diff options
Diffstat (limited to 'kernel')
55 files changed, 985 insertions, 1178 deletions
diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks index 5068e2a4e75..2251882daf5 100644 --- a/kernel/Kconfig.locks +++ b/kernel/Kconfig.locks @@ -124,8 +124,8 @@ config INLINE_SPIN_LOCK_IRQSAVE def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \ ARCH_INLINE_SPIN_LOCK_IRQSAVE -config INLINE_SPIN_UNLOCK - def_bool !DEBUG_SPINLOCK && (!PREEMPT || ARCH_INLINE_SPIN_UNLOCK) +config UNINLINE_SPIN_UNLOCK + bool config INLINE_SPIN_UNLOCK_BH def_bool !DEBUG_SPINLOCK && ARCH_INLINE_SPIN_UNLOCK_BH diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt index 24e7cb0ba26..3f9c97419f0 100644 --- a/kernel/Kconfig.preempt +++ b/kernel/Kconfig.preempt @@ -36,6 +36,7 @@ config PREEMPT_VOLUNTARY config PREEMPT bool "Preemptible Kernel (Low-Latency Desktop)" select PREEMPT_COUNT + select UNINLINE_SPIN_UNLOCK if !ARCH_INLINE_SPIN_UNLOCK help This option reduces the latency of the kernel by making all kernel code (that is not executing in a critical section) diff --git a/kernel/Makefile b/kernel/Makefile index 2d9de86b7e7..cb41b9547c9 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -27,7 +27,6 @@ obj-y += power/ obj-$(CONFIG_FREEZER) += freezer.o obj-$(CONFIG_PROFILING) += profile.o -obj-$(CONFIG_SYSCTL_SYSCALL_CHECK) += sysctl_check.o obj-$(CONFIG_STACKTRACE) += stacktrace.o obj-y += time/ obj-$(CONFIG_DEBUG_MUTEXES) += mutex-debug.o diff --git a/kernel/cgroup.c b/kernel/cgroup.c index f4ea4b6f3cf..ed64ccac67c 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -1883,7 +1883,7 @@ static void cgroup_task_migrate(struct cgroup *cgrp, struct cgroup *oldcgrp, */ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk) { - int retval; + int retval = 0; struct cgroup_subsys *ss, *failed_ss = NULL; struct cgroup *oldcgrp; struct cgroupfs_root *root = cgrp->root; diff --git a/kernel/compat.c b/kernel/compat.c index f346cedfe24..74ff8498809 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -31,11 +31,10 @@ #include <asm/uaccess.h> /* - * Note that the native side is already converted to a timespec, because - * that's what we want anyway. + * Get/set struct timeval with struct timespec on the native side */ -static int compat_get_timeval(struct timespec *o, - struct compat_timeval __user *i) +static int compat_get_timeval_convert(struct timespec *o, + struct compat_timeval __user *i) { long usec; @@ -46,8 +45,8 @@ static int compat_get_timeval(struct timespec *o, return 0; } -static int compat_put_timeval(struct compat_timeval __user *o, - struct timeval *i) +static int compat_put_timeval_convert(struct compat_timeval __user *o, + struct timeval *i) { return (put_user(i->tv_sec, &o->tv_sec) || put_user(i->tv_usec, &o->tv_usec)) ? -EFAULT : 0; @@ -117,7 +116,7 @@ asmlinkage long compat_sys_gettimeofday(struct compat_timeval __user *tv, if (tv) { struct timeval ktv; do_gettimeofday(&ktv); - if (compat_put_timeval(tv, &ktv)) + if (compat_put_timeval_convert(tv, &ktv)) return -EFAULT; } if (tz) { @@ -135,7 +134,7 @@ asmlinkage long compat_sys_settimeofday(struct compat_timeval __user *tv, struct timezone ktz; if (tv) { - if (compat_get_timeval(&kts, tv)) + if (compat_get_timeval_convert(&kts, tv)) return -EFAULT; } if (tz) { @@ -146,12 +145,29 @@ asmlinkage long compat_sys_settimeofday(struct compat_timeval __user *tv, return do_sys_settimeofday(tv ? &kts : NULL, tz ? &ktz : NULL); } +int get_compat_timeval(struct timeval *tv, const struct compat_timeval __user *ctv) +{ + return (!access_ok(VERIFY_READ, ctv, sizeof(*ctv)) || + __get_user(tv->tv_sec, &ctv->tv_sec) || + __get_user(tv->tv_usec, &ctv->tv_usec)) ? -EFAULT : 0; +} +EXPORT_SYMBOL_GPL(get_compat_timeval); + +int put_compat_timeval(const struct timeval *tv, struct compat_timeval __user *ctv) +{ + return (!access_ok(VERIFY_WRITE, ctv, sizeof(*ctv)) || + __put_user(tv->tv_sec, &ctv->tv_sec) || + __put_user(tv->tv_usec, &ctv->tv_usec)) ? -EFAULT : 0; +} +EXPORT_SYMBOL_GPL(put_compat_timeval); + int get_compat_timespec(struct timespec *ts, const struct compat_timespec __user *cts) { return (!access_ok(VERIFY_READ, cts, sizeof(*cts)) || __get_user(ts->tv_sec, &cts->tv_sec) || __get_user(ts->tv_nsec, &cts->tv_nsec)) ? -EFAULT : 0; } +EXPORT_SYMBOL_GPL(get_compat_timespec); int put_compat_timespec(const struct timespec *ts, struct compat_timespec __user *cts) { @@ -161,6 +177,42 @@ int put_compat_timespec(const struct timespec *ts, struct compat_timespec __user } EXPORT_SYMBOL_GPL(put_compat_timespec); +int compat_get_timeval(struct timeval *tv, const void __user *utv) +{ + if (COMPAT_USE_64BIT_TIME) + return copy_from_user(tv, utv, sizeof *tv) ? -EFAULT : 0; + else + return get_compat_timeval(tv, utv); +} +EXPORT_SYMBOL_GPL(compat_get_timeval); + +int compat_put_timeval(const struct timeval *tv, void __user *utv) +{ + if (COMPAT_USE_64BIT_TIME) + return copy_to_user(utv, tv, sizeof *tv) ? -EFAULT : 0; + else + return put_compat_timeval(tv, utv); +} +EXPORT_SYMBOL_GPL(compat_put_timeval); + +int compat_get_timespec(struct timespec *ts, const void __user *uts) +{ + if (COMPAT_USE_64BIT_TIME) + return copy_from_user(ts, uts, sizeof *ts) ? -EFAULT : 0; + else + return get_compat_timespec(ts, uts); +} +EXPORT_SYMBOL_GPL(compat_get_timespec); + +int compat_put_timespec(const struct timespec *ts, void __user *uts) +{ + if (COMPAT_USE_64BIT_TIME) + return copy_to_user(uts, ts, sizeof *ts) ? -EFAULT : 0; + else + return put_compat_timespec(ts, uts); +} +EXPORT_SYMBOL_GPL(compat_put_timespec); + static long compat_nanosleep_restart(struct restart_block *restart) { struct compat_timespec __user *rmtp; diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 1010cc61931..14f7070b4ba 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -270,11 +270,11 @@ static struct file_system_type cpuset_fs_type = { * are online. If none are online, walk up the cpuset hierarchy * until we find one that does have some online cpus. If we get * all the way to the top and still haven't found any online cpus, - * return cpu_online_map. Or if passed a NULL cs from an exit'ing - * task, return cpu_online_map. + * return cpu_online_mask. Or if passed a NULL cs from an exit'ing + * task, return cpu_online_mask. * * One way or another, we guarantee to return some non-empty subset - * of cpu_online_map. + * of cpu_online_mask. * * Call with callback_mutex held. */ @@ -867,7 +867,7 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs, int retval; int is_load_balanced; - /* top_cpuset.cpus_allowed tracks cpu_online_map; it's read-only */ + /* top_cpuset.cpus_allowed tracks cpu_online_mask; it's read-only */ if (cs == &top_cpuset) return -EACCES; @@ -2149,7 +2149,7 @@ void __init cpuset_init_smp(void) * * Description: Returns the cpumask_var_t cpus_allowed of the cpuset * attached to the specified @tsk. Guaranteed to return some non-empty - * subset of cpu_online_map, even if this means going outside the + * subset of cpu_online_mask, even if this means going outside the * tasks cpuset. **/ @@ -2162,10 +2162,9 @@ void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask) mutex_unlock(&callback_mutex); } -int cpuset_cpus_allowed_fallback(struct task_struct *tsk) +void cpuset_cpus_allowed_fallback(struct task_struct *tsk) { const struct cpuset *cs; - int cpu; rcu_read_lock(); cs = task_cs(tsk); @@ -2186,22 +2185,10 @@ int cpuset_cpus_allowed_fallback(struct task_struct *tsk) * changes in tsk_cs()->cpus_allowed. Otherwise we can temporary * set any mask even if it is not right from task_cs() pov, * the pending set_cpus_allowed_ptr() will fix things. + * + * select_fallback_rq() will fix things ups and set cpu_possible_mask + * if required. */ - - cpu = cpumask_any_and(&tsk->cpus_allowed, cpu_active_mask); - if (cpu >= nr_cpu_ids) { - /* - * Either tsk->cpus_allowed is wrong (see above) or it - * is actually empty. The latter case is only possible - * if we are racing with remove_tasks_in_empty_cpuset(). - * Like above we can temporary set any mask and rely on - * set_cpus_allowed_ptr() as synchronization point. - */ - do_set_cpus_allowed(tsk, cpu_possible_mask); - cpu = cpumask_any(cpu_active_mask); - } - - return cpu; } void cpuset_init_current_mems_allowed(void) diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c index 0d7c08784ef..1dc53bae56e 100644 --- a/kernel/debug/debug_core.c +++ b/kernel/debug/debug_core.c @@ -41,6 +41,7 @@ #include <linux/delay.h> #include <linux/sched.h> #include <linux/sysrq.h> +#include <linux/reboot.h> #include <linux/init.h> #include <linux/kgdb.h> #include <linux/kdb.h> @@ -52,7 +53,6 @@ #include <asm/cacheflush.h> #include <asm/byteorder.h> #include <linux/atomic.h> -#include <asm/system.h> #include "debug_core.h" @@ -75,6 +75,8 @@ static int exception_level; struct kgdb_io *dbg_io_ops; static DEFINE_SPINLOCK(kgdb_registration_lock); +/* Action for the reboot notifiter, a global allow kdb to change it */ +static int kgdbreboot; /* kgdb console driver is loaded */ static int kgdb_con_registered; /* determine if kgdb console output should be used */ @@ -96,6 +98,7 @@ static int __init opt_kgdb_con(char *str) early_param("kgdbcon", opt_kgdb_con); module_param(kgdb_use_con, int, 0644); +module_param(kgdbreboot, int, 0644); /* * Holds information about breakpoints in a kernel. These breakpoints are @@ -784,6 +787,33 @@ void __init dbg_late_init(void) kdb_init(KDB_INIT_FULL); } +static int +dbg_notify_reboot(struct notifier_block *this, unsigned long code, void *x) +{ + /* + * Take the following action on reboot notify depending on value: + * 1 == Enter debugger + * 0 == [the default] detatch debug client + * -1 == Do nothing... and use this until the board resets + */ + switch (kgdbreboot) { + case 1: + kgdb_breakpoint(); + case -1: + goto done; + } + if (!dbg_kdb_mode) + gdbstub_exit(code); +done: + return NOTIFY_DONE; +} + +static struct notifier_block dbg_reboot_notifier = { + .notifier_call = dbg_notify_reboot, + .next = NULL, + .priority = INT_MAX, +}; + static void kgdb_register_callbacks(void) { if (!kgdb_io_module_registered) { @@ -791,6 +821,7 @@ static void kgdb_register_callbacks(void) kgdb_arch_init(); if (!dbg_is_early) kgdb_arch_late(); + register_reboot_notifier(&dbg_reboot_notifier); atomic_notifier_chain_register(&panic_notifier_list, &kgdb_panic_event_nb); #ifdef CONFIG_MAGIC_SYSRQ @@ -812,6 +843,7 @@ static void kgdb_unregister_callbacks(void) */ if (kgdb_io_module_registered) { kgdb_io_module_registered = 0; + unregister_reboot_notifier(&dbg_reboot_notifier); atomic_notifier_chain_unregister(&panic_notifier_list, &kgdb_panic_event_nb); kgdb_arch_exit(); diff --git a/kernel/debug/gdbstub.c b/kernel/debug/gdbstub.c index c22d8c28ad8..ce615e06448 100644 --- a/kernel/debug/gdbstub.c +++ b/kernel/debug/gdbstub.c @@ -1111,6 +1111,13 @@ void gdbstub_exit(int status) unsigned char checksum, ch, buffer[3]; int loop; + if (!kgdb_connected) + return; + kgdb_connected = 0; + + if (!dbg_io_ops || dbg_kdb_mode) + return; + buffer[0] = 'W'; buffer[1] = hex_asc_hi(status); buffer[2] = hex_asc_lo(status); @@ -1129,5 +1136,6 @@ void gdbstub_exit(int status) dbg_io_ops->write_char(hex_asc_lo(checksum)); /* make sure the output is flushed, lest the bootloader clobber it */ - dbg_io_ops->flush(); + if (dbg_io_ops->flush) + dbg_io_ops->flush(); } diff --git a/kernel/debug/kdb/kdb_bp.c b/kernel/debug/kdb/kdb_bp.c index 20059ef4459..8418c2f8ec5 100644 --- a/kernel/debug/kdb/kdb_bp.c +++ b/kernel/debug/kdb/kdb_bp.c @@ -153,6 +153,13 @@ static int _kdb_bp_install(struct pt_regs *regs, kdb_bp_t *bp) } else { kdb_printf("%s: failed to set breakpoint at 0x%lx\n", __func__, bp->bp_addr); +#ifdef CONFIG_DEBUG_RODATA + if (!bp->bp_type) { + kdb_printf("Software breakpoints are unavailable.\n" + " Change the kernel CONFIG_DEBUG_RODATA=n\n" + " OR use hw breaks: help bph\n"); + } +#endif return 1; } return 0; diff --git a/kernel/debug/kdb/kdb_bt.c b/kernel/debug/kdb/kdb_bt.c index 7179eac7b41..07c9bbb94a0 100644 --- a/kernel/debug/kdb/kdb_bt.c +++ b/kernel/debug/kdb/kdb_bt.c @@ -15,7 +15,6 @@ #include <linux/sched.h> #include <linux/kdb.h> #include <linux/nmi.h> -#include <asm/system.h> #include "kdb_private.h" diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c index 4802eb5840e..9b5f17da1c5 100644 --- a/kernel/debug/kdb/kdb_io.c +++ b/kernel/debug/kdb/kdb_io.c @@ -689,7 +689,7 @@ kdb_printit: if (!dbg_kdb_mode && kgdb_connected) { gdbstub_msg_write(kdb_buffer, retlen); } else { - if (!dbg_io_ops->is_console) { + if (dbg_io_ops && !dbg_io_ops->is_console) { len = strlen(kdb_buffer); cp = kdb_buffer; while (len--) { diff --git a/kernel/debug/kdb/kdb_keyboard.c b/kernel/debug/kdb/kdb_keyboard.c index 4bca634975c..118527aa60e 100644 --- a/kernel/debug/kdb/kdb_keyboard.c +++ b/kernel/debug/kdb/kdb_keyboard.c @@ -25,6 +25,7 @@ #define KBD_STAT_MOUSE_OBF 0x20 /* Mouse output buffer full */ static int kbd_exists; +static int kbd_last_ret; /* * Check if the keyboard controller has a keypress for us. @@ -90,8 +91,11 @@ int kdb_get_kbd_char(void) return -1; } - if ((scancode & 0x80) != 0) + if ((scancode & 0x80) != 0) { + if (scancode == 0x9c) + kbd_last_ret = 0; return -1; + } scancode &= 0x7f; @@ -178,35 +182,82 @@ int kdb_get_kbd_char(void) return -1; /* ignore unprintables */ } - if ((scancode & 0x7f) == 0x1c) { - /* - * enter key. All done. Absorb the release scancode. - */ + if (scancode == 0x1c) { + kbd_last_ret = 1; + return 13; + } + + return keychar & 0xff; +} +EXPORT_SYMBOL_GPL(kdb_get_kbd_char); + +/* + * Best effort cleanup of ENTER break codes on leaving KDB. Called on + * exiting KDB, when we know we processed an ENTER or KP ENTER scan + * code. + */ +void kdb_kbd_cleanup_state(void) +{ + int scancode, scanstatus; + + /* + * Nothing to clean up, since either + * ENTER was never pressed, or has already + * gotten cleaned up. + */ + if (!kbd_last_ret) + return; + + kbd_last_ret = 0; + /* + * Enter key. Need to absorb the break code here, lest it gets + * leaked out if we exit KDB as the result of processing 'g'. + * + * This has several interesting implications: + * + Need to handle KP ENTER, which has break code 0xe0 0x9c. + * + Need to handle repeat ENTER and repeat KP ENTER. Repeats + * only get a break code at the end of the repeated + * sequence. This means we can't propagate the repeated key + * press, and must swallow it away. + * + Need to handle possible PS/2 mouse input. + * + Need to handle mashed keys. + */ + + while (1) { while ((inb(KBD_STATUS_REG) & KBD_STAT_OBF) == 0) - ; + cpu_relax(); /* - * Fetch the scancode + * Fetch the scancode. */ scancode = inb(KBD_DATA_REG); scanstatus = inb(KBD_STATUS_REG); - while (scanstatus & KBD_STAT_MOUSE_OBF) { - scancode = inb(KBD_DATA_REG); - scanstatus = inb(KBD_STATUS_REG); - } + /* + * Skip mouse input. + */ + if (scanstatus & KBD_STAT_MOUSE_OBF) + continue; - if (scancode != 0x9c) { - /* - * Wasn't an enter-release, why not? - */ - kdb_printf("kdb: expected enter got 0x%x status 0x%x\n", - scancode, scanstatus); - } + /* + * If we see 0xe0, this is either a break code for KP + * ENTER, or a repeat make for KP ENTER. Either way, + * since the second byte is equivalent to an ENTER, + * skip the 0xe0 and try again. + * + * If we see 0x1c, this must be a repeat ENTER or KP + * ENTER (and we swallowed 0xe0 before). Try again. + * + * We can also see make and break codes for other keys + * mashed before or after pressing ENTER. Thus, if we + * see anything other than 0x9c, we have to try again. + * + * Note, if you held some key as ENTER was depressed, + * that break code would get leaked out. + */ + if (scancode != 0x9c) + continue; - return 13; + return; } - - return keychar & 0xff; } -EXPORT_SYMBOL_GPL(kdb_get_kbd_char); diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index e2ae7349437..67b847dfa2b 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -1400,6 +1400,9 @@ int kdb_main_loop(kdb_reason_t reason, kdb_reason_t reason2, int error, if (KDB_STATE(DOING_SS)) KDB_STATE_CLEAR(SSBPT); + /* Clean up any keyboard devices before leaving */ + kdb_kbd_cleanup_state(); + return result; } diff --git a/kernel/debug/kdb/kdb_private.h b/kernel/debug/kdb/kdb_private.h index e381d105b40..47c4e56e513 100644 --- a/kernel/debug/kdb/kdb_private.h +++ b/kernel/debug/kdb/kdb_private.h @@ -246,6 +246,13 @@ extern void debug_kusage(void); extern void kdb_set_current_task(struct task_struct *); extern struct task_struct *kdb_current_task; + +#ifdef CONFIG_KDB_KEYBOARD +extern void kdb_kbd_cleanup_state(void); +#else /* ! CONFIG_KDB_KEYBOARD */ +#define kdb_kbd_cleanup_state() +#endif /* ! CONFIG_KDB_KEYBOARD */ + #ifdef CONFIG_MODULES extern struct list_head *kdb_modules; #endif /* CONFIG_MODULES */ diff --git a/kernel/dma.c b/kernel/dma.c index 68a2306522c..6c6262f86c1 100644 --- a/kernel/dma.c +++ b/kernel/dma.c @@ -18,7 +18,6 @@ #include <linux/proc_fs.h> #include <linux/init.h> #include <asm/dma.h> -#include <asm/system.h> diff --git a/kernel/events/core.c b/kernel/events/core.c index 4b50357914f..a6a9ec4cd8f 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3348,7 +3348,7 @@ static void calc_timer_values(struct perf_event *event, *running = ctx_time - event->tstamp_running; } -void __weak perf_update_user_clock(struct perf_event_mmap_page *userpg, u64 now) +void __weak arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now) { } @@ -3398,7 +3398,7 @@ void perf_event_update_userpage(struct perf_event *event) userpg->time_running = running + atomic64_read(&event->child_total_time_running); - perf_update_user_clock(userpg, now); + arch_perf_update_userpage(userpg, now); barrier(); ++userpg->lock; @@ -7116,6 +7116,13 @@ void __init perf_event_init(void) /* do not patch jump label more than once per second */ jump_label_rate_limit(&perf_sched_events, HZ); + + /* + * Build time assertion that we keep the data_head at the intended + * location. IOW, validation we got the __reserved[] size right. + */ + BUILD_BUG_ON((offsetof(struct perf_event_mmap_page, data_head)) |