -1; + int i, err = -1; + u64 (*tc_sched_clock)(void); + + tc.regmap = regmap; + tc.base = base; + tc.channels[0] = channel; + tc.channels[1] = channel1; + tc.irq = irq; + tc.bits = bits; + + tc.clk[0] = tcb_clk_get(node, tc.channels[0]); + if (IS_ERR(tc.clk[0])) + return PTR_ERR(tc.clk[0]); + err = clk_prepare_enable(tc.clk[0]); + if (err) { + pr_debug("can't enable T0 clk\n"); + goto err_clk; + } + + /* How fast will we be counting? Pick something over 5 MHz. */ + rate = (u32)clk_get_rate(tc.clk[0]); + for (i = 0; i < 5; i++) { + unsigned int divisor = atmel_tc_divisors[i]; + unsigned int tmp; + + if (!divisor) + continue; + + tmp = rate / divisor; + pr_debug("TC: %u / %-3u [%d] --> %u\n", rate, divisor, i, tmp); + if (best_divisor_idx > 0) { + if (tmp < 5 * 1000 * 1000) + continue; + } + divided_rate = tmp; + best_divisor_idx = i; + } + + if (tc.bits == 32) { + tc.clksrc.read = tc_get_cycles32; + tcb_setup_single_chan(&tc, best_divisor_idx); + tc_sched_clock = tc_sched_clock_read32; + snprintf(tc.name, sizeof(tc.name), "%s:%d", + kbasename(node->parent->full_name), tc.channels[0]); + } else { + tc.clk[1] = tcb_clk_get(node, tc.channels[1]); + if (IS_ERR(tc.clk[1])) + goto err_disable_t0; + + err = clk_prepare_enable(tc.clk[1]); + if (err) { + pr_debug("can't enable T1 clk\n"); + goto err_clk1; + } + tc.clksrc.read = tc_get_cycles, + tcb_setup_dual_chan(&tc, best_divisor_idx); + tc_sched_clock = tc_sched_clock_read; + snprintf(tc.name, sizeof(tc.name), "%s:%d,%d", + kbasename(node->parent->full_name), tc.channels[0], + tc.channels[1]); + } + + pr_debug("%s at %d.%03d MHz\n", tc.name, + divided_rate / 1000000, + ((divided_rate + 500000) % 1000000) / 1000); + + tc.clksrc.name = tc.name; + tc.clksrc.suspend = tc_clksrc_suspend; + tc.clksrc.resume = tc_clksrc_resume; + + err = clocksource_register_hz(&tc.clksrc, divided_rate); + if (err) + goto err_disable_t1; + + sched_clock_register(tc_sched_clock, 32, divided_rate); + + tc.registered = true; + + /* Set up and register clockevents */ + tc.clkevt.name = tc.name; + tc.clkevt.cpumask = cpumask_of(0); + tc.clkevt.set_next_event = tcb_clkevt_next_event; + tc.clkevt.set_state_oneshot = tcb_clkevt_oneshot; + tc.clkevt.set_state_shutdown = tcb_clkevt_shutdown; + clockevents_config_and_register(&tc.clkevt, divided_rate, 1, + BIT(tc.bits) - 1); + + return 0; + +err_disable_t1: + if (tc.bits == 16) + clk_disable_unprepare(tc.clk[1]); + +err_clk1: + if (tc.bits == 16) + clk_put(tc.clk[1]); + +err_disable_t0: + clk_disable_unprepare(tc.clk[0]); + +err_clk: + clk_put(tc.clk[0]); + + pr_err("%s: unable to register clocksource/clockevent\n", + tc.clksrc.name); + + return err; +} + +static int __init tcb_clksrc_init(struct device_node *node) +{ + const struct of_device_id *match; + const struct atmel_tcb_info *tcb_info; + struct regmap *regmap; + void __iomem *tcb_base; + u32 channel; + int bits, irq, err, chan1 = -1; + + if (tc.registered && tce.registered) + return -ENODEV; + + /* + * The regmap has to be used to access registers that are shared + * between channels on the same TCB but we keep direct IO access for + * the counters to avoid the impact on performance + */ + regmap = syscon_node_to_regmap(node->parent); + if (IS_ERR(regmap)) + return PTR_ERR(regmap); + + tcb_base = of_iomap(node->parent, 0); + if (!tcb_base) { + pr_err("%s +%d %s\n", __FILE__, __LINE__, __func__); + return -ENXIO; + } + + match = of_match_node(atmel_tcb_dt_ids, node->parent); + tcb_info = match->data; + bits = tcb_info->bits; + + err = of_property_read_u32_index(node, "reg", 0, &channel); + if (err) + return err; + + irq = tcb_irq_get(node, channel); + if (irq < 0) + return irq; + + if (tc.registered) + return tc_clkevt_register(node, regmap, tcb_base, channel, irq, + bits); + + if (bits == 16) { + of_property_read_u32_index(node, "reg", 1, &chan1); + if (chan1 == -1) { + if (tce.registered) { + pr_err("%s: clocksource needs two channels\n", + node->parent->full_name); + return -EINVAL; + } else { + return tc_clkevt_register(node, regmap, + tcb_base, channel, + irq, bits); + } + } + } + + return tcb_clksrc_register(node, regmap, tcb_base, channel, chan1, irq, + bits); +} +CLOCKSOURCE_OF_DECLARE(atmel_tcb_clksrc, "atmel,tcb-timer", + tcb_clksrc_init); diff --git a/drivers/connector/cn_proc.c b/drivers/connector/cn_proc.c index ad48fd52cb53..c5264b3ee0b0 100644 --- a/drivers/connector/cn_proc.c +++ b/drivers/connector/cn_proc.c @@ -32,6 +32,7 @@ #include <linux/pid_namespace.h> #include <linux/cn_proc.h> +#include <linux/locallock.h> /* * Size of a cn_msg followed by a proc_event structure. Since the @@ -54,10 +55,11 @@ static struct cb_id cn_proc_event_id = { CN_IDX_PROC, CN_VAL_PROC }; /* proc_event_counts is used as the sequence number of the netlink message */ static DEFINE_PER_CPU(__u32, proc_event_counts) = { 0 }; +static DEFINE_LOCAL_IRQ_LOCK(send_msg_lock); static inline void send_msg(struct cn_msg *msg) { - preempt_disable(); + local_lock(send_msg_lock); msg->seq = __this_cpu_inc_return(proc_event_counts) - 1; ((struct proc_event *)msg->data)->cpu = smp_processor_id(); @@ -70,7 +72,7 @@ static inline void send_msg(struct cn_msg *msg) */ cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_NOWAIT); - preempt_enable(); + local_unlock(send_msg_lock); } void proc_fork_connector(struct task_struct *task) diff --git a/drivers/cpufreq/Kconfig.x86 b/drivers/cpufreq/Kconfig.x86 index 35f71825b7f3..bb4a6160d0f7 100644 --- a/drivers/cpufreq/Kconfig.x86 +++ b/drivers/cpufreq/Kconfig.x86 @@ -125,7 +125,7 @@ config X86_POWERNOW_K7_ACPI config X86_POWERNOW_K8 tristate "AMD Opteron/Athlon64 PowerNow!" - depends on ACPI && ACPI_PROCESSOR && X86_ACPI_CPUFREQ + depends on ACPI && ACPI_PROCESSOR && X86_ACPI_CPUFREQ && !PREEMPT_RT_BASE help This adds the CPUFreq driver for K8/early Opteron/Athlon64 processors. Support for K10 and newer processors is now in acpi-cpufreq. diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 232f4915223b..d6176ce50b45 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -84,7 +84,7 @@ struct mm_struct efi_mm = { .mmlist = LIST_HEAD_INIT(efi_mm.mmlist), }; -static bool disable_runtime; +static bool disable_runtime = IS_ENABLED(CONFIG_PREEMPT_RT_BASE); static int __init setup_noefi(char *arg) { disable_runtime = true; @@ -110,6 +110,9 @@ static int __init parse_efi_cmdline(char *str) if (parse_option_str(str, "noruntime")) disable_runtime = true; + if (parse_option_str(str, "runtime")) + disable_runtime = false; + return 0; } early_param("efi", parse_efi_cmdline); diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index c16cb025755e..f24b82a4d403 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -1009,6 +1009,7 @@ static bool i915_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe, spin_lock_irqsave(&dev_priv->uncore.lock, irqflags); /* preempt_disable_rt() should go right here in PREEMPT_RT patchset. */ + preempt_disable_rt(); /* Get optional system timestamp before query. */ if (stime) @@ -1060,6 +1061,7 @@ static bool i915_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe, *etime = ktime_get(); /* preempt_enable_rt() should go right here in PREEMPT_RT patchset. */ + preempt_enable_rt(); spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c index ee23613f9fd4..263b671bb16a 100644 --- a/drivers/gpu/drm/i915/intel_sprite.c +++ b/drivers/gpu/drm/i915/intel_sprite.c @@ -36,6 +36,7 @@ #include <drm/drm_rect.h> #include <drm/drm_atomic.h> #include <drm/drm_plane_helper.h> +#include <linux/locallock.h> #include "intel_drv.h" #include "intel_frontbuffer.h" #include <drm/i915_drm.h> @@ -74,6 +75,8 @@ int intel_usecs_to_scanlines(const struct drm_display_mode *adjusted_mode, #define VBLANK_EVASION_TIME_US 100 #endif +static DEFINE_LOCAL_IRQ_LOCK(pipe_update_lock); + /** * intel_pipe_update_start() - start update of a set of display registers * @new_crtc_state: the new crtc state @@ -107,7 +110,7 @@ void intel_pipe_update_start(const struct intel_crtc_state *new_crtc_state) VBLANK_EVASION_TIME_US); max = vblank_start - 1; - local_irq_disable(); + local_lock_irq(pipe_update_lock); if (min <= 0 || max <= 0) return; @@ -137,11 +140,11 @@ void intel_pipe_update_start(const struct intel_crtc_state *new_crtc_state) break; } - local_irq_enable(); + local_unlock_irq(pipe_update_lock); timeout = schedule_timeout(timeout); - local_irq_disable(); + local_lock_irq(pipe_update_lock); } finish_wait(wq, &wait); @@ -206,7 +209,7 @@ void intel_pipe_update_end(struct intel_crtc_state *new_crtc_state) new_crtc_state->base.event = NULL; } - local_irq_enable(); + local_unlock_irq(pipe_update_lock); if (intel_vgpu_active(dev_priv)) return; diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c index d8e2d7b3b836..072b831aaf4f 100644 --- a/drivers/gpu/drm/radeon/radeon_display.c +++ b/drivers/gpu/drm/radeon/radeon_display.c @@ -1813,6 +1813,7 @@ int radeon_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe, struct radeon_device *rdev = dev->dev_private; /* preempt_disable_rt() should go right here in PREEMPT_RT patchset. */ + preempt_disable_rt(); /* Get optional system timestamp before query. */ if (stime) @@ -1905,6 +1906,7 @@ int radeon_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe, *etime = ktime_get(); /* preempt_enable_rt() should go right here in PREEMPT_RT patchset. */ + preempt_enable_rt(); /* Decode into vertical and horizontal scanout position. */ *vpos = position & 0x1fff; diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c index 0d2b97883e63..426c03d83b42 100644 --- a/drivers/hv/hv.c +++ b/drivers/hv/hv.c @@ -112,10 +112,12 @@ int hv_post_message(union hv_connection_id connection_id, static void hv_stimer0_isr(void) { struct hv_per_cpu_context *hv_cpu; + struct pt_regs *regs = get_irq_regs(); + u64 ip = regs ? instruction_pointer(regs) : 0; hv_cpu = this_cpu_ptr(hv_context.cpu_context); hv_cpu->clk_evt->event_handler(hv_cpu->clk_evt); - add_interrupt_randomness(stimer0_vector, 0); + add_interrupt_randomness(stimer0_vector, 0, ip); } static int hv_ce_set_next_event(unsigned long delta, diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h index 87d3d7da78f8..1d2d8a4b837d 100644 --- a/drivers/hv/hyperv_vmbus.h +++ b/drivers/hv/hyperv_vmbus.h @@ -31,6 +31,7 @@ #include <linux/atomic.h> #include <linux/hyperv.h> #include <linux/interrupt.h> +#include <linux/irq.h> #include "hv_trace.h" diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 5675f1beb1c6..034a2b8c6a8d 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -992,6 +992,8 @@ static void vmbus_isr(void) void *page_addr = hv_cpu->synic_event_page; struct hv_message *msg; union hv_synic_event_flags *event; + struct pt_regs *regs = get_irq_regs(); + u64 ip = regs ? instruction_pointer(regs) : 0; bool handled = false; if (unlikely(page_addr == NULL)) @@ -1035,7 +1037,7 @@ static void vmbus_isr(void) tasklet_schedule(&hv_cpu->msg_dpc); } - add_interrupt_randomness(HYPERVISOR_CALLBACK_VECTOR, 0); + add_interrupt_randomness(HYPERVISOR_CALLBACK_VECTOR, 0, ip); } diff --git a/drivers/infiniband/hw/hfi1/affinity.c b/drivers/infiniband/hw/hfi1/affinity.c index bedd5fba33b0..3f4259f11a35 100644 --- a/drivers/infiniband/hw/hfi1/affinity.c +++ b/drivers/infiniband/hw/hfi1/affinity.c @@ -1037,7 +1037,7 @@ int hfi1_get_proc_affinity(int node) struct hfi1_affinity_node *entry; cpumask_var_t diff, hw_thread_mask, available_mask, intrs_mask; const struct cpumask *node_mask, - *proc_mask = ¤t->cpus_allowed; + *proc_mask = current->cpus_ptr; struct hfi1_affinity_node_list *affinity = &node_affinity; struct cpu_mask_set *set = &affinity->proc; @@ -1045,7 +1045,7 @@ int hfi1_get_proc_affinity(int node) * check whether process/context affinity has already * been set */ - if (cpumask_weight(proc_mask) == 1) { + if (current->nr_cpus_allowed == 1) { hfi1_cdbg(PROC, "PID %u %s affinity set to CPU %*pbl", current->pid, current->comm, cpumask_pr_args(proc_mask)); @@ -1056,7 +1056,7 @@ int hfi1_get_proc_affinity(int node) cpu = cpumask_first(proc_mask); cpumask_set_cpu(cpu, &set->used); goto done; - } else if (cpumask_weight(proc_mask) < cpumask_weight(&set->mask)) { + } else if (current->nr_cpus_allowed < cpumask_weight(&set->mask)) { hfi1_cdbg(PROC, "PID %u %s affinity set to CPU set(s) %*pbl", current->pid, current->comm, cpumask_pr_args(proc_mask)); diff --git a/drivers/infiniband/hw/hfi1/sdma.c b/drivers/infiniband/hw/hfi1/sdma.c index 7fb350b87b49..85fe1a0c22c7 100644 --- a/drivers/infiniband/hw/hfi1/sdma.c +++ b/drivers/infiniband/hw/hfi1/sdma.c @@ -855,14 +855,13 @@ struct sdma_engine *sdma_select_user_engine(struct hfi1_devdata *dd, { struct sdma_rht_node *rht_node; struct sdma_engine *sde = NULL; - const struct cpumask *current_mask = ¤t->cpus_allowed; unsigned long cpu_id; /* * To ensure that always the same sdma engine(s) will be * selected make sure the process is pinned to this CPU only. */ - if (cpumask_weight(current_mask) != 1) + if (current->nr_cpus_allowed != 1) goto out; cpu_id = smp_processor_id(); diff --git a/drivers/infiniband/hw/qib/qib_file_ops.c b/drivers/infiniband/hw/qib/qib_file_ops.c index 98e1ce14fa2a..5d3828625017 100644 --- a/drivers/infiniband/hw/qib/qib_file_ops.c +++ b/drivers/infiniband/hw/qib/qib_file_ops.c @@ -1142,7 +1142,7 @@ static __poll_t qib_poll(struct file *fp, struct poll_table_struct *pt) static void assign_ctxt_affinity(struct file *fp, struct qib_devdata *dd) { struct qib_filedata *fd = fp->private_data; - const unsigned int weight = cpumask_weight(¤t->cpus_allowed); + const unsigned int weight = current->nr_cpus_allowed; const struct cpumask *local_mask = cpumask_of_pcibus(dd->pcidev->bus); int local_cpu; @@ -1623,9 +1623,8 @@ static int qib_assign_ctxt(struct file *fp, const struct qib_user_info *uinfo) ret = find_free_ctxt(i_minor - 1, fp, uinfo); else { int unit; - const unsigned int cpu = cpumask_first(¤t->cpus_allowed); - const unsigned int weight = - cpumask_weight(¤t->cpus_allowed); + const unsigned int cpu = cpumask_first(current->cpus_ptr); + const unsigned int weight = current->nr_cpus_allowed; if (weight == 1 && !test_bit(cpu, qib_cpulist)) if (!find_hca(cpu, &unit) && unit >= 0) diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 5e859102de22..772efb129659 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -1964,12 +1964,6 @@ static int __attach_device(struct iommu_dev_data *dev_data, { int ret; - /* - * Must be called with IRQs disabled. Warn here to detect early - * when its not. - */ - WARN_ON(!irqs_disabled()); - /* lock domain */ spin_lock(&domain->lock); @@ -2135,12 +2129,6 @@ static void __detach_device(struct iommu_dev_data *dev_data) { struct protection_domain *domain; - /* - * Must be called with IRQs disabled. Warn here to detect early - * when its not. - */ - WARN_ON(!irqs_disabled()); - domain = dev_data->domain; spin_lock(&domain->lock); diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 1784edcdd5bb..f8849eb99728 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -166,7 +166,7 @@ static struct { } vpe_proxy; static LIST_HEAD(its_nodes); -static DEFINE_SPINLOCK(its_lock); +static DEFINE_RAW_SPINLOCK(its_lock); static struct rdists *gic_rdists; static struct irq_domain *its_parent; @@ -177,6 +177,7 @@ static DEFINE_RAW_SPINLOCK(vmovp_lock); static DEFINE_IDA(its_vpeid_ida); #define gic_data_rdist() (raw_cpu_ptr(gic_rdists->rdist)) +#define gic_data_rdist_cpu(cpu) (per_cpu_ptr(gic_rdists->rdist, cpu)) #define gic_data_rdist_rd_base() (gic_data_rdist()->rd_base) #define gic_data_rdist_vlpi_base() (gic_data_rdist_rd_base() + SZ_128K) @@ -1561,7 +1562,7 @@ static void its_free_prop_table(struct page *prop_page) get_order(LPI_PROPBASE_SZ)); } -static int __init its_alloc_lpi_tables(void) +static int __init its_alloc_lpi_prop_table(void) { phys_addr_t paddr; @@ -1908,30 +1909,47 @@ static u64 its_clear_vpend_valid(void __iomem *vlpi_base) return val; } -static void its_cpu_init_lpis(void) +static int __init allocate_lpi_tables(void) { - void __iomem *rbase = gic_data_rdist_rd_base(); - struct page *pend_page; - u64 val, tmp; + int err, cpu; - /* If we didn't allocate the pending table yet, do it now */ - pend_page = gic_data_rdist()->pend_page; - if (!pend_page) { - phys_addr_t paddr; + err = its_alloc_lpi_prop_table(); + if (err) + return err; + + /* + * We allocate all the pending tables anyway, as we may have a + * mix of RDs that have had LPIs enabled, and some that + * don't. We'll free the unused ones as each CPU comes online. + */ + for_each_possible_cpu(cpu) { + struct page *pend_page; pend_page = its_allocate_pending_table(GFP_NOWAIT); if (!pend_page) { - pr_err("Failed to allocate PENDBASE for CPU%d\n", - smp_processor_id()); - return; + pr_err("Failed to allocate PENDBASE for CPU%d\n", cpu); + return -ENOMEM; } - paddr = page_to_phys(pend_page); - pr_info("CPU%d: using LPI pending table @%pa\n", - smp_processor_id(), &paddr); - gic_data_rdist()->pend_page = pend_page; + gic_data_rdist_cpu(cpu)->pend_page = pend_page; } + return 0; +} + +static void its_cpu_init_lpis(void) +{ + void __iomem *rbase = gic_data_rdist_rd_base(); + struct page *pend_page; + phys_addr_t paddr; + u64 val, tmp; + + if (gic_data_rdist()->lpi_enabled) + return; + + pend_page = gic_data_rdist()->pend_page; + paddr = page_to_phys(pend_page); + /* set PROPBASE */ val = (page_to_phys(gic_rdists->prop_page) | GICR_PROPBASER_InnerShareable | @@ -2007,6 +2025,10 @@ static void its_cpu_init_lpis(void) /* Make sure the GIC has seen the above */ dsb(sy); + gic_data_rdist()->lpi_enabled = true; + pr_info("GICv3: CPU%d: using LPI pending table @%pa\n", + smp_processor_id(), + &paddr); } static void its_cpu_init_collection(struct its_node *its) @@ -2052,12 +2074,12 @@ static void its_cpu_init_collections(void) { struct its_node *its; - spin_lock(&its_lock); + raw_spin_lock(&its_lock); list_for_each_entry(its, &its_nodes, entry) its_cpu_init_collection(its); - spin_unlock(&its_lock); + raw_spin_unlock(&its_lock); } static struct its_device *its_find_device(struct its_node *its, u32 dev_id) @@ -3126,7 +3148,7 @@ static int its_save_disable(void) struct its_node *its; int err = 0; - spin_lock(&its_lock); + raw_spin_lock(&its_lock); list_for_each_entry(its, &its_nodes, entry) { void __iomem *base; @@ -3158,7 +3180,7 @@ err: writel_relaxed(its->ctlr_save, base + GITS_CTLR); } } - spin_unlock(&its_lock); + raw_spin_unlock(&its_lock); return err; } @@ -3168,7 +3190,7 @@ static void its_restore_enable(void) struct its_node *its; int ret; - spin_lock(&its_lock); + raw_spin_lock(&its_lock); list_for_each_entry(its, &its_nodes, entry) { void __iomem *base; int i; @@ -3220,7 +3242,7 @@ static void its_restore_enable(void) GITS_TYPER_HCC(gic_read_typer(base + GITS_TYPER))) its_cpu_init_collection(its); } - spin_unlock(&its_lock); + raw_spin_unlock(&its_lock); } static struct syscore_ops its_syscore_ops = { @@ -3455,9 +3477,9 @@ static int __init its_probe_one(struct resource *res, if (err) goto out_free_tables; - spin_lock(&its_lock); + raw_spin_lock(&its_lock); list_add(&its->entry, &its_nodes); - spin_unlock(&its_lock); + raw_spin_unlock(&its_lock); return 0; @@ -3484,16 +3506,6 @@ static int redist_disable_lpis(void) u64 timeout = USEC_PER_SEC; u64 val; - /* - * If coming via a CPU hotplug event, we don't need to disable - * LPIs before trying to re-enable them. They are already - * configured and all is well in the world. Detect this case - * by checking the allocation of the pending table for the - * current CPU. - */ - if (gic_data_rdist()->pend_page) - return 0; - if (!gic_rdists_supports_plpis()) { pr_info("CPU%d: LPIs not supported\n", smp_processor_id()); return -ENXIO; @@ -3503,7 +3515,18 @@ static int redist_disable_lpis(void) if (!(val & GICR_CTLR_ENABLE_LPIS)) return 0; - pr_warn("CPU%d: Booted with LPIs enabled, memory probably corrupted\n", + /* + * If coming via a CPU hotplug event, we don't need to disable + * LPIs before trying to re-enable them. They are already + * configured and all is well in the world. + */ + if (gic_data_rdist()->lpi_enabled) + return 0; + + /* + * From that point on, we only try to do some damage control. + */ + pr_warn("GICv3: CPU%d: Booted with LPIs enabled, memory probably corrupted\n", smp_processor_id()); add_taint(TAINT_CRAP, LOCKDEP_STILL_OK); @@ -3759,7 +3782,8 @@ int __init its_init(struct fwnode_handle *handle, struct rdists *rdists, } gic_rdists = rdists; - err = its_alloc_lpi_tables(); + + err = allocate_lpi_tables(); if (err) return err; diff --git a/drivers/leds/trigger/Kconfig b/drivers/leds/trigger/Kconfig index a2559b4fdfff..c27053177433 100644 --- a/drivers/leds/trigger/Kconfig +++ b/drivers/leds/trigger/Kconfig @@ -69,7 +69,7 @@ config LEDS_TRIGGER_BACKLIGHT config LEDS_TRIGGER_CPU bool "LED CPU Trigger" - depends on LEDS_TRIGGERS + depends on LEDS_TRIGGERS && !PREEMPT_RT_BASE help This allows LEDs to be controlled by active CPUs. This shows the active CPUs across an array of LEDs so you can see which diff --git a/drivers/md/bcache/Kconfig b/drivers/md/bcache/Kconfig index 17bf109c58e9..dd66990f3515 100644 --- a/drivers/md/bcache/Kconfig +++ b/drivers/md/bcache/Kconfig @@ -1,6 +1,7 @@ config BCACHE tristate "Block device as cache" + depends on !PREEMPT_RT_FULL ---help--- Allows a block device to be used as cache for other devices; uses a btree for indexing and the layout is optimized for SSDs. diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c index 6e547b8dd298..29736c7e5f1f 100644 --- a/drivers/md/dm-rq.c +++ b/drivers/md/dm-rq.c @@ -688,7 +688,6 @@ static void dm_old_request_fn(struct request_queue *q) /* Establish tio->ti before queuing work (map_tio_request) */ tio->ti = ti; kthread_queue_work(&md->kworker, &tio->work); - BUG_ON(!irqs_disabled()); } } diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index e3da8a13d643..9b840a4bf527 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -409,16 +409,14 @@ void raid5_release_stripe(struct stripe_head *sh) md_wakeup_thread(conf->mddev->thread); return; slow_path: - local_irq_save(flags); /* we are ok here if STRIPE_ON_RELEASE_LIST is set or not */ - if (atomic_dec_and_lock(&sh->count, &conf->device_lock)) { + if (atomic_dec_and_lock_irqsave(&sh->count, &conf->device_lock, flags)) { INIT_LIST_HEAD(&list); hash = sh->hash_lock_index; do_release_stripe(conf, sh, &list); - spin_unlock(&conf->device_lock); + spin_unlock_irqrestore(&conf->device_lock, flags); release_inactive_stripe_list(conf, &list, hash); } - local_irq_restore(flags); } static inline void remove_hash(struct stripe_head *sh) @@ -2071,8 +2069,9 @@ static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request) struct raid5_percpu *percpu; unsigned long cpu; - cpu = get_cpu(); + cpu = get_cpu_light(); percpu = per_cpu_ptr(conf->percpu, cpu); + spin_lock(&percpu->lock); if (test_bit(STRIPE_OP_BIOFILL, &ops_request)) { ops_run_biofill(sh); overlap_clear++; @@ -2131,7 +2130,8 @@ static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request) if (test_and_clear_bit(R5_Overlap, &dev->flags)) wake_up(&sh->raid_conf->wait_for_overlap); } - put_cpu(); + spin_unlock(&percpu->lock); + put_cpu_light(); } static void free_stripe(struct kmem_cache *sc, struct stripe_head *sh) @@ -6813,6 +6813,7 @@ static int raid456_cpu_up_prepare(unsigned int cpu, struct hlist_node *node) __func__, cpu); return -ENOMEM; } + spin_lock_init(&per_cpu_ptr(conf->percpu, cpu)->lock); return 0; } @@ -6823,7 +6824,6 @@ static int raid5_alloc_percpu(struct r5conf *conf) conf->percpu = alloc_percpu(struct raid5_percpu); if (!conf->percpu) return -ENOMEM; - err = cpuhp_state_add_instance(CPUHP_MD_RAID5_PREPARE, &conf->node); if (!err) { conf->scribble_disks = max(conf->raid_disks, diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h index 8474c224127b..a3bf907ab2af 100644 --- a/drivers/md/raid5.h +++ b/drivers/md/raid5.h @@ -637,6 +637,7 @@ struct r5conf { int recovery_disabled; /* per cpu variables */ struct raid5_percpu { + spinlock_t lock; /* Protection for -RT */ struct page *spare_page; /* Used when checking P/Q in raid6 */ struct flex_array *scribble; /* space for constructing buffer * lists and performing address diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig index 3726eacdf65d..0900dec7ec04 100644 --- a/drivers/misc/Kconfig +++ b/drivers/misc/Kconfig @@ -69,8 +69,7 @@ config ATMEL_TCB_CLKSRC are combined to make a single 32-bit timer. When GENERIC_CLOCKEVENTS is defined, the third timer channel - may be used as a clock event device supporting oneshot mode - (delays of up to two seconds) based on the 32 KiHz clock. + may be used as a clock event device supporting oneshot mode. config ATMEL_TCB_CLKSRC_BLOCK int @@ -83,6 +82,15 @@ config ATMEL_TCB_CLKSRC_BLOCK TC can be used for other purposes, such as PWM generation and interval timing. +config ATMEL_TCB_CLKSRC_USE_SLOW_CLOCK + bool "TC Block use 32 KiHz clock" + depends on ATMEL_TCB_CLKSRC + default y + help + Select this to use 32 KiHz base clock rate as TC block clock + source for clock events. + + config DUMMY_IRQ tristate "Dummy IRQ handler" default n diff --git a/drivers/net/wireless/intersil/orinoco/orinoco_usb.c b/drivers/net/wireless/intersil/orinoco/orinoco_usb.c index 94ad6fe29e69..5d2361e1873c 100644 --- a/drivers/net/wireless/intersil/orinoco/orinoco_usb.c +++ b/drivers/net/wireless/intersil/orinoco/orinoco_usb.c @@ -697,7 +697,7 @@ static void ezusb_req_ctx_wait(struct ezusb_priv *upriv, while (!ctx->done.done && msecs--) udelay(1000); } else { - wait_event_interruptible(ctx->done.wait, + swait_event_interruptible(ctx->done.wait, ctx->done.done); } break; diff --git a/drivers/of/base.c b/drivers/of/base.c index 682c15e08035..4a33ef482bcc 100644 --- a/drivers/of/base.c +++ b/drivers/of/base.c @@ -106,31 +106,34 @@ static u32 phandle_cache_mask; /* * Caller must hold devtree_lock. */ -static void __of_free_phandle_cache(void) +static struct device_node** __of_free_phandle_cache(void) { u32 cache_entries = phandle_cache_mask + 1; u32 k; + struct device_node **shadow; if (!phandle_cache) - return; + return NULL; for (k = 0; k < cache_entries; k++) of_node_put(phandle_cache[k]); - kfree(phandle_cache); + shadow = phandle_cache; phandle_cache = NULL; + return shadow; } int of_free_phandle_cache(void) { unsigned long flags; + struct device_node **shadow; raw_spin_lock_irqsave(&devtree_lock, flags); - __of_free_phandle_cache(); + shadow = __of_free_phandle_cache(); raw_spin_unlock_irqrestore(&devtree_lock, flags); - + kfree(shadow); return 0; } #if !defined(CONFIG_MODULES) @@ -165,10 +168,11 @@ void of_populate_phandle_cache(void) u32 cache_entries; struct device_node *np; u32 phandles = 0; + struct device_node **shadow; raw_spin_lock_irqsave(&devtree_lock, flags); - __of_free_phandle_cache(); + shadow = __of_free_phandle_cache(); for_each_of_allnodes(np) if (np->phandle && np->phandle != OF_PHANDLE_ILLEGAL) @@ -176,12 +180,14 @@ void of_populate_phandle_cache(void) if (!phandles) goto out; + raw_spin_unlock_irqrestore(&devtree_lock, flags); cache_entries = roundup_pow_of_two(phandles); phandle_cache_mask = cache_entries - 1; phandle_cache = kcalloc(cache_entries, sizeof(*phandle_cache), GFP_ATOMIC); + raw_spin_lock_irqsave(&devtree_lock, flags); if (!phandle_cache) goto out; @@ -193,6 +199,7 @@ void of_populate_phandle_cache(void) out: raw_spin_unlock_irqrestore(&devtree_lock, flags); + kfree(shadow); } void __init of_core_init(void) diff --git a/drivers/pci/switch/switchtec.c b/drivers/pci/switch/switchtec.c index 20340ad5bbe7..4d9affabeaf2 100644 --- a/drivers/pci/switch/switchtec.c +++ b/drivers/pci/switch/switchtec.c @@ -43,10 +43,11 @@ struct switchtec_user { enum mrpc_state state; - struct completion comp; + wait_queue_head_t cmd_comp; struct kref kref; struct list_head list; + bool cmd_done; u32 cmd; u32 status; u32 return_code; @@ -68,7 +69,7 @@ static struct switchtec_user *stuser_create(struct switchtec_dev *stdev) stuser->stdev = stdev; kref_init(&stuser->kref); INIT_LIST_HEAD(&stuser->list); - init_completion(&stuser->comp); + init_waitqueue_head(&stuser->cmd_comp); stuser->event_cnt = atomic_read(&stdev->event_cnt); dev_dbg(&stdev->dev, "%s: %p\n", __func__, stuser); @@ -151,7 +152,7 @@ static int mrpc_queue_cmd(struct switchtec_user *stuser) kref_get(&stuser->kref); stuser->read_len = sizeof(stuser->data); stuser_set_state(stuser, MRPC_QUEUED); - init_completion(&stuser->comp); + stuser->cmd_done = false; list_add_tail(&stuser->list, &stdev->mrpc_queue); mrpc_cmd_submit(stdev); @@ -188,7 +189,8 @@ static void mrpc_complete_cmd(struct switchtec_dev *stdev) stuser->read_len); out: - complete_all(&stuser->comp); + stuser->cmd_done = true; + wake_up_interruptible(&stuser->cmd_comp); list_del_init(&stuser->list); stuser_put(stuser); stdev->mrpc_busy = 0; @@ -458,10 +460,11 @@ static ssize_t switchtec_dev_read(struct file *filp, char __user *data, mutex_unlock(&stdev->mrpc_mutex); if (filp->f_flags & O_NONBLOCK) { - if (!try_wait_for_completion(&stuser->comp)) + if (!READ_ONCE(stuser->cmd_done)) return -EAGAIN; } else { - rc = wait_for_completion_interruptible(&stuser->comp); + rc = wait_event_interruptible(stuser->cmd_comp, + stuser->cmd_done); if (rc < 0) return rc; } @@ -509,7 +512,7 @@ static __poll_t switchtec_dev_poll(struct file *filp, poll_table *wait) struct switchtec_dev *stdev = stuser->stdev; __poll_t ret = 0; - poll_wait(filp, &stuser->comp.wait, wait); + poll_wait(filp, &stuser->cmd_comp, wait); poll_wait(filp, &stdev->event_wq, wait); if (lock_mutex_and_test_alive(stdev)) @@ -517,7 +520,7 @@ static __poll_t switchtec_dev_poll(struct file *filp, poll_table *wait) mutex_unlock(&stdev->mrpc_mutex); - if (try_wait_for_completion(&stuser->comp)) + if (READ_ONCE(stuser->cmd_done)) ret |= EPOLLIN | EPOLLRDNORM; if (stuser->event_cnt != atomic_read(&stdev->event_cnt)) @@ -1041,7 +1044,8 @@ static void stdev_kill(struct switchtec_dev *stdev) /* Wake up and kill any users waiting on an MRPC request */ list_for_each_entry_safe(stuser, tmpuser, &stdev->mrpc_queue, list) { - complete_all(&stuser->comp); + stuser->cmd_done = true; + wake_up_interruptible(&stuser->cmd_comp); list_del_init(&stuser->list); stuser_put(stuser); } diff --git a/drivers/scsi/fcoe/fcoe.c b/drivers/scsi/fcoe/fcoe.c index 6768b2e8148a..c20f51af6bdf 100644 --- a/drivers/scsi/fcoe/fcoe.c +++ b/drivers/scsi/fcoe/fcoe.c @@ -1459,11 +1459,11 @@ err2: static int fcoe_alloc_paged_crc_eof(struct sk_buff *skb, int tlen) { struct fcoe_percpu_s *fps; - int rc; + int rc, cpu = get_cpu_light(); - fps = &get_cpu_var(fcoe_percpu); + fps = &per_cpu(fcoe_percpu, cpu); rc = fcoe_get_paged_crc_eof(skb, tlen, fps); - put_cpu_var(fcoe_percpu); + put_cpu_light(); return rc; } @@ -1650,11 +1650,11 @@ static inline int fcoe_filter_frames(struct fc_lport *lport, return 0; } - stats = per_cpu_ptr(lport->stats, get_cpu()); + stats = per_cpu_ptr(lport->stats, get_cpu_light()); stats->InvalidCRCCount++; if (stats->InvalidCRCCount < 5) printk(KERN_WARNING "fcoe: dropping frame with CRC error\n"); - put_cpu(); + put_cpu_light(); return -EINVAL; } @@ -1697,7 +1697,7 @@ static void fcoe_recv_frame(struct sk_buff *skb) */ hp = (struct fcoe_hdr *) skb_network_header(skb); - stats = per_cpu_ptr(lport->stats, get_cpu()); + stats = per_cpu_ptr(lport->stats, get_cpu_light()); if (unlikely(FC_FCOE_DECAPS_VER(hp) != FC_FCOE_VER)) { if (stats->ErrorFrames < 5) printk(KERN_WARNING "fcoe: FCoE version " @@ -1729,13 +1729,13 @@ static void fcoe_recv_frame(struct sk_buff *skb) goto drop; if (!fcoe_filter_frames(lport, fp)) { - put_cpu(); + put_cpu_light(); fc_exch_recv(lport, fp); return; } drop: stats->ErrorFrames++; - put_cpu(); + put_cpu_light(); kfree_skb(skb); } diff --git a/drivers/scsi/fcoe/fcoe_ctlr.c b/drivers/scsi/fcoe/fcoe_ctlr.c index 789a9eced52e..66c9396b7e0b 100644 --- a/drivers/scsi/fcoe/fcoe_ctlr.c +++ b/drivers/scsi/fcoe/fcoe_ctlr.c @@ -838,7 +838,7 @@ static unsigned long fcoe_ctlr_age_fcfs(struct fcoe_ctlr *fip) INIT_LIST_HEAD(&del_list); - stats = per_cpu_ptr(fip->lp->stats, get_cpu()); + stats = per_cpu_ptr(fip->lp->stats, get_cpu_light()); list_for_each_entry_safe(fcf, next, &fip->fcfs, list) { deadline = fcf->time + fcf->fka_period + fcf->fka_period / 2; @@ -874,7 +874,7 @@ static unsigned long fcoe_ctlr_age_fcfs(struct fcoe_ctlr *fip) sel_time = fcf->time; } } - put_cpu(); + put_cpu_light(); list_for_each_entry_safe(fcf, next, &del_list, list) { /* Removes fcf from current list */ diff --git a/drivers/scsi/libfc/fc_exch.c b/drivers/scsi/libfc/fc_exch.c index 42bcf7f3a0f9..2ce045d6860c 100644 --- a/drivers/scsi/libfc/fc_exch.c +++ b/drivers/scsi/libfc/fc_exch.c @@ -833,10 +833,10 @@ static struct fc_exch *fc_exch_em_alloc(struct fc_lport *lport, } memset(ep, 0, sizeof(*ep)); - cpu = get_cpu(); + cpu = get_cpu_light(); pool = per_cpu_ptr(mp->pool, cpu); spin_lock_bh(&pool->lock); - put_cpu(); + put_cpu_light(); /* peek cache of free slot */ if (pool->left != FC_XID_UNKNOWN) { diff --git a/drivers/scsi/libsas/sas_ata.c b/drivers/scsi/libsas/sas_ata.c index 41cdda7a926b..cbd1e1277845 100644 --- a/drivers/scsi/libsas/sas_ata.c +++ b/drivers/scsi/libsas/sas_ata.c @@ -176,7 +176,6 @@ qc_already_gone: static unsigned int sas_ata_qc_issue(struct ata_queued_cmd *qc) { - unsigned long flags; struct sas_task *task; struct scatterlist *sg; int ret = AC_ERR_SYSTEM; @@ -190,7 +189,6 @@ static unsigned int sas_ata_qc_issue(struct ata_queued_cmd *qc) /* TODO: audit callers to ensure they are ready for qc_issue to * unconditionally re-enable interrupts */ - local_irq_save(flags); spin_unlock(ap->lock); /* If the device fell off, no sense in issuing commands */ @@ -252,7 +250,6 @@ static unsigned int sas_ata_qc_issue(struct ata_queued_cmd *qc) out: spin_lock(ap->lock); - local_irq_restore(flags); return ret; } diff --git a/drivers/scsi/qla2xxx/qla_inline.h b/drivers/scsi/qla2xxx/qla_inline.h index 59fd5a9dfeb8..735f122607f3 100644 --- a/drivers/scsi/qla2xxx/qla_inline.h +++ b/drivers/scsi/qla2xxx/qla_inline.h @@ -58,14 +58,12 @@ qla2x00_debounce_register(volatile uint16_t __iomem *addr) static inline void qla2x00_poll(struct rsp_que *rsp) { - unsigned long flags; struct qla_hw_data *ha = rsp->hw; - local_irq_save(flags); + if (IS_P3P_TYPE(ha)) qla82xx_poll(0, rsp); else ha->isp_ops->intr_handler(0, rsp); - local_irq_restore(flags); } static inline uint8_t * diff --git a/drivers/staging/android/vsoc.c b/drivers/staging/android/vsoc.c index 806beda1040b..6c7f666c0e33 100644 --- a/drivers/staging/android/vsoc.c +++ b/drivers/staging/android/vsoc.c @@ -438,12 +438,10 @@ static int handle_vsoc_cond_wait(struct file *filp, struct vsoc_cond_wait *arg) if (!timespec_valid(&ts)) return -EINVAL; - hrtimer_init_on_stack(&to->timer, CLOCK_MONOTONIC, - HRTIMER_MODE_ABS); + hrtimer_init_sleeper_on_stack(to, CLOCK_MONOTONIC, + HRTIMER_MODE_ABS, current); hrtimer_set_expires_range_ns(&to->timer, timespec_to_ktime(ts), current->timer_slack_ns); - - hrtimer_init_sleeper(to, current); } while (1) { diff --git a/drivers/thermal/x86_pkg_temp_thermal.c b/drivers/thermal/x86_pkg_temp_thermal.c index 1ef937d799e4..a5991cbb408f 100644 --- a/drivers/thermal/x86_pkg_temp_thermal.c +++ b/drivers/thermal/x86_pkg_temp_thermal.c @@ -29,6 +29,7 @@ #include <linux/pm.h> #include <linux/thermal.h> #include <linux/debugfs.h> +#include <linux/swork.h> #include <asm/cpu_device_id.h> #include <asm/mce.h> @@ -329,7 +330,7 @@ static void pkg_thermal_schedule_work(int cpu, struct delayed_work *work) schedule_delayed_work_on(cpu, work, ms); } -static int pkg_thermal_notify(u64 msr_val) +static void pkg_thermal_notify_work(struct swork_event *event) { int cpu = smp_processor_id(); struct pkg_device *pkgdev; @@ -348,9 +349,47 @@ static int pkg_thermal_notify(u64 msr_val) } spin_unlock_irqrestore(&pkg_temp_lock, flags); +} + +#ifdef CONFIG_PREEMPT_RT_FULL +static struct swork_event notify_work; + +static int pkg_thermal_notify_work_init(void) +{ + int err; + + err = swork_get(); + if (err) + return err; + + INIT_SWORK(¬ify_work, pkg_thermal_notify_work); return 0; } +static void pkg_thermal_notify_work_cleanup(void) +{ + swork_put(); +} + +static int pkg_thermal_notify(u64 msr_val) +{ + swork_queue(¬ify_work); + return 0; +} + +#else /* !CONFIG_PREEMPT_RT_FULL */ + +static int pkg_thermal_notify_work_init(void) { return 0; } + +static void pkg_thermal_notify_work_cleanup(void) { } + +static int pkg_thermal_notify(u64 msr_val) +{ + pkg_thermal_notify_work(NULL); + return 0; +} +#endif /* CONFIG_PREEMPT_RT_FULL */ + static int pkg_temp_thermal_device_add(unsigned int cpu) { int pkgid = topology_logical_package_id(cpu); @@ -515,11 +554,16 @@ static int __init pkg_temp_thermal_init(void) if (!x86_match_cpu(pkg_temp_thermal_ids)) return -ENODEV; + if (!pkg_thermal_notify_work_init()) + return -ENODEV; + max_packages = topology_max_packages(); packages = kcalloc(max_packages, sizeof(struct pkg_device *), GFP_KERNEL); - if (!packages) - return -ENOMEM; + if (!packages) { + ret = -ENOMEM; + goto err; + } ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "thermal/x86_pkg:online", pkg_thermal_cpu_online, pkg_thermal_cpu_offline); @@ -537,6 +581,7 @@ static int __init pkg_temp_thermal_init(void) return 0; err: + pkg_thermal_notify_work_cleanup(); kfree(packages); return ret; } @@ -550,6 +595,7 @@ static void __exit pkg_temp_thermal_exit(void) cpuhp_remove_state(pkg_thermal_hp_state); debugfs_remove_recursive(debugfs); kfree(packages); + pkg_thermal_notify_work_cleanup(); } module_exit(pkg_temp_thermal_exit) diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c index 9342fc2ee7df..03cec859a9f1 100644 --- a/drivers/tty/serial/8250/8250_core.c +++ b/drivers/tty/serial/8250/8250_core.c @@ -54,7 +54,16 @@ static struct uart_driver serial8250_reg; static unsigned int skip_txen_test; /* force skip of txen test at init time */ -#define PASS_LIMIT 512 +/* + * On -rt we can have a more delays, and legitimately + * so - so don't drop work spuriously and spam the + * syslog: + */ +#ifdef CONFIG_PREEMPT_RT_FULL +# define PASS_LIMIT 1000000 +#else +# define PASS_LIMIT 512 +#endif #include <asm/serial.h> /* diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index 5cbc13e3d316..7cab171b45a9 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -31,6 +31,7 @@ #include <linux/nmi.h> #include <linux/mutex.h> #include <linux/slab.h> +#include <linux/kdb.h> #include <linux/uaccess.h> #include <linux/pm_runtime.h> #include <linux/ktime.h> @@ -3221,9 +3222,9 @@ void serial8250_console_write(struct uart_8250_port *up, const char *s, serial8250_rpm_get(up); - if (port->sysrq) + if (port->sysrq || oops_in_progress) locked = 0; - else if (oops_in_progress) + else if (in_kdb_printk()) locked = spin_trylock_irqsave(&port->lock, flags); else spin_lock_irqsave(&port->lock, flags); diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c index 89ade213a1a9..59b4ab7b50bf 100644 --- a/drivers/tty/serial/amba-pl011.c +++ b/drivers/tty/serial/amba-pl011.c @@ -2211,18 +2211,24 @@ pl011_console_write(struct console *co, const char *s, unsigned int count) { struct uart_amba_port *uap = amba_ports[co->index]; unsigned int old_cr = 0, new_cr; - unsigned long flags; + unsigned long flags = 0; int locked = 1; clk_enable(uap->clk); - local_irq_save(flags); + /* + * local_irq_save(flags); + * + * This local_irq_save() is nonsense. If we come in via sysrq + * handling then interrupts are already disabled. Aside of + * that the port.sysrq check is racy on SMP regardless. + */ if (uap->port.sysrq) locked = 0; else if (oops_in_progress) - locked = spin_trylock(&uap->port.lock); + locked = spin_trylock_irqsave(&uap->port.lock, flags); else - spin_lock(&uap->port.lock); + spin_lock_irqsave(&uap->port.lock, flags); /* * First save the CR then disable the interrupts @@ -2248,8 +2254,7 @@ pl011_console_write(struct console *co, const char *s, unsigned int count) pl011_write(old_cr, uap, REG_CR); if (locked) - spin_unlock(&uap->port.lock); - local_irq_restore(flags); + spin_unlock_irqrestore(&uap->port.lock, flags); clk_disable(uap->clk); } diff --git a/drivers/tty/serial/omap-serial.c b/drivers/tty/serial/omap-serial.c index 6420ae581a80..0f4f41ed9ffa 100644 --- a/drivers/tty/serial/omap-serial.c +++ b/drivers/tty/serial/omap-serial.c @@ -1307,13 +1307,10 @@ serial_omap_console_write(struct console *co, const char *s, pm_runtime_get_sync(up->dev); - local_irq_save(flags); - if (up->port.sysrq) - locked = 0; - else if (oops_in_progress) - locked = spin_trylock(&up->port.lock); + if (up->port.sysrq || oops_in_progress) + locked = spin_trylock_irqsave(&up->port.lock, flags); else - spin_lock(&up->port.lock); + spin_lock_irqsave(&up->port.lock, flags); /* * First save the IER then disable the interrupts @@ -1342,8 +1339,7 @@ serial_omap_console_write(struct console *co, const char *s, pm_runtime_mark_last_busy(up->dev); pm_runtime_put_autosuspend(up->dev); if (locked) - spin_unlock(&up->port.lock); - local_irq_restore(flags); + spin_unlock_irqrestore(&up->port.lock, flags); } static int __init diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c index b82a7d787add..2f3015356124 100644 --- a/drivers/usb/core/hcd.c +++ b/drivers/usb/core/hcd.c @@ -1738,7 +1738,6 @@ static void __usb_hcd_giveback_urb(struct urb *urb) struct usb_hcd *hcd = bus_to_hcd(urb->dev->bus); struct usb_anchor *anchor = urb->anchor; int status = urb->unlinked; - unsigned long flags; urb->hcpriv = NULL; if (unlikely((urb->transfer_flags & URB_SHORT_NOT_OK) && @@ -1766,9 +1765,7 @@ static void __usb_hcd_giveback_urb(struct urb *urb) * and no one may trigger the above deadlock situation when * running complete() in tasklet. */ - local_irq_save(flags); urb->complete(urb); - local_irq_restore(flags); usb_anchor_resume_wakeups(anchor); atomic_dec(&urb->use_count); diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index aa15593a3ac4..5e9269cd14fa 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -1624,7 +1624,7 @@ static void ffs_data_put(struct ffs_data *ffs) pr_info("%s(): freeing\n", __func__); ffs_data_clear(ffs); BUG_ON(waitqueue_active(&ffs->ev.waitq) || - waitqueue_active(&ffs->ep0req_completion.wait) || + swait_active(&ffs->ep0req_completion.wait) || waitqueue_active(&ffs->wait)); destroy_workqueue(ffs->io_completion_wq); kfree(ffs->dev_name); diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c index 37ca0e669bd8..17cd1d5f2180 100644 --- a/drivers/usb/gadget/legacy/inode.c +++ b/drivers/usb/gadget/legacy/inode.c @@ -343,7 +343,7 @@ ep_io (struct ep_data *epdata, void *buf, unsigned len) spin_unlock_irq (&epdata->dev->lock); if (likely (value == 0)) { - value = wait_event_interruptible (done.wait, done.done); + value = swait_event_interruptible (done.wait, done.done); if (value != 0) { spin_lock_irq (&epdata->dev->lock); if (likely (epdata->ep != NULL)) { @@ -352,7 +352,7 @@ ep_io (struct ep_data *epdata, void *buf, unsigned len) usb_ep_dequeue (epdata->ep, epdata->req); spin_unlock_irq (&epdata->dev->lock); - wait_event (done.wait, done.done); + swait_event (done.wait, done.done); if (epdata->status == -ECONNRESET) epdata->status = -EINTR; } else { diff --git a/drivers/watchdog/watchdog_dev.c b/drivers/watchdog/watchdog_dev.c index ffbdc4642ea5..84f75b5045f6 100644 --- a/drivers/watchdog/watchdog_dev.c +++ b/drivers/watchdog/watchdog_dev.c @@ -147,7 +147,7 @@ static inline void watchdog_update_worker(struct watchdog_device *wdd) ktime_t t = watchdog_next_keepalive(wdd); if (t > 0) - hrtimer_start(&wd_data->timer, t, HRTIMER_MODE_REL); + hrtimer_start(&wd_data->timer, t, HRTIMER_MODE_REL_HARD); } else { hrtimer_cancel(&wd_data->timer); } @@ -166,7 +166,7 @@ static int __watchdog_ping(struct watchdog_device *wdd) if (ktime_after(earliest_keepalive, now)) { hrtimer_start(&wd_data->timer, ktime_sub(earliest_keepalive, now), - HRTIMER_MODE_REL); + HRTIMER_MODE_REL_HARD); return 0; } @@ -945,7 +945,7 @@ static int watchdog_cdev_register(struct watchdog_device *wdd, dev_t devno) return -ENODEV; kthread_init_work(&wd_data->work, watchdog_ping_work); - hrtimer_init(&wd_data->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + hrtimer_init(&wd_data->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD); wd_data->timer.function = watchdog_timer_expired; if (wdd->id == 0) { @@ -992,7 +992,7 @@ static int watchdog_cdev_register(struct watchdog_device *wdd, dev_t devno) __module_get(wdd->ops->owner); kref_get(&wd_data->kref); if (handle_boot_enabled) - hrtimer_start(&wd_data->timer, 0, HRTIMER_MODE_REL); + hrtimer_start(&wd_data->timer, 0, HRTIMER_MODE_REL_HARD); else pr_info("watchdog%d running and kernel based pre-userspace handler disabled\n", wdd->id); @@ -40,6 +40,7 @@ #include <linux/ramfs.h> #include <linux/percpu-refcount.h> #include <linux/mount.h> +#include <linux/swork.h> #include <asm/kmap_types.h> #include <linux/uaccess.h> @@ -119,6 +120,7 @@ struct kioctx { long nr_pages; struct rcu_work free_rwork; /* see free_ioctx() */ + struct swork_event free_swork; /* see free_ioctx() */ /* * signals when all in-flight requests are done @@ -257,6 +259,7 @@ static int __init aio_setup(void) .mount = aio_mount, .kill_sb = kill_anon_super, }; + BUG_ON(swork_get()); aio_mnt = kern_mount(&aio_fs); if (IS_ERR(aio_mnt)) panic("Failed to create aio fs mount."); @@ -598,9 +601,9 @@ static void free_ioctx_reqs(struct percpu_ref *ref) * and ctx->users has dropped to 0, so we know no more kiocbs can be submitted - * now it's safe to cancel any that need to be. */ -static void free_ioctx_users(struct percpu_ref *ref) +static void free_ioctx_users_work(struct swork_event *sev) { - struct kioctx *ctx = container_of(ref, struct kioctx, users); + struct kioctx *ctx = container_of(sev, struct kioctx, free_swork); struct aio_kiocb *req; spin_lock_irq(&ctx->ctx_lock); @@ -618,6 +621,14 @@ static void free_ioctx_users(struct percpu_ref *ref) percpu_ref_put(&ctx->reqs); } +static void free_ioctx_users(struct percpu_ref *ref) +{ + struct kioctx *ctx = container_of(ref, struct kioctx, users); + + INIT_SWORK(&ctx->free_swork, free_ioctx_users_work); + swork_queue(&ctx->free_swork); +} + static int ioctx_add_table(struct kioctx *ctx, struct mm_struct *mm) { unsigned i, new_nr; diff --git a/fs/autofs/expire.c b/fs/autofs/expire.c index c5a95906a21e..b1ffe0efacb2 100644 --- a/fs/autofs/expire.c +++ b/fs/autofs/expire.c @@ -8,6 +8,7 @@ * option, any later version, incorporated herein by reference. */ +#include <linux/delay.h> #include "autofs_i.h" static unsigned long now; @@ -148,7 +149,7 @@ again: parent = p->d_parent; if (!spin_trylock(&parent->d_lock)) { spin_unlock(&p->d_lock); - cpu_relax(); + cpu_chill(); goto relock; } spin_unlock(&p->d_lock); diff --git a/fs/buffer.c b/fs/buffer.c index e527cb72661a..10ac2e256656 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -274,8 +274,7 @@ static void end_buffer_async_read(struct buffer_head *bh, int uptodate) * decide that the page is now completely done. */ first = page_buffers(page); - local_irq_save(flags); - bit_spin_lock(BH_Uptodate_Lock, &first->b_state); + flags = bh_uptodate_lock_irqsave(first); clear_buffer_async_read(bh); unlock_buffer(bh); tmp = bh; @@ -288,8 +287,7 @@ static void end_buffer_async_read(struct buffer_head *bh, int uptodate) } tmp = tmp->b_this_page; } while (tmp != bh); - bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); - local_irq_restore(flags); + bh_uptodate_unlock_irqrestore(first, flags); /* * If none of the buffers had errors and they are all @@ -301,9 +299,7 @@ static void end_buffer_async_read(struct buffer_head *bh, int uptodate) return; still_busy: - bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); - local_irq_restore(flags); - return; + bh_uptodate_unlock_irqrestore(first, flags); } /* @@ -330,8 +326,7 @@ void end_buffer_async_write(struct buffer_head *bh, int uptodate) } first = page_buffers(page); - local_irq_save(flags); - bit_spin_lock(BH_Uptodate_Lock, &first->b_state); + flags = bh_uptodate_lock_irqsave(first); clear_buffer_async_write(bh); unlock_buffer(bh); @@ -343,15 +338,12 @@ void end_buffer_async_write(struct buffer_head *bh, int uptodate) } tmp = tmp->b_this_page; } - bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); - local_irq_restore(flags); + bh_uptodate_unlock_irqrestore(first, flags); end_page_writeback(page); return; still_busy: - bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); - local_irq_restore(flags); - return; + bh_uptodate_unlock_irqrestore(first, flags); } EXPORT_SYMBOL(end_buffer_async_write); @@ -3357,6 +3349,7 @@ struct buffer_head *alloc_buffer_head(gfp_t gfp_flags) struct buffer_head *ret = kmem_cache_zalloc(bh_cachep, gfp_flags); if (ret) { INIT_LIST_HEAD(&ret->b_assoc_buffers); + buffer_head_init_locks(ret); preempt_disable(); __this_cpu_inc(bh_accounting.nr); recalc_bh_state(); diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index 3925a7bfc74d..33f7723fb83e 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -80,7 +80,7 @@ cifs_prime_dcache(struct dentry *parent, struct qstr *name, struct inode *inode; struct super_block *sb = parent->d_sb; struct cifs_sb_info *cifs_sb = CIFS_SB(sb); - DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); + DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq); cifs_dbg(FYI, "%s: for %s\n", __func__, name->name); diff --git a/fs/dcache.c b/fs/dcache.c index fbab0c053830..f494ffeb86b9 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -2432,9 +2432,10 @@ EXPORT_SYMBOL(d_rehash); static inline unsigned start_dir_add(struct inode *dir) { + preempt_disable_rt(); for (;;) { - unsigned n = dir->i_dir_seq; - if (!(n & 1) && cmpxchg(&dir->i_dir_seq, n, n + 1) == n) + unsigned n = dir->__i_dir_seq; + if (!(n & 1) && cmpxchg(&dir->__i_dir_seq, n, n + 1) == n) return n; cpu_relax(); } @@ -2442,26 +2443,30 @@ static inline unsigned start_dir_add(struct inode *dir) static inline void end_dir_add(struct inode *dir, unsigned n) { - smp_store_release(&dir->i_dir_seq, n + 2); + smp_store_release(&dir->__i_dir_seq, n + 2); + preempt_enable_rt(); } static void d_wait_lookup(struct dentry *dentry) { - if (d_in_lookup(dentry)) { - DECLARE_WAITQUEUE(wait, current); - add_wait_queue(dentry->d_wait, &wait); - do { - set_current_state(TASK_UNINTERRUPTIBLE); - spin_unlock(&dentry->d_lock); - schedule(); - spin_lock(&dentry->d_lock); - } while (d_in_lookup(dentry)); - } + struct swait_queue __wait; + + if (!d_in_lookup(dentry)) + return; + + INIT_LIST_HEAD(&__wait.task_list); + do { + prepare_to_swait(dentry->d_wait, &__wait, TASK_UNINTERRUPTIBLE); + spin_unlock(&dentry->d_lock); + schedule(); + spin_lock(&dentry->d_lock); + } while (d_in_lookup(dentry)); + finish_swait(dentry->d_wait, &__wait); } struct dentry *d_alloc_parallel(struct dentry *parent, const struct qstr *name, - wait_queue_head_t *wq) + struct swait_queue_head *wq) { unsigned int hash = name->hash; struct hlist_bl_head *b = in_lookup_hash(parent, hash); @@ -2475,7 +2480,7 @@ struct dentry *d_alloc_parallel(struct dentry *parent, retry: rcu_read_lock(); - seq = smp_load_acquire(&parent->d_inode->i_dir_seq); + seq = smp_load_acquire(&parent->d_inode->__i_dir_seq); r_seq = read_seqbegin(&rename_lock); dentry = __d_lookup_rcu(parent, name, &d_seq); if (unlikely(dentry)) { @@ -2503,7 +2508,7 @@ retry: } hlist_bl_lock(b); - if (unlikely(READ_ONCE(parent->d_inode->i_dir_seq) != seq)) { + if (unlikely(READ_ONCE(parent->d_inode->__i_dir_seq) != seq)) { hlist_bl_unlock(b); rcu_read_unlock(); goto retry; @@ -2576,7 +2581,7 @@ void __d_lookup_done(struct dentry *dentry) hlist_bl_lock(b); dentry->d_flags &= ~DCACHE_PAR_LOOKUP; __hlist_bl_del(&dentry->d_u.d_in_lookup_hash); - wake_up_all(dentry->d_wait); + swake_up_all(dentry->d_wait); dentry->d_wait = NULL; hlist_bl_unlock(b); INIT_HLIST_NODE(&dentry->d_u.d_alias); @@ -3116,6 +3121,8 @@ __setup("dhash_entries=", set_dhash_entries); static void __init dcache_init_early(void) { + unsigned int loop; + /* If hashes are distributed across NUMA nodes, defer * hash allocation until vmalloc space is available. */ @@ -3132,11 +3139,16 @@ static void __init dcache_init_early(void) NULL, 0, 0); + + for (loop = 0; loop < (1U << d_hash_shift); loop++) + INIT_HLIST_BL_HEAD(dentry_hashtable + loop); + d_hash_shift = 32 - d_hash_shift; } static void __init dcache_init(void) { + unsigned int loop; /* * A constructor could be added for stable state like the lists, * but it is probably not worth it because of the cache nature @@ -3160,6 +3172,10 @@ static void __init dcache_init(void) NULL, 0, 0); + + for (loop = 0; loop < (1U << d_hash_shift); loop++) + INIT_HLIST_BL_HEAD(dentry_hashtable + loop); + d_hash_shift = 32 - d_hash_shift; } diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 727aa6dba072..4749006f9aaf 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -563,12 +563,12 @@ static int ep_poll_wakeup_proc(void *priv, void *cookie, int call_nests) static void ep_poll_safewake(wait_queue_head_t *wq) { - int this_cpu = get_cpu(); + int this_cpu = get_cpu_light(); ep_call_nested(&poll_safewake_ncalls, EP_MAX_NESTS, ep_poll_wakeup_proc, NULL, wq, (void *) (long) this_cpu); - put_cpu(); + put_cpu_light(); } #else diff --git a/fs/exec.c b/fs/exec.c index 10d3edde4b62..a2046c72e6c5 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1029,12 +1029,14 @@ static int exec_mmap(struct mm_struct *mm) } } task_lock(tsk); + preempt_disable_rt(); active_mm = tsk->active_mm; tsk->mm = mm; tsk->active_mm = mm; activate_mm(active_mm, mm); tsk->mm->vmacache_seqnum = 0; vmacache_flush(tsk); + preempt_enable_rt(); task_unlock(tsk); if (old_mm) { up_read(&old_mm->mmap_sem); diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index db7590178dfc..d76364124443 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -95,8 +95,7 @@ static void ext4_finish_bio(struct bio *bio) * We check all buffers in the page under BH_Uptodate_Lock * to avoid races with other end io clearing async_write flags */ - local_irq_save(flags); - bit_spin_lock(BH_Uptodate_Lock, &head->b_state); + flags = bh_uptodate_lock_irqsave(head); do { if (bh_offset(bh) < bio_start || bh_offset(bh) + bh->b_size > bio_end) { @@ -108,8 +107,7 @@ static void ext4_finish_bio(struct bio *bio) if (bio->bi_status) buffer_io_error(bh); } while ((bh = bh->b_this_page) != head); - bit_spin_unlock(BH_Uptodate_Lock, &head->b_state); - local_irq_restore(flags); + bh_uptodate_unlock_irqrestore(head, flags); if (!under_io) { #ifdef CONFIG_EXT4_FS_ENCRYPTION if (data_page) diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c index c550512ce335..d5d57da32ffa 100644 --- a/fs/fscache/cookie.c +++ b/fs/fscache/cookie.c @@ -962,3 +962,11 @@ inconsistent: return -ESTALE; } EXPORT_SYMBOL(__fscache_check_consistency); + +void __init fscache_cookie_init(void) +{ + int i; + + for (i = 0; i < (1 << fscache_cookie_hash_shift) - 1; i++) + INIT_HLIST_BL_HEAD(&fscache_cookie_hash[i]); +} diff --git a/fs/fscache/main.c b/fs/fscache/main.c index 30ad89db1efc..1d5f1d679ffa 100644 --- a/fs/fscache/main.c +++ b/fs/fscache/main.c @@ -149,6 +149,7 @@ static int __init fscache_init(void) ret = -ENOMEM; goto error_cookie_jar; } + fscache_cookie_init(); fscache_root = kobject_create_and_add("fscache", kernel_kobj); if (!fscache_root) diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index d3a820ed5c94..00e3dd578d27 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -1196,7 +1196,7 @@ static int fuse_direntplus_link(struct file *file, struct inode *dir = d_inode(parent); struct fuse_conn *fc; struct inode *inode; - DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); + DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq); if (!o->nodeid) { /* diff --git a/fs/inode.c b/fs/inode.c index b0fdf39be6fd..1e97ea3d57c7 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -155,7 +155,7 @@ int inode_init_always(struct super_block *sb, struct inode *inode) inode->i_bdev = NULL; inode->i_cdev = NULL; inode->i_link = NULL; - inode->i_dir_seq = 0; + inode->__i_dir_seq = 0; inode->i_rdev = 0; inode->dirtied_when = 0; diff --git a/fs/libfs.c b/fs/libfs.c index 0fb590d79f30..cd95874a1952 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -90,7 +90,7 @@ static struct dentry *next_positive(struct dentry *parent, struct list_head *from, int count) { - unsigned *seq = &parent->d_inode->i_dir_seq, n; + unsigned *seq = &parent->d_inode->__i_dir_seq, n; struct dentry *res; struct list_head *p; bool skipped; @@ -123,8 +123,9 @@ retry: static void move_cursor(struct dentry *cursor, struct list_head *after) { struct dentry *parent = cursor->d_parent; - unsigned n, *seq = &parent->d_inode->i_dir_seq; + unsigned n, *seq = &parent->d_inode->__i_dir_seq; spin_lock(&parent->d_lock); + preempt_disable_rt(); for (;;) { n = *seq; if (!(n & 1) && cmpxchg(seq, n, n + 1) == n) @@ -137,6 +138,7 @@ static void move_cursor(struct dentry *cursor, struct list_head *after) else list_add_tail(&cursor->d_child, &parent->d_subdirs); smp_store_release(seq, n + 2); + preempt_enable_rt(); spin_unlock(&parent->d_lock); } diff --git a/fs/locks.c b/fs/locks.c index fafce5a8d74f..e768982e20d4 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -945,7 +945,7 @@ static int flock_lock_inode(struct inode *inode, struct file_lock *request) return -ENOMEM; } - percpu_down_read_preempt_disable(&file_rwsem); + percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); if (request->fl_flags & FL_ACCESS) goto find_conflict; @@ -986,7 +986,7 @@ find_conflict: out: spin_unlock(&ctx->flc_lock); - percpu_up_read_preempt_enable(&file_rwsem); + percpu_up_read(&file_rwsem); if (new_fl) locks_free_lock(new_fl); locks_dispose_list(&dispose); @@ -1023,7 +1023,7 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request, new_fl2 = locks_alloc_lock(); } - percpu_down_read_preempt_disable(&file_rwsem); + percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); /* * New lock request. Walk all POSIX locks and look for conflicts. If @@ -1195,7 +1195,7 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request, } out: spin_unlock(&ctx->flc_lock); - percpu_up_read_preempt_enable(&file_rwsem); + percpu_up_read(&file_rwsem); /* * Free any unused locks. */ @@ -1470,7 +1470,7 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) return error; } - percpu_down_read_preempt_disable(&file_rwsem); + percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); time_out_leases(inode, &dispose); @@ -1522,13 +1522,13 @@ restart: locks_insert_block(fl, new_fl); trace_break_lease_block(inode, new_fl); spin_unlock(&ctx->flc_lock); - percpu_up_read_preempt_enable(&file_rwsem); + percpu_up_read(&file_rwsem); locks_dispose_list(&dispose); error = wait_event_interruptible_timeout(new_fl->fl_wait, !new_fl->fl_next, break_time); - percpu_down_read_preempt_disable(&file_rwsem); + percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); trace_break_lease_unblock(inode, new_fl); locks_delete_block(new_fl); @@ -1545,7 +1545,7 @@ restart: } out: spin_unlock(&ctx->flc_lock); - percpu_up_read_preempt_enable(&file_rwsem); + percpu_up_read(&file_rwsem); locks_dispose_list(&dispose); locks_free_lock(new_fl); return error; @@ -1617,7 +1617,7 @@ int fcntl_getlease(struct file *filp) ctx = smp_load_acquire(&inode->i_flctx); if (ctx && !list_empty_careful(&ctx->flc_lease)) { - percpu_down_read_preempt_disable(&file_rwsem); + percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); time_out_leases(inode, &dispose); list_for_each_entry(fl, &ctx->flc_lease, fl_list) { @@ -1627,7 +1627,7 @@ int fcntl_getlease(struct file *filp) break; } spin_unlock(&ctx->flc_lock); - percpu_up_read_preempt_enable(&file_rwsem); + percpu_up_read(&file_rwsem); locks_dispose_list(&dispose); } @@ -1702,7 +1702,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr return -EINVAL; } - percpu_down_read_preempt_disable(&file_rwsem); + percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); time_out_leases(inode, &dispose); error = check_conflicting_open(dentry, arg, lease->fl_flags); @@ -1773,7 +1773,7 @@ out_setup: lease->fl_lmops->lm_setup(lease, priv); out: spin_unlock(&ctx->flc_lock); - percpu_up_read_preempt_enable(&file_rwsem); + percpu_up_read(&file_rwsem); locks_dispose_list(&dispose); if (is_deleg) inode_unlock(inode); @@ -1796,7 +1796,7 @@ static int generic_delete_lease(struct file *filp, void *owner) return error; } - percpu_down_read_preempt_disable(&file_rwsem); + percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); list_for_each_entry(fl, &ctx->flc_lease, fl_list) { if (fl->fl_file == filp && @@ -1809,7 +1809,7 @@ static int generic_delete_lease(struct file *filp, void *owner) if (victim) error = fl->fl_lmops->lm_change(victim, F_UNLCK, &dispose); spin_unlock(&ctx->flc_lock); - percpu_up_read_preempt_enable(&file_rwsem); + percpu_up_read(&file_rwsem); locks_dispose_list(&dispose); return error; } @@ -2540,13 +2540,13 @@ locks_remove_lease(struct file *filp, struct file_lock_context *ctx) if (list_empty(&ctx->flc_lease)) return; - percpu_down_read_preempt_disable(&file_rwsem); + percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list) if (filp == fl->fl_file) lease_modify(fl, F_UNLCK, &dispose); spin_unlock(&ctx->flc_lock); - percpu_up_read_preempt_enable(&file_rwsem); + percpu_up_read(&file_rwsem); locks_dispose_list(&dispose); } diff --git a/fs/namei.c b/fs/namei.c index 389e48e93542..879c66045c68 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1604,7 +1604,7 @@ static struct dentry *__lookup_slow(const struct qstr *name, { struct dentry *dentry, *old; struct inode *inode = dir->d_inode; - DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); + DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq); /* Don't go there if it's already dead */ if (unlikely(IS_DEADDIR(inode))) @@ -3121,7 +3121,7 @@ static int lookup_open(struct nameidata *nd, struct path *path, struct dentry *dentry; int error, create_error = 0; umode_t mode = op->mode; - DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); + DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq); if (unlikely(IS_DEADDIR(dir_inode))) return -ENOENT; diff --git a/fs/namespace.c b/fs/namespace.c index 90b8c4d8c9e3..93f3eec4c652 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -14,6 +14,7 @@ #include <linux/mnt_namespace.h> #include <linux/user_namespace.h> #include <linux/namei.h> +#include <linux/delay.h> #include <linux/security.h> #include <linux/cred.h> #include <linux/idr.h> @@ -353,8 +354,11 @@ int __mnt_want_write(struct vfsmount *m) * incremented count after it has set MNT_WRITE_HOLD. */ smp_mb(); - while (READ_ONCE(mnt->mnt.mnt_flags) & MNT_WRITE_HOLD) - cpu_relax(); + while (READ_ONCE(mnt->mnt.mnt_flags) & MNT_WRITE_HOLD) { + preempt_enable(); + cpu_chill(); + preempt_disable(); + } /* * After the slowpath clears MNT_WRITE_HOLD, mnt_is_readonly will * be set to match its requirements. So we must not load that until diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index 75fe92eaa681..e8d05393443f 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -152,11 +152,11 @@ again: sp = state->owner; /* Block nfs4_proc_unlck */ mutex_lock(&sp->so_delegreturn_mutex); - seq = raw_seqcount_begin(&sp->so_reclaim_seqcount); + seq = read_seqbegin(&sp->so_reclaim_seqlock); err = nfs4_open_delegation_recall(ctx, state, stateid, type); if (!err) err = nfs_delegation_claim_locks(ctx, state, stateid); - if (!err && read_seqcount_retry(&sp->so_reclaim_seqcount, seq)) + if (!err && read_seqretry(&sp->so_reclaim_seqlock, seq)) err = -EAGAIN; mutex_unlock(&sp->so_delegreturn_mutex); put_nfs_open_context(ctx); diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 7a9c14426855..539b750a89bc 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -445,7 +445,7 @@ static void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry) { struct qstr filename = QSTR_INIT(entry->name, entry->len); - DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); + DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq); struct dentry *dentry; struct dentry *alias; struct inode *dir = d_inode(parent); @@ -1454,7 +1454,7 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry, struct file *file, unsigned open_flags, umode_t mode, int *opened) { - DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); + DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq); struct nfs_open_context *ctx; struct dentry *res; struct iattr attr = { .ia_valid = ATTR_OPEN }; @@ -1775,7 +1775,11 @@ int nfs_rmdir(struct inode *dir, struct dentry *dentry) trace_nfs_rmdir_enter(dir, dentry); if (d_really_is_positive(dentry)) { +#ifdef CONFIG_PREEMPT_RT_BASE + down(&NFS_I(d_inode(dentry))->rmdir_sem); +#else down_write(&NFS_I(d_inode(dentry))->rmdir_sem); +#endif error = NFS_PROTO(dir)->rmdir(dir, &dentry->d_name); /* Ensure the VFS deletes this inode */ switch (error) { @@ -1785,7 +1789,11 @@ int nfs_rmdir(struct inode *dir, struct dentry *dentry) case -ENOENT: nfs_dentry_handle_enoent(dentry); } +#ifdef CONFIG_PREEMPT_RT_BASE + up(&NFS_I(d_inode(dentry))->rmdir_sem); +#else up_write(&NFS_I(d_inode(dentry))->rmdir_sem); +#endif } else error = NFS_PROTO(dir)->rmdir(dir, &dentry->d_name); trace_nfs_rmdir_exit(dir, dentry, error); diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index b65aee481d13..110ee6f78c31 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -2103,7 +2103,11 @@ static void init_once(void *foo) atomic_long_set(&nfsi->nrequests, 0); atomic_long_set(&nfsi->commit_info.ncommit, 0); atomic_set(&nfsi->commit_info.rpcs_out, 0); +#ifdef CONFIG_PREEMPT_RT_BASE + sema_init(&nfsi->rmdir_sem, 1); +#else init_rwsem(&nfsi->rmdir_sem); +#endif mutex_init(&nfsi->commit_mutex); nfs4_init_once(nfsi); } diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index 60643c96b29f..2025a427fb74 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -114,7 +114,7 @@ struct nfs4_state_owner { unsigned long so_flags; struct list_head so_states; struct nfs_seqid_counter so_seqid; - seqcount_t so_reclaim_seqcount; + seqlock_t so_reclaim_seqlock; struct mutex so_delegreturn_mutex; }; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index a31235221d52..e306ea61248a 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -2826,7 +2826,7 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata, unsigned int seq; int ret; - seq = raw_seqcount_begin(&sp->so_reclaim_seqcount); + seq = raw_seqcount_begin(&sp->so_reclaim_seqlock.seqcount); ret = _nfs4_proc_open(opendata, ctx); if (ret != 0) @@ -2864,7 +2864,7 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata, if (d_inode(dentry) == state->inode) { nfs_inode_attach_open_context(ctx); - if (read_seqcount_retry(&sp->so_reclaim_seqcount, seq)) + if (read_seqretry(&sp->so_reclaim_seqlock, seq)) nfs4_schedule_stateid_recovery(server, state); else pnfs_parse_lgopen(state->inode, opendata->lgp, ctx); diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index b0cae6ba9316..ae8a6b3c5a9d 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -515,7 +515,7 @@ nfs4_alloc_state_owner(struct nfs_server *server, nfs4_init_seqid_counter(&sp->so_seqid); atomic_set(&sp->so_count, 1); INIT_LIST_HEAD(&sp->so_lru); - seqcount_init(&sp->so_reclaim_seqcount); + seqlock_init(&sp->so_reclaim_seqlock); mutex_init(&sp->so_delegreturn_mutex); return sp; } @@ -1567,8 +1567,12 @@ static int nfs4_reclaim_open_state(struct nfs4_state_owner *sp, const struct nfs * recovering after a network partition or a reboot from a * server that doesn't support a grace period. */ +#ifdef CONFIG_PREEMPT_RT_FULL + write_seqlock(&sp->so_reclaim_seqlock); +#else + write_seqcount_begin(&sp->so_reclaim_seqlock.seqcount); +#endif spin_lock(&sp->so_lock); - raw_write_seqcount_begin(&sp->so_reclaim_seqcount); restart: list_for_each_entry(state, &sp->so_states, open_states) { if (!test_and_clear_bit(ops->state_flag_bit, &state->flags)) @@ -1637,14 +1641,20 @@ restart: spin_lock(&sp->so_lock); goto restart; } - raw_write_seqcount_end(&sp->so_reclaim_seqcount); spin_unlock(&sp->so_lock); +#ifdef CONFIG_PREEMPT_RT_FULL + write_sequnlock(&sp->so_reclaim_seqlock); +#else + write_seqcount_end(&sp->so_reclaim_seqlock.seqcount); +#endif return 0; out_err: nfs4_put_open_state(state); - spin_lock(&sp->so_lock); - raw_write_seqcount_end(&sp->so_reclaim_seqcount); - spin_unlock(&sp->so_lock); +#ifdef CONFIG_PREEMPT_RT_FULL + write_sequnlock(&sp->so_reclaim_seqlock); +#else + write_seqcount_end(&sp->so_reclaim_seqlock.seqcount); +#endif return status; } diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c index fd61bf0fce63..839bfa76f41e 100644 --- a/fs/nfs/unlink.c +++ b/fs/nfs/unlink.c @@ -13,7 +13,7 @@ #include <linux/sunrpc/clnt.h> #include <linux/nfs_fs.h> #include <linux/sched.h> -#include <linux/wait.h> +#include <linux/swait.h> #include <linux/namei.h> #include <linux/fsnotify.h> @@ -52,6 +52,29 @@ static void nfs_async_unlink_done(struct rpc_task *task, void *calldata) rpc_restart_call_prepare(task); } +#ifdef CONFIG_PREEMPT_RT_BASE +static void nfs_down_anon(struct semaphore *sema) +{ + down(sema); +} + +static void nfs_up_anon(struct semaphore *sema) +{ + up(sema); +} + +#else +static void nfs_down_anon(struct rw_semaphore *rwsem) +{ + down_read_non_owner(rwsem); +} + +static void nfs_up_anon(struct rw_semaphore *rwsem) +{ + up_read_non_owner(rwsem); +} +#endif + /** * nfs_async_unlink_release - Release the sillydelete data. * @task: rpc_task of the sillydelete @@ -65,7 +88,7 @@ static void nfs_async_unlink_release(void *calldata) struct dentry *dentry = data->dentry; struct super_block *sb = dentry->d_sb; - up_read_non_owner(&NFS_I(d_inode(dentry->d_parent))->rmdir_sem); + nfs_up_anon(&NFS_I(d_inode(dentry->d_parent))->rmdir_sem); d_lookup_done(dentry); nfs_free_unlinkdata(data); dput(dentry); @@ -118,10 +141,10 @@ static int nfs_call_unlink(struct dentry *dentry, struct inode *inode, struct nf struct inode *dir = d_inode(dentry->d_parent); struct dentry *alias; - down_read_non_owner(&NFS_I(dir)->rmdir_sem); + nfs_down_anon(&NFS_I(dir)->rmdir_sem); alias = d_alloc_parallel(dentry->d_parent, &data->args.name, &data->wq); if (IS_ERR(alias)) { - up_read_non_owner(&NFS_I(dir)->rmdir_sem); + nfs_up_anon(&NFS_I(dir)->rmdir_sem); return 0; } if (!d_in_lookup(alias)) { @@ -143,7 +166,7 @@ static int nfs_call_unlink(struct dentry *dentry, struct inode *inode, struct nf ret = 0; spin_unlock(&alias->d_lock); dput(alias); - up_read_non_owner(&NFS_I(dir)->rmdir_sem); + nfs_up_anon(&NFS_I(dir)->rmdir_sem); /* * If we'd displaced old cached devname, free it. At that * point dentry is definitely not a root, so we won't need @@ -183,7 +206,7 @@ nfs_async_unlink(struct dentry *dentry, const struct qstr *name) goto out_free_name; } data->res.dir_attr = &data->dir_attr; - init_waitqueue_head(&data->wq); + init_swait_queue_head(&data->wq); status = -EBUSY; spin_lock(&dentry->d_lock); diff --git a/fs/ntfs/aops.c b/fs/ntfs/aops.c index 3a2e509c77c5..b4e03c6fc67b 100644 --- a/fs/ntfs/aops.c +++ b/fs/ntfs/aops.c @@ -93,13 +93,11 @@ static void ntfs_end_buffer_async_read(struct buffer_head *bh, int uptodate) ofs = 0; if (file_ofs < init_size) ofs = init_size - file_ofs; - local_irq_save(flags); kaddr = kmap_atomic(page); memset(kaddr + bh_offset(bh) + ofs, 0, bh->b_size - ofs); flush_dcache_page(page); kunmap_atomic(kaddr); - local_irq_restore(flags); } } else { clear_buffer_uptodate(bh); @@ -108,8 +106,7 @@ static void ntfs_end_buffer_async_read(struct buffer_head *bh, int uptodate) "0x%llx.", (unsigned long long)bh->b_blocknr); } first = page_buffers(page); - local_irq_save(flags); - bit_spin_lock(BH_Uptodate_Lock, &first->b_state); + flags = bh_uptodate_lock_irqsave(first); clear_buffer_async_read(bh); unlock_buffer(bh); tmp = bh; @@ -124,8 +121,7 @@ static void ntfs_end_buffer_async_read(struct buffer_head *bh, int uptodate) } tmp = tmp->b_this_page; } while (tmp != bh); - bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); - local_irq_restore(flags); + bh_uptodate_unlock_irqrestore(first, flags); /* * If none of the buffers had errors then we can set the page uptodate, * but we first have to perform the post read mst fixups, if the @@ -146,13 +142,11 @@ static void ntfs_end_buffer_async_read(struct buffer_head *bh, int uptodate) recs = PAGE_SIZE / rec_size; /* Should have been verified before we got here... */ BUG_ON(!recs); - local_irq_save(flags); kaddr = kmap_atomic(page); for (i = 0; i < recs; i++) post_read_mst_fixup((NTFS_RECORD*)(kaddr + i * rec_size), rec_size); kunmap_atomic(kaddr); - local_irq_restore(flags); flush_dcache_page(page); if (likely(page_uptodate && !PageError(page))) SetPageUptodate(page); @@ -160,9 +154,7 @@ static void ntfs_end_buffer_async_read(struct buffer_head *bh, int uptodate) unlock_page(page); return; still_busy: - bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); - local_irq_restore(flags); - return; + bh_uptodate_unlock_irqrestore(first, flags); } /** diff --git a/fs/proc/array.c b/fs/proc/array.c index 0ceb3b6b37e7..ccfef702c771 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -381,9 +381,9 @@ static inline void task_context_switch_counts(struct seq_file *m, static void task_cpus_allowed(struct seq_file *m, struct task_struct *task) { seq_printf(m, "Cpus_allowed:\t%*pb\n", - cpumask_pr_args(&task->cpus_allowed)); + cpumask_pr_args(task->cpus_ptr)); seq_printf(m, "Cpus_allowed_list:\t%*pbl\n", - cpumask_pr_args(&task->cpus_allowed)); + cpumask_pr_args(task->cpus_ptr)); } static inline void task_core_dumping(struct seq_file *m, struct mm_struct *mm) diff --git a/fs/proc/base.c b/fs/proc/base.c index 1b0a7440a25a..e0b380b55b5a 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1874,7 +1874,7 @@ bool proc_fill_cache(struct file *file, struct dir_context *ctx, child = d_hash_and_lookup(dir, &qname); if (!child) { - DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); + DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq); child = d_alloc_parallel(dir, &qname, &wq); if (IS_ERR(child)) goto end_instantiate; diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 7325baa8f9d4..31f25ff3999f 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -677,7 +677,7 @@ static bool proc_sys_fill_cache(struct file *file, child = d_lookup(dir, &qname); if (!child) { - DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); + DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq); child = d_alloc_parallel(dir, &qname, &wq); if (IS_ERR(child)) return false; diff --git a/fs/squashfs/decompressor_multi_percpu.c b/fs/squashfs/decompressor_multi_percpu.c index 23a9c28ad8ea..6a73c4fa88e7 100644 --- a/fs/squashfs/decompressor_multi_percpu.c +++ b/fs/squashfs/decompressor_multi_percpu.c @@ -10,6 +10,7 @@ #include <linux/slab.h> #include <linux/percpu.h> #include <linux/buffer_head.h> +#include <linux/locallock.h> #include "squashfs_fs.h" #include "squashfs_fs_sb.h" @@ -25,6 +26,8 @@ struct squashfs_stream { void *stream; }; +static DEFINE_LOCAL_IRQ_LOCK(stream_lock); + void *squashfs_decompressor_create(struct squashfs_sb_info *msblk, void *comp_opts) { @@ -79,10 +82,15 @@ int squashfs_decompress(struct squashfs_sb_info *msblk, struct buffer_head **bh, { struct squashfs_stream __percpu *percpu = (struct squashfs_stream __percpu *) msblk->stream; - struct squashfs_stream *stream = get_cpu_ptr(percpu); - int res = msblk->decompressor->decompress(msblk, stream->stream, bh, b, - offset, length, output); - put_cpu_ptr(stream); + struct squashfs_stream *stream; + int res; + + stream = get_locked_ptr(stream_lock, percpu); + + res = msblk->decompressor->decompress(msblk, stream->stream, bh, b, + offset, length, output); + + put_locked_ptr(stream_lock, stream); if (res < 0) ERROR("%s decompression failed, data probably corrupt\n", diff --git a/fs/timerfd.c b/fs/timerfd.c index cdad49da3ff7..1b304f2f1d08 100644 --- a/fs/timerfd.c +++ b/fs/timerfd.c @@ -471,7 +471,10 @@ static int do_timerfd_settime(int ufd, int flags, break; } spin_unlock_irq(&ctx->wqh.lock); - cpu_relax(); + if (isalarm(ctx)) + hrtimer_wait_for_timer(&ctx->t.alarm.timer); + else + hrtimer_wait_for_timer(&ctx->t.tmr); } /* diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 8eb3ba3d4d00..2bb3366229ac 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -108,8 +108,7 @@ xfs_finish_page_writeback( ASSERT(bvec->bv_offset + bvec->bv_len <= PAGE_SIZE); ASSERT((bvec->bv_len & (i_blocksize(inode) - 1)) == 0); - local_irq_save(flags); - bit_spin_lock(BH_Uptodate_Lock, &head->b_state); + flags = bh_uptodate_lock_irqsave(head); do { if (off >= bvec->bv_offset && off < bvec->bv_offset + bvec->bv_len) { @@ -131,8 +130,7 @@ xfs_finish_page_writeback( } off += bh->b_size; } while ((bh = bh->b_this_page) != head); - bit_spin_unlock(BH_Uptodate_Lock, &head->b_state); - local_irq_restore(flags); + bh_uptodate_unlock_irqrestore(head, flags); if (!busy) end_page_writeback(bvec->bv_page); diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index 0e8c6647c6bd..07e02d6df5ad 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -12,6 +12,7 @@ #include <linux/timer.h> #include <linux/workqueue.h> #include <linux/kref.h> +#include <linux/refcount.h> struct page; struct device; @@ -75,7 +76,7 @@ enum wb_reason { */ struct bdi_writeback_congested { unsigned long state; /* WB_[a]sync_congested flags */ - atomic_t refcnt; /* nr of attached wb's and blkg */ + refcount_t refcnt; /* nr of attached wb's and blkg */ #ifdef CONFIG_CGROUP_WRITEBACK struct backing_dev_info *__bdi; /* the associated bdi, set to NULL diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 72ca0f3d39f3..c28a47cbe355 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -404,13 +404,13 @@ static inline bool inode_cgwb_enabled(struct inode *inode) static inline struct bdi_writeback_congested * wb_congested_get_create(struct backing_dev_info *bdi, int blkcg_id, gfp_t gfp) { - atomic_inc(&bdi->wb_congested->refcnt); + refcount_inc(&bdi->wb_congested->refcnt); return bdi->wb_congested; } static inline void wb_congested_put(struct bdi_writeback_congested *congested) { - if (atomic_dec_and_test(&congested->refcnt)) + if (refcount_dec_and_test(&congested->refcnt)) kfree(congested); } diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index ca3f2c2edd85..51869c44ef0d 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -247,7 +247,7 @@ static inline u16 blk_mq_unique_tag_to_tag(u32 unique_tag) return unique_tag & BLK_MQ_UNIQUE_TAG_MASK; } - +void __blk_mq_complete_request_remote_work(struct work_struct *work); int blk_mq_request_started(struct request *rq); void blk_mq_start_request(struct request *rq); void blk_mq_end_request(struct request *rq, blk_status_t error); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 79226ca8f80f..7271d7bf5c15 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -27,6 +27,7 @@ #include <linux/percpu-refcount.h> #include <linux/scatterlist.h> #include <linux/blkzoned.h> +#include <linux/swork.h> #include <linux/seqlock.h> #include <linux/u64_stats_sync.h> @@ -151,6 +152,9 @@ enum mq_rq_state { */ struct request { struct request_queue *q; +#ifdef CONFIG_PREEMPT_RT_FULL + struct work_struct work; +#endif struct blk_mq_ctx *mq_ctx; int cpu; @@ -648,6 +652,7 @@ struct request_queue { #endif struct rcu_head rcu_head; wait_queue_head_t mq_freeze_wq; + struct swork_event mq_pcpu_wake; struct percpu_ref q_usage_counter; struct list_head all_q_node; diff --git a/include/linux/bottom_half.h b/include/linux/bottom_half.h index a19519f4241d..40dd5ef9c154 100644 --- a/include/linux/bottom_half.h +++ b/include/linux/bottom_half.h @@ -4,6 +4,39 @@ #include <linux/preempt.h> +#ifdef CONFIG_PREEMPT_RT_FULL + +extern void __local_bh_disable(void); +extern void _local_bh_enable(void); +extern void __local_bh_enable(void); + +static inline void local_bh_disable(void) +{ + __local_bh_disable(); +} + +static inline void __local_bh_disable_ip(unsigned long ip, unsigned int cnt) +{ + __local_bh_disable(); +} + +static inline void local_bh_enable(void) +{ + __local_bh_enable(); +} + +static inline void __local_bh_enable_ip(unsigned long ip, unsigned int cnt) +{ + __local_bh_enable(); +} + +static inline void local_bh_enable_ip(unsigned long ip) +{ + __local_bh_enable(); +} + +#else + #ifdef CONFIG_TRACE_IRQFLAGS extern void __local_bh_disable_ip(unsigned long ip, unsigned int cnt); #else @@ -31,5 +64,6 @@ static inline void local_bh_enable(void) { __local_bh_enable_ip(_THIS_IP_, SOFTIRQ_DISABLE_OFFSET); } +#endif #endif /* _LINUX_BH_H */ diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 96225a77c112..5869330d1f38 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -76,8 +76,50 @@ struct buffer_head { struct address_space *b_assoc_map; /* mapping this buffer is associated with */ atomic_t b_count; /* users using this buffer_head */ +#ifdef CONFIG_PREEMPT_RT_BASE + spinlock_t b_uptodate_lock; +#if IS_ENABLED(CONFIG_JBD2) + spinlock_t b_state_lock; + spinlock_t b_journal_head_lock; +#endif +#endif }; +static inline unsigned long bh_uptodate_lock_irqsave(struct buffer_head *bh) +{ + unsigned long flags; + +#ifndef CONFIG_PREEMPT_RT_BASE + local_irq_save(flags); + bit_spin_lock(BH_Uptodate_Lock, &bh->b_state); +#else + spin_lock_irqsave(&bh->b_uptodate_lock, flags); +#endif + return flags; +} + +static inline void +bh_uptodate_unlock_irqrestore(struct buffer_head *bh, unsigned long flags) +{ +#ifndef CONFIG_PREEMPT_RT_BASE + bit_spin_unlock(BH_Uptodate_Lock, &bh->b_state); + local_irq_restore(flags); +#else + spin_unlock_irqrestore(&bh->b_uptodate_lock, flags); +#endif +} + +static inline void buffer_head_init_locks(struct buffer_head *bh) +{ +#ifdef CONFIG_PREEMPT_RT_BASE + spin_lock_init(&bh->b_uptodate_lock); +#if IS_ENABLED(CONFIG_JBD2) + spin_lock_init(&bh->b_state_lock); + spin_lock_init(&bh->b_journal_head_lock); +#endif +#endif +} + /* * macro tricks to expand the set_buffer_foo(), clear_buffer_foo() * and buffer_foo() functions. diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 4b486a6fe952..7c09b3bcce4b 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -20,6 +20,7 @@ #include <linux/u64_stats_sync.h> #include <linux/workqueue.h> #include <linux/bpf-cgroup.h> +#include <linux/swork.h> #ifdef CONFIG_CGROUPS @@ -157,6 +158,7 @@ struct cgroup_subsys_state { /* percpu_ref killing and RCU release */ struct work_struct destroy_work; + struct swork_event destroy_swork; struct rcu_work destroy_rwork; /* diff --git a/include/linux/completion.h b/include/linux/completion.h index 519e94915d18..bf8e77001f18 100644 --- a/include/linux/completion.h +++ b/include/linux/completion.h @@ -9,7 +9,7 @@ * See kernel/sched/completion.c for details. */ -#include <linux/wait.h> +#include <linux/swait.h> /* * struct completion - structure used to maintain state for a "completion" @@ -25,7 +25,7 @@ */ struct completion { unsigned int done; - wait_queue_head_t wait; + struct swait_queue_head wait; }; #define init_completion_map(x, m) __init_completion(x) @@ -34,7 +34,7 @@ static inline void complete_acquire(struct completion *x) {} static inline void complete_release(struct completion *x) {} #define COMPLETION_INITIALIZER(work) \ - { 0, __WAIT_QUEUE_HEAD_INITIALIZER((work).wait) } + { 0, __SWAIT_QUEUE_HEAD_INITIALIZER((work).wait) } #define COMPLETION_INITIALIZER_ONSTACK_MAP(work, map) \ (*({ init_completion_map(&(work), &(map)); &(work); })) @@ -85,7 +85,7 @@ static inline void complete_release(struct completion *x) {} static inline void __init_completion(struct completion *x) { x->done = 0; - init_waitqueue_head(&x->wait); + init_swait_queue_head(&x->wait); } /** diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 5db1a555dadf..e9cd1436485d 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -112,6 +112,8 @@ extern void cpu_hotplug_disable(void); extern void cpu_hotplug_enable(void); void clear_tasks_mm_cpumask(int cpu); int cpu_down(unsigned int cpu); +extern void pin_current_cpu(void); +extern void unpin_current_cpu(void); #else /* CONFIG_HOTPLUG_CPU */ @@ -122,6 +124,9 @@ static inline void cpus_read_unlock(void) { } static inline void lockdep_assert_cpus_held(void) { } static inline void cpu_hotplug_disable(void) { } static inline void cpu_hotplug_enable(void) { } +static inline void pin_current_cpu(void) { } +static inline void unpin_current_cpu(void) { } + #endif /* !CONFIG_HOTPLUG_CPU */ /* Wrappers which go away once all code is converted */ diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 474cd4040c8b..03625cbd3847 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -105,7 +105,7 @@ struct dentry { union { struct list_head d_lru; /* LRU list */ - wait_queue_head_t *d_wait; /* in-lookup ones only */ + struct swait_queue_head *d_wait; /* in-lookup ones only */ }; struct list_head d_child; /* child of parent list */ struct list_head d_subdirs; /* our children */ @@ -238,7 +238,7 @@ extern struct dentry * d_alloc(struct dentry *, const struct qstr *); extern struct dentry * d_alloc_anon(struct super_block *); extern struct dentry * d_alloc_pseudo(struct super_block *, const struct qstr *); extern struct dentry * d_alloc_parallel(struct dentry *, const struct qstr *, - wait_queue_head_t *); + struct swait_queue_head *); extern struct dentry * d_splice_alias(struct inode *, struct dentry *); extern struct dentry * d_add_ci(struct dentry *, struct inode *, struct qstr *); extern struct dentry * d_exact_alias(struct dentry *, struct inode *); diff --git a/include/linux/delay.h b/include/linux/delay.h index b78bab4395d8..7c4bc414a504 100644 --- a/include/linux/delay.h +++ b/include/linux/delay.h @@ -64,4 +64,10 @@ static inline void ssleep(unsigned int seconds) msleep(seconds * 1000); } +#ifdef CONFIG_PREEMPT_RT_FULL +extern void cpu_chill(void); +#else +# define cpu_chill() cpu_relax() +#endif + #endif /* defined(_LINUX_DELAY_H) */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 69f9a7fc11a3..46da20d6f98a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -660,7 +660,7 @@ struct inode { struct block_device *i_bdev; struct cdev *i_cdev; char *i_link; - unsigned i_dir_seq; + unsigned __i_dir_seq; }; __u32 i_generation; diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 84b90a79d75a..87a9330eafa2 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -230,6 +230,7 @@ extern void __fscache_readpages_cancel(struct fscache_cookie *cookie, extern void __fscache_disable_cookie(struct fscache_cookie *, const void *, bool); extern void __fscache_enable_cookie(struct fscache_cookie *, const void *, loff_t, bool (*)(void *), void *); +extern void fscache_cookie_init(void); /** * fscache_register_netfs - Register a filesystem as desiring caching services diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 0690679832d4..eaa2ef9bc10e 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -8,6 +8,7 @@ #include <linux/mm.h> #include <linux/uaccess.h> #include <linux/hardirq.h> +#include <linux/sched.h> #include <asm/cacheflush.h> @@ -66,7 +67,7 @@ static inline void kunmap(struct page *page) static inline void *kmap_atomic(struct page *page) { - preempt_disable(); + preempt_disable_nort(); pagefault_disable(); return page_address(page); } @@ -75,7 +76,7 @@ static inline void *kmap_atomic(struct page *page) static inline void __kunmap_atomic(void *addr) { pagefault_enable(); - preempt_enable(); + preempt_enable_nort(); } #define kmap_atomic_pfn(pfn) kmap_atomic(pfn_to_page(pfn)) @@ -87,32 +88,51 @@ static inline void __kunmap_atomic(void *addr) #if defined(CONFIG_HIGHMEM) || defined(CONFIG_X86_32) +#ifndef CONFIG_PREEMPT_RT_FULL DECLARE_PER_CPU(int, __kmap_atomic_idx); +#endif static inline int kmap_atomic_idx_push(void) { +#ifndef CONFIG_PREEMPT_RT_FULL int idx = __this_cpu_inc_return(__kmap_atomic_idx) - 1; -#ifdef CONFIG_DEBUG_HIGHMEM +# ifdef CONFIG_DEBUG_HIGHMEM WARN_ON_ONCE(in_irq() && !irqs_disabled()); BUG_ON(idx >= KM_TYPE_NR); -#endif +# endif return idx; +#else + current->kmap_idx++; + BUG_ON(current->kmap_idx > KM_TYPE_NR); + return current->kmap_idx - 1; +#endif } static inline int kmap_atomic_idx(void) { +#ifndef CONFIG_PREEMPT_RT_FULL return __this_cpu_read(__kmap_atomic_idx) - 1; +#else + return current->kmap_idx - 1; +#endif } static inline void kmap_atomic_idx_pop(void) { -#ifdef CONFIG_DEBUG_HIGHMEM +#ifndef CONFIG_PREEMPT_RT_FULL +# ifdef CONFIG_DEBUG_HIGHMEM int idx = __this_cpu_dec_return(__kmap_atomic_idx); BUG_ON(idx < 0); -#else +# else __this_cpu_dec(__kmap_atomic_idx); +# endif +#else + current->kmap_idx--; +# ifdef CONFIG_DEBUG_HIGHMEM + BUG_ON(current->kmap_idx < 0); +# endif #endif } diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 3892e9c8b2de..2bdb047c7656 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -22,6 +22,7 @@ #include <linux/percpu.h> #include <linux/timer.h> #include <linux/timerqueue.h> +#include <linux/wait.h> struct hrtimer_clock_base; struct hrtimer_cpu_base; @@ -41,6 +42,7 @@ enum hrtimer_mode { HRTIMER_MODE_REL = 0x01, HRTIMER_MODE_PINNED = 0x02, HRTIMER_MODE_SOFT = 0x04, + HRTIMER_MODE_HARD = 0x08, HRTIMER_MODE_ABS_PINNED = HRTIMER_MODE_ABS | HRTIMER_MODE_PINNED, HRTIMER_MODE_REL_PINNED = HRTIMER_MODE_REL | HRTIMER_MODE_PINNED, @@ -51,6 +53,11 @@ enum hrtimer_mode { HRTIMER_MODE_ABS_PINNED_SOFT = HRTIMER_MODE_ABS_PINNED | HRTIMER_MODE_SOFT, HRTIMER_MODE_REL_PINNED_SOFT = HRTIMER_MODE_REL_PINNED | HRTIMER_MODE_SOFT, + HRTIMER_MODE_ABS_HARD = HRTIMER_MODE_ABS | HRTIMER_MODE_HARD, + HRTIMER_MODE_REL_HARD = HRTIMER_MODE_REL | HRTIMER_MODE_HARD, + + HRTIMER_MODE_ABS_PINNED_HARD = HRTIMER_MODE_ABS_PINNED | HRTIMER_MODE_HARD, + HRTIMER_MODE_REL_PINNED_HARD = HRTIMER_MODE_REL_PINNED | HRTIMER_MODE_HARD, }; /* @@ -216,6 +223,9 @@ struct hrtimer_cpu_base { ktime_t expires_next; struct hrtimer *next_timer; ktime_t softirq_expires_next; +#ifdef CONFIG_PREEMPT_RT_BASE + wait_queue_head_t wait; +#endif struct hrtimer *softirq_next_timer; struct hrtimer_clock_base clock_base[HRTIMER_MAX_CLOCK_BASES]; } ____cacheline_aligned; @@ -364,10 +374,17 @@ DECLARE_PER_CPU(struct tick_device, tick_cpu_device); /* Initialize timers: */ extern void hrtimer_init(struct hrtimer *timer, clockid_t which_clock, enum hrtimer_mode mode); +extern void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, clockid_t clock_id, + enum hrtimer_mode mode, + struct task_struct *task); #ifdef CONFIG_DEBUG_OBJECTS_TIMERS extern void hrtimer_init_on_stack(struct hrtimer *timer, clockid_t which_clock, enum hrtimer_mode mode); +extern void hrtimer_init_sleeper_on_stack(struct hrtimer_sleeper *sl, + clockid_t clock_id, + enum hrtimer_mode mode, + struct task_struct *task); extern void destroy_hrtimer_on_stack(struct hrtimer *timer); #else @@ -377,6 +394,15 @@ static inline void hrtimer_init_on_stack(struct hrtimer *timer, { hrtimer_init(timer, which_clock, mode); } + +static inline void hrtimer_init_sleeper_on_stack(struct hrtimer_sleeper *sl, + clockid_t clock_id, + enum hrtimer_mode mode, + struct task_struct *task) +{ + hrtimer_init_sleeper(sl, clock_id, mode, task); +} + static inline void destroy_hrtimer_on_stack(struct hrtimer *timer) { } #endif @@ -417,6 +443,13 @@ static inline void hrtimer_restart(struct hrtimer *timer) hrtimer_start_expires(timer, HRTIMER_MODE_ABS); } +/* Softirq preemption could deadlock timer removal */ +#ifdef CONFIG_PREEMPT_RT_BASE + extern void hrtimer_wait_for_timer(const struct hrtimer *timer); +#else +# define hrtimer_wait_for_timer(timer) do { cpu_relax(); } while (0) +#endif + /* Query timers: */ extern ktime_t __hrtimer_get_remaining(const struct hrtimer *timer, bool adjust); @@ -442,7 +475,7 @@ static inline int hrtimer_is_queued(struct hrtimer *timer) * Helper function to check, whether the timer is running the callback * function */ -static inline int hrtimer_callback_running(struct hrtimer *timer) +static inline int hrtimer_callback_running(const struct hrtimer *timer) { return timer->base->running == timer; } @@ -480,9 +513,6 @@ extern long hrtimer_nanosleep(const struct timespec64 *rqtp, const enum hrtimer_mode mode, const clockid_t clockid); -extern void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, - struct task_struct *tsk); - extern int schedule_hrtimeout_range(ktime_t *expires, u64 delta, const enum hrtimer_mode mode); extern int schedule_hrtimeout_range_clock(ktime_t *expires, diff --git a/include/linux/idr.h b/include/linux/idr.h index e856f4e0ab35..f7869f04d223 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -158,10 +158,7 @@ static inline bool idr_is_empty(const struct idr *idr) * Each idr_preload() should be matched with an invocation of this * function. See idr_preload() for details. */ -static inline void idr_preload_end(void) -{ - preempt_enable(); -} +void idr_preload_end(void); /** * idr_for_each_entry() - Iterate over an IDR's elements of a given type. diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index eeceac3376fc..72333899f043 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -13,6 +13,7 @@ #include <linux/hrtimer.h> #include <linux/kref.h> #include <linux/workqueue.h> +#include <linux/swork.h> #include <linux/atomic.h> #include <asm/ptrace.h> @@ -61,6 +62,7 @@ * interrupt handler after suspending interrupts. For system * wakeup devices users need to implement wakeup detection in * their interrupt handlers. + * IRQF_NO_SOFTIRQ_CALL - Do not process softirqs in the irq thread context (RT) */ #define IRQF_SHARED 0x00000080 #define IRQF_PROBE_SHARED 0x00000100 @@ -74,6 +76,7 @@ #define IRQF_NO_THREAD 0x00010000 #define IRQF_EARLY_RESUME 0x00020000 #define IRQF_COND_SUSPEND 0x00040000 +#define IRQF_NO_SOFTIRQ_CALL 0x00080000 #define IRQF_TIMER (__IRQF_TIMER | IRQF_NO_SUSPEND | IRQF_NO_THREAD) @@ -225,6 +228,7 @@ extern void resume_device_irqs(void); * struct irq_affinity_notify - context for notification of IRQ affinity changes * @irq: Interrupt to which notification applies * @kref: Reference count, for internal use + * @swork: Swork item, for internal use * @work: Work item, for internal use * @notify: Function to be called on change. This will be * called in process context. @@ -236,7 +240,11 @@ extern void resume_device_irqs(void); struct irq_affinity_notify { unsigned int irq; struct kref kref; +#ifdef CONFIG_PREEMPT_RT_BASE + struct swork_event swork; +#else struct work_struct work; +#endif void (*notify)(struct irq_affinity_notify *, const cpumask_t *mask); void (*release)(struct kref *ref); }; @@ -427,7 +435,11 @@ extern int irq_set_irqchip_state(unsigned int irq, enum irqchip_irq_state which, bool state); #ifdef CONFIG_IRQ_FORCED_THREADING +# ifdef CONFIG_PREEMPT_RT_BASE +# define force_irqthreads (true) +# else extern bool force_irqthreads; +# endif #else #define force_irqthreads (0) #endif @@ -493,9 +505,10 @@ struct softirq_action void (*action)(struct softirq_action *); }; +#ifndef CONFIG_PREEMPT_RT_FULL asmlinkage void do_softirq(void); asmlinkage void __do_softirq(void); - +static inline void thread_do_softirq(void) { do_softirq(); } #ifdef __ARCH_HAS_DO_SOFTIRQ void do_softirq_own_stack(void); #else @@ -504,13 +517,25 @@ static inline void do_softirq_own_stack(void) __do_softirq(); } #endif +#else +extern void thread_do_softirq(void); +#endif extern void open_softirq(int nr, void (*action)(struct softirq_action *)); extern void softirq_init(void); extern void __raise_softirq_irqoff(unsigned int nr); +#ifdef CONFIG_PREEMPT_RT_FULL +extern void __raise_softirq_irqoff_ksoft(unsigned int nr); +#else +static inline void __raise_softirq_irqoff_ksoft(unsigned int nr) +{ + __raise_softirq_irqoff(nr); +} +#endif extern void raise_softirq_irqoff(unsigned int nr); extern void raise_softirq(unsigned int nr); +extern void softirq_check_pending_idle(void); DECLARE_PER_CPU(struct task_struct *, ksoftirqd); @@ -532,8 +557,9 @@ static inline struct task_struct *this_cpu_ksoftirqd(void) to be executed on some cpu at least once after this. * If the tasklet is already scheduled, but its execution is still not started, it will be executed only once. - * If this tasklet is already running on another CPU (or schedule is called - from tasklet itself), it is rescheduled for later. + * If this tasklet is already running on another CPU, it is rescheduled + for later. + * Schedule must not be called from the tasklet itself (a lockup occurs) * Tasklet is strictly serialized wrt itself, but not wrt another tasklets. If client needs some intertask synchronization, he makes it with spinlocks. @@ -558,27 +584,36 @@ struct tasklet_struct name = { NULL, 0, ATOMIC_INIT(1), func, data } enum { TASKLET_STATE_SCHED, /* Tasklet is scheduled for execution */ - TASKLET_STATE_RUN /* Tasklet is running (SMP only) */ + TASKLET_STATE_RUN, /* Tasklet is running (SMP only) */ + TASKLET_STATE_PENDING /* Tasklet is pending */ }; -#ifdef CONFIG_SMP +#define TASKLET_STATEF_SCHED (1 << TASKLET_STATE_SCHED) +#define TASKLET_STATEF_RUN (1 << TASKLET_STATE_RUN) +#define TASKLET_STATEF_PENDING (1 << TASKLET_STATE_PENDING) + +#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL) static inline int tasklet_trylock(struct tasklet_struct *t) { return !test_and_set_bit(TASKLET_STATE_RUN, &(t)->state); } +static inline int tasklet_tryunlock(struct tasklet_struct *t) +{ + return cmpxchg(&t->state, TASKLET_STATEF_RUN, 0) == TASKLET_STATEF_RUN; +} + static inline void tasklet_unlock(struct tasklet_struct *t) { smp_mb__before_atomic(); clear_bit(TASKLET_STATE_RUN, &(t)->state); } -static inline void tasklet_unlock_wait(struct tasklet_struct *t) -{ - while (test_bit(TASKLET_STATE_RUN, &(t)->state)) { barrier(); } -} +extern void tasklet_unlock_wait(struct tasklet_struct *t); + #else #define tasklet_trylock(t) 1 +#define tasklet_tryunlock(t) 1 #define tasklet_unlock_wait(t) do { } while (0) #define tasklet_unlock(t) do { } while (0) #endif @@ -612,17 +647,18 @@ static inline void tasklet_disable(struct tasklet_struct *t) smp_mb(); } -static inline void tasklet_enable(struct tasklet_struct *t) -{ - smp_mb__before_atomic(); - atomic_dec(&t->count); -} - +extern void tasklet_enable(struct tasklet_struct *t); extern void tasklet_kill(struct tasklet_struct *t); extern void tasklet_kill_immediate(struct tasklet_struct *t, unsigned int cpu); extern void tasklet_init(struct tasklet_struct *t, void (*func)(unsigned long), unsigned long data); +#ifdef CONFIG_PREEMPT_RT_FULL +extern void softirq_early_init(void); +#else +static inline void softirq_early_init(void) { } +#endif + struct tasklet_hrtimer { struct hrtimer timer; struct tasklet_struct tasklet; diff --git a/include/linux/irq.h b/include/linux/irq.h index c9bffda04a45..73d3146db74d 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -69,6 +69,7 @@ enum irqchip_irq_state; * IRQ_IS_POLLED - Always polled by another interrupt. Exclude * it from the spurious interrupt detection * mechanism and from core side polling. + * IRQ_NO_SOFTIRQ_CALL - No softirq processing in the irq thread context (RT) * IRQ_DISABLE_UNLAZY - Disable lazy irq disable */ enum { @@ -96,13 +97,14 @@ enum { IRQ_PER_CPU_DEVID = (1 << 17), IRQ_IS_POLLED = (1 << 18), IRQ_DISABLE_UNLAZY = (1 << 19), + IRQ_NO_SOFTIRQ_CALL = (1 << 20), }; #define IRQF_MODIFY_MASK \ (IRQ_TYPE_SENSE_MASK | IRQ_NOPROBE | IRQ_NOREQUEST | \ IRQ_NOAUTOEN | IRQ_MOVE_PCNTXT | IRQ_LEVEL | IRQ_NO_BALANCING | \ IRQ_PER_CPU | IRQ_NESTED_THREAD | IRQ_NOTHREAD | IRQ_PER_CPU_DEVID | \ - IRQ_IS_POLLED | IRQ_DISABLE_UNLAZY) + IRQ_IS_POLLED | IRQ_DISABLE_UNLAZY | IRQ_NO_SOFTIRQ_CALL) #define IRQ_NO_BALANCING_MASK (IRQ_PER_CPU | IRQ_NO_BALANCING) diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h index b11fcdfd0770..0c50559987c5 100644 --- a/include/linux/irq_work.h +++ b/include/linux/irq_work.h @@ -18,6 +18,8 @@ /* Doesn't want IPI, wait for tick: */ #define IRQ_WORK_LAZY BIT(2) +/* Run hard IRQ context, even on RT */ +#define IRQ_WORK_HARD_IRQ BIT(3) #define IRQ_WORK_CLAIMED (IRQ_WORK_PENDING | IRQ_WORK_BUSY) @@ -52,4 +54,10 @@ static inline bool irq_work_needs_cpu(void) { return false; } static inline void irq_work_run(void) { } #endif +#if defined(CONFIG_IRQ_WORK) && defined(CONFIG_PREEMPT_RT_FULL) +void irq_work_tick_soft(void); +#else +static inline void irq_work_tick_soft(void) { } +#endif + #endif /* _LINUX_IRQ_WORK_H */ diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 72ed08d9e1b5..56295a0fb1db 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -574,6 +574,7 @@ struct rdists { void __iomem *rd_base; struct page *pend_page; phys_addr_t phys_base; + bool lpi_enabled; } __percpu *rdist; struct page *prop_page; int id_bits; diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index 1d679feff3f6..928229da36e4 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -72,6 +72,7 @@ struct irq_desc { unsigned int irqs_unhandled; atomic_t threads_handled; int threads_handled_last; + u64 random_ip; raw_spinlock_t lock; struct cpumask *percpu_enabled; const struct cpumask *percpu_affinity; diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index 9700f00bbc04..819ea4af3661 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -32,14 +32,6 @@ do { \ do { \ current->hardirq_context--; \ } while (0) -# define lockdep_softirq_enter() \ -do { \ - current->softirq_context++; \ -} while (0) -# define lockdep_softirq_exit() \ -do { \ - current->softirq_context--; \ -} while (0) #else # define trace_hardirqs_on() do { } while (0) # define trace_hardirqs_off() do { } while (0) @@ -55,6 +47,21 @@ do { \ # define lockdep_softirq_exit() do { } while (0) #endif +#if defined(CONFIG_TRACE_IRQFLAGS) && !defined(CONFIG_PREEMPT_RT_FULL) +# define lockdep_softirq_enter() \ +do { \ + current->softirq_context++; \ +} while (0) +# define lockdep_softirq_exit() \ +do { \ + current->softirq_context--; \ +} while (0) + +#else +# define lockdep_softirq_enter() do { } while (0) +# define lockdep_softirq_exit() do { } while (0) +#endif + #if defined(CONFIG_IRQSOFF_TRACER) || \ defined(CONFIG_PREEMPT_TRACER) extern void stop_critical_timings(void); diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 583b82b5a1e9..57f4ad8d45a5 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -347,32 +347,56 @@ static inline struct journal_head *bh2jh(struct buffer_head *bh) static inline void jbd_lock_bh_state(struct buffer_head *bh) { +#ifndef CONFIG_PREEMPT_RT_BASE bit_spin_lock(BH_State, &bh->b_state); +#else + spin_lock(&bh->b_state_lock); +#endif } static inline int jbd_trylock_bh_state(struct buffer_head *bh) { +#ifndef CONFIG_PREEMPT_RT_BASE return bit_spin_trylock(BH_State, &bh->b_state); +#else + return spin_trylock(&bh->b_state_lock); +#endif } static inline int jbd_is_locked_bh_state(struct buffer_head *bh) { +#ifndef CONFIG_PREEMPT_RT_BASE return bit_spin_is_locked(BH_State, &bh->b_state); +#else + return spin_is_locked(&bh->b_state_lock); +#endif } static inline void jbd_unlock_bh_state(struct buffer_head *bh) { +#ifndef CONFIG_PREEMPT_RT_BASE bit_spin_unlock(BH_State, &bh->b_state); +#else + spin_unlock(&bh->b_state_lock); +#endif } static inline void jbd_lock_bh_journal_head(struct buffer_head *bh) { +#ifndef CONFIG_PREEMPT_RT_BASE bit_spin_lock(BH_JournalHead, &bh->b_state); +#else + spin_lock(&bh->b_journal_head_lock); +#endif } static inline void jbd_unlock_bh_journal_head(struct buffer_head *bh) { +#ifndef CONFIG_PREEMPT_RT_BASE bit_spin_unlock(BH_JournalHead, &bh->b_state); +#else + spin_unlock(&bh->b_journal_head_lock); +#endif } #define J_ASSERT(assert) BUG_ON(!(assert)) diff --git a/include/linux/kdb.h b/include/linux/kdb.h index 68bd88223417..e033b25b0b72 100644 --- a/include/linux/kdb.h +++ b/include/linux/kdb.h @@ -167,6 +167,7 @@ extern __printf(2, 0) int vkdb_printf(enum kdb_msgsrc src, const char *fmt, extern __printf(1, 2) int kdb_printf(const char *, ...); typedef __printf(1, 2) int (*kdb_printf_t)(const char *, ...); +#define in_kdb_printk() (kdb_trap_printk) extern void kdb_init(int level); /* Access to kdb specific polling devices */ @@ -201,6 +202,7 @@ extern int kdb_register_flags(char *, kdb_func_t, char *, char *, extern int kdb_unregister(char *); #else /* ! CONFIG_KGDB_KDB */ static inline __printf(1, 2) int kdb_printf(const char *fmt, ...) { return 0; } +#define in_kdb_printk() (0) static inline void kdb_init(int level) {} static inline int kdb_register(char *cmd, kdb_func_t func, char *usage, char *help, short minlen) { return 0; } diff --git a/include/linux/kernel.h b/include/linux/kernel.h index edf6a995ce01..05cccf18a6db 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -226,6 +226,9 @@ extern int _cond_resched(void); */ # define might_sleep() \ do { __might_sleep(__FILE__, __LINE__, 0); might_resched(); } while (0) + +# define might_sleep_no_state_check() \ + do { ___might_sleep(__FILE__, __LINE__, 0); might_resched(); } while (0) # define sched_annotate_sleep() (current->task_state_change = 0) #else static inline void ___might_sleep(const char *file, int line, @@ -233,6 +236,7 @@ extern int _cond_resched(void); static inline void __might_sleep(const char *file, int line, int preempt_offset) { } # define might_sleep() do { might_resched(); } while (0) +# define might_sleep_no_state_check() do { might_resched(); } while (0) # define sched_annotate_sleep() do { } while (0) #endif diff --git a/include/linux/kthread.h b/include/linux/kthread.h index c1961761311d..ad292898f7f2 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -85,7 +85,7 @@ enum { struct kthread_worker { unsigned int flags; - spinlock_t lock; + raw_spinlock_t lock; struct list_head work_list; struct list_head delayed_work_list; struct task_struct *task; diff --git a/include/linux/libata.h b/include/linux/libata.h index bc4f87cbe7f4..b947f5ef68cc 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1858,8 +1858,6 @@ extern unsigned int ata_sff_data_xfer(struct ata_queued_cmd *qc, unsigned char *buf, unsigned int buflen, int rw); extern unsigned int ata_sff_data_xfer32(struct ata_queued_cmd *qc, unsigned char *buf, unsigned int buflen, int rw); -extern unsigned int ata_sff_data_xfer_noirq(struct ata_queued_cmd *qc, - unsigned char *buf, unsigned int buflen, int rw); extern void ata_sff_irq_on(struct ata_port *ap); extern void ata_sff_irq_clear(struct ata_port *ap); extern int ata_sff_hsm_move(struct ata_port *ap, struct ata_queued_cmd *qc, diff --git a/include/linux/list_bl.h b/include/linux/list_bl.h index 3fc2cc57ba1b..0b5de7d9ffcf 100644 --- a/include/linux/list_bl.h +++ b/include/linux/list_bl.h @@ -3,6 +3,7 @@ #define _LINUX_LIST_BL_H #include <linux/list.h> +#include <linux/spinlock.h> #include <linux/bit_spinlock.h> /* @@ -33,13 +34,24 @@ struct hlist_bl_head { struct hlist_bl_node *first; +#ifdef CONFIG_PREEMPT_RT_BASE + raw_spinlock_t lock; +#endif }; struct hlist_bl_node { struct hlist_bl_node *next, **pprev; }; -#define INIT_HLIST_BL_HEAD(ptr) \ - ((ptr)->first = NULL) + +#ifdef CONFIG_PREEMPT_RT_BASE +#define INIT_HLIST_BL_HEAD(h) \ +do { \ + (h)->first = NULL; \ + raw_spin_lock_init(&(h)->lock); \ +} while (0) +#else +#define INIT_HLIST_BL_HEAD(h) (h)->first = NULL +#endif static inline void INIT_HLIST_BL_NODE(struct hlist_bl_node *h) { @@ -119,12 +131,26 @@ static inline void hlist_bl_del_init(struct hlist_bl_node *n) static inline void hlist_bl_lock(struct hlist_bl_head *b) { +#ifndef CONFIG_PREEMPT_RT_BASE bit_spin_lock(0, (unsigned long *)b); +#else + raw_spin_lock(&b->lock); +#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) + __set_bit(0, (unsigned long *)b); +#endif +#endif } static inline void hlist_bl_unlock(struct hlist_bl_head *b) { +#ifndef CONFIG_PREEMPT_RT_BASE __bit_spin_unlock(0, (unsigned long *)b); +#else +#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) + __clear_bit(0, (unsigned long *)b); +#endif + raw_spin_unlock(&b->lock); +#endif } static inline bool hlist_bl_is_locked(struct hlist_bl_head *b) diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h index c1c5c13762a6..009eace6a3f1 100644 --- a/include/linux/list_lru.h +++ b/include/linux/list_lru.h @@ -163,6 +163,23 @@ unsigned long list_lru_walk_one(struct list_lru *lru, int nid, struct mem_cgroup *memcg, list_lru_walk_cb isolate, void *cb_arg, unsigned long *nr_to_walk); +/** + * list_lru_walk_one_irq: walk a list_lru, isolating and disposing freeable items. + * @lru: the lru pointer. + * @nid: the node id to scan from. + * @memcg: the cgroup to scan from. + * @isolate: callback function that is resposible for deciding what to do with + * the item currently being scanned + * @cb_arg: opaque type that will be passed to @isolate + * @nr_to_walk: how many items to scan. + * + * Same as @list_lru_walk_one except that the spinlock is acquired with + * spin_lock_irq(). + */ +unsigned long list_lru_walk_one_irq(struct list_lru *lru, + int nid, struct mem_cgroup *memcg, + list_lru_walk_cb isolate, void *cb_arg, + unsigned long *nr_to_walk); unsigned long list_lru_walk_node(struct list_lru *lru, int nid, list_lru_walk_cb isolate, void *cb_arg, unsigned long *nr_to_walk); @@ -176,6 +193,14 @@ list_lru_shrink_walk(struct list_lru *lru, struct shrink_control *sc, } static inline unsigned long +list_lru_shrink_walk_irq(struct list_lru *lru, struct shrink_control *sc, + list_lru_walk_cb isolate, void *cb_arg) +{ + return list_lru_walk_one_irq(lru, sc->nid, sc->memcg, isolate, cb_arg, + &sc->nr_to_scan); +} + +static inline unsigned long list_lru_walk(struct list_lru *lru, list_lru_walk_cb isolate, void *cb_arg, unsigned long nr_to_walk) { diff --git a/include/linux/locallock.h b/include/linux/locallock.h new file mode 100644 index 000000000000..921eab83cd34 --- /dev/null +++ b/include/linux/locallock.h @@ -0,0 +1,281 @@ +#ifndef _LINUX_LOCALLOCK_H +#define _LINUX_LOCALLOCK_H + +#include <linux/percpu.h> +#include <linux/spinlock.h> + +#ifdef CONFIG_PREEMPT_RT_BASE + +#ifdef CONFIG_DEBUG_SPINLOCK +# define LL_WARN(cond) WARN_ON(cond) +#else +# define LL_WARN(cond) do { } while (0) +#endif + +/* + * per cpu lock based substitute for local_irq_*() + */ +struct local_irq_lock { + spinlock_t lock; + struct task_struct *owner; + int nestcnt; + unsigned long flags; +}; + +#define DEFINE_LOCAL_IRQ_LOCK(lvar) \ + DEFINE_PER_CPU(struct local_irq_lock, lvar) = { \ + .lock = __SPIN_LOCK_UNLOCKED((lvar).lock) } + +#define DECLARE_LOCAL_IRQ_LOCK(lvar) \ + DECLARE_PER_CPU(struct local_irq_lock, lvar) + +#define local_irq_lock_init(lvar) \ + do { \ + int __cpu; \ + for_each_possible_cpu(__cpu) \ + spin_lock_init(&per_cpu(lvar, __cpu).lock); \ + } while (0) + +static inline void __local_lock(struct local_irq_lock *lv) +{ + if (lv->owner != current) { + spin_lock(&lv->lock); + LL_WARN(lv->owner); + LL_WARN(lv->nestcnt); + lv->owner = current; + } + lv->nestcnt++; +} + +#define local_lock(lvar) \ + do { __local_lock(&get_local_var(lvar)); } while (0) + +#define local_lock_on(lvar, cpu) \ + do { __local_lock(&per_cpu(lvar, cpu)); } while (0) + +static inline int __local_trylock(struct local_irq_lock *lv) +{ + if (lv->owner != current && spin_trylock(&lv->lock)) { + LL_WARN(lv->owner); + LL_WARN(lv->nestcnt); + lv->owner = current; + lv->nestcnt = 1; + return 1; + } else if (lv->owner == current) { + lv->nestcnt++; + return 1; + } + return 0; +} + +#define local_trylock(lvar) \ + ({ \ + int __locked; \ + __locked = __local_trylock(&get_local_var(lvar)); \ + if (!__locked) \ + put_local_var(lvar); \ + __locked; \ + }) + +static inline void __local_unlock(struct local_irq_lock *lv) +{ + LL_WARN(lv->nestcnt == 0); + LL_WARN(lv->owner != current); + if (--lv->nestcnt) + return; + + lv->owner = NULL; + spin_unlock(&lv->lock); +} + +#define local_unlock(lvar) \ + do { \ + __local_unlock(this_cpu_ptr(&lvar)); \ + put_local_var(lvar); \ + } while (0) + +#define local_unlock_on(lvar, cpu) \ + do { __local_unlock(&per_cpu(lvar, cpu)); } while (0) + +static inline void __local_lock_irq(struct local_irq_lock *lv) +{ + spin_lock_irqsave(&lv->lock, lv->flags); + LL_WARN(lv->owner); + LL_WARN(lv->nestcnt); + lv->owner = current; + lv->nestcnt = 1; +} + +#define local_lock_irq(lvar) \ + do { __local_lock_irq(&get_local_var(lvar)); } while (0) + +#define local_lock_irq_on(lvar, cpu) \ + do { __local_lock_irq(&per_cpu(lvar, cpu)); } while (0) + +static inline void __local_unlock_irq(struct local_irq_lock *lv) +{ + LL_WARN(!lv->nestcnt); + LL_WARN(lv->owner != current); + lv->owner = NULL; + lv->nestcnt = 0; + spin_unlock_irq(&lv->lock); +} + +#define local_unlock_irq(lvar) \ + do { \ + __local_unlock_irq(this_cpu_ptr(&lvar)); \ + put_local_var(lvar); \ + } while (0) + +#define local_unlock_irq_on(lvar, cpu) \ + do { \ + __local_unlock_irq(&per_cpu(lvar, cpu)); \ + } while (0) + +static inline int __local_lock_irqsave(struct local_irq_lock *lv) +{ + if (lv->owner != current) { + __local_lock_irq(lv); + return 0; + } else { + lv->nestcnt++; + return 1; + } +} + +#define local_lock_irqsave(lvar, _flags) \ + do { \ + if (__local_lock_irqsave(&get_local_var(lvar))) \ + put_local_var(lvar); \ + _flags = __this_cpu_read(lvar.flags); \ + } while (0) + +#define local_lock_irqsave_on(lvar, _flags, cpu) \ + do { \ + __local_lock_irqsave(&per_cpu(lvar, cpu)); \ + _flags = per_cpu(lvar, cpu).flags; \ + } while (0) + +static inline int __local_unlock_irqrestore(struct local_irq_lock *lv, + unsigned long flags) +{ + LL_WARN(!lv->nestcnt); + LL_WARN(lv->owner != current); + if (--lv->nestcnt) + return 0; + + lv->owner = NULL; + spin_unlock_irqrestore(&lv->lock, lv->flags); + return 1; +} + +#define local_unlock_irqrestore(lvar, flags) \ + do { \ + if (__local_unlock_irqrestore(this_cpu_ptr(&lvar), flags)) \ + put_local_var(lvar); \ + } while (0) + +#define local_unlock_irqrestore_on(lvar, flags, cpu) \ + do { \ + __local_unlock_irqrestore(&per_cpu(lvar, cpu), flags); \ + } while (0) + +#define local_spin_trylock_irq(lvar, lock) \ + ({ \ + int __locked; \ + local_lock_irq(lvar); \ + __locked = spin_trylock(lock); \ + if (!__locked) \ + local_unlock_irq(lvar); \ + __locked; \ + }) + +#define local_spin_lock_irq(lvar, lock) \ + do { \ + local_lock_irq(lvar); \ + spin_lock(lock); \ + } while (0) + +#define local_spin_unlock_irq(lvar, lock) \ + do { \ + spin_unlock(lock); \ + local_unlock_irq(lvar); \ + } while (0) + +#define local_spin_lock_irqsave(lvar, lock, flags) \ + do { \ + local_lock_irqsave(lvar, flags); \ + spin_lock(lock); \ + } while (0) + +#define local_spin_unlock_irqrestore(lvar, lock, flags) \ + do { \ + spin_unlock(lock); \ + local_unlock_irqrestore(lvar, flags); \ + } while (0) + +#define get_locked_var(lvar, var) \ + (*({ \ + local_lock(lvar); \ + this_cpu_ptr(&var); \ + })) + +#define put_locked_var(lvar, var) local_unlock(lvar); + +#define get_locked_ptr(lvar, var) \ + ({ \ + local_lock(lvar); \ + this_cpu_ptr(var); \ + }) + +#define put_locked_ptr(lvar, var) local_unlock(lvar); + +#define local_lock_cpu(lvar) \ + ({ \ + local_lock(lvar); \ + smp_processor_id(); \ + }) + +#define local_unlock_cpu(lvar) local_unlock(lvar) + +#else /* PREEMPT_RT_BASE */ + +#define DEFINE_LOCAL_IRQ_LOCK(lvar) __typeof__(const int) lvar +#define DECLARE_LOCAL_IRQ_LOCK(lvar) extern __typeof__(const int) lvar + +static inline void local_irq_lock_init(int lvar) { } + +#define local_trylock(lvar) \ + ({ \ + preempt_disable(); \ + 1; \ + }) + +#define local_lock(lvar) preempt_disable() +#define local_unlock(lvar) preempt_enable() +#define local_lock_irq(lvar) local_irq_disable() +#define local_lock_irq_on(lvar, cpu) local_irq_disable() +#define local_unlock_irq(lvar) local_irq_enable() +#define local_unlock_irq_on(lvar, cpu) local_irq_enable() +#define local_lock_irqsave(lvar, flags) local_irq_save(flags) +#define local_unlock_irqrestore(lvar, flags) local_irq_restore(flags) + +#define local_spin_trylock_irq(lvar, lock) spin_trylock_irq(lock) +#define local_spin_lock_irq(lvar, lock) spin_lock_irq(lock) +#define local_spin_unlock_irq(lvar, lock) spin_unlock_irq(lock) +#define local_spin_lock_irqsave(lvar, lock, flags) \ + spin_lock_irqsave(lock, flags) +#define local_spin_unlock_irqrestore(lvar, lock, flags) \ + spin_unlock_irqrestore(lock, flags) + +#define get_locked_var(lvar, var) get_cpu_var(var) +#define put_locked_var(lvar, var) put_cpu_var(var) +#define get_locked_ptr(lvar, var) get_cpu_ptr(var) +#define put_locked_ptr(lvar, var) put_cpu_ptr(var) + +#define local_lock_cpu(lvar) get_cpu() +#define local_unlock_cpu(lvar) put_cpu() + +#endif + +#endif diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index b39c68e9ddc9..7730c19f2747 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -12,6 +12,7 @@ #include <linux/completion.h> #include <linux/cpumask.h> #include <linux/uprobes.h> +#include <linux/rcupdate.h> #include <linux/page-flags-layout.h> #include <linux/workqueue.h> @@ -485,6 +486,9 @@ struct mm_struct { bool tlb_flush_batched; #endif struct uprobes_state uprobes_state; +#ifdef CONFIG_PREEMPT_RT_BASE + struct rcu_head delayed_drop; +#endif #ifdef CONFIG_HUGETLB_PAGE atomic_long_t hugetlb_usage; #endif diff --git a/include/linux/mutex.h b/include/linux/mutex.h index 3093dd162424..cad906f54d0a 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -22,6 +22,17 @@ struct ww_acquire_ctx; +#ifdef CONFIG_DEBUG_LOCK_ALLOC +# define __DEP_MAP_MUTEX_INITIALIZER(lockname) \ + , .dep_map = { .name = #lockname } +#else +# define __DEP_MAP_MUTEX_INITIALIZER(lockname) +#endif + +#ifdef CONFIG_PREEMPT_RT_FULL +# include <linux/mutex_rt.h> +#else + /* * Simple, straightforward mutexes with strict semantics: * @@ -118,13 +129,6 @@ do { \ __mutex_init((mutex), #mutex, &__key); \ } while (0) -#ifdef CONFIG_DEBUG_LOCK_ALLOC -# define __DEP_MAP_MUTEX_INITIALIZER(lockname) \ - , .dep_map = { .name = #lockname } -#else -# define __DEP_MAP_MUTEX_INITIALIZER(lockname) -#endif - #define __MUTEX_INITIALIZER(lockname) \ { .owner = ATOMIC_LONG_INIT(0) \ , .wait_lock = __SPIN_LOCK_UNLOCKED(lockname.wait_lock) \ @@ -229,4 +233,6 @@ mutex_trylock_recursive(struct mutex *lock) return mutex_trylock(lock); } +#endif /* !PREEMPT_RT_FULL */ + #endif /* __LINUX_MUTEX_H */ diff --git a/include/linux/mutex_rt.h b/include/linux/mutex_rt.h new file mode 100644 index 000000000000..3fcb5edb1d2b --- /dev/null +++ b/include/linux/mutex_rt.h @@ -0,0 +1,130 @@ +#ifndef __LINUX_MUTEX_RT_H +#define __LINUX_MUTEX_RT_H + +#ifndef __LINUX_MUTEX_H +#error "Please include mutex.h" +#endif + +#include <linux/rtmutex.h> + +/* FIXME: Just for __lockfunc */ +#include <linux/spinlock.h> + +struct mutex { + struct rt_mutex lock; +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map dep_map; +#endif +}; + +#define __MUTEX_INITIALIZER(mutexname) \ + { \ + .lock = __RT_MUTEX_INITIALIZER(mutexname.lock) \ + __DEP_MAP_MUTEX_INITIALIZER(mutexname) \ + } + +#define DEFINE_MUTEX(mutexname) \ + struct mutex mutexname = __MUTEX_INITIALIZER(mutexname) + +extern void __mutex_do_init(struct mutex *lock, const char *name, struct lock_class_key *key); +extern void __lockfunc _mutex_lock(struct mutex *lock); +extern void __lockfunc _mutex_lock_io(struct mutex *lock); +extern void __lockfunc _mutex_lock_io_nested(struct mutex *lock, int subclass); +extern int __lockfunc _mutex_lock_interruptible(struct mutex *lock); +extern int __lockfunc _mutex_lock_killable(struct mutex *lock); +extern void __lockfunc _mutex_lock_nested(struct mutex *lock, int subclass); +extern void __lockfunc _mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest_lock); +extern int __lockfunc _mutex_lock_interruptible_nested(struct mutex *lock, int subclass); +extern int __lockfunc _mutex_lock_killable_nested(struct mutex *lock, int subclass); +extern int __lockfunc _mutex_trylock(struct mutex *lock); +extern void __lockfunc _mutex_unlock(struct mutex *lock); + +#define mutex_is_locked(l) rt_mutex_is_locked(&(l)->lock) +#define mutex_lock(l) _mutex_lock(l) +#define mutex_lock_interruptible(l) _mutex_lock_interruptible(l) +#define mutex_lock_killable(l) _mutex_lock_killable(l) +#define mutex_trylock(l) _mutex_trylock(l) +#define mutex_unlock(l) _mutex_unlock(l) +#define mutex_lock_io(l) _mutex_lock_io(l); + +#define __mutex_owner(l) ((l)->lock.owner) + +#ifdef CONFIG_DEBUG_MUTEXES +#define mutex_destroy(l) rt_mutex_destroy(&(l)->lock) +#else +static inline void mutex_destroy(struct mutex *lock) {} +#endif + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +# define mutex_lock_nested(l, s) _mutex_lock_nested(l, s) +# define mutex_lock_interruptible_nested(l, s) \ + _mutex_lock_interruptible_nested(l, s) +# define mutex_lock_killable_nested(l, s) \ + _mutex_lock_killable_nested(l, s) +# define mutex_lock_io_nested(l, s) _mutex_lock_io_nested(l, s) + +# define mutex_lock_nest_lock(lock, nest_lock) \ +do { \ + typecheck(struct lockdep_map *, &(nest_lock)->dep_map); \ + _mutex_lock_nest_lock(lock, &(nest_lock)->dep_map); \ +} while (0) + +#else +# define mutex_lock_nested(l, s) _mutex_lock(l) +# define mutex_lock_interruptible_nested(l, s) \ + _mutex_lock_interruptible(l) +# define mutex_lock_killable_nested(l, s) \ + _mutex_lock_killable(l) +# define mutex_lock_nest_lock(lock, nest_lock) mutex_lock(lock) +# define mutex_lock_io_nested(l, s) _mutex_lock_io(l) +#endif + +# define mutex_init(mutex) \ +do { \ + static struct lock_class_key __key; \ + \ + rt_mutex_init(&(mutex)->lock); \ + __mutex_do_init((mutex), #mutex, &__key); \ +} while (0) + +# define __mutex_init(mutex, name, key) \ +do { \ + rt_mutex_init(&(mutex)->lock); \ + __mutex_do_init((mutex), name, key); \ +} while (0) + +/** + * These values are chosen such that FAIL and SUCCESS match the + * values of the regular mutex_trylock(). + */ +enum mutex_trylock_recursive_enum { + MUTEX_TRYLOCK_FAILED = 0, + MUTEX_TRYLOCK_SUCCESS = 1, + MUTEX_TRYLOCK_RECURSIVE, +}; +/** + * mutex_trylock_recursive - trylock variant that allows recursive locking + * @lock: mutex to be locked + * + * This function should not be used, _ever_. It is purely for hysterical GEM + * raisins, and once those are gone this will be removed. + * + * Returns: + * MUTEX_TRYLOCK_FAILED - trylock failed, + * MUTEX_TRYLOCK_SUCCESS - lock acquired, + * MUTEX_TRYLOCK_RECURSIVE - we already owned the lock. + */ +int __rt_mutex_owner_current(struct rt_mutex *lock); + +static inline /* __deprecated */ __must_check enum mutex_trylock_recursive_enum +mutex_trylock_recursive(struct mutex *lock) +{ + if (unlikely(__rt_mutex_owner_current(&lock->lock))) + return MUTEX_TRYLOCK_RECURSIVE; + + return mutex_trylock(lock); +} + +extern int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock); + +#endif diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 89777b9c1f0a..2e5800802bdb 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -411,7 +411,19 @@ typedef enum rx_handler_result rx_handler_result_t; typedef rx_handler_result_t rx_handler_func_t(struct sk_buff **pskb); void __napi_schedule(struct napi_struct *n); + +/* + * When PREEMPT_RT_FULL is defined, all device interrupt handlers + * run as threads, and they can also be preempted (without PREEMPT_RT + * interrupt threads can not be preempted). Which means that calling + * __napi_schedule_irqoff() from an interrupt handler can be preempted + * and can corrupt the napi->poll_list. + */ +#ifdef CONFIG_PREEMPT_RT_FULL +#define __napi_schedule_irqoff(n) __napi_schedule(n) +#else void __napi_schedule_irqoff(struct napi_struct *n); +#endif static inline bool napi_disable_pending(struct napi_struct *n) { @@ -573,7 +585,11 @@ struct netdev_queue { * write-mostly part */ spinlock_t _xmit_lock ____cacheline_aligned_in_smp; +#ifdef CONFIG_PREEMPT_RT_FULL + struct task_struct *xmit_lock_owner; +#else int xmit_lock_owner; +#endif /* * Time (in jiffies) of last Tx */ @@ -2567,14 +2583,53 @@ void netdev_freemem(struct net_device *dev); void synchronize_net(void); int init_dummy_netdev(struct net_device *dev); -DECLARE_PER_CPU(int, xmit_recursion); #define XMIT_RECURSION_LIMIT 10 +#ifdef CONFIG_PREEMPT_RT_FULL +static inline int dev_recursion_level(void) +{ + return current->xmit_recursion; +} + +static inline int xmit_rec_read(void) +{ + return current->xmit_recursion; +} + +static inline void xmit_rec_inc(void) +{ + current->xmit_recursion++; +} + +static inline void xmit_rec_dec(void) +{ + current->xmit_recursion--; +} + +#else + +DECLARE_PER_CPU(int, xmit_recursion); static inline int dev_recursion_level(void) { return this_cpu_read(xmit_recursion); } +static inline int xmit_rec_read(void) +{ + return __this_cpu_read(xmit_recursion); +} + +static inline void xmit_rec_inc(void) +{ + __this_cpu_inc(xmit_recursion); +} + +static inline void xmit_rec_dec(void) +{ + __this_cpu_dec(xmit_recursion); +} +#endif + struct net_device *dev_get_by_index(struct net *net, int ifindex); struct net_device *__dev_get_by_index(struct net *net, int ifindex); struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex); @@ -2929,6 +2984,7 @@ struct softnet_data { unsigned int dropped; struct sk_buff_head input_pkt_queue; struct napi_struct backlog; + struct sk_buff_head tofree_queue; }; @@ -3651,10 +3707,48 @@ static inline u32 netif_msg_init(int debug_value, int default_msg_enable_bits) return (1 << debug_value) - 1; } +#ifdef CONFIG_PREEMPT_RT_FULL +static inline void netdev_queue_set_owner(struct netdev_queue *txq, int cpu) +{ + txq->xmit_lock_owner = current; +} + +static inline void netdev_queue_clear_owner(struct netdev_queue *txq) +{ + txq->xmit_lock_owner = NULL; +} + +static inline bool netdev_queue_has_owner(struct netdev_queue *txq) +{ + if (txq->xmit_lock_owner != NULL) + return true; + return false; +} + +#else + +static inline void netdev_queue_set_owner(struct netdev_queue *txq, int cpu) +{ + txq->xmit_lock_owner = cpu; +} + +static inline void netdev_queue_clear_owner(struct netdev_queue *txq) +{ + txq->xmit_lock_owner = -1; +} + +static inline bool netdev_queue_has_owner(struct netdev_queue *txq) +{ + if (txq->xmit_lock_owner != -1) + return true; + return false; +} +#endif + static inline void __netif_tx_lock(struct netdev_queue *txq, int cpu) { spin_lock(&txq->_xmit_lock); - txq->xmit_lock_owner = cpu; + netdev_queue_set_owner(txq, cpu); } static inline bool __netif_tx_acquire(struct netdev_queue *txq) @@ -3671,32 +3765,32 @@ static inline void __netif_tx_release(struct netdev_queue *txq) static inline void __netif_tx_lock_bh(struct netdev_queue *txq) { spin_lock_bh(&txq->_xmit_lock); - txq->xmit_lock_owner = smp_processor_id(); + netdev_queue_set_owner(txq, smp_processor_id()); } static inline bool __netif_tx_trylock(struct netdev_queue *txq) { bool ok = spin_trylock(&txq->_xmit_lock); if (likely(ok)) - txq->xmit_lock_owner = smp_processor_id(); + netdev_queue_set_owner(txq, smp_processor_id()); return ok; } static inline void __netif_tx_unlock(struct netdev_queue *txq) { - txq->xmit_lock_owner = -1; + netdev_queue_clear_owner(txq); spin_unlock(&txq->_xmit_lock); } static inline void __netif_tx_unlock_bh(struct netdev_queue *txq) { - txq->xmit_lock_owner = -1; + netdev_queue_clear_owner(txq); spin_unlock_bh(&txq->_xmit_lock); } static inline void txq_trans_update(struct netdev_queue *txq) { - if (txq->xmit_lock_owner != -1) + if (netdev_queue_has_owner(txq)) txq->trans_start = jiffies; } diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 9077b3ebea08..1710f2aff350 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -6,6 +6,7 @@ #include <linux/netdevice.h> #include <linux/static_key.h> #include <linux/netfilter.h> +#include <linux/locallock.h> #include <uapi/linux/netfilter/x_tables.h> /* Test a struct->invflags and a boolean for inequality */ @@ -345,6 +346,8 @@ void xt_free_table_info(struct xt_table_info *info); */ DECLARE_PER_CPU(seqcount_t, xt_recseq); +DECLARE_LOCAL_IRQ_LOCK(xt_write_lock); + /* xt_tee_enabled - true if x_tables needs to handle reentrancy * * Enabled if current ip(6)tables ruleset has at least one -j TEE rule. @@ -365,6 +368,9 @@ static inline unsigned int xt_write_recseq_begin(void) { unsigned int addend; + /* RT protection */ + local_lock(xt_write_lock); + /* * Low order bit of sequence is set if we already * called xt_write_recseq_begin(). @@ -395,6 +401,7 @@ static inline void xt_write_recseq_end(unsigned int addend) /* this is kind of a write_seqcount_end(), but addend is 0 or 1 */ smp_wmb(); __this_cpu_add(xt_recseq.sequence, addend); + local_unlock(xt_write_lock); } /* diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 2f129bbfaae8..e5d6b89b0674 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -163,7 +163,11 @@ struct nfs_inode { /* Readers: in-flight sillydelete RPC calls */ /* Writers: rmdir */ +#ifdef CONFIG_PREEMPT_RT_BASE + struct semaphore rmdir_sem; +#else struct rw_semaphore rmdir_sem; +#endif struct mutex commit_mutex; #if IS_ENABLED(CONFIG_NFS_V4) diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index cfa7931e19d6..b261b317d14e 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1536,7 +1536,7 @@ struct nfs_unlinkdata { struct nfs_removeargs args; struct nfs_removeres res; struct dentry *dentry; - wait_queue_head_t wq; + struct swait_queue_head wq; struct rpc_cred *cred; struct nfs_fattr dir_attr; long timeout; diff --git a/include/linux/percpu-rwsem.h b/include/linux/percpu-rwsem.h index 79b99d653e03..fb44e237316d 100644 --- a/include/linux/percpu-rwsem.h +++ b/include/linux/percpu-rwsem.h @@ -29,7 +29,7 @@ static struct percpu_rw_semaphore name = { \ extern int __percpu_down_read(struct percpu_rw_semaphore *, int); extern void __percpu_up_read(struct percpu_rw_semaphore *); -static inline void percpu_down_read_preempt_disable(struct percpu_rw_semaphore *sem) +static inline void percpu_down_read(struct percpu_rw_semaphore *sem) { might_sleep(); @@ -47,16 +47,10 @@ static inline void percpu_down_read_preempt_disable(struct percpu_rw_semaphore * __this_cpu_inc(*sem->read_count); if (unlikely(!rcu_sync_is_idle(&sem->rss))) __percpu_down_read(sem, false); /* Unconditional memory barrier */ - barrier(); /* - * The barrier() prevents the compiler from + * The preempt_enable() prevents the compiler from * bleeding the critical section out. */ -} - -static inline void percpu_down_read(struct percpu_rw_semaphore *sem) -{ - percpu_down_read_preempt_disable(sem); preempt_enable(); } @@ -83,13 +77,9 @@ static inline int percpu_down_read_trylock(struct percpu_rw_semaphore *sem) return ret; } -static inline void percpu_up_read_preempt_enable(struct percpu_rw_semaphore *sem) +static inline void percpu_up_read(struct percpu_rw_semaphore *sem) { - /* - * The barrier() prevents the compiler from - * bleeding the critical section out. - */ - barrier(); + preempt_disable(); /* * Same as in percpu_down_read(). */ @@ -102,12 +92,6 @@ static inline void percpu_up_read_preempt_enable(struct percpu_rw_semaphore *sem rwsem_release(&sem->rw_sem.dep_map, 1, _RET_IP_); } -static inline void percpu_up_read(struct percpu_rw_semaphore *sem) -{ - preempt_disable(); - percpu_up_read_preempt_enable(sem); -} - extern void percpu_down_write(struct percpu_rw_semaphore *); extern void percpu_up_write(struct percpu_rw_semaphore *); diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 296bbe49d5d1..4414796e3941 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -19,6 +19,35 @@ #define PERCPU_MODULE_RESERVE 0 #endif +#ifdef CONFIG_PREEMPT_RT_FULL + +#define get_local_var(var) (*({ \ + migrate_disable(); \ + this_cpu_ptr(&var); })) + +#define put_local_var(var) do { \ + (void)&(var); \ + migrate_enable(); \ +} while (0) + +# define get_local_ptr(var) ({ \ + migrate_disable(); \ + this_cpu_ptr(var); }) + +# define put_local_ptr(var) do { \ + (void)(var); \ + migrate_enable(); \ +} while (0) + +#else + +#define get_local_var(var) get_cpu_var(var) +#define put_local_var(var) put_cpu_var(var) +#define get_local_ptr(var) get_cpu_ptr(var) +#define put_local_ptr(var) put_cpu_ptr(var) + +#endif + /* minimum unit size, also is the maximum supported allocation size */ #define PCPU_MIN_UNIT_SIZE PFN_ALIGN(32 << 10) diff --git a/include/linux/pid.h b/include/linux/pid.h index 7633d55d9a24..bb31d4178380 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -3,6 +3,7 @@ #define _LINUX_PID_H #include <linux/rculist.h> +#include <linux/atomic.h> enum pid_type { diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index ee7e987ea1b4..0571b498db73 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -114,8 +114,8 @@ struct k_itimer { struct { struct alarm alarmtimer; } alarm; - struct rcu_head rcu; } it; + struct rcu_head rcu; }; void run_posix_cpu_timers(struct task_struct *task); diff --git a/include/linux/preempt.h b/include/linux/preempt.h index 5bd3f151da78..9e41b8548be8 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -51,7 +51,11 @@ #define HARDIRQ_OFFSET (1UL << HARDIRQ_SHIFT) #define NMI_OFFSET (1UL << NMI_SHIFT) -#define SOFTIRQ_DISABLE_OFFSET (2 * SOFTIRQ_OFFSET) +#ifndef CONFIG_PREEMPT_RT_FULL +# define SOFTIRQ_DISABLE_OFFSET (2 * SOFTIRQ_OFFSET) +#else +# define SOFTIRQ_DISABLE_OFFSET (0) +#endif /* We use the MSB mostly because its available */ #define PREEMPT_NEED_RESCHED 0x80000000 @@ -81,9 +85,15 @@ #include <asm/preempt.h> #define hardirq_count() (preempt_count() & HARDIRQ_MASK) -#define softirq_count() (preempt_count() & SOFTIRQ_MASK) #define irq_count() (preempt_count() & (HARDIRQ_MASK | SOFTIRQ_MASK \ | NMI_MASK)) +#ifndef CONFIG_PREEMPT_RT_FULL +# define softirq_count() (preempt_count() & SOFTIRQ_MASK) +# define in_serving_softirq() (softirq_count() & SOFTIRQ_OFFSET) +#else +# define softirq_count() ((unsigned long)current->softirq_nestcnt) +extern int in_serving_softirq(void); +#endif /* * Are we doing bottom half or hardware interrupt processing? @@ -101,7 +111,6 @@ #define in_irq() (hardirq_count()) #define in_softirq() (softirq_count()) #define in_interrupt() (irq_count()) -#define in_serving_softirq() (softirq_count() & SOFTIRQ_OFFSET) #define in_nmi() (preempt_count() & NMI_MASK) #define in_task() (!(preempt_count() & \ (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET))) @@ -118,7 +127,11 @@ /* * The preempt_count offset after spin_lock() */ +#if !defined(CONFIG_PREEMPT_RT_FULL) #define PREEMPT_LOCK_OFFSET PREEMPT_DISABLE_OFFSET +#else +#define PREEMPT_LOCK_OFFSET 0 +#endif /* * The preempt_count offset needed for things like: @@ -167,6 +180,20 @@ extern void preempt_count_sub(int val); #define preempt_count_inc() preempt_count_add(1) #define preempt_count_dec() preempt_count_sub(1) +#ifdef CONFIG_PREEMPT_LAZY +#define add_preempt_lazy_count(val) do { preempt_lazy_count() += (val); } while (0) +#define sub_preempt_lazy_count(val) do { preempt_lazy_count() -= (val); } while (0) +#define inc_preempt_lazy_count() add_preempt_lazy_count(1) +#define dec_preempt_lazy_count() sub_preempt_lazy_count(1) +#define preempt_lazy_count() (current_thread_info()->preempt_lazy_count) +#else +#define add_preempt_lazy_count(val) do { } while (0) +#define sub_preempt_lazy_count(val) do { } while (0) +#define inc_preempt_lazy_count() do { } while (0) +#define dec_preempt_lazy_count() do { } while (0) +#define preempt_lazy_count() (0) +#endif + #ifdef CONFIG_PREEMPT_COUNT #define preempt_disable() \ @@ -175,16 +202,53 @@ do { \ barrier(); \ } while (0) +#define preempt_lazy_disable() \ +do { \ + inc_preempt_lazy_count(); \ + barrier(); \ +} while (0) + #define sched_preempt_enable_no_resched() \ do { \ barrier(); \ preempt_count_dec(); \ } while (0) -#define preempt_enable_no_resched() sched_preempt_enable_no_resched() +#ifdef CONFIG_PREEMPT_RT_BASE +# define preempt_enable_no_resched() sched_preempt_enable_no_resched() +# define preempt_check_resched_rt() preempt_check_resched() +#else +# define preempt_enable_no_resched() preempt_enable() +# define preempt_check_resched_rt() barrier(); +#endif #define preemptible() (preempt_count() == 0 && !irqs_disabled()) +#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE) + +extern void migrate_disable(void); +extern void migrate_enable(void); + +int __migrate_disabled(struct task_struct *p); + +#elif !defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE) + +extern void migrate_disable(void); +extern void migrate_enable(void); +static inline int __migrate_disabled(struct task_struct *p) +{ + return 0; +} + +#else +#define migrate_disable() preempt_disable() +#define migrate_enable() preempt_enable() +static inline int __migrate_disabled(struct task_struct *p) +{ + return 0; +} +#endif + #ifdef CONFIG_PREEMPT #define preempt_enable() \ do { \ @@ -206,6 +270,13 @@ do { \ __preempt_schedule(); \ } while (0) +#define preempt_lazy_enable() \ +do { \ + dec_preempt_lazy_count(); \ + barrier(); \ + preempt_check_resched(); \ +} while (0) + #else /* !CONFIG_PREEMPT */ #define preempt_enable() \ do { \ @@ -213,6 +284,12 @@ do { \ preempt_count_dec(); \ } while (0) +#define preempt_lazy_enable() \ +do { \ + dec_preempt_lazy_count(); \ + barrier(); \ +} while (0) + #define preempt_enable_notrace() \ do { \ barrier(); \ @@ -251,8 +328,16 @@ do { \ #define preempt_disable_notrace() barrier() #define preempt_enable_no_resched_notrace() barrier() #define preempt_enable_notrace() barrier() +#define preempt_check_resched_rt() barrier() #define preemptible() 0 +#define migrate_disable() barrier() +#define migrate_enable() barrier() + +static inline int __migrate_disabled(struct task_struct *p) +{ + return 0; +} #endif /* CONFIG_PREEMPT_COUNT */ #ifdef MODULE @@ -271,10 +356,22 @@ do { \ } while (0) #define preempt_fold_need_resched() \ do { \ - if (tif_need_resched()) \ + if (tif_need_resched_now()) \ set_preempt_need_resched(); \ } while (0) +#ifdef CONFIG_PREEMPT_RT_FULL +# define preempt_disable_rt() preempt_disable() +# define preempt_enable_rt() preempt_enable() +# define preempt_disable_nort() barrier() +# define preempt_enable_nort() barrier() +#else +# define preempt_disable_rt() barrier() +# define preempt_enable_rt() barrier() +# define preempt_disable_nort() preempt_disable() +# define preempt_enable_nort() preempt_enable() +#endif + #ifdef CONFIG_PREEMPT_NOTIFIERS struct preempt_notifier; diff --git a/include/linux/printk.h b/include/linux/printk.h index 09993f3b46a7..1ecf6925e2c2 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -140,9 +140,11 @@ struct va_format { #ifdef CONFIG_EARLY_PRINTK extern asmlinkage __printf(1, 2) void early_printk(const char *fmt, ...); +extern void printk_kill(void); #else static inline __printf(1, 2) __cold void early_printk(const char *s, ...) { } +static inline void printk_kill(void) { } #endif #ifdef CONFIG_PRINTK_NMI diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 34149e8b5f73..affb0fc4c5b6 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -330,6 +330,8 @@ unsigned int radix_tree_gang_lookup_slot(const struct radix_tree_root *, int radix_tree_preload(gfp_t gfp_mask); int radix_tree_maybe_preload(gfp_t gfp_mask); int radix_tree_maybe_preload_order(gfp_t gfp_mask, int order); +void radix_tree_preload_end(void); + void radix_tree_init(void); void *radix_tree_tag_set(struct radix_tree_root *, unsigned long index, unsigned int tag); @@ -349,11 +351,6 @@ unsigned int radix_tree_gang_lookup_tag_slot(const struct radix_tree_root *, unsigned int max_items, unsigned int tag); int radix_tree_tagged(const struct radix_tree_root *, unsigned int tag); -static inline void radix_tree_preload_end(void) -{ - preempt_enable(); -} - int radix_tree_split_preload(unsigned old_order, unsigned new_order, gfp_t); int radix_tree_split(struct radix_tree_root *, unsigned long index, unsigned new_order); diff --git a/include/linux/random.h b/include/linux/random.h index 2ddf13b4281e..46f0049efabb 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -32,7 +32,7 @@ static inline void add_latent_entropy(void) {} extern void add_input_randomness(unsigned int type, unsigned int code, unsigned int value) __latent_entropy; -extern void add_interrupt_randomness(int irq, int irq_flags) __latent_entropy; +extern void add_interrupt_randomness(int irq, int irq_flags, __u64 ip) __latent_entropy; extern void get_random_bytes(void *buf, int nbytes); extern int wait_for_random_bytes(void); diff --git a/include/linux/rbtree.h b/include/linux/rbtree.h index fcbeed4053ef..2aa2aec354c2 100644 --- a/include/linux/rbtree.h +++ b/include/linux/rbtree.h @@ -31,7 +31,7 @@ #include <linux/kernel.h> #include <linux/stddef.h> -#include <linux/rcupdate.h> +#include <linux/rcu_assign_pointer.h> struct rb_node { unsigned long __rb_parent_color; diff --git a/include/linux/rcu_assign_pointer.h b/include/linux/rcu_assign_pointer.h new file mode 100644 index 000000000000..7066962a4379 --- /dev/null +++ b/include/linux/rcu_assign_pointer.h @@ -0,0 +1,54 @@ +#ifndef __LINUX_RCU_ASSIGN_POINTER_H__ +#define __LINUX_RCU_ASSIGN_POINTER_H__ +#include <linux/compiler.h> +#include <asm/barrier.h> + +/** + * RCU_INITIALIZER() - statically initialize an RCU-protected global variable + * @v: The value to statically initialize with. + */ +#define RCU_INITIALIZER(v) (typeof(*(v)) __force __rcu *)(v) + +/** + * rcu_assign_pointer() - assign to RCU-protected pointer + * @p: pointer to assign to + * @v: value to assign (publish) + * + * Assigns the specified value to the specified RCU-protected + * pointer, ensuring that any concurrent RCU readers will see + * any prior initialization. + * + * Inserts memory barriers on architectures that require them + * (which is most of them), and also prevents the compiler from + * reordering the code that initializes the structure after the pointer + * assignment. More importantly, this call documents which pointers + * will be dereferenced by RCU read-side code. + * + * In some special cases, you may use RCU_INIT_POINTER() instead + * of rcu_assign_pointer(). RCU_INIT_POINTER() is a bit faster due + * to the fact that it does not constrain either the CPU or the compiler. + * That said, using RCU_INIT_POINTER() when you should have used + * rcu_assign_pointer() is a very bad thing that results in + * impossible-to-diagnose memory corruption. So please be careful. + * See the RCU_INIT_POINTER() comment header for details. + * + * Note that rcu_assign_pointer() evaluates each of its arguments only + * once, appearances notwithstanding. One of the "extra" evaluations + * is in typeof() and the other visible only to sparse (__CHECKER__), + * neither of which actually execute the argument. As with most cpp + * macros, this execute-arguments-only-once property is important, so + * please be careful when making changes to rcu_assign_pointer() and the + * other macros that it invokes. + */ +#define rcu_assign_pointer(p, v) \ +({ \ + uintptr_t _r_a_p__v = (uintptr_t)(v); \ + \ + if (__builtin_constant_p(v) && (_r_a_p__v) == (uintptr_t)NULL) \ + WRITE_ONCE((p), (typeof(p))(_r_a_p__v)); \ + else \ + smp_store_release(&p, RCU_INITIALIZER((typeof(p))_r_a_p__v)); \ + _r_a_p__v; \ +}) + +#endif diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 7c6710b8c1eb..d4027cc1eb0f 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -42,6 +42,7 @@ #include <linux/lockdep.h> #include <asm/processor.h> #include <linux/cpumask.h> +#include <linux/rcu_assign_pointer.h> #define ULONG_CMP_GE(a, b) (ULONG_MAX / 2 >= (a) - (b)) #define ULONG_CMP_LT(a, b) (ULONG_MAX / 2 < (a) - (b)) @@ -55,7 +56,11 @@ void call_rcu(struct rcu_head *head, rcu_callback_t func); #define call_rcu call_rcu_sched #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ +#ifdef CONFIG_PREEMPT_RT_FULL +#define call_rcu_bh call_rcu +#else void call_rcu_bh(struct rcu_head *head, rcu_callback_t func); +#endif void call_rcu_sched(struct rcu_head *head, rcu_callback_t func); void synchronize_sched(void); void rcu_barrier_tasks(void); @@ -74,6 +79,11 @@ void synchronize_rcu(void); * types of kernel builds, the rcu_read_lock() nesting depth is unknowable. */ #define rcu_preempt_depth() (current->rcu_read_lock_nesting) +#ifndef CONFIG_PREEMPT_RT_FULL +#define sched_rcu_preempt_depth() rcu_preempt_depth() +#else +static inline int sched_rcu_preempt_depth(void) { return 0; } +#endif #else /* #ifdef CONFIG_PREEMPT_RCU */ @@ -97,6 +107,8 @@ static inline int rcu_preempt_depth(void) return 0; } +#define sched_rcu_preempt_depth() rcu_preempt_depth() + #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ /* Internal to kernel */ @@ -254,7 +266,14 @@ extern struct lockdep_map rcu_sched_lock_map; extern struct lockdep_map rcu_callback_map; int debug_lockdep_rcu_enabled(void); int rcu_read_lock_held(void); +#ifdef CONFIG_PREEMPT_RT_FULL +static inline int rcu_read_lock_bh_held(void) +{ + return rcu_read_lock_held(); +} +#else int rcu_read_lock_bh_held(void); +#endif int rcu_read_lock_sched_held(void); #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ @@ -364,54 +383,6 @@ static inline void rcu_preempt_sleep_check(void) { } }) /** - * RCU_INITIALIZER() - statically initialize an RCU-protected global variable - * @v: The value to statically initialize with. - */ -#define RCU_INITIALIZER(v) (typeof(*(v)) __force __rcu *)(v) - -/** - * rcu_assign_pointer() - assign to RCU-protected pointer - * @p: pointer to assign to - * @v: value to assign (publish) - * - * Assigns the specified value to the specified RCU-protected - * pointer, ensuring that any concurrent RCU readers will see - * any prior initialization. - * - * Inserts memory barriers on architectures that require them - * (which is most of them), and also prevents the compiler from - * reordering the code that initializes the structure after the pointer - * assignment. More importantly, this call documents which pointers - * will be dereferenced by RCU read-side code. - * - * In some special cases, you may use RCU_INIT_POINTER() instead - * of rcu_assign_pointer(). RCU_INIT_POINTER() is a bit faster due - * to the fact that it does not constrain either the CPU or the compiler. - * That said, using RCU_INIT_POINTER() when you should have used - * rcu_assign_pointer() is a very bad thing that results in - * impossible-to-diagnose memory corruption. So please be careful. - * See the RCU_INIT_POINTER() comment header for details. - * - * Note that rcu_assign_pointer() evaluates each of its arguments only - * once, appearances notwithstanding. One of the "extra" evaluations - * is in typeof() and the other visible only to sparse (__CHECKER__), - * neither of which actually execute the argument. As with most cpp - * macros, this execute-arguments-only-once property is important, so - * please be careful when making changes to rcu_assign_pointer() and the - * other macros that it invokes. - */ -#define rcu_assign_pointer(p, v) \ -({ \ - uintptr_t _r_a_p__v = (uintptr_t)(v); \ - \ - if (__builtin_constant_p(v) && (_r_a_p__v) == (uintptr_t)NULL) \ - WRITE_ONCE((p), (typeof(p))(_r_a_p__v)); \ - else \ - smp_store_release(&p, RCU_INITIALIZER((typeof(p))_r_a_p__v)); \ - _r_a_p__v; \ -}) - -/** * rcu_swap_protected() - swap an RCU and a regular pointer * @rcu_ptr: RCU pointer * @ptr: regular pointer @@ -703,10 +674,14 @@ static inline void rcu_read_unlock(void) static inline void rcu_read_lock_bh(void) { local_bh_disable(); +#ifdef CONFIG_PREEMPT_RT_FULL + rcu_read_lock(); +#else __acquire(RCU_BH); rcu_lock_acquire(&rcu_bh_lock_map); RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_lock_bh() used illegally while idle"); +#endif } /* @@ -716,10 +691,14 @@ static inline void rcu_read_lock_bh(void) */ static inline void rcu_read_unlock_bh(void) { +#ifdef CONFIG_PREEMPT_RT_FULL + rcu_read_unlock(); +#else RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_unlock_bh() used illegally while idle"); rcu_lock_release(&rcu_bh_lock_map); __release(RCU_BH); +#endif local_bh_enable(); } diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 914655848ef6..462ce061bac7 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -44,7 +44,11 @@ static inline void rcu_virt_note_context_switch(int cpu) rcu_note_context_switch(false); } +#ifdef CONFIG_PREEMPT_RT_FULL +# define synchronize_rcu_bh synchronize_rcu +#else void synchronize_rcu_bh(void); +#endif void synchronize_sched_expedited(void); void synchronize_rcu_expedited(void); @@ -72,7 +76,11 @@ static inline void synchronize_rcu_bh_expedited(void) } void rcu_barrier(void); +#ifdef CONFIG_PREEMPT_RT_FULL +# define rcu_barrier_bh rcu_barrier +#else void rcu_barrier_bh(void); +#endif void rcu_barrier_sched(void); bool rcu_eqs_special_set(int cpu); unsigned long get_state_synchronize_rcu(void); diff --git a/include/linux/rtmutex.h b/include/linux/rtmutex.h index 6fd615a0eea9..138bd1e183e0 100644 --- a/include/linux/rtmutex.h +++ b/include/linux/rtmutex.h @@ -14,11 +14,15 @@ #define __LINUX_RT_MUTEX_H #include <linux/linkage.h> +#include <linux/spinlock_types_raw.h> #include <linux/rbtree.h> -#include <linux/spinlock_types.h> extern int max_lock_depth; /* for sysctl */ +#ifdef CONFIG_DEBUG_MUTEXES +#include <linux/debug_locks.h> +#endif + /** * The rt_mutex structure * @@ -31,8 +35,8 @@ struct rt_mutex { raw_spinlock_t wait_lock; struct rb_root_cached waiters; struct task_struct *owner; -#ifdef CONFIG_DEBUG_RT_MUTEXES int save_state; +#ifdef CONFIG_DEBUG_RT_MUTEXES const char *name, *file; int line; void *magic; @@ -82,16 +86,23 @@ do { \ #define __DEP_MAP_RT_MUTEX_INITIALIZER(mutexname) #endif -#define __RT_MUTEX_INITIALIZER(mutexname) \ - { .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(mutexname.wait_lock) \ +#define __RT_MUTEX_INITIALIZER_PLAIN(mutexname) \ + .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(mutexname.wait_lock) \ , .waiters = RB_ROOT_CACHED \ , .owner = NULL \ __DEBUG_RT_MUTEX_INITIALIZER(mutexname) \ - __DEP_MAP_RT_MUTEX_INITIALIZER(mutexname)} + __DEP_MAP_RT_MUTEX_INITIALIZER(mutexname) + +#define __RT_MUTEX_INITIALIZER(mutexname) \ + { __RT_MUTEX_INITIALIZER_PLAIN(mutexname) } #define DEFINE_RT_MUTEX(mutexname) \ struct rt_mutex mutexname = __RT_MUTEX_INITIALIZER(mutexname) +#define __RT_MUTEX_INITIALIZER_SAVE_STATE(mutexname) \ + { __RT_MUTEX_INITIALIZER_PLAIN(mutexname) \ + , .save_state = 1 } + /** * rt_mutex_is_locked - is the mutex locked * @lock: the mutex to be queried @@ -115,6 +126,7 @@ extern void rt_mutex_lock(struct rt_mutex *lock); #endif extern int rt_mutex_lock_interruptible(struct rt_mutex *lock); +extern int rt_mutex_lock_killable(struct rt_mutex *lock); extern int rt_mutex_timed_lock(struct rt_mutex *lock, struct hrtimer_sleeper *timeout); diff --git a/include/linux/rwlock_rt.h b/include/linux/rwlock_rt.h new file mode 100644 index 000000000000..a9c4c2ac4d1f --- /dev/null +++ b/include/linux/rwlock_rt.h @@ -0,0 +1,119 @@ +#ifndef __LINUX_RWLOCK_RT_H +#define __LINUX_RWLOCK_RT_H + +#ifndef __LINUX_SPINLOCK_H +#error Do not include directly. Use spinlock.h +#endif + +extern void __lockfunc rt_write_lock(rwlock_t *rwlock); +extern void __lockfunc rt_read_lock(rwlock_t *rwlock); +extern int __lockfunc rt_write_trylock(rwlock_t *rwlock); +extern int __lockfunc rt_read_trylock(rwlock_t *rwlock); +extern void __lockfunc rt_write_unlock(rwlock_t *rwlock); +extern void __lockfunc rt_read_unlock(rwlock_t *rwlock); +extern int __lockfunc rt_read_can_lock(rwlock_t *rwlock); +extern int __lockfunc rt_write_can_lock(rwlock_t *rwlock); +extern void __rt_rwlock_init(rwlock_t *rwlock, char *name, struct lock_class_key *key); + +#define read_can_lock(rwlock) rt_read_can_lock(rwlock) +#define write_can_lock(rwlock) rt_write_can_lock(rwlock) + +#define read_trylock(lock) __cond_lock(lock, rt_read_trylock(lock)) +#define write_trylock(lock) __cond_lock(lock, rt_write_trylock(lock)) + +static inline int __write_trylock_rt_irqsave(rwlock_t *lock, unsigned long *flags) +{ + /* XXX ARCH_IRQ_ENABLED */ + *flags = 0; + return rt_write_trylock(lock); +} + +#define write_trylock_irqsave(lock, flags) \ + __cond_lock(lock, __write_trylock_rt_irqsave(lock, &(flags))) + +#define read_lock_irqsave(lock, flags) \ + do { \ + typecheck(unsigned long, flags); \ + rt_read_lock(lock); \ + flags = 0; \ + } while (0) + +#define write_lock_irqsave(lock, flags) \ + do { \ + typecheck(unsigned long, flags); \ + rt_write_lock(lock); \ + flags = 0; \ + } while (0) + +#define read_lock(lock) rt_read_lock(lock) + +#define read_lock_bh(lock) \ + do { \ + local_bh_disable(); \ + rt_read_lock(lock); \ + } while (0) + +#define read_lock_irq(lock) read_lock(lock) + +#define write_lock(lock) rt_write_lock(lock) + +#define write_lock_bh(lock) \ + do { \ + local_bh_disable(); \ + rt_write_lock(lock); \ + } while (0) + +#define write_lock_irq(lock) write_lock(lock) + +#define read_unlock(lock) rt_read_unlock(lock) + +#define read_unlock_bh(lock) \ + do { \ + rt_read_unlock(lock); \ + local_bh_enable(); \ + } while (0) + +#define read_unlock_irq(lock) read_unlock(lock) + +#define write_unlock(lock) rt_write_unlock(lock) + +#define write_unlock_bh(lock) \ + do { \ + rt_write_unlock(lock); \ + local_bh_enable(); \ + } while (0) + +#define write_unlock_irq(lock) write_unlock(lock) + +#define read_unlock_irqrestore(lock, flags) \ + do { \ + typecheck(unsigned long, flags); \ + (void) flags; \ + rt_read_unlock(lock); \ + } while (0) + +#define write_unlock_irqrestore(lock, flags) \ + do { \ + typecheck(unsigned long, flags); \ + (void) flags; \ + rt_write_unlock(lock); \ + } while (0) + +#define rwlock_init(rwl) \ +do { \ + static struct lock_class_key __key; \ + \ + __rt_rwlock_init(rwl, #rwl, &__key); \ +} while (0) + +/* + * Internal functions made global for CPU pinning + */ +void __read_rt_lock(struct rt_rw_lock *lock); +int __read_rt_trylock(struct rt_rw_lock *lock); +void __write_rt_lock(struct rt_rw_lock *lock); +int __write_rt_trylock(struct rt_rw_lock *lock); +void __read_rt_unlock(struct rt_rw_lock *lock); +void __write_rt_unlock(struct rt_rw_lock *lock); + +#endif diff --git a/include/linux/rwlock_types.h b/include/linux/rwlock_types.h index 857a72ceb794..c21683f3e14a 100644 --- a/include/linux/rwlock_types.h +++ b/include/linux/rwlock_types.h @@ -1,6 +1,10 @@ #ifndef __LINUX_RWLOCK_TYPES_H #define __LINUX_RWLOCK_TYPES_H +#if !defined(__LINUX_SPINLOCK_TYPES_H) +# error "Do not include directly, include spinlock_types.h" +#endif + /* * include/linux/rwlock_types.h - generic rwlock type definitions * and initializers diff --git a/include/linux/rwlock_types_rt.h b/include/linux/rwlock_types_rt.h new file mode 100644 index 000000000000..546a1f8f1274 --- /dev/null +++ b/include/linux/rwlock_types_rt.h @@ -0,0 +1,55 @@ +#ifndef __LINUX_RWLOCK_TYPES_RT_H +#define __LINUX_RWLOCK_TYPES_RT_H + +#ifndef __LINUX_SPINLOCK_TYPES_H +#error "Do not include directly. Include spinlock_types.h instead" +#endif + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +# define RW_DEP_MAP_INIT(lockname) .dep_map = { .name = #lockname } +#else +# define RW_DEP_MAP_INIT(lockname) +#endif + +typedef struct rt_rw_lock rwlock_t; + +#define __RW_LOCK_UNLOCKED(name) __RWLOCK_RT_INITIALIZER(name) + +#define DEFINE_RWLOCK(name) \ + rwlock_t name = __RW_LOCK_UNLOCKED(name) + +/* + * A reader biased implementation primarily for CPU pinning. + * + * Can be selected as general replacement for the single reader RT rwlock + * variant + */ +struct rt_rw_lock { + struct rt_mutex rtmutex; + atomic_t readers; +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map dep_map; +#endif +}; + +#define READER_BIAS (1U << 31) +#define WRITER_BIAS (1U << 30) + +#define __RWLOCK_RT_INITIALIZER(name) \ +{ \ + .readers = ATOMIC_INIT(READER_BIAS), \ + .rtmutex = __RT_MUTEX_INITIALIZER_SAVE_STATE(name.rtmutex), \ + RW_DEP_MAP_INIT(name) \ +} + +void __rwlock_biased_rt_init(struct rt_rw_lock *lock, const char *name, + struct lock_class_key *key); + +#define rwlock_biased_rt_init(rwlock) \ + do { \ + static struct lock_class_key __key; \ + \ + __rwlock_biased_rt_init((rwlock), #rwlock, &__key); \ + } while (0) + +#endif diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h index ab93b6eae696..b1e32373f44f 100644 --- a/include/linux/rwsem.h +++ b/include/linux/rwsem.h @@ -20,6 +20,10 @@ #include <linux/osq_lock.h> #endif +#ifdef CONFIG_PREEMPT_RT_FULL +#include <linux/rwsem_rt.h> +#else /* PREEMPT_RT_FULL */ + struct rw_semaphore; #ifdef CONFIG_RWSEM_GENERIC_SPINLOCK @@ -114,6 +118,13 @@ static inline int rwsem_is_contended(struct rw_semaphore *sem) return !list_empty(&sem->wait_list); } +#endif /* !PREEMPT_RT_FULL */ + +/* + * The functions below are the same for all rwsem implementations including + * the RT specific variant. + */ + /* * lock for reading */ diff --git a/include/linux/rwsem_rt.h b/include/linux/rwsem_rt.h new file mode 100644 index 000000000000..2018ff77904a --- /dev/null +++ b/include/linux/rwsem_rt.h @@ -0,0 +1,68 @@ +#ifndef _LINUX_RWSEM_RT_H +#define _LINUX_RWSEM_RT_H + +#ifndef _LINUX_RWSEM_H +#error "Include rwsem.h" +#endif + +#include <linux/rtmutex.h> +#include <linux/swait.h> + +#define READER_BIAS (1U << 31) +#define WRITER_BIAS (1U << 30) + +struct rw_semaphore { + atomic_t readers; + struct rt_mutex rtmutex; +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map dep_map; +#endif +}; + +#define __RWSEM_INITIALIZER(name) \ +{ \ + .readers = ATOMIC_INIT(READER_BIAS), \ + .rtmutex = __RT_MUTEX_INITIALIZER(name.rtmutex), \ + RW_DEP_MAP_INIT(name) \ +} + +#define DECLARE_RWSEM(lockname) \ + struct rw_semaphore lockname = __RWSEM_INITIALIZER(lockname) + +extern void __rwsem_init(struct rw_semaphore *rwsem, const char *name, + struct lock_class_key *key); + +#define __init_rwsem(sem, name, key) \ +do { \ + rt_mutex_init(&(sem)->rtmutex); \ + __rwsem_init((sem), (name), (key)); \ +} while (0) + +#define init_rwsem(sem) \ +do { \ + static struct lock_class_key __key; \ + \ + __init_rwsem((sem), #sem, &__key); \ +} while (0) + +static inline int rwsem_is_locked(struct rw_semaphore *sem) +{ + return atomic_read(&sem->readers) != READER_BIAS; +} + +static inline int rwsem_is_contended(struct rw_semaphore *sem) +{ + return atomic_read(&sem->readers) > 0; +} + +extern void __down_read(struct rw_semaphore *sem); +extern int __down_read_killable(struct rw_semaphore *sem); +extern int __down_read_trylock(struct rw_semaphore *sem); +extern void __down_write(struct rw_semaphore *sem); +extern int __must_check __down_write_killable(struct rw_semaphore *sem); +extern int __down_write_trylock(struct rw_semaphore *sem); +extern void __up_read(struct rw_semaphore *sem); +extern void __up_write(struct rw_semaphore *sem); +extern void __downgrade_write(struct rw_semaphore *sem); + +#endif diff --git a/include/linux/sched.h b/include/linux/sched.h index ce5f64cbaae5..f8324d0c00d2 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -28,6 +28,7 @@ #include <linux/mm_types_task.h> #include <linux/task_io_accounting.h> #include <linux/rseq.h> +#include <asm/kmap_types.h> /* task_struct member predeclarations (sorted alphabetically): */ struct audit_context; @@ -101,12 +102,8 @@ struct task_group; __TASK_TRACED | EXIT_DEAD | EXIT_ZOMBIE | \ TASK_PARKED) -#define task_is_traced(task) ((task->state & __TASK_TRACED) != 0) - #define task_is_stopped(task) ((task->state & __TASK_STOPPED) != 0) -#define task_is_stopped_or_traced(task) ((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0) - #define task_contributes_to_load(task) ((task->state & TASK_UNINTERRUPTIBLE) != 0 && \ (task->flags & PF_FROZEN) == 0 && \ (task->state & TASK_NOLOAD) == 0) @@ -134,6 +131,9 @@ struct task_group; smp_store_mb(current->state, (state_value)); \ } while (0) +#define __set_current_state_no_track(state_value) \ + current->state = (state_value); + #define set_special_state(state_value) \ do { \ unsigned long flags; /* may shadow */ \ @@ -143,6 +143,7 @@ struct task_group; current->state = (state_value); \ raw_spin_unlock_irqrestore(¤t->pi_lock, flags); \ } while (0) + #else /* * set_current_state() includes a barrier so that the write of current->state @@ -187,6 +188,9 @@ struct task_group; #define set_current_state(state_value) \ smp_store_mb(current->state, (state_value)) +#define __set_current_state_no_track(state_value) \ + __set_current_state(state_value) + /* * set_special_state() should be used for those states when the blocking task * can not use the regular condition based wait-loop. In that case we must @@ -600,6 +604,8 @@ struct task_struct { #endif /* -1 unrunnable, 0 runnable, >0 stopped: */ volatile long state; + /* saved state for "spinlock sleepers" */ + volatile long saved_state; /* * This begins the randomizable portion of task_struct. Only @@ -660,7 +666,25 @@ struct task_struct { unsigned int policy; int nr_cpus_allowed; - cpumask_t cpus_allowed; + const cpumask_t *cpus_ptr; + cpumask_t cpus_mask; +#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE) + int migrate_disable; + int migrate_disable_update; + int pinned_on_cpu; +# ifdef CONFIG_SCHED_DEBUG + int migrate_disable_atomic; +# endif + +#elif !defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE) +# ifdef CONFIG_SCHED_DEBUG + int migrate_disable; + int migrate_disable_atomic; +# endif +#endif +#ifdef CONFIG_PREEMPT_RT_FULL + int sleeping_lock; +#endif #ifdef CONFIG_PREEMPT_RCU int rcu_read_lock_nesting; @@ -819,6 +843,9 @@ struct task_struct { #ifdef CONFIG_POSIX_TIMERS struct task_cputime cputime_expires; struct list_head cpu_timers[3]; +#ifdef CONFIG_PREEMPT_RT_BASE + struct task_struct *posix_timer_list; +#endif #endif /* Process credentials: */ @@ -862,11 +889,17 @@ struct task_struct { /* Signal handlers: */ struct signal_struct *signal; struct sighand_struct *sighand; + struct sigqueue *sigqueue_cache; + sigset_t blocked; sigset_t real_blocked; /* Restored if set_restore_sigmask() was used: */ sigset_t saved_sigmask; struct sigpending pending; +#ifdef CONFIG_PREEMPT_RT_FULL + /* TODO: move me into ->restart_block ? */ + struct siginfo forced_info; +#endif unsigned long sas_ss_sp; size_t sas_ss_size; unsigned int sas_ss_flags; @@ -891,6 +924,7 @@ struct task_struct { raw_spinlock_t pi_lock; struct wake_q_node wake_q; + struct wake_q_node wake_q_sleeper; #ifdef CONFIG_RT_MUTEXES /* PI waiters blocked on a rt_mutex held by this task: */ @@ -1159,9 +1193,23 @@ struct task_struct { unsigned int sequential_io; unsigned int sequential_io_avg; #endif +#ifdef CONFIG_PREEMPT_RT_BASE + struct rcu_head put_rcu; + int softirq_nestcnt; + unsigned int softirqs_raised; +#endif +#ifdef CONFIG_PREEMPT_RT_FULL +# if defined CONFIG_HIGHMEM || defined CONFIG_X86_32 + int kmap_idx; + pte_t kmap_pte[KM_TYPE_NR]; +# endif +#endif #ifdef CONFIG_DEBUG_ATOMIC_SLEEP unsigned long task_state_change; #endif +#ifdef CONFIG_PREEMPT_RT_FULL + int xmit_recursion; +#endif int pagefault_disabled; #ifdef CONFIG_MMU struct task_struct *oom_reaper_list; @@ -1375,6 +1423,7 @@ extern struct pid *cad_pid; /* * Per process flags */ +#define PF_IN_SOFTIRQ 0x00000001 /* Task is serving softirq */ #define PF_IDLE 0x00000002 /* I am an IDLE thread */ #define PF_EXITING 0x00000004 /* Getting shut down */ #define PF_EXITPIDONE 0x00000008 /* PI exit done on shut down */ @@ -1398,7 +1447,7 @@ extern struct pid *cad_pid; #define PF_KTHREAD 0x00200000 /* I am a kernel thread */ #define PF_RANDOMIZE 0x00400000 /* Randomize virtual address space */ #define PF_SWAPWRITE 0x00800000 /* Allowed to write to swap */ -#define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_allowed */ +#define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_mask */ #define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ #define PF_MUTEX_TESTER 0x20000000 /* Thread belongs to the rt mutex tester */ #define PF_FREEZER_SKIP 0x40000000 /* Freezer should not count it as freezable */ @@ -1603,6 +1652,7 @@ extern struct task_struct *find_get_task_by_vpid(pid_t nr); extern int wake_up_state(struct task_struct *tsk, unsigned int state); extern int wake_up_process(struct task_struct *tsk); +extern int wake_up_lock_sleeper(struct task_struct *tsk); extern void wake_up_new_task(struct task_struct *tsk); #ifdef CONFIG_SMP @@ -1685,6 +1735,89 @@ static inline int test_tsk_need_resched(struct task_struct *tsk) return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED)); } +#ifdef CONFIG_PREEMPT_LAZY +static inline void set_tsk_need_resched_lazy(struct task_struct *tsk) +{ + set_tsk_thread_flag(tsk,TIF_NEED_RESCHED_LAZY); +} + +static inline void clear_tsk_need_resched_lazy(struct task_struct *tsk) +{ + clear_tsk_thread_flag(tsk,TIF_NEED_RESCHED_LAZY); +} + +static inline int test_tsk_need_resched_lazy(struct task_struct *tsk) +{ + return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED_LAZY)); +} + +static inline int need_resched_lazy(void) +{ + return test_thread_flag(TIF_NEED_RESCHED_LAZY); +} + +static inline int need_resched_now(void) +{ + return test_thread_flag(TIF_NEED_RESCHED); +} + +#else +static inline void clear_tsk_need_resched_lazy(struct task_struct *tsk) { } +static inline int need_resched_lazy(void) { return 0; } + +static inline int need_resched_now(void) +{ + return test_thread_flag(TIF_NEED_RESCHED); +} + +#endif + + +static inline bool __task_is_stopped_or_traced(struct task_struct *task) +{ + if (task->state & (__TASK_STOPPED | __TASK_TRACED)) + return true; +#ifdef CONFIG_PREEMPT_RT_FULL + if (task->saved_state & (__TASK_STOPPED | __TASK_TRACED)) + return true; +#endif + return false; +} + +static inline bool task_is_stopped_or_traced(struct task_struct *task) +{ + bool traced_stopped; + +#ifdef CONFIG_PREEMPT_RT_FULL + unsigned long flags; + + raw_spin_lock_irqsave(&task->pi_lock, flags); + traced_stopped = __task_is_stopped_or_traced(task); + raw_spin_unlock_irqrestore(&task->pi_lock, flags); +#else + traced_stopped = __task_is_stopped_or_traced(task); +#endif + return traced_stopped; +} + +static inline bool task_is_traced(struct task_struct *task) +{ + bool traced = false; + + if (task->state & __TASK_TRACED) + return true; +#ifdef CONFIG_PREEMPT_RT_FULL + /* in case the task is sleeping on tasklist_lock */ + raw_spin_lock_irq(&task->pi_lock); + if (task->state & __TASK_TRACED) + traced = true; + else if (task->saved_state & __TASK_TRACED) + traced = true; + raw_spin_unlock_irq(&task->pi_lock); +#endif + return traced; +} + /* * cond_resched() and cond_resched_lock(): latency reduction via * explicit rescheduling in places that are safe. The return @@ -1737,6 +1870,23 @@ static __always_inline bool need_resched(void) return unlikely(tif_need_resched()); } +#ifdef CONFIG_PREEMPT_RT_FULL +static inline void sleeping_lock_inc(void) +{ + current->sleeping_lock++; +} + +static inline void sleeping_lock_dec(void) +{ + current->sleeping_lock--; +} + +#else + +static inline void sleeping_lock_inc(void) { } +static inline void sleeping_lock_dec(void) { } +#endif + /* * Wrappers for p->thread_info->cpu access. No-op on UP. */ diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 1a83cc6ea4af..4174cb89a288 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -49,6 +49,17 @@ static inline void mmdrop(struct mm_struct *mm) __mmdrop(mm); } +#ifdef CONFIG_PREEMPT_RT_BASE +extern void __mmdrop_delayed(struct rcu_head *rhp); +static inline void mmdrop_delayed(struct mm_struct *mm) +{ + if (atomic_dec_and_test(&mm->mm_count)) + call_rcu(&mm->delayed_drop, __mmdrop_delayed); +} +#else +# define mmdrop_delayed(mm) mmdrop(mm) +#endif + /* * This has to be called after a get_task_mm()/mmget_not_zero() * followed by taking the mmap_sem for writing before modifying the diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 108ede99e533..bb98c5b43f81 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -88,6 +88,15 @@ extern void sched_exec(void); #define get_task_struct(tsk) do { atomic_inc(&(tsk)->usage); } while(0) +#ifdef CONFIG_PREEMPT_RT_BASE +extern void __put_task_struct_cb(struct rcu_head *rhp); + +static inline void put_task_struct(struct task_struct *t) +{ + if (atomic_dec_and_test(&t->usage)) + call_rcu(&t->put_rcu, __put_task_struct_cb); +} +#else extern void __put_task_struct(struct task_struct *t); static inline void put_task_struct(struct task_struct *t) @@ -95,7 +104,7 @@ static inline void put_task_struct(struct task_struct *t) if (atomic_dec_and_test(&t->usage)) __put_task_struct(t); } - +#endif struct task_struct *task_rcu_dereference(struct task_struct **ptask); #ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT diff --git a/include/linux/sched/user.h b/include/linux/sched/user.h index 96fe289c4c6e..39ad98c09c58 100644 --- a/include/linux/sched/user.h +++ b/include/linux/sched/user.h @@ -4,6 +4,7 @@ #include <linux/uidgid.h> #include <linux/atomic.h> +#include <linux/refcount.h> #include <linux/ratelimit.h> struct key; @@ -12,7 +13,7 @@ struct key; * Some day this will be a full-fledged user tracking system.. */ struct user_struct { - atomic_t __count; /* reference count */ + refcount_t __count; /* reference count */ atomic_t processes; /* How many processes does this user have? */ atomic_t sigpending; /* How many pending signals does this user have? */ #ifdef CONFIG_FANOTIFY @@ -59,7 +60,7 @@ extern struct user_struct root_user; extern struct user_struct * alloc_uid(kuid_t); static inline struct user_struct *get_uid(struct user_struct *u) { - atomic_inc(&u->__count); + refcount_inc(&u->__count); return u; } extern void free_uid(struct user_struct *); diff --git a/include/linux/sched/wake_q.h b/include/linux/sched/wake_q.h index 10b19a192b2d..ce3ccff3d9d8 100644 --- a/include/linux/sched/wake_q.h +++ b/include/linux/sched/wake_q.h @@ -47,8 +47,29 @@ static inline void wake_q_init(struct wake_q_head *head) head->lastp = &head->first; } -extern void wake_q_add(struct wake_q_head *head, - struct task_struct *task); -extern void wake_up_q(struct wake_q_head *head); +extern void __wake_q_add(struct wake_q_head *head, + struct task_struct *task, bool sleeper); +static inline void wake_q_add(struct wake_q_head *head, + struct task_struct *task) +{ + __wake_q_add(head, task, false); +} + +static inline void wake_q_add_sleeper(struct wake_q_head *head, + struct task_struct *task) +{ + __wake_q_add(head, task, true); +} + +extern void __wake_up_q(struct wake_q_head *head, bool sleeper); +static inline void wake_up_q(struct wake_q_head *head) +{ + __wake_up_q(head, false); +} + +static inline void wake_up_q_sleeper(struct wake_q_head *head) +{ + __wake_up_q(head, true); +} #endif /* _LINUX_SCHED_WAKE_Q_H */ diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index bcf4cf26b8c8..58f9909d6659 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -221,20 +221,30 @@ static inline int read_seqcount_retry(const seqcount_t *s, unsigned start) return __read_seqcount_retry(s, start); } - - -static inline void raw_write_seqcount_begin(seqcount_t *s) +static inline void __raw_write_seqcount_begin(seqcount_t *s) { s->sequence++; smp_wmb(); } -static inline void raw_write_seqcount_end(seqcount_t *s) +static inline void raw_write_seqcount_begin(seqcount_t *s) +{ + preempt_disable_rt(); + __raw_write_seqcount_begin(s); +} + +static inline void __raw_write_seqcount_end(seqcount_t *s) { smp_wmb(); s->sequence++; } +static inline void raw_write_seqcount_end(seqcount_t *s) +{ + __raw_write_seqcount_end(s); + preempt_enable_rt(); +} + /** * raw_write_seqcount_barrier - do a seq write barrier * @s: pointer to seqcount_t @@ -428,10 +438,33 @@ typedef struct { /* * Read side functions for starting and finalizing a read side section. */ +#ifndef CONFIG_PREEMPT_RT_FULL static inline unsigned read_seqbegin(const seqlock_t *sl) { return read_seqcount_begin(&sl->seqcount); } +#else +/* + * Starvation safe read side for RT + */ +static inline unsigned read_seqbegin(seqlock_t *sl) +{ + unsigned ret; + +repeat: + ret = READ_ONCE(sl->seqcount.sequence); + if (unlikely(ret & 1)) { + /* + * Take the lock and let the writer proceed (i.e. evtl + * boost it), otherwise we could loop here forever. + */ + spin_unlock_wait(&sl->lock); + goto repeat; + } + smp_rmb(); + return ret; +} +#endif static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start) { @@ -446,36 +479,45 @@ static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start) static inline void write_seqlock(seqlock_t *sl) { spin_lock(&sl->lock); - write_seqcount_begin(&sl->seqcount); + __raw_write_seqcount_begin(&sl->seqcount); +} + +static inline int try_write_seqlock(seqlock_t *sl) +{ + if (spin_trylock(&sl->lock)) { + __raw_write_seqcount_begin(&sl->seqcount); + return 1; + } + return 0; } static inline void write_sequnlock(seqlock_t *sl) { - write_seqcount_end(&sl->seqcount); + __raw_write_seqcount_end(&sl->seqcount); spin_unlock(&sl->lock); } static inline void write_seqlock_bh(seqlock_t *sl) { spin_lock_bh(&sl->lock); - write_seqcount_begin(&sl->seqcount); + __raw_write_seqcount_begin(&sl->seqcount); } static inline void write_sequnlock_bh(seqlock_t *sl) { - write_seqcount_end(&sl->seqcount); + __raw_write_seqcount_end(&sl->seqcount); spin_unlock_bh(&sl->lock); } static inline void write_seqlock_irq(seqlock_t *sl) { spin_lock_irq(&sl->lock); - write_seqcount_begin(&sl->seqcount); + __raw_write_seqcount_begin(&sl->seqcount); } static inline void write_sequnlock_irq(seqlock_t *sl) { - write_seqcount_end(&sl->seqcount); + __raw_write_seqcount_end(&sl->seqcount); spin_unlock_irq(&sl->lock); } @@ -484,7 +526,7 @@ static inline unsigned long __write_seqlock_irqsave(seqlock_t *sl) unsigned long flags; spin_lock_irqsave(&sl->lock, flags); - write_seqcount_begin(&sl->seqcount); + __raw_write_seqcount_begin(&sl->seqcount); return flags; } @@ -494,7 +536,7 @@ static inline unsigned long __write_seqlock_irqsave(seqlock_t *sl) static inline void write_sequnlock_irqrestore(seqlock_t *sl, unsigned long flags) { - write_seqcount_end(&sl->seqcount); + __raw_write_seqcount_end(&sl->seqcount); spin_unlock_irqrestore(&sl->lock, flags); } diff --git a/include/linux/signal.h b/include/linux/signal.h index 42ba31da534f..747406c6bd7c 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -245,6 +245,7 @@ static inline void init_sigpending(struct sigpending *sig) } extern void flush_sigqueue(struct sigpending *queue); +extern void flush_task_sigqueue(struct task_struct *tsk); /* Test if 'sig' is valid signal. Use this instead of testing _NSIG directly */ static inline int valid_signal(unsigned long sig) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 2e0db70fc052..4159be5b87df 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -287,6 +287,7 @@ struct sk_buff_head { __u32 qlen; spinlock_t lock; + raw_spinlock_t raw_lock; }; struct sk_buff; @@ -1687,6 +1688,12 @@ static inline void skb_queue_head_init(struct sk_buff_head *list) __skb_queue_head_init(list); } +static inline void skb_queue_head_init_raw(struct sk_buff_head *list) +{ + raw_spin_lock_init(&list->raw_lock); + __skb_queue_head_init(list); +} + static inline void skb_queue_head_init_class(struct sk_buff_head *list, struct lock_class_key *class) { diff --git a/include/linux/smp.h b/include/linux/smp.h index 9fb239e12b82..5801e516ba63 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -202,6 +202,9 @@ static inline int get_boot_cpu_id(void) #define get_cpu() ({ preempt_disable(); smp_processor_id(); }) #define put_cpu() preempt_enable() +#define get_cpu_light() ({ migrate_disable(); smp_processor_id(); }) +#define put_cpu_light() migrate_enable() + /* * Callback to arch code if there's nosmp or maxcpus=0 on the * boot command line: diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index fd57888d4942..01cda2439feb 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -279,7 +279,11 @@ static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock) }) /* Include rwlock functions */ -#include <linux/rwlock.h> +#ifdef CONFIG_PREEMPT_RT_FULL +# include <linux/rwlock_rt.h> +#else +# include <linux/rwlock.h> +#endif /* * Pull the _spin_*()/_read_*()/_write_*() functions/declarations: @@ -290,6 +294,10 @@ static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock) # include <linux/spinlock_api_up.h> #endif +#ifdef CONFIG_PREEMPT_RT_FULL +# include <linux/spinlock_rt.h> +#else /* PREEMPT_RT_FULL */ + /* * Map the spin_lock functions to the raw variants for PREEMPT_RT=n */ @@ -410,6 +418,8 @@ static __always_inline int spin_is_contended(spinlock_t *lock) #define assert_spin_locked(lock) assert_raw_spin_locked(&(lock)->rlock) +#endif /* !PREEMPT_RT_FULL */ + /* * Pull the atomic_t declaration: * (asm-mips/atomic.h needs above definitions) diff --git a/include/linux/spinlock_api_smp.h b/include/linux/spinlock_api_smp.h index 42dfab89e740..29d99ae5a8ab 100644 --- a/include/linux/spinlock_api_smp.h +++ b/include/linux/spinlock_api_smp.h @@ -187,6 +187,8 @@ static inline int __raw_spin_trylock_bh(raw_spinlock_t *lock) return 0; } -#include <linux/rwlock_api_smp.h> +#ifndef CONFIG_PREEMPT_RT_FULL +# include <linux/rwlock_api_smp.h> +#endif #endif /* __LINUX_SPINLOCK_API_SMP_H */ diff --git a/include/linux/spinlock_rt.h b/include/linux/spinlock_rt.h new file mode 100644 index 000000000000..3696a77fa77d --- /dev/null +++ b/include/linux/spinlock_rt.h @@ -0,0 +1,156 @@ +#ifndef __LINUX_SPINLOCK_RT_H +#define __LINUX_SPINLOCK_RT_H + +#ifndef __LINUX_SPINLOCK_H +#error Do not include directly. Use spinlock.h +#endif + +#include <linux/bug.h> + +extern void +__rt_spin_lock_init(spinlock_t *lock, const char *name, struct lock_class_key *key); + +#define spin_lock_init(slock) \ +do { \ + static struct lock_class_key __key; \ + \ + rt_mutex_init(&(slock)->lock); \ + __rt_spin_lock_init(slock, #slock, &__key); \ +} while (0) + +extern void __lockfunc rt_spin_lock(spinlock_t *lock); +extern unsigned long __lockfunc rt_spin_lock_trace_flags(spinlock_t *lock); +extern void __lockfunc rt_spin_lock_nested(spinlock_t *lock, int subclass); +extern void __lockfunc rt_spin_unlock(spinlock_t *lock); +extern void __lockfunc rt_spin_unlock_wait(spinlock_t *lock); +extern int __lockfunc rt_spin_trylock_irqsave(spinlock_t *lock, unsigned long *flags); +extern int __lockfunc rt_spin_trylock_bh(spinlock_t *lock); +extern int __lockfunc rt_spin_trylock(spinlock_t *lock); +extern int atomic_dec_and_spin_lock(atomic_t *atomic, spinlock_t *lock); + +/* + * lockdep-less calls, for derived types like rwlock: + * (for trylock they can use rt_mutex_trylock() directly. + * Migrate disable handling must be done at the call site. + */ +extern void __lockfunc __rt_spin_lock(struct rt_mutex *lock); +extern void __lockfunc __rt_spin_trylock(struct rt_mutex *lock); +extern void __lockfunc __rt_spin_unlock(struct rt_mutex *lock); + +#define spin_lock(lock) rt_spin_lock(lock) + +#define spin_lock_bh(lock) \ + do { \ + local_bh_disable(); \ + rt_spin_lock(lock); \ + } while (0) + +#define spin_lock_irq(lock) spin_lock(lock) + +#define spin_do_trylock(lock) __cond_lock(lock, rt_spin_trylock(lock)) + +#define spin_trylock(lock) \ +({ \ + int __locked; \ + __locked = spin_do_trylock(lock); \ + __locked; \ +}) + +#ifdef CONFIG_LOCKDEP +# define spin_lock_nested(lock, subclass) \ + do { \ + rt_spin_lock_nested(lock, subclass); \ + } while (0) + +#define spin_lock_bh_nested(lock, subclass) \ + do { \ + local_bh_disable(); \ + rt_spin_lock_nested(lock, subclass); \ + } while (0) + +# define spin_lock_irqsave_nested(lock, flags, subclass) \ + do { \ + typecheck(unsigned long, flags); \ + flags = 0; \ + rt_spin_lock_nested(lock, subclass); \ + } while (0) +#else +# define spin_lock_nested(lock, subclass) spin_lock(lock) +# define spin_lock_bh_nested(lock, subclass) spin_lock_bh(lock) + +# define spin_lock_irqsave_nested(lock, flags, subclass) \ + do { \ + typecheck(unsigned long, flags); \ + flags = 0; \ + spin_lock(lock); \ + } while (0) +#endif + +#define spin_lock_irqsave(lock, flags) \ + do { \ + typecheck(unsigned long, flags); \ + flags = 0; \ + spin_lock(lock); \ + } while (0) + +static inline unsigned long spin_lock_trace_flags(spinlock_t *lock) +{ + unsigned long flags = 0; +#ifdef CONFIG_TRACE_IRQFLAGS + flags = rt_spin_lock_trace_flags(lock); +#else + spin_lock(lock); /* lock_local */ +#endif + return flags; +} + +/* FIXME: we need rt_spin_lock_nest_lock */ +#define spin_lock_nest_lock(lock, nest_lock) spin_lock_nested(lock, 0) + +#define spin_unlock(lock) rt_spin_unlock(lock) + +#define spin_unlock_bh(lock) \ + do { \ + rt_spin_unlock(lock); \ + local_bh_enable(); \ + } while (0) + +#define spin_unlock_irq(lock) spin_unlock(lock) + +#define spin_unlock_irqrestore(lock, flags) \ + do { \ + typecheck(unsigned long, flags); \ + (void) flags; \ + spin_unlock(lock); \ + } while (0) + +#define spin_trylock_bh(lock) __cond_lock(lock, rt_spin_trylock_bh(lock)) +#define spin_trylock_irq(lock) spin_trylock(lock) + +#define spin_trylock_irqsave(lock, flags) \ + rt_spin_trylock_irqsave(lock, &(flags)) + +#define spin_unlock_wait(lock) rt_spin_unlock_wait(lock) + +#ifdef CONFIG_GENERIC_LOCKBREAK +# define spin_is_contended(lock) ((lock)->break_lock) +#else +# define spin_is_contended(lock) (((void)(lock), 0)) +#endif + +static inline int spin_can_lock(spinlock_t *lock) +{ + return !rt_mutex_is_locked(&lock->lock); +} + +static inline int spin_is_locked(spinlock_t *lock) +{ + return rt_mutex_is_locked(&lock->lock); +} + +static inline void assert_spin_locked(spinlock_t *lock) +{ + BUG_ON(!spin_is_locked(lock)); +} + +#endif diff --git a/include/linux/spinlock_types.h b/include/linux/spinlock_types.h index 24b4e6f2c1a2..10bac715ea96 100644 --- a/include/linux/spinlock_types.h +++ b/include/linux/spinlock_types.h @@ -9,77 +9,15 @@ * Released under the General Public License (GPL). */ -#if defined(CONFIG_SMP) -# include <asm/spinlock_types.h> -#else -# include <linux/spinlock_types_up.h> -#endif - -#include <linux/lockdep.h> - -typedef struct raw_spinlock { - arch_spinlock_t raw_lock; -#ifdef CONFIG_DEBUG_SPINLOCK - unsigned int magic, owner_cpu; - void *owner; -#endif -#ifdef CONFIG_DEBUG_LOCK_ALLOC - struct lockdep_map dep_map; -#endif -} raw_spinlock_t; - -#define SPINLOCK_MAGIC 0xdead4ead - -#define SPINLOCK_OWNER_INIT ((void *)-1L) - -#ifdef CONFIG_DEBUG_LOCK_ALLOC -# define SPIN_DEP_MAP_INIT(lockname) .dep_map = { .name = #lockname } -#else -# define SPIN_DEP_MAP_INIT(lockname) -#endif +#include <linux/spinlock_types_raw.h> -#ifdef CONFIG_DEBUG_SPINLOCK -# define SPIN_DEBUG_INIT(lockname) \ - .magic = SPINLOCK_MAGIC, \ - .owner_cpu = -1, \ - .owner = SPINLOCK_OWNER_INIT, +#ifndef CONFIG_PREEMPT_RT_FULL +# include <linux/spinlock_types_nort.h> +# include <linux/rwlock_types.h> #else -# define SPIN_DEBUG_INIT(lockname) +# include <linux/rtmutex.h> +# include <linux/spinlock_types_rt.h> +# include <linux/rwlock_types_rt.h> #endif -#define __RAW_SPIN_LOCK_INITIALIZER(lockname) \ - { \ - .raw_lock = __ARCH_SPIN_LOCK_UNLOCKED, \ - SPIN_DEBUG_INIT(lockname) \ - SPIN_DEP_MAP_INIT(lockname) } - -#define __RAW_SPIN_LOCK_UNLOCKED(lockname) \ - (raw_spinlock_t) __RAW_SPIN_LOCK_INITIALIZER(lockname) - -#define DEFINE_RAW_SPINLOCK(x) raw_spinlock_t x = __RAW_SPIN_LOCK_UNLOCKED(x) - -typedef struct spinlock { - union { - struct raw_spinlock rlock; - -#ifdef CONFIG_DEBUG_LOCK_ALLOC -# define LOCK_PADSIZE (offsetof(struct raw_spinlock, dep_map)) - struct { - u8 __padding[LOCK_PADSIZE]; - struct lockdep_map dep_map; - }; -#endif - }; -} spinlock_t; - -#define __SPIN_LOCK_INITIALIZER(lockname) \ - { { .rlock = __RAW_SPIN_LOCK_INITIALIZER(lockname) } } - -#define __SPIN_LOCK_UNLOCKED(lockname) \ - (spinlock_t ) __SPIN_LOCK_INITIALIZER(lockname) - -#define DEFINE_SPINLOCK(x) spinlock_t x = __SPIN_LOCK_UNLOCKED(x) - -#include <linux/rwlock_types.h> - #endif /* __LINUX_SPINLOCK_TYPES_H */ diff --git a/include/linux/spinlock_types_nort.h b/include/linux/spinlock_types_nort.h new file mode 100644 index 000000000000..f1dac1fb1d6a --- /dev/null +++ b/include/linux/spinlock_types_nort.h @@ -0,0 +1,33 @@ +#ifndef __LINUX_SPINLOCK_TYPES_NORT_H +#define __LINUX_SPINLOCK_TYPES_NORT_H + +#ifndef __LINUX_SPINLOCK_TYPES_H +#error "Do not include directly. Include spinlock_types.h instead" +#endif + +/* + * The non RT version maps spinlocks to raw_spinlocks + */ +typedef struct spinlock { + union { + struct raw_spinlock rlock; + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +# define LOCK_PADSIZE (offsetof(struct raw_spinlock, dep_map)) + struct { + u8 __padding[LOCK_PADSIZE]; + struct lockdep_map dep_map; + }; +#endif + }; +} spinlock_t; + +#define __SPIN_LOCK_INITIALIZER(lockname) \ + { { .rlock = __RAW_SPIN_LOCK_INITIALIZER(lockname) } } + +#define __SPIN_LOCK_UNLOCKED(lockname) \ + (spinlock_t ) __SPIN_LOCK_INITIALIZER(lockname) + +#define DEFINE_SPINLOCK(x) spinlock_t x = __SPIN_LOCK_UNLOCKED(x) + +#endif diff --git a/include/linux/spinlock_types_raw.h b/include/linux/spinlock_types_raw.h new file mode 100644 index 000000000000..822bf64a61d3 --- /dev/null +++ b/include/linux/spinlock_types_raw.h @@ -0,0 +1,55 @@ +#ifndef __LINUX_SPINLOCK_TYPES_RAW_H +#define __LINUX_SPINLOCK_TYPES_RAW_H + +#include <linux/types.h> + +#if defined(CONFIG_SMP) +# include <asm/spinlock_types.h> +#else +# include <linux/spinlock_types_up.h> +#endif + +#include <linux/lockdep.h> + +typedef struct raw_spinlock { + arch_spinlock_t raw_lock; +#ifdef CONFIG_DEBUG_SPINLOCK + unsigned int magic, owner_cpu; + void *owner; +#endif +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map dep_map; +#endif +} raw_spinlock_t; + +#define SPINLOCK_MAGIC 0xdead4ead + +#define SPINLOCK_OWNER_INIT ((void *)-1L) + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +# define SPIN_DEP_MAP_INIT(lockname) .dep_map = { .name = #lockname } +#else +# define SPIN_DEP_MAP_INIT(lockname) +#endif + +#ifdef CONFIG_DEBUG_SPINLOCK +# define SPIN_DEBUG_INIT(lockname) \ + .magic = SPINLOCK_MAGIC, \ + .owner_cpu = -1, \ + .owner = SPINLOCK_OWNER_INIT, +#else +# define SPIN_DEBUG_INIT(lockname) +#endif + +#define __RAW_SPIN_LOCK_INITIALIZER(lockname) \ + { \ + .raw_lock = __ARCH_SPIN_LOCK_UNLOCKED, \ + SPIN_DEBUG_INIT(lockname) \ + SPIN_DEP_MAP_INIT(lockname) } + +#define __RAW_SPIN_LOCK_UNLOCKED(lockname) \ + (raw_spinlock_t) __RAW_SPIN_LOCK_INITIALIZER(lockname) + +#define DEFINE_RAW_SPINLOCK(x) raw_spinlock_t x = __RAW_SPIN_LOCK_UNLOCKED(x) + +#endif diff --git a/include/linux/spinlock_types_rt.h b/include/linux/spinlock_types_rt.h new file mode 100644 index 000000000000..3e3d8c5f7a9a --- /dev/null +++ b/include/linux/spinlock_types_rt.h @@ -0,0 +1,48 @@ +#ifndef __LINUX_SPINLOCK_TYPES_RT_H +#define __LINUX_SPINLOCK_TYPES_RT_H + +#ifndef __LINUX_SPINLOCK_TYPES_H +#error "Do not include directly. Include spinlock_types.h instead" +#endif + +#include <linux/cache.h> + +/* + * PREEMPT_RT: spinlocks - an RT mutex plus lock-break field: + */ +typedef struct spinlock { + struct rt_mutex lock; + unsigned int break_lock; +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map dep_map; +#endif +} spinlock_t; + +#ifdef CONFIG_DEBUG_RT_MUTEXES +# define __RT_SPIN_INITIALIZER(name) \ + { \ + .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock), \ + .save_state = 1, \ + .file = __FILE__, \ + .line = __LINE__ , \ + } +#else +# define __RT_SPIN_INITIALIZER(name) \ + { \ + .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock), \ + .save_state = 1, \ + } +#endif + +/* +.wait_list = PLIST_HEAD_INIT_RAW((name).lock.wait_list, (name).lock.wait_lock) +*/ + +#define __SPIN_LOCK_UNLOCKED(name) \ + { .lock = __RT_SPIN_INITIALIZER(name.lock), \ + SPIN_DEP_MAP_INIT(name) } + +#define DEFINE_SPINLOCK(name) \ + spinlock_t name = __SPIN_LOCK_UNLOCKED(name) + +#endif diff --git a/include/linux/spinlock_types_up.h b/include/linux/spinlock_types_up.h index c09b6407ae1b..b0243ba07fb7 100644 --- a/include/linux/spinlock_types_up.h +++ b/include/linux/spinlock_types_up.h @@ -1,10 +1,6 @@ #ifndef __LINUX_SPINLOCK_TYPES_UP_H #define __LINUX_SPINLOCK_TYPES_UP_H -#ifndef __LINUX_SPINLOCK_TYPES_H -# error "please don't include this file directly" -#endif - /* * include/linux/spinlock_types_up.h - spinlock type definitions for UP * diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 440b62f7502e..ee9fefa76106 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -196,6 +196,12 @@ struct platform_s2idle_ops { void (*end)(void); }; +#if defined(CONFIG_SUSPEND) || defined(CONFIG_HIBERNATION) +extern bool pm_in_action; +#else +# define pm_in_action false +#endif + #ifdef CONFIG_SUSPEND extern suspend_state_t mem_sleep_current; extern suspend_state_t mem_sleep_default; diff --git a/include/linux/swait.h b/include/linux/swait.h index bf8cb0dee23c..4ac81dd0c22f 100644 --- a/include/linux/swait.h +++ b/include/linux/swait.h @@ -160,6 +160,7 @@ static inline bool swq_has_sleeper(struct swait_queue_head *wq) extern void swake_up(struct swait_queue_head *q); extern void swake_up_all(struct swait_queue_head *q); extern void swake_up_locked(struct swait_queue_head *q); +extern void swake_up_all_locked(struct swait_queue_head *q); extern void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait); extern void prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait, int state); diff --git a/include/linux/swap.h b/include/linux/swap.h index b51bea64366f..9c3fbe012bc3 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -12,6 +12,7 @@ #include <linux/fs.h> #include <linux/atomic.h> #include <linux/page-flags.h> +#include <linux/locallock.h> #include <asm/page.h> struct notifier_block; @@ -331,6 +332,7 @@ extern unsigned long nr_free_pagecache_pages(void); /* linux/mm/swap.c */ +DECLARE_LOCAL_IRQ_LOCK(swapvec_lock); extern void lru_cache_add(struct page *); extern void lru_cache_add_anon(struct page *page); extern void lru_cache_add_file(struct page *page); diff --git a/include/linux/swork.h b/include/linux/swork.h new file mode 100644 index 000000000000..f175fa9a6016 --- /dev/null +++ b/include/linux/swork.h @@ -0,0 +1,24 @@ +#ifndef _LINUX_SWORK_H +#define _LINUX_SWORK_H + +#include <linux/list.h> + +struct swork_event { + struct list_head item; + unsigned long flags; + void (*func)(struct swork_event *); +}; + +static inline void INIT_SWORK(struct swork_event *event, + void (*func)(struct swork_event *)) +{ + event->flags = 0; + event->func = func; +} + +bool swork_queue(struct swork_event *sev); + +int swork_get(void); +void swork_put(void); + +#endif /* _LINUX_SWORK_H */ diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index 8d8821b3689a..d3fcab20d2a3 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -97,7 +97,17 @@ static inline int test_ti_thread_flag(struct thread_info *ti, int flag) #define test_thread_flag(flag) \ test_ti_thread_flag(current_thread_info(), flag) -#define tif_need_resched() test_thread_flag(TIF_NEED_RESCHED) +#ifdef CONFIG_PREEMPT_LAZY +#define tif_need_resched() (test_thread_flag(TIF_NEED_RESCHED) || \ + test_thread_flag(TIF_NEED_RESCHED_LAZY)) +#define tif_need_resched_now() (test_thread_flag(TIF_NEED_RESCHED)) +#define tif_need_resched_lazy() test_thread_flag(TIF_NEED_RESCHED_LAZY)) + +#else +#define tif_need_resched() test_thread_flag(TIF_NEED_RESCHED) +#define tif_need_resched_now() test_thread_flag(TIF_NEED_RESCHED) +#define tif_need_resched_lazy() 0 +#endif #ifndef CONFIG_HAVE_ARCH_WITHIN_STACK_FRAMES static inline int arch_within_stack_frames(const void * const stack, diff --git a/include/linux/timer.h b/include/linux/timer.h index 7b066fd38248..54627d046b3a 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -172,7 +172,7 @@ extern void add_timer(struct timer_list *timer); extern int try_to_del_timer_sync(struct timer_list *timer); -#ifdef CONFIG_SMP +#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL) extern int del_timer_sync(struct timer_list *timer); #else # define del_timer_sync(t) del_timer(t) diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 78a010e19ed4..c20237c5ab66 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -62,6 +62,9 @@ struct trace_entry { unsigned char flags; unsigned char preempt_count; int pid; + unsigned short migrate_disable; + unsigned short padding; + unsigned char preempt_lazy_count; }; #define TRACE_EVENT_TYPE_MAX \ diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index efe79c1cdd47..128a8489047d 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -185,6 +185,7 @@ static __always_inline void pagefault_disabled_dec(void) */ static inline void pagefault_disable(void) { + migrate_disable(); pagefault_disabled_inc(); /* * make sure to have issued the store before a pagefault @@ -201,6 +202,7 @@ static inline void pagefault_enable(void) */ barrier(); pagefault_disabled_dec(); + migrate_enable(); } /* diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index f25cef84b41d..febee8649220 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -54,7 +54,9 @@ DECLARE_PER_CPU(struct vm_event_state, vm_event_states); */ static inline void __count_vm_event(enum vm_event_item item) { + preempt_disable_rt(); raw_cpu_inc(vm_event_states.event[item]); + preempt_enable_rt(); } static inline void count_vm_event(enum vm_event_item item) @@ -64,7 +66,9 @@ static inline void count_vm_event(enum vm_event_item item) static inline void __count_vm_events(enum vm_event_item item, long delta) { + preempt_disable_rt(); raw_cpu_add(vm_event_states.event[item], delta); + preempt_enable_rt(); } static inline void count_vm_events(enum vm_event_item item, long delta) diff --git a/include/linux/wait.h b/include/linux/wait.h index d9f131ecf708..88d3697b21b4 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -10,6 +10,7 @@ #include <asm/current.h> #include <uapi/linux/wait.h> +#include <linux/atomic.h> typedef struct wait_queue_entry wait_queue_entry_t; @@ -488,8 +489,8 @@ do { \ int __ret = 0; \ struct hrtimer_sleeper __t; \ \ - hrtimer_init_on_stack(&__t.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); \ - hrtimer_init_sleeper(&__t, current); \ + hrtimer_init_sleeper_on_stack(&__t, CLOCK_MONOTONIC, HRTIMER_MODE_REL, \ + current); \ if ((timeout) != KTIME_MAX) \ hrtimer_start_range_ns(&__t.timer, timeout, \ current->timer_slack_ns, \ diff --git a/include/net/gen_stats.h b/include/net/gen_stats.h index 0304ba2ae353..56efde33d016 100644 --- a/include/net/gen_stats.h +++ b/include/net/gen_stats.h @@ -6,6 +6,7 @@ #include <linux/socket.h> #include <linux/rtnetlink.h> #include <linux/pkt_sched.h> +#include <net/net_seq_lock.h> struct gnet_stats_basic_cpu { struct gnet_stats_basic_packed bstats; @@ -36,11 +37,11 @@ int gnet_stats_start_copy_compat(struct sk_buff *skb, int type, spinlock_t *lock, struct gnet_dump *d, int padattr); -int gnet_stats_copy_basic(const seqcount_t *running, +int gnet_stats_copy_basic(net_seqlock_t *running, struct gnet_dump *d, struct gnet_stats_basic_cpu __percpu *cpu, struct gnet_stats_basic_packed *b); -void __gnet_stats_copy_basic(const seqcount_t *running, +void __gnet_stats_copy_basic(net_seqlock_t *running, struct gnet_stats_basic_packed *bstats, struct gnet_stats_basic_cpu __percpu *cpu, struct gnet_stats_basic_packed *b); @@ -60,13 +61,13 @@ int gen_new_estimator(struct gnet_stats_basic_packed *bstats, struct gnet_stats_basic_cpu __percpu *cpu_bstats, struct net_rate_estimator __rcu **rate_est, spinlock_t *stats_lock, - seqcount_t *running, struct nlattr *opt); + net_seqlock_t *running, struct nlattr *opt); void gen_kill_estimator(struct net_rate_estimator __rcu **ptr); int gen_replace_estimator(struct gnet_stats_basic_packed *bstats, struct gnet_stats_basic_cpu __percpu *cpu_bstats, struct net_rate_estimator __rcu **ptr, spinlock_t *stats_lock, - seqcount_t *running, struct nlattr *opt); + net_seqlock_t *running, struct nlattr *opt); bool gen_estimator_active(struct net_rate_estimator __rcu **ptr); bool gen_estimator_read(struct net_rate_estimator __rcu **ptr, struct gnet_stats_rate_est64 *sample); diff --git a/include/net/neighbour.h b/include/net/neighbour.h index beeeed126872..6dd1765e22ec 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -451,7 +451,7 @@ static inline int neigh_hh_bridge(struct hh_cache *hh, struct sk_buff *skb) } #endif -static inline int neigh_hh_output(const struct hh_cache *hh, struct sk_buff *skb) +static inline int neigh_hh_output(struct hh_cache *hh, struct sk_buff *skb) { unsigned int hh_alen = 0; unsigned int seq; @@ -493,7 +493,7 @@ static inline int neigh_hh_output(const struct hh_cache *hh, struct sk_buff *skb static inline int neigh_output(struct neighbour *n, struct sk_buff *skb) { - const struct hh_cache *hh = &n->hh; + struct hh_cache *hh = &n->hh; if ((n->nud_state & NUD_CONNECTED) && hh->hh_len) return neigh_hh_output(hh, skb); @@ -534,7 +534,7 @@ struct neighbour_cb { #define NEIGH_CB(skb) ((struct neighbour_cb *)(skb)->cb) -static inline void neigh_ha_snapshot(char *dst, const struct neighbour *n, +static inline void neigh_ha_snapshot(char *dst, struct neighbour *n, const struct net_device *dev) { unsigned int seq; diff --git a/include/net/net_seq_lock.h b/include/net/net_seq_lock.h new file mode 100644 index 000000000000..a7034298a82a --- /dev/null +++ b/include/net/net_seq_lock.h @@ -0,0 +1,15 @@ +#ifndef __NET_NET_SEQ_LOCK_H__ +#define __NET_NET_SEQ_LOCK_H__ + +#ifdef CONFIG_PREEMPT_RT_BASE +# define net_seqlock_t seqlock_t +# define net_seq_begin(__r) read_seqbegin(__r) +# define net_seq_retry(__r, __s) read_seqretry(__r, __s) + +#else +# define net_seqlock_t seqcount_t +# define net_seq_begin(__r) read_seqcount_begin(__r) +# define net_seq_retry(__r, __s) read_seqcount_retry(__r, __s) +#endif + +#endif diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 4872a9f9a995..2a6c49ab3029 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -10,6 +10,7 @@ #include <linux/percpu.h> #include <linux/dynamic_queue_limits.h> #include <linux/list.h> +#include <net/net_seq_lock.h> #include <linux/refcount.h> #include <linux/workqueue.h> #include <net/gen_stats.h> @@ -97,7 +98,7 @@ struct Qdisc { struct sk_buff_head gso_skb ____cacheline_aligned_in_smp; struct qdisc_skb_head q; struct gnet_stats_basic_packed bstats; - seqcount_t running; + net_seqlock_t running; struct gnet_stats_queue qstats; unsigned long state; struct Qdisc *next_sched; @@ -118,7 +119,11 @@ static inline bool qdisc_is_running(struct Qdisc *qdisc) { if (qdisc->flags & TCQ_F_NOLOCK) return spin_is_locked(&qdisc->seqlock); +#ifdef CONFIG_PREEMPT_RT_BASE + return spin_is_locked(&qdisc->running.lock) ? true : false; +#else return (raw_read_seqcount(&qdisc->running) & 1) ? true : false; +#endif } static inline bool qdisc_run_begin(struct Qdisc *qdisc) @@ -129,17 +134,27 @@ static inline bool qdisc_run_begin(struct Qdisc *qdisc) } else if (qdisc_is_running(qdisc)) { return false; } +#ifdef CONFIG_PREEMPT_RT_BASE + if (try_write_seqlock(&qdisc->running)) + return true; + return false; +#else /* Variant of write_seqcount_begin() telling lockdep a trylock * was attempted. */ raw_write_seqcount_begin(&qdisc->running); seqcount_acquire(&qdisc->running.dep_map, 0, 1, _RET_IP_); return true; +#endif } static inline void qdisc_run_end(struct Qdisc *qdisc) { +#ifdef CONFIG_PREEMPT_RT_BASE + write_sequnlock(&qdisc->running); +#else write_seqcount_end(&qdisc->running); +#endif if (qdisc->flags & TCQ_F_NOLOCK) spin_unlock(&qdisc->seqlock); } @@ -407,7 +422,7 @@ static inline spinlock_t *qdisc_root_sleeping_lock(const struct Qdisc *qdisc) return qdisc_lock(root); } -static inline seqcount_t *qdisc_root_sleeping_running(const struct Qdisc *qdisc) +static inline net_seqlock_t *qdisc_root_sleeping_running(const struct Qdisc *qdisc) { struct Qdisc *root = qdisc_root_sleeping(qdisc); diff --git a/include/soc/at91/atmel_tcb.h b/include/soc/at91/atmel_tcb.h new file mode 100644 index 000000000000..d263ea677225 --- /dev/null +++ b/include/soc/at91/atmel_tcb.h @@ -0,0 +1,216 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2018 Microchip */ + +#ifndef __SOC_ATMEL_TCB_H +#define __SOC_ATMEL_TCB_H + +/* Channel registers */ +#define ATMEL_TC_COFFS(c) ((c) * 0x40) +#define ATMEL_TC_CCR(c) ATMEL_TC_COFFS(c) +#define ATMEL_TC_CMR(c) (ATMEL_TC_COFFS(c) + 0x4) +#define ATMEL_TC_SMMR(c) (ATMEL_TC_COFFS(c) + 0x8) +#define ATMEL_TC_RAB(c) (ATMEL_TC_COFFS(c) + 0xc) +#define ATMEL_TC_CV(c) (ATMEL_TC_COFFS(c) + 0x10) +#define ATMEL_TC_RA(c) (ATMEL_TC_COFFS(c) + 0x14) +#define ATMEL_TC_RB(c) (ATMEL_TC_COFFS(c) + 0x18) +#define ATMEL_TC_RC(c) (ATMEL_TC_COFFS(c) + 0x1c) +#define ATMEL_TC_SR(c) (ATMEL_TC_COFFS(c) + 0x20) +#define ATMEL_TC_IER(c) (ATMEL_TC_COFFS(c) + 0x24) +#define ATMEL_TC_IDR(c) (ATMEL_TC_COFFS(c) + 0x28) +#define ATMEL_TC_IMR(c) (ATMEL_TC_COFFS(c) + 0x2c) +#define ATMEL_TC_EMR(c) (ATMEL_TC_COFFS(c) + 0x30) + +/* Block registers */ +#define ATMEL_TC_BCR 0xc0 +#define ATMEL_TC_BMR 0xc4 +#define ATMEL_TC_QIER 0xc8 +#define ATMEL_TC_QIDR 0xcc +#define ATMEL_TC_QIMR 0xd0 +#define ATMEL_TC_QISR 0xd4 +#define ATMEL_TC_FMR 0xd8 +#define ATMEL_TC_WPMR 0xe4 + +/* CCR fields */ +#define ATMEL_TC_CCR_CLKEN BIT(0) +#define ATMEL_TC_CCR_CLKDIS BIT(1) +#define ATMEL_TC_CCR_SWTRG BIT(2) + +/* Common CMR fields */ +#define ATMEL_TC_CMR_TCLKS_MSK GENMASK(2, 0) +#define ATMEL_TC_CMR_TCLK(x) (x) +#define ATMEL_TC_CMR_XC(x) ((x) + 5) +#define ATMEL_TC_CMR_CLKI BIT(3) +#define ATMEL_TC_CMR_BURST_MSK GENMASK(5, 4) +#define ATMEL_TC_CMR_BURST_XC(x) (((x) + 1) << 4) +#define ATMEL_TC_CMR_WAVE BIT(15) + +/* Capture mode CMR fields */ +#define ATMEL_TC_CMR_LDBSTOP BIT(6) +#define ATMEL_TC_CMR_LDBDIS BIT(7) +#define ATMEL_TC_CMR_ETRGEDG_MSK GENMASK(9, 8) +#define ATMEL_TC_CMR_ETRGEDG_NONE (0 << 8) +#define ATMEL_TC_CMR_ETRGEDG_RISING (1 << 8) +#define ATMEL_TC_CMR_ETRGEDG_FALLING (2 << 8) +#define ATMEL_TC_CMR_ETRGEDG_BOTH (3 << 8) +#define ATMEL_TC_CMR_ABETRG BIT(10) +#define ATMEL_TC_CMR_CPCTRG BIT(14) +#define ATMEL_TC_CMR_LDRA_MSK GENMASK(17, 16) +#define ATMEL_TC_CMR_LDRA_NONE (0 << 16) +#define ATMEL_TC_CMR_LDRA_RISING (1 << 16) +#define ATMEL_TC_CMR_LDRA_FALLING (2 << 16) +#define ATMEL_TC_CMR_LDRA_BOTH (3 << 16) +#define ATMEL_TC_CMR_LDRB_MSK GENMASK(19, 18) +#define ATMEL_TC_CMR_LDRB_NONE (0 << 18) +#define ATMEL_TC_CMR_LDRB_RISING (1 << 18) +#define ATMEL_TC_CMR_LDRB_FALLING (2 << 18) +#define ATMEL_TC_CMR_LDRB_BOTH (3 << 18) +#define ATMEL_TC_CMR_SBSMPLR_MSK GENMASK(22, 20) +#define ATMEL_TC_CMR_SBSMPLR(x) ((x) << 20) + +/* Waveform mode CMR fields */ +#define ATMEL_TC_CMR_CPCSTOP BIT(6) +#define ATMEL_TC_CMR_CPCDIS BIT(7) +#define ATMEL_TC_CMR_EEVTEDG_MSK GENMASK(9, 8) +#define ATMEL_TC_CMR_EEVTEDG_NONE (0 << 8) +#define ATMEL_TC_CMR_EEVTEDG_RISING (1 << 8) +#define ATMEL_TC_CMR_EEVTEDG_FALLING (2 << 8) +#define ATMEL_TC_CMR_EEVTEDG_BOTH (3 << 8) +#define ATMEL_TC_CMR_EEVT_MSK GENMASK(11, 10) +#define ATMEL_TC_CMR_EEVT_XC(x) (((x) + 1) << 10) +#define ATMEL_TC_CMR_ENETRG BIT(12) +#define ATMEL_TC_CMR_WAVESEL_MSK GENMASK(14, 13) +#define ATMEL_TC_CMR_WAVESEL_UP (0 << 13) +#define ATMEL_TC_CMR_WAVESEL_UPDOWN (1 << 13) +#define ATMEL_TC_CMR_WAVESEL_UPRC (2 << 13) +#define ATMEL_TC_CMR_WAVESEL_UPDOWNRC (3 << 13) +#define ATMEL_TC_CMR_ACPA_MSK GENMASK(17, 16) +#define ATMEL_TC_CMR_ACPA(a) (ATMEL_TC_CMR_ACTION_##a << 16) +#define ATMEL_TC_CMR_ACPC_MSK GENMASK(19, 18) +#define ATMEL_TC_CMR_ACPC(a) (ATMEL_TC_CMR_ACTION_##a << 18) +#define ATMEL_TC_CMR_AEEVT_MSK GENMASK(21, 20) +#define ATMEL_TC_CMR_AEEVT(a) (ATMEL_TC_CMR_ACTION_##a << 20) +#define ATMEL_TC_CMR_ASWTRG_MSK GENMASK(23, 22) +#define ATMEL_TC_CMR_ASWTRG(a) (ATMEL_TC_CMR_ACTION_##a << 22) +#define ATMEL_TC_CMR_BCPB_MSK GENMASK(25, 24) +#define ATMEL_TC_CMR_BCPB(a) (ATMEL_TC_CMR_ACTION_##a << 24) +#define ATMEL_TC_CMR_BCPC_MSK GENMASK(27, 26) +#define ATMEL_TC_CMR_BCPC(a) (ATMEL_TC_CMR_ACTION_##a << 26) +#define ATMEL_TC_CMR_BEEVT_MSK GENMASK(29, 28) +#define ATMEL_TC_CMR_BEEVT(a) (ATMEL_TC_CMR_ACTION_##a << 28) +#define ATMEL_TC_CMR_BSWTRG_MSK GENMASK(31, 30) +#define ATMEL_TC_CMR_BSWTRG(a) (ATMEL_TC_CMR_ACTION_##a << 30) +#define ATMEL_TC_CMR_ACTION_NONE 0 +#define ATMEL_TC_CMR_ACTION_SET 1 +#define ATMEL_TC_CMR_ACTION_CLEAR 2 +#define ATMEL_TC_CMR_ACTION_TOGGLE 3 + +/* SMMR fields */ +#define ATMEL_TC_SMMR_GCEN BIT(0) +#define ATMEL_TC_SMMR_DOWN BIT(1) + +/* SR/IER/IDR/IMR fields */ +#define ATMEL_TC_COVFS BIT(0) +#define ATMEL_TC_LOVRS BIT(1) +#define ATMEL_TC_CPAS BIT(2) +#define ATMEL_TC_CPBS BIT(3) +#define ATMEL_TC_CPCS BIT(4) +#define ATMEL_TC_LDRAS BIT(5) +#define ATMEL_TC_LDRBS BIT(6) +#define ATMEL_TC_ETRGS BIT(7) +#define ATMEL_TC_CLKSTA BIT(16) +#define ATMEL_TC_MTIOA BIT(17) +#define ATMEL_TC_MTIOB BIT(18) + +/* EMR fields */ +#define ATMEL_TC_EMR_TRIGSRCA_MSK GENMASK(1, 0) +#define ATMEL_TC_EMR_TRIGSRCA_TIOA 0 +#define ATMEL_TC_EMR_TRIGSRCA_PWMX 1 +#define ATMEL_TC_EMR_TRIGSRCB_MSK GENMASK(5, 4) +#define ATMEL_TC_EMR_TRIGSRCB_TIOB (0 << 4) +#define ATMEL_TC_EMR_TRIGSRCB_PWM (1 << 4) +#define ATMEL_TC_EMR_NOCLKDIV BIT(8) + +/* BCR fields */ +#define ATMEL_TC_BCR_SYNC BIT(0) + +/* BMR fields */ +#define ATMEL_TC_BMR_TCXC_MSK(c) GENMASK(((c) * 2) + 1, (c) * 2) +#define ATMEL_TC_BMR_TCXC(x, c) ((x) << (2 * (c))) +#define ATMEL_TC_BMR_QDEN BIT(8) +#define ATMEL_TC_BMR_POSEN BIT(9) +#define ATMEL_TC_BMR_SPEEDEN BIT(10) +#define ATMEL_TC_BMR_QDTRANS BIT(11) +#define ATMEL_TC_BMR_EDGPHA BIT(12) +#define ATMEL_TC_BMR_INVA BIT(13) +#define ATMEL_TC_BMR_INVB BIT(14) +#define ATMEL_TC_BMR_INVIDX BIT(15) +#define ATMEL_TC_BMR_SWAP BIT(16) +#define ATMEL_TC_BMR_IDXPHB BIT(17) +#define ATMEL_TC_BMR_AUTOC BIT(18) +#define ATMEL_TC_MAXFILT_MSK GENMASK(25, 20) +#define ATMEL_TC_MAXFILT(x) (((x) - 1) << 20) +#define ATMEL_TC_MAXCMP_MSK GENMASK(29, 26) +#define ATMEL_TC_MAXCMP(x) ((x) << 26) + +/* QEDC fields */ +#define ATMEL_TC_QEDC_IDX BIT(0) +#define ATMEL_TC_QEDC_DIRCHG BIT(1) +#define ATMEL_TC_QEDC_QERR BIT(2) +#define ATMEL_TC_QEDC_MPE BIT(3) +#define ATMEL_TC_QEDC_DIR BIT(8) + +/* FMR fields */ +#define ATMEL_TC_FMR_ENCF(x) BIT(x) + +/* WPMR fields */ +#define ATMEL_TC_WPMR_WPKEY (0x54494d << 8) +#define ATMEL_TC_WPMR_WPEN BIT(0) + +static inline struct clk *tcb_clk_get(struct device_node *node, int channel) +{ + struct clk *clk; + char clk_name[] = "t0_clk"; + + clk_name[1] += channel; + clk = of_clk_get_by_name(node->parent, clk_name); + if (!IS_ERR(clk)) + return clk; + + return of_clk_get_by_name(node->parent, "t0_clk"); +} + +static inline int tcb_irq_get(struct device_node *node, int channel) +{ + int irq; + + irq = of_irq_get(node->parent, channel); + if (irq > 0) + return irq; + + return of_irq_get(node->parent, 0); +} + +static const u8 atmel_tc_divisors[5] = { 2, 8, 32, 128, 0, }; + +struct atmel_tcb_info { + int bits; +}; + +static const struct atmel_tcb_info atmel_tcb_infos[] = { + { .bits = 16 }, + { .bits = 32 }, +}; + +static const struct of_device_id atmel_tcb_dt_ids[] = { + { + .compatible = "atmel,at91rm9200-tcb", + .data = &atmel_tcb_infos[0], + }, { + .compatible = "atmel,at91sam9x5-tcb", + .data = &atmel_tcb_infos[1], + }, { + /* sentinel */ + } +}; + +#endif /* __SOC_ATMEL_TCB_H */ diff --git a/include/trace/events/cgroup.h b/include/trace/events/cgroup.h index d74722c2ac8b..a401ff5e7847 100644 --- a/include/trace/events/cgroup.h +++ b/include/trace/events/cgroup.h @@ -53,24 +53,22 @@ DEFINE_EVENT(cgroup_root, cgroup_remount, DECLARE_EVENT_CLASS(cgroup, - TP_PROTO(struct cgroup *cgrp), + TP_PROTO(struct cgroup *cgrp, const char *path), - TP_ARGS(cgrp), + TP_ARGS(cgrp, path), TP_STRUCT__entry( __field( int, root ) __field( int, id ) __field( int, level ) - __dynamic_array(char, path, - cgroup_path(cgrp, NULL, 0) + 1) + __string( path, path ) ), TP_fast_assign( __entry->root = cgrp->root->hierarchy_id; __entry->id = cgrp->id; __entry->level = cgrp->level; - cgroup_path(cgrp, __get_dynamic_array(path), - __get_dynamic_array_len(path)); + __assign_str(path, path); ), TP_printk("root=%d id=%d level=%d path=%s", @@ -79,45 +77,45 @@ DECLARE_EVENT_CLASS(cgroup, DEFINE_EVENT(cgroup, cgroup_mkdir, - TP_PROTO(struct cgroup *cgroup), + TP_PROTO(struct cgroup *cgrp, const char *path), - TP_ARGS(cgroup) + TP_ARGS(cgrp, path) ); DEFINE_EVENT(cgroup, cgroup_rmdir, - TP_PROTO(struct cgroup *cgroup), + TP_PROTO(struct cgroup *cgrp, const char *path), - TP_ARGS(cgroup) + TP_ARGS(cgrp, path) ); DEFINE_EVENT(cgroup, cgroup_release, - TP_PROTO(struct cgroup *cgroup), + TP_PROTO(struct cgroup *cgrp, const char *path), - TP_ARGS(cgroup) + TP_ARGS(cgrp, path) ); DEFINE_EVENT(cgroup, cgroup_rename, - TP_PROTO(struct cgroup *cgroup), + TP_PROTO(struct cgroup *cgrp, const char *path), - TP_ARGS(cgroup) + TP_ARGS(cgrp, path) ); DECLARE_EVENT_CLASS(cgroup_migrate, - TP_PROTO(struct cgroup *dst_cgrp, struct task_struct *task, bool threadgroup), + TP_PROTO(struct cgroup *dst_cgrp, const char *path, + struct task_struct *task, bool threadgroup), - TP_ARGS(dst_cgrp, task, threadgroup), + TP_ARGS(dst_cgrp, path, task, threadgroup), TP_STRUCT__entry( __field( int, dst_root ) __field( int, dst_id ) __field( int, dst_level ) - __dynamic_array(char, dst_path, - cgroup_path(dst_cgrp, NULL, 0) + 1) __field( int, pid ) + __string( dst_path, path ) __string( comm, task->comm ) ), @@ -125,8 +123,7 @@ DECLARE_EVENT_CLASS(cgroup_migrate, __entry->dst_root = dst_cgrp->root->hierarchy_id; __entry->dst_id = dst_cgrp->id; __entry->dst_level = dst_cgrp->level; - cgroup_path(dst_cgrp, __get_dynamic_array(dst_path), - __get_dynamic_array_len(dst_path)); + __assign_str(dst_path, path); __entry->pid = task->pid; __assign_str(comm, task->comm); ), @@ -138,16 +135,18 @@ DECLARE_EVENT_CLASS(cgroup_migrate, DEFINE_EVENT(cgroup_migrate, cgroup_attach_task, - TP_PROTO(struct cgroup *dst_cgrp, struct task_struct *task, bool threadgroup), + TP_PROTO(struct cgroup *dst_cgrp, const char *path, + struct task_struct *task, bool threadgroup), - TP_ARGS(dst_cgrp, task, threadgroup) + TP_ARGS(dst_cgrp, path, task, threadgroup) ); DEFINE_EVENT(cgroup_migrate, cgroup_transfer_tasks, - TP_PROTO(struct cgroup *dst_cgrp, struct task_struct *task, bool threadgroup), + TP_PROTO(struct cgroup *dst_cgrp, const char *path, + struct task_struct *task, bool threadgroup), - TP_ARGS(dst_cgrp, task, threadgroup) + TP_ARGS(dst_cgrp, path, task, threadgroup) ); #endif /* _TRACE_CGROUP_H */ diff --git a/init/Kconfig b/init/Kconfig index 2a48832fd40e..a0ddf5c2376c 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -741,6 +741,7 @@ config CFS_BANDWIDTH config RT_GROUP_SCHED bool "Group scheduling for SCHED_RR/FIFO" depends on CGROUP_SCHED + depends on !PREEMPT_RT_FULL default n help This feature lets you explicitly allocate real CPU bandwidth @@ -1616,6 +1617,7 @@ choice config SLAB bool "SLAB" + depends on !PREEMPT_RT_FULL select HAVE_HARDENED_USERCOPY_ALLOCATOR help The regular slab allocator that is established and known to work @@ -1636,6 +1638,7 @@ config SLUB config SLOB depends on EXPERT bool "SLOB (Simple Allocator)" + depends on !PREEMPT_RT_FULL help SLOB replaces the stock allocator with a drastically simpler allocator. SLOB is generally more space efficient but @@ -1677,7 +1680,7 @@ config SLAB_FREELIST_HARDENED config SLUB_CPU_PARTIAL default y - depends on SLUB && SMP + depends on SLUB && SMP && !PREEMPT_RT_FULL bool "SLUB per cpu partial cache" help Per cpu partial caches accellerate objects allocation and freeing diff --git a/init/Makefile b/init/Makefile index a3e5ce2bcf08..7779232563ae 100644 --- a/init/Makefile +++ b/init/Makefile @@ -34,4 +34,4 @@ silent_chk_compile.h = : include/generated/compile.h: FORCE @$($(quiet)chk_compile.h) $(Q)$(CONFIG_SHELL) $(srctree)/scripts/mkcompile_h $@ \ - "$(UTS_MACHINE)" "$(CONFIG_SMP)" "$(CONFIG_PREEMPT)" "$(CC) $(KBUILD_CFLAGS)" + "$(UTS_MACHINE)" "$(CONFIG_SMP)" "$(CONFIG_PREEMPT)" "$(CONFIG_PREEMPT_RT_FULL)" "$(CC) $(KBUILD_CFLAGS)" diff --git a/init/init_task.c b/init/init_task.c index 74f60baa2799..588a8ad289ab 100644 --- a/init/init_task.c +++ b/init/init_task.c @@ -43,6 +43,12 @@ static struct sighand_struct init_sighand = { .signalfd_wqh = __WAIT_QUEUE_HEAD_INITIALIZER(init_sighand.signalfd_wqh), }; +#if defined(CONFIG_POSIX_TIMERS) && defined(CONFIG_PREEMPT_RT_BASE) +# define INIT_TIMER_LIST .posix_timer_list = NULL, +#else +# define INIT_TIMER_LIST +#endif + /* * Set up the first task table, touch at your own risk!. Base=0, * limit=0x1fffff (=2MB) @@ -64,7 +70,8 @@ struct task_struct init_task .static_prio = MAX_PRIO - 20, .normal_prio = MAX_PRIO - 20, .policy = SCHED_NORMAL, - .cpus_allowed = CPU_MASK_ALL, + .cpus_ptr = &init_task.cpus_mask, + .cpus_mask = CPU_MASK_ALL, .nr_cpus_allowed= NR_CPUS, .mm = NULL, .active_mm = &init_mm, @@ -111,6 +118,7 @@ struct task_struct init_task INIT_CPU_TIMERS(init_task) .pi_lock = __RAW_SPIN_LOCK_UNLOCKED(init_task.pi_lock), .timer_slack_ns = 50000, /* 50 usec default slack */ + INIT_TIMER_LIST .pids = { [PIDTYPE_PID] = INIT_PID_LINK(PIDTYPE_PID), [PIDTYPE_PGID] = INIT_PID_LINK(PIDTYPE_PGID), diff --git a/init/main.c b/init/main.c index 66dd87f4663d..5f3778d2f830 100644 --- a/init/main.c +++ b/init/main.c @@ -561,6 +561,7 @@ asmlinkage __visible void __init start_kernel(void) setup_command_line(command_line); setup_nr_cpu_ids(); setup_per_cpu_areas(); + softirq_early_init(); smp_prepare_boot_cpu(); /* arch-specific boot-cpu hooks */ boot_cpu_hotplug_init(); diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks index 84d882f3e299..af27c4000812 100644 --- a/kernel/Kconfig.locks +++ b/kernel/Kconfig.locks @@ -225,11 +225,11 @@ config ARCH_SUPPORTS_ATOMIC_RMW config MUTEX_SPIN_ON_OWNER def_bool y - depends on SMP && ARCH_SUPPORTS_ATOMIC_RMW + depends on SMP && ARCH_SUPPORTS_ATOMIC_RMW && !PREEMPT_RT_FULL config RWSEM_SPIN_ON_OWNER def_bool y - depends on SMP && RWSEM_XCHGADD_ALGORITHM && ARCH_SUPPORTS_ATOMIC_RMW + depends on SMP && RWSEM_XCHGADD_ALGORITHM && ARCH_SUPPORTS_ATOMIC_RMW && !PREEMPT_RT_FULL config LOCK_SPIN_ON_OWNER def_bool y diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt index 3f9c97419f02..11dbe26a8279 100644 --- a/kernel/Kconfig.preempt +++ b/kernel/Kconfig.preempt @@ -1,3 +1,16 @@ +config PREEMPT + bool + select PREEMPT_COUNT + +config PREEMPT_RT_BASE + bool + select PREEMPT + +config HAVE_PREEMPT_LAZY + bool + +config PREEMPT_LAZY + def_bool y if HAVE_PREEMPT_LAZY && PREEMPT_RT_FULL choice prompt "Preemption Model" @@ -33,9 +46,9 @@ config PREEMPT_VOLUNTARY Select this if you are building a kernel for a desktop system. -config PREEMPT +config PREEMPT__LL bool "Preemptible Kernel (Low-Latency Desktop)" - select PREEMPT_COUNT + select PREEMPT select UNINLINE_SPIN_UNLOCK if !ARCH_INLINE_SPIN_UNLOCK help This option reduces the latency of the kernel by making @@ -52,6 +65,22 @@ config PREEMPT embedded system with latency requirements in the milliseconds range. +config PREEMPT_RTB + bool "Preemptible Kernel (Basic RT)" + select PREEMPT_RT_BASE + help + This option is basically the same as (Low-Latency Desktop) but + enables changes which are preliminary for the full preemptible + RT kernel. + +config PREEMPT_RT_FULL + bool "Fully Preemptible Kernel (RT)" + depends on IRQ_FORCED_THREADING + select PREEMPT_RT_BASE + select PREEMPT_RCU + help + All and everything + endchoice config PREEMPT_COUNT diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h index 77ff1cd6a252..75568fcf2180 100644 --- a/kernel/cgroup/cgroup-internal.h +++ b/kernel/cgroup/cgroup-internal.h @@ -8,6 +8,32 @@ #include <linux/list.h> #include <linux/refcount.h> +#define TRACE_CGROUP_PATH_LEN 1024 +extern spinlock_t trace_cgroup_path_lock; +extern char trace_cgroup_path[TRACE_CGROUP_PATH_LEN]; + +/* + * cgroup_path() takes a spin lock. It is good practice not to take + * spin locks within trace point handlers, as they are mostly hidden + * from normal view. As cgroup_path() can take the kernfs_rename_lock + * spin lock, it is best to not call that function from the trace event + * handler. + * + * Note: trace_cgroup_##type##_enabled() is a static branch that will only + * be set when the trace event is enabled. + */ +#define TRACE_CGROUP_PATH(type, cgrp, ...) \ + do { \ + if (trace_cgroup_##type##_enabled()) { \ + spin_lock(&trace_cgroup_path_lock); \ + cgroup_path(cgrp, trace_cgroup_path, \ + TRACE_CGROUP_PATH_LEN); \ + trace_cgroup_##type(cgrp, trace_cgroup_path, \ + ##__VA_ARGS__); \ + spin_unlock(&trace_cgroup_path_lock); \ + } \ + } while (0) + /* * A cgroup can be associated with multiple css_sets as different tasks may * belong to different cgroups on different hierarchies. In the other diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index 8b4f0768efd6..51063e7a93c2 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -135,7 +135,7 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from) if (task) { ret = cgroup_migrate(task, false, &mgctx); if (!ret) - trace_cgroup_transfer_tasks(to, task, false); + TRACE_CGROUP_PATH(transfer_tasks, to, task, false); put_task_struct(task); } } while (task && !ret); @@ -865,7 +865,7 @@ static int cgroup1_rename(struct kernfs_node *kn, struct kernfs_node *new_parent ret = kernfs_rename(kn, new_parent, new_name_str); if (!ret) - trace_cgroup_rename(cgrp); + TRACE_CGROUP_PATH(rename, cgrp); mutex_unlock(&cgroup_mutex); diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 97ca037a60a7..829915249f04 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -83,6 +83,9 @@ EXPORT_SYMBOL_GPL(cgroup_mutex); EXPORT_SYMBOL_GPL(css_set_lock); #endif +DEFINE_SPINLOCK(trace_cgroup_path_lock); +char trace_cgroup_path[TRACE_CGROUP_PATH_LEN]; + /* * Protects cgroup_idr and css_idr so that IDs can be released without * grabbing cgroup_mutex. @@ -2641,7 +2644,7 @@ int cgroup_attach_task(struct cgroup *dst_cgrp, struct task_struct *leader, cgroup_migrate_finish(&mgctx); if (!ret) - trace_cgroup_attach_task(dst_cgrp, leader, threadgroup); + TRACE_CGROUP_PATH(attach_task, dst_cgrp, leader, threadgroup); return ret; } @@ -4623,10 +4626,10 @@ static void css_free_rwork_fn(struct work_struct *work) } } -static void css_release_work_fn(struct work_struct *work) +static void css_release_work_fn(struct swork_event *sev) { struct cgroup_subsys_state *css = - container_of(work, struct cgroup_subsys_state, destroy_work); + container_of(sev, struct cgroup_subsys_state, destroy_swork); struct cgroup_subsys *ss = css->ss; struct cgroup *cgrp = css->cgroup; @@ -4649,7 +4652,7 @@ static void css_release_work_fn(struct work_struct *work) struct cgroup *tcgrp; /* cgroup release path */ - trace_cgroup_release(cgrp); + TRACE_CGROUP_PATH(release, cgrp); if (cgroup_on_dfl(cgrp)) cgroup_rstat_flush(cgrp); @@ -4688,8 +4691,8 @@ static void css_release(struct percpu_ref *ref) struct cgroup_subsys_state *css = container_of(ref, struct cgroup_subsys_state, refcnt); - INIT_WORK(&css->destroy_work, css_release_work_fn); - queue_work(cgroup_destroy_wq, &css->destroy_work); + INIT_SWORK(&css->destroy_swork, css_release_work_fn); + swork_queue(&css->destroy_swork); } static void init_and_link_css(struct cgroup_subsys_state *css, @@ -4996,7 +4999,7 @@ int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, umode_t mode) if (ret) goto out_destroy; - trace_cgroup_mkdir(cgrp); + TRACE_CGROUP_PATH(mkdir, cgrp); /* let's create and online css's */ kernfs_activate(kn); @@ -5186,9 +5189,8 @@ int cgroup_rmdir(struct kernfs_node *kn) return 0; ret = cgroup_destroy_locked(cgrp); - if (!ret) - trace_cgroup_rmdir(cgrp); + TRACE_CGROUP_PATH(rmdir, cgrp); cgroup_kn_unlock(kn); return ret; @@ -5416,6 +5418,7 @@ static int __init cgroup_wq_init(void) */ cgroup_destroy_wq = alloc_workqueue("cgroup_destroy", 0, 1); BUG_ON(!cgroup_destroy_wq); + BUG_ON(swork_get()); return 0; } core_initcall(cgroup_wq_init); diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 266f10cb7222..3e5d90076368 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -288,7 +288,7 @@ static struct cpuset top_cpuset = { */ static DEFINE_MUTEX(cpuset_mutex); -static DEFINE_SPINLOCK(callback_lock); +static DEFINE_RAW_SPINLOCK(callback_lock); static struct workqueue_struct *cpuset_migrate_mm_wq; @@ -922,9 +922,9 @@ static void update_cpumasks_hier(struct cpuset *cs, struct cpumask *new_cpus) continue; rcu_read_unlock(); - spin_lock_irq(&callback_lock); + raw_spin_lock_irq(&callback_lock); cpumask_copy(cp->effective_cpus, new_cpus); - spin_unlock_irq(&callback_lock); + raw_spin_unlock_irq(&callback_lock); WARN_ON(!is_in_v2_mode() && !cpumask_equal(cp->cpus_allowed, cp->effective_cpus)); @@ -989,9 +989,9 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs, if (retval < 0) return retval; - spin_lock_irq(&callback_lock); + raw_spin_lock_irq(&callback_lock); cpumask_copy(cs->cpus_allowed, trialcs->cpus_allowed); - spin_unlock_irq(&callback_lock); + raw_spin_unlock_irq(&callback_lock); /* use trialcs->cpus_allowed as a temp variable */ update_cpumasks_hier(cs, trialcs->cpus_allowed); @@ -1175,9 +1175,9 @@ static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems) continue; rcu_read_unlock(); - spin_lock_irq(&callback_lock); + raw_spin_lock_irq(&callback_lock); cp->effective_mems = *new_mems; - spin_unlock_irq(&callback_lock); + raw_spin_unlock_irq(&callback_lock); WARN_ON(!is_in_v2_mode() && !nodes_equal(cp->mems_allowed, cp->effective_mems)); @@ -1245,9 +1245,9 @@ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs, if (retval < 0) goto done; - spin_lock_irq(&callback_lock); + raw_spin_lock_irq(&callback_lock); cs->mems_allowed = trialcs->mems_allowed; - spin_unlock_irq(&callback_lock); + raw_spin_unlock_irq(&callback_lock); /* use trialcs->mems_allowed as a temp variable */ update_nodemasks_hier(cs, &trialcs->mems_allowed); @@ -1338,9 +1338,9 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, spread_flag_changed = ((is_spread_slab(cs) != is_spread_slab(trialcs)) || (is_spread_page(cs) != is_spread_page(trialcs))); - spin_lock_irq(&callback_lock); + raw_spin_lock_irq(&callback_lock); cs->flags = trialcs->flags; - spin_unlock_irq(&callback_lock); + raw_spin_unlock_irq(&callback_lock); if (!cpumask_empty(trialcs->cpus_allowed) && balance_flag_changed) rebuild_sched_domains_locked(); @@ -1755,7 +1755,7 @@ static int cpuset_common_seq_show(struct seq_file *sf, void *v) cpuset_filetype_t type = seq_cft(sf)->private; int ret = 0; - spin_lock_irq(&callback_lock); + raw_spin_lock_irq(&callback_lock); switch (type) { case FILE_CPULIST: @@ -1774,7 +1774,7 @@ static int cpuset_common_seq_show(struct seq_file *sf, void *v) ret = -EINVAL; } - spin_unlock_irq(&callback_lock); + raw_spin_unlock_irq(&callback_lock); return ret; } @@ -1989,12 +1989,12 @@ static int cpuset_css_online(struct cgroup_subsys_state *css) cpuset_inc(); - spin_lock_irq(&callback_lock); + raw_spin_lock_irq(&callback_lock); if (is_in_v2_mode()) { cpumask_copy(cs->effective_cpus, parent->effective_cpus); cs->effective_mems = parent->effective_mems; } - spin_unlock_irq(&callback_lock); + raw_spin_unlock_irq(&callback_lock); if (!test_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags)) goto out_unlock; @@ -2021,12 +2021,12 @@ static int cpuset_css_online(struct cgroup_subsys_state *css) } rcu_read_unlock(); - spin_lock_irq(&callback_lock); + raw_spin_lock_irq(&callback_lock); cs->mems_allowed = parent->mems_allowed; cs->effective_mems = parent->mems_allowed; cpumask_copy(cs->cpus_allowed, parent->cpus_allowed); cpumask_copy(cs->effective_cpus, parent->cpus_allowed); - spin_unlock_irq(&callback_lock); + raw_spin_unlock_irq(&callback_lock); out_unlock: mutex_unlock(&cpuset_mutex); return 0; @@ -2065,7 +2065,7 @@ static void cpuset_css_free(struct cgroup_subsys_state *css) static void cpuset_bind(struct cgroup_subsys_state *root_css) { mutex_lock(&cpuset_mutex); - spin_lock_irq(&callback_lock); + raw_spin_lock_irq(&callback_lock); if (is_in_v2_mode()) { cpumask_copy(top_cpuset.cpus_allowed, cpu_possible_mask); @@ -2076,7 +2076,7 @@ static void cpuset_bind(struct cgroup_subsys_state *root_css) top_cpuset.mems_allowed = top_cpuset.effective_mems; } - spin_unlock_irq(&callback_lock); + raw_spin_unlock_irq(&callback_lock); mutex_unlock(&cpuset_mutex); } @@ -2090,7 +2090,7 @@ static void cpuset_fork(struct task_struct *task) if (task_css_is_root(task, cpuset_cgrp_id)) return; - set_cpus_allowed_ptr(task, ¤t->cpus_allowed); + set_cpus_allowed_ptr(task, current->cpus_ptr); task->mems_allowed = current->mems_allowed; } @@ -2174,12 +2174,12 @@ hotplug_update_tasks_legacy(struct cpuset *cs, { bool is_empty; - spin_lock_irq(&callback_lock); + raw_spin_lock_irq(&callback_lock); cpumask_copy(cs->cpus_allowed, new_cpus); cpumask_copy(cs->effective_cpus, new_cpus); cs->mems_allowed = *new_mems; cs->effective_mems = *new_mems; - spin_unlock_irq(&callback_lock); + raw_spin_unlock_irq(&callback_lock); /* * Don't call update_tasks_cpumask() if the cpuset becomes empty, @@ -2216,10 +2216,10 @@ hotplug_update_tasks(struct cpuset *cs, if (nodes_empty(*new_mems)) *new_mems = parent_cs(cs)->effective_mems; - spin_lock_irq(&callback_lock); + raw_spin_lock_irq(&callback_lock); cpumask_copy(cs->effective_cpus, new_cpus); cs->effective_mems = *new_mems; - spin_unlock_irq(&callback_lock); + raw_spin_unlock_irq(&callback_lock); if (cpus_updated) update_tasks_cpumask(cs); @@ -2312,21 +2312,21 @@ static void cpuset_hotplug_workfn(struct work_struct *work) /* synchronize cpus_allowed to cpu_active_mask */ if (cpus_updated) { - spin_lock_irq(&callback_lock); + raw_spin_lock_irq(&callback_lock); if (!on_dfl) cpumask_copy(top_cpuset.cpus_allowed, &new_cpus); cpumask_copy(top_cpuset.effective_cpus, &new_cpus); - spin_unlock_irq(&callback_lock); + raw_spin_unlock_irq(&callback_lock); /* we don't mess with cpumasks of tasks in top_cpuset */ } /* synchronize mems_allowed to N_MEMORY */ if (mems_updated) { - spin_lock_irq(&callback_lock); + raw_spin_lock_irq(&callback_lock); if (!on_dfl) top_cpuset.mems_allowed = new_mems; top_cpuset.effective_mems = new_mems; - spin_unlock_irq(&callback_lock); + raw_spin_unlock_irq(&callback_lock); update_tasks_nodemask(&top_cpuset); } @@ -2425,11 +2425,11 @@ void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask) { unsigned long flags; - spin_lock_irqsave(&callback_lock, flags); + raw_spin_lock_irqsave(&callback_lock, flags); rcu_read_lock(); guarantee_online_cpus(task_cs(tsk), pmask); rcu_read_unlock(); - spin_unlock_irqrestore(&callback_lock, flags); + raw_spin_unlock_irqrestore(&callback_lock, flags); } void cpuset_cpus_allowed_fallback(struct task_struct *tsk) @@ -2477,11 +2477,11 @@ nodemask_t cpuset_mems_allowed(struct task_struct *tsk) nodemask_t mask; unsigned long flags; - spin_lock_irqsave(&callback_lock, flags); + raw_spin_lock_irqsave(&callback_lock, flags); rcu_read_lock(); guarantee_online_mems(task_cs(tsk), &mask); rcu_read_unlock(); - spin_unlock_irqrestore(&callback_lock, flags); + raw_spin_unlock_irqrestore(&callback_lock, flags); return mask; } @@ -2573,14 +2573,14 @@ bool __cpuset_node_allowed(int node, gfp_t gfp_mask) return true; /* Not hardwall and node outside mems_allowed: scan up cpusets */ - spin_lock_irqsave(&callback_lock, flags); + raw_spin_lock_irqsave(&callback_lock, flags); rcu_read_lock(); cs = nearest_hardwall_ancestor(task_cs(current)); allowed = node_isset(node, cs->mems_allowed); rcu_read_unlock(); - spin_unlock_irqrestore(&callback_lock, flags); + raw_spin_unlock_irqrestore(&callback_lock, flags); return allowed; } diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c index bb95a35e8c2d..3266a9781b4e 100644 --- a/kernel/cgroup/rstat.c +++ b/kernel/cgroup/rstat.c @@ -159,8 +159,9 @@ static void cgroup_rstat_flush_locked(struct cgroup *cgrp, bool may_sleep) raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu); struct cgroup *pos = NULL; + unsigned long flags; - raw_spin_lock(cpu_lock); + raw_spin_lock_irqsave(cpu_lock, flags); while ((pos = cgroup_rstat_cpu_pop_updated(pos, cgrp, cpu))) { struct cgroup_subsys_state *css; @@ -172,7 +173,7 @@ static void cgroup_rstat_flush_locked(struct cgroup *cgrp, bool may_sleep) css->ss->css_rstat_flush(css, cpu); rcu_read_unlock(); } - raw_spin_unlock(cpu_lock); + raw_spin_unlock_irqrestore(cpu_lock, flags); /* if @may_sleep, play nice and yield if necessary */ if (may_sleep && (need_resched() || diff --git a/kernel/cpu.c b/kernel/cpu.c index 59e418f192d2..edbb3edc6d83 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -75,6 +75,11 @@ static DEFINE_PER_CPU(struct cpuhp_cpu_state, cpuhp_state) = { .fail = CPUHP_INVALID, }; +#if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PREEMPT_RT_FULL) +static DEFINE_PER_CPU(struct rt_rw_lock, cpuhp_pin_lock) = \ + __RWLOCK_RT_INITIALIZER(cpuhp_pin_lock); +#endif + #if defined(CONFIG_LOCKDEP) && defined(CONFIG_SMP) static struct lockdep_map cpuhp_state_up_map = STATIC_LOCKDEP_MAP_INIT("cpuhp_state-up", &cpuhp_state_up_map); @@ -284,6 +289,55 @@ static int cpu_hotplug_disabled; #ifdef CONFIG_HOTPLUG_CPU +/** + * pin_current_cpu - Prevent the current cpu from being unplugged + */ +void pin_current_cpu(void) +{ +#ifdef CONFIG_PREEMPT_RT_FULL + struct rt_rw_lock *cpuhp_pin; + unsigned int cpu; + int ret; + +again: + cpuhp_pin = this_cpu_ptr(&cpuhp_pin_lock); + ret = __read_rt_trylock(cpuhp_pin); + if (ret) { + current->pinned_on_cpu = smp_processor_id(); + return; + } + cpu = smp_processor_id(); + preempt_lazy_enable(); + preempt_enable(); + + __read_rt_lock(cpuhp_pin); + + preempt_disable(); + preempt_lazy_disable(); + if (cpu != smp_processor_id()) { + __read_rt_unlock(cpuhp_pin); + goto again; + } + current->pinned_on_cpu = cpu; +#endif +} + +/** + * unpin_current_cpu - Allow unplug of current cpu + */ +void unpin_current_cpu(void) +{ +#ifdef CONFIG_PREEMPT_RT_FULL + struct rt_rw_lock *cpuhp_pin = this_cpu_ptr(&cpuhp_pin_lock); + + if (WARN_ON(current->pinned_on_cpu != smp_processor_id())) + cpuhp_pin = per_cpu_ptr(&cpuhp_pin_lock, current->pinned_on_cpu); + + current->pinned_on_cpu = -1; + __read_rt_unlock(cpuhp_pin); +#endif +} + DEFINE_STATIC_PERCPU_RWSEM(cpu_hotplug_lock); void cpus_read_lock(void) @@ -871,6 +925,9 @@ static int take_cpu_down(void *_param) static int takedown_cpu(unsigned int cpu) { +#ifdef CONFIG_PREEMPT_RT_FULL + struct rt_rw_lock *cpuhp_pin = per_cpu_ptr(&cpuhp_pin_lock, cpu); +#endif struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int err; @@ -883,11 +940,18 @@ static int takedown_cpu(unsigned int cpu) */ irq_lock_sparse(); +#ifdef CONFIG_PREEMPT_RT_FULL + __write_rt_lock(cpuhp_pin); +#endif + /* * So now all preempt/rcu users must observe !cpu_active(). */ err = stop_machine_cpuslocked(take_cpu_down, NULL, cpumask_of(cpu)); if (err) { +#ifdef CONFIG_PREEMPT_RT_FULL + __write_rt_unlock(cpuhp_pin); +#endif /* CPU refused to die */ irq_unlock_sparse(); /* Unpark the hotplug thread so we can rollback there */ @@ -906,6 +970,9 @@ static int takedown_cpu(unsigned int cpu) wait_for_ap_thread(st, false); BUG_ON(st->state != CPUHP_AP_IDLE_DEAD); +#ifdef CONFIG_PREEMPT_RT_FULL + __write_rt_unlock(cpuhp_pin); +#endif /* Interrupts are moved away from the dying cpu, reenable alloc/free */ irq_unlock_sparse(); diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c index 6a4b41484afe..197cb422f6e1 100644 --- a/kernel/debug/kdb/kdb_io.c +++ b/kernel/debug/kdb/kdb_io.c @@ -857,9 +857,11 @@ int kdb_printf(const char *fmt, ...) va_list ap; int r; + kdb_trap_printk++; va_start(ap, fmt); r = vkdb_printf(KDB_MSGSRC_INTERNAL, fmt, ap); va_end(ap); + kdb_trap_printk--; return r; } diff --git a/kernel/events/core.c b/kernel/events/core.c index 62438d9601c4..cc2c07b3287c 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1102,7 +1102,7 @@ static void __perf_mux_hrtimer_init(struct perf_cpu_context *cpuctx, int cpu) cpuctx->hrtimer_interval = ns_to_ktime(NSEC_PER_MSEC * interval); raw_spin_lock_init(&cpuctx->hrtimer_lock); - hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED); + hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED_HARD); timer->function = perf_mux_hrtimer_handler; } @@ -9221,7 +9221,7 @@ static void perf_swevent_init_hrtimer(struct perf_event *event) if (!is_sampling_event(event)) return; - hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD); hwc->hrtimer.function = perf_swevent_hrtimer; /* diff --git a/kernel/exit.c b/kernel/exit.c index 5f0e1fb0f37c..a5dd0b87d8fe 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -159,7 +159,7 @@ static void __exit_signal(struct task_struct *tsk) * Do this under ->siglock, we can race with another thread * doing sigqueue_free() if we have SIGQUEUE_PREALLOC signals. */ - flush_sigqueue(&tsk->pending); + flush_task_sigqueue(tsk); tsk->sighand = NULL; spin_unlock(&sighand->siglock); diff --git a/kernel/fork.c b/kernel/fork.c index 68441e43389d..c9b4001f36d2 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -40,6 +40,7 @@ #include <linux/hmm.h> #include <linux/fs.h> #include <linux/mm.h> +#include <linux/kprobes.h> #include <linux/vmacache.h> #include <linux/nsproxy.h> #include <linux/capability.h> @@ -636,6 +637,19 @@ void __mmdrop(struct mm_struct *mm) } EXPORT_SYMBOL_GPL(__mmdrop); +#ifdef CONFIG_PREEMPT_RT_BASE +/* + * RCU callback for delayed mm drop. Not strictly rcu, but we don't + * want another facility to make this work. + */ +void __mmdrop_delayed(struct rcu_head *rhp) +{ + struct mm_struct *mm = container_of(rhp, struct mm_struct, delayed_drop); + + __mmdrop(mm); +} +#endif + static void mmdrop_async_fn(struct work_struct *work) { struct mm_struct *mm; @@ -670,13 +684,24 @@ static inline void put_signal_struct(struct signal_struct *sig) if (atomic_dec_and_test(&sig->sigcnt)) free_signal_struct(sig); } - +#ifdef CONFIG_PREEMPT_RT_BASE +static +#endif void __put_task_struct(struct task_struct *tsk) { WARN_ON(!tsk->exit_state); WARN_ON(atomic_read(&tsk->usage)); WARN_ON(tsk == current); + /* + * Remove function-return probe instances associated with this + * task and put them back on the free list. + */ + kprobe_flush_task(tsk); + + /* Task is done with its stack. */ + put_task_stack(tsk); + cgroup_free(tsk); task_numa_free(tsk); security_task_free(tsk); @@ -687,7 +712,18 @@ void __put_task_struct(struct task_struct *tsk) if (!profile_handoff_task(tsk)) free_task(tsk); } +#ifndef CONFIG_PREEMPT_RT_BASE EXPORT_SYMBOL_GPL(__put_task_struct); +#else +void __put_task_struct_cb(struct rcu_head *rhp) +{ + struct task_struct *tsk = container_of(rhp, struct task_struct, put_rcu); + + __put_task_struct(tsk); + +} +EXPORT_SYMBOL_GPL(__put_task_struct_cb); +#endif void __init __weak arch_task_cache_init(void) { } @@ -844,6 +880,8 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) #ifdef CONFIG_STACKPROTECTOR tsk->stack_canary = get_random_canary(); #endif + if (orig->cpus_ptr == &orig->cpus_mask) + tsk->cpus_ptr = &tsk->cpus_mask; /* * One for us, one for whoever does the "release_task()" (usually @@ -856,6 +894,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) tsk->splice_pipe = NULL; tsk->task_frag.page = NULL; tsk->wake_q.next = NULL; + tsk->wake_q_sleeper.next = NULL; account_kernel_stack(tsk, 1); @@ -1572,6 +1611,9 @@ static void rt_mutex_init_task(struct task_struct *p) */ static void posix_cpu_timers_init(struct task_struct *tsk) { +#ifdef CONFIG_PREEMPT_RT_BASE + tsk->posix_timer_list = NULL; +#endif tsk->cputime_expires.prof_exp = 0; tsk->cputime_expires.virt_exp = 0; tsk->cputime_expires.sched_exp = 0; @@ -1743,6 +1785,7 @@ static __latent_entropy struct task_struct *copy_process( spin_lock_init(&p->alloc_lock); init_sigpending(&p->pending); + p->sigqueue_cache = NULL; p->utime = p->stime = p->gtime = 0; #ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME diff --git a/kernel/futex.c b/kernel/futex.c index 28f655d1e0f3..18b3952d2dc2 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -918,7 +918,9 @@ void exit_pi_state_list(struct task_struct *curr) if (head->next != next) { /* retain curr->pi_lock for the loop invariant */ raw_spin_unlock(&pi_state->pi_mutex.wait_lock); + raw_spin_unlock_irq(&curr->pi_lock); spin_unlock(&hb->lock); + raw_spin_lock_irq(&curr->pi_lock); put_pi_state(pi_state); continue; } @@ -1474,6 +1476,7 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_pi_state *pi_ struct task_struct *new_owner; bool postunlock = false; DEFINE_WAKE_Q(wake_q); + DEFINE_WAKE_Q(wake_sleeper_q); int ret = 0; new_owner = rt_mutex_next_owner(&pi_state->pi_mutex); @@ -1533,13 +1536,13 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_pi_state *pi_ pi_state->owner = new_owner; raw_spin_unlock(&new_owner->pi_lock); - postunlock = __rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q); - + postunlock = __rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q, + &wake_sleeper_q); out_unlock: raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); if (postunlock) - rt_mutex_postunlock(&wake_q); + rt_mutex_postunlock(&wake_q, &wake_sleeper_q); return ret; } @@ -2146,6 +2149,16 @@ retry_private: requeue_pi_wake_futex(this, &key2, hb2); drop_count++; continue; + } else if (ret == -EAGAIN) { + /* + * Waiter was woken by timeout or + * signal and has set pi_blocked_on to + * PI_WAKEUP_INPROGRESS before we + * tried to enqueue it on the rtmutex. + */ + this->pi_state = NULL; + put_pi_state(pi_state); + continue; } else if (ret) { /* * rt_mutex_start_proxy_lock() detected a @@ -2701,10 +2714,9 @@ static int futex_wait(u32 __user *uaddr, unsigned int flags, u32 val, if (abs_time) { to = &timeout; - hrtimer_init_on_stack(&to->timer, (flags & FLAGS_CLOCKRT) ? - CLOCK_REALTIME : CLOCK_MONOTONIC, - HRTIMER_MODE_ABS); - hrtimer_init_sleeper(to, current); + hrtimer_init_sleeper_on_stack(to, (flags & FLAGS_CLOCKRT) ? + CLOCK_REALTIME : CLOCK_MONOTONIC, + HRTIMER_MODE_ABS, current); hrtimer_set_expires_range_ns(&to->timer, *abs_time, current->timer_slack_ns); } @@ -2803,9 +2815,8 @@ static int futex_lock_pi(u32 __user *uaddr, unsigned int flags, if (time) { to = &timeout; - hrtimer_init_on_stack(&to->timer, CLOCK_REALTIME, - HRTIMER_MODE_ABS); - hrtimer_init_sleeper(to, current); + hrtimer_init_sleeper_on_stack(to, CLOCK_REALTIME, + HRTIMER_MODE_ABS, current); hrtimer_set_expires(&to->timer, *time); } @@ -2860,7 +2871,7 @@ retry_private: goto no_block; } - rt_mutex_init_waiter(&rt_waiter); + rt_mutex_init_waiter(&rt_waiter, false); /* * On PREEMPT_RT_FULL, when hb->lock becomes an rt_mutex, we must not @@ -2876,6 +2887,14 @@ retry_private: * before __rt_mutex_start_proxy_lock() is done. */ raw_spin_lock_irq(&q.pi_state->pi_mutex.wait_lock); + /* + * the migrate_disable() here disables migration in the in_atomic() fast + * path which is enabled again in the following spin_unlock(). We have + * one migrate_disable() pending in the slow-path which is reversed + * after the raw_spin_unlock_irq() where we leave the atomic context. + */ + migrate_disable(); + spin_unlock(q.lock_ptr); /* * __rt_mutex_start_proxy_lock() unconditionally enqueues the @rt_waiter @@ -2884,6 +2903,7 @@ retry_private: */ ret = __rt_mutex_start_proxy_lock(&q.pi_state->pi_mutex, &rt_waiter, current); raw_spin_unlock_irq(&q.pi_state->pi_mutex.wait_lock); + migrate_enable(); if (ret) { if (ret == 1) @@ -3032,11 +3052,21 @@ retry: * rt_waiter. Also see the WARN in wake_futex_pi(). */ raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); + /* + * Magic trickery for now to make the RT migrate disable + * logic happy. The following spin_unlock() happens with + * interrupts disabled so the internal migrate_enable() + * won't undo the migrate_disable() which was issued when + * locking hb->lock. + */ + migrate_disable(); spin_unlock(&hb->lock); /* drops pi_state->pi_mutex.wait_lock */ ret = wake_futex_pi(uaddr, uval, pi_state); + migrate_enable(); + put_pi_state(pi_state); /* @@ -3207,7 +3237,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, struct hrtimer_sleeper timeout, *to = NULL; struct futex_pi_state *pi_state = NULL; struct rt_mutex_waiter rt_waiter; - struct futex_hash_bucket *hb; + struct futex_hash_bucket *hb, *hb2; union futex_key key2 = FUTEX_KEY_INIT; struct futex_q q = futex_q_init; int res, ret; @@ -3223,10 +3253,9 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, if (abs_time) { to = &timeout; - hrtimer_init_on_stack(&to->timer, (flags & FLAGS_CLOCKRT) ? - CLOCK_REALTIME : CLOCK_MONOTONIC, - HRTIMER_MODE_ABS); - hrtimer_init_sleeper(to, current); + hrtimer_init_sleeper_on_stack(to, (flags & FLAGS_CLOCKRT) ? + CLOCK_REALTIME : CLOCK_MONOTONIC, + HRTIMER_MODE_ABS, current); hrtimer_set_expires_range_ns(&to->timer, *abs_time, current->timer_slack_ns); } @@ -3235,7 +3264,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, * The waiter is allocated on our stack, manipulated by the requeue * code while we sleep on uaddr. */ - rt_mutex_init_waiter(&rt_waiter); + rt_mutex_init_waiter(&rt_waiter, false); ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2, VERIFY_WRITE); if (unlikely(ret != 0)) @@ -3266,20 +3295,55 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, /* Queue the futex_q, drop the hb lock, wait for wakeup. */ futex_wait_queue_me(hb, &q, to); - spin_lock(&hb->lock); - ret = handle_early_requeue_pi_wakeup(hb, &q, &key2, to); - spin_unlock(&hb->lock); - if (ret) - goto out_put_keys; + /* + * On RT we must avoid races with requeue and trying to block + * on two mutexes (hb->lock and uaddr2's rtmutex) by + * serializing access to pi_blocked_on with pi_lock. + */ + raw_spin_lock_irq(¤t->pi_lock); + if (current->pi_blocked_on) { + /* + * We have been requeued or are in the process of + * being requeued. + */ + raw_spin_unlock_irq(¤t->pi_lock); + } else { + /* + * Setting pi_blocked_on to PI_WAKEUP_INPROGRESS + * prevents a concurrent requeue from moving us to the + * uaddr2 rtmutex. After that we can safely acquire + * (and possibly block on) hb->lock. + */ + current->pi_blocked_on = PI_WAKEUP_INPROGRESS; + raw_spin_unlock_irq(¤t->pi_lock); + + spin_lock(&hb->lock); + + /* + * Clean up pi_blocked_on. We might leak it otherwise + * when we succeeded with the hb->lock in the fast + * path. + */ + raw_spin_lock_irq(¤t->pi_lock); + current->pi_blocked_on = NULL; + raw_spin_unlock_irq(¤t->pi_lock); + + ret = handle_early_requeue_pi_wakeup(hb, &q, &key2, to); + spin_unlock(&hb->lock); + if (ret) + goto out_put_keys; + } /* - * In order for us to be here, we know our q.key == key2, and since - * we took the hb->lock above, we also know that futex_requeue() has - * completed and we no longer have to concern ourselves with a wakeup - * race with the atomic proxy lock acquisition by the requeue code. The - * futex_requeue dropped our key1 reference and incremented our key2 - * reference count. + * In order to be here, we have either been requeued, are in + * the process of being requeued, or requeue successfully + * acquired uaddr2 on our behalf. If pi_blocked_on was + * non-null above, we may be racing with a requeue. Do not + * rely on q->lock_ptr to be hb2->lock until after blocking on + * hb->lock or hb2->lock. The futex_requeue dropped our key1 + * reference and incremented our key2 reference count. */ + hb2 = hash_futex(&key2); /* Check if the requeue code acquired the second futex for us. */ if (!q.rt_waiter) { @@ -3288,7 +3352,8 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, * did a lock-steal - fix up the PI-state in that case. */ if (q.pi_state && (q.pi_state->owner != current)) { - spin_lock(q.lock_ptr); + spin_lock(&hb2->lock); + BUG_ON(&hb2->lock != q.lock_ptr); ret = fixup_pi_state_owner(uaddr2, &q, current); if (ret && rt_mutex_owner(&q.pi_state->pi_mutex) == current) { pi_state = q.pi_state; @@ -3299,7 +3364,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, * the requeue_pi() code acquired for us. */ put_pi_state(q.pi_state); - spin_unlock(q.lock_ptr); + spin_unlock(&hb2->lock); } } else { struct rt_mutex *pi_mutex; @@ -3313,7 +3378,8 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, pi_mutex = &q.pi_state->pi_mutex; ret = rt_mutex_wait_proxy_lock(pi_mutex, to, &rt_waiter); - spin_lock(q.lock_ptr); + spin_lock(&hb2->lock); + BUG_ON(&hb2->lock != q.lock_ptr); if (ret && !rt_mutex_cleanup_proxy_lock(pi_mutex, &rt_waiter)) ret = 0; diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index 38554bc35375..06a80bbf78af 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -185,10 +185,16 @@ irqreturn_t handle_irq_event_percpu(struct irq_desc *desc) { irqreturn_t retval; unsigned int flags = 0; + struct pt_regs *regs = get_irq_regs(); + u64 ip = regs ? instruction_pointer(regs) : 0; retval = __handle_irq_event_percpu(desc, &flags); - add_interrupt_randomness(desc->irq_data.irq, flags); +#ifdef CONFIG_PREEMPT_RT_FULL + desc->random_ip = ip; +#else + add_interrupt_randomness(desc->irq_data.irq, flags, ip); +#endif if (!noirqdebug) note_interrupt(desc, retval); diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index fb83dedb7e5b..070b73475d28 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -23,6 +23,7 @@ #include "internals.h" #ifdef CONFIG_IRQ_FORCED_THREADING +# ifndef CONFIG_PREEMPT_RT_BASE __read_mostly bool force_irqthreads; EXPORT_SYMBOL_GPL(force_irqthreads); @@ -32,6 +33,7 @@ static int __init setup_forced_irqthreads(char *arg) return 0; } early_param("threadirqs", setup_forced_irqthreads); +# endif #endif static void __synchronize_hardirq(struct irq_desc *desc) @@ -257,7 +259,12 @@ int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask, if (desc->affinity_notify) { kref_get(&desc->affinity_notify->kref); + +#ifdef CONFIG_PREEMPT_RT_BASE + swork_queue(&desc->affinity_notify->swork); +#else schedule_work(&desc->affinity_notify->work); +#endif } irqd_set(data, IRQD_AFFINITY_SET); @@ -295,10 +302,8 @@ int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m) } EXPORT_SYMBOL_GPL(irq_set_affinity_hint); -static void irq_affinity_notify(struct work_struct *work) +static void _irq_affinity_notify(struct irq_affinity_notify *notify) { - struct irq_affinity_notify *notify = - container_of(work, struct irq_affinity_notify, work); struct irq_desc *desc = irq_to_desc(notify->irq); cpumask_var_t cpumask; unsigned long flags; @@ -320,6 +325,35 @@ out: kref_put(¬ify->kref, notify->release); } +#ifdef CONFIG_PREEMPT_RT_BASE +static void init_helper_thread(void) +{ + static int init_sworker_once; + + if (init_sworker_once) + return; + if (WARN_ON(swork_get())) + return; + init_sworker_once = 1; +} + +static void irq_affinity_notify(struct swork_event *swork) +{ + struct irq_affinity_notify *notify = + container_of(swork, struct irq_affinity_notify, swork); + _irq_affinity_notify(notify); +} + +#else + +static void irq_affinity_notify(struct work_struct *work) +{ + struct irq_affinity_notify *notify = + container_of(work, struct irq_affinity_notify, work); + _irq_affinity_notify(notify); +} +#endif + /** * irq_set_affinity_notifier - control notification of IRQ affinity changes * @irq: Interrupt for which to enable/disable notification @@ -348,7 +382,12 @@ irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify) if (notify) { notify->irq = irq; kref_init(¬ify->kref); +#ifdef CONFIG_PREEMPT_RT_BASE + INIT_SWORK(¬ify->swork, irq_affinity_notify); + init_helper_thread(); +#else INIT_WORK(¬ify->work, irq_affinity_notify); +#endif } raw_spin_lock_irqsave(&desc->lock, flags); @@ -356,10 +395,8 @@ irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify) desc->affinity_notify = notify; raw_spin_unlock_irqrestore(&desc->lock, flags); - if (old_notify) { - cancel_work_sync(&old_notify->work); + if (old_notify) kref_put(&old_notify->kref, old_notify->release); - } return 0; } @@ -929,7 +966,15 @@ irq_forced_thread_fn(struct irq_desc *desc, struct irqaction *action) atomic_inc(&desc->threads_handled); irq_finalize_oneshot(desc, action); - local_bh_enable(); + /* + * Interrupts which have real time requirements can be set up + * to avoid softirq processing in the thread handler. This is + * safe as these interrupts do not raise soft interrupts. + */ + if (irq_settings_no_softirq_call(desc)) + _local_bh_enable(); + else + local_bh_enable(); return ret; } @@ -1027,6 +1072,12 @@ static int irq_thread(void *data) if (action_ret == IRQ_WAKE_THREAD) irq_wake_secondary(desc, action); +#ifdef CONFIG_PREEMPT_RT_FULL + migrate_disable(); + add_interrupt_randomness(action->irq, 0, + desc->random_ip ^ (unsigned long) action); + migrate_enable(); +#endif wake_threads_waitq(desc); } @@ -1440,6 +1491,9 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) irqd_set(&desc->irq_data, IRQD_NO_BALANCING); } + if (new->flags & IRQF_NO_SOFTIRQ_CALL) + irq_settings_set_no_softirq_call(desc); + if (irq_settings_can_autoenable(desc)) { irq_startup(desc, IRQ_RESEND, IRQ_START_COND); } else { @@ -2220,7 +2274,7 @@ EXPORT_SYMBOL_GPL(irq_get_irqchip_state); * This call sets the internal irqchip state of an interrupt, * depending on the value of @which. * - * This function should be called with preemption disabled if the + * This function should be called with migration disabled if the * interrupt controller has per-cpu registers. */ int irq_set_irqchip_state(unsigned int irq, enum irqchip_irq_state which, diff --git a/kernel/irq/settings.h b/kernel/irq/settings.h index e43795cd2ccf..47e2f9e23586 100644 --- a/kernel/irq/settings.h +++ b/kernel/irq/settings.h @@ -17,6 +17,7 @@ enum { _IRQ_PER_CPU_DEVID = IRQ_PER_CPU_DEVID, _IRQ_IS_POLLED = IRQ_IS_POLLED, _IRQ_DISABLE_UNLAZY = IRQ_DISABLE_UNLAZY, + _IRQ_NO_SOFTIRQ_CALL = IRQ_NO_SOFTIRQ_CALL, _IRQF_MODIFY_MASK = IRQF_MODIFY_MASK, }; @@ -31,6 +32,7 @@ enum { #define IRQ_PER_CPU_DEVID GOT_YOU_MORON #define IRQ_IS_POLLED GOT_YOU_MORON #define IRQ_DISABLE_UNLAZY GOT_YOU_MORON +#define IRQ_NO_SOFTIRQ_CALL GOT_YOU_MORON #undef IRQF_MODIFY_MASK #define IRQF_MODIFY_MASK GOT_YOU_MORON @@ -41,6 +43,16 @@ irq_settings_clr_and_set(struct irq_desc *desc, u32 clr, u32 set) desc->status_use_accessors |= (set & _IRQF_MODIFY_MASK); } +static inline bool irq_settings_no_softirq_call(struct irq_desc *desc) +{ + return desc->status_use_accessors & _IRQ_NO_SOFTIRQ_CALL; +} + +static inline void irq_settings_set_no_softirq_call(struct irq_desc *desc) +{ + desc->status_use_accessors |= _IRQ_NO_SOFTIRQ_CALL; +} + static inline bool irq_settings_is_per_cpu(struct irq_desc *desc) { return desc->status_use_accessors & _IRQ_PER_CPU; diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c index d867d6ddafdd..cd12ee86c01e 100644 --- a/kernel/irq/spurious.c +++ b/kernel/irq/spurious.c @@ -442,6 +442,10 @@ MODULE_PARM_DESC(noirqdebug, "Disable irq lockup detection when true"); static int __init irqfixup_setup(char *str) { +#ifdef CONFIG_PREEMPT_RT_BASE + pr_warn("irqfixup boot option not supported w/ CONFIG_PREEMPT_RT_BASE\n"); + return 1; +#endif irqfixup = 1; printk(KERN_WARNING "Misrouted IRQ fixup support enabled.\n"); printk(KERN_WARNING "This may impact system performance.\n"); @@ -454,6 +458,10 @@ module_param(irqfixup, int, 0644); static int __init irqpoll_setup(char *str) { +#ifdef CONFIG_PREEMPT_RT_BASE + pr_warn("irqpoll boot option not supported w/ CONFIG_PREEMPT_RT_BASE\n"); + return 1; +#endif irqfixup = 2; printk(KERN_WARNING "Misrouted IRQ fixup and polling support " "enabled\n"); diff --git a/kernel/irq_work.c b/kernel/irq_work.c index 73288914ed5e..2940622da5b3 100644 --- a/kernel/irq_work.c +++ b/kernel/irq_work.c @@ -17,6 +17,7 @@ #include <linux/cpu.h> #include <linux/notifier.h> #include <linux/smp.h> +#include <linux/interrupt.h> #include <asm/processor.h> @@ -57,29 +58,35 @@ void __weak arch_irq_work_raise(void) } /* Enqueue on current CPU, work must already be claimed and preempt disabled */ -static void __irq_work_queue_local(struct irq_work *work) +static void __irq_work_queue_local(struct irq_work *work, struct llist_head *list) { - /* If the work is "lazy", handle it from next tick if any */ - if (work->flags & IRQ_WORK_LAZY) { - if (llist_add(&work->llnode, this_cpu_ptr(&lazy_list)) && - tick_nohz_tick_stopped()) - arch_irq_work_raise(); - } else { - if (llist_add(&work->llnode, this_cpu_ptr(&raised_list))) - arch_irq_work_raise(); - } + bool empty; + + empty = llist_add(&work->llnode, list); + + if (empty && + (!(work->flags & IRQ_WORK_LAZY) || + tick_nohz_tick_stopped())) + arch_irq_work_raise(); } /* Enqueue the irq work @work on the current CPU */ bool irq_work_queue(struct irq_work *work) { + struct llist_head *list; + /* Only queue if not already pending */ if (!irq_work_claim(work)) return false; /* Queue the entry and raise the IPI if needed. */ preempt_disable(); - __irq_work_queue_local(work); + if (IS_ENABLED(CONFIG_PREEMPT_RT_FULL) && !(work->flags & IRQ_WORK_HARD_IRQ)) + list = this_cpu_ptr(&lazy_list); + else + list = this_cpu_ptr(&raised_list); + + __irq_work_queue_local(work, list); preempt_enable(); return true; @@ -98,6 +105,9 @@ bool irq_work_queue_on(struct irq_work *work, int cpu) return irq_work_queue(work); #else /* CONFIG_SMP: */ + struct llist_head *list; + bool lazy_work, realtime = IS_ENABLED(CONFIG_PREEMPT_RT_FULL); + /* All work should have been flushed before going offline */ WARN_ON_ONCE(cpu_is_offline(cpu)); @@ -106,13 +116,21 @@ bool irq_work_queue_on(struct irq_work *work, int cpu) return false; preempt_disable(); + + lazy_work = work->flags & IRQ_WORK_LAZY; + + if (lazy_work || (realtime && !(work->flags & IRQ_WORK_HARD_IRQ))) + list = &per_cpu(lazy_list, cpu); + else + list = &per_cpu(raised_list, cpu); + if (cpu != smp_processor_id()) { /* Arch remote IPI send/receive backend aren't NMI safe */ WARN_ON_ONCE(in_nmi()); - if (llist_add(&work->llnode, &per_cpu(raised_list, cpu))) + if (llist_add(&work->llnode, list)) arch_send_call_function_single_ipi(cpu); } else { - __irq_work_queue_local(work); + __irq_work_queue_local(work, list); } preempt_enable(); @@ -128,9 +146,8 @@ bool irq_work_needs_cpu(void) raised = this_cpu_ptr(&raised_list); lazy = this_cpu_ptr(&lazy_list); - if (llist_empty(raised) || arch_irq_work_has_interrupt()) - if (llist_empty(lazy)) - return false; + if (llist_empty(raised) && llist_empty(lazy)) + return false; /* All work should have been flushed before going offline */ WARN_ON_ONCE(cpu_is_offline(smp_processor_id())); @@ -144,8 +161,12 @@ static void irq_work_run_list(struct llist_head *list) struct llist_node *llnode; unsigned long flags; +#ifndef CONFIG_PREEMPT_RT_FULL + /* + * nort: On RT IRQ-work may run in SOFTIRQ context. + */ BUG_ON(!irqs_disabled()); - +#endif if (llist_empty(list)) return; @@ -177,7 +198,16 @@ static void irq_work_run_list(struct llist_head *list) void irq_work_run(void) { irq_work_run_list(this_cpu_ptr(&raised_list)); - irq_work_run_list(this_cpu_ptr(&lazy_list)); + if (IS_ENABLED(CONFIG_PREEMPT_RT_FULL)) { + /* + * NOTE: we raise softirq via IPI for safety, + * and execute in irq_work_tick() to move the + * overhead from hard to soft irq context. + */ + if (!llist_empty(this_cpu_ptr(&lazy_list))) + raise_softirq(TIMER_SOFTIRQ); + } else + irq_work_run_list(this_cpu_ptr(&lazy_list)); } EXPORT_SYMBOL_GPL(irq_work_run); @@ -187,8 +217,17 @@ void irq_work_tick(void) if (!llist_empty(raised) && !arch_irq_work_has_interrupt()) irq_work_run_list(raised); + + if (!IS_ENABLED(CONFIG_PREEMPT_RT_FULL)) + irq_work_run_list(this_cpu_ptr(&lazy_list)); +} + +#if defined(CONFIG_IRQ_WORK) && defined(CONFIG_PREEMPT_RT_FULL) +void irq_work_tick_soft(void) +{ irq_work_run_list(this_cpu_ptr(&lazy_list)); } +#endif /* * Synchronize against the irq_work @entry, ensures the entry is not diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c index 46ba853656f6..9a23632b6294 100644 --- a/kernel/ksysfs.c +++ b/kernel/ksysfs.c @@ -140,6 +140,15 @@ KERNEL_ATTR_RO(vmcoreinfo); #endif /* CONFIG_CRASH_CORE */ +#if defined(CONFIG_PREEMPT_RT_FULL) +static ssize_t realtime_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%d\n", 1); +} +KERNEL_ATTR_RO(realtime); +#endif + /* whether file capabilities are enabled */ static ssize_t fscaps_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) @@ -231,6 +240,9 @@ static struct attribute * kernel_attrs[] = { &rcu_expedited_attr.attr, &rcu_normal_attr.attr, #endif +#ifdef CONFIG_PREEMPT_RT_FULL + &realtime_attr.attr, +#endif NULL }; diff --git a/kernel/kthread.c b/kernel/kthread.c index 486dedbd9af5..c1d9ee6671c6 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -597,7 +597,7 @@ void __kthread_init_worker(struct kthread_worker *worker, struct lock_class_key *key) { memset(worker, 0, sizeof(struct kthread_worker)); - spin_lock_init(&worker->lock); + raw_spin_lock_init(&worker->lock); lockdep_set_class_and_name(&worker->lock, key, name); INIT_LIST_HEAD(&worker->work_list); INIT_LIST_HEAD(&worker->delayed_work_list); @@ -639,21 +639,21 @@ repeat: if (kthread_should_stop()) { __set_current_state(TASK_RUNNING); - spin_lock_irq(&worker->lock); + raw_spin_lock_irq(&worker->lock); worker->task = NULL; - spin_unlock_irq(&worker->lock); + raw_spin_unlock_irq(&worker->lock); return 0; } work = NULL; - spin_lock_irq(&worker->lock); + raw_spin_lock_irq(&worker->lock); if (!list_empty(&worker->work_list)) { work = list_first_entry(&worker->work_list, struct kthread_work, node); list_del_init(&work->node); } worker->current_work = work; - spin_unlock_irq(&worker->lock); + raw_spin_unlock_irq(&worker->lock); if (work) { __set_current_state(TASK_RUNNING); @@ -810,12 +810,12 @@ bool kthread_queue_work(struct kthread_worker *worker, bool ret = false; unsigned long flags; - spin_lock_irqsave(&worker->lock, flags); + raw_spin_lock_irqsave(&worker->lock, flags); if (!queuing_blocked(worker, work)) { kthread_insert_work(worker, work, &worker->work_list); ret = true; } - spin_unlock_irqrestore(&worker->lock, flags); + raw_spin_unlock_irqrestore(&worker->lock, flags); return ret; } EXPORT_SYMBOL_GPL(kthread_queue_work); @@ -841,7 +841,7 @@ void kthread_delayed_work_timer_fn(struct timer_list *t) if (WARN_ON_ONCE(!worker)) return; - spin_lock(&worker->lock); + raw_spin_lock(&worker->lock); /* Work must not be used with >1 worker, see kthread_queue_work(). */ WARN_ON_ONCE(work->worker != worker); @@ -850,7 +850,7 @@ void kthread_delayed_work_timer_fn(struct timer_list *t) list_del_init(&work->node); kthread_insert_work(worker, work, &worker->work_list); - spin_unlock(&worker->lock); + raw_spin_unlock(&worker->lock); } EXPORT_SYMBOL(kthread_delayed_work_timer_fn); @@ -906,14 +906,14 @@ bool kthread_queue_delayed_work(struct kthread_worker *worker, unsigned long flags; bool ret = false; - spin_lock_irqsave(&worker->lock, flags); + raw_spin_lock_irqsave(&worker->lock, flags); if (!queuing_blocked(worker, work)) { __kthread_queue_delayed_work(worker, dwork, delay); ret = true; } - spin_unlock_irqrestore(&worker->lock, flags); + raw_spin_unlock_irqrestore(&worker->lock, flags); return ret; } EXPORT_SYMBOL_GPL(kthread_queue_delayed_work); @@ -949,7 +949,7 @@ void kthread_flush_work(struct kthread_work *work) if (!worker) return; - spin_lock_irq(&worker->lock); + raw_spin_lock_irq(&worker->lock); /* Work must not be used with >1 worker, see kthread_queue_work(). */ WARN_ON_ONCE(work->worker != worker); @@ -961,7 +961,7 @@ void kthread_flush_work(struct kthread_work *work) else noop = true; - spin_unlock_irq(&worker->lock); + raw_spin_unlock_irq(&worker->lock); if (!noop) wait_for_completion(&fwork.done); @@ -994,9 +994,9 @@ static bool __kthread_cancel_work(struct kthread_work *work, bool is_dwork, * any queuing is blocked by setting the canceling counter. */ work->canceling++; - spin_unlock_irqrestore(&worker->lock, *flags); + raw_spin_unlock_irqrestore(&worker->lock, *flags); del_timer_sync(&dwork->timer); - spin_lock_irqsave(&worker->lock, *flags); + raw_spin_lock_irqsave(&worker->lock, *flags); work->canceling--; } @@ -1043,7 +1043,7 @@ bool kthread_mod_delayed_work(struct kthread_worker *worker, unsigned long flags; int ret = false; - spin_lock_irqsave(&worker->lock, flags); + raw_spin_lock_irqsave(&worker->lock, flags); /* Do not bother with canceling when never queued. */ if (!work->worker) @@ -1060,7 +1060,7 @@ bool kthread_mod_delayed_work(struct kthread_worker *worker, fast_queue: __kthread_queue_delayed_work(worker, dwork, delay); out: - spin_unlock_irqrestore(&worker->lock, flags); + raw_spin_unlock_irqrestore(&worker->lock, flags); return ret; } EXPORT_SYMBOL_GPL(kthread_mod_delayed_work); @@ -1074,7 +1074,7 @@ static bool __kthread_cancel_work_sync(struct kthread_work *work, bool is_dwork) if (!worker) goto out; - spin_lock_irqsave(&worker->lock, flags); + raw_spin_lock_irqsave(&worker->lock, flags); /* Work must not be used with >1 worker, see kthread_queue_work(). */ WARN_ON_ONCE(work->worker != worker); @@ -1088,13 +1088,13 @@ static bool __kthread_cancel_work_sync(struct kthread_work *work, bool is_dwork) * In the meantime, block any queuing by setting the canceling counter. */ work->canceling++; - spin_unlock_irqrestore(&worker->lock, flags); + raw_spin_unlock_irqrestore(&worker->lock, flags); kthread_flush_work(work); - spin_lock_irqsave(&worker->lock, flags); + raw_spin_lock_irqsave(&worker->lock, flags); work->canceling--; out_fast: - spin_unlock_irqrestore(&worker->lock, flags); + raw_spin_unlock_irqrestore(&worker->lock, flags); out: return ret; } diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile index 392c7f23af76..c0bf04b6b965 100644 --- a/kernel/locking/Makefile +++ b/kernel/locking/Makefile @@ -3,7 +3,7 @@ # and is generally not a function of system call inputs. KCOV_INSTRUMENT := n -obj-y += mutex.o semaphore.o rwsem.o percpu-rwsem.o +obj-y += semaphore.o percpu-rwsem.o ifdef CONFIG_FUNCTION_TRACER CFLAGS_REMOVE_lockdep.o = $(CC_FLAGS_FTRACE) @@ -12,7 +12,11 @@ CFLAGS_REMOVE_mutex-debug.o = $(CC_FLAGS_FTRACE) CFLAGS_REMOVE_rtmutex-debug.o = $(CC_FLAGS_FTRACE) endif +ifneq ($(CONFIG_PREEMPT_RT_FULL),y) +obj-y += mutex.o obj-$(CONFIG_DEBUG_MUTEXES) += mutex-debug.o +endif +obj-y += rwsem.o obj-$(CONFIG_LOCKDEP) += lockdep.o ifeq ($(CONFIG_PROC_FS),y) obj-$(CONFIG_LOCKDEP) += lockdep_proc.o @@ -25,8 +29,11 @@ obj-$(CONFIG_RT_MUTEXES) += rtmutex.o obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock_debug.o +ifneq ($(CONFIG_PREEMPT_RT_FULL),y) obj-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o obj-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem-xadd.o +endif +obj-$(CONFIG_PREEMPT_RT_FULL) += mutex-rt.o rwsem-rt.o rwlock-rt.o obj-$(CONFIG_QUEUED_RWLOCKS) += qrwlock.o obj-$(CONFIG_LOCK_TORTURE_TEST) += locktorture.o obj-$(CONFIG_WW_MUTEX_SELFTEST) += test-ww_mutex.o diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 3824fc3419b8..4b925f3ae426 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -3849,6 +3849,7 @@ static void check_flags(unsigned long flags) } } +#ifndef CONFIG_PREEMPT_RT_FULL /* * We dont accurately track softirq state in e.g. * hardirq contexts (such as on 4KSTACKS), so only @@ -3863,6 +3864,7 @@ static void check_flags(unsigned long flags) DEBUG_LOCKS_WARN_ON(!current->softirqs_enabled); } } +#endif if (!debug_locks) print_irqtrace_events(current); diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c index 8402b3349dca..c4cf0fd9ee67 100644 --- a/kernel/locking/locktorture.c +++ b/kernel/locking/locktorture.c @@ -26,7 +26,6 @@ #include <linux/kthread.h> #include <linux/sched/rt.h> #include <linux/spinlock.h> -#include <linux/rwlock.h> #include <linux/mutex.h> #include <linux/rwsem.h> #include <linux/smp.h> diff --git a/kernel/locking/mutex-rt.c b/kernel/locking/mutex-rt.c new file mode 100644 index 000000000000..4f81595c0f52 --- /dev/null +++ b/kernel/locking/mutex-rt.c @@ -0,0 +1,223 @@ +/* + * kernel/rt.c + * + * Real-Time Preemption Support + * + * started by Ingo Molnar: + * + * Copyright (C) 2004-2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> + * Copyright (C) 2006, Timesys Corp., Thomas Gleixner <tglx@timesys.com> + * + * historic credit for proving that Linux spinlocks can be implemented via + * RT-aware mutexes goes to many people: The Pmutex project (Dirk Grambow + * and others) who prototyped it on 2.4 and did lots of comparative + * research and analysis; TimeSys, for proving that you can implement a + * fully preemptible kernel via the use of IRQ threading and mutexes; + * Bill Huey for persuasively arguing on lkml that the mutex model is the + * right one; and to MontaVista, who ported pmutexes to 2.6. + * + * This code is a from-scratch implementation and is not based on pmutexes, + * but the idea of converting spinlocks to mutexes is used here too. + * + * lock debugging, locking tree, deadlock detection: + * + * Copyright (C) 2004, LynuxWorks, Inc., Igor Manyilov, Bill Huey + * Released under the General Public License (GPL). + * + * Includes portions of the generic R/W semaphore implementation from: + * + * Copyright (c) 2001 David Howells (dhowells@redhat.com). + * - Derived partially from idea by Andrea Arcangeli <andrea@suse.de> + * - Derived also from comments by Linus + * + * Pending ownership of locks and ownership stealing: + * + * Copyright (C) 2005, Kihon Technologies Inc., Steven Rostedt + * + * (also by Steven Rostedt) + * - Converted single pi_lock to individual task locks. + * + * By Esben Nielsen: + * Doing priority inheritance with help of the scheduler. + * + * Copyright (C) 2006, Timesys Corp., Thomas Gleixner <tglx@timesys.com> + * - major rework based on Esben Nielsens initial patch + * - replaced thread_info references by task_struct refs + * - removed task->pending_owner dependency + * - BKL drop/reacquire for semaphore style locks to avoid deadlocks + * in the scheduler return path as discussed with Steven Rostedt + * + * Copyright (C) 2006, Kihon Technologies Inc. + * Steven Rostedt <rostedt@goodmis.org> + * - debugged and patched Thomas Gleixner's rework. + * - added back the cmpxchg to the rework. + * - turned atomic require back on for SMP. + */ + +#include <linux/spinlock.h> +#include <linux/rtmutex.h> +#include <linux/sched.h> +#include <linux/delay.h> +#include <linux/module.h> +#include <linux/kallsyms.h> +#include <linux/syscalls.h> +#include <linux/interrupt.h> +#include <linux/plist.h> +#include <linux/fs.h> +#include <linux/futex.h> +#include <linux/hrtimer.h> + +#include "rtmutex_common.h" + +/* + * struct mutex functions + */ +void __mutex_do_init(struct mutex *mutex, const char *name, + struct lock_class_key *key) +{ +#ifdef CONFIG_DEBUG_LOCK_ALLOC + /* + * Make sure we are not reinitializing a held lock: + */ + debug_check_no_locks_freed((void *)mutex, sizeof(*mutex)); + lockdep_init_map(&mutex->dep_map, name, key, 0); +#endif + mutex->lock.save_state = 0; +} +EXPORT_SYMBOL(__mutex_do_init); + +void __lockfunc _mutex_lock(struct mutex *lock) +{ + mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_); + __rt_mutex_lock_state(&lock->lock, TASK_UNINTERRUPTIBLE); +} +EXPORT_SYMBOL(_mutex_lock); + +void __lockfunc _mutex_lock_io(struct mutex *lock) +{ + int token; + + token = io_schedule_prepare(); + _mutex_lock(lock); + io_schedule_finish(token); +} +EXPORT_SYMBOL_GPL(_mutex_lock_io); + +int __lockfunc _mutex_lock_interruptible(struct mutex *lock) +{ + int ret; + + mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_); + ret = __rt_mutex_lock_state(&lock->lock, TASK_INTERRUPTIBLE); + if (ret) + mutex_release(&lock->dep_map, 1, _RET_IP_); + return ret; +} +EXPORT_SYMBOL(_mutex_lock_interruptible); + +int __lockfunc _mutex_lock_killable(struct mutex *lock) +{ + int ret; + + mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_); + ret = __rt_mutex_lock_state(&lock->lock, TASK_KILLABLE); + if (ret) + mutex_release(&lock->dep_map, 1, _RET_IP_); + return ret; +} +EXPORT_SYMBOL(_mutex_lock_killable); + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +void __lockfunc _mutex_lock_nested(struct mutex *lock, int subclass) +{ + mutex_acquire_nest(&lock->dep_map, subclass, 0, NULL, _RET_IP_); + __rt_mutex_lock_state(&lock->lock, TASK_UNINTERRUPTIBLE); +} +EXPORT_SYMBOL(_mutex_lock_nested); + +void __lockfunc _mutex_lock_io_nested(struct mutex *lock, int subclass) +{ + int token; + + token = io_schedule_prepare(); + + mutex_acquire_nest(&lock->dep_map, subclass, 0, NULL, _RET_IP_); + __rt_mutex_lock_state(&lock->lock, TASK_UNINTERRUPTIBLE); + + io_schedule_finish(token); +} +EXPORT_SYMBOL_GPL(_mutex_lock_io_nested); + +void __lockfunc _mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest) +{ + mutex_acquire_nest(&lock->dep_map, 0, 0, nest, _RET_IP_); + __rt_mutex_lock_state(&lock->lock, TASK_UNINTERRUPTIBLE); +} +EXPORT_SYMBOL(_mutex_lock_nest_lock); + +int __lockfunc _mutex_lock_interruptible_nested(struct mutex *lock, int subclass) +{ + int ret; + + mutex_acquire_nest(&lock->dep_map, subclass, 0, NULL, _RET_IP_); + ret = __rt_mutex_lock_state(&lock->lock, TASK_INTERRUPTIBLE); + if (ret) + mutex_release(&lock->dep_map, 1, _RET_IP_); + return ret; +} +EXPORT_SYMBOL(_mutex_lock_interruptible_nested); + +int __lockfunc _mutex_lock_killable_nested(struct mutex *lock, int subclass) +{ + int ret; + + mutex_acquire(&lock->dep_map, subclass, 0, _RET_IP_); + ret = __rt_mutex_lock_state(&lock->lock, TASK_KILLABLE); + if (ret) + mutex_release(&lock->dep_map, 1, _RET_IP_); + return ret; +} +EXPORT_SYMBOL(_mutex_lock_killable_nested); +#endif + +int __lockfunc _mutex_trylock(struct mutex *lock) +{ + int ret = __rt_mutex_trylock(&lock->lock); + + if (ret) + mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_); + + return ret; +} +EXPORT_SYMBOL(_mutex_trylock); + +void __lockfunc _mutex_unlock(struct mutex *lock) +{ + mutex_release(&lock->dep_map, 1, _RET_IP_); + __rt_mutex_unlock(&lock->lock); +} +EXPORT_SYMBOL(_mutex_unlock); + +/** + * atomic_dec_and_mutex_lock - return holding mutex if we dec to 0 + * @cnt: the atomic which we are to dec + * @lock: the mutex to return holding if we dec to 0 + * + * return true and hold lock if we dec to 0, return false otherwise + */ +int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock) +{ + /* dec if we can't possibly hit 0 */ + if (atomic_add_unless(cnt, -1, 1)) + return 0; + /* we might hit 0, so take the lock */ + mutex_lock(lock); + if (!atomic_dec_and_test(cnt)) { + /* when we actually did the dec, we didn't hit 0 */ + mutex_unlock(lock); + return 0; + } + /* we hit 0, and we hold the lock */ + return 1; +} +EXPORT_SYMBOL(atomic_dec_and_mutex_lock); diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 9562aaa2afdc..38201a99a2ea 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -7,6 +7,11 @@ * Copyright (C) 2005-2006 Timesys Corp., Thomas Gleixner <tglx@timesys.com> * Copyright (C) 2005 Kihon Technologies Inc., Steven Rostedt * Copyright (C) 2006 Esben Nielsen + * Adaptive Spinlocks: + * Copyright (C) 2008 Novell, Inc., Gregory Haskins, Sven Dietrich, + * and Peter Morreale, + * Adaptive Spinlocks simplification: + * Copyright (C) 2008 Red Hat, Inc., Steven Rostedt <srostedt@redhat.com> * * See Documentation/locking/rt-mutex-design.txt for details. */ @@ -18,6 +23,8 @@ #include <linux/sched/wake_q.h> #include <linux/sched/debug.h> #include <linux/timer.h> +#include <linux/ww_mutex.h> +#include <linux/blkdev.h> #include "rtmutex_common.h" @@ -135,6 +142,12 @@ static void fixup_rt_mutex_waiters(struct rt_mutex *lock) WRITE_ONCE(*p, owner & ~RT_MUTEX_HAS_WAITERS); } +static int rt_mutex_real_waiter(struct rt_mutex_waiter *waiter) +{ + return waiter && waiter != PI_WAKEUP_INPROGRESS && + waiter != PI_REQUEUE_INPROGRESS; +} + /* * We can speed up the acquire/release, if there's no debugging state to be * set up. @@ -228,7 +241,7 @@ static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock, * Only use with rt_mutex_waiter_{less,equal}() */ #define task_to_waiter(p) \ - &(struct rt_mutex_waiter){ .prio = (p)->prio, .deadline = (p)->dl.deadline } + &(struct rt_mutex_waiter){ .prio = (p)->prio, .deadline = (p)->dl.deadline, .task = (p) } static inline int rt_mutex_waiter_less(struct rt_mutex_waiter *left, @@ -268,6 +281,27 @@ rt_mutex_waiter_equal(struct rt_mutex_waiter *left, return 1; } +#define STEAL_NORMAL 0 +#define STEAL_LATERAL 1 + +static inline int +rt_mutex_steal(struct rt_mutex *lock, struct rt_mutex_waiter *waiter, int mode) +{ + struct rt_mutex_waiter *top_waiter = rt_mutex_top_waiter(lock); + + if (waiter == top_waiter || rt_mutex_waiter_less(waiter, top_waiter)) + return 1; + + /* + * Note that RT tasks are excluded from lateral-steals + * to prevent the introduction of an unbounded latency. + */ + if (mode == STEAL_NORMAL || rt_task(waiter->task)) + return 0; + + return rt_mutex_waiter_equal(waiter, top_waiter); +} + static void rt_mutex_enqueue(struct rt_mutex *lock, struct rt_mutex_waiter *waiter) { @@ -372,6 +406,14 @@ static bool rt_mutex_cond_detect_deadlock(struct rt_mutex_waiter *waiter, return debug_rt_mutex_detect_deadlock(waiter, chwalk); } +static void rt_mutex_wake_waiter(struct rt_mutex_waiter *waiter) +{ + if (waiter->savestate) + wake_up_lock_sleeper(waiter->task); + else + wake_up_process(waiter->task); +} + /* * Max number of times we'll walk the boosting chain: */ @@ -379,7 +421,8 @@ int max_lock_depth = 1024; static inline struct rt_mutex *task_blocked_on_lock(struct task_struct *p) { - return p->pi_blocked_on ? p->pi_blocked_on->lock : NULL; + return rt_mutex_real_waiter(p->pi_blocked_on) ? + p->pi_blocked_on->lock : NULL; } /* @@ -515,7 +558,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, * reached or the state of the chain has changed while we * dropped the locks. */ - if (!waiter) + if (!rt_mutex_real_waiter(waiter)) goto out_unlock_pi; /* @@ -696,13 +739,16 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, * follow here. This is the end of the chain we are walking. */ if (!rt_mutex_owner(lock)) { + struct rt_mutex_waiter *lock_top_waiter; + /* * If the requeue [7] above changed the top waiter, * then we need to wake the new top waiter up to try * to get the lock. */ - if (prerequeue_top_waiter != rt_mutex_top_waiter(lock)) - wake_up_process(rt_mutex_top_waiter(lock)->task); + lock_top_waiter = rt_mutex_top_waiter(lock); + if (prerequeue_top_waiter != lock_top_waiter) + rt_mutex_wake_waiter(lock_top_waiter); raw_spin_unlock_irq(&lock->wait_lock); return 0; } @@ -804,9 +850,11 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, * @task: The task which wants to acquire the lock * @waiter: The waiter that is queued to the lock's wait tree if the * callsite called task_blocked_on_lock(), otherwise NULL + * @mode: Lock steal mode (STEAL_NORMAL, STEAL_LATERAL) */ -static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, - struct rt_mutex_waiter *waiter) +static int __try_to_take_rt_mutex(struct rt_mutex *lock, + struct task_struct *task, + struct rt_mutex_waiter *waiter, int mode) { lockdep_assert_held(&lock->wait_lock); @@ -842,12 +890,11 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, */ if (waiter) { /* - * If waiter is not the highest priority waiter of - * @lock, give up. + * If waiter is not the highest priority waiter of @lock, + * or its peer when lateral steal is allowed, give up. */ - if (waiter != rt_mutex_top_waiter(lock)) + if (!rt_mutex_steal(lock, waiter, mode)) return 0; - /* * We can acquire the lock. Remove the waiter from the * lock waiters tree. @@ -865,14 +912,12 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, */ if (rt_mutex_has_waiters(lock)) { /* - * If @task->prio is greater than or equal to - * the top waiter priority (kernel view), - * @task lost. + * If @task->prio is greater than the top waiter + * priority (kernel view), or equal to it when a + * lateral steal is forbidden, @task lost. */ - if (!rt_mutex_waiter_less(task_to_waiter(task), - rt_mutex_top_waiter(lock))) + if (!rt_mutex_steal(lock, task_to_waiter(task), mode)) return 0; - /* * The current top waiter stays enqueued. We * don't have to change anything in the lock @@ -919,6 +964,338 @@ takeit: return 1; } +#ifdef CONFIG_PREEMPT_RT_FULL +/* + * preemptible spin_lock functions: + */ +static inline void rt_spin_lock_fastlock(struct rt_mutex *lock, + void (*slowfn)(struct rt_mutex *lock)) +{ + might_sleep_no_state_check(); + + if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) + return; + else + slowfn(lock); +} + +static inline void rt_spin_lock_fastunlock(struct rt_mutex *lock, + void (*slowfn)(struct rt_mutex *lock)) +{ + if (likely(rt_mutex_cmpxchg_release(lock, current, NULL))) + return; + else + slowfn(lock); +} +#ifdef CONFIG_SMP +/* + * Note that owner is a speculative pointer and dereferencing relies + * on rcu_read_lock() and the check against the lock owner. + */ +static int adaptive_wait(struct rt_mutex *lock, + struct task_struct *owner) +{ + int res = 0; + + rcu_read_lock(); + for (;;) { + if (owner != rt_mutex_owner(lock)) + break; + /* + * Ensure that owner->on_cpu is dereferenced _after_ + * checking the above to be valid. + */ + barrier(); + if (!owner->on_cpu) { + res = 1; + break; + } + cpu_relax(); + } + rcu_read_unlock(); + return res; +} +#else +static int adaptive_wait(struct rt_mutex *lock, + struct task_struct *orig_owner) +{ + return 1; +} +#endif + +static int task_blocks_on_rt_mutex(struct rt_mutex *lock, + struct rt_mutex_waiter *waiter, + struct task_struct *task, + enum rtmutex_chainwalk chwalk); +/* + * Slow path lock function spin_lock style: this variant is very + * careful not to miss any non-lock wakeups. + * + * We store the current state under p->pi_lock in p->saved_state and + * the try_to_wake_up() code handles this accordingly. + */ +void __sched rt_spin_lock_slowlock_locked(struct rt_mutex *lock, + struct rt_mutex_waiter *waiter, + unsigned long flags) +{ + struct task_struct *lock_owner, *self = current; + struct rt_mutex_waiter *top_waiter; + int ret; + + if (__try_to_take_rt_mutex(lock, self, NULL, STEAL_LATERAL)) + return; + + BUG_ON(rt_mutex_owner(lock) == self); + + /* + * We save whatever state the task is in and we'll restore it + * after acquiring the lock taking real wakeups into account + * as well. We are serialized via pi_lock against wakeups. See + * try_to_wake_up(). + */ + raw_spin_lock(&self->pi_lock); + self->saved_state = self->state; + __set_current_state_no_track(TASK_UNINTERRUPTIBLE); + raw_spin_unlock(&self->pi_lock); + + ret = task_blocks_on_rt_mutex(lock, waiter, self, RT_MUTEX_MIN_CHAINWALK); + BUG_ON(ret); + + for (;;) { + /* Try to acquire the lock again. */ + if (__try_to_take_rt_mutex(lock, self, waiter, STEAL_LATERAL)) + break; + + top_waiter = rt_mutex_top_waiter(lock); + lock_owner = rt_mutex_owner(lock); + + raw_spin_unlock_irqrestore(&lock->wait_lock, flags); + + debug_rt_mutex_print_deadlock(waiter); + + if (top_waiter != waiter || adaptive_wait(lock, lock_owner)) + schedule(); + + raw_spin_lock_irqsave(&lock->wait_lock, flags); + + raw_spin_lock(&self->pi_lock); + __set_current_state_no_track(TASK_UNINTERRUPTIBLE); + raw_spin_unlock(&self->pi_lock); + } + + /* + * Restore the task state to current->saved_state. We set it + * to the original state above and the try_to_wake_up() code + * has possibly updated it when a real (non-rtmutex) wakeup + * happened while we were blocked. Clear saved_state so + * try_to_wakeup() does not get confused. + */ + raw_spin_lock(&self->pi_lock); + __set_current_state_no_track(self->saved_state); + self->saved_state = TASK_RUNNING; + raw_spin_unlock(&self->pi_lock); + + /* + * try_to_take_rt_mutex() sets the waiter bit + * unconditionally. We might have to fix that up: + */ + fixup_rt_mutex_waiters(lock); + + BUG_ON(rt_mutex_has_waiters(lock) && waiter == rt_mutex_top_waiter(lock)); + BUG_ON(!RB_EMPTY_NODE(&waiter->tree_entry)); +} + +static void noinline __sched rt_spin_lock_slowlock(struct rt_mutex *lock) +{ + struct rt_mutex_waiter waiter; + unsigned long flags; + + rt_mutex_init_waiter(&waiter, true); + + raw_spin_lock_irqsave(&lock->wait_lock, flags); + rt_spin_lock_slowlock_locked(lock, &waiter, flags); + raw_spin_unlock_irqrestore(&lock->wait_lock, flags); + debug_rt_mutex_free_waiter(&waiter); +} + +static bool __sched __rt_mutex_unlock_common(struct rt_mutex *lock, + struct wake_q_head *wake_q, + struct wake_q_head *wq_sleeper); +/* + * Slow path to release a rt_mutex spin_lock style + */ +void __sched rt_spin_lock_slowunlock(struct rt_mutex *lock) +{ + unsigned long flags; + DEFINE_WAKE_Q(wake_q); + DEFINE_WAKE_Q(wake_sleeper_q); + bool postunlock; + + raw_spin_lock_irqsave(&lock->wait_lock, flags); + postunlock = __rt_mutex_unlock_common(lock, &wake_q, &wake_sleeper_q); + raw_spin_unlock_irqrestore(&lock->wait_lock, flags); + + if (postunlock) + rt_mutex_postunlock(&wake_q, &wake_sleeper_q); +} + +void __lockfunc rt_spin_lock(spinlock_t *lock) +{ + sleeping_lock_inc(); + migrate_disable(); + spin_acquire(&lock->dep_map, 0, 0, _RET_IP_); + rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock); +} +EXPORT_SYMBOL(rt_spin_lock); + +void __lockfunc __rt_spin_lock(struct rt_mutex *lock) +{ + rt_spin_lock_fastlock(lock, rt_spin_lock_slowlock); +} + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +void __lockfunc rt_spin_lock_nested(spinlock_t *lock, int subclass) +{ + sleeping_lock_inc(); + migrate_disable(); + spin_acquire(&lock->dep_map, subclass, 0, _RET_IP_); + rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock); +} +EXPORT_SYMBOL(rt_spin_lock_nested); +#endif + +void __lockfunc rt_spin_unlock(spinlock_t *lock) +{ + /* NOTE: we always pass in '1' for nested, for simplicity */ + spin_release(&lock->dep_map, 1, _RET_IP_); + rt_spin_lock_fastunlock(&lock->lock, rt_spin_lock_slowunlock); + migrate_enable(); + sleeping_lock_dec(); +} +EXPORT_SYMBOL(rt_spin_unlock); + +void __lockfunc __rt_spin_unlock(struct rt_mutex *lock) +{ + rt_spin_lock_fastunlock(lock, rt_spin_lock_slowunlock); +} +EXPORT_SYMBOL(__rt_spin_unlock); + +/* + * Wait for the lock to get unlocked: instead of polling for an unlock + * (like raw spinlocks do), we lock and unlock, to force the kernel to + * schedule if there's contention: + */ +void __lockfunc rt_spin_unlock_wait(spinlock_t *lock) +{ + spin_lock(lock); + spin_unlock(lock); +} +EXPORT_SYMBOL(rt_spin_unlock_wait); + +int __lockfunc rt_spin_trylock(spinlock_t *lock) +{ + int ret; + + sleeping_lock_inc(); + migrate_disable(); + ret = __rt_mutex_trylock(&lock->lock); + if (ret) { + spin_acquire(&lock->dep_map, 0, 1, _RET_IP_); + } else { + migrate_enable(); + sleeping_lock_dec(); + } + return ret; +} +EXPORT_SYMBOL(rt_spin_trylock); + +int __lockfunc rt_spin_trylock_bh(spinlock_t *lock) +{ + int ret; + + local_bh_disable(); + ret = __rt_mutex_trylock(&lock->lock); + if (ret) { + sleeping_lock_inc(); + migrate_disable(); + spin_acquire(&lock->dep_map, 0, 1, _RET_IP_); + } else + local_bh_enable(); + return ret; +} +EXPORT_SYMBOL(rt_spin_trylock_bh); + +int __lockfunc rt_spin_trylock_irqsave(spinlock_t *lock, unsigned long *flags) +{ + int ret; + + *flags = 0; + ret = __rt_mutex_trylock(&lock->lock); + if (ret) { + sleeping_lock_inc(); + migrate_disable(); + spin_acquire(&lock->dep_map, 0, 1, _RET_IP_); + } + return ret; +} +EXPORT_SYMBOL(rt_spin_trylock_irqsave); + +void +__rt_spin_lock_init(spinlock_t *lock, const char *name, struct lock_class_key *key) +{ +#ifdef CONFIG_DEBUG_LOCK_ALLOC + /* + * Make sure we are not reinitializing a held lock: + */ + debug_check_no_locks_freed((void *)lock, sizeof(*lock)); + lockdep_init_map(&lock->dep_map, name, key, 0); +#endif +} +EXPORT_SYMBOL(__rt_spin_lock_init); + +#endif /* PREEMPT_RT_FULL */ + +#ifdef CONFIG_PREEMPT_RT_FULL + static inline int __sched +__mutex_lock_check_stamp(struct rt_mutex *lock, struct ww_acquire_ctx *ctx) +{ + struct ww_mutex *ww = container_of(lock, struct ww_mutex, base.lock); + struct ww_acquire_ctx *hold_ctx = READ_ONCE(ww->ctx); + + if (!hold_ctx) + return 0; + + if (unlikely(ctx == hold_ctx)) + return -EALREADY; + + if (ctx->stamp - hold_ctx->stamp <= LONG_MAX && + (ctx->stamp != hold_ctx->stamp || ctx > hold_ctx)) { +#ifdef CONFIG_DEBUG_MUTEXES + DEBUG_LOCKS_WARN_ON(ctx->contending_lock); + ctx->contending_lock = ww; +#endif + return -EDEADLK; + } + + return 0; +} +#else + static inline int __sched +__mutex_lock_check_stamp(struct rt_mutex *lock, struct ww_acquire_ctx *ctx) +{ + BUG(); + return 0; +} + +#endif + +static inline int +try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, + struct rt_mutex_waiter *waiter) +{ + return __try_to_take_rt_mutex(lock, task, waiter, STEAL_NORMAL); +} + /* * Task blocks on lock. * @@ -951,6 +1328,22 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, return -EDEADLK; raw_spin_lock(&task->pi_lock); + /* + * In the case of futex requeue PI, this will be a proxy + * lock. The task will wake unaware that it is enqueueed on + * this lock. Avoid blocking on two locks and corrupting + * pi_blocked_on via the PI_WAKEUP_INPROGRESS + * flag. futex_wait_requeue_pi() sets this when it wakes up + * before requeue (due to a signal or timeout). Do not enqueue + * the task if PI_WAKEUP_INPROGRESS is set. + */ + if (task != current && task->pi_blocked_on == PI_WAKEUP_INPROGRESS) { + raw_spin_unlock(&task->pi_lock); + return -EAGAIN; + } + + BUG_ON(rt_mutex_real_waiter(task->pi_blocked_on)); + waiter->task = task; waiter->lock = lock; waiter->prio = task->prio; @@ -974,7 +1367,7 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, rt_mutex_enqueue_pi(owner, waiter); rt_mutex_adjust_prio(owner); - if (owner->pi_blocked_on) + if (rt_mutex_real_waiter(owner->pi_blocked_on)) chain_walk = 1; } else if (rt_mutex_cond_detect_deadlock(waiter, chwalk)) { chain_walk = 1; @@ -1016,6 +1409,7 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, * Called with lock->wait_lock held and interrupts disabled. */ static void mark_wakeup_next_waiter(struct wake_q_head *wake_q, + struct wake_q_head *wake_sleeper_q, struct rt_mutex *lock) { struct rt_mutex_waiter *waiter; @@ -1055,7 +1449,10 @@ static void mark_wakeup_next_waiter(struct wake_q_head *wake_q, * Pairs with preempt_enable() in rt_mutex_postunlock(); */ preempt_disable(); - wake_q_add(wake_q, waiter->task); + if (waiter->savestate) + wake_q_add_sleeper(wake_sleeper_q, waiter->task); + else + wake_q_add(wake_q, waiter->task); raw_spin_unlock(¤t->pi_lock); } @@ -1070,7 +1467,7 @@ static void remove_waiter(struct rt_mutex *lock, { bool is_top_waiter = (waiter == rt_mutex_top_waiter(lock)); struct task_struct *owner = rt_mutex_owner(lock); - struct rt_mutex *next_lock; + struct rt_mutex *next_lock = NULL; lockdep_assert_held(&lock->wait_lock); @@ -1096,7 +1493,8 @@ static void remove_waiter(struct rt_mutex *lock, rt_mutex_adjust_prio(owner); /* Store the lock on which owner is blocked or NULL */ - next_lock = task_blocked_on_lock(owner); + if (rt_mutex_real_waiter(owner->pi_blocked_on)) + next_lock = task_blocked_on_lock(owner); raw_spin_unlock(&owner->pi_lock); @@ -1132,26 +1530,28 @@ void rt_mutex_adjust_pi(struct task_struct *task) raw_spin_lock_irqsave(&task->pi_lock, flags); waiter = task->pi_blocked_on; - if (!waiter || rt_mutex_waiter_equal(waiter, task_to_waiter(task))) { + if (!rt_mutex_real_waiter(waiter) || + rt_mutex_waiter_equal(waiter, task_to_waiter(task))) { raw_spin_unlock_irqrestore(&task->pi_lock, flags); return; } next_lock = waiter->lock; - raw_spin_unlock_irqrestore(&task->pi_lock, flags); /* gets dropped in rt_mutex_adjust_prio_chain()! */ get_task_struct(task); + raw_spin_unlock_irqrestore(&task->pi_lock, flags); rt_mutex_adjust_prio_chain(task, RT_MUTEX_MIN_CHAINWALK, NULL, next_lock, NULL, task); } -void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter) +void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter, bool savestate) { debug_rt_mutex_init_waiter(waiter); RB_CLEAR_NODE(&waiter->pi_tree_entry); RB_CLEAR_NODE(&waiter->tree_entry); waiter->task = NULL; + waiter->savestate = savestate; } /** @@ -1167,7 +1567,8 @@ void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter) static int __sched __rt_mutex_slowlock(struct rt_mutex *lock, int state, struct hrtimer_sleeper *timeout, - struct rt_mutex_waiter *waiter) + struct rt_mutex_waiter *waiter, + struct ww_acquire_ctx *ww_ctx) { int ret = 0; @@ -1176,16 +1577,17 @@ __rt_mutex_slowlock(struct rt_mutex *lock, int state, if (try_to_take_rt_mutex(lock, current, waiter)) break; - /* - * TASK_INTERRUPTIBLE checks for signals and - * timeout. Ignored otherwise. - */ - if (likely(state == TASK_INTERRUPTIBLE)) { - /* Signal pending? */ - if (signal_pending(current)) - ret = -EINTR; - if (timeout && !timeout->task) - ret = -ETIMEDOUT; + if (timeout && !timeout->task) { + ret = -ETIMEDOUT; + break; + } + if (signal_pending_state(state, current)) { + ret = -EINTR; + break; + } + + if (ww_ctx && ww_ctx->acquired > 0) { + ret = __mutex_lock_check_stamp(lock, ww_ctx); if (ret) break; } @@ -1224,33 +1626,104 @@ static void rt_mutex_handle_deadlock(int res, int detect_deadlock, } } -/* - * Slow path lock function: - */ -static int __sched -rt_mutex_slowlock(struct rt_mutex *lock, int state, - struct hrtimer_sleeper *timeout, - enum rtmutex_chainwalk chwalk) +static __always_inline void ww_mutex_lock_acquired(struct ww_mutex *ww, + struct ww_acquire_ctx *ww_ctx) { - struct rt_mutex_waiter waiter; - unsigned long flags; - int ret = 0; +#ifdef CONFIG_DEBUG_MUTEXES + /* + * If this WARN_ON triggers, you used ww_mutex_lock to acquire, + * but released with a normal mutex_unlock in this call. + * + * This should never happen, always use ww_mutex_unlock. + */ + DEBUG_LOCKS_WARN_ON(ww->ctx); - rt_mutex_init_waiter(&waiter); + /* + * Not quite done after calling ww_acquire_done() ? + */ + DEBUG_LOCKS_WARN_ON(ww_ctx->done_acquire); + + if (ww_ctx->contending_lock) { + /* + * After -EDEADLK you tried to + * acquire a different ww_mutex? Bad! + */ + DEBUG_LOCKS_WARN_ON(ww_ctx->contending_lock != ww); + + /* + * You called ww_mutex_lock after receiving -EDEADLK, + * but 'forgot' to unlock everything else first? + */ + DEBUG_LOCKS_WARN_ON(ww_ctx->acquired > 0); + ww_ctx->contending_lock = NULL; + } /* - * Technically we could use raw_spin_[un]lock_irq() here, but this can - * be called in early boot if the cmpxchg() fast path is disabled - * (debug, no architecture support). In this case we will acquire the - * rtmutex with lock->wait_lock held. But we cannot unconditionally - * enable interrupts in that early boot case. So we need to use the - * irqsave/restore variants. + * Naughty, using a different class will lead to undefined behavior! */ - raw_spin_lock_irqsave(&lock->wait_lock, flags); + DEBUG_LOCKS_WARN_ON(ww_ctx->ww_class != ww->ww_class); +#endif + ww_ctx->acquired++; +} + +#ifdef CONFIG_PREEMPT_RT_FULL +static void ww_mutex_account_lock(struct rt_mutex *lock, + struct ww_acquire_ctx *ww_ctx) +{ + struct ww_mutex *ww = container_of(lock, struct ww_mutex, base.lock); + struct rt_mutex_waiter *waiter, *n; + + /* + * This branch gets optimized out for the common case, + * and is only important for ww_mutex_lock. + */ + ww_mutex_lock_acquired(ww, ww_ctx); + ww->ctx = ww_ctx; + + /* + * Give any possible sleeping processes the chance to wake up, + * so they can recheck if they have to back off. + */ + rbtree_postorder_for_each_entry_safe(waiter, n, &lock->waiters.rb_root, + tree_entry) { + /* XXX debug rt mutex waiter wakeup */ + + BUG_ON(waiter->lock != lock); + rt_mutex_wake_waiter(waiter); + } +} + +#else + +static void ww_mutex_account_lock(struct rt_mutex *lock, + struct ww_acquire_ctx *ww_ctx) +{ + BUG(); +} +#endif + +int __sched rt_mutex_slowlock_locked(struct rt_mutex *lock, int state, + struct hrtimer_sleeper *timeout, + enum rtmutex_chainwalk chwalk, + struct ww_acquire_ctx *ww_ctx, + struct rt_mutex_waiter *waiter) +{ + int ret; + +#ifdef CONFIG_PREEMPT_RT_FULL + if (ww_ctx) { + struct ww_mutex *ww; + + ww = container_of(lock, struct ww_mutex, base.lock); + if (unlikely(ww_ctx == READ_ONCE(ww->ctx))) + return -EALREADY; + } +#endif /* Try to acquire the lock again: */ if (try_to_take_rt_mutex(lock, current, NULL)) { - raw_spin_unlock_irqrestore(&lock->wait_lock, flags); + if (ww_ctx) + ww_mutex_account_lock(lock, ww_ctx); return 0; } @@ -1260,16 +1733,26 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state, if (unlikely(timeout)) hrtimer_start_expires(&timeout->timer, HRTIMER_MODE_ABS); - ret = task_blocks_on_rt_mutex(lock, &waiter, current, chwalk); + ret = task_blocks_on_rt_mutex(lock, waiter, current, chwalk); - if (likely(!ret)) + if (likely(!ret)) { /* sleep on the mutex */ - ret = __rt_mutex_slowlock(lock, state, timeout, &waiter); + ret = __rt_mutex_slowlock(lock, state, timeout, waiter, + ww_ctx); + } else if (ww_ctx) { + /* ww_mutex received EDEADLK, let it become EALREADY */ + ret = __mutex_lock_check_stamp(lock, ww_ctx); + BUG_ON(!ret); + } if (unlikely(ret)) { __set_current_state(TASK_RUNNING); - remove_waiter(lock, &waiter); - rt_mutex_handle_deadlock(ret, chwalk, &waiter); + remove_waiter(lock, waiter); + /* ww_mutex wants to report EDEADLK/EALREADY, let it */ + if (!ww_ctx) + rt_mutex_handle_deadlock(ret, chwalk, waiter); + } else if (ww_ctx) { + ww_mutex_account_lock(lock, ww_ctx); } /* @@ -1277,6 +1760,36 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state, * unconditionally. We might have to fix that up. */ fixup_rt_mutex_waiters(lock); + return ret; +} + +/* + * Slow path lock function: + */ +static int __sched +rt_mutex_slowlock(struct rt_mutex *lock, int state, + struct hrtimer_sleeper *timeout, + enum rtmutex_chainwalk chwalk, + struct ww_acquire_ctx *ww_ctx) +{ + struct rt_mutex_waiter waiter; + unsigned long flags; + int ret = 0; + + rt_mutex_init_waiter(&waiter, false); + + /* + * Technically we could use raw_spin_[un]lock_irq() here, but this can + * be called in early boot if the cmpxchg() fast path is disabled + * (debug, no architecture support). In this case we will acquire the + * rtmutex with lock->wait_lock held. But we cannot unconditionally + * enable interrupts in that early boot case. So we need to use the + * irqsave/restore variants. + */ + raw_spin_lock_irqsave(&lock->wait_lock, flags); + + ret = rt_mutex_slowlock_locked(lock, state, timeout, chwalk, ww_ctx, + &waiter); raw_spin_unlock_irqrestore(&lock->wait_lock, flags); @@ -1337,7 +1850,8 @@ static inline int rt_mutex_slowtrylock(struct rt_mutex *lock) * Return whether the current task needs to call rt_mutex_postunlock(). */ static bool __sched rt_mutex_slowunlock(struct rt_mutex *lock, - struct wake_q_head *wake_q) + struct wake_q_head *wake_q, + struct wake_q_head *wake_sleeper_q) { unsigned long flags; @@ -1391,7 +1905,7 @@ static bool __sched rt_mutex_slowunlock(struct rt_mutex *lock, * * Queue the next waiter for wakeup once we release the wait_lock. */ - mark_wakeup_next_waiter(wake_q, lock); + mark_wakeup_next_waiter(wake_q, wake_sleeper_q, lock); raw_spin_unlock_irqrestore(&lock->wait_lock, flags); return true; /* call rt_mutex_postunlock() */ @@ -1405,29 +1919,45 @@ static bool __sched rt_mutex_slowunlock(struct rt_mutex *lock, */ static inline int rt_mutex_fastlock(struct rt_mutex *lock, int state, + struct ww_acquire_ctx *ww_ctx, int (*slowfn)(struct rt_mutex *lock, int state, struct hrtimer_sleeper *timeout, - enum rtmutex_chainwalk chwalk)) + enum rtmutex_chainwalk chwalk, + struct ww_acquire_ctx *ww_ctx)) { if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) return 0; - return slowfn(lock, state, NULL, RT_MUTEX_MIN_CHAINWALK); + /* + * If rt_mutex blocks, the function sched_submit_work will not call + * blk_schedule_flush_plug (because tsk_is_pi_blocked would be true). + * We must call blk_schedule_flush_plug here, if we don't call it, + * a deadlock in device mapper may happen. + */ + if (unlikely(blk_needs_flush_plug(current))) + blk_schedule_flush_plug(current); + + return slowfn(lock, state, NULL, RT_MUTEX_MIN_CHAINWALK, ww_ctx); } static inline int rt_mutex_timed_fastlock(struct rt_mutex *lock, int state, struct hrtimer_sleeper *timeout, enum rtmutex_chainwalk chwalk, + struct ww_acquire_ctx *ww_ctx, int (*slowfn)(struct rt_mutex *lock, int state, struct hrtimer_sleeper *timeout, - enum rtmutex_chainwalk chwalk)) + enum rtmutex_chainwalk chwalk, + struct ww_acquire_ctx *ww_ctx)) { if (chwalk == RT_MUTEX_MIN_CHAINWALK && likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) return 0; - return slowfn(lock, state, timeout, chwalk); + if (unlikely(blk_needs_flush_plug(current))) + blk_schedule_flush_plug(current); + + return slowfn(lock, state, timeout, chwalk, ww_ctx); } static inline int @@ -1443,9 +1973,11 @@ rt_mutex_fasttrylock(struct rt_mutex *lock, /* * Performs the wakeup of the the top-waiter and re-enables preemption. */ -void rt_mutex_postunlock(struct wake_q_head *wake_q) +void rt_mutex_postunlock(struct wake_q_head *wake_q, + struct wake_q_head *wake_sleeper_q) { wake_up_q(wake_q); + wake_up_q_sleeper(wake_sleeper_q); /* Pairs with preempt_disable() in rt_mutex_slowunlock() */ preempt_enable(); @@ -1454,23 +1986,46 @@ void rt_mutex_postunlock(struct wake_q_head *wake_q) static inline void rt_mutex_fastunlock(struct rt_mutex *lock, bool (*slowfn)(struct rt_mutex *lock, - struct wake_q_head *wqh)) + struct wake_q_head *wqh, + struct wake_q_head *wq_sleeper)) { DEFINE_WAKE_Q(wake_q); + DEFINE_WAKE_Q(wake_sleeper_q); if (likely(rt_mutex_cmpxchg_release(lock, current, NULL))) return; - if (slowfn(lock, &wake_q)) - rt_mutex_postunlock(&wake_q); + if (slowfn(lock, &wake_q, &wake_sleeper_q)) + rt_mutex_postunlock(&wake_q, &wake_sleeper_q); } -static inline void __rt_mutex_lock(struct rt_mutex *lock, unsigned int subclass) +int __sched __rt_mutex_lock_state(struct rt_mutex *lock, int state) { might_sleep(); + return rt_mutex_fastlock(lock, state, NULL, rt_mutex_slowlock); +} + +/** + * rt_mutex_lock_state - lock a rt_mutex with a given state + * + * @lock: The rt_mutex to be locked + * @state: The state to set when blocking on the rt_mutex + */ +static inline int __sched rt_mutex_lock_state(struct rt_mutex *lock, + unsigned int subclass, int state) +{ + int ret; mutex_acquire(&lock->dep_map, subclass, 0, _RET_IP_); - rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, rt_mutex_slowlock); + ret = __rt_mutex_lock_state(lock, state); + if (ret) + mutex_release(&lock->dep_map, 1, _RET_IP_); + return ret; +} + +static inline void __rt_mutex_lock(struct rt_mutex *lock, unsigned int subclass) +{ + rt_mutex_lock_state(lock, subclass, TASK_UNINTERRUPTIBLE); } #ifdef CONFIG_DEBUG_LOCK_ALLOC @@ -1511,16 +2066,7 @@ EXPORT_SYMBOL_GPL(rt_mutex_lock); */ int __sched rt_mutex_lock_interruptible(struct rt_mutex *lock) { - int ret; - - might_sleep(); - - mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_); - ret = rt_mutex_fastlock(lock, TASK_INTERRUPTIBLE, rt_mutex_slowlock); - if (ret) - mutex_release(&lock->dep_map, 1, _RET_IP_); - - return ret; + return rt_mutex_lock_state(lock, 0, TASK_INTERRUPTIBLE); } EXPORT_SYMBOL_GPL(rt_mutex_lock_interruptible); @@ -1538,6 +2084,22 @@ int __sched __rt_mutex_futex_trylock(struct rt_mutex *lock) } /** + * rt_mutex_lock_killable - lock a rt_mutex killable + * + * @lock: the rt_mutex to be locked + * @detect_deadlock: deadlock detection on/off + * + * Returns: + * 0 on success + * -EINTR when interrupted by a signal + */ +int __sched rt_mutex_lock_killable(struct rt_mutex *lock) +{ + return rt_mutex_lock_state(lock, 0, TASK_KILLABLE); +} +EXPORT_SYMBOL_GPL(rt_mutex_lock_killable); + +/** * rt_mutex_timed_lock - lock a rt_mutex interruptible * the timeout structure is provided * by the caller @@ -1560,6 +2122,7 @@ rt_mutex_timed_lock(struct rt_mutex *lock, struct hrtimer_sleeper *timeout) mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_); ret = rt_mutex_timed_fastlock(lock, TASK_INTERRUPTIBLE, timeout, RT_MUTEX_MIN_CHAINWALK, + NULL, rt_mutex_slowlock); if (ret) mutex_release(&lock->dep_map, 1, _RET_IP_); @@ -1568,6 +2131,18 @@ rt_mutex_timed_lock(struct rt_mutex *lock, struct hrtimer_sleeper *timeout) } EXPORT_SYMBOL_GPL(rt_mutex_timed_lock); +int __sched __rt_mutex_trylock(struct rt_mutex *lock) +{ +#ifdef CONFIG_PREEMPT_RT_FULL + if (WARN_ON_ONCE(in_irq() || in_nmi())) +#else + if (WARN_ON_ONCE(in_irq() || in_nmi() || in_serving_softirq())) +#endif + return 0; + + return rt_mutex_fasttrylock(lock, rt_mutex_slowtrylock); +} + /** * rt_mutex_trylock - try to lock a rt_mutex * @@ -1583,10 +2158,7 @@ int __sched rt_mutex_trylock(struct rt_mutex *lock) { int ret; - if (WARN_ON_ONCE(in_irq() || in_nmi() || in_serving_softirq())) - return 0; - - ret = rt_mutex_fasttrylock(lock, rt_mutex_slowtrylock); + ret = __rt_mutex_trylock(lock); if (ret) mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_); @@ -1594,6 +2166,11 @@ int __sched rt_mutex_trylock(struct rt_mutex *lock) } EXPORT_SYMBOL_GPL(rt_mutex_trylock); +void __sched __rt_mutex_unlock(struct rt_mutex *lock) +{ + rt_mutex_fastunlock(lock, rt_mutex_slowunlock); +} + /** * rt_mutex_unlock - unlock a rt_mutex * @@ -1602,16 +2179,13 @@ EXPORT_SYMBOL_GPL(rt_mutex_trylock); void __sched rt_mutex_unlock(struct rt_mutex *lock) { mutex_release(&lock->dep_map, 1, _RET_IP_); - rt_mutex_fastunlock(lock, rt_mutex_slowunlock); + __rt_mutex_unlock(lock); } EXPORT_SYMBOL_GPL(rt_mutex_unlock); -/** - * Futex variant, that since futex variants do not use the fast-path, can be - * simple and will not need to retry. - */ -bool __sched __rt_mutex_futex_unlock(struct rt_mutex *lock, - struct wake_q_head *wake_q) +static bool __sched __rt_mutex_unlock_common(struct rt_mutex *lock, + struct wake_q_head *wake_q, + struct wake_q_head *wq_sleeper) { lockdep_assert_held(&lock->wait_lock); @@ -1628,23 +2202,35 @@ bool __sched __rt_mutex_futex_unlock(struct rt_mutex *lock, * avoid inversion prior to the wakeup. preempt_disable() * therein pairs with rt_mutex_postunlock(). */ - mark_wakeup_next_waiter(wake_q, lock); + mark_wakeup_next_waiter(wake_q, wq_sleeper, lock); return true; /* call postunlock() */ } +/** + * Futex variant, that since futex variants do not use the fast-path, can be + * simple and will not need to retry. + */ +bool __sched __rt_mutex_futex_unlock(struct rt_mutex *lock, + struct wake_q_head *wake_q, + struct wake_q_head *wq_sleeper) +{ + return __rt_mutex_unlock_common(lock, wake_q, wq_sleeper); +} + void __sched rt_mutex_futex_unlock(struct rt_mutex *lock) { DEFINE_WAKE_Q(wake_q); + DEFINE_WAKE_Q(wake_sleeper_q); unsigned long flags; bool postunlock; raw_spin_lock_irqsave(&lock->wait_lock, flags); - postunlock = __rt_mutex_futex_unlock(lock, &wake_q); + postunlock = __rt_mutex_futex_unlock(lock, &wake_q, &wake_sleeper_q); raw_spin_unlock_irqrestore(&lock->wait_lock, flags); if (postunlock) - rt_mutex_postunlock(&wake_q); + rt_mutex_postunlock(&wake_q, &wake_sleeper_q); } /** @@ -1683,7 +2269,7 @@ void __rt_mutex_init(struct rt_mutex *lock, const char *name, if (name && key) debug_rt_mutex_init(lock, name, key); } -EXPORT_SYMBOL_GPL(__rt_mutex_init); +EXPORT_SYMBOL(__rt_mutex_init); /** * rt_mutex_init_proxy_locked - initialize and lock a rt_mutex on behalf of a @@ -1703,6 +2289,14 @@ void rt_mutex_init_proxy_locked(struct rt_mutex *lock, struct task_struct *proxy_owner) { __rt_mutex_init(lock, NULL, NULL); +#ifdef CONFIG_DEBUG_SPINLOCK + /* + * get another key class for the wait_lock. LOCK_PI and UNLOCK_PI is + * holding the ->wait_lock of the proxy_lock while unlocking a sleeping + * lock. + */ + raw_spin_lock_init(&lock->wait_lock); +#endif debug_rt_mutex_proxy_lock(lock, proxy_owner); rt_mutex_set_owner(lock, proxy_owner); } @@ -1756,6 +2350,34 @@ int __rt_mutex_start_proxy_lock(struct rt_mutex *lock, if (try_to_take_rt_mutex(lock, task, NULL)) return 1; +#ifdef CONFIG_PREEMPT_RT_FULL + /* + * In PREEMPT_RT there's an added race. + * If the task, that we are about to requeue, times out, + * it can set the PI_WAKEUP_INPROGRESS. This tells the requeue + * to skip this task. But right after the task sets + * its pi_blocked_on to PI_WAKEUP_INPROGRESS it can then + * block on the spin_lock(&hb->lock), which in RT is an rtmutex. + * This will replace the PI_WAKEUP_INPROGRESS with the actual + * lock that it blocks on. We *must not* place this task + * on this proxy lock in that case. + * + * To prevent this race, we first take the task's pi_lock + * and check if it has updated its pi_blocked_on. If it has, + * we assume that it woke up and we return -EAGAIN. + * Otherwise, we set the task's pi_blocked_on to + * PI_REQUEUE_INPROGRESS, so that if the task is waking up + * it will know that we are in the process of requeuing it. + */ + raw_spin_lock(&task->pi_lock); + if (task->pi_blocked_on) { + raw_spin_unlock(&task->pi_lock); + return -EAGAIN; + } + task->pi_blocked_on = PI_REQUEUE_INPROGRESS; + raw_spin_unlock(&task->pi_lock); +#endif + /* We enforce deadlock detection for futexes */ ret = task_blocks_on_rt_mutex(lock, waiter, task, RT_MUTEX_FULL_CHAINWALK); @@ -1850,17 +2472,36 @@ int rt_mutex_wait_proxy_lock(struct rt_mutex *lock, struct hrtimer_sleeper *to, struct rt_mutex_waiter *waiter) { + struct task_struct *tsk = current; int ret; raw_spin_lock_irq(&lock->wait_lock); /* sleep on the mutex */ set_current_state(TASK_INTERRUPTIBLE); - ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter); + ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter, NULL); /* * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might * have to fix that up. */ fixup_rt_mutex_waiters(lock); + /* + * RT has a problem here when the wait got interrupted by a timeout + * or a signal. task->pi_blocked_on is still set. The task must + * acquire the hash bucket lock when returning from this function. + * + * If the hash bucket lock is contended then the + * BUG_ON(rt_mutex_real_waiter(task->pi_blocked_on)) in + * task_blocks_on_rt_mutex() will trigger. This can be avoided by + * clearing task->pi_blocked_on which removes the task from the + * boosting chain of the rtmutex. That's correct because the task + * is not longer blocked on it. + */ + if (ret) { + raw_spin_lock(&tsk->pi_lock); + tsk->pi_blocked_on = NULL; + raw_spin_unlock(&tsk->pi_lock); + } + raw_spin_unlock_irq(&lock->wait_lock); return ret; @@ -1922,3 +2563,99 @@ bool rt_mutex_cleanup_proxy_lock(struct rt_mutex *lock, return cleanup; } + +static inline int +ww_mutex_deadlock_injection(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) +{ +#ifdef CONFIG_DEBUG_WW_MUTEX_SLOWPATH + unsigned tmp; + + if (ctx->deadlock_inject_countdown-- == 0) { + tmp = ctx->deadlock_inject_interval; + if (tmp > UINT_MAX/4) + tmp = UINT_MAX; + else + tmp = tmp*2 + tmp + tmp/2; + + ctx->deadlock_inject_interval = tmp; + ctx->deadlock_inject_countdown = tmp; + ctx->contending_lock = lock; + + ww_mutex_unlock(lock); + + return -EDEADLK; + } +#endif + + return 0; +} + +#ifdef CONFIG_PREEMPT_RT_FULL +int __sched +ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) +{ + int ret; + + might_sleep(); + + mutex_acquire_nest(&lock->base.dep_map, 0, 0, + ctx ? &ctx->dep_map : NULL, _RET_IP_); + ret = rt_mutex_slowlock(&lock->base.lock, TASK_INTERRUPTIBLE, NULL, 0, + ctx); + if (ret) + mutex_release(&lock->base.dep_map, 1, _RET_IP_); + else if (!ret && ctx && ctx->acquired > 1) + return ww_mutex_deadlock_injection(lock, ctx); + + return ret; +} +EXPORT_SYMBOL_GPL(ww_mutex_lock_interruptible); + +int __sched +ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) +{ + int ret; + + might_sleep(); + + mutex_acquire_nest(&lock->base.dep_map, 0, 0, + ctx ? &ctx->dep_map : NULL, _RET_IP_); + ret = rt_mutex_slowlock(&lock->base.lock, TASK_UNINTERRUPTIBLE, NULL, 0, + ctx); + if (ret) + mutex_release(&lock->base.dep_map, 1, _RET_IP_); + else if (!ret && ctx && ctx->acquired > 1) + return ww_mutex_deadlock_injection(lock, ctx); + + return ret; +} +EXPORT_SYMBOL_GPL(ww_mutex_lock); + +void __sched ww_mutex_unlock(struct ww_mutex *lock) +{ + int nest = !!lock->ctx; + + /* + * The unlocking fastpath is the 0->1 transition from 'locked' + * into 'unlocked' state: + */ + if (nest) { +#ifdef CONFIG_DEBUG_MUTEXES + DEBUG_LOCKS_WARN_ON(!lock->ctx->acquired); +#endif + if (lock->ctx->acquired > 0) + lock->ctx->acquired--; + lock->ctx = NULL; + } + + mutex_release(&lock->base.dep_map, nest, _RET_IP_); + __rt_mutex_unlock(&lock->base.lock); +} +EXPORT_SYMBOL(ww_mutex_unlock); + +int __rt_mutex_owner_current(struct rt_mutex *lock) +{ + return rt_mutex_owner(lock) == current; +} +EXPORT_SYMBOL(__rt_mutex_owner_current); +#endif diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h index d1d62f942be2..546aaf058b9e 100644 --- a/kernel/locking/rtmutex_common.h +++ b/kernel/locking/rtmutex_common.h @@ -15,6 +15,7 @@ #include <linux/rtmutex.h> #include <linux/sched/wake_q.h> +#include <linux/sched/debug.h> /* * This is the control structure for tasks blocked on a rt_mutex, @@ -29,6 +30,7 @@ struct rt_mutex_waiter { struct rb_node pi_tree_entry; struct task_struct *task; struct rt_mutex *lock; + bool savestate; #ifdef CONFIG_DEBUG_RT_MUTEXES unsigned long ip; struct pid *deadlock_task_pid; @@ -130,12 +132,15 @@ enum rtmutex_chainwalk { /* * PI-futex support (proxy locking functions, etc.): */ +#define PI_WAKEUP_INPROGRESS ((struct rt_mutex_waiter *) 1) +#define PI_REQUEUE_INPROGRESS ((struct rt_mutex_waiter *) 2) + extern struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock); extern void rt_mutex_init_proxy_locked(struct rt_mutex *lock, struct task_struct *proxy_owner); extern void rt_mutex_proxy_unlock(struct rt_mutex *lock, struct task_struct *proxy_owner); -extern void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter); +extern void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter, bool savetate); extern int __rt_mutex_start_proxy_lock(struct rt_mutex *lock, struct rt_mutex_waiter *waiter, struct task_struct *task); @@ -153,9 +158,27 @@ extern int __rt_mutex_futex_trylock(struct rt_mutex *l); extern void rt_mutex_futex_unlock(struct rt_mutex *lock); extern bool __rt_mutex_futex_unlock(struct rt_mutex *lock, - struct wake_q_head *wqh); - -extern void rt_mutex_postunlock(struct wake_q_head *wake_q); + struct wake_q_head *wqh, + struct wake_q_head *wq_sleeper); + +extern void rt_mutex_postunlock(struct wake_q_head *wake_q, + struct wake_q_head *wake_sleeper_q); + +/* RW semaphore special interface */ +struct ww_acquire_ctx; + +extern int __rt_mutex_lock_state(struct rt_mutex *lock, int state); +extern int __rt_mutex_trylock(struct rt_mutex *lock); +extern void __rt_mutex_unlock(struct rt_mutex *lock); +int __sched rt_mutex_slowlock_locked(struct rt_mutex *lock, int state, + struct hrtimer_sleeper *timeout, + enum rtmutex_chainwalk chwalk, + struct ww_acquire_ctx *ww_ctx, + struct rt_mutex_waiter *waiter); +void __sched rt_spin_lock_slowlock_locked(struct rt_mutex *lock, + struct rt_mutex_waiter *waiter, + unsigned long flags); +void __sched rt_spin_lock_slowunlock(struct rt_mutex *lock); #ifdef CONFIG_DEBUG_RT_MUTEXES # include "rtmutex-debug.h" diff --git a/kernel/locking/rwlock-rt.c b/kernel/locking/rwlock-rt.c new file mode 100644 index 000000000000..f2e155b2c4a8 --- /dev/null +++ b/kernel/locking/rwlock-rt.c @@ -0,0 +1,378 @@ +/* + */ +#include <linux/sched/debug.h> +#include <linux/export.h> + +#include "rtmutex_common.h" +#include <linux/rwlock_types_rt.h> + +/* + * RT-specific reader/writer locks + * + * write_lock() + * 1) Lock lock->rtmutex + * 2) Remove the reader BIAS to force readers into the slow path + * 3) Wait until all readers have left the critical region + * 4) Mark it write locked + * + * write_unlock() + * 1) Remove the write locked marker + * 2) Set the reader BIAS so readers can use the fast path again + * 3) Unlock lock->rtmutex to release blocked readers + * + * read_lock() + * 1) Try fast path acquisition (reader BIAS is set) + * 2) Take lock->rtmutex.wait_lock which protects the writelocked flag + * 3) If !writelocked, acquire it for read + * 4) If writelocked, block on lock->rtmutex + * 5) unlock lock->rtmutex, goto 1) + * + * read_unlock() + * 1) Try fast path release (reader count != 1) + * 2) Wake the writer waiting in write_lock()#3 + * + * read_lock()#3 has the consequence, that rw locks on RT are not writer + * fair, but writers, which should be avoided in RT tasks (think tasklist + * lock), are subject to the rtmutex priority/DL inheritance mechanism. + * + * It's possible to make the rw locks writer fair by keeping a list of + * active readers. A blocked writer would force all newly incoming readers + * to block on the rtmutex, but the rtmutex would have to be proxy locked + * for one reader after the other. We can't use multi-reader inheritance + * because there is no way to support that with + * SCHED_DEADLINE. Implementing the one by one reader boosting/handover + * mechanism is a major surgery for a very dubious value. + * + * The risk of writer starvation is there, but the pathological use cases + * which trigger it are not necessarily the typical RT workloads. + */ + +void __rwlock_biased_rt_init(struct rt_rw_lock *lock, const char *name, + struct lock_class_key *key) +{ +#ifdef CONFIG_DEBUG_LOCK_ALLOC + /* + * Make sure we are not reinitializing a held semaphore: + */ + debug_check_no_locks_freed((void *)lock, sizeof(*lock)); + lockdep_init_map(&lock->dep_map, name, key, 0); +#endif + atomic_set(&lock->readers, READER_BIAS); + rt_mutex_init(&lock->rtmutex); + lock->rtmutex.save_state = 1; +} + +int __read_rt_trylock(struct rt_rw_lock *lock) +{ + int r, old; + + /* + * Increment reader count, if lock->readers < 0, i.e. READER_BIAS is + * set. + */ + for (r = atomic_read(&lock->readers); r < 0;) { + old = atomic_cmpxchg(&lock->readers, r, r + 1); + if (likely(old == r)) + return 1; + r = old; + } + return 0; +} + +void __sched __read_rt_lock(struct rt_rw_lock *lock) +{ + struct rt_mutex *m = &lock->rtmutex; + struct rt_mutex_waiter waiter; + unsigned long flags; + + if (__read_rt_trylock(lock)) + return; + + raw_spin_lock_irqsave(&m->wait_lock, flags); + /* + * Allow readers as long as the writer has not completely + * acquired the semaphore for write. + */ + if (atomic_read(&lock->readers) != WRITER_BIAS) { + atomic_inc(&lock->readers); + raw_spin_unlock_irqrestore(&m->wait_lock, flags); + return; + } + + /* + * Call into the slow lock path with the rtmutex->wait_lock + * held, so this can't result in the following race: + * + * Reader1 Reader2 Writer + * read_lock() + * write_lock() + * rtmutex_lock(m) + * swait() + * read_lock() + * unlock(m->wait_lock) + * read_unlock() + * swake() + * lock(m->wait_lock) + * lock->writelocked=true + * unlock(m->wait_lock) + * + * write_unlock() + * lock->writelocked=false + * rtmutex_unlock(m) + * read_lock() + * write_lock() + * rtmutex_lock(m) + * swait() + * rtmutex_lock(m) + * + * That would put Reader1 behind the writer waiting on + * Reader2 to call read_unlock() which might be unbound. + */ + rt_mutex_init_waiter(&waiter, false); + rt_spin_lock_slowlock_locked(m, &waiter, flags); + /* + * The slowlock() above is guaranteed to return with the rtmutex is + * now held, so there can't be a writer active. Increment the reader + * count and immediately drop the rtmutex again. + */ + atomic_inc(&lock->readers); + raw_spin_unlock_irqrestore(&m->wait_lock, flags); + rt_spin_lock_slowunlock(m); + + debug_rt_mutex_free_waiter(&waiter); +} + +void __read_rt_unlock(struct rt_rw_lock *lock) +{ + struct rt_mutex *m = &lock->rtmutex; + struct task_struct *tsk; + + /* + * sem->readers can only hit 0 when a writer is waiting for the + * active readers to leave the critical region. + */ + if (!atomic_dec_and_test(&lock->readers)) + return; + + raw_spin_lock_irq(&m->wait_lock); + /* + * Wake the writer, i.e. the rtmutex owner. It might release the + * rtmutex concurrently in the fast path, but to clean up the rw + * lock it needs to acquire m->wait_lock. The worst case which can + * happen is a spurious wakeup. + */ + tsk = rt_mutex_owner(m); + if (tsk) + wake_up_process(tsk); + + raw_spin_unlock_irq(&m->wait_lock); +} + +static void __write_unlock_common(struct rt_rw_lock *lock, int bias, + unsigned long flags) +{ + struct rt_mutex *m = &lock->rtmutex; + + atomic_add(READER_BIAS - bias, &lock->readers); + raw_spin_unlock_irqrestore(&m->wait_lock, flags); + rt_spin_lock_slowunlock(m); +} + +void __sched __write_rt_lock(struct rt_rw_lock *lock) +{ + struct rt_mutex *m = &lock->rtmutex; + struct task_struct *self = current; + unsigned long flags; + + /* Take the rtmutex as a first step */ + __rt_spin_lock(m); + + /* Force readers into slow path */ + atomic_sub(READER_BIAS, &lock->readers); + + raw_spin_lock_irqsave(&m->wait_lock, flags); + + raw_spin_lock(&self->pi_lock); + self->saved_state = self->state; + __set_current_state_no_track(TASK_UNINTERRUPTIBLE); + raw_spin_unlock(&self->pi_lock); + + for (;;) { + /* Have all readers left the critical region? */ + if (!atomic_read(&lock->readers)) { + atomic_set(&lock->readers, WRITER_BIAS); + raw_spin_lock(&self->pi_lock); + __set_current_state_no_track(self->saved_state); + self->saved_state = TASK_RUNNING; + raw_spin_unlock(&self->pi_lock); + raw_spin_unlock_irqrestore(&m->wait_lock, flags); + return; + } + + raw_spin_unlock_irqrestore(&m->wait_lock, flags); + + if (atomic_read(&lock->readers) != 0) + schedule(); + + raw_spin_lock_irqsave(&m->wait_lock, flags); + + raw_spin_lock(&self->pi_lock); + __set_current_state_no_track(TASK_UNINTERRUPTIBLE); + raw_spin_unlock(&self->pi_lock); + } +} + +int __write_rt_trylock(struct rt_rw_lock *lock) +{ + struct rt_mutex *m = &lock->rtmutex; + unsigned long flags; + + if (!__rt_mutex_trylock(m)) + return 0; + + atomic_sub(READER_BIAS, &lock->readers); + + raw_spin_lock_irqsave(&m->wait_lock, flags); + if (!atomic_read(&lock->readers)) { + atomic_set(&lock->readers, WRITER_BIAS); + raw_spin_unlock_irqrestore(&m->wait_lock, flags); + return 1; + } + __write_unlock_common(lock, 0, flags); + return 0; +} + +void __write_rt_unlock(struct rt_rw_lock *lock) +{ + struct rt_mutex *m = &lock->rtmutex; + unsigned long flags; + + raw_spin_lock_irqsave(&m->wait_lock, flags); + __write_unlock_common(lock, WRITER_BIAS, flags); +} + +/* Map the reader biased implementation */ +static inline int do_read_rt_trylock(rwlock_t *rwlock) +{ + return __read_rt_trylock(rwlock); +} + +static inline int do_write_rt_trylock(rwlock_t *rwlock) +{ + return __write_rt_trylock(rwlock); +} + +static inline void do_read_rt_lock(rwlock_t *rwlock) +{ + __read_rt_lock(rwlock); +} + +static inline void do_write_rt_lock(rwlock_t *rwlock) +{ + __write_rt_lock(rwlock); +} + +static inline void do_read_rt_unlock(rwlock_t *rwlock) +{ + __read_rt_unlock(rwlock); +} + +static inline void do_write_rt_unlock(rwlock_t *rwlock) +{ + __write_rt_unlock(rwlock); +} + +static inline void do_rwlock_rt_init(rwlock_t *rwlock, const char *name, + struct lock_class_key *key) +{ + __rwlock_biased_rt_init(rwlock, name, key); +} + +int __lockfunc rt_read_can_lock(rwlock_t *rwlock) +{ + return atomic_read(&rwlock->readers) < 0; +} + +int __lockfunc rt_write_can_lock(rwlock_t *rwlock) +{ + return atomic_read(&rwlock->readers) == READER_BIAS; +} + +/* + * The common functions which get wrapped into the rwlock API. + */ +int __lockfunc rt_read_trylock(rwlock_t *rwlock) +{ + int ret; + + sleeping_lock_inc(); + migrate_disable(); + ret = do_read_rt_trylock(rwlock); + if (ret) { + rwlock_acquire_read(&rwlock->dep_map, 0, 1, _RET_IP_); + } else { + migrate_enable(); + sleeping_lock_dec(); + } + return ret; +} +EXPORT_SYMBOL(rt_read_trylock); + +int __lockfunc rt_write_trylock(rwlock_t *rwlock) +{ + int ret; + + sleeping_lock_inc(); + migrate_disable(); + ret = do_write_rt_trylock(rwlock); + if (ret) { + rwlock_acquire(&rwlock->dep_map, 0, 1, _RET_IP_); + } else { + migrate_enable(); + sleeping_lock_dec(); + } + return ret; +} +EXPORT_SYMBOL(rt_write_trylock); + +void __lockfunc rt_read_lock(rwlock_t *rwlock) +{ + sleeping_lock_inc(); + migrate_disable(); + rwlock_acquire_read(&rwlock->dep_map, 0, 0, _RET_IP_); + do_read_rt_lock(rwlock); +} +EXPORT_SYMBOL(rt_read_lock); + +void __lockfunc rt_write_lock(rwlock_t *rwlock) +{ + sleeping_lock_inc(); + migrate_disable(); + rwlock_acquire(&rwlock->dep_map, 0, 0, _RET_IP_); + do_write_rt_lock(rwlock); +} +EXPORT_SYMBOL(rt_write_lock); + +void __lockfunc rt_read_unlock(rwlock_t *rwlock) +{ + rwlock_release(&rwlock->dep_map, 1, _RET_IP_); + do_read_rt_unlock(rwlock); + migrate_enable(); + sleeping_lock_dec(); +} +EXPORT_SYMBOL(rt_read_unlock); + +void __lockfunc rt_write_unlock(rwlock_t *rwlock) +{ + rwlock_release(&rwlock->dep_map, 1, _RET_IP_); + do_write_rt_unlock(rwlock); + migrate_enable(); + sleeping_lock_dec(); +} +EXPORT_SYMBOL(rt_write_unlock); + +void __rt_rwlock_init(rwlock_t *rwlock, char *name, struct lock_class_key *key) +{ + do_rwlock_rt_init(rwlock, name, key); +} +EXPORT_SYMBOL(__rt_rwlock_init); diff --git a/kernel/locking/rwsem-rt.c b/kernel/locking/rwsem-rt.c new file mode 100644 index 000000000000..660e22caf709 --- /dev/null +++ b/kernel/locking/rwsem-rt.c @@ -0,0 +1,293 @@ +/* + */ +#include <linux/rwsem.h> +#include <linux/sched/debug.h> +#include <linux/sched/signal.h> +#include <linux/export.h> + +#include "rtmutex_common.h" + +/* + * RT-specific reader/writer semaphores + * + * down_write() + * 1) Lock sem->rtmutex + * 2) Remove the reader BIAS to force readers into the slow path + * 3) Wait until all readers have left the critical region + * 4) Mark it write locked + * + * up_write() + * 1) Remove the write locked marker + * 2) Set the reader BIAS so readers can use the fast path again + * 3) Unlock sem->rtmutex to release blocked readers + * + * down_read() + * 1) Try fast path acquisition (reader BIAS is set) + * 2) Take sem->rtmutex.wait_lock which protects the writelocked flag + * 3) If !writelocked, acquire it for read + * 4) If writelocked, block on sem->rtmutex + * 5) unlock sem->rtmutex, goto 1) + * + * up_read() + * 1) Try fast path release (reader count != 1) + * 2) Wake the writer waiting in down_write()#3 + * + * down_read()#3 has the consequence, that rw semaphores on RT are not writer + * fair, but writers, which should be avoided in RT tasks (think mmap_sem), + * are subject to the rtmutex priority/DL inheritance mechanism. + * + * It's possible to make the rw semaphores writer fair by keeping a list of + * active readers. A blocked writer would force all newly incoming readers to + * block on the rtmutex, but the rtmutex would have to be proxy locked for one + * reader after the other. We can't use multi-reader inheritance because there + * is no way to support that with SCHED_DEADLINE. Implementing the one by one + * reader boosting/handover mechanism is a major surgery for a very dubious + * value. + * + * The risk of writer starvation is there, but the pathological use cases + * which trigger it are not necessarily the typical RT workloads. + */ + +void __rwsem_init(struct rw_semaphore *sem, const char *name, + struct lock_class_key *key) +{ +#ifdef CONFIG_DEBUG_LOCK_ALLOC + /* + * Make sure we are not reinitializing a held semaphore: + */ + debug_check_no_locks_freed((void *)sem, sizeof(*sem)); + lockdep_init_map(&sem->dep_map, name, key, 0); +#endif + atomic_set(&sem->readers, READER_BIAS); +} +EXPORT_SYMBOL(__rwsem_init); + +int __down_read_trylock(struct rw_semaphore *sem) +{ + int r, old; + + /* + * Increment reader count, if sem->readers < 0, i.e. READER_BIAS is + * set. + */ + for (r = atomic_read(&sem->readers); r < 0;) { + old = atomic_cmpxchg(&sem->readers, r, r + 1); + if (likely(old == r)) + return 1; + r = old; + } + return 0; +} + +static int __sched __down_read_common(struct rw_semaphore *sem, int state) +{ + struct rt_mutex *m = &sem->rtmutex; + struct rt_mutex_waiter waiter; + int ret; + + if (__down_read_trylock(sem)) + return 0; + + might_sleep(); + raw_spin_lock_irq(&m->wait_lock); + /* + * Allow readers as long as the writer has not completely + * acquired the semaphore for write. + */ + if (atomic_read(&sem->readers) != WRITER_BIAS) { + atomic_inc(&sem->readers); + raw_spin_unlock_irq(&m->wait_lock); + return 0; + } + + /* + * Call into the slow lock path with the rtmutex->wait_lock + * held, so this can't result in the following race: + * + * Reader1 Reader2 Writer + * down_read() + * down_write() + * rtmutex_lock(m) + * swait() + * down_read() + * unlock(m->wait_lock) + * up_read() + * swake() + * lock(m->wait_lock) + * sem->writelocked=true + * unlock(m->wait_lock) + * + * up_write() + * sem->writelocked=false + * rtmutex_unlock(m) + * down_read() + * down_write() + * rtmutex_lock(m) + * swait() + * rtmutex_lock(m) + * + * That would put Reader1 behind the writer waiting on + * Reader2 to call up_read() which might be unbound. + */ + rt_mutex_init_waiter(&waiter, false); + ret = rt_mutex_slowlock_locked(m, state, NULL, RT_MUTEX_MIN_CHAINWALK, + NULL, &waiter); + /* + * The slowlock() above is guaranteed to return with the rtmutex (for + * ret = 0) is now held, so there can't be a writer active. Increment + * the reader count and immediately drop the rtmutex again. + * For ret != 0 we don't hold the rtmutex and need unlock the wait_lock. + * We don't own the lock then. + */ + if (!ret) + atomic_inc(&sem->readers); + raw_spin_unlock_irq(&m->wait_lock); + if (!ret) + __rt_mutex_unlock(m); + + debug_rt_mutex_free_waiter(&waiter); + return ret; +} + +void __down_read(struct rw_semaphore *sem) +{ + int ret; + + ret = __down_read_common(sem, TASK_UNINTERRUPTIBLE); + WARN_ON_ONCE(ret); +} + +int __down_read_killable(struct rw_semaphore *sem) +{ + int ret; + + ret = __down_read_common(sem, TASK_KILLABLE); + if (likely(!ret)) + return ret; + WARN_ONCE(ret != -EINTR, "Unexpected state: %d\n", ret); + return -EINTR; +} + +void __up_read(struct rw_semaphore *sem) +{ + struct rt_mutex *m = &sem->rtmutex; + struct task_struct *tsk; + + /* + * sem->readers can only hit 0 when a writer is waiting for the + * active readers to leave the critical region. + */ + if (!atomic_dec_and_test(&sem->readers)) + return; + + might_sleep(); + raw_spin_lock_irq(&m->wait_lock); + /* + * Wake the writer, i.e. the rtmutex owner. It might release the + * rtmutex concurrently in the fast path (due to a signal), but to + * clean up the rwsem it needs to acquire m->wait_lock. The worst + * case which can happen is a spurious wakeup. + */ + tsk = rt_mutex_owner(m); + if (tsk) + wake_up_process(tsk); + + raw_spin_unlock_irq(&m->wait_lock); +} + +static void __up_write_unlock(struct rw_semaphore *sem, int bias, + unsigned long flags) +{ + struct rt_mutex *m = &sem->rtmutex; + + atomic_add(READER_BIAS - bias, &sem->readers); + raw_spin_unlock_irqrestore(&m->wait_lock, flags); + __rt_mutex_unlock(m); +} + +static int __sched __down_write_common(struct rw_semaphore *sem, int state) +{ + struct rt_mutex *m = &sem->rtmutex; + unsigned long flags; + + /* Take the rtmutex as a first step */ + if (__rt_mutex_lock_state(m, state)) + return -EINTR; + + /* Force readers into slow path */ + atomic_sub(READER_BIAS, &sem->readers); + might_sleep(); + + set_current_state(state); + for (;;) { + raw_spin_lock_irqsave(&m->wait_lock, flags); + /* Have all readers left the critical region? */ + if (!atomic_read(&sem->readers)) { + atomic_set(&sem->readers, WRITER_BIAS); + __set_current_state(TASK_RUNNING); + raw_spin_unlock_irqrestore(&m->wait_lock, flags); + return 0; + } + + if (signal_pending_state(state, current)) { + __set_current_state(TASK_RUNNING); + __up_write_unlock(sem, 0, flags); + return -EINTR; + } + raw_spin_unlock_irqrestore(&m->wait_lock, flags); + + if (atomic_read(&sem->readers) != 0) { + schedule(); + set_current_state(state); + } + } +} + +void __sched __down_write(struct rw_semaphore *sem) +{ + __down_write_common(sem, TASK_UNINTERRUPTIBLE); +} + +int __sched __down_write_killable(struct rw_semaphore *sem) +{ + return __down_write_common(sem, TASK_KILLABLE); +} + +int __down_write_trylock(struct rw_semaphore *sem) +{ + struct rt_mutex *m = &sem->rtmutex; + unsigned long flags; + + if (!__rt_mutex_trylock(m)) + return 0; + + atomic_sub(READER_BIAS, &sem->readers); + + raw_spin_lock_irqsave(&m->wait_lock, flags); + if (!atomic_read(&sem->readers)) { + atomic_set(&sem->readers, WRITER_BIAS); + raw_spin_unlock_irqrestore(&m->wait_lock, flags); + return 1; + } + __up_write_unlock(sem, 0, flags); + return 0; +} + +void __up_write(struct rw_semaphore *sem) +{ + struct rt_mutex *m = &sem->rtmutex; + unsigned long flags; + + raw_spin_lock_irqsave(&m->wait_lock, flags); + __up_write_unlock(sem, WRITER_BIAS, flags); +} + +void __downgrade_write(struct rw_semaphore *sem) +{ + struct rt_mutex *m = &sem->rtmutex; + unsigned long flags; + + raw_spin_lock_irqsave(&m->wait_lock, flags); + /* Release it and account current as reader */ + __up_write_unlock(sem, WRITER_BIAS - 1, flags); +} diff --git a/kernel/locking/spinlock.c b/kernel/locking/spinlock.c index 936f3d14dd6b..e89b70f474af 100644 --- a/kernel/locking/spinlock.c +++ b/kernel/locking/spinlock.c @@ -117,8 +117,11 @@ void __lockfunc __raw_##op##_lock_bh(locktype##_t *lock) \ * __[spin|read|write]_lock_bh() */ BUILD_LOCK_OPS(spin, raw_spinlock); + +#ifndef CONFIG_PREEMPT_RT_FULL BUILD_LOCK_OPS(read, rwlock); BUILD_LOCK_OPS(write, rwlock); +#endif #endif @@ -202,6 +205,8 @@ void __lockfunc _raw_spin_unlock_bh(raw_spinlock_t *lock) EXPORT_SYMBOL(_raw_spin_unlock_bh); #endif +#ifndef CONFIG_PREEMPT_RT_FULL + #ifndef CONFIG_INLINE_READ_TRYLOCK int __lockfunc _raw_read_trylock(rwlock_t *lock) { @@ -346,6 +351,8 @@ void __lockfunc _raw_write_unlock_bh(rwlock_t *lock) EXPORT_SYMBOL(_raw_write_unlock_bh); #endif +#endif /* !PREEMPT_RT_FULL */ + #ifdef CONFIG_DEBUG_LOCK_ALLOC void __lockfunc _raw_spin_lock_nested(raw_spinlock_t *lock, int subclass) diff --git a/kernel/locking/spinlock_debug.c b/kernel/locking/spinlock_debug.c index 9aa0fccd5d43..76d0b40d9193 100644 --- a/kernel/locking/spinlock_debug.c +++ b/kernel/locking/spinlock_debug.c @@ -31,6 +31,7 @@ void __raw_spin_lock_init(raw_spinlock_t *lock, const char *name, EXPORT_SYMBOL(__raw_spin_lock_init); +#ifndef CONFIG_PREEMPT_RT_FULL void __rwlock_init(rwlock_t *lock, const char *name, struct lock_class_key *key) { @@ -48,6 +49,7 @@ void __rwlock_init(rwlock_t *lock, const char *name, } EXPORT_SYMBOL(__rwlock_init); +#endif static void spin_dump(raw_spinlock_t *lock, const char *msg) { @@ -135,6 +137,7 @@ void do_raw_spin_unlock(raw_spinlock_t *lock) arch_spin_unlock(&lock->raw_lock); } +#ifndef CONFIG_PREEMPT_RT_FULL static void rwlock_bug(rwlock_t *lock, const char *msg) { if (!debug_locks_off()) @@ -224,3 +227,5 @@ void do_raw_write_unlock(rwlock_t *lock) debug_write_unlock(lock); arch_write_unlock(&lock->raw_lock); } + +#endif diff --git a/kernel/panic.c b/kernel/panic.c index 6a6df23acd1a..8f0a896e8428 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -479,9 +479,11 @@ static u64 oops_id; static int init_oops_id(void) { +#ifndef CONFIG_PREEMPT_RT_FULL if (!oops_id) get_random_bytes(&oops_id, sizeof(oops_id)); else +#endif oops_id++; return 0; diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index 9c85c7822383..991e3559781d 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -679,6 +679,10 @@ static int load_image_and_restore(void) return error; } +#ifndef CONFIG_SUSPEND +bool pm_in_action; +#endif + /** * hibernate - Carry out system hibernation, including saving the image. */ @@ -692,6 +696,8 @@ int hibernate(void) return -EPERM; } + pm_in_action = true; + lock_system_sleep(); /* The snapshot device should not be opened while we're running */ if (!atomic_add_unless(&snapshot_device_available, -1, 0)) { @@ -770,6 +776,7 @@ int hibernate(void) atomic_inc(&snapshot_device_available); Unlock: unlock_system_sleep(); + pm_in_action = false; pr_info("hibernation exit\n"); return error; diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 87331565e505..d2a84cd8291c 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -594,6 +594,8 @@ static int enter_state(suspend_state_t state) return error; } +bool pm_in_action; + /** * pm_suspend - Externally visible function for suspending the system. * @state: System sleep state to enter. @@ -608,6 +610,7 @@ int pm_suspend(suspend_state_t state) if (state <= PM_SUSPEND_ON || state >= PM_SUSPEND_MAX) return -EINVAL; + pm_in_action = true; pr_info("suspend entry (%s)\n", mem_sleep_labels[state]); error = enter_state(state); if (error) { @@ -617,6 +620,7 @@ int pm_suspend(suspend_state_t state) suspend_stats.success++; } pr_info("suspend exit\n"); + pm_in_action = false; return error; } EXPORT_SYMBOL(pm_suspend); diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 72de8cc5a13e..1c3c086bc36c 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -404,6 +404,65 @@ DEFINE_RAW_SPINLOCK(logbuf_lock); printk_safe_exit_irqrestore(flags); \ } while (0) +#ifdef CONFIG_EARLY_PRINTK +struct console *early_console; + +static void early_vprintk(const char *fmt, va_list ap) +{ + if (early_console) { + char buf[512]; + int n = vscnprintf(buf, sizeof(buf), fmt, ap); + + early_console->write(early_console, buf, n); + } +} + +asmlinkage void early_printk(const char *fmt, ...) +{ + va_list ap; + + va_start(ap, fmt); + early_vprintk(fmt, ap); + va_end(ap); +} + +/* + * This is independent of any log levels - a global + * kill switch that turns off all of printk. + * + * Used by the NMI watchdog if early-printk is enabled. + */ +static bool __read_mostly printk_killswitch; + +static int __init force_early_printk_setup(char *str) +{ + printk_killswitch = true; + return 0; +} +early_param("force_early_printk", force_early_printk_setup); + +void printk_kill(void) +{ + printk_killswitch = true; +} + +#ifdef CONFIG_PRINTK +static int forced_early_printk(const char *fmt, va_list ap) +{ + if (!printk_killswitch) + return 0; + early_vprintk(fmt, ap); + return 1; +} +#endif + +#else +static inline int forced_early_printk(const char *fmt, va_list ap) +{ + return 0; +} +#endif + #ifdef CONFIG_PRINTK DECLARE_WAIT_QUEUE_HEAD(log_wait); /* the next printk record to read by syslog(READ) or /proc/kmsg */ @@ -1357,6 +1416,8 @@ static int syslog_print_all(char __user *buf, int size, bool clear) { char *text; int len = 0; + int attempts = 0; + int num_msg; text = kmalloc(LOG_LINE_MAX + PREFIX_MAX, GFP_KERNEL); if (!text) @@ -1368,6 +1429,14 @@ static int syslog_print_all(char __user *buf, int size, bool clear) u64 seq; u32 idx; +try_again: + attempts++; + if (attempts > 10) { + len = -EBUSY; + goto out; + } + num_msg = 0; + /* * Find first record that fits, including all following records, * into the user-provided buffer for this dump. @@ -1380,6 +1449,14 @@ static int syslog_print_all(char __user *buf, int size, bool clear) len += msg_print_text(msg, true, NULL, 0); idx = log_next(idx); seq++; + num_msg++; + if (num_msg > 5) { + num_msg = 0; + logbuf_unlock_irq(); + logbuf_lock_irq(); + if (clear_seq < log_first_seq) + goto try_again; + } } /* move first record forward until length fits into the buffer */ @@ -1391,6 +1468,14 @@ static int syslog_print_all(char __user *buf, int size, bool clear) len -= msg_print_text(msg, true, NULL, 0); idx = log_next(idx); seq++; + num_msg++; + if (num_msg > 5) { + num_msg = 0; + logbuf_unlock_irq(); + logbuf_lock_irq(); + if (clear_seq < log_first_seq) + goto try_again; + } } /* last message fitting into this dump */ @@ -1429,6 +1514,7 @@ static int syslog_print_all(char __user *buf, int size, bool clear) clear_seq = log_next_seq; clear_idx = log_next_idx; } +out: logbuf_unlock_irq(); kfree(text); @@ -1552,6 +1638,7 @@ SYSCALL_DEFINE3(syslog, int, type, char __user *, buf, int, len) return do_syslog(type, buf, len, SYSLOG_FROM_READER); } +#ifndef CONFIG_PREEMPT_RT_FULL /* * Special console_lock variants that help to reduce the risk of soft-lockups. * They allow to pass console_lock to another printk() call using a busy wait. @@ -1692,6 +1779,15 @@ static int console_trylock_spinning(void) return 1; } +#else + +static int console_trylock_spinning(void) +{ + return console_trylock(); +} + +#endif + /* * Call the console drivers, asking them to write out * log_buf[start] to log_buf[end - 1]. @@ -1707,6 +1803,12 @@ static void call_console_drivers(const char *ext_text, size_t ext_len, if (!console_drivers) return; + if (IS_ENABLED(CONFIG_PREEMPT_RT_BASE)) { + if (in_irq() || in_nmi()) + return; + } + + migrate_disable(); for_each_console(con) { if (exclusive_console && con != exclusive_console) continue; @@ -1722,6 +1824,7 @@ static void call_console_drivers(const char *ext_text, size_t ext_len, else con->write(con, text, len); } + migrate_enable(); } int printk_delay_msec __read_mostly; @@ -1891,6 +1994,13 @@ asmlinkage int vprintk_emit(int facility, int level, bool in_sched = false; unsigned long flags; + /* + * Fall back to early_printk if a debugging subsystem has + * killed printk output + */ + if (unlikely(forced_early_printk(fmt, args))) + return 1; + if (level == LOGLEVEL_SCHED) { level = LOGLEVEL_DEFAULT; in_sched = true; @@ -1906,20 +2016,30 @@ asmlinkage int vprintk_emit(int facility, int level, /* If called from the scheduler, we can not call up(). */ if (!in_sched) { + int may_trylock = 1; + +#ifdef CONFIG_PREEMPT_RT_FULL + /* + * we can't take a sleeping lock with IRQs or preeption disabled + * so we can't print in these contexts + */ + if (!(preempt_count() == 0 && !irqs_disabled())) + may_trylock = 0; +#endif /* * Disable preemption to avoid being preempted while holding * console_sem which would prevent anyone from printing to * console */ - preempt_disable(); + migrate_disable(); /* * Try to acquire and then immediately release the console * semaphore. The release will print out buffers and wake up * /dev/kmsg and syslog() users. */ - if (console_trylock_spinning()) + if (may_trylock && console_trylock_spinning()) console_unlock(); - preempt_enable(); + migrate_enable(); } wake_up_klogd(); @@ -2031,26 +2151,6 @@ static bool suppress_message_printing(int level) { return false; } #endif /* CONFIG_PRINTK */ -#ifdef CONFIG_EARLY_PRINTK -struct console *early_console; - -asmlinkage __visible void early_printk(const char *fmt, ...) -{ - va_list ap; - char buf[512]; - int n; - - if (!early_console) - return; - - va_start(ap, fmt); - n = vscnprintf(buf, sizeof(buf), fmt, ap); - va_end(ap); - - early_console->write(early_console, buf, n); -} -#endif - static int __add_preferred_console(char *name, int idx, char *options, char *brl_options) { @@ -2391,6 +2491,10 @@ skip: console_seq++; raw_spin_unlock(&logbuf_lock); +#ifdef CONFIG_PREEMPT_RT_FULL + printk_safe_exit_irqrestore(flags); + call_console_drivers(ext_text, ext_len, text, len); +#else /* * While actively printing out messages, if another printk() * were to occur on another CPU, it may wait for this one to @@ -2409,6 +2513,7 @@ skip: } printk_safe_exit_irqrestore(flags); +#endif if (do_cond_resched) cond_resched(); @@ -2460,6 +2565,11 @@ void console_unblank(void) { struct console *c; + if (IS_ENABLED(CONFIG_PREEMPT_RT_BASE)) { + if (in_irq() || in_nmi()) + return; + } + /* * console_unblank can no longer be called in interrupt context unless * oops_in_progress is set to 1.. diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 5d0838c2349e..233aedb39a57 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -176,7 +176,14 @@ static bool ptrace_freeze_traced(struct task_struct *task) spin_lock_irq(&task->sighand->siglock); if (task_is_traced(task) && !__fatal_signal_pending(task)) { - task->state = __TASK_TRACED; + unsigned long flags; + + raw_spin_lock_irqsave(&task->pi_lock, flags); + if (task->state & __TASK_TRACED) + task->state = __TASK_TRACED; + else + task->saved_state = __TASK_TRACED; + raw_spin_unlock_irqrestore(&task->pi_lock, flags); ret = true; } spin_unlock_irq(&task->sighand->siglock); diff --git a/kernel/rcu/Kconfig b/kernel/rcu/Kconfig index 9210379c0353..0be2c96fb640 100644 --- a/kernel/rcu/Kconfig +++ b/kernel/rcu/Kconfig @@ -36,7 +36,7 @@ config TINY_RCU config RCU_EXPERT bool "Make expert-level adjustments to RCU configuration" - default n + default y if PREEMPT_RT_FULL help This option needs to be enabled if you wish to make expert-level adjustments to RCU configuration. By default, @@ -172,7 +172,7 @@ config RCU_FANOUT_LEAF config RCU_FAST_NO_HZ bool "Accelerate last non-dyntick-idle CPU's grace periods" - depends on NO_HZ_COMMON && SMP && RCU_EXPERT + depends on NO_HZ_COMMON && SMP && RCU_EXPERT && !PREEMPT_RT_FULL default n help This option permits CPUs to enter dynticks-idle state even if @@ -191,7 +191,7 @@ config RCU_FAST_NO_HZ config RCU_BOOST bool "Enable RCU priority boosting" depends on RT_MUTEXES && PREEMPT_RCU && RCU_EXPERT - default n + default y if PREEMPT_RT_FULL help This option boosts the priority of preempted RCU readers that block the current preemptible RCU grace period for too long. diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h index 40cea6735c2d..ba935f0c0c76 100644 --- a/kernel/rcu/rcu.h +++ b/kernel/rcu/rcu.h @@ -478,20 +478,28 @@ static inline void show_rcu_gp_kthreads(void) { } extern unsigned long rcutorture_testseq; extern unsigned long rcutorture_vernum; unsigned long rcu_batches_started(void); -unsigned long rcu_batches_started_bh(void); unsigned long rcu_batches_started_sched(void); unsigned long rcu_batches_completed(void); -unsigned long rcu_batches_completed_bh(void); unsigned long rcu_batches_completed_sched(void); unsigned long rcu_exp_batches_completed(void); unsigned long rcu_exp_batches_completed_sched(void); unsigned long srcu_batches_completed(struct srcu_struct *sp); void show_rcu_gp_kthreads(void); void rcu_force_quiescent_state(void); -void rcu_bh_force_quiescent_state(void); void rcu_sched_force_quiescent_state(void); extern struct workqueue_struct *rcu_gp_wq; extern struct workqueue_struct *rcu_par_gp_wq; + +#ifndef CONFIG_PREEMPT_RT_FULL +void rcu_bh_force_quiescent_state(void); +unsigned long rcu_batches_started_bh(void); +unsigned long rcu_batches_completed_bh(void); +#else +# define rcu_bh_force_quiescent_state rcu_force_quiescent_state +# define rcu_batches_completed_bh rcu_batches_completed +# define rcu_batches_started_bh rcu_batches_completed +#endif + #endif /* #else #ifdef CONFIG_TINY_RCU */ #ifdef CONFIG_RCU_NOCB_CPU diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index 0910baea3cbc..52cc4dff5352 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -413,6 +413,7 @@ static struct rcu_torture_ops rcu_ops = { .name = "rcu" }; +#ifndef CONFIG_PREEMPT_RT_FULL /* * Definitions for rcu_bh torture testing. */ @@ -452,6 +453,12 @@ static struct rcu_torture_ops rcu_bh_ops = { .name = "rcu_bh" }; +#else +static struct rcu_torture_ops rcu_bh_ops = { + .ttype = INVALID_RCU_FLAVOR, +}; +#endif + /* * Don't even think about trying any of these in real life!!! * The names includes "busted", and they really means it! diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c index bd0fad13e6a9..b5ce6e46d1d0 100644 --- a/kernel/rcu/srcutree.c +++ b/kernel/rcu/srcutree.c @@ -36,6 +36,8 @@ #include <linux/delay.h> #include <linux/module.h> #include <linux/srcu.h> +#include <linux/cpu.h> +#include <linux/locallock.h> #include "rcu.h" #include "rcu_segcblist.h" @@ -458,21 +460,6 @@ static void srcu_gp_start(struct srcu_struct *sp) } /* - * Track online CPUs to guide callback workqueue placement. - */ -DEFINE_PER_CPU(bool, srcu_online); - -void srcu_online_cpu(unsigned int cpu) -{ - WRITE_ONCE(per_cpu(srcu_online, cpu), true); -} - -void srcu_offline_cpu(unsigned int cpu) -{ - WRITE_ONCE(per_cpu(srcu_online, cpu), false); -} - -/* * Place the workqueue handler on the specified CPU if online, otherwise * just run it whereever. This is useful for placing workqueue handlers * that are to invoke the specified CPU's callbacks. @@ -483,12 +470,12 @@ static bool srcu_queue_delayed_work_on(int cpu, struct workqueue_struct *wq, { bool ret; - preempt_disable(); - if (READ_ONCE(per_cpu(srcu_online, cpu))) + cpus_read_lock(); + if (cpu_online(cpu)) ret = queue_delayed_work_on(cpu, wq, dwork, delay); else ret = queue_delayed_work(wq, dwork, delay); - preempt_enable(); + cpus_read_unlock(); return ret; } @@ -768,6 +755,8 @@ static void srcu_flip(struct srcu_struct *sp) * negligible when amoritized over that time period, and the extra latency * of a needlessly non-expedited grace period is similarly negligible. */ +static DEFINE_LOCAL_IRQ_LOCK(sp_llock); + static bool srcu_might_be_idle(struct srcu_struct *sp) { unsigned long curseq; @@ -776,13 +765,13 @@ static bool srcu_might_be_idle(struct srcu_struct *sp) unsigned long t; /* If the local srcu_data structure has callbacks, not idle. */ - local_irq_save(flags); + local_lock_irqsave(sp_llock, flags); sdp = this_cpu_ptr(sp->sda); if (rcu_segcblist_pend_cbs(&sdp->srcu_cblist)) { - local_irq_restore(flags); + local_unlock_irqrestore(sp_llock, flags); return false; /* Callbacks already present, so not idle. */ } - local_irq_restore(flags); + local_unlock_irqrestore(sp_llock, flags); /* * No local callbacks, so probabalistically probe global state. @@ -860,7 +849,7 @@ void __call_srcu(struct srcu_struct *sp, struct rcu_head *rhp, return; } rhp->func = func; - local_irq_save(flags); + local_lock_irqsave(sp_llock, flags); sdp = this_cpu_ptr(sp->sda); spin_lock_rcu_node(sdp); rcu_segcblist_enqueue(&sdp->srcu_cblist, rhp, false); @@ -876,7 +865,8 @@ void __call_srcu(struct srcu_struct *sp, struct rcu_head *rhp, sdp->srcu_gp_seq_needed_exp = s; needexp = true; } - spin_unlock_irqrestore_rcu_node(sdp, flags); + spin_unlock_rcu_node(sdp); + local_unlock_irqrestore(sp_llock, flags); if (needgp) srcu_funnel_gp_start(sp, sdp, s, do_norm); else if (needexp) diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 1d6bdfb10dbd..ec352808632e 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -58,6 +58,13 @@ #include <linux/trace_events.h> #include <linux/suspend.h> #include <linux/ftrace.h> +#include <linux/delay.h> +#include <linux/gfp.h> +#include <linux/oom.h> +#include <linux/smpboot.h> +#include <linux/jiffies.h> +#include <linux/sched/isolation.h> +#include "../time/tick-internal.h" #include "tree.h" #include "rcu.h" @@ -243,6 +250,19 @@ void rcu_sched_qs(void) this_cpu_ptr(&rcu_sched_data), true); } +#ifdef CONFIG_PREEMPT_RT_FULL +static void rcu_preempt_qs(void); + +void rcu_bh_qs(void) +{ + unsigned long flags; + + /* Callers to this function, rcu_preempt_qs(), must disable irqs. */ + local_irq_save(flags); + rcu_preempt_qs(); + local_irq_restore(flags); +} +#else void rcu_bh_qs(void) { RCU_LOCKDEP_WARN(preemptible(), "rcu_bh_qs() invoked with preemption enabled!!!"); @@ -253,6 +273,7 @@ void rcu_bh_qs(void) __this_cpu_write(rcu_bh_data.cpu_no_qs.b.norm, false); } } +#endif /* * Steal a bit from the bottom of ->dynticks for idle entry/exit @@ -549,11 +570,13 @@ EXPORT_SYMBOL_GPL(rcu_batches_started_sched); /* * Return the number of RCU BH batches started thus far for debug & stats. */ +#ifndef CONFIG_PREEMPT_RT_FULL unsigned long rcu_batches_started_bh(void) { return rcu_bh_state.gpnum; } EXPORT_SYMBOL_GPL(rcu_batches_started_bh); +#endif /* * Return the number of RCU batches completed thus far for debug & stats. @@ -573,6 +596,7 @@ unsigned long rcu_batches_completed_sched(void) } EXPORT_SYMBOL_GPL(rcu_batches_completed_sched); +#ifndef CONFIG_PREEMPT_RT_FULL /* * Return the number of RCU BH batches completed thus far for debug & stats. */ @@ -581,6 +605,7 @@ unsigned long rcu_batches_completed_bh(void) return rcu_bh_state.completed; } EXPORT_SYMBOL_GPL(rcu_batches_completed_bh); +#endif /* * Return the number of RCU expedited batches completed thus far for @@ -604,6 +629,7 @@ unsigned long rcu_exp_batches_completed_sched(void) } EXPORT_SYMBOL_GPL(rcu_exp_batches_completed_sched); +#ifndef CONFIG_PREEMPT_RT_FULL /* * Force a quiescent state. */ @@ -622,6 +648,13 @@ void rcu_bh_force_quiescent_state(void) } EXPORT_SYMBOL_GPL(rcu_bh_force_quiescent_state); +#else +void rcu_force_quiescent_state(void) +{ +} +EXPORT_SYMBOL_GPL(rcu_force_quiescent_state); +#endif + /* * Force a quiescent state for RCU-sched. */ @@ -672,9 +705,11 @@ void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags, case RCU_FLAVOR: rsp = rcu_state_p; break; +#ifndef CONFIG_PREEMPT_RT_FULL case RCU_BH_FLAVOR: rsp = &rcu_bh_state; break; +#endif case RCU_SCHED_FLAVOR: rsp = &rcu_sched_state; break; @@ -1259,6 +1294,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) !rdp->rcu_iw_pending && rdp->rcu_iw_gpnum != rnp->gpnum && (rnp->ffmask & rdp->grpmask)) { init_irq_work(&rdp->rcu_iw, rcu_iw_handler); + rdp->rcu_iw.flags = IRQ_WORK_HARD_IRQ; rdp->rcu_iw_pending = true; rdp->rcu_iw_gpnum = rnp->gpnum; irq_work_queue_on(&rdp->rcu_iw, rdp->cpu); @@ -2808,18 +2844,17 @@ __rcu_process_callbacks(struct rcu_state *rsp) /* * Do RCU core processing for the current CPU. */ -static __latent_entropy void rcu_process_callbacks(struct softirq_action *unused) +static __latent_entropy void rcu_process_callbacks(void) { struct rcu_state *rsp; if (cpu_is_offline(smp_processor_id())) return; - trace_rcu_utilization(TPS("Start RCU core")); for_each_rcu_flavor(rsp) __rcu_process_callbacks(rsp); - trace_rcu_utilization(TPS("End RCU core")); } +static DEFINE_PER_CPU(struct task_struct *, rcu_cpu_kthread_task); /* * Schedule RCU callback invocation. If the specified type of RCU * does not support RCU priority boosting, just do a direct call, @@ -2831,20 +2866,107 @@ static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp) { if (unlikely(!READ_ONCE(rcu_scheduler_fully_active))) return; - if (likely(!rsp->boost)) { - rcu_do_batch(rsp, rdp); - return; - } - invoke_rcu_callbacks_kthread(); + rcu_do_batch(rsp, rdp); } +static void rcu_wake_cond(struct task_struct *t, int status) +{ + /* + * If the thread is yielding, only wake it when this + * is invoked from idle + */ + if (t && (status != RCU_KTHREAD_YIELDING || is_idle_task(current))) + wake_up_process(t); +} + +/* + * Wake up this CPU's rcuc kthread to do RCU core processing. + */ static void invoke_rcu_core(void) { - if (cpu_online(smp_processor_id())) - raise_softirq(RCU_SOFTIRQ); + unsigned long flags; + struct task_struct *t; + + if (!cpu_online(smp_processor_id())) + return; + local_irq_save(flags); + __this_cpu_write(rcu_cpu_has_work, 1); + t = __this_cpu_read(rcu_cpu_kthread_task); + if (t != NULL && current != t) + rcu_wake_cond(t, __this_cpu_read(rcu_cpu_kthread_status)); + local_irq_restore(flags); +} + +static void rcu_cpu_kthread_park(unsigned int cpu) +{ + per_cpu(rcu_cpu_kthread_status, cpu) = RCU_KTHREAD_OFFCPU; +} + +static int rcu_cpu_kthread_should_run(unsigned int cpu) +{ + return __this_cpu_read(rcu_cpu_has_work); } /* + * Per-CPU kernel thread that invokes RCU callbacks. This replaces the + * RCU softirq used in flavors and configurations of RCU that do not + * support RCU priority boosting. + */ +static void rcu_cpu_kthread(unsigned int cpu) +{ + unsigned int *statusp = this_cpu_ptr(&rcu_cpu_kthread_status); + char work, *workp = this_cpu_ptr(&rcu_cpu_has_work); + int spincnt; + + for (spincnt = 0; spincnt < 10; spincnt++) { + trace_rcu_utilization(TPS("Start CPU kthread@rcu_wait")); + local_bh_disable(); + *statusp = RCU_KTHREAD_RUNNING; + this_cpu_inc(rcu_cpu_kthread_loops); + local_irq_disable(); + work = *workp; + *workp = 0; + local_irq_enable(); + if (work) + rcu_process_callbacks(); + local_bh_enable(); + if (*workp == 0) { + trace_rcu_utilization(TPS("End CPU kthread@rcu_wait")); + *statusp = RCU_KTHREAD_WAITING; + return; + } + } + *statusp = RCU_KTHREAD_YIELDING; + trace_rcu_utilization(TPS("Start CPU kthread@rcu_yield")); + schedule_timeout_interruptible(2); + trace_rcu_utilization(TPS("End CPU kthread@rcu_yield")); + *statusp = RCU_KTHREAD_WAITING; +} + +static struct smp_hotplug_thread rcu_cpu_thread_spec = { + .store = &rcu_cpu_kthread_task, + .thread_should_run = rcu_cpu_kthread_should_run, + .thread_fn = rcu_cpu_kthread, + .thread_comm = "rcuc/%u", + .setup = rcu_cpu_kthread_setup, + .park = rcu_cpu_kthread_park, +}; + +/* + * Spawn per-CPU RCU core processing kthreads. + */ +static int __init rcu_spawn_core_kthreads(void) +{ + int cpu; + + for_each_possible_cpu(cpu) + per_cpu(rcu_cpu_has_work, cpu) = 0; + BUG_ON(smpboot_register_percpu_thread(&rcu_cpu_thread_spec)); + return 0; +} +early_initcall(rcu_spawn_core_kthreads); + +/* * Handle any core-RCU processing required by a call_rcu() invocation. */ static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp, @@ -3003,6 +3125,7 @@ void call_rcu_sched(struct rcu_head *head, rcu_callback_t func) } EXPORT_SYMBOL_GPL(call_rcu_sched); +#ifndef CONFIG_PREEMPT_RT_FULL /** * call_rcu_bh() - Queue an RCU for invocation after a quicker grace period. * @head: structure to be used for queueing the RCU updates. @@ -3030,6 +3153,7 @@ void call_rcu_bh(struct rcu_head *head, rcu_callback_t func) __call_rcu(head, func, &rcu_bh_state, -1, 0); } EXPORT_SYMBOL_GPL(call_rcu_bh); +#endif /* * Queue an RCU callback for lazy invocation after a grace period. @@ -3115,6 +3239,7 @@ void synchronize_sched(void) } EXPORT_SYMBOL_GPL(synchronize_sched); +#ifndef CONFIG_PREEMPT_RT_FULL /** * synchronize_rcu_bh - wait until an rcu_bh grace period has elapsed. * @@ -3141,6 +3266,7 @@ void synchronize_rcu_bh(void) wait_rcu_gp(call_rcu_bh); } EXPORT_SYMBOL_GPL(synchronize_rcu_bh); +#endif /** * get_state_synchronize_rcu - Snapshot current RCU state @@ -3474,6 +3600,7 @@ static void _rcu_barrier(struct rcu_state *rsp) mutex_unlock(&rsp->barrier_mutex); } +#ifndef CONFIG_PREEMPT_RT_FULL /** * rcu_barrier_bh - Wait until all in-flight call_rcu_bh() callbacks complete. */ @@ -3482,6 +3609,7 @@ void rcu_barrier_bh(void) _rcu_barrier(&rcu_bh_state); } EXPORT_SYMBOL_GPL(rcu_barrier_bh); +#endif /** * rcu_barrier_sched - Wait for in-flight call_rcu_sched() callbacks. @@ -3622,8 +3750,6 @@ int rcutree_online_cpu(unsigned int cpu) rnp->ffmask |= rdp->grpmask; raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } - if (IS_ENABLED(CONFIG_TREE_SRCU)) - srcu_online_cpu(cpu); if (rcu_scheduler_active == RCU_SCHEDULER_INACTIVE) return 0; /* Too early in boot for scheduler work. */ sync_sched_exp_online_cleanup(cpu); @@ -3651,8 +3777,6 @@ int rcutree_offline_cpu(unsigned int cpu) } rcutree_affinity_setting(cpu, cpu); - if (IS_ENABLED(CONFIG_TREE_SRCU)) - srcu_offline_cpu(cpu); return 0; } @@ -4098,12 +4222,13 @@ void __init rcu_init(void) rcu_bootup_announce(); rcu_init_geometry(); +#ifndef CONFIG_PREEMPT_RT_FULL rcu_init_one(&rcu_bh_state); +#endif rcu_init_one(&rcu_sched_state); if (dump_tree) rcu_dump_rcu_node_tree(&rcu_sched_state); __rcu_init_preempt(); - open_softirq(RCU_SOFTIRQ, rcu_process_callbacks); /* * We don't need protection against CPU-hotplug here because diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 78e051dffc5b..a82c97dda043 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -422,7 +422,9 @@ extern struct list_head rcu_struct_flavors; */ extern struct rcu_state rcu_sched_state; +#ifndef CONFIG_PREEMPT_RT_FULL extern struct rcu_state rcu_bh_state; +#endif #ifdef CONFIG_PREEMPT_RCU extern struct rcu_state rcu_preempt_state; @@ -430,12 +432,10 @@ extern struct rcu_state rcu_preempt_state; int rcu_dynticks_snap(struct rcu_dynticks *rdtp); -#ifdef CONFIG_RCU_BOOST DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_status); DECLARE_PER_CPU(int, rcu_cpu_kthread_cpu); DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_loops); DECLARE_PER_CPU(char, rcu_cpu_has_work); -#endif /* #ifdef CONFIG_RCU_BOOST */ #ifndef RCU_TREE_NONCORE @@ -455,8 +455,8 @@ void call_rcu(struct rcu_head *head, rcu_callback_t func); static void __init __rcu_init_preempt(void); static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags); static void rcu_preempt_boost_start_gp(struct rcu_node *rnp); -static void invoke_rcu_callbacks_kthread(void); static bool rcu_is_callbacks_kthread(void); +static void rcu_cpu_kthread_setup(unsigned int cpu); #ifdef CONFIG_RCU_BOOST static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp, struct rcu_node *rnp); diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h index 01b6ddeb4f05..a104cf91e6b9 100644 --- a/kernel/rcu/tree_exp.h +++ b/kernel/rcu/tree_exp.h @@ -479,6 +479,7 @@ static void sync_rcu_exp_select_cpus(struct rcu_state *rsp, sync_exp_reset_tree(rsp); trace_rcu_exp_grace_period(rsp->name, rcu_exp_gp_seq_endval(rsp), TPS("select")); + cpus_read_lock(); /* Schedule work for each leaf rcu_node structure. */ rcu_for_each_leaf_node(rsp, rnp) { rnp->exp_need_flush = false; @@ -493,13 +494,11 @@ static void sync_rcu_exp_select_cpus(struct rcu_state *rsp, continue; } INIT_WORK(&rnp->rew.rew_work, sync_rcu_exp_select_node_cpus); - preempt_disable(); cpu = cpumask_next(rnp->grplo - 1, cpu_online_mask); /* If all offline, queue the work on an unbound CPU. */ if (unlikely(cpu > rnp->grphi)) cpu = WORK_CPU_UNBOUND; queue_work_on(cpu, rcu_par_gp_wq, &rnp->rew.rew_work); - preempt_enable(); rnp->exp_need_flush = true; } @@ -507,6 +506,7 @@ static void sync_rcu_exp_select_cpus(struct rcu_state *rsp, rcu_for_each_leaf_node(rsp, rnp) if (rnp->exp_need_flush) flush_work(&rnp->rew.rew_work); + cpus_read_unlock(); } static void synchronize_sched_expedited_wait(struct rcu_state *rsp) diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 7fd12039e512..4882cd3d2207 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -24,41 +24,16 @@ * Paul E. McKenney <paulmck@linux.vnet.ibm.com> */ -#include <linux/delay.h> -#include <linux/gfp.h> -#include <linux/oom.h> -#include <linux/sched/debug.h> -#include <linux/smpboot.h> -#include <linux/sched/isolation.h> -#include <uapi/linux/sched/types.h> -#include "../time/tick-internal.h" - -#ifdef CONFIG_RCU_BOOST - #include "../locking/rtmutex_common.h" /* * Control variables for per-CPU and per-rcu_node kthreads. These * handle all flavors of RCU. */ -static DEFINE_PER_CPU(struct task_struct *, rcu_cpu_kthread_task); DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_status); DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_loops); DEFINE_PER_CPU(char, rcu_cpu_has_work); -#else /* #ifdef CONFIG_RCU_BOOST */ - -/* - * Some architectures do not define rt_mutexes, but if !CONFIG_RCU_BOOST, - * all uses are in dead code. Provide a definition to keep the compiler - * happy, but add WARN_ON_ONCE() to complain if used in the wrong place. - * This probably needs to be excluded from -rt builds. - */ -#define rt_mutex_owner(a) ({ WARN_ON_ONCE(1); NULL; }) -#define rt_mutex_futex_unlock(x) WARN_ON_ONCE(1) - -#endif /* #else #ifdef CONFIG_RCU_BOOST */ - #ifdef CONFIG_RCU_NOCB_CPU static cpumask_var_t rcu_nocb_mask; /* CPUs to have callbacks offloaded. */ static bool __read_mostly rcu_nocb_poll; /* Offload kthread are to poll. */ @@ -325,9 +300,13 @@ static void rcu_preempt_note_context_switch(bool preempt) struct task_struct *t = current; struct rcu_data *rdp; struct rcu_node *rnp; + int sleeping_l = 0; lockdep_assert_irqs_disabled(); - WARN_ON_ONCE(!preempt && t->rcu_read_lock_nesting > 0); +#if defined(CONFIG_PREEMPT_RT_FULL) + sleeping_l = t->sleeping_lock; +#endif + WARN_ON_ONCE(!preempt && t->rcu_read_lock_nesting > 0 && !sleeping_l); if (t->rcu_read_lock_nesting > 0 && !t->rcu_read_unlock_special.b.blocked) { @@ -508,7 +487,7 @@ void rcu_read_unlock_special(struct task_struct *t) } /* Hardware IRQ handlers cannot block, complain if they get here. */ - if (in_irq() || in_serving_softirq()) { + if (preempt_count() & (HARDIRQ_MASK | SOFTIRQ_OFFSET)) { lockdep_rcu_suspicious(__FILE__, __LINE__, "rcu_read_unlock() from irq or softirq with blocking in critical section!!!\n"); pr_alert("->rcu_read_unlock_special: %#x (b: %d, enq: %d nq: %d)\n", @@ -951,18 +930,21 @@ void exit_rcu(void) #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ +/* + * If boosting, set rcuc kthreads to realtime priority. + */ +static void rcu_cpu_kthread_setup(unsigned int cpu) +{ #ifdef CONFIG_RCU_BOOST + struct sched_param sp; -static void rcu_wake_cond(struct task_struct *t, int status) -{ - /* - * If the thread is yielding, only wake it when this - * is invoked from idle - */ - if (status != RCU_KTHREAD_YIELDING || is_idle_task(current)) - wake_up_process(t); + sp.sched_priority = kthread_prio; + sched_setscheduler_nocheck(current, SCHED_FIFO, &sp); +#endif /* #ifdef CONFIG_RCU_BOOST */ } +#ifdef CONFIG_RCU_BOOST + /* * Carry out RCU priority boosting on the task indicated by ->exp_tasks * or ->boost_tasks, advancing the pointer to the next task in the @@ -1101,23 +1083,6 @@ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags) } /* - * Wake up the per-CPU kthread to invoke RCU callbacks. - */ -static void invoke_rcu_callbacks_kthread(void) -{ - unsigned long flags; - - local_irq_save(flags); - __this_cpu_write(rcu_cpu_has_work, 1); - if (__this_cpu_read(rcu_cpu_kthread_task) != NULL && - current != __this_cpu_read(rcu_cpu_kthread_task)) { - rcu_wake_cond(__this_cpu_read(rcu_cpu_kthread_task), - __this_cpu_read(rcu_cpu_kthread_status)); - } - local_irq_restore(flags); -} - -/* * Is the current CPU running the RCU-callbacks kthread? * Caller must have preemption disabled. */ @@ -1171,67 +1136,6 @@ static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp, return 0; } -static void rcu_kthread_do_work(void) -{ - rcu_do_batch(&rcu_sched_state, this_cpu_ptr(&rcu_sched_data)); - rcu_do_batch(&rcu_bh_state, this_cpu_ptr(&rcu_bh_data)); - rcu_do_batch(&rcu_preempt_state, this_cpu_ptr(&rcu_preempt_data)); -} - -static void rcu_cpu_kthread_setup(unsigned int cpu) -{ - struct sched_param sp; - - sp.sched_priority = kthread_prio; - sched_setscheduler_nocheck(current, SCHED_FIFO, &sp); -} - -static void rcu_cpu_kthread_park(unsigned int cpu) -{ - per_cpu(rcu_cpu_kthread_status, cpu) = RCU_KTHREAD_OFFCPU; -} - -static int rcu_cpu_kthread_should_run(unsigned int cpu) -{ - return __this_cpu_read(rcu_cpu_has_work); -} - -/* - * Per-CPU kernel thread that invokes RCU callbacks. This replaces the - * RCU softirq used in flavors and configurations of RCU that do not - * support RCU priority boosting. - */ -static void rcu_cpu_kthread(unsigned int cpu) -{ - unsigned int *statusp = this_cpu_ptr(&rcu_cpu_kthread_status); - char work, *workp = this_cpu_ptr(&rcu_cpu_has_work); - int spincnt; - - for (spincnt = 0; spincnt < 10; spincnt++) { - trace_rcu_utilization(TPS("Start CPU kthread@rcu_wait")); - local_bh_disable(); - *statusp = RCU_KTHREAD_RUNNING; - this_cpu_inc(rcu_cpu_kthread_loops); - local_irq_disable(); - work = *workp; - *workp = 0; - local_irq_enable(); - if (work) - rcu_kthread_do_work(); - local_bh_enable(); - if (*workp == 0) { - trace_rcu_utilization(TPS("End CPU kthread@rcu_wait")); - *statusp = RCU_KTHREAD_WAITING; - return; - } - } - *statusp = RCU_KTHREAD_YIELDING; - trace_rcu_utilization(TPS("Start CPU kthread@rcu_yield")); - schedule_timeout_interruptible(2); - trace_rcu_utilization(TPS("End CPU kthread@rcu_yield")); - *statusp = RCU_KTHREAD_WAITING; -} - /* * Set the per-rcu_node kthread's affinity to cover all CPUs that are * served by the rcu_node in question. The CPU hotplug lock is still @@ -1262,26 +1166,12 @@ static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu) free_cpumask_var(cm); } -static struct smp_hotplug_thread rcu_cpu_thread_spec = { - .store = &rcu_cpu_kthread_task, - .thread_should_run = rcu_cpu_kthread_should_run, - .thread_fn = rcu_cpu_kthread, - .thread_comm = "rcuc/%u", - .setup = rcu_cpu_kthread_setup, - .park = rcu_cpu_kthread_park, -}; - /* * Spawn boost kthreads -- called as soon as the scheduler is running. */ static void __init rcu_spawn_boost_kthreads(void) { struct rcu_node *rnp; - int cpu; - - for_each_possible_cpu(cpu) - per_cpu(rcu_cpu_has_work, cpu) = 0; - BUG_ON(smpboot_register_percpu_thread(&rcu_cpu_thread_spec)); rcu_for_each_leaf_node(rcu_state_p, rnp) (void)rcu_spawn_one_boost_kthread(rcu_state_p, rnp); } @@ -1304,11 +1194,6 @@ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags) raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } -static void invoke_rcu_callbacks_kthread(void) -{ - WARN_ON_ONCE(1); -} - static bool rcu_is_callbacks_kthread(void) { return false; @@ -1332,7 +1217,7 @@ static void rcu_prepare_kthreads(int cpu) #endif /* #else #ifdef CONFIG_RCU_BOOST */ -#if !defined(CONFIG_RCU_FAST_NO_HZ) +#if !defined(CONFIG_RCU_FAST_NO_HZ) || defined(CONFIG_PREEMPT_RT_FULL) /* * Check to see if any future RCU-related work will need to be done @@ -1348,7 +1233,9 @@ int rcu_needs_cpu(u64 basemono, u64 *nextevt) *nextevt = KTIME_MAX; return rcu_cpu_has_callbacks(NULL); } +#endif /* !defined(CONFIG_RCU_FAST_NO_HZ) || defined(CONFIG_PREEMPT_RT_FULL) */ +#if !defined(CONFIG_RCU_FAST_NO_HZ) /* * Because we do not have RCU_FAST_NO_HZ, don't bother cleaning up * after it. @@ -1444,6 +1331,8 @@ static bool __maybe_unused rcu_try_advance_all_cbs(void) return cbs_ready; } +#ifndef CONFIG_PREEMPT_RT_FULL + /* * Allow the CPU to enter dyntick-idle mode unless it has callbacks ready * to invoke. If the CPU has callbacks, try to advance them. Tell the @@ -1486,6 +1375,7 @@ int rcu_needs_cpu(u64 basemono, u64 *nextevt) *nextevt = basemono + dj * TICK_NSEC; return 0; } +#endif /* #ifndef CONFIG_PREEMPT_RT_FULL */ /* * Prepare a CPU for idle from an RCU perspective. The first major task diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index 5fa09ea3f23f..29cda5a6d4fd 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -68,7 +68,7 @@ extern int rcu_expedited; /* from sysctl */ module_param(rcu_expedited, int, 0); extern int rcu_normal; /* from sysctl */ module_param(rcu_normal, int, 0); -static int rcu_normal_after_boot; +static int rcu_normal_after_boot = IS_ENABLED(CONFIG_PREEMPT_RT_FULL); module_param(rcu_normal_after_boot, int, 0); #endif /* #ifndef CONFIG_TINY_RCU */ @@ -288,6 +288,7 @@ int rcu_read_lock_held(void) } EXPORT_SYMBOL_GPL(rcu_read_lock_held); +#ifndef CONFIG_PREEMPT_RT_FULL /** * rcu_read_lock_bh_held() - might we be in RCU-bh read-side critical section? * @@ -314,6 +315,7 @@ int rcu_read_lock_bh_held(void) return in_softirq() || irqs_disabled(); } EXPORT_SYMBOL_GPL(rcu_read_lock_bh_held); +#endif #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile index d9a02b318108..f66bb24cd96b 100644 --- a/kernel/sched/Makefile +++ b/kernel/sched/Makefile @@ -18,7 +18,7 @@ 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-y += wait.o wait_bit.o swait.o swork.o completion.o obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o topology.o stop_task.o obj-$(CONFIG_SCHED_AUTOGROUP) += autogroup.o diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c index e426b0cb9ac6..2e2a379ba47e 100644 --- a/kernel/sched/completion.c +++ b/kernel/sched/completion.c @@ -29,12 +29,12 @@ void complete(struct completion *x) { unsigned long flags; - spin_lock_irqsave(&x->wait.lock, flags); + raw_spin_lock_irqsave(&x->wait.lock, flags); if (x->done != UINT_MAX) x->done++; - __wake_up_locked(&x->wait, TASK_NORMAL, 1); - spin_unlock_irqrestore(&x->wait.lock, flags); + swake_up_locked(&x->wait); + raw_spin_unlock_irqrestore(&x->wait.lock, flags); } EXPORT_SYMBOL(complete); @@ -58,10 +58,10 @@ void complete_all(struct completion *x) { unsigned long flags; - spin_lock_irqsave(&x->wait.lock, flags); + raw_spin_lock_irqsave(&x->wait.lock, flags); x->done = UINT_MAX; - __wake_up_locked(&x->wait, TASK_NORMAL, 0); - spin_unlock_irqrestore(&x->wait.lock, flags); + swake_up_all_locked(&x->wait); + raw_spin_unlock_irqrestore(&x->wait.lock, flags); } EXPORT_SYMBOL(complete_all); @@ -70,20 +70,20 @@ do_wait_for_common(struct completion *x, long (*action)(long), long timeout, int state) { if (!x->done) { - DECLARE_WAITQUEUE(wait, current); + DECLARE_SWAITQUEUE(wait); - __add_wait_queue_entry_tail_exclusive(&x->wait, &wait); + __prepare_to_swait(&x->wait, &wait); do { if (signal_pending_state(state, current)) { timeout = -ERESTARTSYS; break; } __set_current_state(state); - spin_unlock_irq(&x->wait.lock); + raw_spin_unlock_irq(&x->wait.lock); timeout = action(timeout); - spin_lock_irq(&x->wait.lock); + raw_spin_lock_irq(&x->wait.lock); } while (!x->done && timeout); - __remove_wait_queue(&x->wait, &wait); + __finish_swait(&x->wait, &wait); if (!x->done) return timeout; } @@ -100,9 +100,9 @@ __wait_for_common(struct completion *x, complete_acquire(x); - spin_lock_irq(&x->wait.lock); + raw_spin_lock_irq(&x->wait.lock); timeout = do_wait_for_common(x, action, timeout, state); - spin_unlock_irq(&x->wait.lock); + raw_spin_unlock_irq(&x->wait.lock); complete_release(x); @@ -291,12 +291,12 @@ bool try_wait_for_completion(struct completion *x) if (!READ_ONCE(x->done)) return false; - spin_lock_irqsave(&x->wait.lock, flags); + raw_spin_lock_irqsave(&x->wait.lock, flags); if (!x->done) ret = false; else if (x->done != UINT_MAX) x->done--; - spin_unlock_irqrestore(&x->wait.lock, flags); + raw_spin_unlock_irqrestore(&x->wait.lock, flags); return ret; } EXPORT_SYMBOL(try_wait_for_completion); @@ -322,8 +322,8 @@ bool completion_done(struct completion *x) * otherwise we can end up freeing the completion before complete() * is done referencing it. */ - spin_lock_irqsave(&x->wait.lock, flags); - spin_unlock_irqrestore(&x->wait.lock, flags); + raw_spin_lock_irqsave(&x->wait.lock, flags); + raw_spin_unlock_irqrestore(&x->wait.lock, flags); return true; } EXPORT_SYMBOL(completion_done); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 2c5b222d4de6..e456326a9a0d 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -42,7 +42,11 @@ const_debug unsigned int sysctl_sched_features = * Number of tasks to iterate in a single balance run. * Limited because this is done with IRQs disabled. */ +#ifndef CONFIG_PREEMPT_RT_FULL const_debug unsigned int sysctl_sched_nr_migrate = 32; +#else +const_debug unsigned int sysctl_sched_nr_migrate = 8; +#endif /* * period over which we average the RT time consumption, measured @@ -322,7 +326,7 @@ static void hrtick_rq_init(struct rq *rq) rq->hrtick_csd.info = rq; #endif - hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD); rq->hrtick_timer.function = hrtick; } #else /* CONFIG_SCHED_HRTICK */ @@ -404,9 +408,15 @@ static bool set_nr_if_polling(struct task_struct *p) #endif #endif -void wake_q_add(struct wake_q_head *head, struct task_struct *task) +void __wake_q_add(struct wake_q_head *head, struct task_struct *task, + bool sleeper) { - struct wake_q_node *node = &task->wake_q; + struct wake_q_node *node; + + if (sleeper) + node = &task->wake_q_sleeper; + else + node = &task->wake_q; /* * Atomically grab the task, if ->wake_q is !nil already it means @@ -429,24 +439,32 @@ void wake_q_add(struct wake_q_head *head, struct task_struct *task) head->lastp = &node->next; } -void wake_up_q(struct wake_q_head *head) +void __wake_up_q(struct wake_q_head *head, bool sleeper) { struct wake_q_node *node = head->first; while (node != WAKE_Q_TAIL) { struct task_struct *task; - task = container_of(node, struct task_struct, wake_q); + if (sleeper) + task = container_of(node, struct task_struct, wake_q_sleeper); + else + task = container_of(node, struct task_struct, wake_q); BUG_ON(!task); /* Task can safely be re-inserted now: */ node = node->next; - task->wake_q.next = NULL; - + if (sleeper) + task->wake_q_sleeper.next = NULL; + else + task->wake_q.next = NULL; /* * wake_up_process() implies a wmb() to pair with the queueing * in wake_q_add() so as not to miss wakeups. */ - wake_up_process(task); + if (sleeper) + wake_up_lock_sleeper(task); + else + wake_up_process(task); put_task_struct(task); } } @@ -482,6 +500,48 @@ void resched_curr(struct rq *rq) trace_sched_wake_idle_without_ipi(cpu); } +#ifdef CONFIG_PREEMPT_LAZY + +static int tsk_is_polling(struct task_struct *p) +{ +#ifdef TIF_POLLING_NRFLAG + return test_tsk_thread_flag(p, TIF_POLLING_NRFLAG); +#else + return 0; +#endif +} + +void resched_curr_lazy(struct rq *rq) +{ + struct task_struct *curr = rq->curr; + int cpu; + + if (!sched_feat(PREEMPT_LAZY)) { + resched_curr(rq); + return; + } + + lockdep_assert_held(&rq->lock); + + if (test_tsk_need_resched(curr)) + return; + + if (test_tsk_need_resched_lazy(curr)) + return; + + set_tsk_need_resched_lazy(curr); + + cpu = cpu_of(rq); + if (cpu == smp_processor_id()) + return; + + /* NEED_RESCHED_LAZY must be visible before we test polling */ + smp_mb(); + if (!tsk_is_polling(curr)) + smp_send_reschedule(cpu); +} +#endif + void resched_cpu(int cpu) { struct rq *rq = cpu_rq(cpu); @@ -505,11 +565,14 @@ void resched_cpu(int cpu) */ int get_nohz_timer_target(void) { - int i, cpu = smp_processor_id(); + int i, cpu; struct sched_domain *sd; + preempt_disable_rt(); + cpu = smp_processor_id(); + if (!idle_cpu(cpu) && housekeeping_cpu(cpu, HK_FLAG_TIMER)) - return cpu; + goto preempt_en_rt; rcu_read_lock(); for_each_domain(cpu, sd) { @@ -528,6 +591,8 @@ int get_nohz_timer_target(void) cpu = housekeeping_any_cpu(HK_FLAG_TIMER); unlock: rcu_read_unlock(); +preempt_en_rt: + preempt_enable_rt(); return cpu; } @@ -902,10 +967,10 @@ static inline bool is_per_cpu_kthread(struct task_struct *p) */ static inline bool is_cpu_allowed(struct task_struct *p, int cpu) { - if (!cpumask_test_cpu(cpu, &p->cpus_allowed)) + if (!cpumask_test_cpu(cpu, p->cpus_ptr)) return false; - if (is_per_cpu_kthread(p)) + if (is_per_cpu_kthread(p) || __migrate_disabled(p)) return cpu_online(cpu); return cpu_active(cpu); @@ -997,7 +1062,7 @@ static int migration_cpu_stop(void *data) local_irq_disable(); /* * We need to explicitly wake pending tasks before running - * __migrate_task() such that we will not miss enforcing cpus_allowed + * __migrate_task() such that we will not miss enforcing cpus_ptr * during wakeups, see set_cpus_allowed_ptr()'s TASK_WAKING test. */ sched_ttwu_pending(); @@ -1028,11 +1093,19 @@ static int migration_cpu_stop(void *data) */ void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_mask) { - cpumask_copy(&p->cpus_allowed, new_mask); + cpumask_copy(&p->cpus_mask, new_mask); p->nr_cpus_allowed = cpumask_weight(new_mask); } -void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) +#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE) +int __migrate_disabled(struct task_struct *p) +{ + return p->migrate_disable; +} +#endif + +static void __do_set_cpus_allowed_tail(struct task_struct *p, + const struct cpumask *new_mask) { struct rq *rq = task_rq(p); bool queued, running; @@ -1061,6 +1134,20 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) set_curr_task(rq, p); } +void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) +{ +#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE) + if (__migrate_disabled(p)) { + lockdep_assert_held(&p->pi_lock); + + cpumask_copy(&p->cpus_mask, new_mask); + p->migrate_disable_update = 1; + return; + } +#endif + __do_set_cpus_allowed_tail(p, new_mask); +} + /* * Change a given task's CPU affinity. Migrate the thread to a * proper CPU and schedule it away if the CPU it's executing on @@ -1098,7 +1185,7 @@ static int __set_cpus_allowed_ptr(struct task_struct *p, goto out; } - if (cpumask_equal(&p->cpus_allowed, new_mask)) + if (cpumask_equal(p->cpus_ptr, new_mask)) goto out; if (!cpumask_intersects(new_mask, cpu_valid_mask)) { @@ -1119,9 +1206,16 @@ static int __set_cpus_allowed_ptr(struct task_struct *p, } /* Can the task run on the task's current CPU? If so, we're done */ - if (cpumask_test_cpu(task_cpu(p), new_mask)) + if (cpumask_test_cpu(task_cpu(p), new_mask) || __migrate_disabled(p)) goto out; +#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE) + if (__migrate_disabled(p)) { + p->migrate_disable_update = 1; + goto out; + } +#endif + dest_cpu = cpumask_any_and(cpu_valid_mask, new_mask); if (task_running(rq, p) || p->state == TASK_WAKING) { struct migration_arg arg = { p, dest_cpu }; @@ -1260,10 +1354,10 @@ static int migrate_swap_stop(void *data) if (task_cpu(arg->src_task) != arg->src_cpu) goto unlock; - if (!cpumask_test_cpu(arg->dst_cpu, &arg->src_task->cpus_allowed)) + if (!cpumask_test_cpu(arg->dst_cpu, arg->src_task->cpus_ptr)) goto unlock; - if (!cpumask_test_cpu(arg->src_cpu, &arg->dst_task->cpus_allowed)) + if (!cpumask_test_cpu(arg->src_cpu, arg->dst_task->cpus_ptr)) goto unlock; __migrate_swap_task(arg->src_task, arg->dst_cpu); @@ -1304,10 +1398,10 @@ int migrate_swap(struct task_struct *cur, struct task_struct *p) if (!cpu_active(arg.src_cpu) || !cpu_active(arg.dst_cpu)) goto out; - if (!cpumask_test_cpu(arg.dst_cpu, &arg.src_task->cpus_allowed)) + if (!cpumask_test_cpu(arg.dst_cpu, arg.src_task->cpus_ptr)) goto out; - if (!cpumask_test_cpu(arg.src_cpu, &arg.dst_task->cpus_allowed)) + if (!cpumask_test_cpu(arg.src_cpu, arg.dst_task->cpus_ptr)) goto out; trace_sched_swap_numa(cur, arg.src_cpu, p, arg.dst_cpu); @@ -1317,6 +1411,18 @@ out: return ret; } +static bool check_task_state(struct task_struct *p, long match_state) +{ + bool match = false; + + raw_spin_lock_irq(&p->pi_lock); + if (p->state == match_state || p->saved_state == match_state) + match = true; + raw_spin_unlock_irq(&p->pi_lock); + + return match; +} + /* * wait_task_inactive - wait for a thread to unschedule. * @@ -1361,7 +1467,7 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state) * is actually now running somewhere else! */ while (task_running(rq, p)) { - if (match_state && unlikely(p->state != match_state)) + if (match_state && !check_task_state(p, match_state)) return 0; cpu_relax(); } @@ -1376,7 +1482,8 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state) running = task_running(rq, p); queued = task_on_rq_queued(p); ncsw = 0; - if (!match_state || p->state == match_state) + if (!match_state || p->state == match_state || + p->saved_state == match_state) ncsw = p->nvcsw | LONG_MIN; /* sets MSB */ task_rq_unlock(rq, p, &rf); @@ -1451,7 +1558,7 @@ void kick_process(struct task_struct *p) EXPORT_SYMBOL_GPL(kick_process); /* - * ->cpus_allowed is protected by both rq->lock and p->pi_lock + * ->cpus_ptr is protected by both rq->lock and p->pi_lock * * A few notes on cpu_active vs cpu_online: * @@ -1491,14 +1598,14 @@ static int select_fallback_rq(int cpu, struct task_struct *p) for_each_cpu(dest_cpu, nodemask) { if (!cpu_active(dest_cpu)) continue; - if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed)) + if (cpumask_test_cpu(dest_cpu, p->cpus_ptr)) return dest_cpu; } } for (;;) { /* Any allowed, online CPU? */ - for_each_cpu(dest_cpu, &p->cpus_allowed) { + for_each_cpu(dest_cpu, p->cpus_ptr) { if (!is_cpu_allowed(p, dest_cpu)) continue; @@ -1542,7 +1649,7 @@ out: } /* - * The caller (fork, wakeup) owns p->pi_lock, ->cpus_allowed is stable. + * The caller (fork, wakeup) owns p->pi_lock, ->cpus_ptr is stable. */ static inline int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags) @@ -1552,11 +1659,11 @@ int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags) if (p->nr_cpus_allowed > 1) cpu = p->sched_class->select_task_rq(p, cpu, sd_flags, wake_flags); else - cpu = cpumask_any(&p->cpus_allowed); + cpu = cpumask_any(p->cpus_ptr); /* * In order not to call set_task_cpu() on a blocking task we need - * to rely on ttwu() to place the task on a valid ->cpus_allowed + * to rely on ttwu() to place the task on a valid ->cpus_ptr * CPU. * * Since this is common to all placement strategies, this lives here. @@ -1659,10 +1766,6 @@ static inline void ttwu_activate(struct rq *rq, struct task_struct *p, int en_fl { activate_task(rq, p, en_flags); p->on_rq = TASK_ON_RQ_QUEUED; - - /* If a worker is waking up, notify the workqueue: */ - if (p->flags & PF_WQ_WORKER) - wq_worker_waking_up(p, cpu_of(rq)); } /* @@ -1986,8 +2089,27 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) */ raw_spin_lock_irqsave(&p->pi_lock, flags); smp_mb__after_spinlock(); - if (!(p->state & state)) + if (!(p->state & state)) { + /* + * The task might be running due to a spinlock sleeper + * wakeup. Check the saved state and set it to running + * if the wakeup condition is true. + */ + if (!(wake_flags & WF_LOCK_SLEEPER)) { + if (p->saved_state & state) { + p->saved_state = TASK_RUNNING; + success = 1; + } + } goto out; + } + + /* + * If this is a regular wakeup, then we can unconditionally + * clear the saved state of a "lock sleeper". + */ + if (!(wake_flags & WF_LOCK_SLEEPER)) + p->saved_state = TASK_RUNNING; trace_sched_waking(p); @@ -2084,56 +2206,6 @@ out: } /** - * try_to_wake_up_local - try to wake up a local task with rq lock held - * @p: the thread to be awakened - * @rf: request-queue flags for pinning - * - * Put @p on the run-queue if it's not already there. The caller must - * ensure that this_rq() is locked, @p is bound to this_rq() and not - * the current task. - */ -static void try_to_wake_up_local(struct task_struct *p, struct rq_flags *rf) -{ - struct rq *rq = task_rq(p); - - if (WARN_ON_ONCE(rq != this_rq()) || - WARN_ON_ONCE(p == current)) - return; - - lockdep_assert_held(&rq->lock); - - if (!raw_spin_trylock(&p->pi_lock)) { - /* - * This is OK, because current is on_cpu, which avoids it being - * picked for load-balance and preemption/IRQs are still - * disabled avoiding further scheduler activity on it and we've - * not yet picked a replacement task. - */ - rq_unlock(rq, rf); - raw_spin_lock(&p->pi_lock); - rq_relock(rq, rf); - } - - if (!(p->state & TASK_NORMAL)) - goto out; - - trace_sched_waking(p); - - if (!task_on_rq_queued(p)) { - if (p->in_iowait) { - delayacct_blkio_end(p); - atomic_dec(&rq->nr_iowait); - } - ttwu_activate(rq, p, ENQUEUE_WAKEUP | ENQUEUE_NOCLOCK); - } - - ttwu_do_wakeup(rq, p, 0, rf); - ttwu_stat(p, smp_processor_id(), 0); -out: - raw_spin_unlock(&p->pi_lock); -} - -/** * wake_up_process - Wake up a specific process * @p: The process to be woken up. * @@ -2151,6 +2223,18 @@ int wake_up_process(struct task_struct *p) } EXPORT_SYMBOL(wake_up_process); +/** + * wake_up_lock_sleeper - Wake up a specific process blocked on a "sleeping lock" + * @p: The process to be woken up. + * + * Same as wake_up_process() above, but wake_flags=WF_LOCK_SLEEPER to indicate + * the nature of the wakeup. + */ +int wake_up_lock_sleeper(struct task_struct *p) +{ + return try_to_wake_up(p, TASK_UNINTERRUPTIBLE, WF_LOCK_SLEEPER); +} + int wake_up_state(struct task_struct *p, unsigned int state) { return try_to_wake_up(p, state, 0); @@ -2319,7 +2403,6 @@ static inline void init_schedstats(void) {} int sched_fork(unsigned long clone_flags, struct task_struct *p) { unsigned long flags; - int cpu = get_cpu(); __sched_fork(clone_flags, p); /* @@ -2355,14 +2438,12 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p) p->sched_reset_on_fork = 0; } - if (dl_prio(p->prio)) { - put_cpu(); + if (dl_prio(p->prio)) return -EAGAIN; - } else if (rt_prio(p->prio)) { + else if (rt_prio(p->prio)) p->sched_class = &rt_sched_class; - } else { + else p->sched_class = &fair_sched_class; - } init_entity_runnable_average(&p->se); @@ -2378,7 +2459,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p) * We're setting the CPU for the first time, we don't migrate, * so use __set_task_cpu(). */ - __set_task_cpu(p, cpu); + __set_task_cpu(p, smp_processor_id()); if (p->sched_class->task_fork) p->sched_class->task_fork(p); raw_spin_unlock_irqrestore(&p->pi_lock, flags); @@ -2391,12 +2472,13 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p) p->on_cpu = 0; #endif init_task_preempt_count(p); +#ifdef CONFIG_HAVE_PREEMPT_LAZY + task_thread_info(p)->preempt_lazy_count = 0; +#endif #ifdef CONFIG_SMP plist_node_init(&p->pushable_tasks, MAX_PRIO); RB_CLEAR_NODE(&p->pushable_dl_tasks); #endif - - put_cpu(); return 0; } @@ -2433,7 +2515,7 @@ void wake_up_new_task(struct task_struct *p) #ifdef CONFIG_SMP /* * Fork balancing, do it here and not earlier because: - * - cpus_allowed can change in the fork path + * - cpus_ptr can change in the fork path * - any previously selected CPU might disappear through hotplug * * Use __set_task_cpu() to avoid calling sched_class::migrate_task_rq, @@ -2721,23 +2803,18 @@ static struct rq *finish_task_switch(struct task_struct *prev) * provided by mmdrop(), * - a sync_core for SYNC_CORE. */ + /* + * We use mmdrop_delayed() here so we don't have to do the + * full __mmdrop() when we are the last user. + */ if (mm) { membarrier_mm_sync_core_before_usermode(mm); - mmdrop(mm); + mmdrop_delayed(mm); } if (unlikely(prev_state == TASK_DEAD)) { if (prev->sched_class->task_dead) prev->sched_class->task_dead(prev); - /* - * Remove function-return probe instances associated with this - * task and put them back on the free list. - */ - kprobe_flush_task(prev); - - /* Task is done with its stack. */ - put_task_stack(prev); - put_task_struct(prev); } @@ -3457,25 +3534,13 @@ static void __sched notrace __schedule(bool preempt) atomic_inc(&rq->nr_iowait); delayacct_blkio_start(); } - - /* - * If a worker went to sleep, notify and ask workqueue - * whether it wants to wake up a task to maintain - * concurrency. - */ - if (prev->flags & PF_WQ_WORKER) { - struct task_struct *to_wakeup; - - to_wakeup = wq_worker_sleeping(prev); - if (to_wakeup) - try_to_wake_up_local(to_wakeup, &rf); - } } switch_count = &prev->nvcsw; } next = pick_next_task(rq, prev, &rf); clear_tsk_need_resched(prev); + clear_tsk_need_resched_lazy(prev); clear_preempt_need_resched(); if (likely(prev != next)) { @@ -3527,9 +3592,25 @@ void __noreturn do_task_dead(void) static inline void sched_submit_work(struct task_struct *tsk) { - if (!tsk->state || tsk_is_pi_blocked(tsk)) + if (!tsk->state) return; /* + * If a worker went to sleep, notify and ask workqueue whether + * it wants to wake up a task to maintain concurrency. + * As this function is called inside the schedule() context, + * we disable preemption to avoid it calling schedule() again + * in the possible wakeup of a kworker. + */ + if (tsk->flags & PF_WQ_WORKER) { + preempt_disable(); + wq_worker_sleeping(tsk); + preempt_enable_no_resched(); + } + + if (tsk_is_pi_blocked(tsk)) + return; + + /* * If we are going to sleep and we have plugged IO queued, * make sure to submit it to avoid deadlocks. */ @@ -3537,6 +3618,12 @@ static inline void sched_submit_work(struct task_struct *tsk) blk_schedule_flush_plug(tsk); } +static void sched_update_worker(struct task_struct *tsk) +{ + if (tsk->flags & PF_WQ_WORKER) + wq_worker_running(tsk); +} + asmlinkage __visible void __sched schedule(void) { struct task_struct *tsk = current; @@ -3547,6 +3634,7 @@ asmlinkage __visible void __sched schedule(void) __schedule(false); sched_preempt_enable_no_resched(); } while (need_resched()); + sched_update_worker(tsk); } EXPORT_SYMBOL(schedule); @@ -3635,6 +3723,30 @@ static void __sched notrace preempt_schedule_common(void) } while (need_resched()); } +#ifdef CONFIG_PREEMPT_LAZY +/* + * If TIF_NEED_RESCHED is then we allow to be scheduled away since this is + * set by a RT task. Oterwise we try to avoid beeing scheduled out as long as + * preempt_lazy_count counter >0. + */ +static __always_inline int preemptible_lazy(void) +{ + if (test_thread_flag(TIF_NEED_RESCHED)) + return 1; + if (current_thread_info()->preempt_lazy_count) + return 0; + return 1; +} + +#else + +static inline int preemptible_lazy(void) +{ + return 1; +} + +#endif + #ifdef CONFIG_PREEMPT /* * this is the entry point to schedule() from in-kernel preemption @@ -3649,7 +3761,8 @@ asmlinkage __visible void __sched notrace preempt_schedule(void) */ if (likely(!preemptible())) return; - + if (!preemptible_lazy()) + return; preempt_schedule_common(); } NOKPROBE_SYMBOL(preempt_schedule); @@ -3676,6 +3789,9 @@ asmlinkage __visible void __sched notrace preempt_schedule_notrace(void) if (likely(!preemptible())) return; + if (!preemptible_lazy()) + return; + do { /* * Because the function tracer can trace preempt_count_sub() @@ -4304,7 +4420,7 @@ change: * the entire root_domain to become SCHED_DEADLINE. We * will also fail if there's no bandwidth available. */ - if (!cpumask_subset(span, &p->cpus_allowed) || + if (!cpumask_subset(span, p->cpus_ptr) || rq->rd->dl_bw.bw == 0) { task_rq_unlock(rq, p, &rf); return -EPERM; @@ -4903,7 +5019,7 @@ long sched_getaffinity(pid_t pid, struct cpumask *mask) goto out_unlock; raw_spin_lock_irqsave(&p->pi_lock, flags); - cpumask_and(mask, &p->cpus_allowed, cpu_active_mask); + cpumask_and(mask, &p->cpus_mask, cpu_active_mask); raw_spin_unlock_irqrestore(&p->pi_lock, flags); out_unlock: @@ -5444,7 +5560,9 @@ void init_idle(struct task_struct *idle, int cpu) /* Set the preempt count _outside_ the spinlocks! */ init_idle_preempt_count(idle, cpu); - +#ifdef CONFIG_HAVE_PREEMPT_LAZY + task_thread_info(idle)->preempt_lazy_count = 0; +#endif /* * The idle tasks have their own, simple scheduling class: */ @@ -5483,7 +5601,7 @@ int task_can_attach(struct task_struct *p, * allowed nodes is unnecessary. Thus, cpusets are not * applicable for such threads. This prevents checking for * success of set_cpus_allowed_ptr() on all attached tasks - * before cpus_allowed may be changed. + * before cpus_mask may be changed. */ if (p->flags & PF_NO_SETAFFINITY) { ret = -EINVAL; @@ -5510,7 +5628,7 @@ int migrate_task_to(struct task_struct *p, int target_cpu) if (curr_cpu == target_cpu) return 0; - if (!cpumask_test_cpu(target_cpu, &p->cpus_allowed)) + if (!cpumask_test_cpu(target_cpu, p->cpus_ptr)) return -EINVAL; /* TODO: This is not properly updating schedstats */ @@ -5549,6 +5667,8 @@ void sched_setnuma(struct task_struct *p, int nid) #endif /* CONFIG_NUMA_BALANCING */ #ifdef CONFIG_HOTPLUG_CPU +static DEFINE_PER_CPU(struct mm_struct *, idle_last_mm); + /* * Ensure that the idle task is using init_mm right before its CPU goes * offline. @@ -5564,7 +5684,11 @@ void idle_task_exit(void) current->active_mm = &init_mm; finish_arch_post_lock_switch(); } - mmdrop(mm); + /* + * Defer the cleanup to an alive cpu. On RT we can neither + * call mmdrop() nor mmdrop_delayed() from here. + */ + per_cpu(idle_last_mm, smp_processor_id()) = mm; } /* @@ -5648,7 +5772,7 @@ static void migrate_tasks(struct rq *dead_rq, struct rq_flags *rf) put_prev_task(rq, next); /* - * Rules for changing task_struct::cpus_allowed are holding + * Rules for changing task_struct::cpus_mask are holding * both pi_lock and rq->lock, such that holding either * stabilizes the mask. * @@ -5884,6 +6008,10 @@ int sched_cpu_dying(unsigned int cpu) update_max_interval(); nohz_balance_exit_idle(rq); hrtick_clear(rq); + if (per_cpu(idle_last_mm, cpu)) { + mmdrop_delayed(per_cpu(idle_last_mm, cpu)); + per_cpu(idle_last_mm, cpu) = NULL; + } return 0; } #endif @@ -6120,7 +6248,7 @@ void __init sched_init(void) #ifdef CONFIG_DEBUG_ATOMIC_SLEEP static inline int preempt_count_equals(int preempt_offset) { - int nested = preempt_count() + rcu_preempt_depth(); + int nested = preempt_count() + sched_rcu_preempt_depth(); return (nested == preempt_offset); } @@ -7096,3 +7224,196 @@ const u32 sched_prio_to_wmult[40] = { }; #undef CREATE_TRACE_POINTS + +#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE) + +static inline void +update_nr_migratory(struct task_struct *p, long delta) +{ + if (unlikely((p->sched_class == &rt_sched_class || + p->sched_class == &dl_sched_class) && + p->nr_cpus_allowed > 1)) { + if (p->sched_class == &rt_sched_class) + task_rq(p)->rt.rt_nr_migratory += delta; + else + task_rq(p)->dl.dl_nr_migratory += delta; + } +} + +static inline void +migrate_disable_update_cpus_allowed(struct task_struct *p) +{ + struct rq *rq; + struct rq_flags rf; + + p->cpus_ptr = cpumask_of(smp_processor_id()); + + rq = task_rq_lock(p, &rf); + update_nr_migratory(p, -1); + p->nr_cpus_allowed = 1; + task_rq_unlock(rq, p, &rf); +} + +static inline void +migrate_enable_update_cpus_allowed(struct task_struct *p) +{ + struct rq *rq; + struct rq_flags rf; + + p->cpus_ptr = &p->cpus_mask; + + rq = task_rq_lock(p, &rf); + p->nr_cpus_allowed = cpumask_weight(&p->cpus_mask); + update_nr_migratory(p, 1); + task_rq_unlock(rq, p, &rf); +} + +void migrate_disable(void) +{ + struct task_struct *p = current; + + if (in_atomic() || irqs_disabled()) { +#ifdef CONFIG_SCHED_DEBUG + p->migrate_disable_atomic++; +#endif + return; + } +#ifdef CONFIG_SCHED_DEBUG + if (unlikely(p->migrate_disable_atomic)) { + tracing_off(); + WARN_ON_ONCE(1); + } +#endif + + if (p->migrate_disable) { + p->migrate_disable++; + return; + } + + preempt_disable(); + preempt_lazy_disable(); + pin_current_cpu(); + + migrate_disable_update_cpus_allowed(p); + p->migrate_disable = 1; + + preempt_enable(); +} +EXPORT_SYMBOL(migrate_disable); + +void migrate_enable(void) +{ + struct task_struct *p = current; + + if (in_atomic() || irqs_disabled()) { +#ifdef CONFIG_SCHED_DEBUG + p->migrate_disable_atomic--; +#endif + return; + } + +#ifdef CONFIG_SCHED_DEBUG + if (unlikely(p->migrate_disable_atomic)) { + tracing_off(); + WARN_ON_ONCE(1); + } +#endif + + WARN_ON_ONCE(p->migrate_disable <= 0); + if (p->migrate_disable > 1) { + p->migrate_disable--; + return; + } + + preempt_disable(); + + p->migrate_disable = 0; + migrate_enable_update_cpus_allowed(p); + + if (p->migrate_disable_update) { + struct rq *rq; + struct rq_flags rf; + + rq = task_rq_lock(p, &rf); + update_rq_clock(rq); + + __do_set_cpus_allowed_tail(p, &p->cpus_mask); + task_rq_unlock(rq, p, &rf); + + p->migrate_disable_update = 0; + + WARN_ON(smp_processor_id() != task_cpu(p)); + if (!cpumask_test_cpu(task_cpu(p), &p->cpus_mask)) { + const struct cpumask *cpu_valid_mask = cpu_active_mask; + struct migration_arg arg; + unsigned int dest_cpu; + + if (p->flags & PF_KTHREAD) { + /* + * Kernel threads are allowed on online && !active CPUs + */ + cpu_valid_mask = cpu_online_mask; + } + dest_cpu = cpumask_any_and(cpu_valid_mask, &p->cpus_mask); + arg.task = p; + arg.dest_cpu = dest_cpu; + + unpin_current_cpu(); + preempt_lazy_enable(); + preempt_enable(); + stop_one_cpu(task_cpu(p), migration_cpu_stop, &arg); + tlb_migrate_finish(p->mm); + + return; + } + } + unpin_current_cpu(); + preempt_lazy_enable(); + preempt_enable(); +} +EXPORT_SYMBOL(migrate_enable); + +#elif !defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE) +void migrate_disable(void) +{ +#ifdef CONFIG_SCHED_DEBUG + struct task_struct *p = current; + + if (in_atomic() || irqs_disabled()) { + p->migrate_disable_atomic++; + return; + } + + if (unlikely(p->migrate_disable_atomic)) { + tracing_off(); + WARN_ON_ONCE(1); + } + + p->migrate_disable++; +#endif + barrier(); +} +EXPORT_SYMBOL(migrate_disable); + +void migrate_enable(void) +{ +#ifdef CONFIG_SCHED_DEBUG + struct task_struct *p = current; + + if (in_atomic() || irqs_disabled()) { + p->migrate_disable_atomic--; + return; + } + + if (unlikely(p->migrate_disable_atomic)) { + tracing_off(); + WARN_ON_ONCE(1); + } + + WARN_ON_ONCE(p->migrate_disable <= 0); + p->migrate_disable--; +#endif + barrier(); +} +EXPORT_SYMBOL(migrate_enable); +#endif diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c index 50316455ea66..d57fb2f8ae67 100644 --- a/kernel/sched/cpudeadline.c +++ b/kernel/sched/cpudeadline.c @@ -124,14 +124,14 @@ int cpudl_find(struct cpudl *cp, struct task_struct *p, const struct sched_dl_entity *dl_se = &p->dl; if (later_mask && - cpumask_and(later_mask, cp->free_cpus, &p->cpus_allowed)) { + cpumask_and(later_mask, cp->free_cpus, p->cpus_ptr)) { return 1; } else { int best_cpu = cpudl_maximum(cp); WARN_ON(best_cpu != -1 && !cpu_present(best_cpu)); - if (cpumask_test_cpu(best_cpu, &p->cpus_allowed) && + if (cpumask_test_cpu(best_cpu, p->cpus_ptr) && dl_time_before(dl_se->deadline, cp->elements[0].dl)) { if (later_mask) cpumask_set_cpu(best_cpu, later_mask); diff --git a/kernel/sched/cpupri.c b/kernel/sched/cpupri.c index daaadf939ccb..f7d2c10b4c92 100644 --- a/kernel/sched/cpupri.c +++ b/kernel/sched/cpupri.c @@ -98,11 +98,11 @@ int cpupri_find(struct cpupri *cp, struct task_struct *p, if (skip) continue; - if (cpumask_any_and(&p->cpus_allowed, vec->mask) >= nr_cpu_ids) + if (cpumask_any_and(p->cpus_ptr, vec->mask) >= nr_cpu_ids) continue; if (lowest_mask) { - cpumask_and(lowest_mask, &p->cpus_allowed, vec->mask); + cpumask_and(lowest_mask, p->cpus_ptr, vec->mask); /* * We have to ensure that we have at least one bit diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 0c9fb74dc982..a37ab8bbe567 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -537,7 +537,7 @@ static struct rq *dl_task_offline_migration(struct rq *rq, struct task_struct *p * If we cannot preempt any rq, fall back to pick any * online CPU: */ - cpu = cpumask_any_and(cpu_active_mask, &p->cpus_allowed); + cpu = cpumask_any_and(cpu_active_mask, p->cpus_ptr); if (cpu >= nr_cpu_ids) { /* * Failed to find any suitable CPU. @@ -1052,7 +1052,7 @@ void init_dl_task_timer(struct sched_dl_entity *dl_se) { struct hrtimer *timer = &dl_se->dl_timer; - hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD); timer->function = dl_task_timer; } @@ -1819,7 +1819,7 @@ static void set_curr_task_dl(struct rq *rq) static int pick_dl_task(struct rq *rq, struct task_struct *p, int cpu) { if (!task_running(rq, p) && - cpumask_test_cpu(cpu, &p->cpus_allowed)) + cpumask_test_cpu(cpu, p->cpus_ptr)) return 1; return 0; } @@ -1969,7 +1969,7 @@ static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq) /* Retry if something changed. */ if (double_lock_balance(rq, later_rq)) { if (unlikely(task_rq(task) != rq || - !cpumask_test_cpu(later_rq->cpu, &task->cpus_allowed) || + !cpumask_test_cpu(later_rq->cpu, task->cpus_ptr) || task_running(rq, task) || !dl_task(task) || !task_on_rq_queued(task))) { diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index b2416f6d7fcf..39760c69fd79 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -983,6 +983,10 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns, P(dl.runtime); P(dl.deadline); } +#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE) + P(migrate_disable); +#endif + P(nr_cpus_allowed); #undef PN_SCHEDSTAT #undef PN #undef __PN diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 687140c45d28..13df13b1e314 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1615,7 +1615,7 @@ static void task_numa_compare(struct task_numa_env *env, */ if (cur) { /* Skip this swap candidate if cannot move to the source CPU: */ - if (!cpumask_test_cpu(env->src_cpu, &cur->cpus_allowed)) + if (!cpumask_test_cpu(env->src_cpu, cur->cpus_ptr)) goto unlock; /* @@ -1725,7 +1725,7 @@ static void task_numa_find_cpu(struct task_numa_env *env, for_each_cpu(cpu, cpumask_of_node(env->dst_nid)) { /* Skip this CPU if the source task cannot migrate */ - if (!cpumask_test_cpu(cpu, &env->p->cpus_allowed)) + if (!cpumask_test_cpu(cpu, env->p->cpus_ptr)) continue; env->dst_cpu = cpu; @@ -4341,7 +4341,7 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr) ideal_runtime = sched_slice(cfs_rq, curr); delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime; if (delta_exec > ideal_runtime) { - resched_curr(rq_of(cfs_rq)); + resched_curr_lazy(rq_of(cfs_rq)); /* * The current task ran long enough, ensure it doesn't get * re-elected due to buddy favours. @@ -4365,7 +4365,7 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr) return; if (delta > ideal_runtime) - resched_curr(rq_of(cfs_rq)); + resched_curr_lazy(rq_of(cfs_rq)); } static void @@ -4507,7 +4507,7 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued) * validating it and just reschedule. */ if (queued) { - resched_curr(rq_of(cfs_rq)); + resched_curr_lazy(rq_of(cfs_rq)); return; } /* @@ -4691,7 +4691,7 @@ static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec) * hierarchy can be throttled */ if (!assign_cfs_rq_runtime(cfs_rq) && likely(cfs_rq->curr)) - resched_curr(rq_of(cfs_rq)); + resched_curr_lazy(rq_of(cfs_rq)); } static __always_inline @@ -5227,9 +5227,9 @@ void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b) cfs_b->period = ns_to_ktime(default_cfs_period()); INIT_LIST_HEAD(&cfs_b->throttled_cfs_rq); - hrtimer_init(&cfs_b->period_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED); + hrtimer_init(&cfs_b->period_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED_HARD); cfs_b->period_timer.function = sched_cfs_period_timer; - hrtimer_init(&cfs_b->slack_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + hrtimer_init(&cfs_b->slack_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD); cfs_b->slack_timer.function = sched_cfs_slack_timer; cfs_b->distribute_running = 0; } @@ -5386,7 +5386,7 @@ static void hrtick_start_fair(struct rq *rq, struct task_struct *p) if (delta < 0) { if (rq->curr == p) - resched_curr(rq); + resched_curr_lazy(rq); return; } hrtick_start(rq, delta); @@ -6062,7 +6062,7 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, /* Skip over this group if it has no CPUs allowed */ if (!cpumask_intersects(sched_group_span(group), - &p->cpus_allowed)) + p->cpus_ptr)) continue; local_group = cpumask_test_cpu(this_cpu, @@ -6194,7 +6194,7 @@ find_idlest_group_cpu(struct sched_group *group, struct task_struct *p, int this return cpumask_first(sched_group_span(group)); /* Traverse only the allowed CPUs */ - for_each_cpu_and(i, sched_group_span(group), &p->cpus_allowed) { + for_each_cpu_and(i, sched_group_span(group), p->cpus_ptr) { if (available_idle_cpu(i)) { struct rq *rq = cpu_rq(i); struct cpuidle_state *idle = idle_get_state(rq); @@ -6234,7 +6234,7 @@ static inline int find_idlest_cpu(struct sched_domain *sd, struct task_struct *p { int new_cpu = cpu; - if (!cpumask_intersects(sched_domain_span(sd), &p->cpus_allowed)) + if (!cpumask_intersects(sched_domain_span(sd), p->cpus_ptr)) return prev_cpu; /* @@ -6350,7 +6350,7 @@ static int select_idle_core(struct task_struct *p, struct sched_domain *sd, int if (!test_idle_cores(target, false)) return -1; - cpumask_and(cpus, sched_domain_span(sd), &p->cpus_allowed); + cpumask_and(cpus, sched_domain_span(sd), p->cpus_ptr); for_each_cpu_wrap(core, cpus, target) { bool idle = true; @@ -6384,7 +6384,7 @@ static int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int t return -1; for_each_cpu(cpu, cpu_smt_mask(target)) { - if (!cpumask_test_cpu(cpu, &p->cpus_allowed)) + if (!cpumask_test_cpu(cpu, p->cpus_ptr)) continue; if (available_idle_cpu(cpu)) return cpu; @@ -6447,7 +6447,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t for_each_cpu_wrap(cpu, sched_domain_span(sd), target) { if (!--nr) return -1; - if (!cpumask_test_cpu(cpu, &p->cpus_allowed)) + if (!cpumask_test_cpu(cpu, p->cpus_ptr)) continue; if (available_idle_cpu(cpu)) break; @@ -6484,7 +6484,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target) recent_used_cpu != target && cpus_share_cache(recent_used_cpu, target) && available_idle_cpu(recent_used_cpu) && - cpumask_test_cpu(p->recent_used_cpu, &p->cpus_allowed)) { + cpumask_test_cpu(p->recent_used_cpu, p->cpus_ptr)) { /* * Replace recent_used_cpu with prev as it is a potential * candidate for the next wake: @@ -6702,7 +6702,7 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f if (sd_flag & SD_BALANCE_WAKE) { record_wakee(p); want_affine = !wake_wide(p) && !wake_cap(p, cpu, prev_cpu) - && cpumask_test_cpu(cpu, &p->cpus_allowed); + && cpumask_test_cpu(cpu, p->cpus_ptr); } rcu_read_lock(); @@ -6961,7 +6961,7 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_ return; preempt: - resched_curr(rq); + resched_curr_lazy(rq); /* * Only set the backward buddy when the current task is still * on the rq. This can happen when a wakeup gets interleaved @@ -7438,14 +7438,14 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) /* * We do not migrate tasks that are: * 1) throttled_lb_pair, or - * 2) cannot be migrated to this CPU due to cpus_allowed, or + * 2) cannot be migrated to this CPU due to cpus_ptr, or * 3) running (obviously), or * 4) are cache-hot on their current CPU. */ if (throttled_lb_pair(task_group(p), env->src_cpu, env->dst_cpu)) return 0; - if (!cpumask_test_cpu(env->dst_cpu, &p->cpus_allowed)) { + if (!cpumask_test_cpu(env->dst_cpu, p->cpus_ptr)) { int cpu; schedstat_inc(p->se.statistics.nr_failed_migrations_affine); @@ -7465,7 +7465,7 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) /* Prevent to re-select dst_cpu via env's CPUs: */ for_each_cpu_and(cpu, env->dst_grpmask, env->cpus) { - if (cpumask_test_cpu(cpu, &p->cpus_allowed)) { + if (cpumask_test_cpu(cpu, p->cpus_ptr)) { env->flags |= LBF_DST_PINNED; env->new_dst_cpu = cpu; break; @@ -8038,7 +8038,7 @@ check_cpu_capacity(struct rq *rq, struct sched_domain *sd) /* * Group imbalance indicates (and tries to solve) the problem where balancing - * groups is inadequate due to ->cpus_allowed constraints. + * groups is inadequate due to ->cpus_ptr constraints. * * Imagine a situation of two groups of 4 CPUs each and 4 tasks each with a * cpumask covering 1 CPU of the first group and 3 CPUs of the second group. @@ -8653,7 +8653,7 @@ static struct sched_group *find_busiest_group(struct lb_env *env) /* * If the busiest group is imbalanced the below checks don't * work because they assume all things are equal, which typically - * isn't true due to cpus_allowed constraints and the like. + * isn't true due to cpus_ptr constraints and the like. */ if (busiest->group_type == group_imbalanced) goto force_balance; @@ -9049,7 +9049,7 @@ more_balance: * if the curr task on busiest CPU can't be * moved to this_cpu: */ - if (!cpumask_test_cpu(this_cpu, &busiest->curr->cpus_allowed)) { + if (!cpumask_test_cpu(this_cpu, busiest->curr->cpus_ptr)) { raw_spin_unlock_irqrestore(&busiest->lock, flags); env.flags |= LBF_ALL_PINNED; @@ -10027,7 +10027,7 @@ static void task_fork_fair(struct task_struct *p) * 'current' within the tree based on its new key value. */ swap(curr->vruntime, se->vruntime); - resched_curr(rq); + resched_curr_lazy(rq); } se->vruntime -= cfs_rq->min_vruntime; @@ -10051,7 +10051,7 @@ prio_changed_fair(struct rq *rq, struct task_struct *p, int oldprio) */ if (rq->curr == p) { if (p->prio > oldprio) - resched_curr(rq); + resched_curr_lazy(rq); } else check_preempt_curr(rq, p, 0); } diff --git a/kernel/sched/features.h b/kernel/sched/features.h index 85ae8488039c..12a12be6770b 100644 --- a/kernel/sched/features.h +++ b/kernel/sched/features.h @@ -46,11 +46,19 @@ SCHED_FEAT(LB_BIAS, true) */ SCHED_FEAT(NONTASK_CAPACITY, true) +#ifdef CONFIG_PREEMPT_RT_FULL +SCHED_FEAT(TTWU_QUEUE, false) +# ifdef CONFIG_PREEMPT_LAZY +SCHED_FEAT(PREEMPT_LAZY, true) +# endif +#else + /* * Queue remote wakeups on the target CPU and process them * using the scheduler IPI. Reduces rq->lock contention/bounces. */ SCHED_FEAT(TTWU_QUEUE, true) +#endif /* * When doing wakeups, attempt to limit superfluous scans of the LLC domain. diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index a8e1a778bf6e..0c24b77695c8 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -43,8 +43,8 @@ void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime) raw_spin_lock_init(&rt_b->rt_runtime_lock); - hrtimer_init(&rt_b->rt_period_timer, - CLOCK_MONOTONIC, HRTIMER_MODE_REL); + hrtimer_init(&rt_b->rt_period_timer, CLOCK_MONOTONIC, + HRTIMER_MODE_REL_HARD); rt_b->rt_period_timer.function = sched_rt_period_timer; } @@ -1601,7 +1601,7 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p) static int pick_rt_task(struct rq *rq, struct task_struct *p, int cpu) { if (!task_running(rq, p) && - cpumask_test_cpu(cpu, &p->cpus_allowed)) + cpumask_test_cpu(cpu, p->cpus_ptr)) return 1; return 0; @@ -1738,7 +1738,7 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq) * Also make sure that it wasn't scheduled on its rq. */ if (unlikely(task_rq(task) != rq || - !cpumask_test_cpu(lowest_rq->cpu, &task->cpus_allowed) || + !cpumask_test_cpu(lowest_rq->cpu, task->cpus_ptr) || task_running(rq, task) || !rt_task(task) || !task_on_rq_queued(task))) { diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 2882d905c8a4..3d9a4d51539d 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1418,6 +1418,7 @@ static inline int task_on_rq_migrating(struct task_struct *p) #define WF_SYNC 0x01 /* Waker goes to sleep after wakeup */ #define WF_FORK 0x02 /* Child wakeup after fork */ #define WF_MIGRATED 0x4 /* Internal use, task got migrated */ +#define WF_LOCK_SLEEPER 0x08 /* wakeup spinlock "sleeper" */ /* * To aid in avoiding the subversion of "niceness" due to uneven distribution @@ -1612,6 +1613,15 @@ extern void reweight_task(struct task_struct *p, int prio); extern void resched_curr(struct rq *rq); extern void resched_cpu(int cpu); +#ifdef CONFIG_PREEMPT_LAZY +extern void resched_curr_lazy(struct rq *rq); +#else +static inline void resched_curr_lazy(struct rq *rq) +{ + resched_curr(rq); +} +#endif + extern struct rt_bandwidth def_rt_bandwidth; extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime); diff --git a/kernel/sched/swait.c b/kernel/sched/swait.c index b6fb2c3b3ff7..55d2a044399e 100644 --- a/kernel/sched/swait.c +++ b/kernel/sched/swait.c @@ -32,6 +32,25 @@ void swake_up_locked(struct swait_queue_head *q) } EXPORT_SYMBOL(swake_up_locked); +void swake_up_all_locked(struct swait_queue_head *q) +{ + struct swait_queue *curr; + int wakes = 0; + + while (!list_empty(&q->task_list)) { + + curr = list_first_entry(&q->task_list, typeof(*curr), + task_list); + wake_up_process(curr->task); + list_del_init(&curr->task_list); + wakes++; + } + if (pm_in_action) + return; + WARN(wakes > 2, "complete_all() with %d waiters\n", wakes); +} +EXPORT_SYMBOL(swake_up_all_locked); + void swake_up(struct swait_queue_head *q) { unsigned long flags; @@ -51,6 +70,7 @@ void swake_up_all(struct swait_queue_head *q) struct swait_queue *curr; LIST_HEAD(tmp); + WARN_ON(irqs_disabled()); raw_spin_lock_irq(&q->lock); list_splice_init(&q->task_list, &tmp); while (!list_empty(&tmp)) { diff --git a/kernel/sched/swork.c b/kernel/sched/swork.c new file mode 100644 index 000000000000..5559c22f664c --- /dev/null +++ b/kernel/sched/swork.c @@ -0,0 +1,173 @@ +/* + * Copyright (C) 2014 BMW Car IT GmbH, Daniel Wagner daniel.wagner@bmw-carit.de + * + * Provides a framework for enqueuing callbacks from irq context + * PREEMPT_RT_FULL safe. The callbacks are executed in kthread context. + */ + +#include <linux/swait.h> +#include <linux/swork.h> +#include <linux/kthread.h> +#include <linux/slab.h> +#include <linux/spinlock.h> +#include <linux/export.h> + +#define SWORK_EVENT_PENDING 1 + +static DEFINE_MUTEX(worker_mutex); +static struct sworker *glob_worker; + +struct sworker { + struct list_head events; + struct swait_queue_head wq; + + raw_spinlock_t lock; + + struct task_struct *task; + int refs; +}; + +static bool swork_readable(struct sworker *worker) +{ + bool r; + + if (kthread_should_stop()) + return true; + + raw_spin_lock_irq(&worker->lock); + r = !list_empty(&worker->events); + raw_spin_unlock_irq(&worker->lock); + + return r; +} + +static int swork_kthread(void *arg) +{ + struct sworker *worker = arg; + + for (;;) { + swait_event_interruptible(worker->wq, + swork_readable(worker)); + if (kthread_should_stop()) + break; + + raw_spin_lock_irq(&worker->lock); + while (!list_empty(&worker->events)) { + struct swork_event *sev; + + sev = list_first_entry(&worker->events, + struct swork_event, item); + list_del(&sev->item); + raw_spin_unlock_irq(&worker->lock); + + WARN_ON_ONCE(!test_and_clear_bit(SWORK_EVENT_PENDING, + &sev->flags)); + sev->func(sev); + raw_spin_lock_irq(&worker->lock); + } + raw_spin_unlock_irq(&worker->lock); + } + return 0; +} + +static struct sworker *swork_create(void) +{ + struct sworker *worker; + + worker = kzalloc(sizeof(*worker), GFP_KERNEL); + if (!worker) + return ERR_PTR(-ENOMEM); + + INIT_LIST_HEAD(&worker->events); + raw_spin_lock_init(&worker->lock); + init_swait_queue_head(&worker->wq); + + worker->task = kthread_run(swork_kthread, worker, "kswork"); + if (IS_ERR(worker->task)) { + kfree(worker); + return ERR_PTR(-ENOMEM); + } + + return worker; +} + +static void swork_destroy(struct sworker *worker) +{ + kthread_stop(worker->task); + + WARN_ON(!list_empty(&worker->events)); + kfree(worker); +} + +/** + * swork_queue - queue swork + * + * Returns %false if @work was already on a queue, %true otherwise. + * + * The work is queued and processed on a random CPU + */ +bool swork_queue(struct swork_event *sev) +{ + unsigned long flags; + + if (test_and_set_bit(SWORK_EVENT_PENDING, &sev->flags)) + return false; + + raw_spin_lock_irqsave(&glob_worker->lock, flags); + list_add_tail(&sev->item, &glob_worker->events); + raw_spin_unlock_irqrestore(&glob_worker->lock, flags); + + swake_up(&glob_worker->wq); + return true; +} +EXPORT_SYMBOL_GPL(swork_queue); + +/** + * swork_get - get an instance of the sworker + * + * Returns an negative error code if the initialization if the worker did not + * work, %0 otherwise. + * + */ +int swork_get(void) +{ + struct sworker *worker; + + mutex_lock(&worker_mutex); + if (!glob_worker) { + worker = swork_create(); + if (IS_ERR(worker)) { + mutex_unlock(&worker_mutex); + return -ENOMEM; + } + + glob_worker = worker; + } + + glob_worker->refs++; + mutex_unlock(&worker_mutex); + + return 0; +} +EXPORT_SYMBOL_GPL(swork_get); + +/** + * swork_put - puts an instance of the sworker + * + * Will destroy the sworker thread. This function must not be called until all + * queued events have been completed. + */ +void swork_put(void) +{ + mutex_lock(&worker_mutex); + + glob_worker->refs--; + if (glob_worker->refs > 0) + goto out; + + swork_destroy(glob_worker); + glob_worker = NULL; +out: + mutex_unlock(&worker_mutex); +} +EXPORT_SYMBOL_GPL(swork_put); diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index c0a751464971..6e95f1ca3e22 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -279,6 +279,7 @@ static int init_rootdomain(struct root_domain *rd) rd->rto_cpu = -1; raw_spin_lock_init(&rd->rto_lock); init_irq_work(&rd->rto_push_work, rto_push_irq_work_func); + rd->rto_push_work.flags |= IRQ_WORK_HARD_IRQ; #endif init_dl_bw(&rd->dl_bw); diff --git a/kernel/signal.c b/kernel/signal.c index c4462e92e9cd..fc5c8c1fcb82 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -19,6 +19,7 @@ #include <linux/sched/task.h> #include <linux/sched/task_stack.h> #include <linux/sched/cputime.h> +#include <linux/sched/rt.h> #include <linux/fs.h> #include <linux/tty.h> #include <linux/binfmts.h> @@ -362,13 +363,30 @@ static bool task_participate_group_stop(struct task_struct *task) return false; } +static inline struct sigqueue *get_task_cache(struct task_struct *t) +{ + struct sigqueue *q = t->sigqueue_cache; + + if (cmpxchg(&t->sigqueue_cache, q, NULL) != q) + return NULL; + return q; +} + +static inline int put_task_cache(struct task_struct *t, struct sigqueue *q) +{ + if (cmpxchg(&t->sigqueue_cache, NULL, q) == NULL) + return 0; + return 1; +} + /* * allocate a new signal queue record * - this may be called without locks if and only if t == current, otherwise an * appropriate lock must be held to stop the target task from exiting */ static struct sigqueue * -__sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, int override_rlimit) +__sigqueue_do_alloc(int sig, struct task_struct *t, gfp_t flags, + int override_rlimit, int fromslab) { struct sigqueue *q = NULL; struct user_struct *user; @@ -385,7 +403,10 @@ __sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, int override_rlimi if (override_rlimit || atomic_read(&user->sigpending) <= task_rlimit(t, RLIMIT_SIGPENDING)) { - q = kmem_cache_alloc(sigqueue_cachep, flags); + if (!fromslab) + q = get_task_cache(t); + if (!q) + q = kmem_cache_alloc(sigqueue_cachep, flags); } else { print_dropped_signal(sig); } @@ -402,6 +423,13 @@ __sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, int override_rlimi return q; } +static struct sigqueue * +__sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, + int override_rlimit) +{ + return __sigqueue_do_alloc(sig, t, flags, override_rlimit, 0); +} + static void __sigqueue_free(struct sigqueue *q) { if (q->flags & SIGQUEUE_PREALLOC) @@ -411,6 +439,21 @@ static void __sigqueue_free(struct sigqueue *q) kmem_cache_free(sigqueue_cachep, q); } +static void sigqueue_free_current(struct sigqueue *q) +{ + struct user_struct *up; + + if (q->flags & SIGQUEUE_PREALLOC) + return; + + up = q->user; + if (rt_prio(current->normal_prio) && !put_task_cache(current, q)) { + atomic_dec(&up->sigpending); + free_uid(up); + } else + __sigqueue_free(q); +} + void flush_sigqueue(struct sigpending *queue) { struct sigqueue *q; @@ -424,6 +467,21 @@ void flush_sigqueue(struct sigpending *queue) } /* + * Called from __exit_signal. Flush tsk->pending and + * tsk->sigqueue_cache + */ +void flush_task_sigqueue(struct task_struct *tsk) +{ + struct sigqueue *q; + + flush_sigqueue(&tsk->pending); + + q = get_task_cache(tsk); + if (q) + kmem_cache_free(sigqueue_cachep, q); +} + +/* * Flush all pending signals for this kthread. */ void flush_signals(struct task_struct *t) @@ -544,7 +602,7 @@ still_pending: (info->si_code == SI_TIMER) && (info->si_sys_private); - __sigqueue_free(first); + sigqueue_free_current(first); } else { /* * Ok, it wasn't in the queue. This must be @@ -581,6 +639,8 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info) bool resched_timer = false; int signr; + WARN_ON_ONCE(tsk != current); + /* We only dequeue private signals from ourselves, we don't let * signalfd steal them */ @@ -1227,8 +1287,8 @@ int do_send_sig_info(int sig, struct siginfo *info, struct task_struct *p, * We don't want to have recursive SIGSEGV's etc, for example, * that is why we also clear SIGNAL_UNKILLABLE. */ -int -force_sig_info(int sig, struct siginfo *info, struct task_struct *t) +static int +do_force_sig_info(int sig, struct siginfo *info, struct task_struct *t) { unsigned long int flags; int ret, blocked, ignored; @@ -1257,6 +1317,39 @@ force_sig_info(int sig, struct siginfo *info, struct task_struct *t) return ret; } +int force_sig_info(int sig, struct siginfo *info, struct task_struct *t) +{ +/* + * On some archs, PREEMPT_RT has to delay sending a signal from a trap + * since it can not enable preemption, and the signal code's spin_locks + * turn into mutexes. Instead, it must set TIF_NOTIFY_RESUME which will + * send the signal on exit of the trap. + */ +#ifdef ARCH_RT_DELAYS_SIGNAL_SEND + if (in_atomic()) { + if (WARN_ON_ONCE(t != current)) + return 0; + if (WARN_ON_ONCE(t->forced_info.si_signo)) + return 0; + + if (is_si_special(info)) { + WARN_ON_ONCE(info != SEND_SIG_PRIV); + t->forced_info.si_signo = sig; + t->forced_info.si_errno = 0; + t->forced_info.si_code = SI_KERNEL; + t->forced_info.si_pid = 0; + t->forced_info.si_uid = 0; + } else { + t->forced_info = *info; + } + + set_tsk_thread_flag(t, TIF_NOTIFY_RESUME); + return 0; + } +#endif + return do_force_sig_info(sig, info, t); +} + /* * Nuke all other threads in the group. */ @@ -1673,7 +1766,8 @@ EXPORT_SYMBOL(kill_pid); */ struct sigqueue *sigqueue_alloc(void) { - struct sigqueue *q = __sigqueue_alloc(-1, current, GFP_KERNEL, 0); + /* Preallocated sigqueue objects always from the slabcache ! */ + struct sigqueue *q = __sigqueue_do_alloc(-1, current, GFP_KERNEL, 0, 1); if (q) q->flags |= SIGQUEUE_PREALLOC; @@ -2049,15 +2143,7 @@ static void ptrace_stop(int exit_code, int why, int clear_code, siginfo_t *info) if (gstop_done && ptrace_reparented(current)) do_notify_parent_cldstop(current, false, why); - /* - * Don't want to allow preemption here, because - * sys_ptrace() needs this task to be inactive. - * - * XXX: implement read_unlock_no_resched(). - */ - preempt_disable(); read_unlock(&tasklist_lock); - preempt_enable_no_resched(); freezable_schedule(); } else { /* diff --git a/kernel/softirq.c b/kernel/softirq.c index 6f584861d329..c15583162a55 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -21,11 +21,14 @@ #include <linux/freezer.h> #include <linux/kthread.h> #include <linux/rcupdate.h> +#include <linux/delay.h> #include <linux/ftrace.h> #include <linux/smp.h> #include <linux/smpboot.h> #include <linux/tick.h> +#include <linux/locallock.h> #include <linux/irq.h> +#include <linux/sched/types.h> #define CREATE_TRACE_POINTS #include <trace/events/irq.h> @@ -56,12 +59,108 @@ EXPORT_PER_CPU_SYMBOL(irq_stat); static struct softirq_action softirq_vec[NR_SOFTIRQS] __cacheline_aligned_in_smp; DEFINE_PER_CPU(struct task_struct *, ksoftirqd); +#ifdef CONFIG_PREEMPT_RT_FULL +#define TIMER_SOFTIRQS ((1 << TIMER_SOFTIRQ) | (1 << HRTIMER_SOFTIRQ)) +DEFINE_PER_CPU(struct task_struct *, ktimer_softirqd); +#endif const char * const softirq_to_name[NR_SOFTIRQS] = { "HI", "TIMER", "NET_TX", "NET_RX", "BLOCK", "IRQ_POLL", "TASKLET", "SCHED", "HRTIMER", "RCU" }; +#ifdef CONFIG_NO_HZ_COMMON +# ifdef CONFIG_PREEMPT_RT_FULL + +struct softirq_runner { + struct task_struct *runner[NR_SOFTIRQS]; +}; + +static DEFINE_PER_CPU(struct softirq_runner, softirq_runners); + +static inline void softirq_set_runner(unsigned int sirq) +{ + struct softirq_runner *sr = this_cpu_ptr(&softirq_runners); + + sr->runner[sirq] = current; +} + +static inline void softirq_clr_runner(unsigned int sirq) +{ + struct softirq_runner *sr = this_cpu_ptr(&softirq_runners); + + sr->runner[sirq] = NULL; +} + +/* + * On preempt-rt a softirq running context might be blocked on a + * lock. There might be no other runnable task on this CPU because the + * lock owner runs on some other CPU. So we have to go into idle with + * the pending bit set. Therefor we need to check this otherwise we + * warn about false positives which confuses users and defeats the + * whole purpose of this test. + * + * This code is called with interrupts disabled. + */ +void softirq_check_pending_idle(void) +{ + static int rate_limit; + struct softirq_runner *sr = this_cpu_ptr(&softirq_runners); + u32 warnpending; + int i; + + if (rate_limit >= 10) + return; + + warnpending = local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK; + for (i = 0; i < NR_SOFTIRQS; i++) { + struct task_struct *tsk = sr->runner[i]; + + /* + * The wakeup code in rtmutex.c wakes up the task + * _before_ it sets pi_blocked_on to NULL under + * tsk->pi_lock. So we need to check for both: state + * and pi_blocked_on. + */ + if (tsk) { + raw_spin_lock(&tsk->pi_lock); + if (tsk->pi_blocked_on || tsk->state == TASK_RUNNING) { + /* Clear all bits pending in that task */ + warnpending &= ~(tsk->softirqs_raised); + warnpending &= ~(1 << i); + } + raw_spin_unlock(&tsk->pi_lock); + } + } + + if (warnpending) { + printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n", + warnpending); + rate_limit++; + } +} +# else +/* + * On !PREEMPT_RT we just printk rate limited: + */ +void softirq_check_pending_idle(void) +{ + static int rate_limit; + + if (rate_limit < 10 && + (local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK)) { + printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n", + local_softirq_pending()); + rate_limit++; + } +} +# endif + +#else /* !CONFIG_NO_HZ_COMMON */ +static inline void softirq_set_runner(unsigned int sirq) { } +static inline void softirq_clr_runner(unsigned int sirq) { } +#endif + /* * we cannot loop indefinitely here to avoid userspace starvation, * but we also don't want to introduce a worst case 1/HZ latency @@ -77,6 +176,38 @@ static void wakeup_softirqd(void) wake_up_process(tsk); } +#ifdef CONFIG_PREEMPT_RT_FULL +static void wakeup_timer_softirqd(void) +{ + /* Interrupts are disabled: no need to stop preemption */ + struct task_struct *tsk = __this_cpu_read(ktimer_softirqd); + + if (tsk && tsk->state != TASK_RUNNING) + wake_up_process(tsk); +} +#endif + +static void handle_softirq(unsigned int vec_nr) +{ + struct softirq_action *h = softirq_vec + vec_nr; + int prev_count; + + prev_count = preempt_count(); + + kstat_incr_softirqs_this_cpu(vec_nr); + + trace_softirq_entry(vec_nr); + h->action(h); + trace_softirq_exit(vec_nr); + if (unlikely(prev_count != preempt_count())) { + pr_err("huh, entered softirq %u %s %p with preempt_count %08x, exited with %08x?\n", + vec_nr, softirq_to_name[vec_nr], h->action, + prev_count, preempt_count()); + preempt_count_set(prev_count); + } +} + +#ifndef CONFIG_PREEMPT_RT_FULL /* * If ksoftirqd is scheduled, we do not want to process pending softirqs * right now. Let ksoftirqd handle this at its own rate, to get fairness, @@ -92,6 +223,47 @@ static bool ksoftirqd_running(unsigned long pending) return tsk && (tsk->state == TASK_RUNNING); } +static inline int ksoftirqd_softirq_pending(void) +{ + return local_softirq_pending(); +} + +static void handle_pending_softirqs(u32 pending) +{ + struct softirq_action *h = softirq_vec; + int softirq_bit; + + local_irq_enable(); + + h = softirq_vec; + + while ((softirq_bit = ffs(pending))) { + unsigned int vec_nr; + + h += softirq_bit - 1; + vec_nr = h - softirq_vec; + handle_softirq(vec_nr); + + h++; + pending >>= softirq_bit; + } + + rcu_bh_qs(); + local_irq_disable(); +} + +static void run_ksoftirqd(unsigned int cpu) +{ + local_irq_disable(); + if (ksoftirqd_softirq_pending()) { + __do_softirq(); + local_irq_enable(); + cond_resched(); + return; + } + local_irq_enable(); +} + /* * preempt_count and SOFTIRQ_OFFSET usage: * - preempt_count is changed by SOFTIRQ_OFFSET on entering or leaving @@ -251,10 +423,8 @@ asmlinkage __visible void __softirq_entry __do_softirq(void) unsigned long end = jiffies + MAX_SOFTIRQ_TIME; unsigned long old_flags = current->flags; int max_restart = MAX_SOFTIRQ_RESTART; - struct softirq_action *h; bool in_hardirq; __u32 pending; - int softirq_bit; /* * Mask out PF_MEMALLOC s current task context is borrowed for the @@ -273,36 +443,7 @@ restart: /* Reset the pending bitmask before enabling irqs */ set_softirq_pending(0); - local_irq_enable(); - - h = softirq_vec; - - while ((softirq_bit = ffs(pending))) { - unsigned int vec_nr; - int prev_count; - - h += softirq_bit - 1; - - vec_nr = h - softirq_vec; - prev_count = preempt_count(); - - kstat_incr_softirqs_this_cpu(vec_nr); - - trace_softirq_entry(vec_nr); - h->action(h); - trace_softirq_exit(vec_nr); - if (unlikely(prev_count != preempt_count())) { - pr_err("huh, entered softirq %u %s %p with preempt_count %08x, exited with %08x?\n", - vec_nr, softirq_to_name[vec_nr], h->action, - prev_count, preempt_count()); - preempt_count_set(prev_count); - } - h++; - pending >>= softirq_bit; - } - - rcu_bh_qs(); - local_irq_disable(); + handle_pending_softirqs(pending); pending = local_softirq_pending(); if (pending) { @@ -339,6 +480,309 @@ asmlinkage __visible void do_softirq(void) } /* + * This function must run with irqs disabled! + */ +void raise_softirq_irqoff(unsigned int nr) +{ + __raise_softirq_irqoff(nr); + + /* + * If we're in an interrupt or softirq, we're done + * (this also catches softirq-disabled code). We will + * actually run the softirq once we return from + * the irq or softirq. + * + * Otherwise we wake up ksoftirqd to make sure we + * schedule the softirq soon. + */ + if (!in_interrupt()) + wakeup_softirqd(); +} + +void __raise_softirq_irqoff(unsigned int nr) +{ + trace_softirq_raise(nr); + or_softirq_pending(1UL << nr); +} + +static inline void local_bh_disable_nort(void) { local_bh_disable(); } +static inline void _local_bh_enable_nort(void) { _local_bh_enable(); } +static void ksoftirqd_set_sched_params(unsigned int cpu) { } + +#else /* !PREEMPT_RT_FULL */ + +/* + * On RT we serialize softirq execution with a cpu local lock per softirq + */ +static DEFINE_PER_CPU(struct local_irq_lock [NR_SOFTIRQS], local_softirq_locks); + +void __init softirq_early_init(void) +{ + int i; + + for (i = 0; i < NR_SOFTIRQS; i++) + local_irq_lock_init(local_softirq_locks[i]); +} + +static void lock_softirq(int which) +{ + local_lock(local_softirq_locks[which]); +} + +static void unlock_softirq(int which) +{ + local_unlock(local_softirq_locks[which]); +} + +static void do_single_softirq(int which) +{ + unsigned long old_flags = current->flags; + + current->flags &= ~PF_MEMALLOC; + vtime_account_irq_enter(current); + current->flags |= PF_IN_SOFTIRQ; + lockdep_softirq_enter(); + local_irq_enable(); + handle_softirq(which); + local_irq_disable(); + lockdep_softirq_exit(); + current->flags &= ~PF_IN_SOFTIRQ; + vtime_account_irq_enter(current); + current_restore_flags(old_flags, PF_MEMALLOC); +} + +/* + * Called with interrupts disabled. Process softirqs which were raised + * in current context (or on behalf of ksoftirqd). + */ +static void do_current_softirqs(void) +{ + while (current->softirqs_raised) { + int i = __ffs(current->softirqs_raised); + unsigned int pending, mask = (1U << i); + + current->softirqs_raised &= ~mask; + local_irq_enable(); + + /* + * If the lock is contended, we boost the owner to + * process the softirq or leave the critical section + * now. + */ + lock_softirq(i); + local_irq_disable(); + softirq_set_runner(i); + /* + * Check with the local_softirq_pending() bits, + * whether we need to process this still or if someone + * else took care of it. + */ + pending = local_softirq_pending(); + if (pending & mask) { + set_softirq_pending(pending & ~mask); + do_single_softirq(i); + } + softirq_clr_runner(i); + WARN_ON(current->softirq_nestcnt != 1); + local_irq_enable(); + unlock_softirq(i); + local_irq_disable(); + } +} + +void __local_bh_disable(void) +{ + if (++current->softirq_nestcnt == 1) + migrate_disable(); +} +EXPORT_SYMBOL(__local_bh_disable); + +void __local_bh_enable(void) +{ + if (WARN_ON(current->softirq_nestcnt == 0)) + return; + + local_irq_disable(); + if (current->softirq_nestcnt == 1 && current->softirqs_raised) + do_current_softirqs(); + local_irq_enable(); + + if (--current->softirq_nestcnt == 0) + migrate_enable(); +} +EXPORT_SYMBOL(__local_bh_enable); + +void _local_bh_enable(void) +{ + if (WARN_ON(current->softirq_nestcnt == 0)) + return; + if (--current->softirq_nestcnt == 0) + migrate_enable(); +} +EXPORT_SYMBOL(_local_bh_enable); + +int in_serving_softirq(void) +{ + return current->flags & PF_IN_SOFTIRQ; +} +EXPORT_SYMBOL(in_serving_softirq); + +/* Called with preemption disabled */ +static void run_ksoftirqd(unsigned int cpu) +{ + local_irq_disable(); + current->softirq_nestcnt++; + + do_current_softirqs(); + current->softirq_nestcnt--; + local_irq_enable(); + cond_resched(); +} + +/* + * Called from netif_rx_ni(). Preemption enabled, but migration + * disabled. So the cpu can't go away under us. + */ +void thread_do_softirq(void) +{ + if (!in_serving_softirq() && current->softirqs_raised) { + current->softirq_nestcnt++; + do_current_softirqs(); + current->softirq_nestcnt--; + } +} + +static void do_raise_softirq_irqoff(unsigned int nr) +{ + unsigned int mask; + + mask = 1UL << nr; + + trace_softirq_raise(nr); + or_softirq_pending(mask); + + /* + * If we are not in a hard interrupt and inside a bh disabled + * region, we simply raise the flag on current. local_bh_enable() + * will make sure that the softirq is executed. Otherwise we + * delegate it to ksoftirqd. + */ + if (!in_irq() && current->softirq_nestcnt) + current->softirqs_raised |= mask; + else if (!__this_cpu_read(ksoftirqd) || !__this_cpu_read(ktimer_softirqd)) + return; + + if (mask & TIMER_SOFTIRQS) + __this_cpu_read(ktimer_softirqd)->softirqs_raised |= mask; + else + __this_cpu_read(ksoftirqd)->softirqs_raised |= mask; +} + +static void wakeup_proper_softirq(unsigned int nr) +{ + if ((1UL << nr) & TIMER_SOFTIRQS) + wakeup_timer_softirqd(); + else + wakeup_softirqd(); +} + +void __raise_softirq_irqoff(unsigned int nr) +{ + do_raise_softirq_irqoff(nr); + if (!in_irq() && !current->softirq_nestcnt) + wakeup_proper_softirq(nr); +} + +/* + * Same as __raise_softirq_irqoff() but will process them in ksoftirqd + */ +void __raise_softirq_irqoff_ksoft(unsigned int nr) +{ + unsigned int mask; + + if (WARN_ON_ONCE(!__this_cpu_read(ksoftirqd) || + !__this_cpu_read(ktimer_softirqd))) + return; + mask = 1UL << nr; + + trace_softirq_raise(nr); + or_softirq_pending(mask); + if (mask & TIMER_SOFTIRQS) + __this_cpu_read(ktimer_softirqd)->softirqs_raised |= mask; + else + __this_cpu_read(ksoftirqd)->softirqs_raised |= mask; + wakeup_proper_softirq(nr); +} + +/* + * This function must run with irqs disabled! + */ +void raise_softirq_irqoff(unsigned int nr) +{ + do_raise_softirq_irqoff(nr); + + /* + * If we're in an hard interrupt we let irq return code deal + * with the wakeup of ksoftirqd. + */ + if (in_irq()) + return; + /* + * If we are in thread context but outside of a bh disabled + * region, we need to wake ksoftirqd as well. + * + * CHECKME: Some of the places which do that could be wrapped + * into local_bh_disable/enable pairs. Though it's unclear + * whether this is worth the effort. To find those places just + * raise a WARN() if the condition is met. + */ + if (!current->softirq_nestcnt) + wakeup_proper_softirq(nr); +} + +static inline int ksoftirqd_softirq_pending(void) +{ + return current->softirqs_raised; +} + +static inline void local_bh_disable_nort(void) { } +static inline void _local_bh_enable_nort(void) { } + +static inline void ksoftirqd_set_sched_params(unsigned int cpu) +{ + /* Take over all but timer pending softirqs when starting */ + local_irq_disable(); + current->softirqs_raised = local_softirq_pending() & ~TIMER_SOFTIRQS; + local_irq_enable(); +} + +static inline void ktimer_softirqd_set_sched_params(unsigned int cpu) +{ + struct sched_param param = { .sched_priority = 1 }; + + sched_setscheduler(current, SCHED_FIFO, ¶m); + + /* Take over timer pending softirqs when starting */ + local_irq_disable(); + current->softirqs_raised = local_softirq_pending() & TIMER_SOFTIRQS; + local_irq_enable(); +} + +static inline void ktimer_softirqd_clr_sched_params(unsigned int cpu, + bool online) +{ + struct sched_param param = { .sched_priority = 0 }; + + sched_setscheduler(current, SCHED_NORMAL, ¶m); +} + +static int ktimer_softirqd_should_run(unsigned int cpu) +{ + return current->softirqs_raised; +} + +#endif /* PREEMPT_RT_FULL */ +/* * Enter an interrupt context. */ void irq_enter(void) @@ -349,9 +793,9 @@ void irq_enter(void) * Prevent raise_softirq from needlessly waking up ksoftirqd * here, as softirq will be serviced on return from interrupt. */ - local_bh_disable(); + local_bh_disable_nort(); tick_irq_enter(); - _local_bh_enable(); + _local_bh_enable_nort(); } __irq_enter(); @@ -359,6 +803,7 @@ void irq_enter(void) static inline void invoke_softirq(void) { +#ifndef CONFIG_PREEMPT_RT_FULL if (ksoftirqd_running(local_softirq_pending())) return; @@ -381,6 +826,18 @@ static inline void invoke_softirq(void) } else { wakeup_softirqd(); } +#else /* PREEMPT_RT_FULL */ + unsigned long flags; + + local_irq_save(flags); + if (__this_cpu_read(ksoftirqd) && + __this_cpu_read(ksoftirqd)->softirqs_raised) + wakeup_softirqd(); + if (__this_cpu_read(ktimer_softirqd) && + __this_cpu_read(ktimer_softirqd)->softirqs_raised) + wakeup_timer_softirqd(); + local_irq_restore(flags); +#endif } static inline void tick_irq_exit(void) @@ -416,26 +873,6 @@ void irq_exit(void) trace_hardirq_exit(); /* must be last! */ } -/* - * This function must run with irqs disabled! - */ -inline void raise_softirq_irqoff(unsigned int nr) -{ - __raise_softirq_irqoff(nr); - - /* - * If we're in an interrupt or softirq, we're done - * (this also catches softirq-disabled code). We will - * actually run the softirq once we return from - * the irq or softirq. - * - * Otherwise we wake up ksoftirqd to make sure we - * schedule the softirq soon. - */ - if (!in_interrupt()) - wakeup_softirqd(); -} - void raise_softirq(unsigned int nr) { unsigned long flags; @@ -445,12 +882,6 @@ void raise_softirq(unsigned int nr) local_irq_restore(flags); } -void __raise_softirq_irqoff(unsigned int nr) -{ - trace_softirq_raise(nr); - or_softirq_pending(1UL << nr); -} - void open_softirq(int nr, void (*action)(struct softirq_action *)) { softirq_vec[nr].action = action; @@ -475,11 +906,38 @@ static void __tasklet_schedule_common(struct tasklet_struct *t, unsigned long flags; local_irq_save(flags); + if (!tasklet_trylock(t)) { + local_irq_restore(flags); + return; + } + head = this_cpu_ptr(headp); - t->next = NULL; - *head->tail = t; - head->tail = &(t->next); - raise_softirq_irqoff(softirq_nr); +again: + /* We may have been preempted before tasklet_trylock + * and __tasklet_action may have already run. + * So double check the sched bit while the takslet + * is locked before adding it to the list. + */ + if (test_bit(TASKLET_STATE_SCHED, &t->state)) { + t->next = NULL; + *head->tail = t; + head->tail = &(t->next); + raise_softirq_irqoff(softirq_nr); + tasklet_unlock(t); + } else { + /* This is subtle. If we hit the corner case above + * It is possible that we get preempted right here, + * and another task has successfully called + * tasklet_schedule(), then this function, and + * failed on the trylock. Thus we must be sure + * before releasing the tasklet lock, that the + * SCHED_BIT is clear. Otherwise the tasklet + * may get its SCHED_BIT set, but not added to the + * list + */ + if (!tasklet_tryunlock(t)) + goto again; + } local_irq_restore(flags); } @@ -497,11 +955,21 @@ void __tasklet_hi_schedule(struct tasklet_struct *t) } EXPORT_SYMBOL(__tasklet_hi_schedule); +void tasklet_enable(struct tasklet_struct *t) +{ + if (!atomic_dec_and_test(&t->count)) + return; + if (test_and_clear_bit(TASKLET_STATE_PENDING, &t->state)) + tasklet_schedule(t); +} +EXPORT_SYMBOL(tasklet_enable); + static void tasklet_action_common(struct softirq_action *a, struct tasklet_head *tl_head, unsigned int softirq_nr) { struct tasklet_struct *list; + int loops = 1000000; local_irq_disable(); list = tl_head->head; @@ -513,25 +981,56 @@ static void tasklet_action_common(struct softirq_action *a, struct tasklet_struct *t = list; list = list->next; + /* + * Should always succeed - after a tasklist got on the + * list (after getting the SCHED bit set from 0 to 1), + * nothing but the tasklet softirq it got queued to can + * lock it: + */ + if (!tasklet_trylock(t)) { + WARN_ON(1); + continue; + } + + t->next = NULL; - if (tasklet_trylock(t)) { - if (!atomic_read(&t->count)) { - if (!test_and_clear_bit(TASKLET_STATE_SCHED, - &t->state)) - BUG(); - t->func(t->data); + if (unlikely(atomic_read(&t->count))) { +out_disabled: + /* implicit unlock: */ + wmb(); + t->state = TASKLET_STATEF_PENDING; + continue; + } + /* + * After this point on the tasklet might be rescheduled + * on another CPU, but it can only be added to another + * CPU's tasklet list if we unlock the tasklet (which we + * dont do yet). + */ + if (!test_and_clear_bit(TASKLET_STATE_SCHED, &t->state)) + WARN_ON(1); +again: + t->func(t->data); + + while (!tasklet_tryunlock(t)) { + /* + * If it got disabled meanwhile, bail out: + */ + if (atomic_read(&t->count)) + goto out_disabled; + /* + * If it got scheduled meanwhile, re-execute + * the tasklet function: + */ + if (test_and_clear_bit(TASKLET_STATE_SCHED, &t->state)) + goto again; + if (!--loops) { + printk("hm, tasklet state: %08lx\n", t->state); + WARN_ON(1); tasklet_unlock(t); - continue; + break; } - tasklet_unlock(t); } - - local_irq_disable(); - t->next = NULL; - *tl_head->tail = t; - tl_head->tail = &t->next; - __raise_softirq_irqoff(softirq_nr); - local_irq_enable(); } } @@ -563,7 +1062,7 @@ void tasklet_kill(struct tasklet_struct *t) while (test_and_set_bit(TASKLET_STATE_SCHED, &t->state)) { do { - yield(); + msleep(1); } while (test_bit(TASKLET_STATE_SCHED, &t->state)); } tasklet_unlock_wait(t); @@ -637,25 +1136,26 @@ void __init softirq_init(void) open_softirq(HI_SOFTIRQ, tasklet_hi_action); } -static int ksoftirqd_should_run(unsigned int cpu) -{ - return local_softirq_pending(); -} - -static void run_ksoftirqd(unsigned int cpu) +#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL) +void tasklet_unlock_wait(struct tasklet_struct *t) { - local_irq_disable(); - if (local_softirq_pending()) { + while (test_bit(TASKLET_STATE_RUN, &(t)->state)) { /* - * We can safely run softirq on inline stack, as we are not deep - * in the task stack here. + * Hack for now to avoid this busy-loop: */ - __do_softirq(); - local_irq_enable(); - cond_resched(); - return; +#ifdef CONFIG_PREEMPT_RT_FULL + msleep(1); +#else + barrier(); +#endif } - local_irq_enable(); +} +EXPORT_SYMBOL(tasklet_unlock_wait); +#endif + +static int ksoftirqd_should_run(unsigned int cpu) +{ + return ksoftirqd_softirq_pending(); } #ifdef CONFIG_HOTPLUG_CPU @@ -722,17 +1222,31 @@ static int takeover_tasklets(unsigned int cpu) static struct smp_hotplug_thread softirq_threads = { .store = &ksoftirqd, + .setup = ksoftirqd_set_sched_params, .thread_should_run = ksoftirqd_should_run, .thread_fn = run_ksoftirqd, .thread_comm = "ksoftirqd/%u", }; +#ifdef CONFIG_PREEMPT_RT_FULL +static struct smp_hotplug_thread softirq_timer_threads = { + .store = &ktimer_softirqd, + .setup = ktimer_softirqd_set_sched_params, + .cleanup = ktimer_softirqd_clr_sched_params, + .thread_should_run = ktimer_softirqd_should_run, + .thread_fn = run_ksoftirqd, + .thread_comm = "ktimersoftd/%u", +}; +#endif + static __init int spawn_ksoftirqd(void) { cpuhp_setup_state_nocalls(CPUHP_SOFTIRQ_DEAD, "softirq:dead", NULL, takeover_tasklets); BUG_ON(smpboot_register_percpu_thread(&softirq_threads)); - +#ifdef CONFIG_PREEMPT_RT_FULL + BUG_ON(smpboot_register_percpu_thread(&softirq_timer_threads)); +#endif return 0; } early_initcall(spawn_ksoftirqd); diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index fdeb9bc6affb..966708e8ce14 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -436,7 +436,7 @@ int alarm_cancel(struct alarm *alarm) int ret = alarm_try_to_cancel(alarm); if (ret >= 0) return ret; - cpu_relax(); + hrtimer_wait_for_timer(&alarm->timer); } } EXPORT_SYMBOL_GPL(alarm_cancel); diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 3e93c54bd3a1..1ea0244fc32f 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -730,6 +730,29 @@ static void hrtimer_switch_to_hres(void) retrigger_next_event(NULL); } +#ifdef CONFIG_PREEMPT_RT_FULL + +static struct swork_event clock_set_delay_work; + +static void run_clock_set_delay(struct swork_event *event) +{ + clock_was_set(); +} + +void clock_was_set_delayed(void) +{ + swork_queue(&clock_set_delay_work); +} + +static __init int create_clock_set_delay_thread(void) +{ + WARN_ON(swork_get()); + INIT_SWORK(&clock_set_delay_work, run_clock_set_delay); + return 0; +} +early_initcall(create_clock_set_delay_thread); +#else /* PREEMPT_RT_FULL */ + static void clock_was_set_work(struct work_struct *work) { clock_was_set(); @@ -745,6 +768,7 @@ void clock_was_set_delayed(void) { schedule_work(&hrtimer_work); } +#endif #else @@ -939,6 +963,33 @@ u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval) } EXPORT_SYMBOL_GPL(hrtimer_forward); +#ifdef CONFIG_PREEMPT_RT_BASE +# define wake_up_timer_waiters(b) wake_up(&(b)->wait) + +/** + * hrtimer_wait_for_timer - Wait for a running timer + * + * @timer: timer to wait for + * + * The function waits in case the timers callback function is + * currently executed on the waitqueue of the timer base. The + * waitqueue is woken up after the timer callback function has + * finished execution. + */ +void hrtimer_wait_for_timer(const struct hrtimer *timer) +{ + struct hrtimer_clock_base *base = timer->base; + + if (base && base->cpu_base && + base->index >= HRTIMER_BASE_MONOTONIC_SOFT) + wait_event(base->cpu_base->wait, + !(hrtimer_callback_running(timer))); +} + +#else +# define wake_up_timer_waiters(b) do { } while (0) +#endif + /* * enqueue_hrtimer - internal function to (re)start a timer * @@ -1108,7 +1159,9 @@ void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, * Check whether the HRTIMER_MODE_SOFT bit and hrtimer.is_soft * match. */ +#ifndef CONFIG_PREEMPT_RT_BASE WARN_ON_ONCE(!(mode & HRTIMER_MODE_SOFT) ^ !timer->is_soft); +#endif base = lock_hrtimer_base(timer, &flags); @@ -1171,7 +1224,7 @@ int hrtimer_cancel(struct hrtimer *timer) if (ret >= 0) return ret; - cpu_relax(); + hrtimer_wait_for_timer(timer); } } EXPORT_SYMBOL_GPL(hrtimer_cancel); @@ -1268,10 +1321,17 @@ static inline int hrtimer_clockid_to_base(clockid_t clock_id) static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id, enum hrtimer_mode mode) { - bool softtimer = !!(mode & HRTIMER_MODE_SOFT); - int base = softtimer ? HRTIMER_MAX_CLOCK_BASES / 2 : 0; + bool softtimer; + int base; struct hrtimer_cpu_base *cpu_base; + softtimer = !!(mode & HRTIMER_MODE_SOFT); +#ifdef CONFIG_PREEMPT_RT_FULL + if (!softtimer && !(mode & HRTIMER_MODE_HARD)) + softtimer = true; +#endif + base = softtimer ? HRTIMER_MAX_CLOCK_BASES / 2 : 0; + memset(timer, 0, sizeof(struct hrtimer)); cpu_base = raw_cpu_ptr(&hrtimer_bases); @@ -1477,6 +1537,7 @@ static __latent_entropy void hrtimer_run_softirq(struct softirq_action *h) hrtimer_update_softirq_timer(cpu_base, true); raw_spin_unlock_irqrestore(&cpu_base->lock, flags); + wake_up_timer_waiters(cpu_base); } #ifdef CONFIG_HIGH_RES_TIMERS @@ -1649,13 +1710,52 @@ static enum hrtimer_restart hrtimer_wakeup(struct hrtimer *timer) return HRTIMER_NORESTART; } -void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, struct task_struct *task) +static void __hrtimer_init_sleeper(struct hrtimer_sleeper *sl, + clockid_t clock_id, + enum hrtimer_mode mode, + struct task_struct *task) { +#ifdef CONFIG_PREEMPT_RT_FULL + if (!(mode & (HRTIMER_MODE_SOFT | HRTIMER_MODE_HARD))) { + if (task_is_realtime(current) || system_state != SYSTEM_RUNNING) + mode |= HRTIMER_MODE_HARD; + else + mode |= HRTIMER_MODE_SOFT; + } +#endif + __hrtimer_init(&sl->timer, clock_id, mode); sl->timer.function = hrtimer_wakeup; sl->task = task; } + +/** + * hrtimer_init_sleeper - initialize sleeper to the given clock + * @sl: sleeper to be initialized + * @clock_id: the clock to be used + * @mode: timer mode abs/rel + * @task: the task to wake up + */ +void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, clockid_t clock_id, + enum hrtimer_mode mode, struct task_struct *task) +{ + debug_init(&sl->timer, clock_id, mode); + __hrtimer_init_sleeper(sl, clock_id, mode, task); + +} EXPORT_SYMBOL_GPL(hrtimer_init_sleeper); +#ifdef CONFIG_DEBUG_OBJECTS_TIMERS +void hrtimer_init_sleeper_on_stack(struct hrtimer_sleeper *sl, + clockid_t clock_id, + enum hrtimer_mode mode, + struct task_struct *task) +{ + debug_object_init_on_stack(&sl->timer, &hrtimer_debug_descr); + __hrtimer_init_sleeper(sl, clock_id, mode, task); +} +EXPORT_SYMBOL_GPL(hrtimer_init_sleeper_on_stack); +#endif + int nanosleep_copyout(struct restart_block *restart, struct timespec64 *ts) { switch(restart->nanosleep.type) { @@ -1679,8 +1779,6 @@ static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mod { struct restart_block *restart; - hrtimer_init_sleeper(t, current); - do { set_current_state(TASK_INTERRUPTIBLE); hrtimer_start_expires(&t->timer, mode); @@ -1717,10 +1815,9 @@ static long __sched hrtimer_nanosleep_restart(struct restart_block *restart) struct hrtimer_sleeper t; int ret; - hrtimer_init_on_stack(&t.timer, restart->nanosleep.clockid, - HRTIMER_MODE_ABS); + hrtimer_init_sleeper_on_stack(&t, restart->nanosleep.clockid, + HRTIMER_MODE_ABS, current); hrtimer_set_expires_tv64(&t.timer, restart->nanosleep.expires); - ret = do_nanosleep(&t, HRTIMER_MODE_ABS); destroy_hrtimer_on_stack(&t.timer); return ret; @@ -1738,7 +1835,7 @@ long hrtimer_nanosleep(const struct timespec64 *rqtp, if (dl_task(current) || rt_task(current)) slack = 0; - hrtimer_init_on_stack(&t.timer, clockid, mode); + hrtimer_init_sleeper_on_stack(&t, clockid, mode, current); hrtimer_set_expires_range_ns(&t.timer, timespec64_to_ktime(*rqtp), slack); ret = do_nanosleep(&t, mode); if (ret != -ERESTART_RESTARTBLOCK) @@ -1798,6 +1895,27 @@ COMPAT_SYSCALL_DEFINE2(nanosleep, struct compat_timespec __user *, rqtp, } #endif +#ifdef CONFIG_PREEMPT_RT_FULL +/* + * Sleep for 1 ms in hope whoever holds what we want will let it go. + */ +void cpu_chill(void) +{ + ktime_t chill_time; + unsigned int freeze_flag = current->flags & PF_NOFREEZE; + + chill_time = ktime_set(0, NSEC_PER_MSEC); + set_current_state(TASK_UNINTERRUPTIBLE); + current->flags |= PF_NOFREEZE; + sleeping_lock_inc(); + schedule_hrtimeout(&chill_time, HRTIMER_MODE_REL_HARD); + sleeping_lock_dec(); + if (!freeze_flag) + current->flags &= ~PF_NOFREEZE; +} +EXPORT_SYMBOL(cpu_chill); +#endif + /* * Functions related to boot-time initialization: */ @@ -1819,6 +1937,9 @@ int hrtimers_prepare_cpu(unsigned int cpu) cpu_base->softirq_next_timer = NULL; cpu_base->expires_next = KTIME_MAX; cpu_base->softirq_expires_next = KTIME_MAX; +#ifdef CONFIG_PREEMPT_RT_BASE + init_waitqueue_head(&cpu_base->wait); +#endif return 0; } @@ -1937,11 +2058,9 @@ schedule_hrtimeout_range_clock(ktime_t *expires, u64 delta, return -EINTR; } - hrtimer_init_on_stack(&t.timer, clock_id, mode); + hrtimer_init_sleeper_on_stack(&t, clock_id, mode, current); hrtimer_set_expires_range_ns(&t.timer, *expires, delta); - hrtimer_init_sleeper(&t, current); - hrtimer_start_expires(&t.timer, mode); if (likely(t.task)) diff --git a/kernel/time/itimer.c b/kernel/time/itimer.c index f26acef5d7b4..760f38528365 100644 --- a/kernel/time/itimer.c +++ b/kernel/time/itimer.c @@ -214,6 +214,7 @@ again: /* We are sharing ->siglock with it_real_fn() */ if (hrtimer_try_to_cancel(timer) < 0) { spin_unlock_irq(&tsk->sighand->siglock); + hrtimer_wait_for_timer(&tsk->signal->real_timer); goto again; } expires = timeval_to_ktime(value->it_value); diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c index 497719127bf9..62acb8914c9e 100644 --- a/kernel/time/jiffies.c +++ b/kernel/time/jiffies.c @@ -74,7 +74,8 @@ static struct clocksource clocksource_jiffies = { .max_cycles = 10, }; -__cacheline_aligned_in_smp DEFINE_SEQLOCK(jiffies_lock); +__cacheline_aligned_in_smp DEFINE_RAW_SPINLOCK(jiffies_lock); +__cacheline_aligned_in_smp seqcount_t jiffies_seq; #if (BITS_PER_LONG < 64) u64 get_jiffies_64(void) @@ -83,9 +84,9 @@ u64 get_jiffies_64(void) u64 ret; do { - seq = read_seqbegin(&jiffies_lock); + seq = read_seqcount_begin(&jiffies_seq); ret = jiffies_64; - } while (read_seqretry(&jiffies_lock, seq)); + } while (read_seqcount_retry(&jiffies_seq, seq)); return ret; } EXPORT_SYMBOL(get_jiffies_64); diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index 294d7b65af33..93376a9ff7bd 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -3,8 +3,10 @@ * Implement CPU time clocks for the POSIX clock interface. */ +#include <uapi/linux/sched/types.h> #include <linux/sched/signal.h> #include <linux/sched/cputime.h> +#include <linux/sched/rt.h> #include <linux/posix-timers.h> #include <linux/errno.h> #include <linux/math64.h> @@ -15,6 +17,7 @@ #include <linux/workqueue.h> #include <linux/compat.h> #include <linux/sched/deadline.h> +#include <linux/smpboot.h> #include "posix-timers.h" @@ -1135,14 +1138,12 @@ static inline int fastpath_timer_check(struct task_struct *tsk) * already updated our counts. We need to check if any timers fire now. * Interrupts are disabled. */ -void run_posix_cpu_timers(struct task_struct *tsk) +static void __run_posix_cpu_timers(struct task_struct *tsk) { LIST_HEAD(firing); struct k_itimer *timer, *next; unsigned long flags; - lockdep_assert_irqs_disabled(); - /* * The fast path checks that there are no expired thread or thread * group timers. If that's so, just return. @@ -1195,6 +1196,153 @@ void run_posix_cpu_timers(struct task_struct *tsk) } } +#ifdef CONFIG_PREEMPT_RT_BASE +#include <linux/kthread.h> +#include <linux/cpu.h> +DEFINE_PER_CPU(struct task_struct *, posix_timer_task); +DEFINE_PER_CPU(struct task_struct *, posix_timer_tasklist); +DEFINE_PER_CPU(bool, posix_timer_th_active); + +static void posix_cpu_kthread_fn(unsigned int cpu) +{ + struct task_struct *tsk = NULL; + struct task_struct *next = NULL; + + BUG_ON(per_cpu(posix_timer_task, cpu) != current); + + /* grab task list */ + raw_local_irq_disable(); + tsk = per_cpu(posix_timer_tasklist, cpu); + per_cpu(posix_timer_tasklist, cpu) = NULL; + raw_local_irq_enable(); + + /* its possible the list is empty, just return */ + if (!tsk) + return; + + /* Process task list */ + while (1) { + /* save next */ + next = tsk->posix_timer_list; + + /* run the task timers, clear its ptr and + * unreference it + */ + __run_posix_cpu_timers(tsk); + tsk->posix_timer_list = NULL; + put_task_struct(tsk); + + /* check if this is the last on the list */ + if (next == tsk) + break; + tsk = next; + } +} + +static inline int __fastpath_timer_check(struct task_struct *tsk) +{ + /* tsk == current, ensure it is safe to use ->signal/sighand */ + if (unlikely(tsk->exit_state)) + return 0; + + if (!task_cputime_zero(&tsk->cputime_expires)) + return 1; + + if (!task_cputime_zero(&tsk->signal->cputime_expires)) + return 1; + + return 0; +} + +void run_posix_cpu_timers(struct task_struct *tsk) +{ + unsigned int cpu = smp_processor_id(); + struct task_struct *tasklist; + + BUG_ON(!irqs_disabled()); + + if (per_cpu(posix_timer_th_active, cpu) != true) + return; + + /* get per-cpu references */ + tasklist = per_cpu(posix_timer_tasklist, cpu); + + /* check to see if we're already queued */ + if (!tsk->posix_timer_list && __fastpath_timer_check(tsk)) { + get_task_struct(tsk); + if (tasklist) { + tsk->posix_timer_list = tasklist; + } else { + /* + * The list is terminated by a self-pointing + * task_struct + */ + tsk->posix_timer_list = tsk; + } + per_cpu(posix_timer_tasklist, cpu) = tsk; + + wake_up_process(per_cpu(posix_timer_task, cpu)); + } +} + +static int posix_cpu_kthread_should_run(unsigned int cpu) +{ + return __this_cpu_read(posix_timer_tasklist) != NULL; +} + +static void posix_cpu_kthread_park(unsigned int cpu) +{ + this_cpu_write(posix_timer_th_active, false); +} + +static void posix_cpu_kthread_unpark(unsigned int cpu) +{ + this_cpu_write(posix_timer_th_active, true); +} + +static void posix_cpu_kthread_setup(unsigned int cpu) +{ + struct sched_param sp; + + sp.sched_priority = MAX_RT_PRIO - 1; + sched_setscheduler_nocheck(current, SCHED_FIFO, &sp); + posix_cpu_kthread_unpark(cpu); +} + +static struct smp_hotplug_thread posix_cpu_thread = { + .store = &posix_timer_task, + .thread_should_run = posix_cpu_kthread_should_run, + .thread_fn = posix_cpu_kthread_fn, + .thread_comm = "posixcputmr/%u", + .setup = posix_cpu_kthread_setup, + .park = posix_cpu_kthread_park, + .unpark = posix_cpu_kthread_unpark, +}; + +static int __init posix_cpu_thread_init(void) +{ + /* Start one for boot CPU. */ + unsigned long cpu; + int ret; + + /* init the per-cpu posix_timer_tasklets */ + for_each_possible_cpu(cpu) + per_cpu(posix_timer_tasklist, cpu) = NULL; + + ret = smpboot_register_percpu_thread(&posix_cpu_thread); + WARN_ON(ret); + + return 0; +} +early_initcall(posix_cpu_thread_init); +#else /* CONFIG_PREEMPT_RT_BASE */ +void run_posix_cpu_timers(struct task_struct *tsk) +{ + lockdep_assert_irqs_disabled(); + __run_posix_cpu_timers(tsk); +} +#endif /* CONFIG_PREEMPT_RT_BASE */ + /* * Set one of the process-wide special case CPU timers or RLIMIT_CPU. * The tsk->sighand->siglock must be held by the caller. diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index 0e17fda5cb8a..5cd0626714a7 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -475,7 +475,7 @@ static struct k_itimer * alloc_posix_timer(void) static void k_itimer_rcu_free(struct rcu_head *head) { - struct k_itimer *tmr = container_of(head, struct k_itimer, it.rcu); + struct k_itimer *tmr = container_of(head, struct k_itimer, rcu); kmem_cache_free(posix_timers_cache, tmr); } @@ -492,7 +492,7 @@ static void release_posix_timer(struct k_itimer *tmr, int it_id_set) } put_pid(tmr->it_pid); sigqueue_free(tmr->sigq); - call_rcu(&tmr->it.rcu, k_itimer_rcu_free); + call_rcu(&tmr->rcu, k_itimer_rcu_free); } static int common_timer_create(struct k_itimer *new_timer) @@ -831,6 +831,22 @@ static void common_hrtimer_arm(struct k_itimer *timr, ktime_t expires, hrtimer_start_expires(timer, HRTIMER_MODE_ABS); } +/* + * Protected by RCU! + */ +static void timer_wait_for_callback(const struct k_clock *kc, struct k_itimer *timr) +{ +#ifdef CONFIG_PREEMPT_RT_FULL + if (kc->timer_arm == common_hrtimer_arm) + hrtimer_wait_for_timer(&timr->it.real.timer); + else if (kc == &alarm_clock) + hrtimer_wait_for_timer(&timr->it.alarm.alarmtimer.timer); + else + /* FIXME: Whacky hack for posix-cpu-timers */ + schedule_timeout(1); +#endif +} + static int common_hrtimer_try_to_cancel(struct k_itimer *timr) { return hrtimer_try_to_cancel(&timr->it.real.timer); @@ -895,6 +911,7 @@ retry: if (!timr) return -EINVAL; + rcu_read_lock(); kc = timr->kclock; if (WARN_ON_ONCE(!kc || !kc->timer_set)) error = -EINVAL; @@ -903,9 +920,12 @@ retry: unlock_timer(timr, flag); if (error == TIMER_RETRY) { + timer_wait_for_callback(kc, timr); old_spec64 = NULL; // We already got the old time... + rcu_read_unlock(); goto retry; } + rcu_read_unlock(); return error; } @@ -987,10 +1007,15 @@ retry_delete: if (!timer) return -EINVAL; + rcu_read_lock(); if (timer_delete_hook(timer) == TIMER_RETRY) { unlock_timer(timer, flags); + timer_wait_for_callback(clockid_to_kclock(timer->it_clock), + timer); + rcu_read_unlock(); goto retry_delete; } + rcu_read_unlock(); spin_lock(¤t->sighand->siglock); list_del(&timer->list); @@ -1016,8 +1041,18 @@ static void itimer_delete(struct k_itimer *timer) retry_delete: spin_lock_irqsave(&timer->it_lock, flags); + /* On RT we can race with a deletion */ + if (!timer->it_signal) { + unlock_timer(timer, flags); + return; + } + if (timer_delete_hook(timer) == TIMER_RETRY) { + rcu_read_lock(); unlock_timer(timer, flags); + timer_wait_for_callback(clockid_to_kclock(timer->it_clock), + timer); + rcu_read_unlock(); goto retry_delete; } list_del(&timer->list); diff --git a/kernel/time/tick-broadcast-hrtimer.c b/kernel/time/tick-broadcast-hrtimer.c index 58045eb976c3..f0a34afbc252 100644 --- a/kernel/time/tick-broadcast-hrtimer.c +++ b/kernel/time/tick-broadcast-hrtimer.c @@ -106,7 +106,7 @@ static enum hrtimer_restart bc_handler(struct hrtimer *t) void tick_setup_hrtimer_broadcast(void) { - hrtimer_init(&bctimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); + hrtimer_init(&bctimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD); bctimer.function = bc_handler; clockevents_register_device(&ce_broadcast_hrtimer); } diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index a02e0f6b287c..32f5101f07ce 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -79,13 +79,15 @@ int tick_is_oneshot_available(void) static void tick_periodic(int cpu) { if (tick_do_timer_cpu == cpu) { - write_seqlock(&jiffies_lock); + raw_spin_lock(&jiffies_lock); + write_seqcount_begin(&jiffies_seq); /* Keep track of the next tick event */ tick_next_period = ktime_add(tick_next_period, tick_period); do_timer(1); - write_sequnlock(&jiffies_lock); + write_seqcount_end(&jiffies_seq); + raw_spin_unlock(&jiffies_lock); update_wall_time(); } @@ -157,9 +159,9 @@ void tick_setup_periodic(struct clock_event_device *dev, int broadcast) ktime_t next; do { - seq = read_seqbegin(&jiffies_lock); + seq = read_seqcount_begin(&jiffies_seq); next = tick_next_period; - } while (read_seqretry(&jiffies_lock, seq)); + } while (read_seqcount_retry(&jiffies_seq, seq)); clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT); diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 5b33e2f5c0ed..da4a3f8feb56 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -67,7 +67,8 @@ static void tick_do_update_jiffies64(ktime_t now) return; /* Reevaluate with jiffies_lock held */ - write_seqlock(&jiffies_lock); + raw_spin_lock(&jiffies_lock); + write_seqcount_begin(&jiffies_seq); delta = ktime_sub(now, last_jiffies_update); if (delta >= tick_period) { @@ -90,10 +91,12 @@ static void tick_do_update_jiffies64(ktime_t now) /* Keep the tick_next_period variable up to date */ tick_next_period = ktime_add(last_jiffies_update, tick_period); } else { - write_sequnlock(&jiffies_lock); + write_seqcount_end(&jiffies_seq); + raw_spin_unlock(&jiffies_lock); return; } - write_sequnlock(&jiffies_lock); + write_seqcount_end(&jiffies_seq); + raw_spin_unlock(&jiffies_lock); update_wall_time(); } @@ -104,12 +107,14 @@ static ktime_t tick_init_jiffy_update(void) { ktime_t period; - write_seqlock(&jiffies_lock); + raw_spin_lock(&jiffies_lock); + write_seqcount_begin(&jiffies_seq); /* Did we start the jiffies update yet ? */ if (last_jiffies_update == 0) last_jiffies_update = tick_next_period; period = last_jiffies_update; - write_sequnlock(&jiffies_lock); + write_seqcount_end(&jiffies_seq); + raw_spin_unlock(&jiffies_lock); return period; } @@ -227,6 +232,7 @@ static void nohz_full_kick_func(struct irq_work *work) static DEFINE_PER_CPU(struct irq_work, nohz_full_kick_work) = { .func = nohz_full_kick_func, + .flags = IRQ_WORK_HARD_IRQ, }; /* @@ -652,10 +658,10 @@ static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu) /* Read jiffies and the time when jiffies were updated last */ do { - seq = read_seqbegin(&jiffies_lock); + seq = read_seqcount_begin(&jiffies_seq); basemono = last_jiffies_update; basejiff = jiffies; - } while (read_seqretry(&jiffies_lock, seq)); + } while (read_seqcount_retry(&jiffies_seq, seq)); ts->last_jiffies = basejiff; ts->timer_expires_base = basemono; @@ -886,14 +892,7 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts) return false; if (unlikely(local_softirq_pending() && cpu_online(cpu))) { - static int ratelimit; - - if (ratelimit < 10 && - (local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK)) { - pr_warn("NOHZ: local_softirq_pending %02x\n", - (unsigned int) local_softirq_pending()); - ratelimit++; - } + softirq_check_pending_idle(); return false; } @@ -1305,7 +1304,7 @@ void tick_setup_sched_timer(void) /* * Emulate tick processing via per-CPU hrtimers: */ - hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); + hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD); ts->sched_timer.function = tick_sched_timer; /* Get the next period (per-CPU) */ diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 58936ed15f9f..5fb17b76ec80 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -2365,8 +2365,10 @@ EXPORT_SYMBOL(hardpps); */ void xtime_update(unsigned long ticks) { - write_seqlock(&jiffies_lock); + raw_spin_lock(&jiffies_lock); + write_seqcount_begin(&jiffies_seq); do_timer(ticks); - write_sequnlock(&jiffies_lock); + write_seqcount_end(&jiffies_seq); + raw_spin_unlock(&jiffies_lock); update_wall_time(); } diff --git a/kernel/time/timekeeping.h b/kernel/time/timekeeping.h index 141ab3ab0354..099737f6f10c 100644 --- a/kernel/time/timekeeping.h +++ b/kernel/time/timekeeping.h @@ -25,7 +25,8 @@ static inline void sched_clock_resume(void) { } extern void do_timer(unsigned long ticks); extern void update_wall_time(void); -extern seqlock_t jiffies_lock; +extern raw_spinlock_t jiffies_lock; +extern seqcount_t jiffies_seq; #define CS_NAME_LEN 32 diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 786f8c014e7e..09496b7c0001 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -44,6 +44,7 @@ #include <linux/sched/debug.h> #include <linux/slab.h> #include <linux/compat.h> +#include <linux/swait.h> #include <linux/uaccess.h> #include <asm/unistd.h> @@ -197,6 +198,9 @@ EXPORT_SYMBOL(jiffies_64); struct timer_base { raw_spinlock_t lock; struct timer_list *running_timer; +#ifdef CONFIG_PREEMPT_RT_FULL + struct swait_queue_head wait_for_running_timer; +#endif unsigned long clk; unsigned long next_expiry; unsigned int cpu; @@ -213,8 +217,7 @@ static DEFINE_PER_CPU(struct timer_base, timer_bases[NR_BASES]); static DEFINE_STATIC_KEY_FALSE(timers_nohz_active); static DEFINE_MUTEX(timer_keys_mutex); -static void timer_update_keys(struct work_struct *work); -static DECLARE_WORK(timer_update_work, timer_update_keys); +static struct swork_event timer_update_swork; #ifdef CONFIG_SMP unsigned int sysctl_timer_migration = 1; @@ -232,7 +235,7 @@ static void timers_update_migration(void) static inline void timers_update_migration(void) { } #endif /* !CONFIG_SMP */ -static void timer_update_keys(struct work_struct *work) +static void timer_update_keys(struct swork_event *event) { mutex_lock(&timer_keys_mutex); timers_update_migration(); @@ -242,8 +245,16 @@ static void timer_update_keys(struct work_struct *work) void timers_update_nohz(void) { - schedule_work(&timer_update_work); + swork_queue(&timer_update_swork); +} + +static __init int hrtimer_init_thread(void) +{ + WARN_ON(swork_get()); + INIT_SWORK(&timer_update_swork, timer_update_keys); + return 0; } +early_initcall(hrtimer_init_thread); int timer_migration_handler(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, @@ -1178,6 +1189,33 @@ void add_timer_on(struct timer_list *timer, int cpu) } EXPORT_SYMBOL_GPL(add_timer_on); +#ifdef CONFIG_PREEMPT_RT_FULL +/* + * Wait for a running timer + */ +static void wait_for_running_timer(struct timer_list *timer) +{ + struct timer_base *base; + u32 tf = timer->flags; + + if (tf & TIMER_MIGRATING) + return; + + base = get_timer_base(tf); + swait_event(base->wait_for_running_timer, + base->running_timer != timer); +} + +# define wakeup_timer_waiters(b) swake_up_all(&(b)->wait_for_running_timer) +#else +static inline void wait_for_running_timer(struct timer_list *timer) +{ + cpu_relax(); +} + +# define wakeup_timer_waiters(b) do { } while (0) +#endif + /** * del_timer - deactivate a timer. * @timer: the timer to be deactivated @@ -1233,7 +1271,7 @@ int try_to_del_timer_sync(struct timer_list *timer) } EXPORT_SYMBOL(try_to_del_timer_sync); -#ifdef CONFIG_SMP +#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL) /** * del_timer_sync - deactivate a timer and wait for the handler to finish. * @timer: the timer to be deactivated @@ -1293,7 +1331,7 @@ int del_timer_sync(struct timer_list *timer) int ret = try_to_del_timer_sync(timer); if (ret >= 0) return ret; - cpu_relax(); + wait_for_running_timer(timer); } } EXPORT_SYMBOL(del_timer_sync); @@ -1354,13 +1392,16 @@ static void expire_timers(struct timer_base *base, struct hlist_head *head) fn = timer->function; - if (timer->flags & TIMER_IRQSAFE) { + if (!IS_ENABLED(CONFIG_PREEMPT_RT_FULL) && + timer->flags & TIMER_IRQSAFE) { raw_spin_unlock(&base->lock); call_timer_fn(timer, fn); + base->running_timer = NULL; raw_spin_lock(&base->lock); } else { raw_spin_unlock_irq(&base->lock); call_timer_fn(timer, fn); + base->running_timer = NULL; raw_spin_lock_irq(&base->lock); } } @@ -1681,8 +1722,8 @@ static inline void __run_timers(struct timer_base *base) while (levels--) expire_timers(base, heads + levels); } - base->running_timer = NULL; raw_spin_unlock_irq(&base->lock); + wakeup_timer_waiters(base); } /* @@ -1692,6 +1733,7 @@ static __latent_entropy void run_timer_softirq(struct softirq_action *h) { struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); + irq_work_tick_soft(); __run_timers(base); if (IS_ENABLED(CONFIG_NO_HZ_COMMON)) __run_timers(this_cpu_ptr(&timer_bases[BASE_DEF])); @@ -1927,6 +1969,9 @@ static void __init init_timer_cpu(int cpu) base->cpu = cpu; raw_spin_lock_init(&base->lock); base->clk = jiffies; +#ifdef CONFIG_PREEMPT_RT_FULL + init_swait_queue_head(&base->wait_for_running_timer); +#endif } } diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 120b19fa4a44..98406990a503 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -2136,6 +2136,7 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags, struct task_struct *tsk = current; entry->preempt_count = pc & 0xff; + entry->preempt_lazy_count = preempt_lazy_count(); entry->pid = (tsk) ? tsk->pid : 0; entry->flags = #ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT @@ -2146,8 +2147,11 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags, ((pc & NMI_MASK ) ? TRACE_FLAG_NMI : 0) | ((pc & HARDIRQ_MASK) ? TRACE_FLAG_HARDIRQ : 0) | ((pc & SOFTIRQ_OFFSET) ? TRACE_FLAG_SOFTIRQ : 0) | - (tif_need_resched() ? TRACE_FLAG_NEED_RESCHED : 0) | + (tif_need_resched_now() ? TRACE_FLAG_NEED_RESCHED : 0) | + (need_resched_lazy() ? TRACE_FLAG_NEED_RESCHED_LAZY : 0) | (test_preempt_need_resched() ? TRACE_FLAG_PREEMPT_RESCHED : 0); + + entry->migrate_disable = (tsk) ? __migrate_disabled(tsk) & 0xFF : 0; } EXPORT_SYMBOL_GPL(tracing_generic_entry_update); @@ -3346,14 +3350,17 @@ get_total_entries(struct trace_buffer *buf, static void print_lat_help_header(struct seq_file *m) { - seq_puts(m, "# _------=> CPU# \n" - "# / _-----=> irqs-off \n" - "# | / _----=> need-resched \n" - "# || / _---=> hardirq/softirq \n" - "# ||| / _--=> preempt-depth \n" - "# |||| / delay \n" - "# cmd pid ||||| time | caller \n" - "# \\ / ||||| \\ | / \n"); + seq_puts(m, "# _--------=> CPU# \n" + "# / _-------=> irqs-off \n" + "# | / _------=> need-resched \n" + "# || / _-----=> need-resched_lazy \n" + "# ||| / _----=> hardirq/softirq \n" + "# |||| / _---=> preempt-depth \n" + "# ||||| / _--=> preempt-lazy-depth\n" + "# |||||| / _-=> migrate-disable \n" + "# ||||||| / delay \n" + "# cmd pid |||||||| time | caller \n" + "# \\ / |||||||| \\ | / \n"); } static void print_event_info(struct trace_buffer *buf, struct seq_file *m) @@ -3391,15 +3398,17 @@ static void print_func_help_header_irq(struct trace_buffer *buf, struct seq_file tgid ? tgid_space : space); seq_printf(m, "# %s / _----=> need-resched\n", tgid ? tgid_space : space); - seq_printf(m, "# %s| / _---=> hardirq/softirq\n", + seq_printf(m, "# %s| / _---=> need-resched_lazy\n", + tgid ? tgid_space : space); + seq_printf(m, "# %s|| / _--=> hardirq/softirq\n", tgid ? tgid_space : space); - seq_printf(m, "# %s|| / _--=> preempt-depth\n", + seq_printf(m, "# %s||| / preempt-depth\n", tgid ? tgid_space : space); - seq_printf(m, "# %s||| / delay\n", + seq_printf(m, "# %s|||| / delay\n", tgid ? tgid_space : space); - seq_printf(m, "# TASK-PID %sCPU# |||| TIMESTAMP FUNCTION\n", + seq_printf(m, "# TASK-PID %sCPU# ||||| TIMESTAMP FUNCTION\n", tgid ? " TGID " : space); - seq_printf(m, "# | | %s | |||| | |\n", + seq_printf(m, "# | | %s | ||||| | |\n", tgid ? " | " : space); } diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index c726983c4981..2f611c5777f9 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -127,6 +127,7 @@ struct kretprobe_trace_entry_head { * NEED_RESCHED - reschedule is requested * HARDIRQ - inside an interrupt handler * SOFTIRQ - inside a softirq handler + * NEED_RESCHED_LAZY - lazy reschedule is requested */ enum trace_flag_type { TRACE_FLAG_IRQS_OFF = 0x01, @@ -136,6 +137,7 @@ enum trace_flag_type { TRACE_FLAG_SOFTIRQ = 0x10, TRACE_FLAG_PREEMPT_RESCHED = 0x20, TRACE_FLAG_NMI = 0x40, + TRACE_FLAG_NEED_RESCHED_LAZY = 0x80, }; #define TRACE_BUF_SIZE 1024 diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 93c2af760faf..88ea6cc99b38 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -187,6 +187,8 @@ static int trace_define_common_fields(void) __common_field(unsigned char, flags); __common_field(unsigned char, preempt_count); __common_field(int, pid); + __common_field(unsigned short, migrate_disable); + __common_field(unsigned short, padding); return ret; } diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c index d7c8e4ec3d9d..518c61a1bceb 100644 --- a/kernel/trace/trace_hwlat.c +++ b/kernel/trace/trace_hwlat.c @@ -279,7 +279,7 @@ static void move_to_next_cpu(void) * of this thread, than stop migrating for the duration * of the current test. */ - if (!cpumask_equal(current_mask, ¤t->cpus_allowed)) + if (!cpumask_equal(current_mask, current->cpus_ptr)) goto disable; get_online_cpus(); diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 1c8e30fda46a..cad60dda84e3 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -447,6 +447,7 @@ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry) { char hardsoft_irq; char need_resched; + char need_resched_lazy; char irqs_off; int hardirq; int softirq; @@ -477,6 +478,9 @@ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry) break; } + need_resched_lazy = + (entry->flags & TRACE_FLAG_NEED_RESCHED_LAZY) ? 'L' : '.'; + hardsoft_irq = (nmi && hardirq) ? 'Z' : nmi ? 'z' : @@ -485,14 +489,25 @@ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry) softirq ? 's' : '.' ; - trace_seq_printf(s, "%c%c%c", - irqs_off, need_resched, hardsoft_irq); + trace_seq_printf(s, "%c%c%c%c", + irqs_off, need_resched, need_resched_lazy, + hardsoft_irq); if (entry->preempt_count) trace_seq_printf(s, "%x", entry->preempt_count); else trace_seq_putc(s, '.'); + if (entry->preempt_lazy_count) + trace_seq_printf(s, "%x", entry->preempt_lazy_count); + else + trace_seq_putc(s, '.'); + + if (entry->migrate_disable) + trace_seq_printf(s, "%x", entry->migrate_disable); + else + trace_seq_putc(s, '.'); + return !trace_seq_has_overflowed(s); } diff --git a/kernel/user.c b/kernel/user.c index 36288d840675..0df9b1640b2a 100644 --- a/kernel/user.c +++ b/kernel/user.c @@ -96,7 +96,7 @@ static DEFINE_SPINLOCK(uidhash_lock); /* root_user.__count is 1, for init task cred */ struct user_struct root_user = { - .__count = ATOMIC_INIT(1), + .__count = REFCOUNT_INIT(1), .processes = ATOMIC_INIT(1), .sigpending = ATOMIC_INIT(0), .locked_shm = 0, @@ -123,7 +123,7 @@ static struct user_struct *uid_hash_find(kuid_t uid, struct hlist_head *hashent) hlist_for_each_entry(user, hashent, uidhash_node) { if (uid_eq(user->uid, uid)) { - atomic_inc(&user->__count); + refcount_inc(&user->__count); return user; } } @@ -169,11 +169,8 @@ void free_uid(struct user_struct *up) if (!up) return; - local_irq_save(flags); - if (atomic_dec_and_lock(&up->__count, &uidhash_lock)) + if (refcount_dec_and_lock_irqsave(&up->__count, &uidhash_lock, &flags)) free_user(up, flags); - else - local_irq_restore(flags); } struct user_struct *alloc_uid(kuid_t uid) @@ -191,7 +188,7 @@ struct user_struct *alloc_uid(kuid_t uid) goto out_unlock; new->uid = uid; - atomic_set(&new->__count, 1); + refcount_set(&new->__count, 1); ratelimit_state_init(&new->ratelimit, HZ, 100); ratelimit_set_flags(&new->ratelimit, RATELIMIT_MSG_ON_RELEASE); diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 51f5a64d9ec2..a46cd2b578bf 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -463,7 +463,7 @@ static void watchdog_enable(unsigned int cpu) * Start the timer first to prevent the NMI watchdog triggering * before the timer has a chance to fire. */ - hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD); hrtimer->function = watchdog_timer_fn; hrtimer_start(hrtimer, ns_to_ktime(sample_period), HRTIMER_MODE_REL_PINNED); diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c index 4ece6028007a..210dccc57c04 100644 --- a/kernel/watchdog_hld.c +++ b/kernel/watchdog_hld.c @@ -24,6 +24,8 @@ static DEFINE_PER_CPU(bool, hard_watchdog_warn); static DEFINE_PER_CPU(bool, watchdog_nmi_touch); static DEFINE_PER_CPU(struct perf_event *, watchdog_ev); static DEFINE_PER_CPU(struct perf_event *, dead_event); +static DEFINE_RAW_SPINLOCK(watchdog_output_lock); + static struct cpumask dead_events_mask; static unsigned long hardlockup_allcpu_dumped; @@ -134,6 +136,13 @@ static void watchdog_overflow_callback(struct perf_event *event, /* only print hardlockups once */ if (__this_cpu_read(hard_watchdog_warn) == true) return; + /* + * If early-printk is enabled then make sure we do not + * lock up in printk() and kill console logging: + */ + printk_kill(); + + raw_spin_lock(&watchdog_output_lock); pr_emerg("Watchdog detected hard LOCKUP on cpu %d", this_cpu); print_modules(); @@ -151,6 +160,7 @@ static void watchdog_overflow_callback(struct perf_event *event, !test_and_set_bit(0, &hardlockup_allcpu_dumped)) trigger_allbutself_cpu_backtrace(); + raw_spin_unlock(&watchdog_output_lock); if (hardlockup_panic) nmi_panic(regs, "Hard LOCKUP"); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index cd8b61bded78..12137825bf5a 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -49,6 +49,8 @@ #include <linux/uaccess.h> #include <linux/sched/isolation.h> #include <linux/nmi.h> +#include <linux/locallock.h> +#include <linux/delay.h> #include "workqueue_internal.h" @@ -123,11 +125,16 @@ enum { * cpu or grabbing pool->lock is enough for read access. If * POOL_DISASSOCIATED is set, it's identical to L. * + * On RT we need the extra protection via rt_lock_idle_list() for + * the list manipulations against read access from + * wq_worker_sleeping(). All other places are nicely serialized via + * pool->lock. + * * A: wq_pool_attach_mutex protected. * * PL: wq_pool_mutex protected. * - * PR: wq_pool_mutex protected for writes. Sched-RCU protected for reads. + * PR: wq_pool_mutex protected for writes. RCU protected for reads. * * PW: wq_pool_mutex and wq->mutex protected for writes. Either for reads. * @@ -136,7 +143,7 @@ enum { * * WQ: wq->mutex protected. * - * WR: wq->mutex protected for writes. Sched-RCU protected for reads. + * WR: wq->mutex protected for writes. RCU protected for reads. * * MD: wq_mayday_lock protected. */ @@ -183,7 +190,7 @@ struct worker_pool { atomic_t nr_running ____cacheline_aligned_in_smp; /* - * Destruction of pool is sched-RCU protected to allow dereferences + * Destruction of pool is RCU protected to allow dereferences * from get_work_pool(). */ struct rcu_head rcu; @@ -212,7 +219,7 @@ struct pool_workqueue { /* * Release of unbound pwq is punted to system_wq. See put_pwq() * and pwq_unbound_release_workfn() for details. pool_workqueue - * itself is also sched-RCU protected so that the first pwq can be + * itself is also RCU protected so that the first pwq can be * determined without grabbing wq->mutex. */ struct work_struct unbound_release_work; @@ -350,6 +357,8 @@ EXPORT_SYMBOL_GPL(system_power_efficient_wq); struct workqueue_struct *system_freezable_power_efficient_wq __read_mostly; EXPORT_SYMBOL_GPL(system_freezable_power_efficient_wq); +static DEFINE_LOCAL_IRQ_LOCK(pendingb_lock); + static int worker_thread(void *__worker); static void workqueue_sysfs_unregister(struct workqueue_struct *wq); @@ -357,20 +366,20 @@ static void workqueue_sysfs_unregister(struct workqueue_struct *wq); #include <trace/events/workqueue.h> #define assert_rcu_or_pool_mutex() \ - RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() && \ + RCU_LOCKDEP_WARN(!rcu_read_lock_held() && \ !lockdep_is_held(&wq_pool_mutex), \ - "sched RCU or wq_pool_mutex should be held") + "RCU or wq_pool_mutex should be held") #define assert_rcu_or_wq_mutex(wq) \ - RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() && \ + RCU_LOCKDEP_WARN(!rcu_read_lock_held() && \ !lockdep_is_held(&wq->mutex), \ - "sched RCU or wq->mutex should be held") + "RCU or wq->mutex should be held") #define assert_rcu_or_wq_mutex_or_pool_mutex(wq) \ - RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() && \ + RCU_LOCKDEP_WARN(!rcu_read_lock_held() && \ !lockdep_is_held(&wq->mutex) && \ !lockdep_is_held(&wq_pool_mutex), \ - "sched RCU, wq->mutex or wq_pool_mutex should be held") + "RCU, wq->mutex or wq_pool_mutex should be held") #define for_each_cpu_worker_pool(pool, cpu) \ for ((pool) = &per_cpu(cpu_worker_pools, cpu)[0]; \ @@ -382,7 +391,7 @@ static void workqueue_sysfs_unregister(struct workqueue_struct *wq); * @pool: iteration cursor * @pi: integer used for iteration * - * This must be called either with wq_pool_mutex held or sched RCU read + * This must be called either with wq_pool_mutex held or RCU read * locked. If the pool needs to be used beyond the locking in effect, the * caller is responsible for guaranteeing that the pool stays online. * @@ -414,7 +423,7 @@ static void workqueue_sysfs_unregister(struct workqueue_struct *wq); * @pwq: iteration cursor * @wq: the target workqueue * - * This must be called either with wq->mutex held or sched RCU read locked. + * This must be called either with wq->mutex held or RCU read locked. * If the pwq needs to be used beyond the locking in effect, the caller is * responsible for guaranteeing that the pwq stays online. * @@ -426,6 +435,31 @@ static void workqueue_sysfs_unregister(struct workqueue_struct *wq); if (({ assert_rcu_or_wq_mutex(wq); false; })) { } \ else +#ifdef CONFIG_PREEMPT_RT_BASE +static inline void rt_lock_idle_list(struct worker_pool *pool) +{ + preempt_disable(); +} +static inline void rt_unlock_idle_list(struct worker_pool *pool) +{ + preempt_enable(); +} +static inline void sched_lock_idle_list(struct worker_pool *pool) { } +static inline void sched_unlock_idle_list(struct worker_pool *pool) { } +#else +static inline void rt_lock_idle_list(struct worker_pool *pool) { } +static inline void rt_unlock_idle_list(struct worker_pool *pool) { } +static inline void sched_lock_idle_list(struct worker_pool *pool) +{ + spin_lock_irq(&pool->lock); +} +static inline void sched_unlock_idle_list(struct worker_pool *pool) +{ + spin_unlock_irq(&pool->lock); +} +#endif + + #ifdef CONFIG_DEBUG_OBJECTS_WORK static struct debug_obj_descr work_debug_descr; @@ -550,7 +584,7 @@ static int worker_pool_assign_id(struct worker_pool *pool) * @wq: the target workqueue * @node: the node ID * - * This must be called with any of wq_pool_mutex, wq->mutex or sched RCU + * This must be called with any of wq_pool_mutex, wq->mutex or RCU * read locked. * If the pwq needs to be used beyond the locking in effect, the caller is * responsible for guaranteeing that the pwq stays online. @@ -694,8 +728,8 @@ static struct pool_workqueue *get_work_pwq(struct work_struct *work) * @work: the work item of interest * * Pools are created and destroyed under wq_pool_mutex, and allows read - * access under sched-RCU read lock. As such, this function should be - * called under wq_pool_mutex or with preemption disabled. + * access under RCU read lock. As such, this function should be + * called under wq_pool_mutex or inside of a rcu_read_lock() region. * * All fields of the returned pool are accessible as long as the above * mentioned locking is in effect. If the returned pool needs to be used @@ -832,50 +866,45 @@ static struct worker *first_idle_worker(struct worker_pool *pool) */ static void wake_up_worker(struct worker_pool *pool) { - struct worker *worker = first_idle_worker(pool); + struct worker *worker; + + rt_lock_idle_list(pool); + + worker = first_idle_worker(pool); if (likely(worker)) wake_up_process(worker->task); + + rt_unlock_idle_list(pool); } /** - * wq_worker_waking_up - a worker is waking up + * wq_worker_running - a worker is running again * @task: task waking up - * @cpu: CPU @task is waking up to * - * This function is called during try_to_wake_up() when a worker is - * being awoken. - * - * CONTEXT: - * spin_lock_irq(rq->lock) + * This function is called when a worker returns from schedule() */ -void wq_worker_waking_up(struct task_struct *task, int cpu) +void wq_worker_running(struct task_struct *task) { struct worker *worker = kthread_data(task); - if (!(worker->flags & WORKER_NOT_RUNNING)) { - WARN_ON_ONCE(worker->pool->cpu != cpu); + if (!worker->sleeping) + return; + if (!(worker->flags & WORKER_NOT_RUNNING)) atomic_inc(&worker->pool->nr_running); - } + worker->sleeping = 0; } /** * wq_worker_sleeping - a worker is going to sleep * @task: task going to sleep * - * This function is called during schedule() when a busy worker is - * going to sleep. Worker on the same cpu can be woken up by - * returning pointer to its task. - * - * CONTEXT: - * spin_lock_irq(rq->lock) - * - * Return: - * Worker task on @cpu to wake up, %NULL if none. + * This function is called from schedule() when a busy worker is + * going to sleep. */ -struct task_struct *wq_worker_sleeping(struct task_struct *task) +void wq_worker_sleeping(struct task_struct *task) { - struct worker *worker = kthread_data(task), *to_wakeup = NULL; + struct worker *worker = kthread_data(task); struct worker_pool *pool; /* @@ -884,29 +913,26 @@ struct task_struct *wq_worker_sleeping(struct task_struct *task) * checking NOT_RUNNING. */ if (worker->flags & WORKER_NOT_RUNNING) - return NULL; + return; pool = worker->pool; - /* this can only happen on the local cpu */ - if (WARN_ON_ONCE(pool->cpu != raw_smp_processor_id())) - return NULL; + if (WARN_ON_ONCE(worker->sleeping)) + return; + + worker->sleeping = 1; /* * The counterpart of the following dec_and_test, implied mb, * worklist not empty test sequence is in insert_work(). * Please read comment there. - * - * NOT_RUNNING is clear. This means that we're bound to and - * running on the local cpu w/ rq lock held and preemption - * disabled, which in turn means that none else could be - * manipulating idle_list, so dereferencing idle_list without pool - * lock is safe. */ if (atomic_dec_and_test(&pool->nr_running) && - !list_empty(&pool->worklist)) - to_wakeup = first_idle_worker(pool); - return to_wakeup ? to_wakeup->task : NULL; + !list_empty(&pool->worklist)) { + sched_lock_idle_list(pool); + wake_up_worker(pool); + sched_unlock_idle_list(pool); + } } /** @@ -1100,12 +1126,14 @@ static void put_pwq_unlocked(struct pool_workqueue *pwq) { if (pwq) { /* - * As both pwqs and pools are sched-RCU protected, the + * As both pwqs and pools are RCU protected, the * following lock operations are safe. */ - spin_lock_irq(&pwq->pool->lock); + rcu_read_lock(); + local_spin_lock_irq(pendingb_lock, &pwq->pool->lock); put_pwq(pwq); - spin_unlock_irq(&pwq->pool->lock); + local_spin_unlock_irq(pendingb_lock, &pwq->pool->lock); + rcu_read_unlock(); } } @@ -1209,7 +1237,7 @@ static int try_to_grab_pending(struct work_struct *work, bool is_dwork, struct worker_pool *pool; struct pool_workqueue *pwq; - local_irq_save(*flags); + local_lock_irqsave(pendingb_lock, *flags); /* try to steal the timer if it exists */ if (is_dwork) { @@ -1228,6 +1256,7 @@ static int try_to_grab_pending(struct work_struct *work, bool is_dwork, if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) return 0; + rcu_read_lock(); /* * The queueing is in progress, or it is already queued. Try to * steal it from ->worklist without clearing WORK_STRUCT_PENDING. @@ -1266,14 +1295,16 @@ static int try_to_grab_pending(struct work_struct *work, bool is_dwork, set_work_pool_and_keep_pending(work, pool->id); spin_unlock(&pool->lock); + rcu_read_unlock(); return 1; } spin_unlock(&pool->lock); fail: - local_irq_restore(*flags); + rcu_read_unlock(); + local_unlock_irqrestore(pendingb_lock, *flags); if (work_is_canceling(work)) return -ENOENT; - cpu_relax(); + cpu_chill(); return -EAGAIN; } @@ -1375,7 +1406,13 @@ static void __queue_work(int cpu, struct workqueue_struct *wq, * queued or lose PENDING. Grabbing PENDING and queueing should * happen with IRQ disabled. */ +#ifndef CONFIG_PREEMPT_RT_FULL + /* + * nort: On RT the "interrupts-disabled" rule has been replaced with + * pendingb_lock. + */ lockdep_assert_irqs_disabled(); +#endif debug_work_activate(work); @@ -1383,6 +1420,7 @@ static void __queue_work(int cpu, struct workqueue_struct *wq, if (unlikely(wq->flags & __WQ_DRAINING) && WARN_ON_ONCE(!is_chained_work(wq))) return; + rcu_read_lock(); retry: if (req_cpu == WORK_CPU_UNBOUND) cpu = wq_select_unbound_cpu(raw_smp_processor_id()); @@ -1439,10 +1477,8 @@ retry: /* pwq determined, queue */ trace_workqueue_queue_work(req_cpu, pwq, work); - if (WARN_ON(!list_empty(&work->entry))) { - spin_unlock(&pwq->pool->lock); - return; - } + if (WARN_ON(!list_empty(&work->entry))) + goto out; pwq->nr_in_flight[pwq->work_color]++; work_flags = work_color_to_flags(pwq->work_color); @@ -1460,7 +1496,9 @@ retry: insert_work(pwq, work, worklist, work_flags); +out: spin_unlock(&pwq->pool->lock); + rcu_read_unlock(); } /** @@ -1480,14 +1518,14 @@ bool queue_work_on(int cpu, struct workqueue_struct *wq, bool ret = false; unsigned long flags; - local_irq_save(flags); + local_lock_irqsave(pendingb_lock,flags); if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { __queue_work(cpu, wq, work); ret = true; } - local_irq_restore(flags); + local_unlock_irqrestore(pendingb_lock, flags); return ret; } EXPORT_SYMBOL(queue_work_on); @@ -1496,8 +1534,11 @@ void delayed_work_timer_fn(struct timer_list *t) { struct delayed_work *dwork = from_timer(dwork, t, timer); + /* XXX */ + /* local_lock(pendingb_lock); */ /* should have been called from irqsafe timer with irq already off */ __queue_work(dwork->cpu, dwork->wq, &dwork->work); + /* local_unlock(pendingb_lock); */ } EXPORT_SYMBOL(delayed_work_timer_fn); @@ -1552,14 +1593,14 @@ bool queue_delayed_work_on(int cpu, struct workqueue_struct *wq, unsigned long flags; /* read the comment in __queue_work() */ - local_irq_save(flags); + local_lock_irqsave(pendingb_lock, flags); if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { __queue_delayed_work(cpu, wq, dwork, delay); ret = true; } - local_irq_restore(flags); + local_unlock_irqrestore(pendingb_lock, flags); return ret; } EXPORT_SYMBOL(queue_delayed_work_on); @@ -1594,7 +1635,7 @@ bool mod_delayed_work_on(int cpu, struct workqueue_struct *wq, if (likely(ret >= 0)) { __queue_delayed_work(cpu, wq, dwork, delay); - local_irq_restore(flags); + local_unlock_irqrestore(pendingb_lock, flags); } /* -ENOENT from try_to_grab_pending() becomes %true */ @@ -1605,11 +1646,12 @@ EXPORT_SYMBOL_GPL(mod_delayed_work_on); static void rcu_work_rcufn(struct rcu_head *rcu) { struct rcu_work *rwork = container_of(rcu, struct rcu_work, rcu); + unsigned long flags; /* read the comment in __queue_work() */ - local_irq_disable(); + local_lock_irqsave(pendingb_lock, flags); __queue_work(WORK_CPU_UNBOUND, rwork->wq, &rwork->work); - local_irq_enable(); + local_unlock_irqrestore(pendingb_lock, flags); } /** @@ -1661,7 +1703,9 @@ static void worker_enter_idle(struct worker *worker) worker->last_active = jiffies; /* idle_list is LIFO */ + rt_lock_idle_list(pool); list_add(&worker->entry, &pool->idle_list); + rt_unlock_idle_list(pool); if (too_many_workers(pool) && !timer_pending(&pool->idle_timer)) mod_timer(&pool->idle_timer, jiffies + IDLE_WORKER_TIMEOUT); @@ -1694,7 +1738,9 @@ static void worker_leave_idle(struct worker *worker) return; worker_clr_flags(worker, WORKER_IDLE); pool->nr_idle--; + rt_lock_idle_list(pool); list_del_init(&worker->entry); + rt_unlock_idle_list(pool); } static struct worker *alloc_worker(int node) @@ -1862,7 +1908,9 @@ static void destroy_worker(struct worker *worker) pool->nr_workers--; pool->nr_idle--; + rt_lock_idle_list(pool); list_del_init(&worker->entry); + rt_unlock_idle_list(pool); worker->flags |= WORKER_DIE; wake_up_process(worker->task); } @@ -2855,14 +2903,14 @@ static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr, might_sleep(); - local_irq_disable(); + rcu_read_lock(); pool = get_work_pool(work); if (!pool) { - local_irq_enable(); + rcu_read_unlock(); return false; } - spin_lock(&pool->lock); + spin_lock_irq(&pool->lock); /* see the comment in try_to_grab_pending() with the same code */ pwq = get_work_pwq(work); if (pwq) { @@ -2894,10 +2942,11 @@ static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr, lock_map_acquire(&pwq->wq->lockdep_map); lock_map_release(&pwq->wq->lockdep_map); } - + rcu_read_unlock(); return true; already_gone: spin_unlock_irq(&pool->lock); + rcu_read_unlock(); return false; } @@ -2997,7 +3046,7 @@ static bool __cancel_work_timer(struct work_struct *work, bool is_dwork) /* tell other tasks trying to grab @work to back off */ mark_work_canceling(work); - local_irq_restore(flags); + local_unlock_irqrestore(pendingb_lock, flags); /* * This allows canceling during early boot. We know that @work @@ -3058,10 +3107,10 @@ EXPORT_SYMBOL_GPL(cancel_work_sync); */ bool flush_delayed_work(struct delayed_work *dwork) { - local_irq_disable(); + local_lock_irq(pendingb_lock); if (del_timer_sync(&dwork->timer)) __queue_work(dwork->cpu, dwork->wq, &dwork->work); - local_irq_enable(); + local_unlock_irq(pendingb_lock); return flush_work(&dwork->work); } EXPORT_SYMBOL(flush_delayed_work); @@ -3099,7 +3148,7 @@ static bool __cancel_work(struct work_struct *work, bool is_dwork) return false; set_work_pool_and_clear_pending(work, get_work_pool_id(work)); - local_irq_restore(flags); + local_unlock_irqrestore(pendingb_lock, flags); return ret; } @@ -3344,7 +3393,7 @@ static void rcu_free_pool(struct rcu_head *rcu) * put_unbound_pool - put a worker_pool * @pool: worker_pool to put * - * Put @pool. If its refcnt reaches zero, it gets destroyed in sched-RCU + * Put @pool. If its refcnt reaches zero, it gets destroyed in RCU * safe manner. get_unbound_pool() calls this function on its failure path * and this function should be able to release pools which went through, * successfully or not, init_worker_pool(). @@ -3398,8 +3447,8 @@ static void put_unbound_pool(struct worker_pool *pool) del_timer_sync(&pool->idle_timer); del_timer_sync(&pool->mayday_timer); - /* sched-RCU protected to allow dereferences from get_work_pool() */ - call_rcu_sched(&pool->rcu, rcu_free_pool); + /* RCU protected to allow dereferences from get_work_pool() */ + call_rcu(&pool->rcu, rcu_free_pool); } /** @@ -3506,14 +3555,14 @@ static void pwq_unbound_release_workfn(struct work_struct *work) put_unbound_pool(pool); mutex_unlock(&wq_pool_mutex); - call_rcu_sched(&pwq->rcu, rcu_free_pwq); + call_rcu(&pwq->rcu, rcu_free_pwq); /* * If we're the last pwq going away, @wq is already dead and no one * is gonna access it anymore. Schedule RCU free. */ if (is_last) - call_rcu_sched(&wq->rcu, rcu_free_wq); + call_rcu(&wq->rcu, rcu_free_wq); } /** @@ -4198,7 +4247,7 @@ void destroy_workqueue(struct workqueue_struct *wq) * The base ref is never dropped on per-cpu pwqs. Directly * schedule RCU free. */ - call_rcu_sched(&wq->rcu, rcu_free_wq); + call_rcu(&wq->rcu, rcu_free_wq); } else { /* * We're the sole accessor of @wq at this point. Directly @@ -4308,7 +4357,8 @@ bool workqueue_congested(int cpu, struct workqueue_struct *wq) struct pool_workqueue *pwq; bool ret; - rcu_read_lock_sched(); + rcu_read_lock(); + preempt_disable(); if (cpu == WORK_CPU_UNBOUND) cpu = smp_processor_id(); @@ -4319,7 +4369,8 @@ bool workqueue_congested(int cpu, struct workqueue_struct *wq) pwq = unbound_pwq_by_node(wq, cpu_to_node(cpu)); ret = !list_empty(&pwq->delayed_works); - rcu_read_unlock_sched(); + preempt_enable(); + rcu_read_unlock(); return ret; } @@ -4345,15 +4396,15 @@ unsigned int work_busy(struct work_struct *work) if (work_pending(work)) ret |= WORK_BUSY_PENDING; - local_irq_save(flags); + rcu_read_lock(); pool = get_work_pool(work); if (pool) { - spin_lock(&pool->lock); + spin_lock_irqsave(&pool->lock, flags); if (find_worker_executing_work(pool, work)) ret |= WORK_BUSY_RUNNING; - spin_unlock(&pool->lock); + spin_unlock_irqrestore(&pool->lock, flags); } - local_irq_restore(flags); + rcu_read_unlock(); return ret; } @@ -4537,7 +4588,7 @@ void show_workqueue_state(void) unsigned long flags; int pi; - rcu_read_lock_sched(); + rcu_read_lock(); pr_info("Showing busy workqueues and worker pools:\n"); @@ -4602,7 +4653,7 @@ void show_workqueue_state(void) touch_nmi_watchdog(); } - rcu_read_unlock_sched(); + rcu_read_unlock(); } /* used to show worker information through /proc/PID/{comm,stat,status} */ @@ -4989,16 +5040,16 @@ bool freeze_workqueues_busy(void) * nr_active is monotonically decreasing. It's safe * to peek without lock. */ - rcu_read_lock_sched(); + rcu_read_lock(); for_each_pwq(pwq, wq) { WARN_ON_ONCE(pwq->nr_active < 0); if (pwq->nr_active) { busy = true; - rcu_read_unlock_sched(); + rcu_read_unlock(); goto out_unlock; } } - rcu_read_unlock_sched(); + rcu_read_unlock(); } out_unlock: mutex_unlock(&wq_pool_mutex); @@ -5193,7 +5244,8 @@ static ssize_t wq_pool_ids_show(struct device *dev, const char *delim = ""; int node, written = 0; - rcu_read_lock_sched(); + get_online_cpus(); + rcu_read_lock(); for_each_node(node) { written += scnprintf(buf + written, PAGE_SIZE - written, "%s%d:%d", delim, node, @@ -5201,7 +5253,8 @@ static ssize_t wq_pool_ids_show(struct device *dev, delim = " "; } written += scnprintf(buf + written, PAGE_SIZE - written, "\n"); - rcu_read_unlock_sched(); + rcu_read_unlock(); + put_online_cpus(); return written; } diff --git a/kernel/workqueue_internal.h b/kernel/workqueue_internal.h index 66fbb5a9e633..30cfed226b39 100644 --- a/kernel/workqueue_internal.h +++ b/kernel/workqueue_internal.h @@ -44,6 +44,7 @@ struct worker { unsigned long last_active; /* L: last active timestamp */ unsigned int flags; /* X: flags */ int id; /* I: worker id */ + int sleeping; /* None */ /* * Opaque string set with work_set_desc(). Printed out with task @@ -69,7 +70,7 @@ static inline struct worker *current_wq_worker(void) * Scheduler hooks for concurrency managed workqueue. Only to be used from * sched/core.c and workqueue.c. */ -void wq_worker_waking_up(struct task_struct *task, int cpu); -struct task_struct *wq_worker_sleeping(struct task_struct *task); +void wq_worker_running(struct task_struct *task); +void wq_worker_sleeping(struct task_struct *task); #endif /* _KERNEL_WORKQUEUE_INTERNAL_H */ diff --git a/lib/Kconfig b/lib/Kconfig index 706836ec314d..499be4544c6b 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -434,6 +434,7 @@ config CHECK_SIGNATURE config CPUMASK_OFFSTACK bool "Force CPU masks off stack" if DEBUG_PER_CPU_MAPS + depends on !PREEMPT_RT_FULL help Use dynamic allocation for cpumask_var_t, instead of putting them on the stack. This is a bit more expensive, but avoids diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 571da31cb8a1..e925ed4175a6 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1201,7 +1201,7 @@ config DEBUG_ATOMIC_SLEEP config DEBUG_LOCKING_API_SELFTESTS bool "Locking API boot-time self-tests" - depends on DEBUG_KERNEL + depends on DEBUG_KERNEL && !PREEMPT_RT_FULL help Say Y here if you want the kernel to run a short self-test during bootup. The self-test checks whether common types of locking bugs diff --git a/lib/debugobjects.c b/lib/debugobjects.c index f80cef7568eb..ac221d3b6202 100644 --- a/lib/debugobjects.c +++ b/lib/debugobjects.c @@ -376,7 +376,10 @@ __debug_object_init(void *addr, struct debug_obj_descr *descr, int onstack) struct debug_obj *obj; unsigned long flags; - fill_pool(); +#ifdef CONFIG_PREEMPT_RT_FULL + if (preempt_count() == 0 && !irqs_disabled()) +#endif + fill_pool(); db = get_bucket((unsigned long) addr); diff --git a/lib/irq_poll.c b/lib/irq_poll.c index 86a709954f5a..9c069ef83d6d 100644 --- a/lib/irq_poll.c +++ b/lib/irq_poll.c @@ -37,6 +37,7 @@ void irq_poll_sched(struct irq_poll *iop) list_add_tail(&iop->list, this_cpu_ptr(&blk_cpu_iopoll)); __raise_softirq_irqoff(IRQ_POLL_SOFTIRQ); local_irq_restore(flags); + preempt_check_resched_rt(); } EXPORT_SYMBOL(irq_poll_sched); @@ -72,6 +73,7 @@ void irq_poll_complete(struct irq_poll *iop) local_irq_save(flags); __irq_poll_complete(iop); local_irq_restore(flags); + preempt_check_resched_rt(); } EXPORT_SYMBOL(irq_poll_complete); @@ -96,6 +98,7 @@ static void __latent_entropy irq_poll_softirq(struct softirq_action *h) } local_irq_enable(); + preempt_check_resched_rt(); /* Even though interrupts have been re-enabled, this * access is safe because interrupts can only add new @@ -133,6 +136,7 @@ static void __latent_entropy irq_poll_softirq(struct softirq_action *h) __raise_softirq_irqoff(IRQ_POLL_SOFTIRQ); local_irq_enable(); + preempt_check_resched_rt(); } /** @@ -196,6 +200,7 @@ static int irq_poll_cpu_dead(unsigned int cpu) this_cpu_ptr(&blk_cpu_iopoll)); __raise_softirq_irqoff(IRQ_POLL_SOFTIRQ); local_irq_enable(); + preempt_check_resched_rt(); return 0; } diff --git a/lib/locking-selftest.c b/lib/locking-selftest.c index b5c1293ce147..075e225f4111 100644 --- a/lib/locking-selftest.c +++ b/lib/locking-selftest.c @@ -742,6 +742,8 @@ GENERATE_TESTCASE(init_held_rtmutex); #include "locking-selftest-spin-hardirq.h" GENERATE_PERMUTATIONS_2_EVENTS(irqsafe1_hard_spin) +#ifndef CONFIG_PREEMPT_RT_FULL + #include "locking-selftest-rlock-hardirq.h" GENERATE_PERMUTATIONS_2_EVENTS(irqsafe1_hard_rlock) @@ -757,9 +759,12 @@ GENERATE_PERMUTATIONS_2_EVENTS(irqsafe1_soft_rlock) #include "locking-selftest-wlock-softirq.h" GENERATE_PERMUTATIONS_2_EVENTS(irqsafe1_soft_wlock) +#endif + #undef E1 #undef E2 +#ifndef CONFIG_PREEMPT_RT_FULL /* * Enabling hardirqs with a softirq-safe lock held: */ @@ -792,6 +797,8 @@ GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2A_rlock) #undef E1 #undef E2 +#endif + /* * Enabling irqs with an irq-safe lock held: */ @@ -815,6 +822,8 @@ GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2A_rlock) #include "locking-selftest-spin-hardirq.h" GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_hard_spin) +#ifndef CONFIG_PREEMPT_RT_FULL + #include "locking-selftest-rlock-hardirq.h" GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_hard_rlock) @@ -830,6 +839,8 @@ GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_soft_rlock) #include "locking-selftest-wlock-softirq.h" GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_soft_wlock) +#endif + #undef E1 #undef E2 @@ -861,6 +872,8 @@ GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_soft_wlock) #include "locking-selftest-spin-hardirq.h" GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_hard_spin) +#ifndef CONFIG_PREEMPT_RT_FULL + #include "locking-selftest-rlock-hardirq.h" GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_hard_rlock) @@ -876,6 +889,8 @@ GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_soft_rlock) #include "locking-selftest-wlock-softirq.h" GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_soft_wlock) +#endif + #undef E1 #undef E2 #undef E3 @@ -909,6 +924,8 @@ GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_soft_wlock) #include "locking-selftest-spin-hardirq.h" GENERATE_PERMUTATIONS_3_EVENTS(irqsafe4_hard_spin) +#ifndef CONFIG_PREEMPT_RT_FULL + #include "locking-selftest-rlock-hardirq.h" GENERATE_PERMUTATIONS_3_EVENTS(irqsafe4_hard_rlock) @@ -924,10 +941,14 @@ GENERATE_PERMUTATIONS_3_EVENTS(irqsafe4_soft_rlock) #include "locking-selftest-wlock-softirq.h" GENERATE_PERMUTATIONS_3_EVENTS(irqsafe4_soft_wlock) +#endif + #undef E1 #undef E2 #undef E3 +#ifndef CONFIG_PREEMPT_RT_FULL + /* * read-lock / write-lock irq inversion. * @@ -990,6 +1011,10 @@ GENERATE_PERMUTATIONS_3_EVENTS(irq_inversion_soft_wlock) #undef E2 #undef E3 +#endif + +#ifndef CONFIG_PREEMPT_RT_FULL + /* * read-lock / write-lock recursion that is actually safe. */ @@ -1028,6 +1053,8 @@ GENERATE_PERMUTATIONS_3_EVENTS(irq_read_recursion_soft) #undef E2 #undef E3 +#endif + /* * read-lock / write-lock recursion that is unsafe. */ @@ -2057,6 +2084,7 @@ void locking_selftest(void) printk(" --------------------------------------------------------------------------\n"); +#ifndef CONFIG_PREEMPT_RT_FULL /* * irq-context testcases: */ @@ -2069,6 +2097,28 @@ void locking_selftest(void) DO_TESTCASE_6x2("irq read-recursion", irq_read_recursion); // DO_TESTCASE_6x2B("irq read-recursion #2", irq_read_recursion2); +#else + /* On -rt, we only do hardirq context test for raw spinlock */ + DO_TESTCASE_1B("hard-irqs-on + irq-safe-A", irqsafe1_hard_spin, 12); + DO_TESTCASE_1B("hard-irqs-on + irq-safe-A", irqsafe1_hard_spin, 21); + + DO_TESTCASE_1B("hard-safe-A + irqs-on", irqsafe2B_hard_spin, 12); + DO_TESTCASE_1B("hard-safe-A + irqs-on", irqsafe2B_hard_spin, 21); + + DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 123); + DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 132); + DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 213); + DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 231); + DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 312); + DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 321); + + DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 123); + DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 132); + DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 213); + DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 231); + DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 312); + DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 321); +#endif ww_tests(); diff --git a/lib/radix-tree.c b/lib/radix-tree.c index a9e41aed6de4..bdfeb6feefb8 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -38,7 +38,7 @@ #include <linux/rcupdate.h> #include <linux/slab.h> #include <linux/string.h> - +#include <linux/locallock.h> /* Number of nodes in fully populated tree of given height */ static unsigned long height_to_maxnodes[RADIX_TREE_MAX_PATH + 1] __read_mostly; @@ -87,6 +87,7 @@ struct radix_tree_preload { struct radix_tree_node *nodes; }; static DEFINE_PER_CPU(struct radix_tree_preload, radix_tree_preloads) = { 0, }; +static DEFINE_LOCAL_IRQ_LOCK(radix_tree_preloads_lock); static inline struct radix_tree_node *entry_to_node(void *ptr) { @@ -405,12 +406,13 @@ radix_tree_node_alloc(gfp_t gfp_mask, struct radix_tree_node *parent, * succeed in getting a node here (and never reach * kmem_cache_alloc) */ - rtp = this_cpu_ptr(&radix_tree_preloads); + rtp = &get_locked_var(radix_tree_preloads_lock, radix_tree_preloads); if (rtp->nr) { ret = rtp->nodes; rtp->nodes = ret->parent; rtp->nr--; } + put_locked_var(radix_tree_preloads_lock, radix_tree_preloads); /* * Update the allocation stack trace as this is more useful * for debugging. @@ -476,14 +478,14 @@ static __must_check int __radix_tree_preload(gfp_t gfp_mask, unsigned nr) */ gfp_mask &= ~__GFP_ACCOUNT; - preempt_disable(); + local_lock(radix_tree_preloads_lock); rtp = this_cpu_ptr(&radix_tree_preloads); while (rtp->nr < nr) { - preempt_enable(); + local_unlock(radix_tree_preloads_lock); node = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask); if (node == NULL) goto out; - preempt_disable(); + local_lock(radix_tree_preloads_lock); rtp = this_cpu_ptr(&radix_tree_preloads); if (rtp->nr < nr) { node->parent = rtp->nodes; @@ -525,7 +527,7 @@ int radix_tree_maybe_preload(gfp_t gfp_mask) if (gfpflags_allow_blocking(gfp_mask)) return __radix_tree_preload(gfp_mask, RADIX_TREE_PRELOAD_SIZE); /* Preloading doesn't help anything with this gfp mask, skip it */ - preempt_disable(); + local_lock(radix_tree_preloads_lock); return 0; } EXPORT_SYMBOL(radix_tree_maybe_preload); @@ -563,7 +565,7 @@ int radix_tree_maybe_preload_order(gfp_t gfp_mask, int order) /* Preloading doesn't help anything with this gfp mask, skip it */ if (!gfpflags_allow_blocking(gfp_mask)) { - preempt_disable(); + local_lock(radix_tree_preloads_lock); return 0; } @@ -597,6 +599,12 @@ int radix_tree_maybe_preload_order(gfp_t gfp_mask, int order) return __radix_tree_preload(gfp_mask, nr_nodes); } +void radix_tree_preload_end(void) +{ + local_unlock(radix_tree_preloads_lock); +} +EXPORT_SYMBOL(radix_tree_preload_end); + static unsigned radix_tree_load_root(const struct radix_tree_root *root, struct radix_tree_node **nodep, unsigned long *maxindex) { @@ -2102,10 +2110,16 @@ EXPORT_SYMBOL(radix_tree_tagged); void idr_preload(gfp_t gfp_mask) { if (__radix_tree_preload(gfp_mask, IDR_PRELOAD_SIZE)) - preempt_disable(); + local_lock(radix_tree_preloads_lock); } EXPORT_SYMBOL(idr_preload); +void idr_preload_end(void) +{ + local_unlock(radix_tree_preloads_lock); +} +EXPORT_SYMBOL(idr_preload_end); + /** * ida_pre_get - reserve resources for ida allocation * @ida: ida handle @@ -2122,7 +2136,7 @@ int ida_pre_get(struct ida *ida, gfp_t gfp) * to return to the ida_pre_get() step. */ if (!__radix_tree_preload(gfp, IDA_PRELOAD_SIZE)) - preempt_enable(); + local_unlock(radix_tree_preloads_lock); if (!this_cpu_read(ida_bitmap)) { struct ida_bitmap *bitmap = kzalloc(sizeof(*bitmap), gfp); diff --git a/lib/scatterlist.c b/lib/scatterlist.c index 7c6096a71704..5c2c68962709 100644 --- a/lib/scatterlist.c +++ b/lib/scatterlist.c @@ -776,7 +776,7 @@ void sg_miter_stop(struct sg_mapping_iter *miter) flush_kernel_dcache_page(miter->page); if (miter->__flags & SG_MITER_ATOMIC) { - WARN_ON_ONCE(preemptible()); + WARN_ON_ONCE(!pagefault_disabled()); kunmap_atomic(miter->addr); } else kunmap(miter->page); diff --git a/lib/smp_processor_id.c b/lib/smp_processor_id.c index 85925aaa4fff..fb35c45b9421 100644 --- a/lib/smp_processor_id.c +++ b/lib/smp_processor_id.c @@ -22,7 +22,7 @@ notrace static unsigned int check_preemption_disabled(const char *what1, * Kernel threads bound to a single CPU can safely use * smp_processor_id(): */ - if (cpumask_equal(¤t->cpus_allowed, cpumask_of(this_cpu))) + if (cpumask_equal(current->cpus_ptr, cpumask_of(this_cpu))) goto out; /* diff --git a/localversion-rt b/localversion-rt new file mode 100644 index 000000000000..700c857efd9b --- /dev/null +++ b/localversion-rt @@ -0,0 +1 @@ +-rt8 diff --git a/mm/Kconfig b/mm/Kconfig index f3bc3aed6510..2b75718a1159 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -378,7 +378,7 @@ config NOMMU_INITIAL_TRIM_EXCESS config TRANSPARENT_HUGEPAGE bool "Transparent Hugepage Support" - depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE + depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE && !PREEMPT_RT_FULL select COMPACTION select RADIX_TREE_MULTIORDER help diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 12fec6b4f6ec..a8d8336916d5 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -438,10 +438,10 @@ retry: if (new_congested) { /* !found and storage for new one already allocated, insert */ congested = new_congested; - new_congested = NULL; rb_link_node(&congested->rb_node, parent, node); rb_insert_color(&congested->rb_node, &bdi->cgwb_congested_tree); - goto found; + spin_unlock_irqrestore(&cgwb_lock, flags); + return congested; } spin_unlock_irqrestore(&cgwb_lock, flags); @@ -451,13 +451,13 @@ retry: if (!new_congested) return NULL; - atomic_set(&new_congested->refcnt, 0); + refcount_set(&new_congested->refcnt, 1); new_congested->__bdi = bdi; new_congested->blkcg_id = blkcg_id; goto retry; found: - atomic_inc(&congested->refcnt); + refcount_inc(&congested->refcnt); spin_unlock_irqrestore(&cgwb_lock, flags); kfree(new_congested); return congested; @@ -473,11 +473,8 @@ void wb_congested_put(struct bdi_writeback_congested *congested) { unsigned long flags; - local_irq_save(flags); - if (!atomic_dec_and_lock(&congested->refcnt, &cgwb_lock)) { - local_irq_restore(flags); + if (!refcount_dec_and_lock_irqsave(&congested->refcnt, &cgwb_lock, &flags)) return; - } /* bdi might already have been destroyed leaving @congested unlinked */ if (congested->__bdi) { @@ -805,7 +802,7 @@ static int cgwb_bdi_init(struct backing_dev_info *bdi) if (!bdi->wb_congested) return -ENOMEM; - atomic_set(&bdi->wb_congested->refcnt, 1); + refcount_set(&bdi->wb_congested->refcnt, 1); err = wb_init(&bdi->wb, bdi, 1, GFP_KERNEL); if (err) { diff --git a/mm/compaction.c b/mm/compaction.c index faca45ebe62d..f8ccb9d9daa3 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -1657,10 +1657,12 @@ check_drain: block_start_pfn(cc->migrate_pfn, cc->order); if (cc->last_migrated_pfn < current_block_start) { - cpu = get_cpu(); + cpu = get_cpu_light(); + local_lock_irq(swapvec_lock); lru_add_drain_cpu(cpu); + local_unlock_irq(swapvec_lock); drain_local_pages(zone); - put_cpu(); + put_cpu_light(); /* No more flushing until we migrate again */ cc->last_migrated_pfn = 0; } diff --git a/mm/highmem.c b/mm/highmem.c index 59db3223a5d6..22aa3ddbd87b 100644 --- a/mm/highmem.c +++ b/mm/highmem.c @@ -30,10 +30,11 @@ #include <linux/kgdb.h> #include <asm/tlbflush.h> - +#ifndef CONFIG_PREEMPT_RT_FULL #if defined(CONFIG_HIGHMEM) || defined(CONFIG_X86_32) DEFINE_PER_CPU(int, __kmap_atomic_idx); #endif +#endif /* * Virtual_count is not a pure "count". @@ -108,8 +109,9 @@ static inline wait_queue_head_t *get_pkmap_wait_queue_head(unsigned int color) unsigned long totalhigh_pages __read_mostly; EXPORT_SYMBOL(totalhigh_pages); - +#ifndef CONFIG_PREEMPT_RT_FULL EXPORT_PER_CPU_SYMBOL(__kmap_atomic_idx); +#endif unsigned int nr_free_highpages (void) { diff --git a/mm/kasan/quarantine.c b/mm/kasan/quarantine.c index 3a8ddf8baf7d..b209dbaefde8 100644 --- a/mm/kasan/quarantine.c +++ b/mm/kasan/quarantine.c @@ -103,7 +103,7 @@ static int quarantine_head; static int quarantine_tail; /* Total size of all objects in global_quarantine across all batches. */ static unsigned long quarantine_size; -static DEFINE_SPINLOCK(quarantine_lock); +static DEFINE_RAW_SPINLOCK(quarantine_lock); DEFINE_STATIC_SRCU(remove_cache_srcu); /* Maximum size of the global queue. */ @@ -190,7 +190,7 @@ void quarantine_put(struct kasan_free_meta *info, struct kmem_cache *cache) if (unlikely(q->bytes > QUARANTINE_PERCPU_SIZE)) { qlist_move_all(q, &temp); - spin_lock(&quarantine_lock); + raw_spin_lock(&quarantine_lock); WRITE_ONCE(quarantine_size, quarantine_size + temp.bytes); qlist_move_all(&temp, &global_quarantine[quarantine_tail]); if (global_quarantine[quarantine_tail].bytes >= @@ -203,7 +203,7 @@ void quarantine_put(struct kasan_free_meta *info, struct kmem_cache *cache) if (new_tail != quarantine_head) quarantine_tail = new_tail; } - spin_unlock(&quarantine_lock); + raw_spin_unlock(&quarantine_lock); } local_irq_restore(flags); @@ -230,7 +230,7 @@ void quarantine_reduce(void) * expected case). */ srcu_idx = srcu_read_lock(&remove_cache_srcu); - spin_lock_irqsave(&quarantine_lock, flags); + raw_spin_lock_irqsave(&quarantine_lock, flags); /* * Update quarantine size in case of hotplug. Allocate a fraction of @@ -254,7 +254,7 @@ void quarantine_reduce(void) quarantine_head = 0; } - spin_unlock_irqrestore(&quarantine_lock, flags); + raw_spin_unlock_irqrestore(&quarantine_lock, flags); qlist_free_all(&to_free, NULL); srcu_read_unlock(&remove_cache_srcu, srcu_idx); @@ -310,17 +310,17 @@ void quarantine_remove_cache(struct kmem_cache *cache) */ on_each_cpu(per_cpu_remove_cache, cache, 1); - spin_lock_irqsave(&quarantine_lock, flags); + raw_spin_lock_irqsave(&quarantine_lock, flags); for (i = 0; i < QUARANTINE_BATCHES; i++) { if (qlist_empty(&global_quarantine[i])) continue; qlist_move_cache(&global_quarantine[i], &to_free, cache); /* Scanning whole quarantine can take a while. */ - spin_unlock_irqrestore(&quarantine_lock, flags); + raw_spin_unlock_irqrestore(&quarantine_lock, flags); cond_resched(); - spin_lock_irqsave(&quarantine_lock, flags); + raw_spin_lock_irqsave(&quarantine_lock, flags); } - spin_unlock_irqrestore(&quarantine_lock, flags); + raw_spin_unlock_irqrestore(&quarantine_lock, flags); qlist_free_all(&to_free, cache); diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 14ef1312474f..d5b24e468d97 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -26,7 +26,7 @@ * * The following locks and mutexes are used by kmemleak: * - * - kmemleak_lock (rwlock): protects the object_list modifications and + * - kmemleak_lock (raw spinlock): protects the object_list modifications and * accesses to the object_tree_root. The object_list is the main list * holding the metadata (struct kmemleak_object) for the allocated memory * blocks. The object_tree_root is a red black tree used to look-up @@ -197,7 +197,7 @@ static LIST_HEAD(gray_list); /* search tree for object boundaries */ static struct rb_root object_tree_root = RB_ROOT; /* rw_lock protecting the access to object_list and object_tree_root */ -static DEFINE_RWLOCK(kmemleak_lock); +static DEFINE_RAW_SPINLOCK(kmemleak_lock); /* allocation caches for kmemleak internal data */ static struct kmem_cache *object_cache; @@ -491,9 +491,9 @@ static struct kmemleak_object *find_and_get_object(unsigned long ptr, int alias) struct kmemleak_object *object; rcu_read_lock(); - read_lock_irqsave(&kmemleak_lock, flags); + raw_spin_lock_irqsave(&kmemleak_lock, flags); object = lookup_object(ptr, alias); - read_unlock_irqrestore(&kmemleak_lock, flags); + raw_spin_unlock_irqrestore(&kmemleak_lock, flags); /* check whether the object is still available */ if (object && !get_object(object)) @@ -513,13 +513,13 @@ static struct kmemleak_object *find_and_remove_object(unsigned long ptr, int ali unsigned long flags; struct kmemleak_object *object; - write_lock_irqsave(&kmemleak_lock, flags); + raw_spin_lock_irqsave(&kmemleak_lock, flags); object = lookup_object(ptr, alias); if (object) { rb_erase(&object->rb_node, &object_tree_root); list_del_rcu(&object->object_list); } - write_unlock_irqrestore(&kmemleak_lock, flags); + raw_spin_unlock_irqrestore(&kmemleak_lock, flags); return object; } @@ -593,7 +593,7 @@ static struct kmemleak_object *create_object(unsigned long ptr, size_t size, /* kernel backtrace */ object->trace_len = __save_stack_trace(object->trace); - write_lock_irqsave(&kmemleak_lock, flags); + raw_spin_lock_irqsave(&kmemleak_lock, flags); min_addr = min(min_addr, ptr); max_addr = max(max_addr, ptr + size); @@ -624,7 +624,7 @@ static struct kmemleak_object *create_object(unsigned long ptr, size_t size, list_add_tail_rcu(&object->object_list, &object_list); out: - write_unlock_irqrestore(&kmemleak_lock, flags); + raw_spin_unlock_irqrestore(&kmemleak_lock, flags); return object; } @@ -1310,7 +1310,7 @@ static void scan_block(void *_start, void *_end, unsigned long *end = _end - (BYTES_PER_POINTER - 1); unsigned long flags; - read_lock_irqsave(&kmemleak_lock, flags); + raw_spin_lock_irqsave(&kmemleak_lock, flags); for (ptr = start; ptr < end; ptr++) { struct kmemleak_object *object; unsigned long pointer; @@ -1367,7 +1367,7 @@ static void scan_block(void *_start, void *_end, spin_unlock(&object->lock); } } - read_unlock_irqrestore(&kmemleak_lock, flags); + raw_spin_unlock_irqrestore(&kmemleak_lock, flags); } /* diff --git a/mm/list_lru.c b/mm/list_lru.c index b2a2d3c9b33c..d283025966b1 100644 --- a/mm/list_lru.c +++ b/mm/list_lru.c @@ -190,17 +190,15 @@ unsigned long list_lru_count_node(struct list_lru *lru, int nid) EXPORT_SYMBOL_GPL(list_lru_count_node); static unsigned long -__list_lru_walk_one(struct list_lru *lru, int nid, int memcg_idx, +__list_lru_walk_one(struct list_lru_node *nlru, int memcg_idx, list_lru_walk_cb isolate, void *cb_arg, unsigned long *nr_to_walk) { - struct list_lru_node *nlru = &lru->node[nid]; struct list_lru_one *l; struct list_head *item, *n; unsigned long isolated = 0; - spin_lock(&nlru->lock); l = list_lru_from_memcg_idx(nlru, memcg_idx); restart: list_for_each_safe(item, n, &l->list) { @@ -246,8 +244,6 @@ restart: BUG(); } } - - spin_unlock(&nlru->lock); return isolated; } @@ -256,11 +252,32 @@ list_lru_walk_one(struct list_lru *lru, int nid, struct mem_cgroup *memcg, list_lru_walk_cb isolate, void *cb_arg, unsigned long *nr_to_walk) { - return __list_lru_walk_one(lru, nid, memcg_cache_id(memcg), - isolate, cb_arg, nr_to_walk); + struct list_lru_node *nlru = &lru->node[nid]; + unsigned long ret; + + spin_lock(&nlru->lock); + ret = __list_lru_walk_one(nlru, memcg_cache_id(memcg), isolate, cb_arg, + nr_to_walk); + spin_unlock(&nlru->lock); + return ret; } EXPORT_SYMBOL_GPL(list_lru_walk_one); +unsigned long +list_lru_walk_one_irq(struct list_lru *lru, int nid, struct mem_cgroup *memcg, + list_lru_walk_cb isolate, void *cb_arg, + unsigned long *nr_to_walk) +{ + struct list_lru_node *nlru = &lru->node[nid]; + unsigned long ret; + + spin_lock_irq(&nlru->lock); + ret = __list_lru_walk_one(nlru, memcg_cache_id(memcg), isolate, cb_arg, + nr_to_walk); + spin_unlock_irq(&nlru->lock); + return ret; +} + unsigned long list_lru_walk_node(struct list_lru *lru, int nid, list_lru_walk_cb isolate, void *cb_arg, unsigned long *nr_to_walk) @@ -268,12 +285,18 @@ unsigned long list_lru_walk_node(struct list_lru *lru, int nid, long isolated = 0; int memcg_idx; - isolated += __list_lru_walk_one(lru, nid, -1, isolate, cb_arg, - nr_to_walk); + isolated += list_lru_walk_one(lru, nid, NULL, isolate, cb_arg, + nr_to_walk); if (*nr_to_walk > 0 && list_lru_memcg_aware(lru)) { for_each_memcg_cache_index(memcg_idx) { - isolated += __list_lru_walk_one(lru, nid, memcg_idx, - isolate, cb_arg, nr_to_walk); + struct list_lru_node *nlru = &lru->node[nid]; + + spin_lock(&nlru->lock); + isolated += __list_lru_walk_one(nlru, memcg_idx, + isolate, cb_arg, + nr_to_walk); + spin_unlock(&nlru->lock); + if (*nr_to_walk <= 0) break; } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 662e7e001625..7a5a4d88b56c 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -69,6 +69,7 @@ #include <net/sock.h> #include <net/ip.h> #include "slab.h" +#include <linux/locallock.h> #include <linux/uaccess.h> @@ -94,6 +95,8 @@ int do_swap_account __read_mostly; #define do_swap_account 0 #endif +static DEFINE_LOCAL_IRQ_LOCK(event_lock); + /* Whether legacy memory+swap accounting is active */ static bool do_memsw_account(void) { @@ -1794,7 +1797,7 @@ static void drain_all_stock(struct mem_cgroup *root_memcg) * as well as workers from this path always operate on the local * per-cpu data. CPU up doesn't touch memcg_stock at all. */ - curcpu = get_cpu(); + curcpu = get_cpu_light(); for_each_online_cpu(cpu) { struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu); struct mem_cgroup *memcg; @@ -1814,7 +1817,7 @@ static void drain_all_stock(struct mem_cgroup *root_memcg) } css_put(&memcg->css); } - put_cpu(); + put_cpu_light(); mutex_unlock(&percpu_charge_mutex); } @@ -4583,12 +4586,12 @@ static int mem_cgroup_move_account(struct page *page, ret = 0; - local_irq_disable(); + local_lock_irq(event_lock); mem_cgroup_charge_statistics(to, page, compound, nr_pages); memcg_check_events(to, page); mem_cgroup_charge_statistics(from, page, compound, -nr_pages); memcg_check_events(from, page); - local_irq_enable(); + local_unlock_irq(event_lock); out_unlock: unlock_page(page); out: @@ -5662,10 +5665,10 @@ void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, commit_charge(page, memcg, lrucare); - local_irq_disable(); + local_lock_irq(event_lock); mem_cgroup_charge_statistics(memcg, page, compound, nr_pages); memcg_check_events(memcg, page); - local_irq_enable(); + local_unlock_irq(event_lock); if (do_memsw_account() && PageSwapCache(page)) { swp_entry_t entry = { .val = page_private(page) }; @@ -5734,7 +5737,7 @@ static void uncharge_batch(const struct uncharge_gather *ug) memcg_oom_recover(ug->memcg); } - local_irq_save(flags); + local_lock_irqsave(event_lock, flags); __mod_memcg_state(ug->memcg, MEMCG_RSS, -ug->nr_anon); __mod_memcg_state(ug->memcg, MEMCG_CACHE, -ug->nr_file); __mod_memcg_state(ug->memcg, MEMCG_RSS_HUGE, -ug->nr_huge); @@ -5742,7 +5745,7 @@ static void uncharge_batch(const struct uncharge_gather *ug) __count_memcg_events(ug->memcg, PGPGOUT, ug->pgpgout); __this_cpu_add(ug->memcg->stat_cpu->nr_page_events, nr_pages); memcg_check_events(ug->memcg, ug->dummy_page); - local_irq_restore(flags); + local_unlock_irqrestore(event_lock, flags); if (!mem_cgroup_is_root(ug->memcg)) css_put_many(&ug->memcg->css, nr_pages); @@ -5905,10 +5908,10 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage) commit_charge(newpage, memcg, false); - local_irq_save(flags); + local_lock_irqsave(event_lock, flags); mem_cgroup_charge_statistics(memcg, newpage, compound, nr_pages); memcg_check_events(memcg, newpage); - local_irq_restore(flags); + local_unlock_irqrestore(event_lock, flags); } DEFINE_STATIC_KEY_FALSE(memcg_sockets_enabled_key); @@ -6100,6 +6103,7 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry) struct mem_cgroup *memcg, *swap_memcg; unsigned int nr_entries; unsigned short oldid; + unsigned long flags; VM_BUG_ON_PAGE(PageLRU(page), page); VM_BUG_ON_PAGE(page_count(page), page); @@ -6145,13 +6149,17 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry) * important here to have the interrupts disabled because it is the * only synchronisation we have for updating the per-CPU variables. */ + local_lock_irqsave(event_lock, flags); +#ifndef CONFIG_PREEMPT_RT_BASE VM_BUG_ON(!irqs_disabled()); +#endif mem_cgroup_charge_statistics(memcg, page, PageTransHuge(page), -nr_entries); memcg_check_events(memcg, page); if (!mem_cgroup_is_root(memcg)) css_put_many(&memcg->css, nr_entries); + local_unlock_irqrestore(event_lock, flags); } /** diff --git a/mm/mmu_context.c b/mm/mmu_context.c index 3e612ae748e9..d0ccc070979f 100644 --- a/mm/mmu_context.c +++ b/mm/mmu_context.c @@ -25,6 +25,7 @@ void use_mm(struct mm_struct *mm) struct task_struct *tsk = current; task_lock(tsk); + preempt_disable_rt(); active_mm = tsk->active_mm; if (active_mm != mm) { mmgrab(mm); @@ -32,6 +33,7 @@ void use_mm(struct mm_struct *mm) } tsk->mm = mm; switch_mm(active_mm, mm, tsk); + preempt_enable_rt(); task_unlock(tsk); #ifdef finish_arch_post_lock_switch finish_arch_post_lock_switch(); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 31ba80502df9..c8e172c805fa 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -61,6 +61,7 @@ #include <linux/hugetlb.h> #include <linux/sched/rt.h> #include <linux/sched/mm.h> +#include <linux/locallock.h> #include <linux/page_owner.h> #include <linux/kthread.h> #include <linux/memcontrol.h> @@ -291,6 +292,18 @@ EXPORT_SYMBOL(nr_node_ids); EXPORT_SYMBOL(nr_online_nodes); #endif +static DEFINE_LOCAL_IRQ_LOCK(pa_lock); + +#ifdef CONFIG_PREEMPT_RT_BASE +# define cpu_lock_irqsave(cpu, flags) \ + local_lock_irqsave_on(pa_lock, flags, cpu) +# define cpu_unlock_irqrestore(cpu, flags) \ + local_unlock_irqrestore_on(pa_lock, flags, cpu) +#else +# define cpu_lock_irqsave(cpu, flags) local_irq_save(flags) +# define cpu_unlock_irqrestore(cpu, flags) local_irq_restore(flags) +#endif + int page_group_by_mobility_disabled __read_mostly; #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT @@ -1095,7 +1108,7 @@ static inline void prefetch_buddy(struct page *page) } /* - * Frees a number of pages from the PCP lists + * Frees a number of pages which have been collected from the pcp lists. * Assumes all pages on list are in same zone, and of same order. * count is the number of pages to free. * @@ -1105,15 +1118,57 @@ static inline void prefetch_buddy(struct page *page) * And clear the zone's pages_scanned counter, to hold off the "all pages are * pinned" detection logic. */ -static void free_pcppages_bulk(struct zone *zone, int count, - struct per_cpu_pages *pcp) +static void free_pcppages_bulk(struct zone *zone, struct list_head *head, + bool zone_retry) +{ + bool isolated_pageblocks; + struct page *page, *tmp; + unsigned long flags; + + spin_lock_irqsave(&zone->lock, flags); + isolated_pageblocks = has_isolate_pageblock(zone); + + /* + * Use safe version since after __free_one_page(), + * page->lru.next will not point to original list. + */ + list_for_each_entry_safe(page, tmp, head, lru) { + int mt = get_pcppage_migratetype(page); + + if (page_zone(page) != zone) { + /* + * free_unref_page_list() sorts pages by zone. If we end + * up with pages from a different NUMA nodes belonging + * to the same ZONE index then we need to redo with the + * correct ZONE pointer. Skip the page for now, redo it + * on the next iteration. + */ + WARN_ON_ONCE(zone_retry == false); + if (zone_retry) + continue; + } + + /* MIGRATE_ISOLATE page should not go to pcplists */ + VM_BUG_ON_PAGE(is_migrate_isolate(mt), page); + /* Pageblock could have been isolated meanwhile */ + if (unlikely(isolated_pageblocks)) + mt = get_pageblock_migratetype(page); + + list_del(&page->lru); + __free_one_page(page, page_to_pfn(page), zone, 0, mt); + trace_mm_page_pcpu_drain(page, 0, mt); + } + spin_unlock_irqrestore(&zone->lock, flags); +} + +static void isolate_pcp_pages(int count, struct per_cpu_pages *pcp, + struct list_head *dst) + { int migratetype = 0; int batch_free = 0; int prefetch_nr = 0; - bool isolated_pageblocks; - struct page *page, *tmp; - LIST_HEAD(head); + struct page *page; while (count) { struct list_head *list; @@ -1145,7 +1200,7 @@ static void free_pcppages_bulk(struct zone *zone, int count, if (bulkfree_pcp_prepare(page)) continue; - list_add_tail(&page->lru, &head); + list_add_tail(&page->lru, dst); /* * We are going to put the page back to the global @@ -1160,26 +1215,6 @@ static void free_pcppages_bulk(struct zone *zone, int count, prefetch_buddy(page); } while (--count && --batch_free && !list_empty(list)); } - - spin_lock(&zone->lock); - isolated_pageblocks = has_isolate_pageblock(zone); - - /* - * Use safe version since after __free_one_page(), - * page->lru.next will not point to original list. - */ - list_for_each_entry_safe(page, tmp, &head, lru) { - int mt = get_pcppage_migratetype(page); - /* MIGRATE_ISOLATE page should not go to pcplists */ - VM_BUG_ON_PAGE(is_migrate_isolate(mt), page); - /* Pageblock could have been isolated meanwhile */ - if (unlikely(isolated_pageblocks)) - mt = get_pageblock_migratetype(page); - - __free_one_page(page, page_to_pfn(page), zone, 0, mt); - trace_mm_page_pcpu_drain(page, 0, mt); - } - spin_unlock(&zone->lock); } static void free_one_page(struct zone *zone, @@ -1274,10 +1309,10 @@ static void __free_pages_ok(struct page *page, unsigned int order) return; migratetype = get_pfnblock_migratetype(page, pfn); - local_irq_save(flags); + local_lock_irqsave(pa_lock, flags); __count_vm_events(PGFREE, 1 << order); free_one_page(page_zone(page), page, pfn, order, migratetype); - local_irq_restore(flags); + local_unlock_irqrestore(pa_lock, flags); } static void __init __free_pages_boot_core(struct page *page, unsigned int order) @@ -2536,13 +2571,18 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp) { unsigned long flags; int to_drain, batch; + LIST_HEAD(dst); - local_irq_save(flags); + local_lock_irqsave(pa_lock, flags); batch = READ_ONCE(pcp->batch); to_drain = min(pcp->count, batch); if (to_drain > 0) - free_pcppages_bulk(zone, to_drain, pcp); - local_irq_restore(flags); + isolate_pcp_pages(to_drain, pcp, &dst); + + local_unlock_irqrestore(pa_lock, flags); + + if (to_drain > 0) + free_pcppages_bulk(zone, &dst, false); } #endif @@ -2558,14 +2598,21 @@ static void drain_pages_zone(unsigned int cpu, struct zone *zone) unsigned long flags; struct per_cpu_pageset *pset; struct per_cpu_pages *pcp; + LIST_HEAD(dst); + int count; - local_irq_save(flags); + cpu_lock_irqsave(cpu, flags); pset = per_cpu_ptr(zone->pageset, cpu); pcp = &pset->pcp; - if (pcp->count) - free_pcppages_bulk(zone, pcp->count, pcp); - local_irq_restore(flags); + count = pcp->count; + if (count) + isolate_pcp_pages(count, pcp, &dst); + + cpu_unlock_irqrestore(cpu, flags); + + if (count) + free_pcppages_bulk(zone, &dst, false); } /* @@ -2600,6 +2647,7 @@ void drain_local_pages(struct zone *zone) drain_pages(cpu); } +#ifndef CONFIG_PREEMPT_RT_BASE static void drain_local_pages_wq(struct work_struct *work) { /* @@ -2613,6 +2661,7 @@ static void drain_local_pages_wq(struct work_struct *work) drain_local_pages(NULL); preempt_enable(); } +#endif /* * Spill all the per-cpu pages from all CPUs back into the buddy allocator. @@ -2679,7 +2728,14 @@ void drain_all_pages(struct zone *zone) else cpumask_clear_cpu(cpu, &cpus_with_pcps); } - +#ifdef CONFIG_PREEMPT_RT_BASE + for_each_cpu(cpu, &cpus_with_pcps) { + if (zone) + drain_pages_zone(cpu, zone); + else + drain_pages(cpu); + } +#else for_each_cpu(cpu, &cpus_with_pcps) { struct work_struct *work = per_cpu_ptr(&pcpu_drain, cpu); INIT_WORK(work, drain_local_pages_wq); @@ -2687,6 +2743,7 @@ void drain_all_pages(struct zone *zone) } for_each_cpu(cpu, &cpus_with_pcps) flush_work(per_cpu_ptr(&pcpu_drain, cpu)); +#endif mutex_unlock(&pcpu_drain_mutex); } @@ -2758,7 +2815,8 @@ static bool free_unref_page_prepare(struct page *page, unsigned long pfn) return true; } -static void free_unref_page_commit(struct page *page, unsigned long pfn) +static void free_unref_page_commit(struct page *page, unsigned long pfn, + struct list_head *dst) { struct zone *zone = page_zone(page); struct per_cpu_pages *pcp; @@ -2787,7 +2845,8 @@ static void free_unref_page_commit(struct page *page, unsigned long pfn) pcp->count++; if (pcp->count >= pcp->high) { unsigned long batch = READ_ONCE(pcp->batch); - free_pcppages_bulk(zone, batch, pcp); + + isolate_pcp_pages(batch, pcp, dst); } } @@ -2798,13 +2857,17 @@ void free_unref_page(struct page *page) { unsigned long flags; unsigned long pfn = page_to_pfn(page); + struct zone *zone = page_zone(page); + LIST_HEAD(dst); if (!free_unref_page_prepare(page, pfn)) return; - local_irq_save(flags); - free_unref_page_commit(page, pfn); - local_irq_restore(flags); + local_lock_irqsave(pa_lock, flags); + free_unref_page_commit(page, pfn, &dst); + local_unlock_irqrestore(pa_lock, flags); + if (!list_empty(&dst)) + free_pcppages_bulk(zone, &dst, false); } /* @@ -2815,6 +2878,11 @@ void free_unref_page_list(struct list_head *list) struct page *page, *next; unsigned long flags, pfn; int batch_count = 0; + struct list_head dsts[__MAX_NR_ZONES]; + int i; + + for (i = 0; i < __MAX_NR_ZONES; i++) + INIT_LIST_HEAD(&dsts[i]); /* Prepare pages for freeing */ list_for_each_entry_safe(page, next, list, lru) { @@ -2824,25 +2892,42 @@ void free_unref_page_list(struct list_head *list) set_page_private(page, pfn); } - local_irq_save(flags); + local_lock_irqsave(pa_lock, flags); list_for_each_entry_safe(page, next, list, lru) { unsigned long pfn = page_private(page); + enum zone_type type; set_page_private(page, 0); trace_mm_page_free_batched(page); - free_unref_page_commit(page, pfn); + type = page_zonenum(page); + free_unref_page_commit(page, pfn, &dsts[type]); /* * Guard against excessive IRQ disabled times when we get * a large list of pages to free. */ if (++batch_count == SWAP_CLUSTER_MAX) { - local_irq_restore(flags); + local_unlock_irqrestore(pa_lock, flags); batch_count = 0; - local_irq_save(flags); + local_lock_irqsave(pa_lock, flags); } } - local_irq_restore(flags); + local_unlock_irqrestore(pa_lock, flags); + + for (i = 0; i < __MAX_NR_ZONES; ) { + struct page *page; + struct zone *zone; + + if (list_empty(&dsts[i])) { + i++; + continue; + } + + page = list_first_entry(&dsts[i], struct page, lru); + zone = page_zone(page); + + free_pcppages_bulk(zone, &dsts[i], true); + } } /* @@ -2976,7 +3061,7 @@ static struct page *rmqueue_pcplist(struct zone *preferred_zone, struct page *page; unsigned long flags; - local_irq_save(flags); + local_lock_irqsave(pa_lock, flags); pcp = &this_cpu_ptr(zone->pageset)->pcp; list = &pcp->lists[migratetype]; page = __rmqueue_pcplist(zone, migratetype, pcp, list); @@ -2984,7 +3069,7 @@ static struct page *rmqueue_pcplist(struct zone *preferred_zone, __count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order); zone_statistics(preferred_zone, zone); } - local_irq_restore(flags); + local_unlock_irqrestore(pa_lock, flags); return page; } @@ -3011,7 +3096,7 @@ struct page *rmqueue(struct zone *preferred_zone, * allocate greater than order-1 page units with __GFP_NOFAIL. */ WARN_ON_ONCE((gfp_flags & __GFP_NOFAIL) && (order > 1)); - spin_lock_irqsave(&zone->lock, flags); + local_spin_lock_irqsave(pa_lock, &zone->lock, flags); do { page = NULL; @@ -3031,14 +3116,14 @@ struct page *rmqueue(struct zone *preferred_zone, __count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order); zone_statistics(preferred_zone, zone); - local_irq_restore(flags); + local_unlock_irqrestore(pa_lock, flags); out: VM_BUG_ON_PAGE(page && bad_range(zone, page), page); return page; failed: - local_irq_restore(flags); + local_unlock_irqrestore(pa_lock, flags); return NULL; } @@ -7087,8 +7172,9 @@ void __init free_area_init(unsigned long *zones_size) static int page_alloc_cpu_dead(unsigned int cpu) { - + local_lock_irq_on(swapvec_lock, cpu); lru_add_drain_cpu(cpu); + local_unlock_irq_on(swapvec_lock, cpu); drain_pages(cpu); /* @@ -7999,7 +8085,7 @@ void zone_pcp_reset(struct zone *zone) struct per_cpu_pageset *pset; /* avoid races with drain_pages() */ - local_irq_save(flags); + local_lock_irqsave(pa_lock, flags); if (zone->pageset != &boot_pageset) { for_each_online_cpu(cpu) { pset = per_cpu_ptr(zone->pageset, cpu); @@ -8008,7 +8094,7 @@ void zone_pcp_reset(struct zone *zone) free_percpu(zone->pageset); zone->pageset = &boot_pageset; } - local_irq_restore(flags); + local_unlock_irqrestore(pa_lock, flags); } #ifdef CONFIG_MEMORY_HOTREMOVE diff --git a/mm/slab.c b/mm/slab.c index 46f21e73db2f..38f6609343b3 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -233,7 +233,7 @@ static void kmem_cache_node_init(struct kmem_cache_node *parent) parent->shared = NULL; parent->alien = NULL; parent->colour_next = 0; - spin_lock_init(&parent->list_lock); + raw_spin_lock_init(&parent->list_lock); parent->free_objects = 0; parent->free_touched = 0; } @@ -600,9 +600,9 @@ static noinline void cache_free_pfmemalloc(struct kmem_cache *cachep, page_node = page_to_nid(page); n = get_node(cachep, page_node); - spin_lock(&n->list_lock); + raw_spin_lock(&n->list_lock); free_block(cachep, &objp, 1, page_node, &list); - spin_unlock(&n->list_lock); + raw_spin_unlock(&n->list_lock); slabs_destroy(cachep, &list); } @@ -731,7 +731,7 @@ static void __drain_alien_cache(struct kmem_cache *cachep, struct kmem_cache_node *n = get_node(cachep, node); if (ac->avail) { - spin_lock(&n->list_lock); + raw_spin_lock(&n->list_lock); /* * Stuff objects into the remote nodes shared array first. * That way we could avoid the overhead of putting the objects @@ -742,7 +742,7 @@ static void __drain_alien_cache(struct kmem_cache *cachep, free_block(cachep, ac->entry, ac->avail, node, list); ac->avail = 0; - spin_unlock(&n->list_lock); + raw_spin_unlock(&n->list_lock); } } @@ -815,9 +815,9 @@ static int __cache_free_alien(struct kmem_cache *cachep, void *objp, slabs_destroy(cachep, &list); } else { n = get_node(cachep, page_node); - spin_lock(&n->list_lock); + raw_spin_lock(&n->list_lock); free_block(cachep, &objp, 1, page_node, &list); - spin_unlock(&n->list_lock); + raw_spin_unlock(&n->list_lock); slabs_destroy(cachep, &list); } return 1; @@ -858,10 +858,10 @@ static int init_cache_node(struct kmem_cache *cachep, int node, gfp_t gfp) */ n = get_node(cachep, node); if (n) { - spin_lock_irq(&n->list_lock); + raw_spin_lock_irq(&n->list_lock); n->free_limit = (1 + nr_cpus_node(node)) * cachep->batchcount + cachep->num; - spin_unlock_irq(&n->list_lock); + raw_spin_unlock_irq(&n->list_lock); return 0; } @@ -940,7 +940,7 @@ static int setup_kmem_cache_node(struct kmem_cache *cachep, goto fail; n = get_node(cachep, node); - spin_lock_irq(&n->list_lock); + raw_spin_lock_irq(&n->list_lock); if (n->shared && force_change) { free_block(cachep, n->shared->entry, n->shared->avail, node, &list); @@ -958,7 +958,7 @@ static int setup_kmem_cache_node(struct kmem_cache *cachep, new_alien = NULL; } - spin_unlock_irq(&n->list_lock); + raw_spin_unlock_irq(&n->list_lock); slabs_destroy(cachep, &list); /* @@ -997,7 +997,7 @@ static void cpuup_canceled(long cpu) if (!n) continue; - spin_lock_irq(&n->list_lock); + raw_spin_lock_irq(&n->list_lock); /* Free limit for this kmem_cache_node */ n->free_limit -= cachep->batchcount; @@ -1010,7 +1010,7 @@ static void cpuup_canceled(long cpu) } if (!cpumask_empty(mask)) { - spin_unlock_irq(&n->list_lock); + raw_spin_unlock_irq(&n->list_lock); goto free_slab; } @@ -1024,7 +1024,7 @@ static void cpuup_canceled(long cpu) alien = n->alien; n->alien = NULL; - spin_unlock_irq(&n->list_lock); + raw_spin_unlock_irq(&n->list_lock); kfree(shared); if (alien) { @@ -1208,7 +1208,7 @@ static void __init init_list(struct kmem_cache *cachep, struct kmem_cache_node * /* * Do not assume that spinlocks can be initialized via memcpy: */ - spin_lock_init(&ptr->list_lock); + raw_spin_lock_init(&ptr->list_lock); MAKE_ALL_LISTS(cachep, ptr, nodeid); cachep->node[nodeid] = ptr; @@ -1379,11 +1379,11 @@ slab_out_of_memory(struct kmem_cache *cachep, gfp_t gfpflags, int nodeid) for_each_kmem_cache_node(cachep, node, n) { unsigned long total_slabs, free_slabs, free_objs; - spin_lock_irqsave(&n->list_lock, flags); + raw_spin_lock_irqsave(&n->list_lock, flags); total_slabs = n->total_slabs; free_slabs = n->free_slabs; free_objs = n->free_objects; - spin_unlock_irqrestore(&n->list_lock, flags); + raw_spin_unlock_irqrestore(&n->list_lock, flags); pr_warn(" node %d: slabs: %ld/%ld, objs: %ld/%ld\n", node, total_slabs - free_slabs, total_slabs, @@ -2178,7 +2178,7 @@ static void check_spinlock_acquired(struct kmem_cache *cachep) { #ifdef CONFIG_SMP check_irq_off(); - assert_spin_locked(&get_node(cachep, numa_mem_id())->list_lock); + assert_raw_spin_locked(&get_node(cachep, numa_mem_id())->list_lock); #endif } @@ -2186,7 +2186,7 @@ static void check_spinlock_acquired_node(struct kmem_cache *cachep, int node) { #ifdef CONFIG_SMP check_irq_off(); - assert_spin_locked(&get_node(cachep, node)->list_lock); + assert_raw_spin_locked(&get_node(cachep, node)->list_lock); #endif } @@ -2226,9 +2226,9 @@ static void do_drain(void *arg) check_irq_off(); ac = cpu_cache_get(cachep); n = get_node(cachep, node); - spin_lock(&n->list_lock); + raw_spin_lock(&n->list_lock); free_block(cachep, ac->entry, ac->avail, node, &list); - spin_unlock(&n->list_lock); + raw_spin_unlock(&n->list_lock); slabs_destroy(cachep, &list); ac->avail = 0; } @@ -2246,9 +2246,9 @@ static void drain_cpu_caches(struct kmem_cache *cachep) drain_alien_cache(cachep, n->alien); for_each_kmem_cache_node(cachep, node, n) { - spin_lock_irq(&n->list_lock); + raw_spin_lock_irq(&n->list_lock); drain_array_locked(cachep, n->shared, node, true, &list); - spin_unlock_irq(&n->list_lock); + raw_spin_unlock_irq(&n->list_lock); slabs_destroy(cachep, &list); } @@ -2270,10 +2270,10 @@ static int drain_freelist(struct kmem_cache *cache, nr_freed = 0; while (nr_freed < tofree && !list_empty(&n->slabs_free)) { - spin_lock_irq(&n->list_lock); + raw_spin_lock_irq(&n->list_lock); p = n->slabs_free.prev; if (p == &n->slabs_free) { - spin_unlock_irq(&n->list_lock); + raw_spin_unlock_irq(&n->list_lock); goto out; } @@ -2286,7 +2286,7 @@ static int drain_freelist(struct kmem_cache *cache, * to the cache. */ n->free_objects -= cache->num; - spin_unlock_irq(&n->list_lock); + raw_spin_unlock_irq(&n->list_lock); slab_destroy(cache, page); nr_freed++; } @@ -2734,7 +2734,7 @@ static void cache_grow_end(struct kmem_cache *cachep, struct page *page) INIT_LIST_HEAD(&page->lru); n = get_node(cachep, page_to_nid(page)); - spin_lock(&n->list_lock); + raw_spin_lock(&n->list_lock); n->total_slabs++; if (!page->active) { list_add_tail(&page->lru, &(n->slabs_free)); @@ -2744,7 +2744,7 @@ static void cache_grow_end(struct kmem_cache *cachep, struct page *page) STATS_INC_GROWN(cachep); n->free_objects += cachep->num - page->active; - spin_unlock(&n->list_lock); + raw_spin_unlock(&n->list_lock); fixup_objfreelist_debug(cachep, &list); } @@ -2912,7 +2912,7 @@ static struct page *get_first_slab(struct kmem_cache_node *n, bool pfmemalloc) { struct page *page; - assert_spin_locked(&n->list_lock); + assert_raw_spin_locked(&n->list_lock); page = list_first_entry_or_null(&n->slabs_partial, struct page, lru); if (!page) { n->free_touched = 1; @@ -2938,10 +2938,10 @@ static noinline void *cache_alloc_pfmemalloc(struct kmem_cache *cachep, if (!gfp_pfmemalloc_allowed(flags)) return NULL; - spin_lock(&n->list_lock); + raw_spin_lock(&n->list_lock); page = get_first_slab(n, true); if (!page) { - spin_unlock(&n->list_lock); + raw_spin_unlock(&n->list_lock); return NULL; } @@ -2950,7 +2950,7 @@ static noinline void *cache_alloc_pfmemalloc(struct kmem_cache *cachep, fixup_slab_list(cachep, n, page, &list); - spin_unlock(&n->list_lock); + raw_spin_unlock(&n->list_lock); fixup_objfreelist_debug(cachep, &list); return obj; @@ -3009,7 +3009,7 @@ static void *cache_alloc_refill(struct kmem_cache *cachep, gfp_t flags) if (!n->free_objects && (!shared || !shared->avail)) goto direct_grow; - spin_lock(&n->list_lock); + raw_spin_lock(&n->list_lock); shared = READ_ONCE(n->shared); /* See if we can refill from the shared array */ @@ -3033,7 +3033,7 @@ static void *cache_alloc_refill(struct kmem_cache *cachep, gfp_t flags) must_grow: n->free_objects -= ac->avail; alloc_done: - spin_unlock(&n->list_lock); + raw_spin_unlock(&n->list_lock); fixup_objfreelist_debug(cachep, &list); direct_grow: @@ -3258,7 +3258,7 @@ static void *____cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, BUG_ON(!n); check_irq_off(); - spin_lock(&n->list_lock); + raw_spin_lock(&n->list_lock); page = get_first_slab(n, false); if (!page) goto must_grow; @@ -3276,12 +3276,12 @@ static void *____cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, fixup_slab_list(cachep, n, page, &list); - spin_unlock(&n->list_lock); + raw_spin_unlock(&n->list_lock); fixup_objfreelist_debug(cachep, &list); return obj; must_grow: - spin_unlock(&n->list_lock); + raw_spin_unlock(&n->list_lock); page = cache_grow_begin(cachep, gfp_exact_node(flags), nodeid); if (page) { /* This slab isn't counted yet so don't update free_objects */ @@ -3457,7 +3457,7 @@ static void cache_flusharray(struct kmem_cache *cachep, struct array_cache *ac) check_irq_off(); n = get_node(cachep, node); - spin_lock(&n->list_lock); + raw_spin_lock(&n->list_lock); if (n->shared) { struct array_cache *shared_array = n->shared; int max = shared_array->limit - shared_array->avail; @@ -3486,7 +3486,7 @@ free_done: STATS_SET_FREEABLE(cachep, i); } #endif - spin_unlock(&n->list_lock); + raw_spin_unlock(&n->list_lock); slabs_destroy(cachep, &list); ac->avail -= batchcount; memmove(ac->entry, &(ac->entry[batchcount]), sizeof(void *)*ac->avail); @@ -3896,9 +3896,9 @@ static int __do_tune_cpucache(struct kmem_cache *cachep, int limit, node = cpu_to_mem(cpu); n = get_node(cachep, node); - spin_lock_irq(&n->list_lock); + raw_spin_lock_irq(&n->list_lock); free_block(cachep, ac->entry, ac->avail, node, &list); - spin_unlock_irq(&n->list_lock); + raw_spin_unlock_irq(&n->list_lock); slabs_destroy(cachep, &list); } free_percpu(prev); @@ -4023,9 +4023,9 @@ static void drain_array(struct kmem_cache *cachep, struct kmem_cache_node *n, return; } - spin_lock_irq(&n->list_lock); + raw_spin_lock_irq(&n->list_lock); drain_array_locked(cachep, ac, node, false, &list); - spin_unlock_irq(&n->list_lock); + raw_spin_unlock_irq(&n->list_lock); slabs_destroy(cachep, &list); } @@ -4109,7 +4109,7 @@ void get_slabinfo(struct kmem_cache *cachep, struct slabinfo *sinfo) for_each_kmem_cache_node(cachep, node, n) { check_irq_on(); - spin_lock_irq(&n->list_lock); + raw_spin_lock_irq(&n->list_lock); total_slabs += n->total_slabs; free_slabs += n->free_slabs; @@ -4118,7 +4118,7 @@ void get_slabinfo(struct kmem_cache *cachep, struct slabinfo *sinfo) if (n->shared) shared_avail += n->shared->avail; - spin_unlock_irq(&n->list_lock); + raw_spin_unlock_irq(&n->list_lock); } num_objs = total_slabs * cachep->num; active_slabs = total_slabs - free_slabs; @@ -4338,13 +4338,13 @@ static int leaks_show(struct seq_file *m, void *p) for_each_kmem_cache_node(cachep, node, n) { check_irq_on(); - spin_lock_irq(&n->list_lock); + raw_spin_lock_irq(&n->list_lock); list_for_each_entry(page, &n->slabs_full, lru) handle_slab(x, cachep, page); list_for_each_entry(page, &n->slabs_partial, lru) handle_slab(x, cachep, page); - spin_unlock_irq(&n->list_lock); + raw_spin_unlock_irq(&n->list_lock); } } while (!is_store_user_clean(cachep)); diff --git a/mm/slab.h b/mm/slab.h index 797d0334fe6d..c28040a42bbf 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -454,7 +454,7 @@ static inline void slab_post_alloc_hook(struct kmem_cache *s, gfp_t flags, * The slab lists for all objects. */ struct kmem_cache_node { - spinlock_t list_lock; + raw_spinlock_t list_lock; #ifdef CONFIG_SLAB struct list_head slabs_partial; /* partial list first, better asm code */ diff --git a/mm/slub.c b/mm/slub.c index 197e90574f3d..ce980d50c0bb 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1169,7 +1169,7 @@ static noinline int free_debug_processing( unsigned long uninitialized_var(flags); int ret = 0; - spin_lock_irqsave(&n->list_lock, flags); + raw_spin_lock_irqsave(&n->list_lock, flags); slab_lock(page); if (s->flags & SLAB_CONSISTENCY_CHECKS) { @@ -1204,7 +1204,7 @@ out: bulk_cnt, cnt); slab_unlock(page); - spin_unlock_irqrestore(&n->list_lock, flags); + raw_spin_unlock_irqrestore(&n->list_lock, flags); if (!ret) slab_fix(s, "Object at 0x%p not freed", object); return ret; @@ -1332,6 +1332,12 @@ static inline void dec_slabs_node(struct kmem_cache *s, int node, #endif /* CONFIG_SLUB_DEBUG */ +struct slub_free_list { + raw_spinlock_t lock; + struct list_head list; +}; +static DEFINE_PER_CPU(struct slub_free_list, slub_free_list); + /* * Hooks for other subsystems that check memory allocations. In a typical * production configuration these hooks all should produce no code at all. @@ -1566,10 +1572,17 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node) void *start, *p; int idx, order; bool shuffle; + bool enableirqs = false; flags &= gfp_allowed_mask; if (gfpflags_allow_blocking(flags)) + enableirqs = true; +#ifdef CONFIG_PREEMPT_RT_FULL + if (system_state > SYSTEM_BOOTING) + enableirqs = true; +#endif + if (enableirqs) local_irq_enable(); flags |= s->allocflags; @@ -1628,7 +1641,7 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node) page->frozen = 1; out: - if (gfpflags_allow_blocking(flags)) + if (enableirqs) local_irq_disable(); if (!page) return NULL; @@ -1686,6 +1699,16 @@ static void __free_slab(struct kmem_cache *s, struct page *page) __free_pages(page, order); } +static void free_delayed(struct list_head *h) +{ + while (!list_empty(h)) { + struct page *page = list_first_entry(h, struct page, lru); + + list_del(&page->lru); + __free_slab(page->slab_cache, page); + } +} + static void rcu_free_slab(struct rcu_head *h) { struct page *page = container_of(h, struct page, rcu_head); @@ -1697,6 +1720,12 @@ static void free_slab(struct kmem_cache *s, struct page *page) { if (unlikely(s->flags & SLAB_TYPESAFE_BY_RCU)) { call_rcu(&page->rcu_head, rcu_free_slab); + } else if (irqs_disabled()) { + struct slub_free_list *f = this_cpu_ptr(&slub_free_list); + + raw_spin_lock(&f->lock); + list_add(&page->lru, &f->list); + raw_spin_unlock(&f->lock); } else __free_slab(s, page); } @@ -1804,7 +1833,7 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n, if (!n || !n->nr_partial) return NULL; - spin_lock(&n->list_lock); + raw_spin_lock(&n->list_lock); list_for_each_entry_safe(page, page2, &n->partial, lru) { void *t; @@ -1829,7 +1858,7 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n, break; } - spin_unlock(&n->list_lock); + raw_spin_unlock(&n->list_lock); return object; } @@ -2075,7 +2104,7 @@ redo: * that acquire_slab() will see a slab page that * is frozen */ - spin_lock(&n->list_lock); + raw_spin_lock(&n->list_lock); } } else { m = M_FULL; @@ -2086,7 +2115,7 @@ redo: * slabs from diagnostic functions will not see * any frozen slabs. */ - spin_lock(&n->list_lock); + raw_spin_lock(&n->list_lock); } } @@ -2121,7 +2150,7 @@ redo: goto redo; if (lock) - spin_unlock(&n->list_lock); + raw_spin_unlock(&n->list_lock); if (m == M_FREE) { stat(s, DEACTIVATE_EMPTY); @@ -2156,10 +2185,10 @@ static void unfreeze_partials(struct kmem_cache *s, n2 = get_node(s, page_to_nid(page)); if (n != n2) { if (n) - spin_unlock(&n->list_lock); + raw_spin_unlock(&n->list_lock); n = n2; - spin_lock(&n->list_lock); + raw_spin_lock(&n->list_lock); } do { @@ -2188,7 +2217,7 @@ static void unfreeze_partials(struct kmem_cache *s, } if (n) - spin_unlock(&n->list_lock); + raw_spin_unlock(&n->list_lock); while (discard_page) { page = discard_page; @@ -2225,14 +2254,21 @@ static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain) pobjects = oldpage->pobjects; pages = oldpage->pages; if (drain && pobjects > s->cpu_partial) { + struct slub_free_list *f; unsigned long flags; + LIST_HEAD(tofree); /* * partial array is full. Move the existing * set to the per node partial list. */ local_irq_save(flags); unfreeze_partials(s, this_cpu_ptr(s->cpu_slab)); + f = this_cpu_ptr(&slub_free_list); + raw_spin_lock(&f->lock); + list_splice_init(&f->list, &tofree); + raw_spin_unlock(&f->lock); local_irq_restore(flags); + free_delayed(&tofree); oldpage = NULL; pobjects = 0; pages = 0; @@ -2302,7 +2338,22 @@ static bool has_cpu_slab(int cpu, void *info) static void flush_all(struct kmem_cache *s) { + LIST_HEAD(tofree); + int cpu; + on_each_cpu_cond(has_cpu_slab, flush_cpu_slab, s, 1, GFP_ATOMIC); + for_each_online_cpu(cpu) { + struct slub_free_list *f; + + if (!has_cpu_slab(cpu, s)) + continue; + + f = &per_cpu(slub_free_list, cpu); + raw_spin_lock_irq(&f->lock); + list_splice_init(&f->list, &tofree); + raw_spin_unlock_irq(&f->lock); + free_delayed(&tofree); + } } /* @@ -2357,10 +2408,10 @@ static unsigned long count_partial(struct kmem_cache_node *n, unsigned long x = 0; struct page *page; - spin_lock_irqsave(&n->list_lock, flags); + raw_spin_lock_irqsave(&n->list_lock, flags); list_for_each_entry(page, &n->partial, lru) x += get_count(page); - spin_unlock_irqrestore(&n->list_lock, flags); + raw_spin_unlock_irqrestore(&n->list_lock, flags); return x; } #endif /* CONFIG_SLUB_DEBUG || CONFIG_SYSFS */ @@ -2500,8 +2551,10 @@ static inline void *get_freelist(struct kmem_cache *s, struct page *page) * already disabled (which is the case for bulk allocation). */ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, - unsigned long addr, struct kmem_cache_cpu *c) + unsigned long addr, struct kmem_cache_cpu *c, + struct list_head *to_free) { + struct slub_free_list *f; void *freelist; struct page *page; @@ -2557,6 +2610,13 @@ load_freelist: VM_BUG_ON(!c->page->frozen); c->freelist = get_freepointer(s, freelist); c->tid = next_tid(c->tid); + +out: + f = this_cpu_ptr(&slub_free_list); + raw_spin_lock(&f->lock); + list_splice_init(&f->list, to_free); + raw_spin_unlock(&f->lock); + return freelist; new_slab: @@ -2572,7 +2632,7 @@ new_slab: if (unlikely(!freelist)) { slab_out_of_memory(s, gfpflags, node); - return NULL; + goto out; } page = c->page; @@ -2585,7 +2645,7 @@ new_slab: goto new_slab; /* Slab failed checks. Next slab needed */ deactivate_slab(s, page, get_freepointer(s, freelist), c); - return freelist; + goto out; } /* @@ -2597,6 +2657,7 @@ static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, { void *p; unsigned long flags; + LIST_HEAD(tofree); local_irq_save(flags); #ifdef CONFIG_PREEMPT @@ -2608,8 +2669,9 @@ static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, c = this_cpu_ptr(s->cpu_slab); #endif - p = ___slab_alloc(s, gfpflags, node, addr, c); + p = ___slab_alloc(s, gfpflags, node, addr, c, &tofree); local_irq_restore(flags); + free_delayed(&tofree); return p; } @@ -2795,7 +2857,7 @@ static void __slab_free(struct kmem_cache *s, struct page *page, do { if (unlikely(n)) { - spin_unlock_irqrestore(&n->list_lock, flags); + raw_spin_unlock_irqrestore(&n->list_lock, flags); n = NULL; } prior = page->freelist; @@ -2827,7 +2889,7 @@ static void __slab_free(struct kmem_cache *s, struct page *page, * Otherwise the list_lock will synchronize with * other processors updating the list of slabs. */ - spin_lock_irqsave(&n->list_lock, flags); + raw_spin_lock_irqsave(&n->list_lock, flags); } } @@ -2869,7 +2931,7 @@ static void __slab_free(struct kmem_cache *s, struct page *page, add_partial(n, page, DEACTIVATE_TO_TAIL); stat(s, FREE_ADD_PARTIAL); } - spin_unlock_irqrestore(&n->list_lock, flags); + raw_spin_unlock_irqrestore(&n->list_lock, flags); return; slab_empty: @@ -2884,7 +2946,7 @@ slab_empty: remove_full(s, n, page); } - spin_unlock_irqrestore(&n->list_lock, flags); + raw_spin_unlock_irqrestore(&n->list_lock, flags); stat(s, FREE_SLAB); discard_slab(s, page); } @@ -3087,6 +3149,7 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, void **p) { struct kmem_cache_cpu *c; + LIST_HEAD(to_free); int i; /* memcg and kmem_cache debug support */ @@ -3110,7 +3173,7 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, * of re-populating per CPU c->freelist */ p[i] = ___slab_alloc(s, flags, NUMA_NO_NODE, - _RET_IP_, c); + _RET_IP_, c, &to_free); if (unlikely(!p[i])) goto error; @@ -3122,6 +3185,7 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, } c->tid = next_tid(c->tid); local_irq_enable(); + free_delayed(&to_free); /* Clear memory outside IRQ disabled fastpath loop */ if (unlikely(flags & __GFP_ZERO)) { @@ -3136,6 +3200,7 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, return i; error: local_irq_enable(); + free_delayed(&to_free); slab_post_alloc_hook(s, flags, i, p); __kmem_cache_free_bulk(s, i, p); return 0; @@ -3271,7 +3336,7 @@ static void init_kmem_cache_node(struct kmem_cache_node *n) { n->nr_partial = 0; - spin_lock_init(&n->list_lock); + raw_spin_lock_init(&n->list_lock); INIT_LIST_HEAD(&n->partial); #ifdef CONFIG_SLUB_DEBUG atomic_long_set(&n->nr_slabs, 0); @@ -3624,6 +3689,11 @@ static void list_slab_objects(struct kmem_cache *s, struct page *page, const char *text) { #ifdef CONFIG_SLUB_DEBUG +#ifdef CONFIG_PREEMPT_RT_BASE + /* XXX move out of irq-off section */ + slab_err(s, page, text, s->name); +#else + void *addr = page_address(page); void *p; unsigned long *map = kcalloc(BITS_TO_LONGS(page->objects), @@ -3645,6 +3715,7 @@ static void list_slab_objects(struct kmem_cache *s, struct page *page, slab_unlock(page); kfree(map); #endif +#endif } /* @@ -3658,7 +3729,7 @@ static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n) struct page *page, *h; BUG_ON(irqs_disabled()); - spin_lock_irq(&n->list_lock); + raw_spin_lock_irq(&n->list_lock); list_for_each_entry_safe(page, h, &n->partial, lru) { if (!page->inuse) { remove_partial(n, page); @@ -3668,7 +3739,7 @@ static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n) "Objects remaining in %s on __kmem_cache_shutdown()"); } } - spin_unlock_irq(&n->list_lock); + raw_spin_unlock_irq(&n->list_lock); list_for_each_entry_safe(page, h, &discard, lru) discard_slab(s, page); @@ -3941,7 +4012,7 @@ int __kmem_cache_shrink(struct kmem_cache *s) for (i = 0; i < SHRINK_PROMOTE_MAX; i++) INIT_LIST_HEAD(promote + i); - spin_lock_irqsave(&n->list_lock, flags); + raw_spin_lock_irqsave(&n->list_lock, flags); /* * Build lists of slabs to discard or promote. @@ -3972,7 +4043,7 @@ int __kmem_cache_shrink(struct kmem_cache *s) for (i = SHRINK_PROMOTE_MAX - 1; i >= 0; i--) list_splice(promote + i, &n->partial); - spin_unlock_irqrestore(&n->list_lock, flags); + raw_spin_unlock_irqrestore(&n->list_lock, flags); /* Release empty slabs */ list_for_each_entry_safe(page, t, &discard, lru) @@ -4185,6 +4256,12 @@ void __init kmem_cache_init(void) { static __initdata struct kmem_cache boot_kmem_cache, boot_kmem_cache_node; + int cpu; + + for_each_possible_cpu(cpu) { + raw_spin_lock_init(&per_cpu(slub_free_list, cpu).lock); + INIT_LIST_HEAD(&per_cpu(slub_free_list, cpu).list); + } if (debug_guardpage_minorder()) slub_max_order = 0; @@ -4386,7 +4463,7 @@ static int validate_slab_node(struct kmem_cache *s, struct page *page; unsigned long flags; - spin_lock_irqsave(&n->list_lock, flags); + raw_spin_lock_irqsave(&n->list_lock, flags); list_for_each_entry(page, &n->partial, lru) { validate_slab_slab(s, page, map); @@ -4408,7 +4485,7 @@ static int validate_slab_node(struct kmem_cache *s, s->name, count, atomic_long_read(&n->nr_slabs)); out: - spin_unlock_irqrestore(&n->list_lock, flags); + raw_spin_unlock_irqrestore(&n->list_lock, flags); return count; } @@ -4598,12 +4675,12 @@ static int list_locations(struct kmem_cache *s, char *buf, if (!atomic_long_read(&n->nr_slabs)) continue; - spin_lock_irqsave(&n->list_lock, flags); + raw_spin_lock_irqsave(&n->list_lock, flags); list_for_each_entry(page, &n->partial, lru) process_slab(&t, s, page, alloc, map); list_for_each_entry(page, &n->full, lru) process_slab(&t, s, page, alloc, map); - spin_unlock_irqrestore(&n->list_lock, flags); + raw_spin_unlock_irqrestore(&n->list_lock, flags); } for (i = 0; i < t.count; i++) { diff --git a/mm/swap.c b/mm/swap.c index a3fc028e338e..9217027671c8 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -33,6 +33,7 @@ #include <linux/memcontrol.h> #include <linux/gfp.h> #include <linux/uio.h> +#include <linux/locallock.h> #include <linux/hugetlb.h> #include <linux/page_idle.h> @@ -51,6 +52,8 @@ static DEFINE_PER_CPU(struct pagevec, lru_lazyfree_pvecs); #ifdef CONFIG_SMP static DEFINE_PER_CPU(struct pagevec, activate_page_pvecs); #endif +static DEFINE_LOCAL_IRQ_LOCK(rotate_lock); +DEFINE_LOCAL_IRQ_LOCK(swapvec_lock); /* * This path almost never happens for VM activity - pages are normally @@ -253,11 +256,11 @@ void rotate_reclaimable_page(struct page *page) unsigned long flags; get_page(page); - local_irq_save(flags); + local_lock_irqsave(rotate_lock, flags); pvec = this_cpu_ptr(&lru_rotate_pvecs); if (!pagevec_add(pvec, page) || PageCompound(page)) pagevec_move_tail(pvec); - local_irq_restore(flags); + local_unlock_irqrestore(rotate_lock, flags); } } @@ -307,12 +310,13 @@ void activate_page(struct page *page) { page = compound_head(page); if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) { - struct pagevec *pvec = &get_cpu_var(activate_page_pvecs); + struct pagevec *pvec = &get_locked_var(swapvec_lock, + activate_page_pvecs); get_page(page); if (!pagevec_add(pvec, page) || PageCompound(page)) pagevec_lru_move_fn(pvec, __activate_page, NULL); - put_cpu_var(activate_page_pvecs); + put_locked_var(swapvec_lock, activate_page_pvecs); } } @@ -321,6 +325,11 @@ static inline void activate_page_drain(int cpu) { } +static bool need_activate_page_drain(int cpu) +{ + return false; +} + void activate_page(struct page *page) { struct zone *zone = page_zone(page); @@ -334,7 +343,7 @@ void activate_page(struct page *page) static void __lru_cache_activate_page(struct page *page) { - struct pagevec *pvec = &get_cpu_var(lru_add_pvec); + struct pagevec *pvec = &get_locked_var(swapvec_lock, lru_add_pvec); int i; /* @@ -356,7 +365,7 @@ static void __lru_cache_activate_page(struct page *page) } } - put_cpu_var(lru_add_pvec); + put_locked_var(swapvec_lock, lru_add_pvec); } /* @@ -398,12 +407,12 @@ EXPORT_SYMBOL(mark_page_accessed); static void __lru_cache_add(struct page *page) { - struct pagevec *pvec = &get_cpu_var(lru_add_pvec); + struct pagevec *pvec = &get_locked_var(swapvec_lock, lru_add_pvec); get_page(page); if (!pagevec_add(pvec, page) || PageCompound(page)) __pagevec_lru_add(pvec); - put_cpu_var(lru_add_pvec); + put_locked_var(swapvec_lock, lru_add_pvec); } /** @@ -581,9 +590,15 @@ void lru_add_drain_cpu(int cpu) unsigned long flags; /* No harm done if a racing interrupt already did this */ - local_irq_save(flags); +#ifdef CONFIG_PREEMPT_RT_BASE + local_lock_irqsave_on(rotate_lock, flags, cpu); pagevec_move_tail(pvec); - local_irq_restore(flags); + local_unlock_irqrestore_on(rotate_lock, flags, cpu); +#else + local_lock_irqsave(rotate_lock, flags); + pagevec_move_tail(pvec); + local_unlock_irqrestore(rotate_lock, flags); +#endif } pvec = &per_cpu(lru_deactivate_file_pvecs, cpu); @@ -615,11 +630,12 @@ void deactivate_file_page(struct page *page) return; if (likely(get_page_unless_zero(page))) { - struct pagevec *pvec = &get_cpu_var(lru_deactivate_file_pvecs); + struct pagevec *pvec = &get_locked_var(swapvec_lock, + lru_deactivate_file_pvecs); if (!pagevec_add(pvec, page) || PageCompound(page)) pagevec_lru_move_fn(pvec, lru_deactivate_file_fn, NULL); - put_cpu_var(lru_deactivate_file_pvecs); + put_locked_var(swapvec_lock, lru_deactivate_file_pvecs); } } @@ -634,30 +650,49 @@ void mark_page_lazyfree(struct page *page) { if (PageLRU(page) && PageAnon(page) && PageSwapBacked(page) && !PageSwapCache(page) && !PageUnevictable(page)) { - struct pagevec *pvec = &get_cpu_var(lru_lazyfree_pvecs); + struct pagevec *pvec = &get_locked_var(swapvec_lock, + lru_lazyfree_pvecs); get_page(page); if (!pagevec_add(pvec, page) || PageCompound(page)) pagevec_lru_move_fn(pvec, lru_lazyfree_fn, NULL); - put_cpu_var(lru_lazyfree_pvecs); + put_locked_var(swapvec_lock, lru_lazyfree_pvecs); } } void lru_add_drain(void) { - lru_add_drain_cpu(get_cpu()); - put_cpu(); + lru_add_drain_cpu(local_lock_cpu(swapvec_lock)); + local_unlock_cpu(swapvec_lock); } -#ifdef CONFIG_SMP +#ifdef CONFIG_PREEMPT_RT_BASE +static inline void remote_lru_add_drain(int cpu, struct cpumask *has_work) +{ + local_lock_on(swapvec_lock, cpu); + lru_add_drain_cpu(cpu); + local_unlock_on(swapvec_lock, cpu); +} -static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work); +#else static void lru_add_drain_per_cpu(struct work_struct *dummy) { lru_add_drain(); } +static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work); + +static inline void remote_lru_add_drain(int cpu, struct cpumask *has_work) +{ + struct work_struct *work = &per_cpu(lru_add_drain_work, cpu); + + INIT_WORK(work, lru_add_drain_per_cpu); + queue_work_on(cpu, mm_percpu_wq, work); + cpumask_set_cpu(cpu, has_work); +} +#endif + /* * Doesn't need any cpu hotplug locking because we do rely on per-cpu * kworkers being shut down before our page_alloc_cpu_dead callback is @@ -682,30 +717,22 @@ void lru_add_drain_all(void) cpumask_clear(&has_work); for_each_online_cpu(cpu) { - struct work_struct *work = &per_cpu(lru_add_drain_work, cpu); if (pagevec_count(&per_cpu(lru_add_pvec, cpu)) || pagevec_count(&per_cpu(lru_rotate_pvecs, cpu)) || pagevec_count(&per_cpu(lru_deactivate_file_pvecs, cpu)) || pagevec_count(&per_cpu(lru_lazyfree_pvecs, cpu)) || - need_activate_page_drain(cpu)) { - INIT_WORK(work, lru_add_drain_per_cpu); - queue_work_on(cpu, mm_percpu_wq, work); - cpumask_set_cpu(cpu, &has_work); - } + need_activate_page_drain(cpu)) + remote_lru_add_drain(cpu, &has_work); } +#ifndef CONFIG_PREEMPT_RT_BASE for_each_cpu(cpu, &has_work) flush_work(&per_cpu(lru_add_drain_work, cpu)); +#endif mutex_unlock(&lock); } -#else -void lru_add_drain_all(void) -{ - lru_add_drain(); -} -#endif /** * release_pages - batched put_page() diff --git a/mm/vmalloc.c b/mm/vmalloc.c index aec5ae64abc8..4ea5265a37e1 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -852,7 +852,7 @@ static void *new_vmap_block(unsigned int order, gfp_t gfp_mask) struct vmap_block *vb; struct vmap_area *va; unsigned long vb_idx; - int node, err; + int node, err, cpu; void *vaddr; node = numa_node_id(); @@ -895,11 +895,12 @@ static void *new_vmap_block(unsigned int order, gfp_t gfp_mask) BUG_ON(err); radix_tree_preload_end(); - vbq = &get_cpu_var(vmap_block_queue); + cpu = get_cpu_light(); + vbq = this_cpu_ptr(&vmap_block_queue); spin_lock(&vbq->lock); list_add_tail_rcu(&vb->free_list, &vbq->free); spin_unlock(&vbq->lock); - put_cpu_var(vmap_block_queue); + put_cpu_light(); return vaddr; } @@ -968,6 +969,7 @@ static void *vb_alloc(unsigned long size, gfp_t gfp_mask) struct vmap_block *vb; void *vaddr = NULL; unsigned int order; + int cpu; BUG_ON(offset_in_page(size)); BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC); @@ -982,7 +984,8 @@ static void *vb_alloc(unsigned long size, gfp_t gfp_mask) order = get_order(size); rcu_read_lock(); - vbq = &get_cpu_var(vmap_block_queue); + cpu = get_cpu_light(); + vbq = this_cpu_ptr(&vmap_block_queue); list_for_each_entry_rcu(vb, &vbq->free, free_list) { unsigned long pages_off; @@ -1005,7 +1008,7 @@ static void *vb_alloc(unsigned long size, gfp_t gfp_mask) break; } - put_cpu_var(vmap_block_queue); + put_cpu_light(); rcu_read_unlock(); /* Allocate new block if nothing was found */ diff --git a/mm/vmstat.c b/mm/vmstat.c index 2878dc4e9af6..fb6cf15948a9 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -320,6 +320,7 @@ void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item, long x; long t; + preempt_disable_rt(); x = delta + __this_cpu_read(*p); t = __this_cpu_read(pcp->stat_threshold); @@ -329,6 +330,7 @@ void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item, x = 0; } __this_cpu_write(*p, x); + preempt_enable_rt(); } EXPORT_SYMBOL(__mod_zone_page_state); @@ -340,6 +342,7 @@ void __mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item, long x; long t; + preempt_disable_rt(); x = delta + __this_cpu_read(*p); t = __this_cpu_read(pcp->stat_threshold); @@ -349,6 +352,7 @@ void __mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item, x = 0; } __this_cpu_write(*p, x); + preempt_enable_rt(); } EXPORT_SYMBOL(__mod_node_page_state); @@ -381,6 +385,7 @@ void __inc_zone_state(struct zone *zone, enum zone_stat_item item) s8 __percpu *p = pcp->vm_stat_diff + item; s8 v, t; + preempt_disable_rt(); v = __this_cpu_inc_return(*p); t = __this_cpu_read(pcp->stat_threshold); if (unlikely(v > t)) { @@ -389,6 +394,7 @@ void __inc_zone_state(struct zone *zone, enum zone_stat_item item) zone_page_state_add(v + overstep, zone, item); __this_cpu_write(*p, -overstep); } + preempt_enable_rt(); } void __inc_node_state(struct pglist_data *pgdat, enum node_stat_item item) @@ -397,6 +403,7 @@ void __inc_node_state(struct pglist_data *pgdat, enum node_stat_item item) s8 __percpu *p = pcp->vm_node_stat_diff + item; s8 v, t; + preempt_disable_rt(); v = __this_cpu_inc_return(*p); t = __this_cpu_read(pcp->stat_threshold); if (unlikely(v > t)) { @@ -405,6 +412,7 @@ void __inc_node_state(struct pglist_data *pgdat, enum node_stat_item item) node_page_state_add(v + overstep, pgdat, item); __this_cpu_write(*p, -overstep); } + preempt_enable_rt(); } void __inc_zone_page_state(struct page *page, enum zone_stat_item item) @@ -425,6 +433,7 @@ void __dec_zone_state(struct zone *zone, enum zone_stat_item item) s8 __percpu *p = pcp->vm_stat_diff + item; s8 v, t; + preempt_disable_rt(); v = __this_cpu_dec_return(*p); t = __this_cpu_read(pcp->stat_threshold); if (unlikely(v < - t)) { @@ -433,6 +442,7 @@ void __dec_zone_state(struct zone *zone, enum zone_stat_item item) zone_page_state_add(v - overstep, zone, item); __this_cpu_write(*p, overstep); } + preempt_enable_rt(); } void __dec_node_state(struct pglist_data *pgdat, enum node_stat_item item) @@ -441,6 +451,7 @@ void __dec_node_state(struct pglist_data *pgdat, enum node_stat_item item) s8 __percpu *p = pcp->vm_node_stat_diff + item; s8 v, t; + preempt_disable_rt(); v = __this_cpu_dec_return(*p); t = __this_cpu_read(pcp->stat_threshold); if (unlikely(v < - t)) { @@ -449,6 +460,7 @@ void __dec_node_state(struct pglist_data *pgdat, enum node_stat_item item) node_page_state_add(v - overstep, pgdat, item); __this_cpu_write(*p, overstep); } + preempt_enable_rt(); } void __dec_zone_page_state(struct page *page, enum zone_stat_item item) diff --git a/mm/workingset.c b/mm/workingset.c index 40ee02c83978..aa75c0027079 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -366,10 +366,7 @@ static unsigned long count_shadow_nodes(struct shrinker *shrinker, unsigned long nodes; unsigned long cache; - /* list_lru lock nests inside the IRQ-safe i_pages lock */ - local_irq_disable(); nodes = list_lru_shrink_count(&shadow_nodes, sc); - local_irq_enable(); /* * Approximate a reasonable limit for the radix tree nodes @@ -434,7 +431,7 @@ static enum lru_status shadow_lru_isolate(struct list_head *item, /* Coming from the list, invert the lock order */ if (!xa_trylock(&mapping->i_pages)) { - spin_unlock(lru_lock); + spin_unlock_irq(lru_lock); ret = LRU_RETRY; goto out; } @@ -472,26 +469,20 @@ static enum lru_status shadow_lru_isolate(struct list_head *item, workingset_lookup_update(mapping)); out_invalid: - xa_unlock(&mapping->i_pages); + xa_unlock_irq(&mapping->i_pages); ret = LRU_REMOVED_RETRY; out: - local_irq_enable(); cond_resched(); - local_irq_disable(); - spin_lock(lru_lock); + spin_lock_irq(lru_lock); return ret; } static unsigned long scan_shadow_nodes(struct shrinker *shrinker, struct shrink_control *sc) { - unsigned long ret; - /* list_lru lock nests inside the IRQ-safe i_pages lock */ - local_irq_disable(); - ret = list_lru_shrink_walk(&shadow_nodes, sc, shadow_lru_isolate, NULL); - local_irq_enable(); - return ret; + return list_lru_shrink_walk_irq(&shadow_nodes, sc, shadow_lru_isolate, + NULL); } static struct shrinker workingset_shadow_shrinker = { diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 8d87e973a4f5..23e0002de546 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -55,6 +55,7 @@ #include <linux/migrate.h> #include <linux/pagemap.h> #include <linux/fs.h> +#include <linux/locallock.h> #define ZSPAGE_MAGIC 0x58 @@ -72,9 +73,22 @@ */ #define ZS_MAX_ZSPAGE_ORDER 2 #define ZS_MAX_PAGES_PER_ZSPAGE (_AC(1, UL) << ZS_MAX_ZSPAGE_ORDER) - #define ZS_HANDLE_SIZE (sizeof(unsigned long)) +#ifdef CONFIG_PREEMPT_RT_FULL + +struct zsmalloc_handle { + unsigned long addr; + struct mutex lock; +}; + +#define ZS_HANDLE_ALLOC_SIZE (sizeof(struct zsmalloc_handle)) + +#else + +#define ZS_HANDLE_ALLOC_SIZE (sizeof(unsigned long)) +#endif + /* * Object location (<PFN>, <obj_idx>) is encoded as * as single (unsigned long) handle value. @@ -320,7 +334,7 @@ static void SetZsPageMovable(struct zs_pool *pool, struct zspage *zspage) {} static int create_cache(struct zs_pool *pool) { - pool->handle_cachep = kmem_cache_create("zs_handle", ZS_HANDLE_SIZE, + pool->handle_cachep = kmem_cache_create("zs_handle", ZS_HANDLE_ALLOC_SIZE, 0, 0, NULL); if (!pool->handle_cachep) return 1; @@ -344,10 +358,27 @@ static void destroy_cache(struct zs_pool *pool) static unsigned long cache_alloc_handle(struct zs_pool *pool, gfp_t gfp) { - return (unsigned long)kmem_cache_alloc(pool->handle_cachep, - gfp & ~(__GFP_HIGHMEM|__GFP_MOVABLE)); + void *p; + + p = kmem_cache_alloc(pool->handle_cachep, + gfp & ~(__GFP_HIGHMEM|__GFP_MOVABLE)); +#ifdef CONFIG_PREEMPT_RT_FULL + if (p) { + struct zsmalloc_handle *zh = p; + + mutex_init(&zh->lock); + } +#endif + return (unsigned long)p; } +#ifdef CONFIG_PREEMPT_RT_FULL +static struct zsmalloc_handle *zs_get_pure_handle(unsigned long handle) +{ + return (void *)(handle &~((1 << OBJ_TAG_BITS) - 1)); +} +#endif + static void cache_free_handle(struct zs_pool *pool, unsigned long handle) { kmem_cache_free(pool->handle_cachep, (void *)handle); @@ -366,12 +397,18 @@ static void cache_free_zspage(struct zs_pool *pool, struct zspage *zspage) static void record_obj(unsigned long handle, unsigned long obj) { +#ifdef CONFIG_PREEMPT_RT_FULL + struct zsmalloc_handle *zh = zs_get_pure_handle(handle); + + WRITE_ONCE(zh->addr, obj); +#else /* * lsb of @obj represents handle lock while other bits * represent object value the handle is pointing so * updating shouldn't do store tearing. */ WRITE_ONCE(*(unsigned long *)handle, obj); +#endif } /* zpool driver */ @@ -453,6 +490,7 @@ MODULE_ALIAS("zpool-zsmalloc"); /* per-cpu VM mapping areas for zspage accesses that cross page boundaries */ static DEFINE_PER_CPU(struct mapping_area, zs_map_area); +static DEFINE_LOCAL_IRQ_LOCK(zs_map_area_lock); static bool is_zspage_isolated(struct zspage *zspage) { @@ -882,7 +920,13 @@ static unsigned long location_to_obj(struct page *page, unsigned int obj_idx) static unsigned long handle_to_obj(unsigned long handle) { +#ifdef CONFIG_PREEMPT_RT_FULL + struct zsmalloc_handle *zh = zs_get_pure_handle(handle); + + return zh->addr; +#else return *(unsigned long *)handle; +#endif } static unsigned long obj_to_head(struct page *page, void *obj) @@ -896,22 +940,46 @@ static unsigned long obj_to_head(struct page *page, void *obj) static inline int testpin_tag(unsigned long handle) { +#ifdef CONFIG_PREEMPT_RT_FULL + struct zsmalloc_handle *zh = zs_get_pure_handle(handle); + + return mutex_is_locked(&zh->lock); +#else return bit_spin_is_locked(HANDLE_PIN_BIT, (unsigned long *)handle); +#endif } static inline int trypin_tag(unsigned long handle) { +#ifdef CONFIG_PREEMPT_RT_FULL + struct zsmalloc_handle *zh = zs_get_pure_handle(handle); + + return mutex_trylock(&zh->lock); +#else return bit_spin_trylock(HANDLE_PIN_BIT, (unsigned long *)handle); +#endif } static void pin_tag(unsigned long handle) { +#ifdef CONFIG_PREEMPT_RT_FULL + struct zsmalloc_handle *zh = zs_get_pure_handle(handle); + + return mutex_lock(&zh->lock); +#else bit_spin_lock(HANDLE_PIN_BIT, (unsigned long *)handle); +#endif } static void unpin_tag(unsigned long handle) { +#ifdef CONFIG_PREEMPT_RT_FULL + struct zsmalloc_handle *zh = zs_get_pure_handle(handle); + + return mutex_unlock(&zh->lock); +#else bit_spin_unlock(HANDLE_PIN_BIT, (unsigned long *)handle); +#endif } static void reset_page(struct page *page) @@ -1350,7 +1418,7 @@ void *zs_map_object(struct zs_pool *pool, unsigned long handle, class = pool->size_class[class_idx]; off = (class->size * obj_idx) & ~PAGE_MASK; - area = &get_cpu_var(zs_map_area); + area = &get_locked_var(zs_map_area_lock, zs_map_area); area->vm_mm = mm; if (off + class->size <= PAGE_SIZE) { /* this object is contained entirely within a page */ @@ -1404,7 +1472,7 @@ void zs_unmap_object(struct zs_pool *pool, unsigned long handle) __zs_unmap_object(area, pages, off, class->size); } - put_cpu_var(zs_map_area); + put_locked_var(zs_map_area_lock, zs_map_area); migrate_read_unlock(zspage); unpin_tag(handle); diff --git a/net/Kconfig b/net/Kconfig index f738a6f27665..3108bb43f716 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -275,7 +275,7 @@ config CGROUP_NET_CLASSID config NET_RX_BUSY_POLL bool - default y + default y if !PREEMPT_RT_FULL config BQL bool diff --git a/net/core/dev.c b/net/core/dev.c index ee707e1a7d18..f2268e3af513 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -197,6 +197,7 @@ static unsigned int napi_gen_id = NR_CPUS; static DEFINE_READ_MOSTLY_HASHTABLE(napi_hash, 8); static seqcount_t devnet_rename_seq; +static DEFINE_MUTEX(devnet_rename_mutex); static inline void dev_base_seq_inc(struct net *net) { @@ -219,14 +220,14 @@ static inline struct hlist_head *dev_index_hash(struct net *net, int ifindex) static inline void rps_lock(struct softnet_data *sd) { #ifdef CONFIG_RPS - spin_lock(&sd->input_pkt_queue.lock); + raw_spin_lock(&sd->input_pkt_queue.raw_lock); #endif } static inline void rps_unlock(struct softnet_data *sd) { #ifdef CONFIG_RPS - spin_unlock(&sd->input_pkt_queue.lock); + raw_spin_unlock(&sd->input_pkt_queue.raw_lock); #endif } @@ -922,7 +923,8 @@ retry: strcpy(name, dev->name); rcu_read_unlock(); if (read_seqcount_retry(&devnet_rename_seq, seq)) { - cond_resched(); + mutex_lock(&devnet_rename_mutex); + mutex_unlock(&devnet_rename_mutex); goto retry; } @@ -1199,20 +1201,17 @@ int dev_change_name(struct net_device *dev, const char *newname) likely(!(dev->priv_flags & IFF_LIVE_RENAME_OK))) return -EBUSY; - write_seqcount_begin(&devnet_rename_seq); + mutex_lock(&devnet_rename_mutex); + __raw_write_seqcount_begin(&devnet_rename_seq); - if (strncmp(newname, dev->name, IFNAMSIZ) == 0) { - write_seqcount_end(&devnet_rename_seq); - return 0; - } + if (strncmp(newname, dev->name, IFNAMSIZ) == 0) + goto outunlock; memcpy(oldname, dev->name, IFNAMSIZ); err = dev_get_valid_name(net, dev, newname); - if (err < 0) { - write_seqcount_end(&devnet_rename_seq); - return err; - } + if (err < 0) + goto outunlock; if (oldname[0] && !strchr(oldname, '%')) netdev_info(dev, "renamed from %s\n", oldname); @@ -1225,11 +1224,12 @@ rollback: if (ret) { memcpy(dev->name, oldname, IFNAMSIZ); dev->name_assign_type = old_assign_type; - write_seqcount_end(&devnet_rename_seq); - return ret; + err = ret; + goto outunlock; } - write_seqcount_end(&devnet_rename_seq); + __raw_write_seqcount_end(&devnet_rename_seq); + mutex_unlock(&devnet_rename_mutex); netdev_adjacent_rename_links(dev, oldname); @@ -1250,7 +1250,8 @@ rollback: /* err >= 0 after dev_alloc_name() or stores the first errno */ if (err >= 0) { err = ret; - write_seqcount_begin(&devnet_rename_seq); + mutex_lock(&devnet_rename_mutex); + __raw_write_seqcount_begin(&devnet_rename_seq); memcpy(dev->name, oldname, IFNAMSIZ); memcpy(oldname, newname, IFNAMSIZ); dev->name_assign_type = old_assign_type; @@ -1263,6 +1264,11 @@ rollback: } return err; + +outunlock: + __raw_write_seqcount_end(&devnet_rename_seq); + mutex_unlock(&devnet_rename_mutex); + return err; } /** @@ -2541,6 +2547,7 @@ static void __netif_reschedule(struct Qdisc *q) sd->output_queue_tailp = &q->next_sched; raise_softirq_irqoff(NET_TX_SOFTIRQ); local_irq_restore(flags); + preempt_check_resched_rt(); } void __netif_schedule(struct Qdisc *q) @@ -2603,6 +2610,7 @@ void __dev_kfree_skb_irq(struct sk_buff *skb, enum skb_free_reason reason) __this_cpu_write(softnet_data.completion_queue, skb); raise_softirq_irqoff(NET_TX_SOFTIRQ); local_irq_restore(flags); + preempt_check_resched_rt(); } EXPORT_SYMBOL(__dev_kfree_skb_irq); @@ -3276,7 +3284,11 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, * This permits qdisc->running owner to get the lock more * often and dequeue packets faster. */ +#ifdef CONFIG_PREEMPT_RT_FULL + contended = true; +#else contended = qdisc_is_running(q); +#endif if (unlikely(contended)) spin_lock(&q->busylock); @@ -3348,8 +3360,10 @@ static void skb_update_prio(struct sk_buff *skb) #define skb_update_prio(skb) #endif +#ifndef CONFIG_PREEMPT_RT_FULL DEFINE_PER_CPU(int, xmit_recursion); EXPORT_SYMBOL(xmit_recursion); +#endif /** * dev_loopback_xmit - loop back @skb @@ -3589,9 +3603,12 @@ static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv) if (dev->flags & IFF_UP) { int cpu = smp_processor_id(); /* ok because BHs are off */ +#ifdef CONFIG_PREEMPT_RT_FULL + if (txq->xmit_lock_owner != current) { +#else if (txq->xmit_lock_owner != cpu) { - if (unlikely(__this_cpu_read(xmit_recursion) > - XMIT_RECURSION_LIMIT)) +#endif + if (unlikely(xmit_rec_read() > XMIT_RECURSION_LIMIT)) goto recursion_alert; skb = validate_xmit_skb(skb, dev, &again); @@ -3601,9 +3618,9 @@ static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv) HARD_TX_LOCK(dev, txq, cpu); if (!netif_xmit_stopped(txq)) { - __this_cpu_inc(xmit_recursion); + xmit_rec_inc(); skb = dev_hard_start_xmit(skb, dev, txq, &rc); - __this_cpu_dec(xmit_recursion); + xmit_rec_dec(); if (dev_xmit_complete(rc)) { HARD_TX_UNLOCK(dev, txq); goto out; @@ -4022,6 +4039,7 @@ drop: rps_unlock(sd); local_irq_restore(flags); + preempt_check_resched_rt(); atomic_long_inc(&skb->dev->rx_dropped); kfree_skb(skb); @@ -4234,7 +4252,7 @@ static int netif_rx_internal(struct sk_buff *skb) struct rps_dev_flow voidflow, *rflow = &voidflow; int cpu; - preempt_disable(); + migrate_disable(); rcu_read_lock(); cpu = get_rps_cpu(skb->dev, skb, &rflow); @@ -4244,14 +4262,14 @@ static int netif_rx_internal(struct sk_buff *skb) ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail); rcu_read_unlock(); - preempt_enable(); + migrate_enable(); } else #endif { unsigned int qtail; - ret = enqueue_to_backlog(skb, get_cpu(), &qtail); - put_cpu(); + ret = enqueue_to_backlog(skb, get_cpu_light(), &qtail); + put_cpu_light(); } return ret; } @@ -4285,11 +4303,9 @@ int netif_rx_ni(struct sk_buff *skb) trace_netif_rx_ni_entry(skb); - preempt_disable(); + local_bh_disable(); err = netif_rx_internal(skb); - if (local_softirq_pending()) - do_softirq(); - preempt_enable(); + local_bh_enable(); return err; } @@ -4844,7 +4860,7 @@ static void flush_backlog(struct work_struct *work) skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp) { if (skb->dev->reg_state == NETREG_UNREGISTERING) { __skb_unlink(skb, &sd->input_pkt_queue); - kfree_skb(skb); + __skb_queue_tail(&sd->tofree_queue, skb); input_queue_head_incr(sd); } } @@ -4854,11 +4870,14 @@ static void flush_backlog(struct work_struct *work) skb_queue_walk_safe(&sd->process_queue, skb, tmp) { if (skb->dev->reg_state == NETREG_UNREGISTERING) { __skb_unlink(skb, &sd->process_queue); - kfree_skb(skb); + __skb_queue_tail(&sd->tofree_queue, skb); input_queue_head_incr(sd); } } + if (!skb_queue_empty(&sd->tofree_queue)) + raise_softirq_irqoff(NET_RX_SOFTIRQ); local_bh_enable(); + } static void flush_all_backlogs(void) @@ -5373,12 +5392,14 @@ static void net_rps_action_and_irq_enable(struct softnet_data *sd) sd->rps_ipi_list = NULL; local_irq_enable(); + preempt_check_resched_rt(); /* Send pending IPI's to kick RPS processing on remote cpus. */ net_rps_send_ipi(remsd); } else #endif local_irq_enable(); + preempt_check_resched_rt(); } static bool sd_has_rps_ipi_waiting(struct softnet_data *sd) @@ -5408,7 +5429,9 @@ static int process_backlog(struct napi_struct *napi, int quota) while (again) { struct sk_buff *skb; + local_irq_disable(); while ((skb = __skb_dequeue(&sd->process_queue))) { + local_irq_enable(); rcu_read_lock(); __netif_receive_skb(skb); rcu_read_unlock(); @@ -5416,9 +5439,9 @@ static int process_backlog(struct napi_struct *napi, int quota) if (++work >= quota) return work; + local_irq_disable(); } - local_irq_disable(); rps_lock(sd); if (skb_queue_empty(&sd->input_pkt_queue)) { /* @@ -5456,6 +5479,7 @@ void __napi_schedule(struct napi_struct *n) local_irq_save(flags); ____napi_schedule(this_cpu_ptr(&softnet_data), n); local_irq_restore(flags); + preempt_check_resched_rt(); } EXPORT_SYMBOL(__napi_schedule); @@ -5492,6 +5516,7 @@ bool napi_schedule_prep(struct napi_struct *n) } EXPORT_SYMBOL(napi_schedule_prep); +#ifndef CONFIG_PREEMPT_RT_FULL /** * __napi_schedule_irqoff - schedule for receive * @n: entry to schedule @@ -5503,6 +5528,7 @@ void __napi_schedule_irqoff(struct napi_struct *n) ____napi_schedule(this_cpu_ptr(&softnet_data), n); } EXPORT_SYMBOL(__napi_schedule_irqoff); +#endif bool napi_complete_done(struct napi_struct *n, int work_done) { @@ -5860,13 +5886,21 @@ static __latent_entropy void net_rx_action(struct softirq_action *h) unsigned long time_limit = jiffies + usecs_to_jiffies(netdev_budget_usecs); int budget = netdev_budget; + struct sk_buff_head tofree_q; + struct sk_buff *skb; LIST_HEAD(list); LIST_HEAD(repoll); + __skb_queue_head_init(&tofree_q); + local_irq_disable(); + skb_queue_splice_init(&sd->tofree_queue, &tofree_q); list_splice_init(&sd->poll_list, &list); local_irq_enable(); + while ((skb = __skb_dequeue(&tofree_q))) + kfree_skb(skb); + for (;;) { struct napi_struct *n; @@ -5896,7 +5930,7 @@ static __latent_entropy void net_rx_action(struct softirq_action *h) list_splice_tail(&repoll, &list); list_splice(&list, &sd->poll_list); if (!list_empty(&sd->poll_list)) - __raise_softirq_irqoff(NET_RX_SOFTIRQ); + __raise_softirq_irqoff_ksoft(NET_RX_SOFTIRQ); net_rps_action_and_irq_enable(sd); out: @@ -7886,7 +7920,7 @@ static void netdev_init_one_queue(struct net_device *dev, /* Initialize queue lock */ spin_lock_init(&queue->_xmit_lock); netdev_set_xmit_lockdep_class(&queue->_xmit_lock, dev->type); - queue->xmit_lock_owner = -1; + netdev_queue_clear_owner(queue); netdev_queue_numa_node_write(queue, NUMA_NO_NODE); queue->dev = dev; #ifdef CONFIG_BQL @@ -8820,6 +8854,7 @@ static int dev_cpu_dead(unsigned int oldcpu) raise_softirq_irqoff(NET_TX_SOFTIRQ); local_irq_enable(); + preempt_check_resched_rt(); #ifdef CONFIG_RPS remsd = oldsd->rps_ipi_list; @@ -8833,10 +8868,13 @@ static int dev_cpu_dead(unsigned int oldcpu) netif_rx_ni(skb); input_queue_head_incr(oldsd); } - while ((skb = skb_dequeue(&oldsd->input_pkt_queue))) { + while ((skb = __skb_dequeue(&oldsd->input_pkt_queue))) { netif_rx_ni(skb); input_queue_head_incr(oldsd); } + while ((skb = __skb_dequeue(&oldsd->tofree_queue))) { + kfree_skb(skb); + } return 0; } @@ -9142,8 +9180,9 @@ static int __init net_dev_init(void) INIT_WORK(flush, flush_backlog); - skb_queue_head_init(&sd->input_pkt_queue); - skb_queue_head_init(&sd->process_queue); + skb_queue_head_init_raw(&sd->input_pkt_queue); + skb_queue_head_init_raw(&sd->process_queue); + skb_queue_head_init_raw(&sd->tofree_queue); #ifdef CONFIG_XFRM_OFFLOAD skb_queue_head_init(&sd->xfrm_backlog); #endif diff --git a/net/core/filter.c b/net/core/filter.c index c654992ecba4..bc118e6f1c91 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1983,7 +1983,7 @@ static inline int __bpf_tx_skb(struct net_device *dev, struct sk_buff *skb) { int ret; - if (unlikely(__this_cpu_read(xmit_recursion) > XMIT_RECURSION_LIMIT)) { + if (unlikely(xmit_rec_read() > XMIT_RECURSION_LIMIT)) { net_crit_ratelimited("bpf: recursion limit reached on datapath, buggy bpf program?\n"); kfree_skb(skb); return -ENETDOWN; @@ -1991,9 +1991,9 @@ static inline int __bpf_tx_skb(struct net_device *dev, struct sk_buff *skb) skb->dev = dev; - __this_cpu_inc(xmit_recursion); + xmit_rec_inc(); ret = dev_queue_xmit(skb); - __this_cpu_dec(xmit_recursion); + xmit_rec_dec(); return ret; } diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c index 98fd12721221..06855b380b8b 100644 --- a/net/core/gen_estimator.c +++ b/net/core/gen_estimator.c @@ -46,7 +46,7 @@ struct net_rate_estimator { struct gnet_stats_basic_packed *bstats; spinlock_t *stats_lock; - seqcount_t *running; + net_seqlock_t *running; struct gnet_stats_basic_cpu __percpu *cpu_bstats; u8 ewma_log; u8 intvl_log; /* period : (250ms << intvl_log) */ @@ -129,7 +129,7 @@ int gen_new_estimator(struct gnet_stats_basic_packed *bstats, struct gnet_stats_basic_cpu __percpu *cpu_bstats, struct net_rate_estimator __rcu **rate_est, spinlock_t *stats_lock, - seqcount_t *running, + net_seqlock_t *running, struct nlattr *opt) { struct gnet_estimator *parm = nla_data(opt); @@ -222,7 +222,7 @@ int gen_replace_estimator(struct gnet_stats_basic_packed *bstats, struct gnet_stats_basic_cpu __percpu *cpu_bstats, struct net_rate_estimator __rcu **rate_est, spinlock_t *stats_lock, - seqcount_t *running, struct nlattr *opt) + net_seqlock_t *running, struct nlattr *opt) { return gen_new_estimator(bstats, cpu_bstats, rate_est, stats_lock, running, opt); diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c index e2fd8baec65f..8bab88738691 100644 --- a/net/core/gen_stats.c +++ b/net/core/gen_stats.c @@ -142,7 +142,7 @@ __gnet_stats_copy_basic_cpu(struct gnet_stats_basic_packed *bstats, } void -__gnet_stats_copy_basic(const seqcount_t *running, +__gnet_stats_copy_basic(net_seqlock_t *running, struct gnet_stats_basic_packed *bstats, struct gnet_stats_basic_cpu __percpu *cpu, struct gnet_stats_basic_packed *b) @@ -155,10 +155,10 @@ __gnet_stats_copy_basic(const seqcount_t *running, } do { if (running) - seq = read_seqcount_begin(running); + seq = net_seq_begin(running); bstats->bytes = b->bytes; bstats->packets = b->packets; - } while (running && read_seqcount_retry(running, seq)); + } while (running && net_seq_retry(running, seq)); } EXPORT_SYMBOL(__gnet_stats_copy_basic); @@ -176,7 +176,7 @@ EXPORT_SYMBOL(__gnet_stats_copy_basic); * if the room in the socket buffer was not sufficient. */ int -gnet_stats_copy_basic(const seqcount_t *running, +gnet_stats_copy_basic(net_seqlock_t *running, struct gnet_dump *d, struct gnet_stats_basic_cpu __percpu *cpu, struct gnet_stats_basic_packed *b) diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 5f6321019810..be99b444a45a 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -2162,7 +2162,8 @@ static void spin(struct pktgen_dev *pkt_dev, ktime_t spin_until) s64 remaining; struct hrtimer_sleeper t; - hrtimer_init_on_stack(&t.timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); + hrtimer_init_sleeper_on_stack(&t, CLOCK_MONOTONIC, HRTIMER_MODE_ABS, + current); hrtimer_set_expires(&t.timer, spin_until); remaining = ktime_to_ns(hrtimer_expires_remaining(&t.timer)); @@ -2177,7 +2178,6 @@ static void spin(struct pktgen_dev *pkt_dev, ktime_t spin_until) } while (ktime_compare(end_time, spin_until) < 0); } else { /* see do_nanosleep */ - hrtimer_init_sleeper(&t, current); do { set_current_state(TASK_INTERRUPTIBLE); hrtimer_start_expires(&t.timer, HRTIMER_MODE_ABS); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 72b9167bad7a..f99413800fa9 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -63,6 +63,7 @@ #include <linux/errqueue.h> #include <linux/prefetch.h> #include <linux/if_vlan.h> +#include <linux/locallock.h> #include <net/protocol.h> #include <net/dst.h> @@ -330,6 +331,8 @@ struct napi_alloc_cache { static DEFINE_PER_CPU(struct page_frag_cache, netdev_alloc_cache); static DEFINE_PER_CPU(struct napi_alloc_cache, napi_alloc_cache); +static DEFINE_LOCAL_IRQ_LOCK(netdev_alloc_lock); +static DEFINE_LOCAL_IRQ_LOCK(napi_alloc_cache_lock); static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask) { @@ -337,10 +340,10 @@ static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask) unsigned long flags; void *data; - local_irq_save(flags); + local_lock_irqsave(netdev_alloc_lock, flags); nc = this_cpu_ptr(&netdev_alloc_cache); data = page_frag_alloc(nc, fragsz, gfp_mask); - local_irq_restore(flags); + local_unlock_irqrestore(netdev_alloc_lock, flags); return data; } @@ -361,9 +364,13 @@ EXPORT_SYMBOL(netdev_alloc_frag); static void *__napi_alloc_frag(unsigned int fragsz, gfp_t gfp_mask) { - struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); + struct napi_alloc_cache *nc; + void *data; - return page_frag_alloc(&nc->page, fragsz, gfp_mask); + nc = &get_locked_var(napi_alloc_cache_lock, napi_alloc_cache); + data = page_frag_alloc(&nc->page, fragsz, gfp_mask); + put_locked_var(napi_alloc_cache_lock, napi_alloc_cache); + return data; } void *napi_alloc_frag(unsigned int fragsz) @@ -412,13 +419,13 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int len, if (sk_memalloc_socks()) gfp_mask |= __GFP_MEMALLOC; - local_irq_save(flags); + local_lock_irqsave(netdev_alloc_lock, flags); nc = this_cpu_ptr(&netdev_alloc_cache); data = page_frag_alloc(nc, len, gfp_mask); pfmemalloc = nc->pfmemalloc; - local_irq_restore(flags); + local_unlock_irqrestore(netdev_alloc_lock, flags); if (unlikely(!data)) return NULL; @@ -459,9 +466,10 @@ EXPORT_SYMBOL(__netdev_alloc_skb); struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len, gfp_t gfp_mask) { - struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); + struct napi_alloc_cache *nc; struct sk_buff *skb; void *data; + bool pfmemalloc; len += NET_SKB_PAD + NET_IP_ALIGN; @@ -479,7 +487,10 @@ struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len, if (sk_memalloc_socks()) gfp_mask |= __GFP_MEMALLOC; + nc = &get_locked_var(napi_alloc_cache_lock, napi_alloc_cache); data = page_frag_alloc(&nc->page, len, gfp_mask); + pfmemalloc = nc->page.pfmemalloc; + put_locked_var(napi_alloc_cache_lock, napi_alloc_cache); if (unlikely(!data)) return NULL; @@ -490,7 +501,7 @@ struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len, } /* use OR instead of assignment to avoid clearing of bits in mask */ - if (nc->page.pfmemalloc) + if (pfmemalloc) skb->pfmemalloc = 1; skb->head_frag = 1; @@ -722,23 +733,26 @@ void __consume_stateless_skb(struct sk_buff *skb) void __kfree_skb_flush(void) { - struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); + struct napi_alloc_cache *nc; + nc = &get_locked_var(napi_alloc_cache_lock, napi_alloc_cache); /* flush skb_cache if containing objects */ if (nc->skb_count) { kmem_cache_free_bulk(skbuff_head_cache, nc->skb_count, nc->skb_cache); nc->skb_count = 0; } + put_locked_var(napi_alloc_cache_lock, napi_alloc_cache); } static inline void _kfree_skb_defer(struct sk_buff *skb) { - struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); + struct napi_alloc_cache *nc; /* drop skb->head and call any destructors for packet */ skb_release_all(skb); + nc = &get_locked_var(napi_alloc_cache_lock, napi_alloc_cache); /* record skb to CPU local list */ nc->skb_cache[nc->skb_count++] = skb; @@ -753,6 +767,7 @@ static inline void _kfree_skb_defer(struct sk_buff *skb) nc->skb_cache); nc->skb_count = 0; } + put_locked_var(napi_alloc_cache_lock, napi_alloc_cache); } void __kfree_skb_defer(struct sk_buff *skb) { diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index bd77778ca183..44afbbfd676b 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -77,6 +77,7 @@ #include <linux/string.h> #include <linux/netfilter_ipv4.h> #include <linux/slab.h> +#include <linux/locallock.h> #include <net/snmp.h> #include <net/ip.h> #include <net/route.h> @@ -204,6 +205,8 @@ static const struct icmp_control icmp_pointers[NR_ICMP_TYPES+1]; * * On SMP we have one ICMP socket per-cpu. */ +static DEFINE_LOCAL_IRQ_LOCK(icmp_sk_lock); + static struct sock *icmp_sk(struct net *net) { return *this_cpu_ptr(net->ipv4.icmp_sk); @@ -214,12 +217,16 @@ static inline struct sock *icmp_xmit_lock(struct net *net) { struct sock *sk; + if (!local_trylock(icmp_sk_lock)) + return NULL; + sk = icmp_sk(net); if (unlikely(!spin_trylock(&sk->sk_lock.slock))) { /* This can happen if the output path signals a * dst_link_failure() for an outgoing ICMP packet. */ + local_unlock(icmp_sk_lock); return NULL; } return sk; @@ -228,6 +235,7 @@ static inline struct sock *icmp_xmit_lock(struct net *net) static inline void icmp_xmit_unlock(struct sock *sk) { spin_unlock(&sk->sk_lock.slock); + local_unlock(icmp_sk_lock); } int sysctl_icmp_msgs_per_sec __read_mostly = 1000; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 174fa2f2d1dd..0e758b9d92b1 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -62,6 +62,7 @@ #include <linux/init.h> #include <linux/times.h> #include <linux/slab.h> +#include <linux/locallock.h> #include <net/net_namespace.h> #include <net/icmp.h> @@ -633,6 +634,7 @@ void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb) } EXPORT_SYMBOL(tcp_v4_send_check); +static DEFINE_LOCAL_IRQ_LOCK(tcp_sk_lock); /* * This routine will send an RST to the other tcp. * @@ -767,6 +769,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) arg.tos = ip_hdr(skb)->tos; arg.uid = sock_net_uid(net, sk && sk_fullsock(sk) ? sk : NULL); local_bh_disable(); + local_lock(tcp_sk_lock); ctl_sk = *this_cpu_ptr(net->ipv4.tcp_sk); if (sk) ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ? @@ -779,6 +782,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) ctl_sk->sk_mark = 0; __TCP_INC_STATS(net, TCP_MIB_OUTSEGS); __TCP_INC_STATS(net, TCP_MIB_OUTRSTS); + local_unlock(tcp_sk_lock); local_bh_enable(); #ifdef CONFIG_TCP_MD5SIG @@ -859,6 +863,7 @@ static void tcp_v4_send_ack(const struct sock *sk, arg.tos = tos; arg.uid = sock_net_uid(net, sk_fullsock(sk) ? sk : NULL); local_bh_disable(); + local_lock(tcp_sk_lock); ctl_sk = *this_cpu_ptr(net->ipv4.tcp_sk); if (sk) ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ? @@ -870,6 +875,7 @@ static void tcp_v4_send_ack(const struct sock *sk, ctl_sk->sk_mark = 0; __TCP_INC_STATS(net, TCP_MIB_OUTSEGS); + local_unlock(tcp_sk_lock); local_bh_enable(); } diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 168af54db975..9eb5e8717348 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -20,6 +20,7 @@ #include <linux/inetdevice.h> #include <linux/proc_fs.h> #include <linux/mutex.h> +#include <linux/locallock.h> #include <linux/mm.h> #include <linux/rcupdate.h> #include <net/net_namespace.h> @@ -27,6 +28,11 @@ #include "nf_internals.h" +#ifdef CONFIG_PREEMPT_RT_BASE +DEFINE_LOCAL_IRQ_LOCK(xt_write_lock); +EXPORT_PER_CPU_SYMBOL(xt_write_lock); +#endif + const struct nf_ipv6_ops __rcu *nf_ipv6_ops __read_mostly; EXPORT_SYMBOL_GPL(nf_ipv6_ops); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index ba0dbd164c02..f42ef3a277fd 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -63,6 +63,7 @@ #include <linux/if_packet.h> #include <linux/wireless.h> #include <linux/kernel.h> +#include <linux/delay.h> #include <linux/kmod.h> #include <linux/slab.h> #include <linux/vmalloc.h> @@ -666,7 +667,7 @@ static void prb_retire_rx_blk_timer_expired(struct timer_list *t) if (BLOCK_NUM_PKTS(pbd)) { while (atomic_read(&pkc->blk_fill_in_prog)) { /* Waiting for skb_copy_bits to finish... */ - cpu_relax(); + cpu_chill(); } } @@ -928,7 +929,7 @@ static void prb_retire_current_block(struct tpacket_kbdq_core *pkc, if (!(status & TP_STATUS_BLK_TMO)) { while (atomic_read(&pkc->blk_fill_in_prog)) { /* Waiting for skb_copy_bits to finish... */ - cpu_relax(); + cpu_chill(); } } prb_close_block(pkc, pbd, po, status); diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c index ea15d8f2ad08..bd78aeac3488 100644 --- a/net/rds/ib_rdma.c +++ b/net/rds/ib_rdma.c @@ -34,6 +34,7 @@ #include <linux/slab.h> #include <linux/rculist.h> #include <linux/llist.h> +#include <linux/delay.h> #include "rds_single_path.h" #include "ib_mr.h" @@ -210,7 +211,7 @@ static inline void wait_clean_list_grace(void) for_each_online_cpu(cpu) { flag = &per_cpu(clean_list_grace, cpu); while (test_bit(CLEAN_LIST_BUSY_BIT, flag)) - cpu_relax(); + cpu_chill(); } } diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index ce852f8c1d27..ed3acf66104f 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1159,7 +1159,7 @@ static struct Qdisc *qdisc_create(struct net_device *dev, rcu_assign_pointer(sch->stab, stab); } if (tca[TCA_RATE]) { - seqcount_t *running; + net_seqlock_t *running; err = -EOPNOTSUPP; if (sch->flags & TCQ_F_MQROOT) { diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 77b289da7763..b0cc57ff96e3 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -570,7 +570,11 @@ struct Qdisc noop_qdisc = { .ops = &noop_qdisc_ops, .q.lock = __SPIN_LOCK_UNLOCKED(noop_qdisc.q.lock), .dev_queue = &noop_netdev_queue, +#ifdef CONFIG_PREEMPT_RT_BASE + .running = __SEQLOCK_UNLOCKED(noop_qdisc.running), +#else .running = SEQCNT_ZERO(noop_qdisc.running), +#endif .busylock = __SPIN_LOCK_UNLOCKED(noop_qdisc.busylock), }; EXPORT_SYMBOL(noop_qdisc); @@ -859,9 +863,17 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, lockdep_set_class(&sch->busylock, dev->qdisc_tx_busylock ?: &qdisc_tx_busylock); +#ifdef CONFIG_PREEMPT_RT_BASE + seqlock_init(&sch->running); + lockdep_set_class(&sch->running.seqcount, + dev->qdisc_running_key ?: &qdisc_running_key); + lockdep_set_class(&sch->running.lock, + dev->qdisc_running_key ?: &qdisc_running_key); +#else seqcount_init(&sch->running); lockdep_set_class(&sch->running, dev->qdisc_running_key ?: &qdisc_running_key); +#endif sch->ops = ops; sch->flags = ops->static_flags; @@ -1183,7 +1195,7 @@ void dev_deactivate_many(struct list_head *head) /* Wait for outstanding qdisc_run calls. */ list_for_each_entry(dev, head, close_list) { while (some_qdisc_is_busy(dev)) - yield(); + msleep(1); /* The new qdisc is assigned at this point so we can safely * unwind stale skb lists and qdisc statistics */ diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 6cf0fd37cbf0..48c0a0b90946 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -393,7 +393,7 @@ void svc_xprt_do_enqueue(struct svc_xprt *xprt) if (test_and_set_bit(XPT_BUSY, &xprt->xpt_flags)) return; - cpu = get_cpu(); + cpu = get_cpu_light(); pool = svc_pool_for_cpu(xprt->xpt_server, cpu); atomic_long_inc(&pool->sp_stats.packets); @@ -417,7 +417,7 @@ void svc_xprt_do_enqueue(struct svc_xprt *xprt) rqstp = NULL; out_unlock: rcu_read_unlock(); - put_cpu(); + put_cpu_light(); trace_svc_xprt_do_enqueue(xprt, rqstp); } EXPORT_SYMBOL_GPL(svc_xprt_do_enqueue); diff --git a/samples/trace_events/trace-events-sample.c b/samples/trace_events/trace-events-sample.c index 5522692100ba..8b4be8e1802a 100644 --- a/samples/trace_events/trace-events-sample.c +++ b/samples/trace_events/trace-events-sample.c @@ -33,7 +33,7 @@ static void simple_thread_func(int cnt) /* Silly tracepoints */ trace_foo_bar("hello", cnt, array, random_strings[len], - ¤t->cpus_allowed); + current->cpus_ptr); trace_foo_with_template_simple("HELLO", cnt); diff --git a/scripts/mkcompile_h b/scripts/mkcompile_h index 87f1fc9801d7..f67b15236936 100755 --- a/scripts/mkcompile_h +++ b/scripts/mkcompile_h @@ -5,7 +5,8 @@ TARGET=$1 ARCH=$2 SMP=$3 PREEMPT=$4 -CC=$5 +RT=$5 +CC=$6 vecho() { [ "${quiet}" = "silent_" ] || echo "$@" ; } @@ -53,6 +54,7 @@ UTS_VERSION="#$VERSION" CONFIG_FLAGS="" if [ -n "$SMP" ] ; then CONFIG_FLAGS="SMP"; fi if [ -n "$PREEMPT" ] ; then CONFIG_FLAGS="$CONFIG_FLAGS PREEMPT"; fi +if [ -n "$RT" ] ; then CONFIG_FLAGS="$CONFIG_FLAGS RT"; fi UTS_VERSION="$UTS_VERSION $CONFIG_FLAGS $TIMESTAMP" # Truncate to maximum length diff --git a/security/apparmor/include/path.h b/security/apparmor/include/path.h index b6380c5f0097..12abfddb19c9 100644 --- a/security/apparmor/include/path.h +++ b/security/apparmor/include/path.h @@ -40,8 +40,10 @@ struct aa_buffers { #include <linux/percpu.h> #include <linux/preempt.h> +#include <linux/locallock.h> DECLARE_PER_CPU(struct aa_buffers, aa_buffers); +DECLARE_LOCAL_IRQ_LOCK(aa_buffers_lock); #define ASSIGN(FN, A, X, N) ((X) = FN(A, N)) #define EVAL1(FN, A, X) ASSIGN(FN, A, X, 0) /*X = FN(0)*/ @@ -51,7 +53,17 @@ DECLARE_PER_CPU(struct aa_buffers, aa_buffers); #define for_each_cpu_buffer(I) for ((I) = 0; (I) < MAX_PATH_BUFFERS; (I)++) -#ifdef CONFIG_DEBUG_PREEMPT +#ifdef CONFIG_PREEMPT_RT_BASE +static inline void AA_BUG_PREEMPT_ENABLED(const char *s) +{ + struct local_irq_lock *lv; + + lv = this_cpu_ptr(&aa_buffers_lock); + WARN_ONCE(lv->owner != current, + "__get_buffer without aa_buffers_lock\n"); +} + +#elif defined(CONFIG_DEBUG_PREEMPT) #define AA_BUG_PREEMPT_ENABLED(X) AA_BUG(preempt_count() <= 0, X) #else #define AA_BUG_PREEMPT_ENABLED(X) /* nop */ @@ -67,14 +79,15 @@ DECLARE_PER_CPU(struct aa_buffers, aa_buffers); #define get_buffers(X...) \ do { \ - struct aa_buffers *__cpu_var = get_cpu_ptr(&aa_buffers); \ + struct aa_buffers *__cpu_var; \ + __cpu_var = get_locked_ptr(aa_buffers_lock, &aa_buffers); \ __get_buffers(__cpu_var, X); \ } while (0) #define put_buffers(X, Y...) \ do { \ __put_buffers(X, Y); \ - put_cpu_ptr(&aa_buffers); \ + put_locked_ptr(aa_buffers_lock, &aa_buffers); \ } while (0) #endif /* __AA_PATH_H */ diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c index 74f17376202b..029b3cbcf460 100644 --- a/security/apparmor/lsm.c +++ b/security/apparmor/lsm.c @@ -45,7 +45,7 @@ int apparmor_initialized; DEFINE_PER_CPU(struct aa_buffers, aa_buffers); - +DEFINE_LOCAL_IRQ_LOCK(aa_buffers_lock); /* * LSM hook functions diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c index bbc74c6a1522..584e525447bc 100644 --- a/virt/kvm/arm/arm.c +++ b/virt/kvm/arm/arm.c @@ -703,7 +703,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) * involves poking the GIC, which must be done in a * non-preemptible context. */ - preempt_disable(); + migrate_disable(); kvm_pmu_flush_hwstate(vcpu); @@ -752,7 +752,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) kvm_timer_sync_hwstate(vcpu); kvm_vgic_sync_hwstate(vcpu); local_irq_enable(); - preempt_enable(); + migrate_enable(); continue; } @@ -830,7 +830,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) /* Exit types that need handling before we can be preempted */ handle_exit_early(vcpu, run, ret); - preempt_enable(); + migrate_enable(); ret = handle_exit(vcpu, run, ret); } |