diff options
Diffstat (limited to 'include/linux')
| -rw-r--r-- | include/linux/Kbuild | 2 | ||||
| -rw-r--r-- | include/linux/clocksource.h | 2 | ||||
| -rw-r--r-- | include/linux/file.h | 15 | ||||
| -rw-r--r-- | include/linux/freezer.h | 2 | ||||
| -rw-r--r-- | include/linux/futex.h | 2 | ||||
| -rw-r--r-- | include/linux/ide.h | 1 | ||||
| -rw-r--r-- | include/linux/init_task.h | 2 | ||||
| -rw-r--r-- | include/linux/interrupt.h | 3 | ||||
| -rw-r--r-- | include/linux/kvm.h | 227 | ||||
| -rw-r--r-- | include/linux/raid/raid5.h | 3 | ||||
| -rw-r--r-- | include/linux/rtc.h | 1 | ||||
| -rw-r--r-- | include/linux/sched.h | 3 | ||||
| -rw-r--r-- | include/linux/sysctl.h | 5 | ||||
| -rw-r--r-- | include/linux/task_io_accounting.h | 37 | ||||
| -rw-r--r-- | include/linux/task_io_accounting_ops.h | 47 | ||||
| -rw-r--r-- | include/linux/taskstats.h | 28 | ||||
| -rw-r--r-- | include/linux/timer.h | 6 | ||||
| -rw-r--r-- | include/linux/topology.h | 5 |
18 files changed, 356 insertions, 35 deletions
diff --git a/include/linux/Kbuild b/include/linux/Kbuild index e618b25b5add..a1b04d8a1d01 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -61,7 +61,6 @@ header-y += fd.h header-y += fdreg.h header-y += fib_rules.h header-y += fuse.h -header-y += futex.h header-y += genetlink.h header-y += gen_stats.h header-y += gigaset_dev.h @@ -203,6 +202,7 @@ unifdef-y += fb.h unifdef-y += fcntl.h unifdef-y += filter.h unifdef-y += flat.h +unifdef-y += futex.h unifdef-y += fs.h unifdef-y += gameport.h unifdef-y += generic_serial.h diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index d852024ed095..1622d23a8dc3 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -159,7 +159,7 @@ static inline s64 cyc2ns(struct clocksource *cs, cycle_t cycles) * Unless you're the timekeeping code, you should not be using this! */ static inline void clocksource_calculate_interval(struct clocksource *c, - unsigned long length_nsec) + unsigned long length_nsec) { u64 tmp; diff --git a/include/linux/file.h b/include/linux/file.h index 6e77b9177f9e..edca361f2ab4 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -26,19 +26,12 @@ struct embedded_fd_set { unsigned long fds_bits[1]; }; -/* - * More than this number of fds: we use a separately allocated fd_set - */ -#define EMBEDDED_FD_SET_SIZE (BITS_PER_BYTE * sizeof(struct embedded_fd_set)) - struct fdtable { unsigned int max_fds; - int max_fdset; struct file ** fd; /* current fd array */ fd_set *close_on_exec; fd_set *open_fds; struct rcu_head rcu; - struct files_struct *free_files; struct fdtable *next; }; @@ -83,14 +76,8 @@ extern int get_unused_fd(void); extern void FASTCALL(put_unused_fd(unsigned int fd)); struct kmem_cache; -extern struct file ** alloc_fd_array(int); -extern void free_fd_array(struct file **, int); - -extern fd_set *alloc_fdset(int); -extern void free_fdset(fd_set *, int); - extern int expand_files(struct files_struct *, int nr); -extern void free_fdtable(struct fdtable *fdt); +extern void free_fdtable_rcu(struct rcu_head *rcu); extern void __init files_defer_init(void); static inline struct file * fcheck_files(struct files_struct *files, unsigned int fd) diff --git a/include/linux/freezer.h b/include/linux/freezer.h index 6e05e3e7ce39..393063096134 100644 --- a/include/linux/freezer.h +++ b/include/linux/freezer.h @@ -1,5 +1,7 @@ /* Freezer declarations */ +#include <linux/sched.h> + #ifdef CONFIG_PM /* * Check if a process has been frozen diff --git a/include/linux/futex.h b/include/linux/futex.h index d097b5b72bc6..3f153b4e156c 100644 --- a/include/linux/futex.h +++ b/include/linux/futex.h @@ -93,6 +93,7 @@ struct robust_list_head { */ #define ROBUST_LIST_LIMIT 2048 +#ifdef __KERNEL__ long do_futex(u32 __user *uaddr, int op, u32 val, unsigned long timeout, u32 __user *uaddr2, u32 val2, u32 val3); @@ -110,6 +111,7 @@ static inline void exit_pi_state_list(struct task_struct *curr) { } #endif +#endif /* __KERNEL__ */ #define FUTEX_OP_SET 0 /* *(int *)UADDR2 = OPARG; */ #define FUTEX_OP_ADD 1 /* *(int *)UADDR2 += OPARG; */ diff --git a/include/linux/ide.h b/include/linux/ide.h index 9c2050293f17..64e070f62a87 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -796,6 +796,7 @@ typedef struct hwif_s { unsigned sg_mapped : 1; /* sg_table and sg_nents are ready */ unsigned no_io_32bit : 1; /* 1 = can not do 32-bit IO ops */ unsigned err_stops_fifo : 1; /* 1=data FIFO is cleared by an error */ + unsigned atapi_irq_bogon : 1; /* Generates spurious DMA interrupts in PIO mode */ struct device gendev; struct completion gendev_rel_comp; /* To deal with device release() */ diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 7272ff9ee77c..b5315150199e 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -12,12 +12,10 @@ #define INIT_FDTABLE \ { \ .max_fds = NR_OPEN_DEFAULT, \ - .max_fdset = EMBEDDED_FD_SET_SIZE, \ .fd = &init_files.fd_array[0], \ .close_on_exec = (fd_set *)&init_files.close_on_exec_init, \ .open_fds = (fd_set *)&init_files.open_fds_init, \ .rcu = RCU_HEAD_INIT, \ - .free_files = NULL, \ .next = NULL, \ } diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index de7593f4e895..e36e86c869fb 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -231,7 +231,8 @@ enum NET_TX_SOFTIRQ, NET_RX_SOFTIRQ, BLOCK_SOFTIRQ, - TASKLET_SOFTIRQ + TASKLET_SOFTIRQ, + SCHED_SOFTIRQ, }; /* softirq mask and active fields moved to irq_cpustat_t in diff --git a/include/linux/kvm.h b/include/linux/kvm.h new file mode 100644 index 000000000000..5bb2c3c585c1 --- /dev/null +++ b/include/linux/kvm.h @@ -0,0 +1,227 @@ +#ifndef __LINUX_KVM_H +#define __LINUX_KVM_H + +/* + * Userspace interface for /dev/kvm - kernel based virtual machine + * + * Note: this interface is considered experimental and may change without + * notice. + */ + +#include <asm/types.h> +#include <linux/ioctl.h> + +/* + * Architectural interrupt line count, and the size of the bitmap needed + * to hold them. + */ +#define KVM_NR_INTERRUPTS 256 +#define KVM_IRQ_BITMAP_SIZE_BYTES ((KVM_NR_INTERRUPTS + 7) / 8) +#define KVM_IRQ_BITMAP_SIZE(type) (KVM_IRQ_BITMAP_SIZE_BYTES / sizeof(type)) + + +/* for KVM_CREATE_MEMORY_REGION */ +struct kvm_memory_region { + __u32 slot; + __u32 flags; + __u64 guest_phys_addr; + __u64 memory_size; /* bytes */ +}; + +/* for kvm_memory_region::flags */ +#define KVM_MEM_LOG_DIRTY_PAGES 1UL + + +#define KVM_EXIT_TYPE_FAIL_ENTRY 1 +#define KVM_EXIT_TYPE_VM_EXIT 2 + +enum kvm_exit_reason { + KVM_EXIT_UNKNOWN = 0, + KVM_EXIT_EXCEPTION = 1, + KVM_EXIT_IO = 2, + KVM_EXIT_CPUID = 3, + KVM_EXIT_DEBUG = 4, + KVM_EXIT_HLT = 5, + KVM_EXIT_MMIO = 6, +}; + +/* for KVM_RUN */ +struct kvm_run { + /* in */ + __u32 vcpu; + __u32 emulated; /* skip current instruction */ + __u32 mmio_completed; /* mmio request completed */ + + /* out */ + __u32 exit_type; + __u32 exit_reason; + __u32 instruction_length; + union { + /* KVM_EXIT_UNKNOWN */ + struct { + __u32 hardware_exit_reason; + } hw; + /* KVM_EXIT_EXCEPTION */ + struct { + __u32 exception; + __u32 error_code; + } ex; + /* KVM_EXIT_IO */ + struct { +#define KVM_EXIT_IO_IN 0 +#define KVM_EXIT_IO_OUT 1 + __u8 direction; + __u8 size; /* bytes */ + __u8 string; + __u8 string_down; + __u8 rep; + __u8 pad; + __u16 port; + __u64 count; + union { + __u64 address; + __u32 value; + }; + } io; + struct { + } debug; + /* KVM_EXIT_MMIO */ + struct { + __u64 phys_addr; + __u8 data[8]; + __u32 len; + __u8 is_write; + } mmio; + }; +}; + +/* for KVM_GET_REGS and KVM_SET_REGS */ +struct kvm_regs { + /* in */ + __u32 vcpu; + __u32 padding; + + /* out (KVM_GET_REGS) / in (KVM_SET_REGS) */ + __u64 rax, rbx, rcx, rdx; + __u64 rsi, rdi, rsp, rbp; + __u64 r8, r9, r10, r11; + __u64 r12, r13, r14, r15; + __u64 rip, rflags; +}; + +struct kvm_segment { + __u64 base; + __u32 limit; + __u16 selector; + __u8 type; + __u8 present, dpl, db, s, l, g, avl; + __u8 unusable; + __u8 padding; +}; + +struct kvm_dtable { + __u64 base; + __u16 limit; + __u16 padding[3]; +}; + +/* for KVM_GET_SREGS and KVM_SET_SREGS */ +struct kvm_sregs { + /* in */ + __u32 vcpu; + __u32 padding; + + /* out (KVM_GET_SREGS) / in (KVM_SET_SREGS) */ + struct kvm_segment cs, ds, es, fs, gs, ss; + struct kvm_segment tr, ldt; + struct kvm_dtable gdt, idt; + __u64 cr0, cr2, cr3, cr4, cr8; + __u64 efer; + __u64 apic_base; + __u64 interrupt_bitmap[KVM_IRQ_BITMAP_SIZE(__u64)]; +}; + +struct kvm_msr_entry { + __u32 index; + __u32 reserved; + __u64 data; +}; + +/* for KVM_GET_MSRS and KVM_SET_MSRS */ +struct kvm_msrs { + __u32 vcpu; + __u32 nmsrs; /* number of msrs in entries */ + + struct kvm_msr_entry entries[0]; +}; + +/* for KVM_GET_MSR_INDEX_LIST */ +struct kvm_msr_list { + __u32 nmsrs; /* number of msrs in entries */ + __u32 indices[0]; +}; + +/* for KVM_TRANSLATE */ +struct kvm_translation { + /* in */ + __u64 linear_address; + __u32 vcpu; + __u32 padding; + + /* out */ + __u64 physical_address; + __u8 valid; + __u8 writeable; + __u8 usermode; +}; + +/* for KVM_INTERRUPT */ +struct kvm_interrupt { + /* in */ + __u32 vcpu; + __u32 irq; +}; + +struct kvm_breakpoint { + __u32 enabled; + __u32 padding; + __u64 address; +}; + +/* for KVM_DEBUG_GUEST */ +struct kvm_debug_guest { + /* int */ + __u32 vcpu; + __u32 enabled; + struct kvm_breakpoint breakpoints[4]; + __u32 singlestep; +}; + +/* for KVM_GET_DIRTY_LOG */ +struct kvm_dirty_log { + __u32 slot; + __u32 padding; + union { + void __user *dirty_bitmap; /* one bit per page */ + __u64 padding; + }; +}; + +#define KVMIO 0xAE + +#define KVM_RUN _IOWR(KVMIO, 2, struct kvm_run) +#define KVM_GET_REGS _IOWR(KVMIO, 3, struct kvm_regs) +#define KVM_SET_REGS _IOW(KVMIO, 4, struct kvm_regs) +#define KVM_GET_SREGS _IOWR(KVMIO, 5, struct kvm_sregs) +#define KVM_SET_SREGS _IOW(KVMIO, 6, struct kvm_sregs) +#define KVM_TRANSLATE _IOWR(KVMIO, 7, struct kvm_translation) +#define KVM_INTERRUPT _IOW(KVMIO, 8, struct kvm_interrupt) +#define KVM_DEBUG_GUEST _IOW(KVMIO, 9, struct kvm_debug_guest) +#define KVM_SET_MEMORY_REGION _IOW(KVMIO, 10, struct kvm_memory_region) +#define KVM_CREATE_VCPU _IOW(KVMIO, 11, int /* vcpu_slot */) +#define KVM_GET_DIRTY_LOG _IOW(KVMIO, 12, struct kvm_dirty_log) +#define KVM_GET_MSRS _IOWR(KVMIO, 13, struct kvm_msrs) +#define KVM_SET_MSRS _IOWR(KVMIO, 14, struct kvm_msrs) +#define KVM_GET_MSR_INDEX_LIST _IOWR(KVMIO, 15, struct kvm_msr_list) + +#endif diff --git a/include/linux/raid/raid5.h b/include/linux/raid/raid5.h index 03636d7918fe..d8286db60b96 100644 --- a/include/linux/raid/raid5.h +++ b/include/linux/raid/raid5.h @@ -227,7 +227,10 @@ struct raid5_private_data { struct list_head handle_list; /* stripes needing handling */ struct list_head delayed_list; /* stripes that have plugged requests */ struct list_head bitmap_list; /* stripes delaying awaiting bitmap update */ + struct bio *retry_read_aligned; /* currently retrying aligned bios */ + struct bio *retry_read_aligned_list; /* aligned bios retry list */ atomic_t preread_active_stripes; /* stripes with scheduled io */ + atomic_t active_aligned_reads; atomic_t reshape_stripes; /* stripes with pending writes for reshape */ /* unfortunately we need two cache names as we temporarily have diff --git a/include/linux/rtc.h b/include/linux/rtc.h index 09ff4c3e2713..5e22d4510d11 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -106,6 +106,7 @@ extern int rtc_year_days(unsigned int day, unsigned int month, unsigned int year extern int rtc_valid_tm(struct rtc_time *tm); extern int rtc_tm_to_time(struct rtc_time *tm, unsigned long *time); extern void rtc_time_to_tm(unsigned long time, struct rtc_time *tm); +extern void rtc_merge_alarm(struct rtc_time *now, struct rtc_time *alarm); #include <linux/device.h> #include <linux/seq_file.h> diff --git a/include/linux/sched.h b/include/linux/sched.h index ad9c46071ff8..ea92e5c89089 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -82,6 +82,7 @@ struct sched_param { #include <linux/resource.h> #include <linux/timer.h> #include <linux/hrtimer.h> +#include <linux/task_io_accounting.h> #include <asm/processor.h> @@ -647,6 +648,7 @@ enum idle_type #define SD_SHARE_CPUPOWER 128 /* Domain members share cpu power */ #define SD_POWERSAVINGS_BALANCE 256 /* Balance for power savings */ #define SD_SHARE_PKG_RESOURCES 512 /* Domain members share cpu pkg resources */ +#define SD_SERIALIZE 1024 /* Only a single load balancing instance */ #define BALANCE_FOR_MC_POWER \ (sched_smt_power_savings ? SD_POWERSAVINGS_BALANCE : 0) @@ -1013,6 +1015,7 @@ struct task_struct { wait_queue_t *io_wait; /* i/o counters(bytes read/written, #syscalls */ u64 rchar, wchar, syscr, syscw; + struct task_io_accounting ioac; #if defined(CONFIG_TASK_XACCT) u64 acct_rss_mem1; /* accumulated rss usage */ u64 acct_vm_mem1; /* accumulated virtual memory usage */ diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 94316a98e0d0..6d8846e7be6d 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -918,8 +918,7 @@ typedef struct ctl_table ctl_table; typedef int ctl_handler (ctl_table *table, int __user *name, int nlen, void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen, - void **context); + void __user *newval, size_t newlen); typedef int proc_handler (ctl_table *ctl, int write, struct file * filp, void __user *buffer, size_t *lenp, loff_t *ppos); @@ -950,7 +949,7 @@ extern int do_sysctl (int __user *name, int nlen, extern int do_sysctl_strategy (ctl_table *table, int __user *name, int nlen, void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen, void ** context); + void __user *newval, size_t newlen); extern ctl_handler sysctl_string; extern ctl_handler sysctl_intvec; diff --git a/include/linux/task_io_accounting.h b/include/linux/task_io_accounting.h new file mode 100644 index 000000000000..44d00e9cceea --- /dev/null +++ b/include/linux/task_io_accounting.h @@ -0,0 +1,37 @@ +/* + * task_io_accounting: a structure which is used for recording a single task's + * IO statistics. + * + * Don't include this header file directly - it is designed to be dragged in via + * sched.h. + * + * Blame akpm@osdl.org for all this. + */ + +#ifdef CONFIG_TASK_IO_ACCOUNTING +struct task_io_accounting { + /* + * The number of bytes which this task has caused to be read from + * storage. + */ + u64 read_bytes; + + /* + * The number of bytes which this task has caused, or shall cause to be + * written to disk. + */ + u64 write_bytes; + + /* + * A task can cause "negative" IO too. If this task truncates some + * dirty pagecache, some IO which another task has been accounted for + * (in its write_bytes) will not be happening. We _could_ just + * subtract that from the truncating task's write_bytes, but there is + * information loss in doing that. + */ + u64 cancelled_write_bytes; +}; +#else +struct task_io_accounting { +}; +#endif diff --git a/include/linux/task_io_accounting_ops.h b/include/linux/task_io_accounting_ops.h new file mode 100644 index 000000000000..df2a319106b2 --- /dev/null +++ b/include/linux/task_io_accounting_ops.h @@ -0,0 +1,47 @@ +/* + * Task I/O accounting operations + */ +#ifndef __TASK_IO_ACCOUNTING_OPS_INCLUDED +#define __TASK_IO_ACCOUNTING_OPS_INCLUDED + +#ifdef CONFIG_TASK_IO_ACCOUNTING +static inline void task_io_account_read(size_t bytes) +{ + current->ioac.read_bytes += bytes; +} + +static inline void task_io_account_write(size_t bytes) +{ + current->ioac.write_bytes += bytes; +} + +static inline void task_io_account_cancelled_write(size_t bytes) +{ + current->ioac.cancelled_write_bytes += bytes; +} + +static inline void task_io_accounting_init(struct task_struct *tsk) +{ + memset(&tsk->ioac, 0, sizeof(tsk->ioac)); +} + +#else + +static inline void task_io_account_read(size_t bytes) +{ +} + +static inline void task_io_account_write(size_t bytes) +{ +} + +static inline void task_io_account_cancelled_write(size_t bytes) +{ +} + +static inline void task_io_accounting_init(struct task_struct *tsk) +{ +} + +#endif /* CONFIG_TASK_IO_ACCOUNTING */ +#endif /* __TASK_IO_ACCOUNTING_OPS_INCLUDED */ diff --git a/include/linux/taskstats.h b/include/linux/taskstats.h index 45248806ae9c..3fced4798255 100644 --- a/include/linux/taskstats.h +++ b/include/linux/taskstats.h @@ -31,7 +31,7 @@ */ -#define TASKSTATS_VERSION 2 +#define TASKSTATS_VERSION 3 #define TS_COMM_LEN 32 /* should be >= TASK_COMM_LEN * in linux/sched.h */ @@ -115,31 +115,37 @@ struct taskstats { __u64 ac_majflt; /* Major Page Fault Count */ /* Basic Accounting Fields end */ - /* Extended accounting fields start */ + /* Extended accounting fields start */ /* Accumulated RSS usage in duration of a task, in MBytes-usecs. * The current rss usage is added to this counter every time * a tick is charged to a task's system time. So, at the end we * will have memory usage multiplied by system time. Thus an * average usage per system time unit can be calculated. */ - __u64 coremem; /* accumulated RSS usage in MB-usec */ + __u64 coremem; /* accumulated RSS usage in MB-usec */ /* Accumulated virtual memory usage in duration of a task. * Same as acct_rss_mem1 above except that we keep track of VM usage. */ - __u64 virtmem; /* accumulated VM usage in MB-usec */ + __u64 virtmem; /* accumulated VM usage in MB-usec */ /* High watermark of RSS and virtual memory usage in duration of * a task, in KBytes. */ - __u64 hiwater_rss; /* High-watermark of RSS usage, in KB */ - __u64 hiwater_vm; /* High-water VM usage, in KB */ + __u64 hiwater_rss; /* High-watermark of RSS usage, in KB */ + __u64 hiwater_vm; /* High-water VM usage, in KB */ /* The following four fields are I/O statistics of a task. */ - __u64 read_char; /* bytes read */ - __u64 write_char; /* bytes written */ - __u64 read_syscalls; /* read syscalls */ - __u64 write_syscalls; /* write syscalls */ - /* Extended accounting fields end */ + __u64 read_char; /* bytes read */ + __u64 write_char; /* bytes written */ + __u64 read_syscalls; /* read syscalls */ + __u64 write_syscalls; /* write syscalls */ + /* Extended accounting fields end */ + +#define TASKSTATS_HAS_IO_ACCOUNTING + /* Per-task storage I/O accounting starts */ + __u64 read_bytes; /* bytes of read I/O */ + __u64 write_bytes; /* bytes of write I/O */ + __u64 cancelled_write_bytes; /* bytes of cancelled write I/O */ }; diff --git a/include/linux/timer.h b/include/linux/timer.h index c982304dbafd..eeef6643d4c6 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -98,4 +98,10 @@ extern void run_local_timers(void); struct hrtimer; extern int it_real_fn(struct hrtimer *); +unsigned long __round_jiffies(unsigned long j, int cpu); +unsigned long __round_jiffies_relative(unsigned long j, int cpu); +unsigned long round_jiffies(unsigned long j); +unsigned long round_jiffies_relative(unsigned long j); + + #endif diff --git a/include/linux/topology.h b/include/linux/topology.h index da508d1998e4..6c5a6e6e813b 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -93,7 +93,7 @@ .groups = NULL, \ .min_interval = 1, \ .max_interval = 2, \ - .busy_factor = 8, \ + .busy_factor = 64, \ .imbalance_pct = 110, \ .cache_nice_tries = 0, \ .per_cpu_gain = 25, \ @@ -194,7 +194,8 @@ .wake_idx = 0, /* unused */ \ .forkexec_idx = 0, /* unused */ \ .per_cpu_gain = 100, \ - .flags = SD_LOAD_BALANCE, \ + .flags = SD_LOAD_BALANCE \ + | SD_SERIALIZE, \ .last_balance = jiffies, \ .balance_interval = 64, \ .nr_balance_failed = 0, \ |