From 0b6e4d56bf71866a2b58daa8323cf747988ce7e4 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Tue, 28 Oct 2008 20:17:38 +0100 Subject: ftrace: perform an initialization for ftrace to enable it Impact: corrects a bug which made the non-dyn function tracer not functional With latest git, the non-dynamic function tracer didn't get any trace. The problem was the fact that ftrace_enabled wasn't initialized to 1 because ftrace hasn't any init function when DYNAMIC_FTRACE is disabled. So when a tracer tries to register an ftrace_ops struct, __register_ftrace_function failed to set the hook. This patch corrects it by setting an init function to initialize ftrace during the boot. Signed-off-by: Frederic Weisbecker Signed-off-by: Ingo Molnar --- kernel/trace/ftrace.c | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'kernel') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 7618c528756b..4a39d24568c8 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1339,6 +1339,14 @@ void __init ftrace_init(void) } #else + +static int __init ftrace_nodyn_init(void) +{ + ftrace_enabled = 1; + return 0; +} +device_initcall(ftrace_nodyn_init); + # define ftrace_startup() do { } while (0) # define ftrace_shutdown() do { } while (0) # define ftrace_startup_sysctl() do { } while (0) -- cgit v1.2.2 From d68612b257b5f4ea2e6535859c5a26b10011a9df Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Tue, 28 Oct 2008 11:45:42 -0700 Subject: resources: fix x86info results ioremap.c:226 __ioremap_caller+0xf2/0x2d6() WARNINGs Impact: avoid false-positive WARN_ON() Andi Kleen reported: > When running x86info on a 2.6.27-git8 system I get > > resource map sanity check conflict: 0x9e000 0x9efff 0x10000 0x9e7ff System RAM > ------------[ cut here ]------------ > WARNING: at /home/lsrc/linux/arch/x86/mm/ioremap.c:226 __ioremap_caller+0xf2/0x2d6() > ... Some of the pages below the 1MB ISA addresses will be shared typically by both BIOS and system usable RAM. For example: BIOS-e820: 0000000000000000 - 000000000009f800 (usable) BIOS-e820: 000000000009f800 - 00000000000a0000 (reserved) x86info reads the low physical address using /dev/mem, which internally uses ioremap() for accessing non RAM pages. ioremap() of such low pages conflicts with multiple resource entities leading to the above warning. Change the iomem_map_sanity_check() to allow mapping a page spanning multiple resource entities (minimum granularity that one can map is a page anyhow). Signed-off-by: Suresh Siddha Signed-off-by: Ingo Molnar --- kernel/resource.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/resource.c b/kernel/resource.c index 7fec0e427234..6aac5c60b25d 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -17,6 +17,7 @@ #include #include #include +#include #include @@ -849,7 +850,8 @@ int iomem_map_sanity_check(resource_size_t addr, unsigned long size) continue; if (p->end < addr) continue; - if (p->start <= addr && (p->end >= addr + size - 1)) + if (PFN_DOWN(p->start) <= PFN_DOWN(addr) && + PFN_DOWN(p->end) >= PFN_DOWN(addr + size - 1)) continue; printk(KERN_WARNING "resource map sanity check conflict: " "0x%llx 0x%llx 0x%llx 0x%llx %s\n", -- cgit v1.2.2 From f3384b28a05624783b53836ccfed95ecde66a7ad Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Wed, 29 Oct 2008 11:15:57 -0400 Subject: ftrace: fix trace_nop config select Impact: build fix on non-function-tracing architectures The trace_nop is the tracer that is defined when no tracer is set in the ftrace infrastructure. The trace_nop was mistakenly selected by HAVE_FTRACE due to the confusion between ftrace infrastructure and the ftrace function tracer (which has been solved by renaming the function tracer). This patch changes the select to the approriate TRACING. This patch should fix compile errors on architectures that do not define the FUNCTION_TRACER. Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar --- kernel/trace/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index e0cea282e0c5..b58f43bec363 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -8,7 +8,6 @@ config NOP_TRACER config HAVE_FUNCTION_TRACER bool - select NOP_TRACER config HAVE_DYNAMIC_FTRACE bool @@ -28,6 +27,7 @@ config TRACING select RING_BUFFER select STACKTRACE select TRACEPOINTS + select NOP_TRACER menu "Tracers" -- cgit v1.2.2 From a9cf4ddb3b2ce03c3027929b22a920aeff933009 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Thu, 30 Oct 2008 15:23:34 +0800 Subject: sched: change sched_debug's mode to 0444 Impact: change /proc/sched/debug from rw-r--r-- to r--r--r-- /proc/sched_debug is read-only. Signed-off-by: Li Zefan Acked-by: Peter Zijlstra Signed-off-by: Ingo Molnar --- kernel/sched_debug.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c index ad958c1ec708..5ae17762ec32 100644 --- a/kernel/sched_debug.c +++ b/kernel/sched_debug.c @@ -319,7 +319,7 @@ static int __init init_sched_debug_procfs(void) { struct proc_dir_entry *pe; - pe = proc_create("sched_debug", 0644, NULL, &sched_debug_fops); + pe = proc_create("sched_debug", 0444, NULL, &sched_debug_fops); if (!pe) return -ENOMEM; return 0; -- cgit v1.2.2 From 7ccb97437bcc818d0ba6067513475f6ee8177a15 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Wed, 29 Oct 2008 14:00:51 -0700 Subject: freezer_cg: fix improper BUG_ON() causing oops The BUG_ON() should be protected by freezer->lock, otherwise it can be triggered easily when a task has been unfreezed but the corresponding cgroup hasn't been changed to FROZEN state. Signed-off-by: Li Zefan Acked-by: Cedric Le Goater Acked-by: Matt Helsley Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cgroup_freezer.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c index e95056954498..7f54d1c42953 100644 --- a/kernel/cgroup_freezer.c +++ b/kernel/cgroup_freezer.c @@ -190,8 +190,9 @@ static void freezer_fork(struct cgroup_subsys *ss, struct task_struct *task) freezer = task_freezer(task); task_unlock(task); - BUG_ON(freezer->state == CGROUP_FROZEN); spin_lock_irq(&freezer->lock); + BUG_ON(freezer->state == CGROUP_FROZEN); + /* Locking avoids race with FREEZING -> THAWED transitions. */ if (freezer->state == CGROUP_FREEZING) freeze_task(task, true); -- cgit v1.2.2 From 80a6a2cf3bebcf20285cf05373b9c5ec96816577 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Wed, 29 Oct 2008 14:00:52 -0700 Subject: freezer_cg: remove redundant check in freezer_can_attach() It is sufficient to check if @task is frozen, and no need to check if the original freezer is frozen. Signed-off-by: Li Zefan Acked-by: Cedric Le Goater Acked-by: Matt Helsley Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cgroup_freezer.c | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c index 7f54d1c42953..e9c856a265c9 100644 --- a/kernel/cgroup_freezer.c +++ b/kernel/cgroup_freezer.c @@ -162,9 +162,13 @@ static int freezer_can_attach(struct cgroup_subsys *ss, struct task_struct *task) { struct freezer *freezer; - int retval; - /* Anything frozen can't move or be moved to/from */ + /* + * Anything frozen can't move or be moved to/from. + * + * Since orig_freezer->state == FROZEN means that @task has been + * frozen, so it's sufficient to check the latter condition. + */ if (is_task_frozen_enough(task)) return -EBUSY; @@ -173,13 +177,7 @@ static int freezer_can_attach(struct cgroup_subsys *ss, if (freezer->state == CGROUP_FROZEN) return -EBUSY; - retval = 0; - task_lock(task); - freezer = task_freezer(task); - if (freezer->state == CGROUP_FROZEN) - retval = -EBUSY; - task_unlock(task); - return retval; + return 0; } static void freezer_fork(struct cgroup_subsys *ss, struct task_struct *task) -- cgit v1.2.2 From 00c2e63c31d0f431952ff2a671c5c6997dd4f8b2 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Wed, 29 Oct 2008 14:00:53 -0700 Subject: freezer_cg: use thaw_process() in unfreeze_cgroup() Don't duplicate the implementation of thaw_process(). [akpm@linux-foundation.org: make __thaw_process() static] Signed-off-by: Li Zefan Cc: Cedric Le Goater Acked-by: Matt Helsley Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cgroup_freezer.c | 15 ++++----------- kernel/freezer.c | 20 ++++++++++---------- 2 files changed, 14 insertions(+), 21 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c index e9c856a265c9..5e6d26b66e88 100644 --- a/kernel/cgroup_freezer.c +++ b/kernel/cgroup_freezer.c @@ -275,25 +275,18 @@ static int try_to_freeze_cgroup(struct cgroup *cgroup, struct freezer *freezer) return num_cant_freeze_now ? -EBUSY : 0; } -static int unfreeze_cgroup(struct cgroup *cgroup, struct freezer *freezer) +static void unfreeze_cgroup(struct cgroup *cgroup, struct freezer *freezer) { struct cgroup_iter it; struct task_struct *task; cgroup_iter_start(cgroup, &it); while ((task = cgroup_iter_next(cgroup, &it))) { - int do_wake; - - task_lock(task); - do_wake = __thaw_process(task); - task_unlock(task); - if (do_wake) - wake_up_process(task); + thaw_process(task); } cgroup_iter_end(cgroup, &it); - freezer->state = CGROUP_THAWED; - return 0; + freezer->state = CGROUP_THAWED; } static int freezer_change_state(struct cgroup *cgroup, @@ -320,7 +313,7 @@ static int freezer_change_state(struct cgroup *cgroup, } /* state == FREEZING and goal_state == THAWED, so unfreeze */ case CGROUP_FROZEN: - retval = unfreeze_cgroup(cgroup, freezer); + unfreeze_cgroup(cgroup, freezer); break; default: break; diff --git a/kernel/freezer.c b/kernel/freezer.c index ba6248b323ef..2f4936cf7083 100644 --- a/kernel/freezer.c +++ b/kernel/freezer.c @@ -121,16 +121,7 @@ void cancel_freezing(struct task_struct *p) } } -/* - * Wake up a frozen process - * - * task_lock() is needed to prevent the race with refrigerator() which may - * occur if the freezing of tasks fails. Namely, without the lock, if the - * freezing of tasks failed, thaw_tasks() might have run before a task in - * refrigerator() could call frozen_process(), in which case the task would be - * frozen and no one would thaw it. - */ -int __thaw_process(struct task_struct *p) +static int __thaw_process(struct task_struct *p) { if (frozen(p)) { p->flags &= ~PF_FROZEN; @@ -140,6 +131,15 @@ int __thaw_process(struct task_struct *p) return 0; } +/* + * Wake up a frozen process + * + * task_lock() is needed to prevent the race with refrigerator() which may + * occur if the freezing of tasks fails. Namely, without the lock, if the + * freezing of tasks failed, thaw_tasks() might have run before a task in + * refrigerator() could call frozen_process(), in which case the task would be + * frozen and no one would thaw it. + */ int thaw_process(struct task_struct *p) { task_lock(p); -- cgit v1.2.2 From 51308ee59dee1136ed599d875ea8968d7be55c91 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Wed, 29 Oct 2008 14:00:54 -0700 Subject: freezer_cg: simplify freezer_change_state() Just call unfreeze_cgroup() if goal_state == THAWED, and call try_to_freeze_cgroup() if goal_state == FROZEN. No behavior has been changed. Signed-off-by: Li Zefan Acked-by: Cedric Le Goater Acked-by: Matt Helsley Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cgroup_freezer.c | 19 +++++++------------ 1 file changed, 7 insertions(+), 12 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c index 5e6d26b66e88..7fa476f01d05 100644 --- a/kernel/cgroup_freezer.c +++ b/kernel/cgroup_freezer.c @@ -296,27 +296,22 @@ static int freezer_change_state(struct cgroup *cgroup, int retval = 0; freezer = cgroup_freezer(cgroup); + spin_lock_irq(&freezer->lock); + update_freezer_state(cgroup, freezer); if (goal_state == freezer->state) goto out; - switch (freezer->state) { + + switch (goal_state) { case CGROUP_THAWED: - retval = try_to_freeze_cgroup(cgroup, freezer); + unfreeze_cgroup(cgroup, freezer); break; - case CGROUP_FREEZING: - if (goal_state == CGROUP_FROZEN) { - /* Userspace is retrying after - * "/bin/echo FROZEN > freezer.state" returned -EBUSY */ - retval = try_to_freeze_cgroup(cgroup, freezer); - break; - } - /* state == FREEZING and goal_state == THAWED, so unfreeze */ case CGROUP_FROZEN: - unfreeze_cgroup(cgroup, freezer); + retval = try_to_freeze_cgroup(cgroup, freezer); break; default: - break; + BUG(); } out: spin_unlock_irq(&freezer->lock); -- cgit v1.2.2 From ce05fcc30ea41c85f9d50bee1ce289f7cb7fb223 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Wed, 29 Oct 2008 14:01:07 -0700 Subject: kernel/profile: fix profile_init() section mismatch profile_init() calls in to alloc_bootmem() on early initialization. While alloc_bootmem() is __init, the reference itself is safe in that it is tucked below a !slab_is_available() check. So, flag profile_init() as __ref. Signed-off-by: Paul Mundt Cc: Dave Hansen Cc: Sam Ravnborg Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/profile.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/profile.c b/kernel/profile.c index a9e422df6bf6..9830a037d8db 100644 --- a/kernel/profile.c +++ b/kernel/profile.c @@ -102,7 +102,7 @@ int profile_setup(char *str) __setup("profile=", profile_setup); -int profile_init(void) +int __ref profile_init(void) { int buffer_bytes; if (!prof_on) -- cgit v1.2.2 From d25141a818383b3c3b09f065698c544a7a0ec6e7 Mon Sep 17 00:00:00 2001 From: Sukadev Bhattiprolu Date: Wed, 29 Oct 2008 14:01:11 -0700 Subject: 'kill sig -1' must only apply to caller's namespace Currently "kill -1" kills processes in all namespaces and breaks the isolation of namespaces. Earlier attempt to fix this was discussed at: http://lkml.org/lkml/2008/7/23/148 As suggested by Oleg Nesterov in that thread, use "task_pid_vnr() > 1" check since task_pid_vnr() returns 0 if process is outside the caller's namespace. Signed-off-by: Sukadev Bhattiprolu Acked-by: Eric W. Biederman Tested-by: Daniel Hokka Zakrisson Signed-off-by: Oleg Nesterov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/signal.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/signal.c b/kernel/signal.c index 105217da5c82..4530fc654455 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1144,7 +1144,8 @@ static int kill_something_info(int sig, struct siginfo *info, pid_t pid) struct task_struct * p; for_each_process(p) { - if (p->pid > 1 && !same_thread_group(p, current)) { + if (task_pid_vnr(p) > 1 && + !same_thread_group(p, current)) { int err = group_send_sig_info(sig, info, p); ++count; if (err != -EPERM) -- cgit v1.2.2 From 9244489a7b69fe0746dc7cb3957f02e05bd1ceb0 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 24 Oct 2008 09:42:59 -0400 Subject: ftrace: handle archs that do not support irqs_disabled_flags Impact: build fix on non-lockdep architectures Some architectures do not support a way to read the irq flags that is set from "local_irq_save(flags)" to determine if interrupts were disabled or enabled. Ftrace uses this information to display to the user if the trace occurred with interrupts enabled or disabled. Besides the fact that those archs that do not support this will fail to compile, unless they fix it, we do not want to have the trace simply say interrupts were not disabled or they were enabled, without knowing the real answer. This patch adds a 'X' in the output to let the user know that the architecture they are running on does not support a way for the tracer to determine if interrupts were enabled or disabled. It also lets those same archs compile with tracing enabled. Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar --- kernel/trace/trace.c | 7 ++++++- kernel/trace/trace.h | 20 +++++++++++--------- 2 files changed, 17 insertions(+), 10 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index a610ca771558..8a499e2adaec 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -656,7 +656,11 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags, entry->preempt_count = pc & 0xff; entry->pid = (tsk) ? tsk->pid : 0; entry->flags = +#ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT (irqs_disabled_flags(flags) ? TRACE_FLAG_IRQS_OFF : 0) | +#else + TRACE_FLAG_IRQS_NOSUPPORT | +#endif ((pc & HARDIRQ_MASK) ? TRACE_FLAG_HARDIRQ : 0) | ((pc & SOFTIRQ_MASK) ? TRACE_FLAG_SOFTIRQ : 0) | (need_resched() ? TRACE_FLAG_NEED_RESCHED : 0); @@ -1244,7 +1248,8 @@ lat_print_generic(struct trace_seq *s, struct trace_entry *entry, int cpu) trace_seq_printf(s, "%8.8s-%-5d ", comm, entry->pid); trace_seq_printf(s, "%3d", cpu); trace_seq_printf(s, "%c%c", - (entry->flags & TRACE_FLAG_IRQS_OFF) ? 'd' : '.', + (entry->flags & TRACE_FLAG_IRQS_OFF) ? 'd' : + (entry->flags & TRACE_FLAG_IRQS_NOSUPPORT) ? 'X' : '.', ((entry->flags & TRACE_FLAG_NEED_RESCHED) ? 'N' : '.')); hardirq = entry->flags & TRACE_FLAG_HARDIRQ; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 6889ca48f1f1..8465ad052707 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -120,18 +120,20 @@ struct trace_boot { /* * trace_flag_type is an enumeration that holds different * states when a trace occurs. These are: - * IRQS_OFF - interrupts were disabled - * NEED_RESCED - reschedule is requested - * HARDIRQ - inside an interrupt handler - * SOFTIRQ - inside a softirq handler - * CONT - multiple entries hold the trace item + * IRQS_OFF - interrupts were disabled + * IRQS_NOSUPPORT - arch does not support irqs_disabled_flags + * NEED_RESCED - reschedule is requested + * HARDIRQ - inside an interrupt handler + * SOFTIRQ - inside a softirq handler + * CONT - multiple entries hold the trace item */ enum trace_flag_type { TRACE_FLAG_IRQS_OFF = 0x01, - TRACE_FLAG_NEED_RESCHED = 0x02, - TRACE_FLAG_HARDIRQ = 0x04, - TRACE_FLAG_SOFTIRQ = 0x08, - TRACE_FLAG_CONT = 0x10, + TRACE_FLAG_IRQS_NOSUPPORT = 0x02, + TRACE_FLAG_NEED_RESCHED = 0x04, + TRACE_FLAG_HARDIRQ = 0x08, + TRACE_FLAG_SOFTIRQ = 0x10, + TRACE_FLAG_CONT = 0x20, }; #define TRACE_BUF_SIZE 1024 -- cgit v1.2.2 From 42c0202363194007a1ac377d047a95aa39246eb0 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 1 Nov 2008 09:53:58 -0700 Subject: reserve_region_with_split: Fix GFP_KERNEL usage under spinlock This one apparently doesn't generate any warnings, because the function is only used during system bootup, when the warnings are disabled. But it's still very wrong. The __reserve_region_with_split() function is called with the resource_lock held for writing, so it must only ever do GFP_ATOMIC allocations. Signed-off-by: Linus Torvalds --- kernel/resource.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/resource.c b/kernel/resource.c index 6aac5c60b25d..4337063663ef 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -523,7 +523,7 @@ static void __init __reserve_region_with_split(struct resource *root, { struct resource *parent = root; struct resource *conflict; - struct resource *res = kzalloc(sizeof(*res), GFP_KERNEL); + struct resource *res = kzalloc(sizeof(*res), GFP_ATOMIC); if (!res) return; -- cgit v1.2.2 From 28959742c14918f153c1de641bb12b4ea44315a1 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 1 Nov 2008 18:20:09 +0000 Subject: PM_TEST_SUSPEND should depend on RTC_CLASS, not RTC_LIB Insufficient dependency - we really want CONFIG_RTC_CLASS=y there. That will give us CONFIG_RTC_LIB=y, so the old dependency can be simply replaced. Signed-off-by: Al Viro Signed-off-by: Linus Torvalds --- kernel/power/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig index dcd165f92a88..23bd4daeb96b 100644 --- a/kernel/power/Kconfig +++ b/kernel/power/Kconfig @@ -96,7 +96,7 @@ config SUSPEND config PM_TEST_SUSPEND bool "Test suspend/resume and wakealarm during bootup" - depends on SUSPEND && PM_DEBUG && RTC_LIB=y + depends on SUSPEND && PM_DEBUG && RTC_CLASS=y ---help--- This option will let you suspend your machine during bootup, and make it wake up a few seconds later using an RTC wakeup alarm. -- cgit v1.2.2