From 971c90bfa2f0b4fe52d6d9002178d547706f1343 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Thu, 4 Aug 2011 07:25:35 -0700 Subject: alarmtimers: Avoid possible null pointer traversal We don't check if old_setting is non null before assigning it, so correct this. CC: Thomas Gleixner CC: stable@kernel.org Signed-off-by: John Stultz --- kernel/time/alarmtimer.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index 59f369f98a04..1dee3f62a6a7 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -479,11 +479,8 @@ static int alarm_timer_set(struct k_itimer *timr, int flags, if (!rtcdev) return -ENOTSUPP; - /* Save old values */ - old_setting->it_interval = - ktime_to_timespec(timr->it.alarmtimer.period); - old_setting->it_value = - ktime_to_timespec(timr->it.alarmtimer.node.expires); + if (old_setting) + alarm_timer_get(timr, old_setting); /* If the timer was already set, cancel it */ alarm_cancel(&timr->it.alarmtimer); -- cgit v1.2.3-71-gd317 From ea7802f630d356acaf66b3c0b28c00a945fc35dc Mon Sep 17 00:00:00 2001 From: John Stultz Date: Thu, 4 Aug 2011 07:51:56 -0700 Subject: alarmtimers: Memset itimerspec passed into alarm_timer_get Following common_timer_get, zero out the itimerspec passed in. CC: Thomas Gleixner CC: stable@kernel.org Signed-off-by: John Stultz --- kernel/time/alarmtimer.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel') diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index 1dee3f62a6a7..0e9263f6fd09 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -441,6 +441,8 @@ static int alarm_timer_create(struct k_itimer *new_timer) static void alarm_timer_get(struct k_itimer *timr, struct itimerspec *cur_setting) { + memset(cur_setting, 0, sizeof(struct itimerspec)); + cur_setting->it_interval = ktime_to_timespec(timr->it.alarmtimer.period); cur_setting->it_value = -- cgit v1.2.3-71-gd317 From 6af7e471e5a7746b8024d70b4363d3dfe41d36b8 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Wed, 10 Aug 2011 10:26:09 -0700 Subject: alarmtimers: Avoid possible denial of service with high freq periodic timers Its possible to jam up the alarm timers by setting very small interval timers, which will cause the alarmtimer subsystem to spend all of its time firing and restarting timers. This can effectivly lock up a box. A deeper fix is needed, closely mimicking the hrtimer code, but for now just cap the interval to 100us to avoid userland hanging the system. CC: Thomas Gleixner CC: stable@kernel.org Signed-off-by: John Stultz --- kernel/time/alarmtimer.c | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'kernel') diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index 0e9263f6fd09..ea5e1a928d5b 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -481,6 +481,15 @@ static int alarm_timer_set(struct k_itimer *timr, int flags, if (!rtcdev) return -ENOTSUPP; + /* + * XXX HACK! Currently we can DOS a system if the interval + * period on alarmtimers is too small. Cap the interval here + * to 100us and solve this properly in a future patch! -jstultz + */ + if ((new_setting->it_interval.tv_sec == 0) && + (new_setting->it_interval.tv_nsec < 100000)) + new_setting->it_interval.tv_nsec = 100000; + if (old_setting) alarm_timer_get(timr, old_setting); -- cgit v1.2.3-71-gd317 From be27425dcc516fd08245b047ea57f83b8f6f0903 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Fri, 19 Aug 2011 16:15:10 -0700 Subject: Add a personality to report 2.6.x version numbers I ran into a couple of programs which broke with the new Linux 3.0 version. Some of those were binary only. I tried to use LD_PRELOAD to work around it, but it was quite difficult and in one case impossible because of a mix of 32bit and 64bit executables. For example, all kind of management software from HP doesnt work, unless we pretend to run a 2.6 kernel. $ uname -a Linux svivoipvnx001 3.0.0-08107-g97cd98f #1062 SMP Fri Aug 12 18:11:45 CEST 2011 i686 i686 i386 GNU/Linux $ hpacucli ctrl all show Error: No controllers detected. $ rpm -qf /usr/sbin/hpacucli hpacucli-8.75-12.0 Another notable case is that Python now reports "linux3" from sys.platform(); which in turn can break things that were checking sys.platform() == "linux2": https://bugzilla.mozilla.org/show_bug.cgi?id=664564 It seems pretty clear to me though it's a bug in the apps that are using '==' instead of .startswith(), but this allows us to unbreak broken programs. This patch adds a UNAME26 personality that makes the kernel report a 2.6.40+x version number instead. The x is the x in 3.x. I know this is somewhat ugly, but I didn't find a better workaround, and compatibility to existing programs is important. Some programs also read /proc/sys/kernel/osrelease. This can be worked around in user space with mount --bind (and a mount namespace) To use: wget ftp://ftp.kernel.org/pub/linux/kernel/people/ak/uname26/uname26.c gcc -o uname26 uname26.c ./uname26 program Signed-off-by: Andi Kleen Signed-off-by: Linus Torvalds --- include/linux/personality.h | 1 + kernel/sys.c | 38 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 39 insertions(+) (limited to 'kernel') diff --git a/include/linux/personality.h b/include/linux/personality.h index eec3bae164d4..8fc7dd1a57ff 100644 --- a/include/linux/personality.h +++ b/include/linux/personality.h @@ -22,6 +22,7 @@ extern int __set_personality(unsigned int); * These occupy the top three bytes. */ enum { + UNAME26 = 0x0020000, ADDR_NO_RANDOMIZE = 0x0040000, /* disable randomization of VA space */ FDPIC_FUNCPTRS = 0x0080000, /* userspace function ptrs point to descriptors * (signal handling) diff --git a/kernel/sys.c b/kernel/sys.c index dd948a1fca4c..18ee1d2f6474 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -37,6 +37,8 @@ #include #include #include +#include +#include #include #include @@ -44,6 +46,8 @@ #include #include +/* Move somewhere else to avoid recompiling? */ +#include #include #include @@ -1161,6 +1165,34 @@ DECLARE_RWSEM(uts_sem); #define override_architecture(name) 0 #endif +/* + * Work around broken programs that cannot handle "Linux 3.0". + * Instead we map 3.x to 2.6.40+x, so e.g. 3.0 would be 2.6.40 + */ +static int override_release(char __user *release, int len) +{ + int ret = 0; + char buf[len]; + + if (current->personality & UNAME26) { + char *rest = UTS_RELEASE; + int ndots = 0; + unsigned v; + + while (*rest) { + if (*rest == '.' && ++ndots >= 3) + break; + if (!isdigit(*rest) && *rest != '.') + break; + rest++; + } + v = ((LINUX_VERSION_CODE >> 8) & 0xff) + 40; + snprintf(buf, len, "2.6.%u%s", v, rest); + ret = copy_to_user(release, buf, len); + } + return ret; +} + SYSCALL_DEFINE1(newuname, struct new_utsname __user *, name) { int errno = 0; @@ -1170,6 +1202,8 @@ SYSCALL_DEFINE1(newuname, struct new_utsname __user *, name) errno = -EFAULT; up_read(&uts_sem); + if (!errno && override_release(name->release, sizeof(name->release))) + errno = -EFAULT; if (!errno && override_architecture(name)) errno = -EFAULT; return errno; @@ -1191,6 +1225,8 @@ SYSCALL_DEFINE1(uname, struct old_utsname __user *, name) error = -EFAULT; up_read(&uts_sem); + if (!error && override_release(name->release, sizeof(name->release))) + error = -EFAULT; if (!error && override_architecture(name)) error = -EFAULT; return error; @@ -1225,6 +1261,8 @@ SYSCALL_DEFINE1(olduname, struct oldold_utsname __user *, name) if (!error && override_architecture(name)) error = -EFAULT; + if (!error && override_release(name->release, sizeof(name->release))) + error = -EFAULT; return error ? -EFAULT : 0; } #endif -- cgit v1.2.3-71-gd317 From 4c30c6f566c0989ddaee3407da44751e340a63ed Mon Sep 17 00:00:00 2001 From: Nishanth Aravamudan Date: Thu, 25 Aug 2011 15:59:11 -0700 Subject: kernel/printk: do not turn off bootconsole in printk_late_init() if keep_bootcon It seems that 7bf693951a8e ("console: allow to retain boot console via boot option keep_bootcon") doesn't always achieve what it aims, as when printk_late_init() runs it unconditionally turns off all boot consoles. With this patch, I am able to see more messages on the boot console in KVM guests than I can without, when keep_bootcon is specified. I think it is appropriate for the relevant -stable trees. However, it's more of an annoyance than a serious bug (ideally you don't need to keep the boot console around as console handover should be working -- I was encountering a situation where the console handover wasn't working and not having the boot console available meant I couldn't see why). Signed-off-by: Nishanth Aravamudan Cc: David S. Miller Cc: Alan Cox Cc: Greg KH Acked-by: Fabio M. Di Nitto Cc: [2.6.39.x, 3.0.x] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/printk.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/printk.c b/kernel/printk.c index 836a2ae0ac31..28a40d8171b8 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -1604,7 +1604,7 @@ static int __init printk_late_init(void) struct console *con; for_each_console(con) { - if (con->flags & CON_BOOT) { + if (!keep_bootcon && con->flags & CON_BOOT) { printk(KERN_INFO "turn off boot console %s%d\n", con->name, con->index); unregister_console(con); -- cgit v1.2.3-71-gd317 From f5b940997397229975ea073679b03967932a541b Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Fri, 26 Aug 2011 18:03:11 -0400 Subject: All Arch: remove linkage for sys_nfsservctl system call The nfsservctl system call is now gone, so we should remove all linkage for it. Signed-off-by: NeilBrown Signed-off-by: J. Bruce Fields Signed-off-by: Linus Torvalds --- arch/alpha/kernel/systbls.S | 2 +- arch/arm/kernel/calls.S | 2 +- arch/avr32/kernel/syscall_table.S | 2 +- arch/blackfin/mach-common/entry.S | 2 +- arch/cris/arch-v10/kernel/entry.S | 2 +- arch/cris/arch-v32/kernel/entry.S | 2 +- arch/frv/kernel/entry.S | 2 +- arch/h8300/kernel/syscalls.S | 2 +- arch/ia64/kernel/entry.S | 2 +- arch/m32r/kernel/syscall_table.S | 2 +- arch/m68k/kernel/syscalltable.S | 2 +- arch/microblaze/kernel/syscall_table.S | 2 +- arch/mips/kernel/scall32-o32.S | 2 +- arch/mips/kernel/scall64-64.S | 2 +- arch/mips/kernel/scall64-n32.S | 2 +- arch/mips/kernel/scall64-o32.S | 2 +- arch/mn10300/kernel/entry.S | 2 +- arch/s390/kernel/compat_wrapper.S | 6 ------ arch/s390/kernel/syscalls.S | 2 +- arch/sh/kernel/syscalls_32.S | 2 +- arch/sh/kernel/syscalls_64.S | 2 +- arch/sparc/kernel/sys32.S | 1 - arch/sparc/kernel/systbls_32.S | 2 +- arch/sparc/kernel/systbls_64.S | 2 +- arch/x86/ia32/ia32entry.S | 2 +- arch/x86/include/asm/unistd_64.h | 2 +- arch/x86/kernel/syscall_table_32.S | 2 +- arch/xtensa/include/asm/unistd.h | 2 +- fs/compat.c | 5 ----- include/asm-generic/unistd.h | 2 +- include/linux/compat.h | 1 - include/linux/syscalls.h | 3 --- kernel/sys_ni.c | 1 - 33 files changed, 27 insertions(+), 44 deletions(-) (limited to 'kernel') diff --git a/arch/alpha/kernel/systbls.S b/arch/alpha/kernel/systbls.S index b9c28f3f1956..6acea1f96de3 100644 --- a/arch/alpha/kernel/systbls.S +++ b/arch/alpha/kernel/systbls.S @@ -360,7 +360,7 @@ sys_call_table: .quad sys_newuname .quad sys_nanosleep /* 340 */ .quad sys_mremap - .quad sys_nfsservctl + .quad sys_ni_syscall /* old nfsservctl */ .quad sys_setresuid .quad sys_getresuid .quad sys_pciconfig_read /* 345 */ diff --git a/arch/arm/kernel/calls.S b/arch/arm/kernel/calls.S index 80f7896cc016..9943e9e74a1b 100644 --- a/arch/arm/kernel/calls.S +++ b/arch/arm/kernel/calls.S @@ -178,7 +178,7 @@ CALL(sys_ni_syscall) /* vm86 */ CALL(sys_ni_syscall) /* was sys_query_module */ CALL(sys_poll) - CALL(sys_nfsservctl) + CALL(sys_ni_syscall) /* was nfsservctl */ /* 170 */ CALL(sys_setresgid16) CALL(sys_getresgid16) CALL(sys_prctl) diff --git a/arch/avr32/kernel/syscall_table.S b/arch/avr32/kernel/syscall_table.S index c7fd394d28a4..6eba53530d1c 100644 --- a/arch/avr32/kernel/syscall_table.S +++ b/arch/avr32/kernel/syscall_table.S @@ -158,7 +158,7 @@ sys_call_table: .long sys_sched_rr_get_interval .long sys_nanosleep .long sys_poll - .long sys_nfsservctl /* 145 */ + .long sys_ni_syscall /* 145 was nfsservctl */ .long sys_setresgid .long sys_getresgid .long sys_prctl diff --git a/arch/blackfin/mach-common/entry.S b/arch/blackfin/mach-common/entry.S index 225d311c9701..e4137297b790 100644 --- a/arch/blackfin/mach-common/entry.S +++ b/arch/blackfin/mach-common/entry.S @@ -1543,7 +1543,7 @@ ENTRY(_sys_call_table) .long _sys_ni_syscall /* for vm86 */ .long _sys_ni_syscall /* old "query_module" */ .long _sys_ni_syscall /* sys_poll */ - .long _sys_nfsservctl + .long _sys_ni_syscall /* old nfsservctl */ .long _sys_setresgid /* setresgid16 */ /* 170 */ .long _sys_getresgid /* getresgid16 */ .long _sys_prctl diff --git a/arch/cris/arch-v10/kernel/entry.S b/arch/cris/arch-v10/kernel/entry.S index 1161883eb582..592fbe9dfb62 100644 --- a/arch/cris/arch-v10/kernel/entry.S +++ b/arch/cris/arch-v10/kernel/entry.S @@ -771,7 +771,7 @@ sys_call_table: .long sys_ni_syscall /* sys_vm86 */ .long sys_ni_syscall /* Old sys_query_module */ .long sys_poll - .long sys_nfsservctl + .long sys_ni_syscall /* old nfsservctl */ .long sys_setresgid16 /* 170 */ .long sys_getresgid16 .long sys_prctl diff --git a/arch/cris/arch-v32/kernel/entry.S b/arch/cris/arch-v32/kernel/entry.S index 84fed7e91ada..c3ea4694fbaf 100644 --- a/arch/cris/arch-v32/kernel/entry.S +++ b/arch/cris/arch-v32/kernel/entry.S @@ -714,7 +714,7 @@ sys_call_table: .long sys_ni_syscall /* sys_vm86 */ .long sys_ni_syscall /* Old sys_query_module */ .long sys_poll - .long sys_nfsservctl + .long sys_ni_syscall /* Old nfsservctl */ .long sys_setresgid16 /* 170 */ .long sys_getresgid16 .long sys_prctl diff --git a/arch/frv/kernel/entry.S b/arch/frv/kernel/entry.S index 017d6d7b784f..5ba23f715ea5 100644 --- a/arch/frv/kernel/entry.S +++ b/arch/frv/kernel/entry.S @@ -1358,7 +1358,7 @@ sys_call_table: .long sys_ni_syscall /* for vm86 */ .long sys_ni_syscall /* Old sys_query_module */ .long sys_poll - .long sys_nfsservctl + .long sys_ni_syscall /* Old nfsservctl */ .long sys_setresgid16 /* 170 */ .long sys_getresgid16 .long sys_prctl diff --git a/arch/h8300/kernel/syscalls.S b/arch/h8300/kernel/syscalls.S index f4b2e67bcc34..4be2ea2fbe26 100644 --- a/arch/h8300/kernel/syscalls.S +++ b/arch/h8300/kernel/syscalls.S @@ -183,7 +183,7 @@ SYMBOL_NAME_LABEL(sys_call_table) .long SYMBOL_NAME(sys_ni_syscall) /* for vm86 */ .long SYMBOL_NAME(sys_ni_syscall) /* sys_query_module */ .long SYMBOL_NAME(sys_poll) - .long SYMBOL_NAME(sys_nfsservctl) + .long SYMBOL_NAME(sys_ni_syscall) /* old nfsservctl */ .long SYMBOL_NAME(sys_setresgid16) /* 170 */ .long SYMBOL_NAME(sys_getresgid16) .long SYMBOL_NAME(sys_prctl) diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S index 97dd2abdeb1a..198c753d1006 100644 --- a/arch/ia64/kernel/entry.S +++ b/arch/ia64/kernel/entry.S @@ -1614,7 +1614,7 @@ sys_call_table: data8 sys_sched_get_priority_min data8 sys_sched_rr_get_interval data8 sys_nanosleep - data8 sys_nfsservctl + data8 sys_ni_syscall // old nfsservctl data8 sys_prctl // 1170 data8 sys_getpagesize data8 sys_mmap2 diff --git a/arch/m32r/kernel/syscall_table.S b/arch/m32r/kernel/syscall_table.S index 528f2e6ad064..f365c19795ef 100644 --- a/arch/m32r/kernel/syscall_table.S +++ b/arch/m32r/kernel/syscall_table.S @@ -168,7 +168,7 @@ ENTRY(sys_call_table) .long sys_tas /* vm86 syscall holder */ .long sys_ni_syscall /* query_module syscall holder */ .long sys_poll - .long sys_nfsservctl + .long sys_ni_syscall /* was nfsservctl */ .long sys_setresgid /* 170 */ .long sys_getresgid .long sys_prctl diff --git a/arch/m68k/kernel/syscalltable.S b/arch/m68k/kernel/syscalltable.S index 00d1452f9571..c468f2edaa85 100644 --- a/arch/m68k/kernel/syscalltable.S +++ b/arch/m68k/kernel/syscalltable.S @@ -189,7 +189,7 @@ ENTRY(sys_call_table) .long sys_getpagesize .long sys_ni_syscall /* old "query_module" */ .long sys_poll - .long sys_nfsservctl + .long sys_ni_syscall /* old nfsservctl */ .long sys_setresgid16 /* 170 */ .long sys_getresgid16 .long sys_prctl diff --git a/arch/microblaze/kernel/syscall_table.S b/arch/microblaze/kernel/syscall_table.S index d915a122c865..8789daa2a346 100644 --- a/arch/microblaze/kernel/syscall_table.S +++ b/arch/microblaze/kernel/syscall_table.S @@ -173,7 +173,7 @@ ENTRY(sys_call_table) .long sys_ni_syscall /* sys_vm86 */ .long sys_ni_syscall /* Old sys_query_module */ .long sys_poll - .long sys_nfsservctl + .long sys_ni_syscall /* old nfsservctl */ .long sys_setresgid /* 170 */ .long sys_getresgid .long sys_prctl diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S index e521420a45a5..865bc7a6f5a1 100644 --- a/arch/mips/kernel/scall32-o32.S +++ b/arch/mips/kernel/scall32-o32.S @@ -424,7 +424,7 @@ einval: li v0, -ENOSYS sys sys_getresuid 3 sys sys_ni_syscall 0 /* was sys_query_module */ sys sys_poll 3 - sys sys_nfsservctl 3 + sys sys_ni_syscall 0 /* was nfsservctl */ sys sys_setresgid 3 /* 4190 */ sys sys_getresgid 3 sys sys_prctl 5 diff --git a/arch/mips/kernel/scall64-64.S b/arch/mips/kernel/scall64-64.S index 85874d6a8a70..fb7334bea731 100644 --- a/arch/mips/kernel/scall64-64.S +++ b/arch/mips/kernel/scall64-64.S @@ -299,7 +299,7 @@ sys_call_table: PTR sys_ni_syscall /* 5170, was get_kernel_syms */ PTR sys_ni_syscall /* was query_module */ PTR sys_quotactl - PTR sys_nfsservctl + PTR sys_ni_syscall /* was nfsservctl */ PTR sys_ni_syscall /* res. for getpmsg */ PTR sys_ni_syscall /* 5175 for putpmsg */ PTR sys_ni_syscall /* res. for afs_syscall */ diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S index b85842fc87ae..f9296e894e46 100644 --- a/arch/mips/kernel/scall64-n32.S +++ b/arch/mips/kernel/scall64-n32.S @@ -294,7 +294,7 @@ EXPORT(sysn32_call_table) PTR sys_ni_syscall /* 6170, was get_kernel_syms */ PTR sys_ni_syscall /* was query_module */ PTR sys_quotactl - PTR compat_sys_nfsservctl + PTR sys_ni_syscall /* was nfsservctl */ PTR sys_ni_syscall /* res. for getpmsg */ PTR sys_ni_syscall /* 6175 for putpmsg */ PTR sys_ni_syscall /* res. for afs_syscall */ diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S index 46c4763edf21..4d7c9827706f 100644 --- a/arch/mips/kernel/scall64-o32.S +++ b/arch/mips/kernel/scall64-o32.S @@ -392,7 +392,7 @@ sys_call_table: PTR sys_getresuid PTR sys_ni_syscall /* was query_module */ PTR sys_poll - PTR compat_sys_nfsservctl + PTR sys_ni_syscall /* was nfsservctl */ PTR sys_setresgid /* 4190 */ PTR sys_getresgid PTR sys_prctl diff --git a/arch/mn10300/kernel/entry.S b/arch/mn10300/kernel/entry.S index ae435e1d5669..3e3620d9fc45 100644 --- a/arch/mn10300/kernel/entry.S +++ b/arch/mn10300/kernel/entry.S @@ -589,7 +589,7 @@ ENTRY(sys_call_table) .long sys_ni_syscall /* vm86 */ .long sys_ni_syscall /* Old sys_query_module */ .long sys_poll - .long sys_nfsservctl + .long sys_ni_syscall /* was nfsservctl */ .long sys_setresgid16 /* 170 */ .long sys_getresgid16 .long sys_prctl diff --git a/arch/s390/kernel/compat_wrapper.S b/arch/s390/kernel/compat_wrapper.S index 08ab9aa6a0d5..7526db6bf501 100644 --- a/arch/s390/kernel/compat_wrapper.S +++ b/arch/s390/kernel/compat_wrapper.S @@ -665,12 +665,6 @@ ENTRY(sys32_poll_wrapper) lgfr %r4,%r4 # long jg sys_poll # branch to system call -ENTRY(compat_sys_nfsservctl_wrapper) - lgfr %r2,%r2 # int - llgtr %r3,%r3 # struct compat_nfsctl_arg* - llgtr %r4,%r4 # union compat_nfsctl_res* - jg compat_sys_nfsservctl # branch to system call - ENTRY(sys32_setresgid16_wrapper) llgfr %r2,%r2 # __kernel_old_gid_emu31_t llgfr %r3,%r3 # __kernel_old_gid_emu31_t diff --git a/arch/s390/kernel/syscalls.S b/arch/s390/kernel/syscalls.S index 6ee39ef8fe4a..73eb08c874fb 100644 --- a/arch/s390/kernel/syscalls.S +++ b/arch/s390/kernel/syscalls.S @@ -177,7 +177,7 @@ SYSCALL(sys_getresuid16,sys_ni_syscall,sys32_getresuid16_wrapper) /* 165 old get NI_SYSCALL /* for vm86 */ NI_SYSCALL /* old sys_query_module */ SYSCALL(sys_poll,sys_poll,sys32_poll_wrapper) -SYSCALL(sys_nfsservctl,sys_nfsservctl,compat_sys_nfsservctl_wrapper) +NI_SYSCALL /* old nfsservctl */ SYSCALL(sys_setresgid16,sys_ni_syscall,sys32_setresgid16_wrapper) /* 170 old setresgid16 syscall */ SYSCALL(sys_getresgid16,sys_ni_syscall,sys32_getresgid16_wrapper) /* old getresgid16 syscall */ SYSCALL(sys_prctl,sys_prctl,sys32_prctl_wrapper) diff --git a/arch/sh/kernel/syscalls_32.S b/arch/sh/kernel/syscalls_32.S index 39b051de4c7c..293e39c59c00 100644 --- a/arch/sh/kernel/syscalls_32.S +++ b/arch/sh/kernel/syscalls_32.S @@ -185,7 +185,7 @@ ENTRY(sys_call_table) .long sys_ni_syscall /* vm86 */ .long sys_ni_syscall /* old "query_module" */ .long sys_poll - .long sys_nfsservctl + .long sys_ni_syscall /* was nfsservctl */ .long sys_setresgid16 /* 170 */ .long sys_getresgid16 .long sys_prctl diff --git a/arch/sh/kernel/syscalls_64.S b/arch/sh/kernel/syscalls_64.S index 089c4d825d08..ceb34b94afa9 100644 --- a/arch/sh/kernel/syscalls_64.S +++ b/arch/sh/kernel/syscalls_64.S @@ -189,7 +189,7 @@ sys_call_table: .long sys_ni_syscall /* vm86 */ .long sys_ni_syscall /* old "query_module" */ .long sys_poll - .long sys_nfsservctl + .long sys_ni_syscall /* was nfsservctl */ .long sys_setresgid16 /* 170 */ .long sys_getresgid16 .long sys_prctl diff --git a/arch/sparc/kernel/sys32.S b/arch/sparc/kernel/sys32.S index 44e5faf1ad5f..d97f3eb72e06 100644 --- a/arch/sparc/kernel/sys32.S +++ b/arch/sparc/kernel/sys32.S @@ -81,7 +81,6 @@ SIGN2(sys32_fadvise64, compat_sys_fadvise64, %o0, %o4) SIGN2(sys32_fadvise64_64, compat_sys_fadvise64_64, %o0, %o5) SIGN2(sys32_bdflush, sys_bdflush, %o0, %o1) SIGN1(sys32_mlockall, sys_mlockall, %o0) -SIGN1(sys32_nfsservctl, compat_sys_nfsservctl, %o0) SIGN1(sys32_clock_nanosleep, compat_sys_clock_nanosleep, %o1) SIGN1(sys32_timer_settime, compat_sys_timer_settime, %o1) SIGN1(sys32_io_submit, compat_sys_io_submit, %o1) diff --git a/arch/sparc/kernel/systbls_32.S b/arch/sparc/kernel/systbls_32.S index 6e492d59f6b1..09d8ec454450 100644 --- a/arch/sparc/kernel/systbls_32.S +++ b/arch/sparc/kernel/systbls_32.S @@ -67,7 +67,7 @@ sys_call_table: /*235*/ .long sys_fstatfs64, sys_llseek, sys_mlock, sys_munlock, sys_mlockall /*240*/ .long sys_munlockall, sys_sched_setparam, sys_sched_getparam, sys_sched_setscheduler, sys_sched_getscheduler /*245*/ .long sys_sched_yield, sys_sched_get_priority_max, sys_sched_get_priority_min, sys_sched_rr_get_interval, sys_nanosleep -/*250*/ .long sys_mremap, sys_sysctl, sys_getsid, sys_fdatasync, sys_nfsservctl +/*250*/ .long sys_mremap, sys_sysctl, sys_getsid, sys_fdatasync, sys_ni_syscall /*255*/ .long sys_sync_file_range, sys_clock_settime, sys_clock_gettime, sys_clock_getres, sys_clock_nanosleep /*260*/ .long sys_sched_getaffinity, sys_sched_setaffinity, sys_timer_settime, sys_timer_gettime, sys_timer_getoverrun /*265*/ .long sys_timer_delete, sys_timer_create, sys_nis_syscall, sys_io_setup, sys_io_destroy diff --git a/arch/sparc/kernel/systbls_64.S b/arch/sparc/kernel/systbls_64.S index f566518483b5..c9296ab0b1f4 100644 --- a/arch/sparc/kernel/systbls_64.S +++ b/arch/sparc/kernel/systbls_64.S @@ -145,7 +145,7 @@ sys_call_table: .word sys_fstatfs64, sys_llseek, sys_mlock, sys_munlock, sys_mlockall /*240*/ .word sys_munlockall, sys_sched_setparam, sys_sched_getparam, sys_sched_setscheduler, sys_sched_getscheduler .word sys_sched_yield, sys_sched_get_priority_max, sys_sched_get_priority_min, sys_sched_rr_get_interval, sys_nanosleep -/*250*/ .word sys_64_mremap, sys_sysctl, sys_getsid, sys_fdatasync, sys_nfsservctl +/*250*/ .word sys_64_mremap, sys_sysctl, sys_getsid, sys_fdatasync, sys_nis_syscall .word sys_sync_file_range, sys_clock_settime, sys_clock_gettime, sys_clock_getres, sys_clock_nanosleep /*260*/ .word sys_sched_getaffinity, sys_sched_setaffinity, sys_timer_settime, sys_timer_gettime, sys_timer_getoverrun .word sys_timer_delete, sys_timer_create, sys_ni_syscall, sys_io_setup, sys_io_destroy diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index a0e866d233ee..54edb207ff3a 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -672,7 +672,7 @@ ia32_sys_call_table: .quad sys32_vm86_warning /* vm86 */ .quad quiet_ni_syscall /* query_module */ .quad sys_poll - .quad compat_sys_nfsservctl + .quad quiet_ni_syscall /* old nfsservctl */ .quad sys_setresgid16 /* 170 */ .quad sys_getresgid16 .quad sys_prctl diff --git a/arch/x86/include/asm/unistd_64.h b/arch/x86/include/asm/unistd_64.h index d92641cc7acc..201040573444 100644 --- a/arch/x86/include/asm/unistd_64.h +++ b/arch/x86/include/asm/unistd_64.h @@ -414,7 +414,7 @@ __SYSCALL(__NR_query_module, sys_ni_syscall) __SYSCALL(__NR_quotactl, sys_quotactl) #define __NR_nfsservctl 180 -__SYSCALL(__NR_nfsservctl, sys_nfsservctl) +__SYSCALL(__NR_nfsservctl, sys_ni_syscall) /* reserved for LiS/STREAMS */ #define __NR_getpmsg 181 diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S index fbb0a045a1a2..bc19be332bc9 100644 --- a/arch/x86/kernel/syscall_table_32.S +++ b/arch/x86/kernel/syscall_table_32.S @@ -168,7 +168,7 @@ ENTRY(sys_call_table) .long ptregs_vm86 .long sys_ni_syscall /* Old sys_query_module */ .long sys_poll - .long sys_nfsservctl + .long sys_ni_syscall /* Old nfsservctl */ .long sys_setresgid16 /* 170 */ .long sys_getresgid16 .long sys_prctl diff --git a/arch/xtensa/include/asm/unistd.h b/arch/xtensa/include/asm/unistd.h index a6f934f37f1a..798ee6d285a1 100644 --- a/arch/xtensa/include/asm/unistd.h +++ b/arch/xtensa/include/asm/unistd.h @@ -455,7 +455,7 @@ __SYSCALL(203, sys_reboot, 3) #define __NR_quotactl 204 __SYSCALL(204, sys_quotactl, 4) #define __NR_nfsservctl 205 -__SYSCALL(205, sys_nfsservctl, 3) +__SYSCALL(205, sys_ni_syscall, 0) #define __NR__sysctl 206 __SYSCALL(206, sys_sysctl, 1) #define __NR_bdflush 207 diff --git a/fs/compat.c b/fs/compat.c index 0b48d018e38a..58b1da459893 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -1675,11 +1675,6 @@ asmlinkage long compat_sys_ppoll(struct pollfd __user *ufds, } #endif /* HAVE_SET_RESTORE_SIGMASK */ -long asmlinkage compat_sys_nfsservctl(int cmd, void *notused, void *notused2) -{ - return sys_ni_syscall(); -} - #ifdef CONFIG_EPOLL #ifdef HAVE_SET_RESTORE_SIGMASK diff --git a/include/asm-generic/unistd.h b/include/asm-generic/unistd.h index 4f76959397fa..f4c38d8c6674 100644 --- a/include/asm-generic/unistd.h +++ b/include/asm-generic/unistd.h @@ -143,7 +143,7 @@ __SYSCALL(__NR_pivot_root, sys_pivot_root) /* fs/nfsctl.c */ #define __NR_nfsservctl 42 -__SC_COMP(__NR_nfsservctl, sys_nfsservctl, compat_sys_nfsservctl) +__SYSCALL(__NR_nfsservctl, sys_ni_syscall) /* fs/open.c */ #define __NR3264_statfs 43 diff --git a/include/linux/compat.h b/include/linux/compat.h index 8779405e15a8..c6e7523bf765 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -438,7 +438,6 @@ asmlinkage long compat_sys_ppoll(struct pollfd __user *ufds, struct compat_timespec __user *tsp, const compat_sigset_t __user *sigmask, compat_size_t sigsetsize); -asmlinkage long compat_sys_nfsservctl(int cmd, void *notused, void *notused2); asmlinkage long compat_sys_signalfd4(int ufd, const compat_sigset_t __user *sigmask, compat_size_t sigsetsize, int flags); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 8c03b98df5f9..1ff0ec2a5e8d 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -702,9 +702,6 @@ asmlinkage long sys_sysctl(struct __sysctl_args __user *args); asmlinkage long sys_sysinfo(struct sysinfo __user *info); asmlinkage long sys_sysfs(int option, unsigned long arg1, unsigned long arg2); -asmlinkage long sys_nfsservctl(int cmd, - struct nfsctl_arg __user *arg, - void __user *res); asmlinkage long sys_syslog(int type, char __user *buf, int len); asmlinkage long sys_uselib(const char __user *library); asmlinkage long sys_ni_syscall(void); diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index 62cbc8877fef..a9a5de07c4f1 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -16,7 +16,6 @@ asmlinkage long sys_ni_syscall(void) return -ENOSYS; } -cond_syscall(sys_nfsservctl); cond_syscall(sys_quotactl); cond_syscall(sys32_quotactl); cond_syscall(sys_acct); -- cgit v1.2.3-71-gd317 From c259e01a1ec90063042f758e409cd26b2a0963c8 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 22 Jun 2011 19:47:00 +0200 Subject: sched: Separate the scheduler entry for preemption Block-IO and workqueues call into notifier functions from the scheduler core code with interrupts and preemption disabled. These calls should be made before entering the scheduler core. To simplify this, separate the scheduler core code into __schedule(). __schedule() is directly called from the places which set PREEMPT_ACTIVE and from schedule(). This allows us to add the work checks into schedule(), so they are only called when a task voluntary goes to sleep. Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra Cc: Tejun Heo Cc: Jens Axboe Cc: Linus Torvalds Cc: stable@kernel.org # 2.6.39+ Link: http://lkml.kernel.org/r/20110622174918.813258321@linutronix.de Signed-off-by: Ingo Molnar --- kernel/sched.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/kernel/sched.c b/kernel/sched.c index ccacdbdecf45..ec15e8129cf7 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -4279,9 +4279,9 @@ pick_next_task(struct rq *rq) } /* - * schedule() is the main scheduler function. + * __schedule() is the main scheduler function. */ -asmlinkage void __sched schedule(void) +static void __sched __schedule(void) { struct task_struct *prev, *next; unsigned long *switch_count; @@ -4369,6 +4369,11 @@ need_resched: if (need_resched()) goto need_resched; } + +asmlinkage void schedule(void) +{ + __schedule(); +} EXPORT_SYMBOL(schedule); #ifdef CONFIG_MUTEX_SPIN_ON_OWNER @@ -4435,7 +4440,7 @@ asmlinkage void __sched notrace preempt_schedule(void) do { add_preempt_count_notrace(PREEMPT_ACTIVE); - schedule(); + __schedule(); sub_preempt_count_notrace(PREEMPT_ACTIVE); /* @@ -4463,7 +4468,7 @@ asmlinkage void __sched preempt_schedule_irq(void) do { add_preempt_count(PREEMPT_ACTIVE); local_irq_enable(); - schedule(); + __schedule(); local_irq_disable(); sub_preempt_count(PREEMPT_ACTIVE); @@ -5588,7 +5593,7 @@ static inline int should_resched(void) static void __cond_resched(void) { add_preempt_count(PREEMPT_ACTIVE); - schedule(); + __schedule(); sub_preempt_count(PREEMPT_ACTIVE); } -- cgit v1.2.3-71-gd317 From 9c40cef2b799f9b5e7fa5de4d2ad3a0168ba118c Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 22 Jun 2011 19:47:01 +0200 Subject: sched: Move blk_schedule_flush_plug() out of __schedule() There is no real reason to run blk_schedule_flush_plug() with interrupts and preemption disabled. Move it into schedule() and call it when the task is going voluntarily to sleep. There might be false positives when the task is woken between that call and actually scheduling, but that's not really different from being woken immediately after switching away. This fixes a deadlock in the scheduler where the blk_schedule_flush_plug() callchain enables interrupts and thereby allows a wakeup to happen of the task that's going to sleep. Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra Cc: Tejun Heo Cc: Jens Axboe Cc: Linus Torvalds Cc: stable@kernel.org # 2.6.39+ Link: http://lkml.kernel.org/n/tip-dwfxtra7yg1b5r65m32ywtct@git.kernel.org Signed-off-by: Ingo Molnar --- kernel/sched.c | 25 +++++++++++++++---------- 1 file changed, 15 insertions(+), 10 deletions(-) (limited to 'kernel') diff --git a/kernel/sched.c b/kernel/sched.c index ec15e8129cf7..511732c39b6e 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -4322,16 +4322,6 @@ need_resched: if (to_wakeup) try_to_wake_up_local(to_wakeup); } - - /* - * If we are going to sleep and we have plugged IO - * queued, make sure to submit it to avoid deadlocks. - */ - if (blk_needs_flush_plug(prev)) { - raw_spin_unlock(&rq->lock); - blk_schedule_flush_plug(prev); - raw_spin_lock(&rq->lock); - } } switch_count = &prev->nvcsw; } @@ -4370,8 +4360,23 @@ need_resched: goto need_resched; } +static inline void sched_submit_work(struct task_struct *tsk) +{ + if (!tsk->state) + return; + /* + * If we are going to sleep and we have plugged IO queued, + * make sure to submit it to avoid deadlocks. + */ + if (blk_needs_flush_plug(tsk)) + blk_schedule_flush_plug(tsk); +} + asmlinkage void schedule(void) { + struct task_struct *tsk = current; + + sched_submit_work(tsk); __schedule(); } EXPORT_SYMBOL(schedule); -- cgit v1.2.3-71-gd317 From feff8fa0075bdfd43c841e9d689ed81adda988d6 Mon Sep 17 00:00:00 2001 From: WANG Cong Date: Thu, 18 Aug 2011 20:36:57 +0800 Subject: sched: Fix a memory leak in __sdt_free() This patch fixes the following memory leak: unreferenced object 0xffff880107266800 (size 512): comm "sched-powersave", pid 3718, jiffies 4323097853 (age 27495.450s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [] create_object+0x187/0x28b [] kmemleak_alloc+0x73/0x98 [] __kmalloc_node+0x104/0x159 [] kzalloc_node.clone.97+0x15/0x17 [] build_sched_domains+0xb7/0x7f3 [] partition_sched_domains+0x1db/0x24a [] do_rebuild_sched_domains+0x3b/0x47 [] rebuild_sched_domains+0x10/0x12 [] sched_power_savings_store+0x6c/0x7b [] sched_mc_power_savings_store+0x16/0x18 [] sysdev_class_store+0x20/0x22 [] sysfs_write_file+0x108/0x144 [] vfs_write+0xaf/0x102 [] sys_write+0x4d/0x74 [] system_call_fastpath+0x16/0x1b [] 0xffffffffffffffff Signed-off-by: WANG Cong Signed-off-by: Peter Zijlstra Cc: stable@kernel.org # 3.0 Link: http://lkml.kernel.org/r/1313671017-4112-1-git-send-email-amwang@redhat.com Signed-off-by: Ingo Molnar --- kernel/sched.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/sched.c b/kernel/sched.c index 511732c39b6e..c79e7c63a4aa 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -7453,6 +7453,7 @@ static void __sdt_free(const struct cpumask *cpu_map) struct sched_domain *sd = *per_cpu_ptr(sdd->sd, j); if (sd && (sd->flags & SD_OVERLAP)) free_sched_groups(sd->groups, 0); + kfree(*per_cpu_ptr(sdd->sd, j)); kfree(*per_cpu_ptr(sdd->sg, j)); kfree(*per_cpu_ptr(sdd->sgp, j)); } -- cgit v1.2.3-71-gd317 From a8d757ef076f0f95f13a918808824058de25b3eb Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Thu, 25 Aug 2011 15:58:03 +0200 Subject: perf events: Fix slow and broken cgroup context switch code The current cgroup context switch code was incorrect leading to bogus counts. Furthermore, as soon as there was an active cgroup event on a CPU, the context switch cost on that CPU would increase by a significant amount as demonstrated by a simple ping/pong example: $ ./pong Both processes pinned to CPU1, running for 10s 10684.51 ctxsw/s Now start a cgroup perf stat: $ perf stat -e cycles,cycles -A -a -G test -C 1 -- sleep 100 $ ./pong Both processes pinned to CPU1, running for 10s 6674.61 ctxsw/s That's a 37% penalty. Note that pong is not even in the monitored cgroup. The results shown by perf stat are bogus: $ perf stat -e cycles,cycles -A -a -G test -C 1 -- sleep 100 Performance counter stats for 'sleep 100': CPU1 cycles test CPU1 16,984,189,138 cycles # 0.000 GHz The second 'cycles' event should report a count @ CPU clock (here 2.4GHz) as it is counting across all cgroups. The patch below fixes the bogus accounting and bypasses any cgroup switches in case the outgoing and incoming tasks are in the same cgroup. With this patch the same test now yields: $ ./pong Both processes pinned to CPU1, running for 10s 10775.30 ctxsw/s Start perf stat with cgroup: $ perf stat -e cycles,cycles -A -a -G test -C 1 -- sleep 10 Run pong outside the cgroup: $ /pong Both processes pinned to CPU1, running for 10s 10687.80 ctxsw/s The penalty is now less than 2%. And the results for perf stat are correct: $ perf stat -e cycles,cycles -A -a -G test -C 1 -- sleep 10 Performance counter stats for 'sleep 10': CPU1 cycles test # 0.000 GHz CPU1 23,933,981,448 cycles # 0.000 GHz Now perf stat reports the correct counts for for the non cgroup event. If we run pong inside the cgroup, then we also get the correct counts: $ perf stat -e cycles,cycles -A -a -G test -C 1 -- sleep 10 Performance counter stats for 'sleep 10': CPU1 22,297,726,205 cycles test # 0.000 GHz CPU1 23,933,981,448 cycles # 0.000 GHz 10.001457237 seconds time elapsed Signed-off-by: Stephane Eranian Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/20110825135803.GA4697@quad Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 24 +++++++++++------- kernel/events/core.c | 63 ++++++++++++++++++++++++++++++++++++++-------- kernel/sched.c | 2 +- 3 files changed, 69 insertions(+), 20 deletions(-) (limited to 'kernel') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 245bafdafd5e..c816075c01ce 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -944,8 +944,10 @@ extern void perf_pmu_unregister(struct pmu *pmu); extern int perf_num_counters(void); extern const char *perf_pmu_name(void); -extern void __perf_event_task_sched_in(struct task_struct *task); -extern void __perf_event_task_sched_out(struct task_struct *task, struct task_struct *next); +extern void __perf_event_task_sched_in(struct task_struct *prev, + struct task_struct *task); +extern void __perf_event_task_sched_out(struct task_struct *prev, + struct task_struct *next); extern int perf_event_init_task(struct task_struct *child); extern void perf_event_exit_task(struct task_struct *child); extern void perf_event_free_task(struct task_struct *task); @@ -1059,17 +1061,20 @@ perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr) extern struct jump_label_key perf_sched_events; -static inline void perf_event_task_sched_in(struct task_struct *task) +static inline void perf_event_task_sched_in(struct task_struct *prev, + struct task_struct *task) { if (static_branch(&perf_sched_events)) - __perf_event_task_sched_in(task); + __perf_event_task_sched_in(prev, task); } -static inline void perf_event_task_sched_out(struct task_struct *task, struct task_struct *next) +static inline void perf_event_task_sched_out(struct task_struct *prev, + struct task_struct *next) { perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, NULL, 0); - __perf_event_task_sched_out(task, next); + if (static_branch(&perf_sched_events)) + __perf_event_task_sched_out(prev, next); } extern void perf_event_mmap(struct vm_area_struct *vma); @@ -1139,10 +1144,11 @@ extern void perf_event_disable(struct perf_event *event); extern void perf_event_task_tick(void); #else static inline void -perf_event_task_sched_in(struct task_struct *task) { } +perf_event_task_sched_in(struct task_struct *prev, + struct task_struct *task) { } static inline void -perf_event_task_sched_out(struct task_struct *task, - struct task_struct *next) { } +perf_event_task_sched_out(struct task_struct *prev, + struct task_struct *next) { } static inline int perf_event_init_task(struct task_struct *child) { return 0; } static inline void perf_event_exit_task(struct task_struct *child) { } static inline void perf_event_free_task(struct task_struct *task) { } diff --git a/kernel/events/core.c b/kernel/events/core.c index b8785e26ee1c..45847fbb599a 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -399,14 +399,54 @@ void perf_cgroup_switch(struct task_struct *task, int mode) local_irq_restore(flags); } -static inline void perf_cgroup_sched_out(struct task_struct *task) +static inline void perf_cgroup_sched_out(struct task_struct *task, + struct task_struct *next) { - perf_cgroup_switch(task, PERF_CGROUP_SWOUT); + struct perf_cgroup *cgrp1; + struct perf_cgroup *cgrp2 = NULL; + + /* + * we come here when we know perf_cgroup_events > 0 + */ + cgrp1 = perf_cgroup_from_task(task); + + /* + * next is NULL when called from perf_event_enable_on_exec() + * that will systematically cause a cgroup_switch() + */ + if (next) + cgrp2 = perf_cgroup_from_task(next); + + /* + * only schedule out current cgroup events if we know + * that we are switching to a different cgroup. Otherwise, + * do no touch the cgroup events. + */ + if (cgrp1 != cgrp2) + perf_cgroup_switch(task, PERF_CGROUP_SWOUT); } -static inline void perf_cgroup_sched_in(struct task_struct *task) +static inline void perf_cgroup_sched_in(struct task_struct *prev, + struct task_struct *task) { - perf_cgroup_switch(task, PERF_CGROUP_SWIN); + struct perf_cgroup *cgrp1; + struct perf_cgroup *cgrp2 = NULL; + + /* + * we come here when we know perf_cgroup_events > 0 + */ + cgrp1 = perf_cgroup_from_task(task); + + /* prev can never be NULL */ + cgrp2 = perf_cgroup_from_task(prev); + + /* + * only need to schedule in cgroup events if we are changing + * cgroup during ctxsw. Cgroup events were not scheduled + * out of ctxsw out if that was not the case. + */ + if (cgrp1 != cgrp2) + perf_cgroup_switch(task, PERF_CGROUP_SWIN); } static inline int perf_cgroup_connect(int fd, struct perf_event *event, @@ -518,11 +558,13 @@ static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx) { } -static inline void perf_cgroup_sched_out(struct task_struct *task) +static inline void perf_cgroup_sched_out(struct task_struct *task, + struct task_struct *next) { } -static inline void perf_cgroup_sched_in(struct task_struct *task) +static inline void perf_cgroup_sched_in(struct task_struct *prev, + struct task_struct *task) { } @@ -1988,7 +2030,7 @@ void __perf_event_task_sched_out(struct task_struct *task, * cgroup event are system-wide mode only */ if (atomic_read(&__get_cpu_var(perf_cgroup_events))) - perf_cgroup_sched_out(task); + perf_cgroup_sched_out(task, next); } static void task_ctx_sched_out(struct perf_event_context *ctx) @@ -2153,7 +2195,8 @@ static void perf_event_context_sched_in(struct perf_event_context *ctx, * accessing the event control register. If a NMI hits, then it will * keep the event running. */ -void __perf_event_task_sched_in(struct task_struct *task) +void __perf_event_task_sched_in(struct task_struct *prev, + struct task_struct *task) { struct perf_event_context *ctx; int ctxn; @@ -2171,7 +2214,7 @@ void __perf_event_task_sched_in(struct task_struct *task) * cgroup event are system-wide mode only */ if (atomic_read(&__get_cpu_var(perf_cgroup_events))) - perf_cgroup_sched_in(task); + perf_cgroup_sched_in(prev, task); } static u64 perf_calculate_period(struct perf_event *event, u64 nsec, u64 count) @@ -2427,7 +2470,7 @@ static void perf_event_enable_on_exec(struct perf_event_context *ctx) * ctxswin cgroup events which are already scheduled * in. */ - perf_cgroup_sched_out(current); + perf_cgroup_sched_out(current, NULL); raw_spin_lock(&ctx->lock); task_ctx_sched_out(ctx); diff --git a/kernel/sched.c b/kernel/sched.c index ccacdbdecf45..0408cdc6d572 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -3065,7 +3065,7 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev) #ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW local_irq_disable(); #endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */ - perf_event_task_sched_in(current); + perf_event_task_sched_in(prev, current); #ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW local_irq_enable(); #endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */ -- cgit v1.2.3-71-gd317 From 7f310a5d4e8525ac0cc2f58c973d2100ce034410 Mon Sep 17 00:00:00 2001 From: Eric B Munson Date: Thu, 23 Jun 2011 16:34:38 -0400 Subject: perf_event: Fix broken calc_timer_values() We detected a serious issue with PERF_SAMPLE_READ and timing information when events were being multiplexing. Samples would have time_running > time_enabled. That was easy to reproduce with a libpfm4 example (ran 3 times to cause multiplexing on Core 2): $ syst_smpl -e uops_retired:freq=1 & $ syst_smpl -e uops_retired:freq=1 & $ syst_smpl -e uops_retired:freq=1 & IIP:0x0000000040062d ... PERIOD:2355332948 ENA=40144625315 RUN=60014875184 syst_smpl: WARNING: time_running > time_enabled 63277537998 uops_retired:freq=1 , scaled The bug was not present in kernel up to (and including) 3.0. It turns out the bug was introduced by the following commit: commit c4794295917ebeda8013b6cb9c8d71ab4f74a1fa events: Move lockless timer calculation into helper function The parameters of the function got reversed yet the call sites were not updated to reflect the change. That lead to time_running and time_enabled being swapped. That had no effect when there was no multiplexing because in that case time_running = time_enabled but it would show up in any other scenario. Signed-off-by: Stephane Eranian Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/20110829124112.GA4828@quad Signed-off-by: Ingo Molnar --- kernel/events/core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/events/core.c b/kernel/events/core.c index 45847fbb599a..0f857782d06f 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3396,8 +3396,8 @@ static int perf_event_index(struct perf_event *event) } static void calc_timer_values(struct perf_event *event, - u64 *running, - u64 *enabled) + u64 *enabled, + u64 *running) { u64 now, ctx_time; -- cgit v1.2.3-71-gd317 From ed585a651681e822089087b426e6ebfb6d3d9873 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Sun, 11 Sep 2011 13:59:27 +0200 Subject: genirq: Make irq_shutdown() symmetric vs. irq_startup again If an irq_chip provides .irq_shutdown(), but neither of .irq_disable() or .irq_mask(), free_irq() crashes when jumping to NULL. Fix this by only trying .irq_disable() and .irq_mask() if there's no .irq_shutdown() provided. This revives the symmetry with irq_startup(), which tries .irq_startup(), .irq_enable(), and irq_unmask(), and makes it consistent with the comment for irq_chip.irq_shutdown() in , which says: * @irq_shutdown: shut down the interrupt (defaults to ->disable if NULL) This is also how __free_irq() behaved before the big overhaul, cfr. e.g. 3b56f0585fd4c02d047dc406668cb40159b2d340 ("genirq: Remove bogus conditional"), where the core interrupt code always overrode .irq_shutdown() to .irq_disable() if .irq_shutdown() was NULL. Signed-off-by: Geert Uytterhoeven Cc: linux-m68k@lists.linux-m68k.org Link: http://lkml.kernel.org/r/1315742394-16036-2-git-send-email-geert@linux-m68k.org Cc: stable@kernel.org Signed-off-by: Thomas Gleixner --- kernel/irq/chip.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index d5a3009da71a..dc5114b4c16c 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -178,7 +178,7 @@ void irq_shutdown(struct irq_desc *desc) desc->depth = 1; if (desc->irq_data.chip->irq_shutdown) desc->irq_data.chip->irq_shutdown(&desc->irq_data); - if (desc->irq_data.chip->irq_disable) + else if (desc->irq_data.chip->irq_disable) desc->irq_data.chip->irq_disable(&desc->irq_data); else desc->irq_data.chip->irq_mask(&desc->irq_data); -- cgit v1.2.3-71-gd317 From fa2563e41c3d6d6e8af437643981ed28ae0cb56d Mon Sep 17 00:00:00 2001 From: Thomas Tuttle Date: Wed, 14 Sep 2011 16:22:28 -0700 Subject: workqueue: lock cwq access in drain_workqueue Take cwq->gcwq->lock to avoid racing between drain_workqueue checking to make sure the workqueues are empty and cwq_dec_nr_in_flight decrementing and then incrementing nr_active when it activates a delayed work. We discovered this when a corner case in one of our drivers resulted in us trying to destroy a workqueue in which the remaining work would always requeue itself again in the same workqueue. We would hit this race condition and trip the BUG_ON on workqueue.c:3080. Signed-off-by: Thomas Tuttle Acked-by: Tejun Heo Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/workqueue.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 25fb1b0e53fa..1783aabc6128 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -2412,8 +2412,13 @@ reflush: for_each_cwq_cpu(cpu, wq) { struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq); + bool drained; - if (!cwq->nr_active && list_empty(&cwq->delayed_works)) + spin_lock_irq(&cwq->gcwq->lock); + drained = !cwq->nr_active && list_empty(&cwq->delayed_works); + spin_unlock_irq(&cwq->gcwq->lock); + + if (drained) continue; if (++flush_cnt == 10 || -- cgit v1.2.3-71-gd317 From 1a51410abe7d0ee4b1d112780f46df87d3621043 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 19 Sep 2011 17:04:37 -0700 Subject: Make TASKSTATS require root access Ok, this isn't optimal, since it means that 'iotop' needs admin capabilities, and we may have to work on this some more. But at the same time it is very much not acceptable to let anybody just read anybody elses IO statistics quite at this level. Use of the GENL_ADMIN_PERM suggested by Johannes Berg as an alternative to checking the capabilities by hand. Reported-by: Vasiliy Kulikov Cc: Johannes Berg Acked-by: Balbir Singh Signed-off-by: Linus Torvalds --- kernel/taskstats.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/taskstats.c b/kernel/taskstats.c index e19ce1454ee1..e66046456f4f 100644 --- a/kernel/taskstats.c +++ b/kernel/taskstats.c @@ -655,6 +655,7 @@ static struct genl_ops taskstats_ops = { .cmd = TASKSTATS_CMD_GET, .doit = taskstats_user_cmd, .policy = taskstats_cmd_get_policy, + .flags = GENL_ADMIN_PERM, }; static struct genl_ops cgroupstats_ops = { -- cgit v1.2.3-71-gd317 From 58c3c3aa01b455ecb99d61ce73f1444274af696b Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 19 Sep 2011 17:10:57 -0700 Subject: Make taskstats round statistics down to nearest 1k bytes/events Even with just the interface limited to admin, there really is little to reason to give byte-per-byte counts for taskstats. So round it down to something less intrusive. Acked-by: Balbir Singh Signed-off-by: Linus Torvalds --- kernel/tsacct.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) (limited to 'kernel') diff --git a/kernel/tsacct.c b/kernel/tsacct.c index 24dc60d9fa1f..5bbfac85866e 100644 --- a/kernel/tsacct.c +++ b/kernel/tsacct.c @@ -78,6 +78,7 @@ void bacct_add_tsk(struct taskstats *stats, struct task_struct *tsk) #define KB 1024 #define MB (1024*KB) +#define KB_MASK (~(KB-1)) /* * fill in extended accounting fields */ @@ -95,14 +96,14 @@ void xacct_add_tsk(struct taskstats *stats, struct task_struct *p) stats->hiwater_vm = get_mm_hiwater_vm(mm) * PAGE_SIZE / KB; mmput(mm); } - stats->read_char = p->ioac.rchar; - stats->write_char = p->ioac.wchar; - stats->read_syscalls = p->ioac.syscr; - stats->write_syscalls = p->ioac.syscw; + stats->read_char = p->ioac.rchar & KB_MASK; + stats->write_char = p->ioac.wchar & KB_MASK; + stats->read_syscalls = p->ioac.syscr & KB_MASK; + stats->write_syscalls = p->ioac.syscw & KB_MASK; #ifdef CONFIG_TASK_IO_ACCOUNTING - stats->read_bytes = p->ioac.read_bytes; - stats->write_bytes = p->ioac.write_bytes; - stats->cancelled_write_bytes = p->ioac.cancelled_write_bytes; + stats->read_bytes = p->ioac.read_bytes & KB_MASK; + stats->write_bytes = p->ioac.write_bytes & KB_MASK; + stats->cancelled_write_bytes = p->ioac.cancelled_write_bytes & KB_MASK; #else stats->read_bytes = 0; stats->write_bytes = 0; -- cgit v1.2.3-71-gd317 From f9d81f61c84aca693bc353dfef4b8c36c2e5e1b5 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Sun, 25 Sep 2011 19:46:22 +0200 Subject: ptrace: PTRACE_LISTEN forgets to unlock ->siglock If PTRACE_LISTEN fails after lock_task_sighand() it doesn't drop ->siglock. Reported-by: Matt Fleming Signed-off-by: Oleg Nesterov Signed-off-by: Linus Torvalds --- kernel/ptrace.c | 23 ++++++++++------------- 1 file changed, 10 insertions(+), 13 deletions(-) (limited to 'kernel') diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 9de3ecfd20f9..a70d2a5d8c7b 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -744,20 +744,17 @@ int ptrace_request(struct task_struct *child, long request, break; si = child->last_siginfo; - if (unlikely(!si || si->si_code >> 8 != PTRACE_EVENT_STOP)) - break; - - child->jobctl |= JOBCTL_LISTENING; - - /* - * If NOTIFY is set, it means event happened between start - * of this trap and now. Trigger re-trap immediately. - */ - if (child->jobctl & JOBCTL_TRAP_NOTIFY) - signal_wake_up(child, true); - + if (likely(si && (si->si_code >> 8) == PTRACE_EVENT_STOP)) { + child->jobctl |= JOBCTL_LISTENING; + /* + * If NOTIFY is set, it means event happened between + * start of this trap and now. Trigger re-trap. + */ + if (child->jobctl & JOBCTL_TRAP_NOTIFY) + signal_wake_up(child, true); + ret = 0; + } unlock_task_sighand(child, &flags); - ret = 0; break; case PTRACE_DETACH: /* detach a process that was attached. */ -- cgit v1.2.3-71-gd317