From 88d4f0db7fa8785859c1d637f9aac210932b6216 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 25 Jan 2011 19:40:51 +0100 Subject: perf: Fix alloc_callchain_buffers() Commit 927c7a9e92c4 ("perf: Fix race in callchains") introduced a mismatch in the sizing of struct callchain_cpus_entries. nr_cpu_ids must be used instead of num_possible_cpus(), or we might get out of bound memory accesses on some machines. Signed-off-by: Eric Dumazet Cc: Frederic Weisbecker Cc: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: David Miller Cc: Stephane Eranian CC: stable@kernel.org LKML-Reference: <1295980851.3588.351.camel@edumazet-laptop> Signed-off-by: Ingo Molnar --- kernel/perf_event.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/perf_event.c b/kernel/perf_event.c index 126a302c481c..852ae8c66502 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -1999,8 +1999,7 @@ static int alloc_callchain_buffers(void) * accessed from NMI. Use a temporary manual per cpu allocation * until that gets sorted out. */ - size = sizeof(*entries) + sizeof(struct perf_callchain_entry *) * - num_possible_cpus(); + size = offsetof(struct callchain_cpus_entries, cpu_entries[nr_cpu_ids]); entries = kzalloc(size, GFP_KERNEL); if (!entries) -- cgit v1.2.3 From aa5bd67dcfdf9af34c7fa36ebc87d4e1f7e91873 Mon Sep 17 00:00:00 2001 From: Kacper Kornet Date: Sat, 29 Jan 2011 00:21:04 +0100 Subject: Fix prlimit64 for suid/sgid processes Since check_prlimit_permission always fails in the case of SUID/GUID processes, such processes are not able to read or set their own limits. This commit changes this by assuming that process can always read/change its own limits. Signed-off-by: Kacper Kornet Acked-by: Jiri Slaby Signed-off-by: Linus Torvalds --- kernel/sys.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sys.c b/kernel/sys.c index 31b71a276b40..18da702ec813 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1385,7 +1385,8 @@ static int check_prlimit_permission(struct task_struct *task) const struct cred *cred = current_cred(), *tcred; tcred = __task_cred(task); - if ((cred->uid != tcred->euid || + if (current != task && + (cred->uid != tcred->euid || cred->uid != tcred->suid || cred->uid != tcred->uid || cred->gid != tcred->egid || -- cgit v1.2.3 From 4135038a582c20ffdadfcf6564852e0b72a20968 Mon Sep 17 00:00:00 2001 From: Marcin Slusarz Date: Fri, 28 Jan 2011 11:00:31 -0500 Subject: watchdog: Fix broken nowatchdog logic Passing nowatchdog to kernel disables 2 things: creation of watchdog threads AND initialization of percpu watchdog_hrtimer. As hrtimers are initialized only at boot it's not possible to enable watchdog later - for me all watchdog threads started to eat 100% of CPU time, but they could just crash. Additionally, even if these threads would start properly, watchdog_disable_all_cpus was guarded by no_watchdog check, so you couldn't disable watchdog. To fix this, remove no_watchdog variable and use already existing watchdog_enabled variable. Signed-off-by: Marcin Slusarz [ removed another no_watchdog instance ] Signed-off-by: Don Zickus Cc: Stephane Eranian Cc: Peter Zijlstra Cc: Frederic Weisbecker Cc: LKML-Reference: <1296230433-6261-1-git-send-email-dzickus@redhat.com> Signed-off-by: Ingo Molnar --- kernel/watchdog.c | 20 ++++++-------------- 1 file changed, 6 insertions(+), 14 deletions(-) (limited to 'kernel') diff --git a/kernel/watchdog.c b/kernel/watchdog.c index d7ebdf4cea98..d9961ea1c3f4 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -27,7 +27,7 @@ #include #include -int watchdog_enabled; +int watchdog_enabled = 1; int __read_mostly softlockup_thresh = 60; static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts); @@ -43,9 +43,6 @@ static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved); static DEFINE_PER_CPU(struct perf_event *, watchdog_ev); #endif -static int no_watchdog; - - /* boot commands */ /* * Should we panic when a soft-lockup or hard-lockup occurs: @@ -58,7 +55,7 @@ static int __init hardlockup_panic_setup(char *str) if (!strncmp(str, "panic", 5)) hardlockup_panic = 1; else if (!strncmp(str, "0", 1)) - no_watchdog = 1; + watchdog_enabled = 0; return 1; } __setup("nmi_watchdog=", hardlockup_panic_setup); @@ -77,7 +74,7 @@ __setup("softlockup_panic=", softlockup_panic_setup); static int __init nowatchdog_setup(char *str) { - no_watchdog = 1; + watchdog_enabled = 0; return 1; } __setup("nowatchdog", nowatchdog_setup); @@ -85,7 +82,7 @@ __setup("nowatchdog", nowatchdog_setup); /* deprecated */ static int __init nosoftlockup_setup(char *str) { - no_watchdog = 1; + watchdog_enabled = 0; return 1; } __setup("nosoftlockup", nosoftlockup_setup); @@ -476,9 +473,6 @@ static void watchdog_disable_all_cpus(void) { int cpu; - if (no_watchdog) - return; - for_each_online_cpu(cpu) watchdog_disable(cpu); @@ -530,7 +524,8 @@ cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) break; case CPU_ONLINE: case CPU_ONLINE_FROZEN: - err = watchdog_enable(hotcpu); + if (watchdog_enabled) + err = watchdog_enable(hotcpu); break; #ifdef CONFIG_HOTPLUG_CPU case CPU_UP_CANCELED: @@ -555,9 +550,6 @@ void __init lockup_detector_init(void) void *cpu = (void *)(long)smp_processor_id(); int err; - if (no_watchdog) - return; - err = cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu); WARN_ON(notifier_to_errno(err)); -- cgit v1.2.3 From 397357666de6b5b6adb5fa99f9758ec8cf30ac34 Mon Sep 17 00:00:00 2001 From: Marcin Slusarz Date: Fri, 28 Jan 2011 11:00:32 -0500 Subject: watchdog: Fix sysctl consistency If it was not possible to enable watchdog for any cpu, switch watchdog_enabled back to 0, because it's visible via kernel.watchdog sysctl. Signed-off-by: Marcin Slusarz Signed-off-by: Don Zickus Cc: Peter Zijlstra Cc: Frederic Weisbecker Cc: LKML-Reference: <1296230433-6261-2-git-send-email-dzickus@redhat.com> Signed-off-by: Ingo Molnar --- kernel/watchdog.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) (limited to 'kernel') diff --git a/kernel/watchdog.c b/kernel/watchdog.c index d9961ea1c3f4..c7e0049344bd 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -429,9 +429,6 @@ static int watchdog_enable(int cpu) wake_up_process(p); } - /* if any cpu succeeds, watchdog is considered enabled for the system */ - watchdog_enabled = 1; - return 0; } @@ -459,12 +456,16 @@ static void watchdog_disable(int cpu) static void watchdog_enable_all_cpus(void) { int cpu; - int result = 0; + + watchdog_enabled = 0; for_each_online_cpu(cpu) - result += watchdog_enable(cpu); + if (!watchdog_enable(cpu)) + /* if any cpu succeeds, watchdog is considered + enabled for the system */ + watchdog_enabled = 1; - if (result) + if (!watchdog_enabled) printk(KERN_ERR "watchdog: failed to be enabled on some cpus\n"); } -- cgit v1.2.3 From 9ffdc6c37df131f89d52001e0ef03091b158826f Mon Sep 17 00:00:00 2001 From: Marcin Slusarz Date: Fri, 28 Jan 2011 11:00:33 -0500 Subject: watchdog: Don't change watchdog state on read of sysctl Signed-off-by: Marcin Slusarz [ add {}'s to fix a warning ] Signed-off-by: Don Zickus Cc: Peter Zijlstra Cc: Frederic Weisbecker Cc: LKML-Reference: <1296230433-6261-3-git-send-email-dzickus@redhat.com> Signed-off-by: Ingo Molnar --- kernel/watchdog.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/watchdog.c b/kernel/watchdog.c index c7e0049344bd..f37f974aa81b 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -493,10 +493,12 @@ int proc_dowatchdog_enabled(struct ctl_table *table, int write, { proc_dointvec(table, write, buffer, length, ppos); - if (watchdog_enabled) - watchdog_enable_all_cpus(); - else - watchdog_disable_all_cpus(); + if (write) { + if (watchdog_enabled) + watchdog_enable_all_cpus(); + else + watchdog_disable_all_cpus(); + } return 0; } -- cgit v1.2.3 From f1a06390d013244e721372b3f9b66e39b6429c71 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 28 Jan 2011 08:47:15 +0100 Subject: genirq: Prevent irq storm on migration move_native_irq() masks and unmasks the interrupt line unconditionally, but the interrupt line might be masked due to a threaded oneshot handler in progress. Unmasking the line in that case can lead to interrupt storms. Observed on PREEMPT_RT. Originally-from: Ingo Molnar Signed-off-by: Thomas Gleixner Cc: stable@kernel.org --- kernel/irq/migration.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c index 1d2541940480..441fd629ff04 100644 --- a/kernel/irq/migration.c +++ b/kernel/irq/migration.c @@ -56,6 +56,7 @@ void move_masked_irq(int irq) void move_native_irq(int irq) { struct irq_desc *desc = irq_to_desc(irq); + bool masked; if (likely(!(desc->status & IRQ_MOVE_PENDING))) return; @@ -63,8 +64,15 @@ void move_native_irq(int irq) if (unlikely(desc->status & IRQ_DISABLED)) return; - desc->irq_data.chip->irq_mask(&desc->irq_data); + /* + * Be careful vs. already masked interrupts. If this is a + * threaded interrupt with ONESHOT set, we can end up with an + * interrupt storm. + */ + masked = desc->status & IRQ_MASKED; + if (!masked) + desc->irq_data.chip->irq_mask(&desc->irq_data); move_masked_irq(irq); - desc->irq_data.chip->irq_unmask(&desc->irq_data); + if (!masked) + desc->irq_data.chip->irq_unmask(&desc->irq_data); } - -- cgit v1.2.3 From e4a9ea5ee7c8812a7bf0c3fb725ceeaa3d4c2fcc Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 27 Jan 2011 09:15:30 -0500 Subject: tracing: Replace trace_event struct array with pointer array Currently the trace_event structures are placed in the _ftrace_events section, and at link time, the linker makes one large array of all the trace_event structures. On boot up, this array is read (much like the initcall sections) and the events are processed. The problem is that there is no guarantee that gcc will place complex structures nicely together in an array format. Two structures in the same file may be placed awkwardly, because gcc has no clue that they are suppose to be in an array. A hack was used previous to force the alignment to 4, to pack the structures together. But this caused alignment issues with other architectures (sparc). Instead of packing the structures into an array, the structures' addresses are now put into the _ftrace_event section. As pointers are always the natural alignment, gcc should always pack them tightly together (otherwise initcall, extable, etc would also fail). By having the pointers to the structures in the section, we can still iterate the trace_events without causing unnecessary alignment problems with other architectures, or depending on the current behaviour of gcc that will likely change in the future just to tick us kernel developers off a little more. The _ftrace_event section is also moved into the .init.data section as it is now only needed at boot up. Suggested-by: David Miller Cc: Mathieu Desnoyers Acked-by: David S. Miller Signed-off-by: Steven Rostedt --- include/asm-generic/vmlinux.lds.h | 7 +++---- include/linux/module.h | 2 +- include/linux/syscalls.h | 10 ++++++---- include/trace/ftrace.h | 24 +++++++++++++----------- kernel/trace/trace_events.c | 12 ++++++------ kernel/trace/trace_export.c | 6 +++--- 6 files changed, 32 insertions(+), 29 deletions(-) (limited to 'kernel') diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 6ebb81030d2d..f53708be95eb 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -124,7 +124,8 @@ #endif #ifdef CONFIG_EVENT_TRACING -#define FTRACE_EVENTS() VMLINUX_SYMBOL(__start_ftrace_events) = .; \ +#define FTRACE_EVENTS() . = ALIGN(8); \ + VMLINUX_SYMBOL(__start_ftrace_events) = .; \ *(_ftrace_events) \ VMLINUX_SYMBOL(__stop_ftrace_events) = .; #else @@ -179,9 +180,6 @@ TRACE_PRINTKS() \ \ STRUCT_ALIGN(); \ - FTRACE_EVENTS() \ - \ - STRUCT_ALIGN(); \ TRACE_SYSCALLS() /* @@ -482,6 +480,7 @@ KERNEL_CTORS() \ *(.init.rodata) \ MCOUNT_REC() \ + FTRACE_EVENTS() \ DEV_DISCARD(init.rodata) \ CPU_DISCARD(init.rodata) \ MEM_DISCARD(init.rodata) \ diff --git a/include/linux/module.h b/include/linux/module.h index e7c6385c6683..7695a303bb55 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -389,7 +389,7 @@ struct module unsigned int num_trace_bprintk_fmt; #endif #ifdef CONFIG_EVENT_TRACING - struct ftrace_event_call *trace_events; + struct ftrace_event_call **trace_events; unsigned int num_trace_events; #endif #ifdef CONFIG_FTRACE_MCOUNT_RECORD diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 18cd0684fc4e..45508fec366d 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -128,28 +128,30 @@ extern struct trace_event_functions exit_syscall_print_funcs; static struct syscall_metadata \ __attribute__((__aligned__(4))) __syscall_meta_##sname; \ static struct ftrace_event_call __used \ - __attribute__((__aligned__(4))) \ - __attribute__((section("_ftrace_events"))) \ event_enter_##sname = { \ .name = "sys_enter"#sname, \ .class = &event_class_syscall_enter, \ .event.funcs = &enter_syscall_print_funcs, \ .data = (void *)&__syscall_meta_##sname,\ }; \ + static struct ftrace_event_call __used \ + __attribute__((section("_ftrace_events"))) \ + *__event_enter_##sname = &event_enter_##sname; \ __TRACE_EVENT_FLAGS(enter_##sname, TRACE_EVENT_FL_CAP_ANY) #define SYSCALL_TRACE_EXIT_EVENT(sname) \ static struct syscall_metadata \ __attribute__((__aligned__(4))) __syscall_meta_##sname; \ static struct ftrace_event_call __used \ - __attribute__((__aligned__(4))) \ - __attribute__((section("_ftrace_events"))) \ event_exit_##sname = { \ .name = "sys_exit"#sname, \ .class = &event_class_syscall_exit, \ .event.funcs = &exit_syscall_print_funcs, \ .data = (void *)&__syscall_meta_##sname,\ }; \ + static struct ftrace_event_call __used \ + __attribute__((section("_ftrace_events"))) \ + *__event_exit_##sname = &event_exit_##sname; \ __TRACE_EVENT_FLAGS(exit_##sname, TRACE_EVENT_FL_CAP_ANY) #define SYSCALL_METADATA(sname, nb) \ diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h index e16610c208c9..3e68366d485a 100644 --- a/include/trace/ftrace.h +++ b/include/trace/ftrace.h @@ -446,14 +446,16 @@ static inline notrace int ftrace_get_offsets_##call( \ * .reg = ftrace_event_reg, * }; * - * static struct ftrace_event_call __used - * __attribute__((__aligned__(4))) - * __attribute__((section("_ftrace_events"))) event_ = { + * static struct ftrace_event_call event_ = { * .name = "", * .class = event_class_