From ce72a16fa705f960ca2352e95a7c5f4801475e75 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 14 May 2017 20:25:02 -0400 Subject: wait4(2)/waitid(2): separate copying rusage to userland New helpers: kernel_waitid() and kernel_wait4(). sys_waitid(), sys_wait4() and their compat variants switched to those. Copying struct rusage to userland is left to syscall itself. For compat_sys_wait4() that eliminates the use of set_fs() completely. For compat_sys_waitid() it's still needed (for siginfo handling); that will change shortly. Signed-off-by: Al Viro --- kernel/sys.c | 16 ++++++---------- 1 file changed, 6 insertions(+), 10 deletions(-) (limited to 'kernel/sys.c') diff --git a/kernel/sys.c b/kernel/sys.c index 8a94b4eabcaa..dab1a0658a92 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1552,7 +1552,7 @@ static void accumulate_thread_rusage(struct task_struct *t, struct rusage *r) r->ru_oublock += task_io_get_oublock(t); } -static void k_getrusage(struct task_struct *p, int who, struct rusage *r) +void getrusage(struct task_struct *p, int who, struct rusage *r) { struct task_struct *t; unsigned long flags; @@ -1626,20 +1626,16 @@ out: r->ru_maxrss = maxrss * (PAGE_SIZE / 1024); /* convert pages to KBs */ } -int getrusage(struct task_struct *p, int who, struct rusage __user *ru) +SYSCALL_DEFINE2(getrusage, int, who, struct rusage __user *, ru) { struct rusage r; - k_getrusage(p, who, &r); - return copy_to_user(ru, &r, sizeof(r)) ? -EFAULT : 0; -} - -SYSCALL_DEFINE2(getrusage, int, who, struct rusage __user *, ru) -{ if (who != RUSAGE_SELF && who != RUSAGE_CHILDREN && who != RUSAGE_THREAD) return -EINVAL; - return getrusage(current, who, ru); + + getrusage(current, who, &r); + return copy_to_user(ru, &r, sizeof(r)) ? -EFAULT : 0; } #ifdef CONFIG_COMPAT @@ -1651,7 +1647,7 @@ COMPAT_SYSCALL_DEFINE2(getrusage, int, who, struct compat_rusage __user *, ru) who != RUSAGE_THREAD) return -EINVAL; - k_getrusage(current, who, &r); + getrusage(current, who, &r); return put_compat_rusage(&r, ru); } #endif -- cgit v1.2.3 From 613763a1f056211522bac77ff39f25706e678fdd Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 26 May 2017 22:04:29 -0400 Subject: take compat_sys_old_getrlimit() to native syscall ... and sanitize the ifdefs in there Signed-off-by: Al Viro --- kernel/sys.c | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'kernel/sys.c') diff --git a/kernel/sys.c b/kernel/sys.c index 8a94b4eabcaa..3778a8a417b6 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1328,6 +1328,30 @@ SYSCALL_DEFINE2(old_getrlimit, unsigned int, resource, return copy_to_user(rlim, &x, sizeof(x)) ? -EFAULT : 0; } +#ifdef CONFIG_COMPAT +COMPAT_SYSCALL_DEFINE2(old_getrlimit, unsigned int, resource, + struct compat_rlimit __user *, rlim) +{ + struct rlimit r; + + if (resource >= RLIM_NLIMITS) + return -EINVAL; + + task_lock(current->group_leader); + r = current->signal->rlim[resource]; + task_unlock(current->group_leader); + if (r.rlim_cur > 0x7FFFFFFF) + r.rlim_cur = 0x7FFFFFFF; + if (r.rlim_max > 0x7FFFFFFF) + r.rlim_max = 0x7FFFFFFF; + + if (put_user(r.rlim_cur, &rlim->rlim_cur) || + put_user(r.rlim_max, &rlim->rlim_max)) + return -EFAULT; + return 0; +} +#endif + #endif static inline bool rlim64_is_infinity(__u64 rlim64) -- cgit v1.2.3 From ca2406ed58fef3f7c8ef6470cba807bfc3415605 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 31 May 2017 04:22:44 -0400 Subject: times(2): move compat to native Signed-off-by: Al Viro --- kernel/sys.c | 28 +++++++++++++++++++++++++++- 1 file changed, 27 insertions(+), 1 deletion(-) (limited to 'kernel/sys.c') diff --git a/kernel/sys.c b/kernel/sys.c index 3778a8a417b6..161b5eae9c77 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -886,7 +886,7 @@ SYSCALL_DEFINE0(getegid) return from_kgid_munged(current_user_ns(), current_egid()); } -void do_sys_times(struct tms *tms) +static void do_sys_times(struct tms *tms) { u64 tgutime, tgstime, cutime, cstime; @@ -912,6 +912,32 @@ SYSCALL_DEFINE1(times, struct tms __user *, tbuf) return (long) jiffies_64_to_clock_t(get_jiffies_64()); } +#ifdef CONFIG_COMPAT +static compat_clock_t clock_t_to_compat_clock_t(clock_t x) +{ + return compat_jiffies_to_clock_t(clock_t_to_jiffies(x)); +} + +COMPAT_SYSCALL_DEFINE1(times, struct compat_tms __user *, tbuf) +{ + if (tbuf) { + struct tms tms; + struct compat_tms tmp; + + do_sys_times(&tms); + /* Convert our struct tms to the compat version. */ + tmp.tms_utime = clock_t_to_compat_clock_t(tms.tms_utime); + tmp.tms_stime = clock_t_to_compat_clock_t(tms.tms_stime); + tmp.tms_cutime = clock_t_to_compat_clock_t(tms.tms_cutime); + tmp.tms_cstime = clock_t_to_compat_clock_t(tms.tms_cstime); + if (copy_to_user(tbuf, &tmp, sizeof(tmp))) + return -EFAULT; + } + force_successful_syscall_return(); + return compat_jiffies_to_clock_t(jiffies); +} +#endif + /* * This needs some heavy checking ... * I just haven't the stomach for it. I also don't fully -- cgit v1.2.3 From d9e968cb9f849770288f5fde3d8d3a5f7e339052 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 31 May 2017 04:33:51 -0400 Subject: getrlimit()/setrlimit(): move compat to native Signed-off-by: Al Viro --- kernel/sys.c | 48 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 48 insertions(+) (limited to 'kernel/sys.c') diff --git a/kernel/sys.c b/kernel/sys.c index 161b5eae9c77..873e6eaa314f 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1332,6 +1332,54 @@ SYSCALL_DEFINE2(getrlimit, unsigned int, resource, struct rlimit __user *, rlim) return ret; } +#ifdef CONFIG_COMPAT + +COMPAT_SYSCALL_DEFINE2(setrlimit, unsigned int, resource, + struct compat_rlimit __user *, rlim) +{ + struct rlimit r; + struct compat_rlimit r32; + + if (copy_from_user(&r32, rlim, sizeof(struct compat_rlimit))) + return -EFAULT; + + if (r32.rlim_cur == COMPAT_RLIM_INFINITY) + r.rlim_cur = RLIM_INFINITY; + else + r.rlim_cur = r32.rlim_cur; + if (r32.rlim_max == COMPAT_RLIM_INFINITY) + r.rlim_max = RLIM_INFINITY; + else + r.rlim_max = r32.rlim_max; + return do_prlimit(current, resource, &r, NULL); +} + +COMPAT_SYSCALL_DEFINE2(getrlimit, unsigned int, resource, + struct compat_rlimit __user *, rlim) +{ + struct rlimit r; + int ret; + + ret = do_prlimit(current, resource, NULL, &r); + if (!ret) { + struct rlimit r32; + if (r.rlim_cur > COMPAT_RLIM_INFINITY) + r32.rlim_cur = COMPAT_RLIM_INFINITY; + else + r32.rlim_cur = r.rlim_cur; + if (r.rlim_max > COMPAT_RLIM_INFINITY) + r32.rlim_max = COMPAT_RLIM_INFINITY; + else + r32.rlim_max = r.rlim_max; + + if (copy_to_user(rlim, &r32, sizeof(struct compat_rlimit))) + return -EFAULT; + } + return ret; +} + +#endif + #ifdef __ARCH_WANT_SYS_OLD_GETRLIMIT /* -- cgit v1.2.3 From 1860033237d4be09c5d7382585f0c7229367a534 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Mon, 10 Jul 2017 15:48:02 -0700 Subject: mm: make PR_SET_THP_DISABLE immediately active PR_SET_THP_DISABLE has a rather subtle semantic. It doesn't affect any existing mapping because it only updated mm->def_flags which is a template for new mappings. The mappings created after prctl(PR_SET_THP_DISABLE) have VM_NOHUGEPAGE flag set. This can be quite surprising for all those applications which do not do prctl(); fork() & exec() and want to control their own THP behavior. Another usecase when the immediate semantic of the prctl might be useful is a combination of pre- and post-copy migration of containers with CRIU. In this case CRIU populates a part of a memory region with data that was saved during the pre-copy stage. Afterwards, the region is registered with userfaultfd and CRIU expects to get page faults for the parts of the region that were not yet populated. However, khugepaged collapses the pages and the expected page faults do not occur. In more general case, the prctl(PR_SET_THP_DISABLE) could be used as a temporary mechanism for enabling/disabling THP process wide. Implementation wise, a new MMF_DISABLE_THP flag is added. This flag is tested when decision whether to use huge pages is taken either during page fault of at the time of THP collapse. It should be noted, that the new implementation makes PR_SET_THP_DISABLE master override to any per-VMA setting, which was not the case previously. Fixes: a0715cc22601 ("mm, thp: add VM_INIT_DEF_MASK and PRCTL_THP_DISABLE") Link: http://lkml.kernel.org/r/1496415802-30944-1-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Michal Hocko Signed-off-by: Mike Rapoport Cc: Vlastimil Babka Cc: Andrea Arcangeli Cc: Arnd Bergmann Cc: "Kirill A. Shutemov" Cc: Pavel Emelyanov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sys.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'kernel/sys.c') diff --git a/kernel/sys.c b/kernel/sys.c index 47d901586b4e..73fc0af147d0 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -2360,7 +2360,7 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, case PR_GET_THP_DISABLE: if (arg2 || arg3 || arg4 || arg5) return -EINVAL; - error = !!(me->mm->def_flags & VM_NOHUGEPAGE); + error = !!test_bit(MMF_DISABLE_THP, &me->mm->flags); break; case PR_SET_THP_DISABLE: if (arg3 || arg4 || arg5) @@ -2368,9 +2368,9 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, if (down_write_killable(&me->mm->mmap_sem)) return -EINTR; if (arg2) - me->mm->def_flags |= VM_NOHUGEPAGE; + set_bit(MMF_DISABLE_THP, &me->mm->flags); else - me->mm->def_flags &= ~VM_NOHUGEPAGE; + clear_bit(MMF_DISABLE_THP, &me->mm->flags); up_write(&me->mm->mmap_sem); break; case PR_MPX_ENABLE_MANAGEMENT: -- cgit v1.2.3 From 58c7ffc0747a3a9145629d4966291f0586703767 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 12 Jul 2017 04:59:45 +0100 Subject: fix a braino in compat_sys_getrlimit() Reported-and-tested-by: Meelis Roos Fixes: commit d9e968cb9f84 "getrlimit()/setrlimit(): move compat to native" Signed-off-by: Al Viro Acked-by: David S. Miller Signed-off-by: Linus Torvalds --- kernel/sys.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/sys.c') diff --git a/kernel/sys.c b/kernel/sys.c index 73fc0af147d0..2855ee73acd0 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1362,7 +1362,7 @@ COMPAT_SYSCALL_DEFINE2(getrlimit, unsigned int, resource, ret = do_prlimit(current, resource, NULL, &r); if (!ret) { - struct rlimit r32; + struct compat_rlimit r32; if (r.rlim_cur > COMPAT_RLIM_INFINITY) r32.rlim_cur = COMPAT_RLIM_INFINITY; else -- cgit v1.2.3