From 47f61f397cc08b5a9a815bd03cb10c48dab66034 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 26 Jul 2005 11:21:38 -0600 Subject: [PATCH] Add missing device_suspsend(PMSG_FREEZE) calls. In the recent addition of device_suspend calls into sys_reboot two code paths were missed. Signed-off-by: Eric W. Biederman Signed-off-by: Linus Torvalds --- kernel/sys.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel') diff --git a/kernel/sys.c b/kernel/sys.c index 9a24374c23bc..5fc10d3e3891 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -391,6 +391,7 @@ asmlinkage long sys_reboot(int magic1, int magic2, unsigned int cmd, void __user case LINUX_REBOOT_CMD_RESTART: notifier_call_chain(&reboot_notifier_list, SYS_RESTART, NULL); system_state = SYSTEM_RESTART; + device_suspend(PMSG_FREEZE); device_shutdown(); printk(KERN_EMERG "Restarting system.\n"); machine_restart(NULL); @@ -452,6 +453,7 @@ asmlinkage long sys_reboot(int magic1, int magic2, unsigned int cmd, void __user } notifier_call_chain(&reboot_notifier_list, SYS_RESTART, NULL); system_state = SYSTEM_RESTART; + device_suspend(PMSG_FREEZE); device_shutdown(); printk(KERN_EMERG "Starting new kernel\n"); machine_shutdown(); -- cgit v1.2.2 From 4a00ea1e18228e5ef99d4780671fda97226bda30 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 26 Jul 2005 11:24:14 -0600 Subject: [PATCH] Refactor sys_reboot into reusable parts Because the factors of sys_reboot don't exist people calling into the reboot path duplicate the code badly, leading to inconsistent expectations of code in the reboot path. This patch should is just code motion. Signed-off-by: Eric W. Biederman Signed-off-by: Linus Torvalds --- kernel/sys.c | 106 ++++++++++++++++++++++++++++++++++++----------------------- 1 file changed, 64 insertions(+), 42 deletions(-) (limited to 'kernel') diff --git a/kernel/sys.c b/kernel/sys.c index 5fc10d3e3891..7e033809ef5f 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -361,6 +361,62 @@ out_unlock: return retval; } +void kernel_restart(char *cmd) +{ + notifier_call_chain(&reboot_notifier_list, SYS_RESTART, cmd); + system_state = SYSTEM_RESTART; + device_suspend(PMSG_FREEZE); + device_shutdown(); + if (!cmd) { + printk(KERN_EMERG "Restarting system.\n"); + } else { + printk(KERN_EMERG "Restarting system with command '%s'.\n", cmd); + } + printk(".\n"); + machine_restart(cmd); +} +EXPORT_SYMBOL_GPL(kernel_restart); + +void kernel_kexec(void) +{ +#ifdef CONFIG_KEXEC + struct kimage *image; + image = xchg(&kexec_image, 0); + if (!image) { + return; + } + notifier_call_chain(&reboot_notifier_list, SYS_RESTART, NULL); + system_state = SYSTEM_RESTART; + device_suspend(PMSG_FREEZE); + device_shutdown(); + printk(KERN_EMERG "Starting new kernel\n"); + machine_shutdown(); + machine_kexec(image); +#endif +} +EXPORT_SYMBOL_GPL(kernel_kexec); + +void kernel_halt(void) +{ + notifier_call_chain(&reboot_notifier_list, SYS_HALT, NULL); + system_state = SYSTEM_HALT; + device_suspend(PMSG_SUSPEND); + device_shutdown(); + printk(KERN_EMERG "System halted.\n"); + machine_halt(); +} +EXPORT_SYMBOL_GPL(kernel_halt); + +void kernel_power_off(void) +{ + notifier_call_chain(&reboot_notifier_list, SYS_POWER_OFF, NULL); + system_state = SYSTEM_POWER_OFF; + device_suspend(PMSG_SUSPEND); + device_shutdown(); + printk(KERN_EMERG "Power down.\n"); + machine_power_off(); +} +EXPORT_SYMBOL_GPL(kernel_power_off); /* * Reboot system call: for obvious reasons only root may call it, @@ -389,12 +445,7 @@ asmlinkage long sys_reboot(int magic1, int magic2, unsigned int cmd, void __user lock_kernel(); switch (cmd) { case LINUX_REBOOT_CMD_RESTART: - notifier_call_chain(&reboot_notifier_list, SYS_RESTART, NULL); - system_state = SYSTEM_RESTART; - device_suspend(PMSG_FREEZE); - device_shutdown(); - printk(KERN_EMERG "Restarting system.\n"); - machine_restart(NULL); + kernel_restart(NULL); break; case LINUX_REBOOT_CMD_CAD_ON: @@ -406,23 +457,13 @@ asmlinkage long sys_reboot(int magic1, int magic2, unsigned int cmd, void __user break; case LINUX_REBOOT_CMD_HALT: - notifier_call_chain(&reboot_notifier_list, SYS_HALT, NULL); - system_state = SYSTEM_HALT; - device_suspend(PMSG_SUSPEND); - device_shutdown(); - printk(KERN_EMERG "System halted.\n"); - machine_halt(); + kernel_halt(); unlock_kernel(); do_exit(0); break; case LINUX_REBOOT_CMD_POWER_OFF: - notifier_call_chain(&reboot_notifier_list, SYS_POWER_OFF, NULL); - system_state = SYSTEM_POWER_OFF; - device_suspend(PMSG_SUSPEND); - device_shutdown(); - printk(KERN_EMERG "Power down.\n"); - machine_power_off(); + kernel_power_off(); unlock_kernel(); do_exit(0); break; @@ -434,33 +475,14 @@ asmlinkage long sys_reboot(int magic1, int magic2, unsigned int cmd, void __user } buffer[sizeof(buffer) - 1] = '\0'; - notifier_call_chain(&reboot_notifier_list, SYS_RESTART, buffer); - system_state = SYSTEM_RESTART; - device_suspend(PMSG_FREEZE); - device_shutdown(); - printk(KERN_EMERG "Restarting system with command '%s'.\n", buffer); - machine_restart(buffer); + kernel_restart(buffer); break; -#ifdef CONFIG_KEXEC case LINUX_REBOOT_CMD_KEXEC: - { - struct kimage *image; - image = xchg(&kexec_image, 0); - if (!image) { - unlock_kernel(); - return -EINVAL; - } - notifier_call_chain(&reboot_notifier_list, SYS_RESTART, NULL); - system_state = SYSTEM_RESTART; - device_suspend(PMSG_FREEZE); - device_shutdown(); - printk(KERN_EMERG "Starting new kernel\n"); - machine_shutdown(); - machine_kexec(image); - break; - } -#endif + kernel_kexec(); + unlock_kernel(); + return -EINVAL; + #ifdef CONFIG_SOFTWARE_SUSPEND case LINUX_REBOOT_CMD_SW_SUSPEND: { -- cgit v1.2.2 From abcd9e51f5b832439b119d530db1353c12fd4073 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 26 Jul 2005 11:27:34 -0600 Subject: [PATCH] Make ctrl_alt_del call kernel_restart to get a proper reboot. It is obvious we wanted to call kernel_restart here but since we don't have it the code was expanded inline and hasn't been correct since sometime in 2.4. Signed-off-by: Eric W. Biederman Signed-off-by: Linus Torvalds --- kernel/sys.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/sys.c b/kernel/sys.c index 7e033809ef5f..31ac41a73329 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -502,8 +502,7 @@ asmlinkage long sys_reboot(int magic1, int magic2, unsigned int cmd, void __user static void deferred_cad(void *dummy) { - notifier_call_chain(&reboot_notifier_list, SYS_RESTART, NULL); - machine_restart(NULL); + kernel_restart(NULL); } /* -- cgit v1.2.2 From 7c9034735eccbf82608a4602c59aaf6053ea9416 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 26 Jul 2005 11:29:55 -0600 Subject: [PATCH] Add emergency_restart() When the kernel is working well and we want to restart cleanly kernel_restart is the function to use. But in many instances the kernel wants to reboot when thing are expected to be working very badly such as from panic or a software watchdog handler. This patch adds the function emergency_restart() so that callers can be clear what semantics they expect when calling restart. emergency_restart() is expected to be callable from interrupt context and possibly reliable in even more trying circumstances. This is an initial generic implementation for all architectures. Signed-off-by: Eric W. Biederman Signed-off-by: Linus Torvalds --- kernel/sys.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'kernel') diff --git a/kernel/sys.c b/kernel/sys.c index 31ac41a73329..a74039036fb4 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -361,6 +361,12 @@ out_unlock: return retval; } +void emergency_restart(void) +{ + machine_emergency_restart(); +} +EXPORT_SYMBOL_GPL(emergency_restart); + void kernel_restart(char *cmd) { notifier_call_chain(&reboot_notifier_list, SYS_RESTART, cmd); -- cgit v1.2.2 From ff31977782a05504f2586ec9e3e5ab4b09a4c893 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 26 Jul 2005 11:47:32 -0600 Subject: [PATCH] Use kernel_power_off in sysrq-o We already do all of the gymnastics to run from process context to call the power off code so call into the power off code cleanly. This especially helps acpi as part of it's shutdown logic should run acpi_shutdown called from device_shutdown which was not being called from here. Signed-off-by: Eric W. Biederman Signed-off-by: Linus Torvalds --- kernel/power/poweroff.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/power/poweroff.c b/kernel/power/poweroff.c index 715081b2d829..7a4144ba3afd 100644 --- a/kernel/power/poweroff.c +++ b/kernel/power/poweroff.c @@ -9,6 +9,7 @@ #include #include #include +#include /* * When the user hits Sys-Rq o to power down the machine this is the @@ -17,8 +18,7 @@ static void do_poweroff(void *dummy) { - if (pm_power_off) - pm_power_off(); + kernel_power_off(); } static DECLARE_WORK(poweroff_work, do_poweroff, NULL); -- cgit v1.2.2 From 2f048ea81df94f72dee0d42b3d9b941c03b8c9c5 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 26 Jul 2005 11:49:23 -0600 Subject: [PATCH] Call emergency_reboot from panic We know the system is in trouble so there is no question if this is an emergecy :) Signed-off-by: Eric W. Biederman Signed-off-by: Linus Torvalds --- kernel/panic.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/kernel/panic.c b/kernel/panic.c index 74ba5f3e46c7..aabc5f86fa3f 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -111,12 +111,11 @@ NORET_TYPE void panic(const char * fmt, ...) mdelay(1); i++; } - /* - * Should we run the reboot notifier. For the moment Im - * choosing not too. It might crash, be corrupt or do - * more harm than good for other reasons. + /* This will not be a clean reboot, with everything + * shutting down. But if there is a chance of + * rebooting the system it will be rebooted. */ - machine_restart(NULL); + emergency_restart(); } #ifdef __sparc__ { -- cgit v1.2.2 From fdde86ac50357b6a811e3574e47d189e81a21444 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 26 Jul 2005 12:01:17 -0600 Subject: [PATCH] swpsuspend: Have suspend to disk use factors of sys_reboot The suspend to disk code was a poor copy of the code in sys_reboot now that we have kernel_power_off, kernel_restart and kernel_halt use them instead of poorly duplicating them inline. Signed-off-by: Eric W. Biederman Signed-off-by: Linus Torvalds --- kernel/power/disk.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) (limited to 'kernel') diff --git a/kernel/power/disk.c b/kernel/power/disk.c index 3ec789c6b537..664eb0469b6e 100644 --- a/kernel/power/disk.c +++ b/kernel/power/disk.c @@ -59,16 +59,13 @@ static void power_down(suspend_disk_method_t mode) error = pm_ops->enter(PM_SUSPEND_DISK); break; case PM_DISK_SHUTDOWN: - printk("Powering off system\n"); - device_shutdown(); - machine_power_off(); + kernel_power_off(); break; case PM_DISK_REBOOT: - device_shutdown(); - machine_restart(NULL); + kernel_restart(NULL); break; } - machine_halt(); + kernel_halt(); /* Valid image is on the disk, if we continue we risk serious data corruption after resume. */ printk(KERN_CRIT "Please power me down manually\n"); -- cgit v1.2.2 From 18586e721636527cb5177467fb17e2350615978a Mon Sep 17 00:00:00 2001 From: Andreas Steinmetz Date: Sat, 23 Jul 2005 13:42:04 +0200 Subject: [PATCH] Fix RLIMIT_RTPRIO breakage RLIMIT_RTPRIO is supposed to grant non privileged users the right to use SCHED_FIFO/SCHED_RR scheduling policies with priorites bounded by the RLIMIT_RTPRIO value via sched_setscheduler(). This is usually used by audio users. Unfortunately this is broken in 2.6.13rc3 as you can see in the excerpt from sched_setscheduler below: /* * Allow unprivileged RT tasks to decrease priority: */ if (!capable(CAP_SYS_NICE)) { /* can't change policy */ if (policy != p->policy) return -EPERM; After the above unconditional test which causes sched_setscheduler to fail with no regard to the RLIMIT_RTPRIO value the following check is made: /* can't increase priority */ if (policy != SCHED_NORMAL && param->sched_priority > p->rt_priority && param->sched_priority > p->signal->rlim[RLIMIT_RTPRIO].rlim_cur) return -EPERM; Thus I do believe that the RLIMIT_RTPRIO value must be taken into account for the policy check, especially as the RLIMIT_RTPRIO limit is of no use without this change. The attached patch fixes this problem. Signed-off-by: Andreas Steinmetz Acked-by: Ingo Molnar Signed-off-by: Linus Torvalds --- kernel/sched.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sched.c b/kernel/sched.c index 4107db0dc091..a5fb654ea590 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -3528,7 +3528,8 @@ recheck: */ if (!capable(CAP_SYS_NICE)) { /* can't change policy */ - if (policy != p->policy) + if (policy != p->policy && + !p->signal->rlim[RLIMIT_RTPRIO].rlim_cur) return -EPERM; /* can't increase priority */ if (policy != SCHED_NORMAL && -- cgit v1.2.2 From d46523ea32a79fbc8cd1237f9441f45cc3f02456 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 25 Jul 2005 16:28:39 -0400 Subject: [PATCH] fix MAX_USER_RT_PRIO and MAX_RT_PRIO Here's the patch again to fix the code to handle if the values between MAX_USER_RT_PRIO and MAX_RT_PRIO are different. Without this patch, an SMP system will crash if the values are different. Signed-off-by: Steven Rostedt Cc: Ingo Molnar Signed-off-by: Dean Nelson Signed-off-by: Linus Torvalds --- kernel/sched.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/sched.c b/kernel/sched.c index a5fb654ea590..a646e4f36c41 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -3486,7 +3486,7 @@ static void __setscheduler(struct task_struct *p, int policy, int prio) p->policy = policy; p->rt_priority = prio; if (policy != SCHED_NORMAL) - p->prio = MAX_USER_RT_PRIO-1 - p->rt_priority; + p->prio = MAX_RT_PRIO-1 - p->rt_priority; else p->prio = p->static_prio; } @@ -3518,7 +3518,8 @@ recheck: * 1..MAX_USER_RT_PRIO-1, valid priority for SCHED_NORMAL is 0. */ if (param->sched_priority < 0 || - param->sched_priority > MAX_USER_RT_PRIO-1) + (p->mm && param->sched_priority > MAX_USER_RT_PRIO-1) || + (!p->mm && param->sched_priority > MAX_RT_PRIO-1)) return -EINVAL; if ((policy == SCHED_NORMAL) != (param->sched_priority == 0)) return -EINVAL; -- cgit v1.2.2