From f06febc96ba8e0af80bcc3eaec0a109e88275fac Mon Sep 17 00:00:00 2001 From: Frank Mayhar Date: Fri, 12 Sep 2008 09:54:39 -0700 Subject: timers: fix itimer/many thread hang Overview This patch reworks the handling of POSIX CPU timers, including the ITIMER_PROF, ITIMER_VIRT timers and rlimit handling. It was put together with the help of Roland McGrath, the owner and original writer of this code. The problem we ran into, and the reason for this rework, has to do with using a profiling timer in a process with a large number of threads. It appears that the performance of the old implementation of run_posix_cpu_timers() was at least O(n*3) (where "n" is the number of threads in a process) or worse. Everything is fine with an increasing number of threads until the time taken for that routine to run becomes the same as or greater than the tick time, at which point things degrade rather quickly. This patch fixes bug 9906, "Weird hang with NPTL and SIGPROF." Code Changes This rework corrects the implementation of run_posix_cpu_timers() to make it run in constant time for a particular machine. (Performance may vary between one machine and another depending upon whether the kernel is built as single- or multiprocessor and, in the latter case, depending upon the number of running processors.) To do this, at each tick we now update fields in signal_struct as well as task_struct. The run_posix_cpu_timers() function uses those fields to make its decisions. We define a new structure, "task_cputime," to contain user, system and scheduler times and use these in appropriate places: struct task_cputime { cputime_t utime; cputime_t stime; unsigned long long sum_exec_runtime; }; This is included in the structure "thread_group_cputime," which is a new substructure of signal_struct and which varies for uniprocessor versus multiprocessor kernels. For uniprocessor kernels, it uses "task_cputime" as a simple substructure, while for multiprocessor kernels it is a pointer: struct thread_group_cputime { struct task_cputime totals; }; struct thread_group_cputime { struct task_cputime *totals; }; We also add a new task_cputime substructure directly to signal_struct, to cache the earliest expiration of process-wide timers, and task_cputime also replaces the it_*_expires fields of task_struct (used for earliest expiration of thread timers). The "thread_group_cputime" structure contains process-wide timers that are updated via account_user_time() and friends. In the non-SMP case the structure is a simple aggregator; unfortunately in the SMP case that simplicity was not achievable due to cache-line contention between CPUs (in one measured case performance was actually _worse_ on a 16-cpu system than the same test on a 4-cpu system, due to this contention). For SMP, the thread_group_cputime counters are maintained as a per-cpu structure allocated using alloc_percpu(). The timer functions update only the timer field in the structure corresponding to the running CPU, obtained using per_cpu_ptr(). We define a set of inline functions in sched.h that we use to maintain the thread_group_cputime structure and hide the differences between UP and SMP implementations from the rest of the kernel. The thread_group_cputime_init() function initializes the thread_group_cputime structure for the given task. The thread_group_cputime_alloc() is a no-op for UP; for SMP it calls the out-of-line function thread_group_cputime_alloc_smp() to allocate and fill in the per-cpu structures and fields. The thread_group_cputime_free() function, also a no-op for UP, in SMP frees the per-cpu structures. The thread_group_cputime_clone_thread() function (also a UP no-op) for SMP calls thread_group_cputime_alloc() if the per-cpu structures haven't yet been allocated. The thread_group_cputime() function fills the task_cputime structure it is passed with the contents of the thread_group_cputime fields; in UP it's that simple but in SMP it must also safely check that tsk->signal is non-NULL (if it is it just uses the appropriate fields of task_struct) and, if so, sums the per-cpu values for each online CPU. Finally, the three functions account_group_user_time(), account_group_system_time() and account_group_exec_runtime() are used by timer functions to update the respective fields of the thread_group_cputime structure. Non-SMP operation is trivial and will not be mentioned further. The per-cpu structure is always allocated when a task creates its first new thread, via a call to thread_group_cputime_clone_thread() from copy_signal(). It is freed at process exit via a call to thread_group_cputime_free() from cleanup_signal(). All functions that formerly summed utime/stime/sum_sched_runtime values from from all threads in the thread group now use thread_group_cputime() to snapshot the values in the thread_group_cputime structure or the values in the task structure itself if the per-cpu structure hasn't been allocated. Finally, the code in kernel/posix-cpu-timers.c has changed quite a bit. The run_posix_cpu_timers() function has been split into a fast path and a slow path; the former safely checks whether there are any expired thread timers and, if not, just returns, while the slow path does the heavy lifting. With the dedicated thread group fields, timers are no longer "rebalanced" and the process_timer_rebalance() function and related code has gone away. All summing loops are gone and all code that used them now uses the thread_group_cputime() inline. When process-wide timers are set, the new task_cputime structure in signal_struct is used to cache the earliest expiration; this is checked in the fast path. Performance The fix appears not to add significant overhead to existing operations. It generally performs the same as the current code except in two cases, one in which it performs slightly worse (Case 5 below) and one in which it performs very significantly better (Case 2 below). Overall it's a wash except in those two cases. I've since done somewhat more involved testing on a dual-core Opteron system. Case 1: With no itimer running, for a test with 100,000 threads, the fixed kernel took 1428.5 seconds, 513 seconds more than the unfixed system, all of which was spent in the system. There were twice as many voluntary context switches with the fix as without it. Case 2: With an itimer running at .01 second ticks and 4000 threads (the most an unmodified kernel can handle), the fixed kernel ran the test in eight percent of the time (5.8 seconds as opposed to 70 seconds) and had better tick accuracy (.012 seconds per tick as opposed to .023 seconds per tick). Case 3: A 4000-thread test with an initial timer tick of .01 second and an interval of 10,000 seconds (i.e. a timer that ticks only once) had very nearly the same performance in both cases: 6.3 seconds elapsed for the fixed kernel versus 5.5 seconds for the unfixed kernel. With fewer threads (eight in these tests), the Case 1 test ran in essentially the same time on both the modified and unmodified kernels (5.2 seconds versus 5.8 seconds). The Case 2 test ran in about the same time as well, 5.9 seconds versus 5.4 seconds but again with much better tick accuracy, .013 seconds per tick versus .025 seconds per tick for the unmodified kernel. Since the fix affected the rlimit code, I also tested soft and hard CPU limits. Case 4: With a hard CPU limit of 20 seconds and eight threads (and an itimer running), the modified kernel was very slightly favored in that while it killed the process in 19.997 seconds of CPU time (5.002 seconds of wall time), only .003 seconds of that was system time, the rest was user time. The unmodified kernel killed the process in 20.001 seconds of CPU (5.014 seconds of wall time) of which .016 seconds was system time. Really, though, the results were too close to call. The results were essentially the same with no itimer running. Case 5: With a soft limit of 20 seconds and a hard limit of 2000 seconds (where the hard limit would never be reached) and an itimer running, the modified kernel exhibited worse tick accuracy than the unmodified kernel: .050 seconds/tick versus .028 seconds/tick. Otherwise, performance was almost indistinguishable. With no itimer running this test exhibited virtually identical behavior and times in both cases. In times past I did some limited performance testing. those results are below. On a four-cpu Opteron system without this fix, a sixteen-thread test executed in 3569.991 seconds, of which user was 3568.435s and system was 1.556s. On the same system with the fix, user and elapsed time were about the same, but system time dropped to 0.007 seconds. Performance with eight, four and one thread were comparable. Interestingly, the timer ticks with the fix seemed more accurate: The sixteen-thread test with the fix received 149543 ticks for 0.024 seconds per tick, while the same test without the fix received 58720 for 0.061 seconds per tick. Both cases were configured for an interval of 0.01 seconds. Again, the other tests were comparable. Each thread in this test computed the primes up to 25,000,000. I also did a test with a large number of threads, 100,000 threads, which is impossible without the fix. In this case each thread computed the primes only up to 10,000 (to make the runtime manageable). System time dominated, at 1546.968 seconds out of a total 2176.906 seconds (giving a user time of 629.938s). It received 147651 ticks for 0.015 seconds per tick, still quite accurate. There is obviously no comparable test without the fix. Signed-off-by: Frank Mayhar Cc: Roland McGrath Cc: Alexey Dobriyan Cc: Andrew Morton Signed-off-by: Ingo Molnar --- include/linux/time.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux/time.h') diff --git a/include/linux/time.h b/include/linux/time.h index e15206a7e82e..1b70b3c293e9 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -125,6 +125,9 @@ extern int timekeeping_valid_for_hres(void); extern void update_wall_time(void); extern void update_xtime_cache(u64 nsec); +struct tms; +extern void do_sys_times(struct tms *); + /** * timespec_to_ns - Convert timespec to nanoseconds * @ts: pointer to the timespec variable to be converted -- cgit v1.2.3 From b418da16dd44810e5d5a22bba377cca80512a524 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 15 Oct 2008 22:02:06 -0700 Subject: compat: generic compat get/settimeofday Nothing arch specific in get/settimeofday. The details of the timeval conversion varied a little from arch to arch, but all with the same results. Also add an extern declaration for sys_tz to linux/time.h because externs in .c files are fowned upon. I'll kill the externs in various other files in a sparate patch. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Christoph Hellwig Acked-by: David S. Miller [ sparc bits ] Cc: "Luck, Tony" Cc: Ralf Baechle Acked-by: Kyle McMartin Cc: Matthew Wilcox Cc: Grant Grundler Cc: Paul Mackerras Cc: Benjamin Herrenschmidt Cc: Martin Schwidefsky Cc: Heiko Carstens Cc: Ingo Molnar Cc: Thomas Gleixner Cc: "H. Peter Anvin" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/ia64/ia32/ia32_entry.S | 4 +-- arch/ia64/ia32/sys_ia32.c | 56 ------------------------------- arch/mips/kernel/linux32.c | 66 ------------------------------------- arch/mips/kernel/scall64-n32.S | 4 +-- arch/mips/kernel/scall64-o32.S | 4 +-- arch/parisc/kernel/sys_parisc32.c | 58 --------------------------------- arch/parisc/kernel/syscall_table.S | 4 +-- arch/powerpc/kernel/sys_ppc32.c | 63 ----------------------------------- arch/s390/kernel/compat_linux.c | 67 -------------------------------------- arch/s390/kernel/compat_linux.h | 4 --- arch/s390/kernel/compat_wrapper.S | 12 +++---- arch/s390/kernel/syscalls.S | 4 +-- arch/sparc64/kernel/sys_sparc32.c | 62 ----------------------------------- arch/sparc64/kernel/systbls.S | 4 +-- arch/x86/ia32/ia32entry.S | 4 +-- arch/x86/ia32/sys_ia32.c | 64 ------------------------------------ include/linux/compat.h | 5 +++ include/linux/time.h | 2 ++ kernel/compat.c | 58 +++++++++++++++++++++++++++++++++ 19 files changed, 85 insertions(+), 460 deletions(-) (limited to 'include/linux/time.h') diff --git a/arch/ia64/ia32/ia32_entry.S b/arch/ia64/ia32/ia32_entry.S index ff88c48c5d19..53505bb04771 100644 --- a/arch/ia64/ia32/ia32_entry.S +++ b/arch/ia64/ia32/ia32_entry.S @@ -251,8 +251,8 @@ ia32_syscall_table: data8 compat_sys_setrlimit /* 75 */ data8 compat_sys_old_getrlimit data8 compat_sys_getrusage - data8 sys32_gettimeofday - data8 sys32_settimeofday + data8 compat_sys_gettimeofday + data8 compat_sys_settimeofday data8 sys32_getgroups16 /* 80 */ data8 sys32_setgroups16 data8 sys32_old_select diff --git a/arch/ia64/ia32/sys_ia32.c b/arch/ia64/ia32/sys_ia32.c index 2362a8eefb30..f4430bb4bbdc 100644 --- a/arch/ia64/ia32/sys_ia32.c +++ b/arch/ia64/ia32/sys_ia32.c @@ -1113,68 +1113,12 @@ sys32_pipe (int __user *fd) return retval; } -static inline long -get_tv32 (struct timeval *o, struct compat_timeval __user *i) -{ - return (!access_ok(VERIFY_READ, i, sizeof(*i)) || - (__get_user(o->tv_sec, &i->tv_sec) | __get_user(o->tv_usec, &i->tv_usec))); -} - -static inline long -put_tv32 (struct compat_timeval __user *o, struct timeval *i) -{ - return (!access_ok(VERIFY_WRITE, o, sizeof(*o)) || - (__put_user(i->tv_sec, &o->tv_sec) | __put_user(i->tv_usec, &o->tv_usec))); -} - asmlinkage unsigned long sys32_alarm (unsigned int seconds) { return alarm_setitimer(seconds); } -/* Translations due to time_t size differences. Which affects all - sorts of things, like timeval and itimerval. */ - -extern struct timezone sys_tz; - -asmlinkage long -sys32_gettimeofday (struct compat_timeval __user *tv, struct timezone __user *tz) -{ - if (tv) { - struct timeval ktv; - do_gettimeofday(&ktv); - if (put_tv32(tv, &ktv)) - return -EFAULT; - } - if (tz) { - if (copy_to_user(tz, &sys_tz, sizeof(sys_tz))) - return -EFAULT; - } - return 0; -} - -asmlinkage long -sys32_settimeofday (struct compat_timeval __user *tv, struct timezone __user *tz) -{ - struct timeval ktv; - struct timespec kts; - struct timezone ktz; - - if (tv) { - if (get_tv32(&ktv, tv)) - return -EFAULT; - kts.tv_sec = ktv.tv_sec; - kts.tv_nsec = ktv.tv_usec * 1000; - } - if (tz) { - if (copy_from_user(&ktz, tz, sizeof(ktz))) - return -EFAULT; - } - - return do_sys_settimeofday(tv ? &kts : NULL, tz ? &ktz : NULL); -} - struct sel_arg_struct { unsigned int n; unsigned int inp; diff --git a/arch/mips/kernel/linux32.c b/arch/mips/kernel/linux32.c index 89223a9bff2c..aa2c55e3b55f 100644 --- a/arch/mips/kernel/linux32.c +++ b/arch/mips/kernel/linux32.c @@ -133,72 +133,6 @@ asmlinkage long sys32_ftruncate64(unsigned int fd, unsigned long __dummy, return sys_ftruncate(fd, merge_64(a2, a3)); } -static inline long -get_tv32(struct timeval *o, struct compat_timeval __user *i) -{ - return (!access_ok(VERIFY_READ, i, sizeof(*i)) || - (__get_user(o->tv_sec, &i->tv_sec) | - __get_user(o->tv_usec, &i->tv_usec))); -} - -static inline long -put_tv32(struct compat_timeval __user *o, struct timeval *i) -{ - return (!access_ok(VERIFY_WRITE, o, sizeof(*o)) || - (__put_user(i->tv_sec, &o->tv_sec) | - __put_user(i->tv_usec, &o->tv_usec))); -} - -extern struct timezone sys_tz; - -asmlinkage int -sys32_gettimeofday(struct compat_timeval __user *tv, struct timezone __user *tz) -{ - if (tv) { - struct timeval ktv; - do_gettimeofday(&ktv); - if (put_tv32(tv, &ktv)) - return -EFAULT; - } - if (tz) { - if (copy_to_user(tz, &sys_tz, sizeof(sys_tz))) - return -EFAULT; - } - return 0; -} - -static inline long get_ts32(struct timespec *o, struct compat_timeval __user *i) -{ - long usec; - - if (!access_ok(VERIFY_READ, i, sizeof(*i))) - return -EFAULT; - if (__get_user(o->tv_sec, &i->tv_sec)) - return -EFAULT; - if (__get_user(usec, &i->tv_usec)) - return -EFAULT; - o->tv_nsec = usec * 1000; - return 0; -} - -asmlinkage int -sys32_settimeofday(struct compat_timeval __user *tv, struct timezone __user *tz) -{ - struct timespec kts; - struct timezone ktz; - - if (tv) { - if (get_ts32(&kts, tv)) - return -EFAULT; - } - if (tz) { - if (copy_from_user(&ktz, tz, sizeof(ktz))) - return -EFAULT; - } - - return do_sys_settimeofday(tv ? &kts : NULL, tz ? &ktz : NULL); -} - asmlinkage int sys32_llseek(unsigned int fd, unsigned int offset_high, unsigned int offset_low, loff_t __user * result, unsigned int origin) diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S index 324c5499dec2..e266b3aa6560 100644 --- a/arch/mips/kernel/scall64-n32.S +++ b/arch/mips/kernel/scall64-n32.S @@ -214,7 +214,7 @@ EXPORT(sysn32_call_table) PTR sys_fchown PTR sys_lchown PTR sys_umask - PTR sys32_gettimeofday + PTR compat_sys_gettimeofday PTR compat_sys_getrlimit /* 6095 */ PTR compat_sys_getrusage PTR compat_sys_sysinfo @@ -279,7 +279,7 @@ EXPORT(sysn32_call_table) PTR sys_chroot PTR sys_sync PTR sys_acct - PTR sys32_settimeofday + PTR compat_sys_settimeofday PTR compat_sys_mount /* 6160 */ PTR sys_umount PTR sys_swapon diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S index 85fedac99a57..6c7ef8313ebd 100644 --- a/arch/mips/kernel/scall64-o32.S +++ b/arch/mips/kernel/scall64-o32.S @@ -283,8 +283,8 @@ sys_call_table: PTR compat_sys_setrlimit /* 4075 */ PTR compat_sys_getrlimit PTR compat_sys_getrusage - PTR sys32_gettimeofday - PTR sys32_settimeofday + PTR compat_sys_gettimeofday + PTR compat_sys_settimeofday PTR sys_getgroups /* 4080 */ PTR sys_setgroups PTR sys_ni_syscall /* old_select */ diff --git a/arch/parisc/kernel/sys_parisc32.c b/arch/parisc/kernel/sys_parisc32.c index 2c3af17e049c..0838155b7a88 100644 --- a/arch/parisc/kernel/sys_parisc32.c +++ b/arch/parisc/kernel/sys_parisc32.c @@ -179,64 +179,6 @@ asmlinkage long sys32_sched_rr_get_interval(pid_t pid, return ret; } -static int -put_compat_timeval(struct compat_timeval __user *u, struct timeval *t) -{ - struct compat_timeval t32; - t32.tv_sec = t->tv_sec; - t32.tv_usec = t->tv_usec; - return copy_to_user(u, &t32, sizeof t32); -} - -static inline long get_ts32(struct timespec *o, struct compat_timeval __user *i) -{ - long usec; - - if (__get_user(o->tv_sec, &i->tv_sec)) - return -EFAULT; - if (__get_user(usec, &i->tv_usec)) - return -EFAULT; - o->tv_nsec = usec * 1000; - return 0; -} - -asmlinkage int -sys32_gettimeofday(struct compat_timeval __user *tv, struct timezone __user *tz) -{ - extern void do_gettimeofday(struct timeval *tv); - - if (tv) { - struct timeval ktv; - do_gettimeofday(&ktv); - if (put_compat_timeval(tv, &ktv)) - return -EFAULT; - } - if (tz) { - extern struct timezone sys_tz; - if (copy_to_user(tz, &sys_tz, sizeof(sys_tz))) - return -EFAULT; - } - return 0; -} - -asmlinkage -int sys32_settimeofday(struct compat_timeval __user *tv, struct timezone __user *tz) -{ - struct timespec kts; - struct timezone ktz; - - if (tv) { - if (get_ts32(&kts, tv)) - return -EFAULT; - } - if (tz) { - if (copy_from_user(&ktz, tz, sizeof(ktz))) - return -EFAULT; - } - - return do_sys_settimeofday(tv ? &kts : NULL, tz ? &ktz : NULL); -} - /*** copied from mips64 ***/ /* * Ooo, nasty. We need here to frob 32-bit unsigned longs to diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S index 6b5ac38f5a99..c7e59f548817 100644 --- a/arch/parisc/kernel/syscall_table.S +++ b/arch/parisc/kernel/syscall_table.S @@ -149,8 +149,8 @@ ENTRY_COMP(getrlimit) ENTRY_COMP(getrusage) /* struct timeval and timezone are maybe?? consistent wide and narrow */ - ENTRY_DIFF(gettimeofday) - ENTRY_DIFF(settimeofday) + ENTRY_COMP(gettimeofday) + ENTRY_COMP(settimeofday) ENTRY_SAME(getgroups) /* 80 */ ENTRY_SAME(setgroups) /* struct socketaddr... */ diff --git a/arch/powerpc/kernel/sys_ppc32.c b/arch/powerpc/kernel/sys_ppc32.c index d00599bb24a1..bb1cfcfdbbbb 100644 --- a/arch/powerpc/kernel/sys_ppc32.c +++ b/arch/powerpc/kernel/sys_ppc32.c @@ -71,69 +71,6 @@ asmlinkage long compat_sys_sysfs(u32 option, u32 arg1, u32 arg2) return sys_sysfs((int)option, arg1, arg2); } -static inline long get_ts32(struct timespec *o, struct compat_timeval __user *i) -{ - long usec; - - if (!access_ok(VERIFY_READ, i, sizeof(*i))) - return -EFAULT; - if (__get_user(o->tv_sec, &i->tv_sec)) - return -EFAULT; - if (__get_user(usec, &i->tv_usec)) - return -EFAULT; - o->tv_nsec = usec * 1000; - return 0; -} - -static inline long put_tv32(struct compat_timeval __user *o, struct timeval *i) -{ - return (!access_ok(VERIFY_WRITE, o, sizeof(*o)) || - (__put_user(i->tv_sec, &o->tv_sec) | - __put_user(i->tv_usec, &o->tv_usec))); -} - - - - -/* Translations due to time_t size differences. Which affects all - sorts of things, like timeval and itimerval. */ -extern struct timezone sys_tz; - -asmlinkage long compat_sys_gettimeofday(struct compat_timeval __user *tv, struct timezone __user *tz) -{ - if (tv) { - struct timeval ktv; - do_gettimeofday(&ktv); - if (put_tv32(tv, &ktv)) - return -EFAULT; - } - if (tz) { - if (copy_to_user(tz, &sys_tz, sizeof(sys_tz))) - return -EFAULT; - } - - return 0; -} - - - -asmlinkage long compat_sys_settimeofday(struct compat_timeval __user *tv, struct timezone __user *tz) -{ - struct timespec kts; - struct timezone ktz; - - if (tv) { - if (get_ts32(&kts, tv)) - return -EFAULT; - } - if (tz) { - if (copy_from_user(&ktz, tz, sizeof(ktz))) - return -EFAULT; - } - - return do_sys_settimeofday(tv ? &kts : NULL, tz ? &ktz : NULL); -} - #ifdef CONFIG_SYSVIPC long compat_sys_ipc(u32 call, u32 first, u32 second, u32 third, compat_uptr_t ptr, u32 fifth) diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c index 9b471d785ec1..4646382af34f 100644 --- a/arch/s390/kernel/compat_linux.c +++ b/arch/s390/kernel/compat_linux.c @@ -279,22 +279,6 @@ asmlinkage long sys32_getegid16(void) return high2lowgid(current->egid); } -/* 32-bit timeval and related flotsam. */ - -static inline long get_tv32(struct timeval *o, struct compat_timeval __user *i) -{ - return (!access_ok(VERIFY_READ, o, sizeof(*o)) || - (__get_user(o->tv_sec, &i->tv_sec) || - __get_user(o->tv_usec, &i->tv_usec))); -} - -static inline long put_tv32(struct compat_timeval __user *o, struct timeval *i) -{ - return (!access_ok(VERIFY_WRITE, o, sizeof(*o)) || - (__put_user(i->tv_sec, &o->tv_sec) || - __put_user(i->tv_usec, &o->tv_usec))); -} - /* * sys32_ipc() is the de-multiplexer for the SysV IPC calls in 32bit emulation. * @@ -522,57 +506,6 @@ sys32_delete_module(const char __user *name_user, unsigned int flags) #endif /* CONFIG_MODULES */ -/* Translations due to time_t size differences. Which affects all - sorts of things, like timeval and itimerval. */ - -extern struct timezone sys_tz; - -asmlinkage long sys32_gettimeofday(struct compat_timeval __user *tv, struct timezone __user *tz) -{ - if (tv) { - struct timeval ktv; - do_gettimeofday(&ktv); - if (put_tv32(tv, &ktv)) - return -EFAULT; - } - if (tz) { - if (copy_to_user(tz, &sys_tz, sizeof(sys_tz))) - return -EFAULT; - } - return 0; -} - -static inline long get_ts32(struct timespec *o, struct compat_timeval __user *i) -{ - long usec; - - if (!access_ok(VERIFY_READ, i, sizeof(*i))) - return -EFAULT; - if (__get_user(o->tv_sec, &i->tv_sec)) - return -EFAULT; - if (__get_user(usec, &i->tv_usec)) - return -EFAULT; - o->tv_nsec = usec * 1000; - return 0; -} - -asmlinkage long sys32_settimeofday(struct compat_timeval __user *tv, struct timezone __user *tz) -{ - struct timespec kts; - struct timezone ktz; - - if (tv) { - if (get_ts32(&kts, tv)) - return -EFAULT; - } - if (tz) { - if (copy_from_user(&ktz, tz, sizeof(ktz))) - return -EFAULT; - } - - return do_sys_settimeofday(tv ? &kts : NULL, tz ? &ktz : NULL); -} - asmlinkage long sys32_pread64(unsigned int fd, char __user *ubuf, size_t count, u32 poshi, u32 poslo) { diff --git a/arch/s390/kernel/compat_linux.h b/arch/s390/kernel/compat_linux.h index 05f8516366ab..836a28842900 100644 --- a/arch/s390/kernel/compat_linux.h +++ b/arch/s390/kernel/compat_linux.h @@ -202,10 +202,6 @@ long sys32_execve(void); long sys32_init_module(void __user *umod, unsigned long len, const char __user *uargs); long sys32_delete_module(const char __user *name_user, unsigned int flags); -long sys32_gettimeofday(struct compat_timeval __user *tv, - struct timezone __user *tz); -long sys32_settimeofday(struct compat_timeval __user *tv, - struct timezone __user *tz); long sys32_pread64(unsigned int fd, char __user *ubuf, size_t count, u32 poshi, u32 poslo); long sys32_pwrite64(unsigned int fd, const char __user *ubuf, diff --git a/arch/s390/kernel/compat_wrapper.S b/arch/s390/kernel/compat_wrapper.S index ee51ca9e23b5..fc2c97197a53 100644 --- a/arch/s390/kernel/compat_wrapper.S +++ b/arch/s390/kernel/compat_wrapper.S @@ -332,17 +332,17 @@ compat_sys_getrusage_wrapper: llgtr %r3,%r3 # struct rusage_emu31 * jg compat_sys_getrusage # branch to system call - .globl sys32_gettimeofday_wrapper -sys32_gettimeofday_wrapper: + .globl compat_sys_gettimeofday_wrapper +compat_sys_gettimeofday_wrapper: llgtr %r2,%r2 # struct timeval_emu31 * llgtr %r3,%r3 # struct timezone * - jg sys32_gettimeofday # branch to system call + jg compat_sys_gettimeofday # branch to system call - .globl sys32_settimeofday_wrapper -sys32_settimeofday_wrapper: + .globl compat_sys_settimeofday_wrapper +compat_sys_settimeofday_wrapper: llgtr %r2,%r2 # struct timeval_emu31 * llgtr %r3,%r3 # struct timezone * - jg sys32_settimeofday # branch to system call + jg compat_sys_settimeofday # branch to system call .globl sys32_getgroups16_wrapper sys32_getgroups16_wrapper: diff --git a/arch/s390/kernel/syscalls.S b/arch/s390/kernel/syscalls.S index 3ae303914b42..2d61787949d5 100644 --- a/arch/s390/kernel/syscalls.S +++ b/arch/s390/kernel/syscalls.S @@ -86,8 +86,8 @@ SYSCALL(sys_sethostname,sys_sethostname,sys32_sethostname_wrapper) SYSCALL(sys_setrlimit,sys_setrlimit,compat_sys_setrlimit_wrapper) /* 75 */ SYSCALL(sys_old_getrlimit,sys_getrlimit,compat_sys_old_getrlimit_wrapper) SYSCALL(sys_getrusage,sys_getrusage,compat_sys_getrusage_wrapper) -SYSCALL(sys_gettimeofday,sys_gettimeofday,sys32_gettimeofday_wrapper) -SYSCALL(sys_settimeofday,sys_settimeofday,sys32_settimeofday_wrapper) +SYSCALL(sys_gettimeofday,sys_gettimeofday,compat_sys_gettimeofday_wrapper) +SYSCALL(sys_settimeofday,sys_settimeofday,compat_sys_settimeofday_wrapper) SYSCALL(sys_getgroups16,sys_ni_syscall,sys32_getgroups16_wrapper) /* 80 old getgroups16 syscall */ SYSCALL(sys_setgroups16,sys_ni_syscall,sys32_setgroups16_wrapper) /* old setgroups16 syscall */ NI_SYSCALL /* old select syscall */ diff --git a/arch/sparc64/kernel/sys_sparc32.c b/arch/sparc64/kernel/sys_sparc32.c index 73a33dc3bcca..e800503879e4 100644 --- a/arch/sparc64/kernel/sys_sparc32.c +++ b/arch/sparc64/kernel/sys_sparc32.c @@ -58,15 +58,6 @@ #include #include -/* 32-bit timeval and related flotsam. */ - -static inline long put_tv32(struct compat_timeval __user *o, struct timeval *i) -{ - return (!access_ok(VERIFY_WRITE, o, sizeof(*o)) || - (__put_user(i->tv_sec, &o->tv_sec) | - __put_user(i->tv_usec, &o->tv_usec))); -} - #ifdef CONFIG_SYSVIPC asmlinkage long compat_sys_ipc(u32 call, u32 first, u32 second, u32 third, compat_uptr_t ptr, u32 fifth) { @@ -487,59 +478,6 @@ asmlinkage long sys32_delete_module(const char __user *name_user) #endif /* CONFIG_MODULES */ -/* Translations due to time_t size differences. Which affects all - sorts of things, like timeval and itimerval. */ - -extern struct timezone sys_tz; - -asmlinkage long sys32_gettimeofday(struct compat_timeval __user *tv, - struct timezone __user *tz) -{ - if (tv) { - struct timeval ktv; - do_gettimeofday(&ktv); - if (put_tv32(tv, &ktv)) - return -EFAULT; - } - if (tz) { - if (copy_to_user(tz, &sys_tz, sizeof(sys_tz))) - return -EFAULT; - } - return 0; -} - -static inline long get_ts32(struct timespec *o, struct compat_timeval __user *i) -{ - long usec; - - if (!access_ok(VERIFY_READ, i, sizeof(*i))) - return -EFAULT; - if (__get_user(o->tv_sec, &i->tv_sec)) - return -EFAULT; - if (__get_user(usec, &i->tv_usec)) - return -EFAULT; - o->tv_nsec = usec * 1000; - return 0; -} - -asmlinkage long sys32_settimeofday(struct compat_timeval __user *tv, - struct timezone __user *tz) -{ - struct timespec kts; - struct timezone ktz; - - if (tv) { - if (get_ts32(&kts, tv)) - return -EFAULT; - } - if (tz) { - if (copy_from_user(&ktz, tz, sizeof(ktz))) - return -EFAULT; - } - - return do_sys_settimeofday(tv ? &kts : NULL, tz ? &ktz : NULL); -} - asmlinkage compat_ssize_t sys32_pread64(unsigned int fd, char __user *ubuf, compat_size_t count, diff --git a/arch/sparc64/kernel/systbls.S b/arch/sparc64/kernel/systbls.S index 5daee4b04dd5..b2fa4c163638 100644 --- a/arch/sparc64/kernel/systbls.S +++ b/arch/sparc64/kernel/systbls.S @@ -41,8 +41,8 @@ sys_call_table32: /*100*/ .word sys32_getpriority, sys32_rt_sigreturn, sys32_rt_sigaction, sys32_rt_sigprocmask, sys32_rt_sigpending .word compat_sys_rt_sigtimedwait, sys32_rt_sigqueueinfo, compat_sys_rt_sigsuspend, sys_setresuid, sys_getresuid /*110*/ .word sys_setresgid, sys_getresgid, sys_setregid, sys_nis_syscall, sys_nis_syscall - .word sys32_getgroups, sys32_gettimeofday, sys32_getrusage, sys_nis_syscall, sys_getcwd -/*120*/ .word compat_sys_readv, compat_sys_writev, sys32_settimeofday, sys_fchown16, sys_fchmod + .word sys32_getgroups, compat_sys_gettimeofday, sys32_getrusage, sys_nis_syscall, sys_getcwd +/*120*/ .word compat_sys_readv, compat_sys_writev, compat_sys_settimeofday, sys_fchown16, sys_fchmod .word sys_nis_syscall, sys_setreuid16, sys_setregid16, sys_rename, sys_truncate /*130*/ .word sys_ftruncate, sys_flock, compat_sys_lstat64, sys_nis_syscall, sys_nis_syscall .word sys_nis_syscall, sys32_mkdir, sys_rmdir, compat_sys_utimes, compat_sys_stat64 diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index eb4314768bf7..256b00b61892 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -571,8 +571,8 @@ ia32_sys_call_table: .quad compat_sys_setrlimit /* 75 */ .quad compat_sys_old_getrlimit /* old_getrlimit */ .quad compat_sys_getrusage - .quad sys32_gettimeofday - .quad sys32_settimeofday + .quad compat_sys_gettimeofday + .quad compat_sys_settimeofday .quad sys_getgroups16 /* 80 */ .quad sys_setgroups16 .quad sys32_old_select diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c index 4d3ad8d78a4d..2e09dcd3c0a6 100644 --- a/arch/x86/ia32/sys_ia32.c +++ b/arch/x86/ia32/sys_ia32.c @@ -367,75 +367,11 @@ asmlinkage long sys32_rt_sigprocmask(int how, compat_sigset_t __user *set, return 0; } -static inline long get_tv32(struct timeval *o, struct compat_timeval __user *i) -{ - int err = -EFAULT; - - if (access_ok(VERIFY_READ, i, sizeof(*i))) { - err = __get_user(o->tv_sec, &i->tv_sec); - err |= __get_user(o->tv_usec, &i->tv_usec); - } - return err; -} - -static inline long put_tv32(struct compat_timeval __user *o, struct timeval *i) -{ - int err = -EFAULT; - - if (access_ok(VERIFY_WRITE, o, sizeof(*o))) { - err = __put_user(i->tv_sec, &o->tv_sec); - err |= __put_user(i->tv_usec, &o->tv_usec); - } - return err; -} - asmlinkage long sys32_alarm(unsigned int seconds) { return alarm_setitimer(seconds); } -/* - * Translations due to time_t size differences. Which affects all - * sorts of things, like timeval and itimerval. - */ -asmlinkage long sys32_gettimeofday(struct compat_timeval __user *tv, - struct timezone __user *tz) -{ - if (tv) { - struct timeval ktv; - - do_gettimeofday(&ktv); - if (put_tv32(tv, &ktv)) - return -EFAULT; - } - if (tz) { - if (copy_to_user(tz, &sys_tz, sizeof(sys_tz))) - return -EFAULT; - } - return 0; -} - -asmlinkage long sys32_settimeofday(struct compat_timeval __user *tv, - struct timezone __user *tz) -{ - struct timeval ktv; - struct timespec kts; - struct timezone ktz; - - if (tv) { - if (get_tv32(&ktv, tv)) - return -EFAULT; - kts.tv_sec = ktv.tv_sec; - kts.tv_nsec = ktv.tv_usec * NSEC_PER_USEC; - } - if (tz) { - if (copy_from_user(&ktz, tz, sizeof(ktz))) - return -EFAULT; - } - - return do_sys_settimeofday(tv ? &kts : NULL, tz ? &ktz : NULL); -} - struct sel_arg_struct { unsigned int n; unsigned int inp; diff --git a/include/linux/compat.h b/include/linux/compat.h index 999dddd8d939..f061a1ea1b74 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -234,6 +234,11 @@ extern int get_compat_itimerspec(struct itimerspec *dst, extern int put_compat_itimerspec(struct compat_itimerspec __user *dst, const struct itimerspec *src); +asmlinkage long compat_sys_gettimeofday(struct compat_timeval __user *tv, + struct timezone __user *tz); +asmlinkage long compat_sys_settimeofday(struct compat_timeval __user *tv, + struct timezone __user *tz); + asmlinkage long compat_sys_adjtimex(struct compat_timex __user *utp); extern int compat_printk(const char *fmt, ...); diff --git a/include/linux/time.h b/include/linux/time.h index e15206a7e82e..51e883df0fa5 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -29,6 +29,8 @@ struct timezone { #ifdef __KERNEL__ +extern struct timezone sys_tz; + /* Parameters used to convert the timespec values: */ #define MSEC_PER_SEC 1000L #define USEC_PER_MSEC 1000L diff --git a/kernel/compat.c b/kernel/compat.c index 32c254a8ab9a..143990e48cb9 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -26,6 +26,64 @@ #include +/* + * Note that the native side is already converted to a timespec, because + * that's what we want anyway. + */ +static int compat_get_timeval(struct timespec *o, + struct compat_timeval __user *i) +{ + long usec; + + if (get_user(o->tv_sec, &i->tv_sec) || + get_user(usec, &i->tv_usec)) + return -EFAULT; + o->tv_nsec = usec * 1000; + return 0; +} + +static int compat_put_timeval(struct compat_timeval __user *o, + struct timeval *i) +{ + return (put_user(i->tv_sec, &o->tv_sec) || + put_user(i->tv_usec, &o->tv_usec)) ? -EFAULT : 0; +} + +asmlinkage long compat_sys_gettimeofday(struct compat_timeval __user *tv, + struct timezone __user *tz) +{ + if (tv) { + struct timeval ktv; + do_gettimeofday(&ktv); + if (compat_put_timeval(tv, &ktv)) + return -EFAULT; + } + if (tz) { + if (copy_to_user(tz, &sys_tz, sizeof(sys_tz))) + return -EFAULT; + } + + return 0; +} + +asmlinkage long compat_sys_settimeofday(struct compat_timeval __user *tv, + struct timezone __user *tz) +{ + struct timespec kts; + struct timezone ktz; + + if (tv) { + if (compat_get_timeval(&kts, tv)) + return -EFAULT; + } + if (tz) { + if (copy_from_user(&ktz, tz, sizeof(ktz))) + return -EFAULT; + } + + return do_sys_settimeofday(tv ? &kts : NULL, tz ? &ktz : NULL); +} + int get_compat_timespec(struct timespec *ts, const struct compat_timespec __user *cts) { return (!access_ok(VERIFY_READ, cts, sizeof(*cts)) || -- cgit v1.2.3