From 8fb402bccf203ecca8f9e0202b8fd3c937dece6f Mon Sep 17 00:00:00 2001 From: Erik Bosman Date: Fri, 11 Apr 2008 18:54:17 +0200 Subject: generic, x86: add prctl commands PR_GET_TSC and PR_SET_TSC This patch adds prctl commands that make it possible to deny the execution of timestamp counters in userspace. If this is not implemented on a specific architecture, prctl will return -EINVAL. ned-off-by: Erik Bosman Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- kernel/sys.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sys.c b/kernel/sys.c index a626116af5db..6a0cc71ee88d 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -67,6 +67,12 @@ #ifndef SET_ENDIAN # define SET_ENDIAN(a,b) (-EINVAL) #endif +#ifndef GET_TSC_CTL +# define GET_TSC_CTL(a) (-EINVAL) +#endif +#ifndef SET_TSC_CTL +# define SET_TSC_CTL(a) (-EINVAL) +#endif /* * this is where the system-wide overflow UID and GID are defined, for @@ -1737,7 +1743,12 @@ asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3, #else return -EINVAL; #endif - + case PR_GET_TSC: + error = GET_TSC_CTL(arg2); + break; + case PR_SET_TSC: + error = SET_TSC_CTL(arg2); + break; default: error = -EINVAL; break; -- cgit v1.2.1 From d8bb6f4c1670c8324e4135c61ef07486f7f17379 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 1 Apr 2008 19:45:18 +0200 Subject: x86: tsc prevent time going backwards We already catch most of the TSC problems by sanity checks, but there is a subtle bug which has been in the code forever. This can cause time jumps in the range of hours. This was reported in: http://lkml.org/lkml/2007/8/23/96 and http://lkml.org/lkml/2008/3/31/23 I was able to reproduce the problem with a gettimeofday loop test on a dual core and a quad core machine which both have sychronized TSCs. The TSCs seems not to be perfectly in sync though, but the kernel is not able to detect the slight delta in the sync check. Still there exists an extremly small window where this delta can be observed with a real big time jump. So far I was only able to reproduce this with the vsyscall gettimeofday implementation, but in theory this might be observable with the syscall based version as well. CPU 0 updates the clock source variables under xtime/vyscall lock and CPU1, where the TSC is slighty behind CPU0, is reading the time right after the seqlock was unlocked. The clocksource reference data was updated with the TSC from CPU0 and the value which is read from TSC on CPU1 is less than the reference data. This results in a huge delta value due to the unsigned subtraction of the TSC value and the reference value. This algorithm can not be changed due to the support of wrapping clock sources like pm timer. The huge delta is converted to nanoseconds and added to xtime, which is then observable by the caller. The next gettimeofday call on CPU1 will show the correct time again as now the TSC has advanced above the reference value. To prevent this TSC specific wreckage we need to compare the TSC value against the reference value and return the latter when it is larger than the actual TSC value. I pondered to mark the TSC unstable when the readout is smaller than the reference value, but this would render an otherwise good and fast clocksource unusable without a real good reason. Signed-off-by: Thomas Gleixner Signed-off-by: Ingo Molnar --- kernel/time/timekeeping.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel') diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index a3fa587c350c..2d6087c7cf98 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -178,6 +178,7 @@ static void change_clocksource(void) if (clock == new) return; + new->cycle_last = 0; now = clocksource_read(new); nsec = __get_nsec_offset(); timespec_add_ns(&xtime, nsec); @@ -295,6 +296,7 @@ static int timekeeping_resume(struct sys_device *dev) timespec_add_ns(&xtime, timekeeping_suspend_nsecs); update_xtime_cache(0); /* re-base the last cycle value */ + clock->cycle_last = 0; clock->cycle_last = clocksource_read(clock); clock->error = 0; timekeeping_suspended = 0; -- cgit v1.2.1 From 61c4628b538608c1a85211ed8438136adfeb9a95 Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Mon, 10 Mar 2008 15:28:04 -0700 Subject: x86, fpu: split FPU state from task struct - v5 Split the FPU save area from the task struct. This allows easy migration of FPU context, and it's generally cleaner. It also allows the following two optimizations: 1) only allocate when the application actually uses FPU, so in the first lazy FPU trap. This could save memory for non-fpu using apps. Next patch does this lazy allocation. 2) allocate the right size for the actual cpu rather than 512 bytes always. Patches enabling xsave/xrstor support (coming shortly) will take advantage of this. Signed-off-by: Suresh Siddha Signed-off-by: Arjan van de Ven Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- kernel/fork.c | 31 +++++++++++++++++++++++++------ 1 file changed, 25 insertions(+), 6 deletions(-) (limited to 'kernel') diff --git a/kernel/fork.c b/kernel/fork.c index 9c042f901570..44a18192c420 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -132,6 +132,10 @@ void __put_task_struct(struct task_struct *tsk) free_task(tsk); } +void __attribute__((weak)) arch_task_cache_init(void) +{ +} + void __init fork_init(unsigned long mempages) { #ifndef __HAVE_ARCH_TASK_STRUCT_ALLOCATOR @@ -144,6 +148,9 @@ void __init fork_init(unsigned long mempages) ARCH_MIN_TASKALIGN, SLAB_PANIC, NULL); #endif + /* do the arch specific task caches init */ + arch_task_cache_init(); + /* * The default maximum number of threads is set to a safe * value: the thread structures can take up at most half @@ -163,6 +170,13 @@ void __init fork_init(unsigned long mempages) init_task.signal->rlim[RLIMIT_NPROC]; } +int __attribute__((weak)) arch_dup_task_struct(struct task_struct *dst, + struct task_struct *src) +{ + *dst = *src; + return 0; +} + static struct task_struct *dup_task_struct(struct task_struct *orig) { struct task_struct *tsk; @@ -181,15 +195,15 @@ static struct task_struct *dup_task_struct(struct task_struct *orig) return NULL; } - *tsk = *orig; + err = arch_dup_task_struct(tsk, orig); + if (err) + goto out; + tsk->stack = ti; err = prop_local_init_single(&tsk->dirties); - if (err) { - free_thread_info(ti); - free_task_struct(tsk); - return NULL; - } + if (err) + goto out; setup_thread_stack(tsk, orig); @@ -205,6 +219,11 @@ static struct task_struct *dup_task_struct(struct task_struct *orig) #endif tsk->splice_pipe = NULL; return tsk; + +out: + free_thread_info(ti); + free_task_struct(tsk); + return NULL; } #ifdef CONFIG_MMU -- cgit v1.2.1 From 2adee9b30d1382fba97825b9c50e4f50a0117c36 Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Wed, 16 Apr 2008 10:25:35 +0200 Subject: x86: fpu xstate split fix Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- kernel/fork.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/fork.c b/kernel/fork.c index 44a18192c420..89fe414645e9 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -132,9 +132,13 @@ void __put_task_struct(struct task_struct *tsk) free_task(tsk); } -void __attribute__((weak)) arch_task_cache_init(void) -{ -} +/* + * macro override instead of weak attribute alias, to workaround + * gcc 4.1.0 and 4.1.1 bugs with weak attribute and empty functions. + */ +#ifndef arch_task_cache_init +#define arch_task_cache_init() +#endif void __init fork_init(unsigned long mempages) { -- cgit v1.2.1