From e70c9d5e61c6cb2272c866fc1303e62975006752 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Sat, 25 Jun 2005 14:54:25 -0700 Subject: [PATCH] I8K: use standard DMI interface I8K: Change to use stock dmi infrastructure instead of homegrown parsing code. The driver now requires box's DMI data to match list of supported models so driver can be safely compiled-in by default without fear of it poking into random SMM BIOS code. DMI checks can be ignored with i8k.ignore_dmi option. Signed-off-by: Dmitry Torokhov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/dmi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/dmi.h b/include/linux/dmi.h index d2bcf556088b..5e93e6dce9a4 100644 --- a/include/linux/dmi.h +++ b/include/linux/dmi.h @@ -9,6 +9,7 @@ enum dmi_field { DMI_SYS_VENDOR, DMI_PRODUCT_NAME, DMI_PRODUCT_VERSION, + DMI_PRODUCT_SERIAL, DMI_BOARD_VENDOR, DMI_BOARD_NAME, DMI_BOARD_VERSION, -- cgit v1.2.3 From 52a119feaad92d44a0e97d01b22afbcbaf3fc079 Mon Sep 17 00:00:00 2001 From: Ashok Raj Date: Sat, 25 Jun 2005 14:54:57 -0700 Subject: [PATCH] make smp_prepare_cpu to a weak function I really wish smp_prepare_cpu() would disappear eventually. In the interim this is ideally a weak function, so we dont end up changing several places to define this dummy in headers. Today since the dummy declaration is done only in drivers/base/cpu.c but the function is called in kernel/power/smp.c i get undefined reference in my cpu hotplug code for x86_64 under development. Signed-off-by: Ashok Raj Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cpu.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index fe0298e5dae1..e8904c0da686 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -69,6 +69,7 @@ extern struct semaphore cpucontrol; register_cpu_notifier(&fn##_nb); \ } int cpu_down(unsigned int cpu); +extern int __attribute__((weak)) smp_prepare_cpu(int cpu); #define cpu_is_offline(cpu) unlikely(!cpu_online(cpu)) #else #define lock_cpu_hotplug() do { } while (0) -- cgit v1.2.3 From e6982c671c560da4a0bc5c908cbcbec12bd5991d Mon Sep 17 00:00:00 2001 From: Ashok Raj Date: Sat, 25 Jun 2005 14:54:58 -0700 Subject: [PATCH] x86_64: Change init sections for CPU hotplug support This patch adds __cpuinit and __cpuinitdata sections that need to exist past boot to support cpu hotplug. Caveat: This is done *only* for EM64T CPU Hotplug support, on request from Andi Kleen. Much of the generic hotplug code in kernel, and none of the other archs that support CPU hotplug today, i386, ia64, ppc64, s390 and parisc dont mark sections with __cpuinit, but only mark them as __devinit, and __devinitdata. If someone is motivated to change generic code, we need to make sure all existing hotplug code does not break, on other arch's that dont use __cpuinit, and __cpudevinit. Signed-off-by: Ashok Raj Acked-by: Andi Kleen Acked-by: Zwane Mwaikambo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/init.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/init.h b/include/linux/init.h index 05c83e0521ca..59008c3826cf 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -229,6 +229,18 @@ void __init parse_early_param(void); #define __devexitdata __exitdata #endif +#ifdef CONFIG_HOTPLUG_CPU +#define __cpuinit +#define __cpuinitdata +#define __cpuexit +#define __cpuexitdata +#else +#define __cpuinit __init +#define __cpuinitdata __initdata +#define __cpuexit __exit +#define __cpuexitdata __exitdata +#endif + /* Functions marked as __devexit may be discarded at kernel link time, depending on config options. Newer versions of binutils detect references from retained sections to discarded sections and flag an error. Pointers to -- cgit v1.2.3 From 5a72e04df5470df0ec646029d31e5528167ab1a7 Mon Sep 17 00:00:00 2001 From: Li Shaohua Date: Sat, 25 Jun 2005 14:55:06 -0700 Subject: [PATCH] suspend/resume SMP support Using CPU hotplug to support suspend/resume SMP. Both S3 and S4 use disable/enable_nonboot_cpus API. The S4 part is based on Pavel's original S4 SMP patch. Signed-off-by: Li Shaohua Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/suspend.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 2bf0d5fabcdb..f2e96fdfaae0 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -58,7 +58,7 @@ static inline int software_suspend(void) } #endif -#ifdef CONFIG_SMP +#ifdef CONFIG_SUSPEND_SMP extern void disable_nonboot_cpus(void); extern void enable_nonboot_cpus(void); #else -- cgit v1.2.3 From 620b03276488c3cf103caf1e326bd21f00d3df84 Mon Sep 17 00:00:00 2001 From: Pavel Machek Date: Sat, 25 Jun 2005 14:55:11 -0700 Subject: [PATCH] properly stop devices before poweroff Without this patch, Linux provokes emergency disk shutdowns and similar nastiness. It was in SuSE kernels for some time, IIRC. Signed-off-by: Pavel Machek Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pm.h | 33 +++++++++++++++++++++------------ 1 file changed, 21 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm.h b/include/linux/pm.h index ed2b76e75199..14479325e3f3 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -103,7 +103,8 @@ extern int pm_active; /* * Register a device with power management */ -struct pm_dev __deprecated *pm_register(pm_dev_t type, unsigned long id, pm_callback callback); +struct pm_dev __deprecated * +pm_register(pm_dev_t type, unsigned long id, pm_callback callback); /* * Unregister a device with power management @@ -190,17 +191,18 @@ typedef u32 __bitwise pm_message_t; /* * There are 4 important states driver can be in: * ON -- driver is working - * FREEZE -- stop operations and apply whatever policy is applicable to a suspended driver - * of that class, freeze queues for block like IDE does, drop packets for - * ethernet, etc... stop DMA engine too etc... so a consistent image can be - * saved; but do not power any hardware down. - * SUSPEND - like FREEZE, but hardware is doing as much powersaving as possible. Roughly - * pci D3. + * FREEZE -- stop operations and apply whatever policy is applicable to a + * suspended driver of that class, freeze queues for block like IDE + * does, drop packets for ethernet, etc... stop DMA engine too etc... + * so a consistent image can be saved; but do not power any hardware + * down. + * SUSPEND - like FREEZE, but hardware is doing as much powersaving as + * possible. Roughly pci D3. * - * Unfortunately, current drivers only recognize numeric values 0 (ON) and 3 (SUSPEND). - * We'll need to fix the drivers. So yes, putting 3 to all diferent defines is intentional, - * and will go away as soon as drivers are fixed. Also note that typedef is neccessary, - * we'll probably want to switch to + * Unfortunately, current drivers only recognize numeric values 0 (ON) and 3 + * (SUSPEND). We'll need to fix the drivers. So yes, putting 3 to all different + * defines is intentional, and will go away as soon as drivers are fixed. Also + * note that typedef is neccessary, we'll probably want to switch to * typedef struct pm_message_t { int event; int flags; } pm_message_t * or something similar soon. */ @@ -222,11 +224,18 @@ struct dev_pm_info { extern void device_pm_set_parent(struct device * dev, struct device * parent); -extern int device_suspend(pm_message_t state); extern int device_power_down(pm_message_t state); extern void device_power_up(void); extern void device_resume(void); +#ifdef CONFIG_PM +extern int device_suspend(pm_message_t state); +#else +static inline int device_suspend(pm_message_t state) +{ + return 0; +} +#endif #endif /* __KERNEL__ */ -- cgit v1.2.3 From b2b18660066997420b716c1881a6be8b82700d97 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sat, 25 Jun 2005 14:55:38 -0700 Subject: [PATCH] RCU: clean up a few remaining synchronize_kernel() calls 2.6.12-rc6-mm1 has a few remaining synchronize_kernel()s, some (but not all) in comments. This patch changes these synchronize_kernel() calls (and comments) to synchronize_rcu() or synchronize_sched() as follows: - arch/x86_64/kernel/mce.c mce_read(): change to synchronize_sched() to handle races with machine-check exceptions (synchronize_rcu() would not cut it given RCU implementations intended for hardcore realtime use. - drivers/input/serio/i8042.c i8042_stop(): change to synchronize_sched() to handle races with i8042_interrupt() interrupt handler. Again, synchronize_rcu() would not cut it given RCU implementations intended for hardcore realtime use. - include/*/kdebug.h comments: change to synchronize_sched() to handle races with NMIs. As before, synchronize_rcu() would not cut it... - include/linux/list.h comment: change to synchronize_rcu(), since this comment is for list_del_rcu(). - security/keys/key.c unregister_key_type(): change to synchronize_rcu(), since this is interacting with RCU read side. - security/keys/process_keys.c install_session_keyring(): change to synchronize_rcu(), since this is interacting with RCU read side. Signed-off-by: "Paul E. McKenney" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/list.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/list.h b/include/linux/list.h index 399b51d17218..aab2db21b013 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -185,7 +185,7 @@ static inline void list_del(struct list_head *entry) * list_for_each_entry_rcu(). * * Note that the caller is not permitted to immediately free - * the newly deleted entry. Instead, either synchronize_kernel() + * the newly deleted entry. Instead, either synchronize_rcu() * or call_rcu() must be used to defer freeing until an RCU * grace period has elapsed. */ -- cgit v1.2.3 From 7897986bad8f6cd50d6149345aca7f6480f49464 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Sat, 25 Jun 2005 14:57:13 -0700 Subject: [PATCH] sched: balance timers Do CPU load averaging over a number of different intervals. Allow each interval to be chosen by sending a parameter to source_load and target_load. 0 is instantaneous, idx > 0 returns a decaying average with the most recent sample weighted at 2^(idx-1). To a maximum of 3 (could be easily increased). So generally a higher number will result in more conservative balancing. Signed-off-by: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 4 ++++ include/linux/topology.h | 8 ++++++++ 2 files changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 2c69682b0444..664981ac1fb6 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -488,6 +488,10 @@ struct sched_domain { unsigned long long cache_hot_time; /* Task considered cache hot (ns) */ unsigned int cache_nice_tries; /* Leave cache hot tasks for # tries */ unsigned int per_cpu_gain; /* CPU % gained by adding domain cpus */ + unsigned int busy_idx; + unsigned int idle_idx; + unsigned int newidle_idx; + unsigned int wake_idx; int flags; /* See SD_* */ /* Runtime fields. */ diff --git a/include/linux/topology.h b/include/linux/topology.h index d70e8972c67f..ae9c2216dfa6 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -89,6 +89,10 @@ .cache_hot_time = 0, \ .cache_nice_tries = 0, \ .per_cpu_gain = 25, \ + .busy_idx = 0, \ + .idle_idx = 0, \ + .newidle_idx = 0, \ + .wake_idx = 0, \ .flags = SD_LOAD_BALANCE \ | SD_BALANCE_NEWIDLE \ | SD_BALANCE_EXEC \ @@ -115,6 +119,10 @@ .cache_hot_time = (5*1000000/2), \ .cache_nice_tries = 1, \ .per_cpu_gain = 100, \ + .busy_idx = 2, \ + .idle_idx = 0, \ + .newidle_idx = 1, \ + .wake_idx = 1, \ .flags = SD_LOAD_BALANCE \ | SD_BALANCE_NEWIDLE \ | SD_BALANCE_EXEC \ -- cgit v1.2.3 From cafb20c1f9976a70d633bb1e1c8c24eab00e4e80 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Sat, 25 Jun 2005 14:57:17 -0700 Subject: [PATCH] sched: no aggressive idle balancing Remove the very aggressive idle stuff that has recently gone into 2.6 - it is going against the direction we are trying to go. Hopefully we can regain performance through other methods. Signed-off-by: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/topology.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/topology.h b/include/linux/topology.h index ae9c2216dfa6..b23ec64df7f1 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -127,7 +127,6 @@ | SD_BALANCE_NEWIDLE \ | SD_BALANCE_EXEC \ | SD_WAKE_AFFINE \ - | SD_WAKE_IDLE \ | SD_WAKE_BALANCE, \ .last_balance = jiffies, \ .balance_interval = 1, \ -- cgit v1.2.3 From 147cbb4bbe991452698f0772d8292f22825710ba Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Sat, 25 Jun 2005 14:57:19 -0700 Subject: [PATCH] sched: balance on fork Reimplement the balance on exec balancing to be sched-domains aware. Use this to also do balance on fork balancing. Make x86_64 do balance on fork over the NUMA domain. The problem that the non sched domains aware blancing became apparent on dual core, multi socket opterons. What we want is for the new tasks to be sent to a different socket, but more often than not, we would first load up our sibling core, or fill two cores of a single remote socket before selecting a new one. This gives large improvements to STREAM on such systems. Signed-off-by: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 10 ++++++---- include/linux/topology.h | 2 ++ 2 files changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 664981ac1fb6..613491d3a875 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -460,10 +460,11 @@ enum idle_type #define SD_LOAD_BALANCE 1 /* Do load balancing on this domain. */ #define SD_BALANCE_NEWIDLE 2 /* Balance when about to become idle */ #define SD_BALANCE_EXEC 4 /* Balance on exec */ -#define SD_WAKE_IDLE 8 /* Wake to idle CPU on task wakeup */ -#define SD_WAKE_AFFINE 16 /* Wake task to waking CPU */ -#define SD_WAKE_BALANCE 32 /* Perform balancing at task wakeup */ -#define SD_SHARE_CPUPOWER 64 /* Domain members share cpu power */ +#define SD_BALANCE_FORK 8 /* Balance on fork, clone */ +#define SD_WAKE_IDLE 16 /* Wake to idle CPU on task wakeup */ +#define SD_WAKE_AFFINE 32 /* Wake task to waking CPU */ +#define SD_WAKE_BALANCE 64 /* Perform balancing at task wakeup */ +#define SD_SHARE_CPUPOWER 128 /* Domain members share cpu power */ struct sched_group { struct sched_group *next; /* Must be a circular list */ @@ -492,6 +493,7 @@ struct sched_domain { unsigned int idle_idx; unsigned int newidle_idx; unsigned int wake_idx; + unsigned int forkexec_idx; int flags; /* See SD_* */ /* Runtime fields. */ diff --git a/include/linux/topology.h b/include/linux/topology.h index b23ec64df7f1..665597207def 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -93,6 +93,7 @@ .idle_idx = 0, \ .newidle_idx = 0, \ .wake_idx = 0, \ + .forkexec_idx = 0, \ .flags = SD_LOAD_BALANCE \ | SD_BALANCE_NEWIDLE \ | SD_BALANCE_EXEC \ @@ -123,6 +124,7 @@ .idle_idx = 0, \ .newidle_idx = 1, \ .wake_idx = 1, \ + .forkexec_idx = 0, \ .flags = SD_LOAD_BALANCE \ | SD_BALANCE_NEWIDLE \ | SD_BALANCE_EXEC \ -- cgit v1.2.3 From 68767a0ae428801649d510d9a65bb71feed44dd1 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Sat, 25 Jun 2005 14:57:20 -0700 Subject: [PATCH] sched: schedstats update for balance on fork Add SCHEDSTAT statistics for sched-balance-fork. Signed-off-by: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 613491d3a875..36a10781c3f3 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -517,10 +517,16 @@ struct sched_domain { unsigned long alb_failed; unsigned long alb_pushed; - /* sched_balance_exec() stats */ - unsigned long sbe_attempts; + /* SD_BALANCE_EXEC stats */ + unsigned long sbe_cnt; + unsigned long sbe_balanced; unsigned long sbe_pushed; + /* SD_BALANCE_FORK stats */ + unsigned long sbf_cnt; + unsigned long sbf_balanced; + unsigned long sbf_pushed; + /* try_to_wake_up() stats */ unsigned long ttwu_wake_remote; unsigned long ttwu_move_affine; -- cgit v1.2.3 From 687f1661d302bc70ce906594a6d3f615ef075a50 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Sat, 25 Jun 2005 14:57:21 -0700 Subject: [PATCH] sched: sched tuning Do some basic initial tuning. Signed-off-by: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/topology.h | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/topology.h b/include/linux/topology.h index 665597207def..0320225e96da 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -91,7 +91,7 @@ .per_cpu_gain = 25, \ .busy_idx = 0, \ .idle_idx = 0, \ - .newidle_idx = 0, \ + .newidle_idx = 1, \ .wake_idx = 0, \ .forkexec_idx = 0, \ .flags = SD_LOAD_BALANCE \ @@ -121,15 +121,14 @@ .cache_nice_tries = 1, \ .per_cpu_gain = 100, \ .busy_idx = 2, \ - .idle_idx = 0, \ - .newidle_idx = 1, \ + .idle_idx = 1, \ + .newidle_idx = 2, \ .wake_idx = 1, \ - .forkexec_idx = 0, \ + .forkexec_idx = 1, \ .flags = SD_LOAD_BALANCE \ | SD_BALANCE_NEWIDLE \ | SD_BALANCE_EXEC \ - | SD_WAKE_AFFINE \ - | SD_WAKE_BALANCE, \ + | SD_WAKE_AFFINE, \ .last_balance = jiffies, \ .balance_interval = 1, \ .nr_balance_failed = 0, \ -- cgit v1.2.3 From 4866cde064afbb6c2a488c265e696879de616daa Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Sat, 25 Jun 2005 14:57:23 -0700 Subject: [PATCH] sched: cleanup context switch locking Instead of requiring architecture code to interact with the scheduler's locking implementation, provide a couple of defines that can be used by the architecture to request runqueue unlocked context switches, and ask for interrupts to be enabled over the context switch. Also replaces the "switch_lock" used by these architectures with an oncpu flag (note, not a potentially slow bitflag). This eliminates one bus locked memory operation when context switching, and simplifies the task_running function. Signed-off-by: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/init_task.h | 1 - include/linux/sched.h | 10 ++++++++-- 2 files changed, 8 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/init_task.h b/include/linux/init_task.h index a6a8c1a38d5e..03206a425d7a 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -108,7 +108,6 @@ extern struct group_info init_groups; .blocked = {{0}}, \ .alloc_lock = SPIN_LOCK_UNLOCKED, \ .proc_lock = SPIN_LOCK_UNLOCKED, \ - .switch_lock = SPIN_LOCK_UNLOCKED, \ .journal_info = NULL, \ .cpu_timers = INIT_CPU_TIMERS(tsk.cpu_timers), \ } diff --git a/include/linux/sched.h b/include/linux/sched.h index 36a10781c3f3..d27be9337425 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -368,6 +368,11 @@ struct signal_struct { #endif }; +/* Context switch must be unlocked if interrupts are to be enabled */ +#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW +# define __ARCH_WANT_UNLOCKED_CTXSW +#endif + /* * Bits in flags field of signal_struct. */ @@ -594,6 +599,9 @@ struct task_struct { int lock_depth; /* BKL lock depth */ +#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW) + int oncpu; +#endif int prio, static_prio; struct list_head run_list; prio_array_t *array; @@ -716,8 +724,6 @@ struct task_struct { spinlock_t alloc_lock; /* Protection of proc_dentry: nesting proc_lock, dcache_lock, write_lock_irq(&tasklist_lock); */ spinlock_t proc_lock; -/* context-switch lock */ - spinlock_t switch_lock; /* journalling filesystem info */ void *journal_info; -- cgit v1.2.3 From 476d139c218e44e045e4bc6d4cc02b010b343939 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Sat, 25 Jun 2005 14:57:29 -0700 Subject: [PATCH] sched: consolidate sbe sbf Consolidate balance-on-exec with balance-on-fork. This is made easy by the sched-domains RCU patches. As well as the general goodness of code reduction, this allows the runqueues to be unlocked during balance-on-fork. schedstats is a problem. Maybe just have balance-on-event instead of distinguishing fork and exec? Signed-off-by: Nick Piggin Acked-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index d27be9337425..edb2c69a8873 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -930,7 +930,7 @@ extern void FASTCALL(wake_up_new_task(struct task_struct * tsk, #else static inline void kick_process(struct task_struct *tsk) { } #endif -extern void FASTCALL(sched_fork(task_t * p)); +extern void FASTCALL(sched_fork(task_t * p, int clone_flags)); extern void FASTCALL(sched_exit(task_t * p)); extern int in_group_p(gid_t); -- cgit v1.2.3 From 1a20ff27ef75d866730ee796acd811a925af762f Mon Sep 17 00:00:00 2001 From: Dinakar Guniguntala Date: Sat, 25 Jun 2005 14:57:33 -0700 Subject: [PATCH] Dynamic sched domains: sched changes The following patches add dynamic sched domains functionality that was extensively discussed on lkml and lse-tech. I would like to see this added to -mm o The main advantage with this feature is that it ensures that the scheduler load balacing code only balances against the cpus that are in the sched domain as defined by an exclusive cpuset and not all of the cpus in the system. This removes any overhead due to load balancing code trying to pull tasks outside of the cpu exclusive cpuset only to be prevented by the tasks' cpus_allowed mask. o cpu exclusive cpusets are useful for servers running orthogonal workloads such as RT applications requiring low latency and HPC applications that are throughput sensitive o It provides a new API partition_sched_domains in sched.c that makes dynamic sched domains possible. o cpu_exclusive cpusets sets are now associated with a sched domain. Which means that the users can dynamically modify the sched domains through the cpuset file system interface o ia64 sched domain code has been updated to support this feature as well o Currently, this does not support hotplug. (However some of my tests indicate hotplug+preempt is currently broken) o I have tested it extensively on x86. o This should have very minimal impact on performance as none of the fast paths are affected Signed-off-by: Dinakar Guniguntala Acked-by: Paul Jackson Acked-by: Nick Piggin Acked-by: Matthew Dobson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index edb2c69a8873..98c109e4f43d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -539,6 +539,8 @@ struct sched_domain { #endif }; +extern void partition_sched_domains(cpumask_t *partition1, + cpumask_t *partition2); #ifdef ARCH_HAS_SCHED_DOMAIN /* Useful helpers that arch setup code may use. Defined in kernel/sched.c */ extern cpumask_t cpu_isolated_map; -- cgit v1.2.3 From f8cbd99bd3a023db8d6356d19a5f6f539d367327 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sat, 25 Jun 2005 14:57:39 -0700 Subject: [PATCH] sched: voluntary kernel preemption This patch adds a new preemption model: 'Voluntary Kernel Preemption'. The 3 models can be selected from a new menu: (X) No Forced Preemption (Server) ( ) Voluntary Kernel Preemption (Desktop) ( ) Preemptible Kernel (Low-Latency Desktop) we still default to the stock (Server) preemption model. Voluntary preemption works by adding a cond_resched() (reschedule-if-needed) call to every might_sleep() check. It is lighter than CONFIG_PREEMPT - at the cost of not having as tight latencies. It represents a different latency/complexity/overhead tradeoff. It has no runtime impact at all if disabled. Here are size stats that show how the various preemption models impact the kernel's size: text data bss dec hex filename 3618774 547184 179896 4345854 424ffe vmlinux.stock 3626406 547184 179896 4353486 426dce vmlinux.voluntary +0.2% 3748414 548640 179896 4476950 445016 vmlinux.preempt +3.5% voluntary-preempt is +0.2% of .text, preempt is +3.5%. This feature has been tested for many months by lots of people (and it's also included in the RHEL4 distribution and earlier variants were in Fedora as well), and it's intended for users and distributions who dont want to use full-blown CONFIG_PREEMPT for one reason or another. Signed-off-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index e25b97062ce1..687ba8c9973d 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -58,15 +58,23 @@ struct completion; * be biten later when the calling function happens to sleep when it is not * supposed to. */ +#ifdef CONFIG_PREEMPT_VOLUNTARY +extern int cond_resched(void); +# define might_resched() cond_resched() +#else +# define might_resched() do { } while (0) +#endif + #ifdef CONFIG_DEBUG_SPINLOCK_SLEEP -#define might_sleep() __might_sleep(__FILE__, __LINE__) -#define might_sleep_if(cond) do { if (unlikely(cond)) might_sleep(); } while (0) -void __might_sleep(char *file, int line); + void __might_sleep(char *file, int line); +# define might_sleep() \ + do { __might_sleep(__FILE__, __LINE__); might_resched(); } while (0) #else -#define might_sleep() do {} while(0) -#define might_sleep_if(cond) do {} while (0) +# define might_sleep() do { might_resched(); } while (0) #endif +#define might_sleep_if(cond) do { if (unlikely(cond)) might_sleep(); } while (0) + #define abs(x) ({ \ int __x = (x); \ (__x < 0) ? -__x : __x; \ -- cgit v1.2.3 From dc009d92435f99498cbc579ce76bf28e837e2c14 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sat, 25 Jun 2005 14:57:52 -0700 Subject: [PATCH] kexec: add kexec syscalls This patch introduces the architecture independent implementation the sys_kexec_load, the compat_sys_kexec_load system calls. Kexec on panic support has been integrated into the core patch and is relatively clean. In addition the hopefully architecture independent option crashkernel=size@location has been docuemented. It's purpose is to reserve space for the panic kernel to live, and where no DMA transfer will ever be setup to access. Signed-off-by: Eric Biederman Signed-off-by: Alexander Nyberg Signed-off-by: Adrian Bunk Signed-off-by: Vivek Goyal Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kexec.h | 127 +++++++++++++++++++++++++++++++++++++++++++++++ include/linux/reboot.h | 3 ++ include/linux/syscalls.h | 5 +- 3 files changed, 133 insertions(+), 2 deletions(-) create mode 100644 include/linux/kexec.h (limited to 'include/linux') diff --git a/include/linux/kexec.h b/include/linux/kexec.h new file mode 100644 index 000000000000..e3fc35f4e35f --- /dev/null +++ b/include/linux/kexec.h @@ -0,0 +1,127 @@ +#ifndef LINUX_KEXEC_H +#define LINUX_KEXEC_H + +#ifdef CONFIG_KEXEC +#include +#include +#include +#include +#include + +/* Verify architecture specific macros are defined */ + +#ifndef KEXEC_SOURCE_MEMORY_LIMIT +#error KEXEC_SOURCE_MEMORY_LIMIT not defined +#endif + +#ifndef KEXEC_DESTINATION_MEMORY_LIMIT +#error KEXEC_DESTINATION_MEMORY_LIMIT not defined +#endif + +#ifndef KEXEC_CONTROL_MEMORY_LIMIT +#error KEXEC_CONTROL_MEMORY_LIMIT not defined +#endif + +#ifndef KEXEC_CONTROL_CODE_SIZE +#error KEXEC_CONTROL_CODE_SIZE not defined +#endif + +#ifndef KEXEC_ARCH +#error KEXEC_ARCH not defined +#endif + +/* + * This structure is used to hold the arguments that are used when loading + * kernel binaries. + */ + +typedef unsigned long kimage_entry_t; +#define IND_DESTINATION 0x1 +#define IND_INDIRECTION 0x2 +#define IND_DONE 0x4 +#define IND_SOURCE 0x8 + +#define KEXEC_SEGMENT_MAX 8 +struct kexec_segment { + void __user *buf; + size_t bufsz; + unsigned long mem; /* User space sees this as a (void *) ... */ + size_t memsz; +}; + +#ifdef CONFIG_COMPAT +struct compat_kexec_segment { + compat_uptr_t buf; + compat_size_t bufsz; + compat_ulong_t mem; /* User space sees this as a (void *) ... */ + compat_size_t memsz; +}; +#endif + +struct kimage { + kimage_entry_t head; + kimage_entry_t *entry; + kimage_entry_t *last_entry; + + unsigned long destination; + + unsigned long start; + struct page *control_code_page; + + unsigned long nr_segments; + struct kexec_segment segment[KEXEC_SEGMENT_MAX]; + + struct list_head control_pages; + struct list_head dest_pages; + struct list_head unuseable_pages; + + /* Address of next control page to allocate for crash kernels. */ + unsigned long control_page; + + /* Flags to indicate special processing */ + unsigned int type : 1; +#define KEXEC_TYPE_DEFAULT 0 +#define KEXEC_TYPE_CRASH 1 +}; + + + +/* kexec interface functions */ +extern NORET_TYPE void machine_kexec(struct kimage *image) ATTRIB_NORET; +extern int machine_kexec_prepare(struct kimage *image); +extern void machine_kexec_cleanup(struct kimage *image); +extern asmlinkage long sys_kexec_load(unsigned long entry, + unsigned long nr_segments, struct kexec_segment __user *segments, + unsigned long flags); +#ifdef CONFIG_COMPAT +extern asmlinkage long compat_sys_kexec_load(unsigned long entry, + unsigned long nr_segments, struct compat_kexec_segment __user *segments, + unsigned long flags); +#endif +extern struct page *kimage_alloc_control_pages(struct kimage *image, unsigned int order); +extern void crash_kexec(void); +extern struct kimage *kexec_image; + +#define KEXEC_ON_CRASH 0x00000001 +#define KEXEC_ARCH_MASK 0xffff0000 + +/* These values match the ELF architecture values. + * Unless there is a good reason that should continue to be the case. + */ +#define KEXEC_ARCH_DEFAULT ( 0 << 16) +#define KEXEC_ARCH_386 ( 3 << 16) +#define KEXEC_ARCH_X86_64 (62 << 16) +#define KEXEC_ARCH_PPC (20 << 16) +#define KEXEC_ARCH_PPC64 (21 << 16) +#define KEXEC_ARCH_IA_64 (50 << 16) + +#define KEXEC_FLAGS (KEXEC_ON_CRASH) /* List of defined/legal kexec flags */ + +/* Location of a reserved region to hold the crash kernel. + */ +extern struct resource crashk_res; + +#else /* !CONFIG_KEXEC */ +static inline void crash_kexec(void) { } +#endif /* CONFIG_KEXEC */ +#endif /* LINUX_KEXEC_H */ diff --git a/include/linux/reboot.h b/include/linux/reboot.h index d60fafc8bdc5..c5a05e16edb2 100644 --- a/include/linux/reboot.h +++ b/include/linux/reboot.h @@ -51,6 +51,9 @@ extern void machine_restart(char *cmd); extern void machine_halt(void); extern void machine_power_off(void); +extern void machine_shutdown(void); +extern void machine_crash_shutdown(void); + #endif #endif /* _LINUX_REBOOT_H */ diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index c39f6f72cbbc..7ba8f8f747aa 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -159,8 +159,9 @@ asmlinkage long sys_shutdown(int, int); asmlinkage long sys_reboot(int magic1, int magic2, unsigned int cmd, void __user *arg); asmlinkage long sys_restart_syscall(void); -asmlinkage long sys_kexec_load(void *entry, unsigned long nr_segments, - struct kexec_segment *segments, unsigned long flags); +asmlinkage long sys_kexec_load(unsigned long entry, + unsigned long nr_segments, struct kexec_segment __user *segments, + unsigned long flags); asmlinkage long sys_exit(int error_code); asmlinkage void sys_exit_group(int error_code); -- cgit v1.2.3 From cf13f0eaffa31bf6a145c53c589654b11c72ddc7 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Sat, 25 Jun 2005 14:58:11 -0700 Subject: [PATCH] kexec: s390 support Add kexec support for s390 architecture. From: Milton Miller - Fix passing of first argument to relocate_kernel assembly. - Fix Kconfig description. - Remove wrong comment and comments that describe obvious things. - Allow only KEXEC_TYPE_DEFAULT as image type -> dump not supported. Acked-by: Martin Schwidefsky Signed-off-by: Heiko Carstens Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kexec.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index e3fc35f4e35f..0653a27c3d72 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -114,6 +114,7 @@ extern struct kimage *kexec_image; #define KEXEC_ARCH_PPC (20 << 16) #define KEXEC_ARCH_PPC64 (21 << 16) #define KEXEC_ARCH_IA_64 (50 << 16) +#define KEXEC_ARCH_S390 (22 << 16) #define KEXEC_FLAGS (KEXEC_ON_CRASH) /* List of defined/legal kexec flags */ -- cgit v1.2.3 From 92aa63a5a1bf2e7b0c79e6716d24b76dbbdcf951 Mon Sep 17 00:00:00 2001 From: Vivek Goyal Date: Sat, 25 Jun 2005 14:58:18 -0700 Subject: [PATCH] kdump: Retrieve saved max pfn This patch retrieves the max_pfn being used by previous kernel and stores it in a safe location (saved_max_pfn) before it is overwritten due to user defined memory map. This pfn is used to make sure that user does not try to read the physical memory beyond saved_max_pfn. Signed-off-by: Vivek Goyal Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootmem.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 500f451ce0c0..82bd8842d11c 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -22,6 +22,10 @@ extern unsigned long min_low_pfn; */ extern unsigned long max_pfn; +#ifdef CONFIG_CRASH_DUMP +extern unsigned long saved_max_pfn; +#endif + /* * node_bootmem_map is a map pointer - the bits represent all physical * memory pages (including holes) on the node. -- cgit v1.2.3 From 60e64d46a58236e3c718074372cab6a5b56a3b15 Mon Sep 17 00:00:00 2001 From: Vivek Goyal Date: Sat, 25 Jun 2005 14:58:19 -0700 Subject: [PATCH] kdump: Routines for copying dump pages This patch provides the interfaces necessary to read the dump contents, treating it as a high memory device. Signed off by Hariprasad Nellitheertha Signed-off-by: Eric Biederman Signed-off-by: Vivek Goyal Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/crash_dump.h | 13 +++++++++++++ include/linux/highmem.h | 1 + 2 files changed, 14 insertions(+) create mode 100644 include/linux/crash_dump.h (limited to 'include/linux') diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h new file mode 100644 index 000000000000..7d983b817429 --- /dev/null +++ b/include/linux/crash_dump.h @@ -0,0 +1,13 @@ +#ifndef LINUX_CRASH_DUMP_H +#define LINUX_CRASH_DUMP_H + +#ifdef CONFIG_CRASH_DUMP +#include +#include +#include +#include + +extern ssize_t copy_oldmem_page(unsigned long, char *, size_t, + unsigned long, int); +#endif /* CONFIG_CRASH_DUMP */ +#endif /* LINUX_CRASHDUMP_H */ diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 2a7e6c65c882..6bece9280eb7 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -28,6 +28,7 @@ static inline void *kmap(struct page *page) #define kmap_atomic(page, idx) page_address(page) #define kunmap_atomic(addr, idx) do { } while (0) +#define kmap_atomic_pfn(pfn, idx) page_address(pfn_to_page(pfn)) #define kmap_atomic_to_page(ptr) virt_to_page(ptr) #endif /* CONFIG_HIGHMEM */ -- cgit v1.2.3 From 2030eae52b416a9a9f0ffda74c982b7f1e19496d Mon Sep 17 00:00:00 2001 From: Vivek Goyal Date: Sat, 25 Jun 2005 14:58:20 -0700 Subject: [PATCH] Retrieve elfcorehdr address from command line This patch adds support for retrieving the address of elf core header if one is passed in command line. Signed-off-by: Vivek Goyal Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/crash_dump.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h index 7d983b817429..3f25fd1eaa4b 100644 --- a/include/linux/crash_dump.h +++ b/include/linux/crash_dump.h @@ -7,6 +7,7 @@ #include #include +extern unsigned long long elfcorehdr_addr; extern ssize_t copy_oldmem_page(unsigned long, char *, size_t, unsigned long, int); #endif /* CONFIG_CRASH_DUMP */ -- cgit v1.2.3 From 666bfddbe8b8fd4fd44617d6c55193d5ac7edb29 Mon Sep 17 00:00:00 2001 From: Vivek Goyal Date: Sat, 25 Jun 2005 14:58:21 -0700 Subject: [PATCH] kdump: Access dump file in elf format (/proc/vmcore) From: "Vivek Goyal" o Support for /proc/vmcore interface. This interface exports elf core image either in ELF32 or ELF64 format, depending on the format in which elf headers have been stored by crashed kernel. o Added support for CONFIG_VMCORE config option. o Removed the dependency on /proc/kcore. From: "Eric W. Biederman" This patch has been refactored to more closely match the prevailing style in the affected files. And to clearly indicate the dependency between /proc/kcore and proc/vmcore.c From: Hariprasad Nellitheertha This patch contains the code that provides an ELF format interface to the previous kernel's memory post kexec reboot. Signed off by Hariprasad Nellitheertha Signed-off-by: Eric Biederman Signed-off-by: Vivek Goyal Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/crash_dump.h | 4 ++++ include/linux/proc_fs.h | 7 +++++++ 2 files changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h index 3f25fd1eaa4b..534d750d922d 100644 --- a/include/linux/crash_dump.h +++ b/include/linux/crash_dump.h @@ -7,8 +7,12 @@ #include #include +#define ELFCORE_ADDR_MAX (-1ULL) extern unsigned long long elfcorehdr_addr; extern ssize_t copy_oldmem_page(unsigned long, char *, size_t, unsigned long, int); +extern struct file_operations proc_vmcore_operations; +extern struct proc_dir_entry *proc_vmcore; + #endif /* CONFIG_CRASH_DUMP */ #endif /* LINUX_CRASHDUMP_H */ diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 59e505261fd6..0563581e3a02 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -74,6 +74,13 @@ struct kcore_list { size_t size; }; +struct vmcore { + struct list_head list; + unsigned long long paddr; + unsigned long size; + loff_t offset; +}; + #ifdef CONFIG_PROC_FS extern struct proc_dir_entry proc_root; -- cgit v1.2.3 From 6e274d144302068a00794ec22e73520c0615cb6f Mon Sep 17 00:00:00 2001 From: Alexander Nyberg Date: Sat, 25 Jun 2005 14:58:26 -0700 Subject: [PATCH] kdump: Use real pt_regs from exception Makes kexec_crashdump() take a pt_regs * as an argument. This allows to get exact register state at the point of the crash. If we come from direct panic assertion NULL will be passed and the current registers saved before crashdump. This hooks into two places: die(): check the conditions under which we will panic when calling do_exit and go there directly with the pt_regs that caused the fatal fault. die_nmi(): If we receive an NMI lockup while in the kernel use the pt_regs and go directly to crash_kexec(). We're probably nested up badly at this point so this might be the only chance to escape with proper information. Signed-off-by: Alexander Nyberg Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kexec.h | 8 ++++++-- include/linux/reboot.h | 3 ++- 2 files changed, 8 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 0653a27c3d72..7383173a3a9c 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -99,7 +99,8 @@ extern asmlinkage long compat_sys_kexec_load(unsigned long entry, unsigned long flags); #endif extern struct page *kimage_alloc_control_pages(struct kimage *image, unsigned int order); -extern void crash_kexec(void); +extern void crash_kexec(struct pt_regs *); +int kexec_should_crash(struct task_struct *); extern struct kimage *kexec_image; #define KEXEC_ON_CRASH 0x00000001 @@ -123,6 +124,9 @@ extern struct kimage *kexec_image; extern struct resource crashk_res; #else /* !CONFIG_KEXEC */ -static inline void crash_kexec(void) { } +struct pt_regs; +struct task_struct; +static inline void crash_kexec(struct pt_regs *regs) { } +static inline int kexec_should_crash(struct task_struct *p) { return 0; } #endif /* CONFIG_KEXEC */ #endif /* LINUX_KEXEC_H */ diff --git a/include/linux/reboot.h b/include/linux/reboot.h index c5a05e16edb2..2d4dd23168dd 100644 --- a/include/linux/reboot.h +++ b/include/linux/reboot.h @@ -52,7 +52,8 @@ extern void machine_halt(void); extern void machine_power_off(void); extern void machine_shutdown(void); -extern void machine_crash_shutdown(void); +struct pt_regs; +extern void machine_crash_shutdown(struct pt_regs *); #endif -- cgit v1.2.3 From 72414d3f1d22fc3e311b162fca95c430048d38ce Mon Sep 17 00:00:00 2001 From: Maneesh Soni Date: Sat, 25 Jun 2005 14:58:28 -0700 Subject: [PATCH] kexec code cleanup o Following patch provides purely cosmetic changes and corrects CodingStyle guide lines related certain issues like below in kexec related files o braces for one line "if" statements, "for" loops, o more than 80 column wide lines, o No space after "while", "for" and "switch" key words o Changes: o take-2: Removed the extra tab before "case" key words. o take-3: Put operator at the end of line and space before "*/" Signed-off-by: Maneesh Soni Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kexec.h | 13 ++++++++----- include/linux/syscalls.h | 6 +++--- 2 files changed, 11 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 7383173a3a9c..c8468472aec0 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -91,14 +91,17 @@ extern NORET_TYPE void machine_kexec(struct kimage *image) ATTRIB_NORET; extern int machine_kexec_prepare(struct kimage *image); extern void machine_kexec_cleanup(struct kimage *image); extern asmlinkage long sys_kexec_load(unsigned long entry, - unsigned long nr_segments, struct kexec_segment __user *segments, - unsigned long flags); + unsigned long nr_segments, + struct kexec_segment __user *segments, + unsigned long flags); #ifdef CONFIG_COMPAT extern asmlinkage long compat_sys_kexec_load(unsigned long entry, - unsigned long nr_segments, struct compat_kexec_segment __user *segments, - unsigned long flags); + unsigned long nr_segments, + struct compat_kexec_segment __user *segments, + unsigned long flags); #endif -extern struct page *kimage_alloc_control_pages(struct kimage *image, unsigned int order); +extern struct page *kimage_alloc_control_pages(struct kimage *image, + unsigned int order); extern void crash_kexec(struct pt_regs *); int kexec_should_crash(struct task_struct *); extern struct kimage *kexec_image; diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 7ba8f8f747aa..52830b6d94e5 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -159,9 +159,9 @@ asmlinkage long sys_shutdown(int, int); asmlinkage long sys_reboot(int magic1, int magic2, unsigned int cmd, void __user *arg); asmlinkage long sys_restart_syscall(void); -asmlinkage long sys_kexec_load(unsigned long entry, - unsigned long nr_segments, struct kexec_segment __user *segments, - unsigned long flags); +asmlinkage long sys_kexec_load(unsigned long entry, unsigned long nr_segments, + struct kexec_segment __user *segments, + unsigned long flags); asmlinkage long sys_exit(int error_code); asmlinkage void sys_exit_group(int error_code); -- cgit v1.2.3 From 8c0e33c133021ee241e9d51255b9fb18eb34ef0e Mon Sep 17 00:00:00 2001 From: Nick Wilson Date: Sat, 25 Jun 2005 14:59:00 -0700 Subject: [PATCH] Use ALIGN to remove duplicate code This patch makes use of ALIGN() to remove duplicate round-up code. Signed-off-by: Nick Wilson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/a.out.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/a.out.h b/include/linux/a.out.h index af8a1dfa5c32..f913cc3e1b0d 100644 --- a/include/linux/a.out.h +++ b/include/linux/a.out.h @@ -138,7 +138,7 @@ enum machine_type { #endif #endif -#define _N_SEGMENT_ROUND(x) (((x) + SEGMENT_SIZE - 1) & ~(SEGMENT_SIZE - 1)) +#define _N_SEGMENT_ROUND(x) ALIGN(x, SEGMENT_SIZE) #define _N_TXTENDADDR(x) (N_TXTADDR(x)+(x).a_text) -- cgit v1.2.3 From 681ea4b930768444e9d88651c1362b0bf6d2a42b Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Sat, 25 Jun 2005 14:59:04 -0700 Subject: [PATCH] drivers/char/nvram.c: possible cleanups This patch contains the following possible cleanups: - make the needlessly global function __nvram_set_checksum static - #if 0 the unused global function nvram_set_checksum - remove the EXPORT_SYMBOL's for both functions Signed-off-by: Adrian Bunk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nvram.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nvram.h b/include/linux/nvram.h index b031e41b5e0d..9189829c131c 100644 --- a/include/linux/nvram.h +++ b/include/linux/nvram.h @@ -20,8 +20,6 @@ extern void __nvram_write_byte(unsigned char c, int i); extern void nvram_write_byte(unsigned char c, int i); extern int __nvram_check_checksum(void); extern int nvram_check_checksum(void); -extern void __nvram_set_checksum(void); -extern void nvram_set_checksum(void); #endif #endif /* _LINUX_NVRAM_H */ -- cgit v1.2.3 From 93d17d3d84b7147e8f07aeeb15ec01aa92c6b564 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Sat, 25 Jun 2005 14:59:10 -0700 Subject: [PATCH] drivers/block/ll_rw_blk.c: cleanups This patch contains the following cleanups: - make needlessly global code static - remove the following unused global functions: - blkdev_scsi_issue_flush_fn - __blk_attempt_remerge - remove the following unused EXPORT_SYMBOL's: - blk_phys_contig_segment - blk_hw_contig_segment - blkdev_scsi_issue_flush_fn - __blk_attempt_remerge Signed-off-by: Adrian Bunk Acked-by: Jens Axboe Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/blkdev.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 60272141ff19..b54a0348a890 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -539,15 +539,12 @@ extern void generic_make_request(struct bio *bio); extern void blk_put_request(struct request *); extern void blk_end_sync_rq(struct request *rq); extern void blk_attempt_remerge(request_queue_t *, struct request *); -extern void __blk_attempt_remerge(request_queue_t *, struct request *); extern struct request *blk_get_request(request_queue_t *, int, int); extern void blk_insert_request(request_queue_t *, struct request *, int, void *); extern void blk_requeue_request(request_queue_t *, struct request *); extern void blk_plug_device(request_queue_t *); extern int blk_remove_plug(request_queue_t *); extern void blk_recount_segments(request_queue_t *, struct bio *); -extern int blk_phys_contig_segment(request_queue_t *q, struct bio *, struct bio *); -extern int blk_hw_contig_segment(request_queue_t *q, struct bio *, struct bio *); extern int scsi_cmd_ioctl(struct file *, struct gendisk *, unsigned int, void __user *); extern void blk_start_queue(request_queue_t *q); extern void blk_stop_queue(request_queue_t *q); @@ -631,7 +628,6 @@ extern void blk_queue_dma_alignment(request_queue_t *, int); extern struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev); extern void blk_queue_ordered(request_queue_t *, int); extern void blk_queue_issue_flush_fn(request_queue_t *, issue_flush_fn *); -extern int blkdev_scsi_issue_flush_fn(request_queue_t *, struct gendisk *, sector_t *); extern struct request *blk_start_pre_flush(request_queue_t *,struct request *); extern int blk_complete_barrier_rq(request_queue_t *, struct request *, int); extern int blk_complete_barrier_rq_locked(request_queue_t *, struct request *, int); @@ -675,8 +671,6 @@ extern int blkdev_issue_flush(struct block_device *, sector_t *); #define blkdev_entry_to_request(entry) list_entry((entry), struct request, queuelist) -extern void drive_stat_acct(struct request *, int, int); - static inline int queue_hardsect_size(request_queue_t *q) { int retval = 512; -- cgit v1.2.3 From 3e1d1d28d99dabe63c64f7f40f1ca1d646de1f73 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Fri, 24 Jun 2005 23:13:50 -0700 Subject: [PATCH] Cleanup patch for process freezing 1. Establish a simple API for process freezing defined in linux/include/sched.h: frozen(process) Check for frozen process freezing(process) Check if a process is being frozen freeze(process) Tell a process to freeze (go to refrigerator) thaw_process(process) Restart process frozen_process(process) Process is frozen now 2. Remove all references to PF_FREEZE and PF_FROZEN from all kernel sources except sched.h 3. Fix numerous locations where try_to_freeze is manually done by a driver 4. Remove the argument that is no longer necessary from two function calls. 5. Some whitespace cleanup 6. Clear potential race in refrigerator (provides an open window of PF_FREEZE cleared before setting PF_FROZEN, recalc_sigpending does not check PF_FROZEN). This patch does not address the problem of freeze_processes() violating the rule that a task may only modify its own flags by setting PF_FREEZE. This is not clean in an SMP environment. freeze(process) is therefore not SMP safe! Signed-off-by: Christoph Lameter Signed-off-by: Linus Torvalds --- include/linux/sched.h | 73 +++++++++++++++++++++++++++++++++++++++++---------- 1 file changed, 59 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 2c69682b0444..e7fd09b0557f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1245,33 +1245,78 @@ extern void normalize_rt_tasks(void); #endif -/* try_to_freeze - * - * Checks whether we need to enter the refrigerator - * and returns 1 if we did so. - */ #ifdef CONFIG_PM -extern void refrigerator(unsigned long); +/* + * Check if a process has been frozen + */ +static inline int frozen(struct task_struct *p) +{ + return p->flags & PF_FROZEN; +} + +/* + * Check if there is a request to freeze a process + */ +static inline int freezing(struct task_struct *p) +{ + return p->flags & PF_FREEZE; +} + +/* + * Request that a process be frozen + * FIXME: SMP problem. We may not modify other process' flags! + */ +static inline void freeze(struct task_struct *p) +{ + p->flags |= PF_FREEZE; +} + +/* + * Wake up a frozen process + */ +static inline int thaw_process(struct task_struct *p) +{ + if (frozen(p)) { + p->flags &= ~PF_FROZEN; + wake_up_process(p); + return 1; + } + return 0; +} + +/* + * freezing is complete, mark process as frozen + */ +static inline void frozen_process(struct task_struct *p) +{ + p->flags = (p->flags & ~PF_FREEZE) | PF_FROZEN; +} + +extern void refrigerator(void); extern int freeze_processes(void); extern void thaw_processes(void); -static inline int try_to_freeze(unsigned long refrigerator_flags) +static inline int try_to_freeze(void) { - if (unlikely(current->flags & PF_FREEZE)) { - refrigerator(refrigerator_flags); + if (freezing(current)) { + refrigerator(); return 1; } else return 0; } #else -static inline void refrigerator(unsigned long flag) {} +static inline int frozen(struct task_struct *p) { return 0; } +static inline int freezing(struct task_struct *p) { return 0; } +static inline void freeze(struct task_struct *p) { BUG(); } +static inline int thaw_process(struct task_struct *p) { return 1; } +static inline void frozen_process(struct task_struct *p) { BUG(); } + +static inline void refrigerator(void) {} static inline int freeze_processes(void) { BUG(); return 0; } static inline void thaw_processes(void) {} -static inline int try_to_freeze(unsigned long refrigerator_flags) -{ - return 0; -} +static inline int try_to_freeze(void) { return 0; } + #endif /* CONFIG_PM */ #endif /* __KERNEL__ */ -- cgit v1.2.3