From a2db672aa305a045404615e5222ba681bab6cf58 Mon Sep 17 00:00:00 2001 From: Silas Boyd-Wickizer Date: Fri, 3 Aug 2012 12:33:27 -0700 Subject: Use get_online_cpus to avoid races involving CPU hotplug If arch/x86/kernel/msr.c is a module, a CPU might offline or online between the for_each_online_cpu(i) loop and the call to register_hotcpu_notifier in msr_init or the call to unregister_hotcpu_notifier in msr_exit. The potential races can lead to leaks/duplicates, attempts to destroy non-existant devices, or random pointer dereferences. For example, in msr_init if: for_each_online_cpu(i) { err = msr_device_create(i); if (err != 0) goto out_class; } <----- CPU offlines register_hotcpu_notifier(&msr_class_cpu_notifier); and the CPU never onlines before msr_exit, then the module will never call msr_device_destroy for the associated CPU. This fix surrounds for_each_online_cpu and register_hotcpu_notifier or unregister_hotcpu_notifier with get_online_cpus+put_online_cpus. Tested on a VM. Signed-off-by: Silas Boyd-Wickizer Signed-off-by: Paul E. McKenney --- arch/x86/kernel/msr.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'arch') diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c index eb113693f04..a7c5661f849 100644 --- a/arch/x86/kernel/msr.c +++ b/arch/x86/kernel/msr.c @@ -257,12 +257,14 @@ static int __init msr_init(void) goto out_chrdev; } msr_class->devnode = msr_devnode; + get_online_cpus(); for_each_online_cpu(i) { err = msr_device_create(i); if (err != 0) goto out_class; } register_hotcpu_notifier(&msr_class_cpu_notifier); + put_online_cpus(); err = 0; goto out; @@ -271,6 +273,7 @@ out_class: i = 0; for_each_online_cpu(i) msr_device_destroy(i); + put_online_cpus(); class_destroy(msr_class); out_chrdev: __unregister_chrdev(MSR_MAJOR, 0, NR_CPUS, "cpu/msr"); @@ -281,11 +284,13 @@ out: static void __exit msr_exit(void) { int cpu = 0; + get_online_cpus(); for_each_online_cpu(cpu) msr_device_destroy(cpu); class_destroy(msr_class); __unregister_chrdev(MSR_MAJOR, 0, NR_CPUS, "cpu/msr"); unregister_hotcpu_notifier(&msr_class_cpu_notifier); + put_online_cpus(); } module_init(msr_init); -- cgit v1.2.3 From 429227bbe55647aa42f8f63cac61e4544e248629 Mon Sep 17 00:00:00 2001 From: Silas Boyd-Wickizer Date: Fri, 3 Aug 2012 12:34:50 -0700 Subject: Use get_online_cpus to avoid races involving CPU hotplug If arch/x86/kernel/cpuid.c is a module, a CPU might offline or online between the for_each_online_cpu() loop and the call to register_hotcpu_notifier in cpuid_init or the call to unregister_hotcpu_notifier in cpuid_exit. The potential races can lead to leaks/duplicates, attempts to destroy non-existant devices, or random pointer dereferences. For example, in cpuid_exit if: for_each_online_cpu(cpu) cpuid_device_destroy(cpu); class_destroy(cpuid_class); __unregister_chrdev(CPUID_MAJOR, 0, NR_CPUS, "cpu/cpuid"); <----- CPU onlines unregister_hotcpu_notifier(&cpuid_class_cpu_notifier); the hotcpu notifier will attempt to create a device for the cpuid_class, which the module already destroyed. This fix surrounds for_each_online_cpu and register_hotcpu_notifier or unregister_hotcpu_notifier with get_online_cpus+put_online_cpus. Tested on a VM. Signed-off-by: Silas Boyd-Wickizer Signed-off-by: Paul E. McKenney --- arch/x86/kernel/cpuid.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'arch') diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c index 39472dd2323..60c78917190 100644 --- a/arch/x86/kernel/cpuid.c +++ b/arch/x86/kernel/cpuid.c @@ -199,12 +199,14 @@ static int __init cpuid_init(void) goto out_chrdev; } cpuid_class->devnode = cpuid_devnode; + get_online_cpus(); for_each_online_cpu(i) { err = cpuid_device_create(i); if (err != 0) goto out_class; } register_hotcpu_notifier(&cpuid_class_cpu_notifier); + put_online_cpus(); err = 0; goto out; @@ -214,6 +216,7 @@ out_class: for_each_online_cpu(i) { cpuid_device_destroy(i); } + put_online_cpus(); class_destroy(cpuid_class); out_chrdev: __unregister_chrdev(CPUID_MAJOR, 0, NR_CPUS, "cpu/cpuid"); @@ -225,11 +228,13 @@ static void __exit cpuid_exit(void) { int cpu = 0; + get_online_cpus(); for_each_online_cpu(cpu) cpuid_device_destroy(cpu); class_destroy(cpuid_class); __unregister_chrdev(CPUID_MAJOR, 0, NR_CPUS, "cpu/cpuid"); unregister_hotcpu_notifier(&cpuid_class_cpu_notifier); + put_online_cpus(); } module_init(cpuid_init); -- cgit v1.2.3 From 6a6c0272f17cc80a8286d915f2ddf31557c2d559 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 23 Aug 2012 14:11:25 +0200 Subject: alpha: Fix preemption handling in idle loop cpu_idle() is called on the boot CPU by the init code with preemption disabled. But the cpu_idle() function in alpha doesn't handle this when it calls schedule() directly. Fix it by converting it into schedule_preempt_disabled(). Also disable preemption before calling cpu_idle() from secondary CPU entry code to stay consistent with this state. Signed-off-by: Frederic Weisbecker Tested-by: Michael Cree Cc: Richard Henderson Cc: Ivan Kokshaysky Cc: Matt Turner Cc: alpha Cc: Paul E. McKenney Reviewed-by: Josh Triplett --- arch/alpha/kernel/process.c | 3 ++- arch/alpha/kernel/smp.c | 1 + 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c index d6fde98b74b..db56f31dbf7 100644 --- a/arch/alpha/kernel/process.c +++ b/arch/alpha/kernel/process.c @@ -56,7 +56,8 @@ cpu_idle(void) while (!need_resched()) cpu_relax(); - schedule(); + + schedule_preempt_disabled(); } } diff --git a/arch/alpha/kernel/smp.c b/arch/alpha/kernel/smp.c index 35ddc02bfa4..a41ad90a97a 100644 --- a/arch/alpha/kernel/smp.c +++ b/arch/alpha/kernel/smp.c @@ -166,6 +166,7 @@ smp_callin(void) DBGS(("smp_callin: commencing CPU %d current %p active_mm %p\n", cpuid, current, current->active_mm)); + preempt_disable(); /* Do nothing. */ cpu_idle(); } -- cgit v1.2.3 From 4c94cada48f7c660eca582be6032427a5e367117 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 22 Aug 2012 17:27:34 +0200 Subject: alpha: Add missing RCU idle APIs on idle loop In the old times, the whole idle task was considered as an RCU quiescent state. But as RCU became more and more successful overtime, some RCU read side critical section have been added even in the code of some architectures idle tasks, for tracing for example. So nowadays, rcu_idle_enter() and rcu_idle_exit() must be called by the architecture to tell RCU about the part in the idle loop that doesn't make use of rcu read side critical sections, typically the part that puts the CPU in low power mode. This is necessary for RCU to find the quiescent states in idle in order to complete grace periods. Add this missing pair of calls in the Alpha's idle loop. Reported-by: Paul E. McKenney Signed-off-by: Frederic Weisbecker Tested-by: Michael Cree Cc: Richard Henderson Cc: Ivan Kokshaysky Cc: Matt Turner Cc: alpha Cc: Paul E. McKenney Cc: # 3.3+ Reviewed-by: Josh Triplett --- arch/alpha/kernel/process.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'arch') diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c index db56f31dbf7..83638aa096d 100644 --- a/arch/alpha/kernel/process.c +++ b/arch/alpha/kernel/process.c @@ -28,6 +28,7 @@ #include #include #include +#include #include #include @@ -54,9 +55,11 @@ cpu_idle(void) /* FIXME -- EV6 and LCA45 know how to power down the CPU. */ + rcu_idle_enter(); while (!need_resched()) cpu_relax(); + rcu_idle_exit(); schedule_preempt_disabled(); } } -- cgit v1.2.3 From c633f9e788928e91ad11f44df29b47bbbe9550b0 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 22 Aug 2012 17:27:34 +0200 Subject: cris: Add missing RCU idle APIs on idle loop In the old times, the whole idle task was considered as an RCU quiescent state. But as RCU became more and more successful overtime, some RCU read side critical section have been added even in the code of some architectures idle tasks, for tracing for example. So nowadays, rcu_idle_enter() and rcu_idle_exit() must be called by the architecture to tell RCU about the part in the idle loop that doesn't make use of rcu read side critical sections, typically the part that puts the CPU in low power mode. This is necessary for RCU to find the quiescent states in idle in order to complete grace periods. Add this missing pair of calls in the Cris's idle loop. Reported-by: Paul E. McKenney Signed-off-by: Frederic Weisbecker Cc: Mikael Starvik Cc: Jesper Nilsson Cc: Cris Cc: # 3.3+ Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- arch/cris/kernel/process.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'arch') diff --git a/arch/cris/kernel/process.c b/arch/cris/kernel/process.c index 66fd0172879..7f65be6f7f1 100644 --- a/arch/cris/kernel/process.c +++ b/arch/cris/kernel/process.c @@ -25,6 +25,7 @@ #include #include #include +#include //#define DEBUG @@ -74,6 +75,7 @@ void cpu_idle (void) { /* endless idle loop with no priority at all */ while (1) { + rcu_idle_enter(); while (!need_resched()) { void (*idle)(void); /* @@ -86,6 +88,7 @@ void cpu_idle (void) idle = default_idle; idle(); } + rcu_idle_exit(); schedule_preempt_disabled(); } } -- cgit v1.2.3 From 41d8fe5bb3cf91ce2716ac8f43e4b40d802a99c8 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 22 Aug 2012 17:27:34 +0200 Subject: frv: Add missing RCU idle APIs on idle loop In the old times, the whole idle task was considered as an RCU quiescent state. But as RCU became more and more successful overtime, some RCU read side critical section have been added even in the code of some architectures idle tasks, for tracing for example. So nowadays, rcu_idle_enter() and rcu_idle_exit() must be called by the architecture to tell RCU about the part in the idle loop that doesn't make use of rcu read side critical sections, typically the part that puts the CPU in low power mode. This is necessary for RCU to find the quiescent states in idle in order to complete grace periods. Add this missing pair of calls in the Frv's idle loop. Reported-by: Paul E. McKenney Signed-off-by: Frederic Weisbecker Cc: David Howells Cc: # 3.3+ Acked-by: David Howells Reviewed-by: Josh Triplett --- arch/frv/kernel/process.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'arch') diff --git a/arch/frv/kernel/process.c b/arch/frv/kernel/process.c index ff95f50efea..2eb7fa5bf9d 100644 --- a/arch/frv/kernel/process.c +++ b/arch/frv/kernel/process.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #include @@ -69,12 +70,14 @@ void cpu_idle(void) { /* endless idle loop with no priority at all */ while (1) { + rcu_idle_enter(); while (!need_resched()) { check_pgt_cache(); if (!frv_dma_inprogress && idle) idle(); } + rcu_idle_exit(); schedule_preempt_disabled(); } -- cgit v1.2.3 From b2fe1430d4115c74d007c825cb9dc3317f28bb16 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 22 Aug 2012 17:27:34 +0200 Subject: h8300: Add missing RCU idle APIs on idle loop In the old times, the whole idle task was considered as an RCU quiescent state. But as RCU became more and more successful overtime, some RCU read side critical section have been added even in the code of some architectures idle tasks, for tracing for example. So nowadays, rcu_idle_enter() and rcu_idle_exit() must be called by the architecture to tell RCU about the part in the idle loop that doesn't make use of rcu read side critical sections, typically the part that puts the CPU in low power mode. This is necessary for RCU to find the quiescent states in idle in order to complete grace periods. Add this missing pair of calls in the h8300's idle loop. Reported-by: Paul E. McKenney Signed-off-by: Frederic Weisbecker Cc: Yoshinori Sato Cc: # 3.3+ Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- arch/h8300/kernel/process.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'arch') diff --git a/arch/h8300/kernel/process.c b/arch/h8300/kernel/process.c index 0e9c315be10..f153ed1a4c0 100644 --- a/arch/h8300/kernel/process.c +++ b/arch/h8300/kernel/process.c @@ -36,6 +36,7 @@ #include #include #include +#include #include #include @@ -78,8 +79,10 @@ void (*idle)(void) = default_idle; void cpu_idle(void) { while (1) { + rcu_idle_enter(); while (!need_resched()) idle(); + rcu_idle_exit(); schedule_preempt_disabled(); } } -- cgit v1.2.3 From 48ae077cfce72591b8fc80e1dcc87806f86fed7f Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 22 Aug 2012 17:27:34 +0200 Subject: m32r: Add missing RCU idle APIs on idle loop In the old times, the whole idle task was considered as an RCU quiescent state. But as RCU became more and more successful overtime, some RCU read side critical section have been added even in the code of some architectures idle tasks, for tracing for example. So nowadays, rcu_idle_enter() and rcu_idle_exit() must be called by the architecture to tell RCU about the part in the idle loop that doesn't make use of rcu read side critical sections, typically the part that puts the CPU in low power mode. This is necessary for RCU to find the quiescent states in idle in order to complete grace periods. Add this missing pair of calls in the m32r's idle loop. Reported-by: Paul E. McKenney Signed-off-by: Frederic Weisbecker Cc: Hirokazu Takata Cc: # 3.3+ Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- arch/m32r/kernel/process.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'arch') diff --git a/arch/m32r/kernel/process.c b/arch/m32r/kernel/process.c index 3a4a32b2720..384e63f3a4c 100644 --- a/arch/m32r/kernel/process.c +++ b/arch/m32r/kernel/process.c @@ -26,6 +26,7 @@ #include #include #include +#include #include #include @@ -82,6 +83,7 @@ void cpu_idle (void) { /* endless idle loop with no priority at all */ while (1) { + rcu_idle_enter(); while (!need_resched()) { void (*idle)(void) = pm_idle; @@ -90,6 +92,7 @@ void cpu_idle (void) idle(); } + rcu_idle_exit(); schedule_preempt_disabled(); } } -- cgit v1.2.3 From 5b57ba37e82a15f345a6a2eb8c01a2b2d94c5eeb Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 22 Aug 2012 17:27:34 +0200 Subject: m68k: Add missing RCU idle APIs on idle loop In the old times, the whole idle task was considered as an RCU quiescent state. But as RCU became more and more successful overtime, some RCU read side critical section have been added even in the code of some architectures idle tasks, for tracing for example. So nowadays, rcu_idle_enter() and rcu_idle_exit() must be called by the architecture to tell RCU about the part in the idle loop that doesn't make use of rcu read side critical sections, typically the part that puts the CPU in low power mode. This is necessary for RCU to find the quiescent states in idle in order to complete grace periods. Add this missing pair of calls in the m68k's idle loop. Reported-by: Paul E. McKenney Signed-off-by: Frederic Weisbecker Acked-by: Geert Uytterhoeven Cc: m68k Cc: # 3.3+ Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- arch/m68k/kernel/process.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'arch') diff --git a/arch/m68k/kernel/process.c b/arch/m68k/kernel/process.c index c488e3cfab5..ac2892e49c7 100644 --- a/arch/m68k/kernel/process.c +++ b/arch/m68k/kernel/process.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #include @@ -75,8 +76,10 @@ void cpu_idle(void) { /* endless idle loop with no priority at all */ while (1) { + rcu_idle_enter(); while (!need_resched()) idle(); + rcu_idle_exit(); schedule_preempt_disabled(); } } -- cgit v1.2.3 From 5b0753a90b7a98bc613c3767e9263a1a76d4f900 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 22 Aug 2012 17:27:34 +0200 Subject: mn10300: Add missing RCU idle APIs on idle loop In the old times, the whole idle task was considered as an RCU quiescent state. But as RCU became more and more successful overtime, some RCU read side critical section have been added even in the code of some architectures idle tasks, for tracing for example. So nowadays, rcu_idle_enter() and rcu_idle_exit() must be called by the architecture to tell RCU about the part in the idle loop that doesn't make use of rcu read side critical sections, typically the part that puts the CPU in low power mode. This is necessary for RCU to find the quiescent states in idle in order to complete grace periods. Add this missing pair of calls in the mn10300's idle loop. Reported-by: Paul E. McKenney Signed-off-by: Frederic Weisbecker Cc: David Howells Cc: Koichi Yasutake Cc: # 3.3+ Signed-off-by: Paul E. McKenney Acked-by: David Howells Reviewed-by: Josh Triplett --- arch/mn10300/kernel/process.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'arch') diff --git a/arch/mn10300/kernel/process.c b/arch/mn10300/kernel/process.c index 7dab0cd3646..e9cceba193b 100644 --- a/arch/mn10300/kernel/process.c +++ b/arch/mn10300/kernel/process.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #include #include @@ -107,6 +108,7 @@ void cpu_idle(void) { /* endless idle loop with no priority at all */ for (;;) { + rcu_idle_enter(); while (!need_resched()) { void (*idle)(void); @@ -121,6 +123,7 @@ void cpu_idle(void) } idle(); } + rcu_idle_exit(); schedule_preempt_disabled(); } -- cgit v1.2.3 From fbe752188d5589e7fcbb8e79824e560f77dccc92 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 22 Aug 2012 17:27:34 +0200 Subject: parisc: Add missing RCU idle APIs on idle loop In the old times, the whole idle task was considered as an RCU quiescent state. But as RCU became more and more successful overtime, some RCU read side critical section have been added even in the code of some architectures idle tasks, for tracing for example. So nowadays, rcu_idle_enter() and rcu_idle_exit() must be called by the architecture to tell RCU about the part in the idle loop that doesn't make use of rcu read side critical sections, typically the part that puts the CPU in low power mode. This is necessary for RCU to find the quiescent states in idle in order to complete grace periods. Add this missing pair of calls in the parisc's idle loop. Reported-by: Paul E. McKenney Signed-off-by: Frederic Weisbecker Cc: James E.J. Bottomley Cc: Helge Deller Cc: Parisc Cc: # 3.3+ Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- arch/parisc/kernel/process.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'arch') diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c index 2c05a9292a8..8c6b6b6561f 100644 --- a/arch/parisc/kernel/process.c +++ b/arch/parisc/kernel/process.c @@ -48,6 +48,7 @@ #include #include #include +#include #include #include @@ -69,8 +70,10 @@ void cpu_idle(void) /* endless idle loop with no priority at all */ while (1) { + rcu_idle_enter(); while (!need_resched()) barrier(); + rcu_idle_exit(); schedule_preempt_disabled(); check_pgt_cache(); } -- cgit v1.2.3 From 0ee23fda59740767324b4340247ca41a2f498ca6 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 22 Aug 2012 17:27:34 +0200 Subject: score: Add missing RCU idle APIs on idle loop In the old times, the whole idle task was considered as an RCU quiescent state. But as RCU became more and more successful overtime, some RCU read side critical section have been added even in the code of some architectures idle tasks, for tracing for example. So nowadays, rcu_idle_enter() and rcu_idle_exit() must be called by the architecture to tell RCU about the part in the idle loop that doesn't make use of rcu read side critical sections, typically the part that puts the CPU in low power mode. This is necessary for RCU to find the quiescent states in idle in order to complete grace periods. Add this missing pair of calls in scores's idle loop. Reported-by: Paul E. McKenney Signed-off-by: Frederic Weisbecker Cc: Chen Liqin Cc: Lennox Wu Cc: # 3.3+ Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- arch/score/kernel/process.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/score/kernel/process.c b/arch/score/kernel/process.c index 2707023c756..637970cfd3f 100644 --- a/arch/score/kernel/process.c +++ b/arch/score/kernel/process.c @@ -27,6 +27,7 @@ #include #include #include +#include void (*pm_power_off)(void); EXPORT_SYMBOL(pm_power_off); @@ -50,9 +51,10 @@ void __noreturn cpu_idle(void) { /* endless idle loop with no priority at all */ while (1) { + rcu_idle_enter(); while (!need_resched()) barrier(); - + rcu_idle_exit(); schedule_preempt_disabled(); } } -- cgit v1.2.3 From 11ad47a0edbd62bfc0547cfcdf227a911433f207 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 22 Aug 2012 17:27:34 +0200 Subject: xtensa: Add missing RCU idle APIs on idle loop In the old times, the whole idle task was considered as an RCU quiescent state. But as RCU became more and more successful overtime, some RCU read side critical section have been added even in the code of some architectures idle tasks, for tracing for example. So nowadays, rcu_idle_enter() and rcu_idle_exit() must be called by the architecture to tell RCU about the part in the idle loop that doesn't make use of rcu read side critical sections, typically the part that puts the CPU in low power mode. This is necessary for RCU to find the quiescent states in idle in order to complete grace periods. Add this missing pair of calls in the xtensa's idle loop. Reported-by: Paul E. McKenney Signed-off-by: Frederic Weisbecker Cc: Chris Zankel Cc: # 3.3+ Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- arch/xtensa/kernel/process.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'arch') diff --git a/arch/xtensa/kernel/process.c b/arch/xtensa/kernel/process.c index 2c8d6a3d250..bc44311aa18 100644 --- a/arch/xtensa/kernel/process.c +++ b/arch/xtensa/kernel/process.c @@ -31,6 +31,7 @@ #include #include #include +#include #include #include @@ -110,8 +111,10 @@ void cpu_idle(void) /* endless idle loop with no priority at all */ while (1) { + rcu_idle_enter(); while (!need_resched()) platform_idle(); + rcu_idle_exit(); schedule_preempt_disabled(); } } -- cgit v1.2.3 From 93482f4ef1093f5961a63359a34612183d6beea0 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 24 Aug 2012 13:22:13 -0700 Subject: ia64: Add missing RCU idle APIs on idle loop Traditionally, the entire idle task served as an RCU quiescent state. But when RCU read side critical sections started appearing within the idle loop, this traditional strategy became untenable. The fix was to create new RCU APIs named rcu_idle_enter() and rcu_idle_exit(), which must be called by each architecture's idle loop so that RCU can tell when it is safe to ignore a given idle CPU. Unfortunately, this fix was never applied to ia64, a shortcoming remedied by this commit. Reported by: Tony Luck Signed-off-by: Paul E. McKenney Cc: # 3.3+ Signed-off-by: Paul E. McKenney Tested by: Tony Luck Reviewed-by: Josh Triplett --- arch/ia64/kernel/process.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'arch') diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c index dd6fc144974..3e316ec0b83 100644 --- a/arch/ia64/kernel/process.c +++ b/arch/ia64/kernel/process.c @@ -29,6 +29,7 @@ #include #include #include +#include #include #include @@ -279,6 +280,7 @@ cpu_idle (void) /* endless idle loop with no priority at all */ while (1) { + rcu_idle_enter(); if (can_do_pal_halt) { current_thread_info()->status &= ~TS_POLLING; /* @@ -309,6 +311,7 @@ cpu_idle (void) normal_xtp(); #endif } + rcu_idle_exit(); schedule_preempt_disabled(); check_pgt_cache(); if (cpu_is_offline(cpu)) -- cgit v1.2.3 From 2b1d5024e17be459aa6385763ca3faa8f01c52d9 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 11 Jul 2012 20:26:30 +0200 Subject: rcu: Settle config for userspace extended quiescent state Create a new config option under the RCU menu that put CPUs under RCU extended quiescent state (as in dynticks idle mode) when they run in userspace. This require some contribution from architectures to hook into kernel and userspace boundaries. Signed-off-by: Frederic Weisbecker Cc: Alessio Igor Bogani Cc: Andrew Morton Cc: Avi Kivity Cc: Chris Metcalf Cc: Christoph Lameter Cc: Geoff Levand Cc: Gilad Ben Yossef Cc: Hakan Akkan Cc: H. Peter Anvin Cc: Ingo Molnar Cc: Josh Triplett Cc: Kevin Hilman Cc: Max Krasnyansky Cc: Peter Zijlstra Cc: Stephen Hemminger Cc: Steven Rostedt Cc: Sven-Thorsten Dietrich Cc: Thomas Gleixner Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- arch/Kconfig | 10 ++++++++++ include/linux/rcupdate.h | 9 +++++++++ init/Kconfig | 10 ++++++++++ kernel/rcutree.c | 5 ++++- 4 files changed, 33 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/Kconfig b/arch/Kconfig index 72f2fa189cc..1401a758797 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -281,4 +281,14 @@ config SECCOMP_FILTER See Documentation/prctl/seccomp_filter.txt for details. +config HAVE_RCU_USER_QS + bool + help + Provide kernel entry/exit hooks necessary for userspace + RCU extended quiescent state. Syscalls need to be wrapped inside + rcu_user_exit()-rcu_user_enter() through the slow path using + TIF_NOHZ flag. Exceptions handlers must be wrapped as well. Irqs + are already protected inside rcu_irq_enter/rcu_irq_exit() but + preemption or signal handling on irq exit still need to be protected. + source "kernel/gcov/Kconfig" diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index f818dd165b4..f5034f22e94 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -191,10 +191,19 @@ extern void rcu_idle_enter(void); extern void rcu_idle_exit(void); extern void rcu_irq_enter(void); extern void rcu_irq_exit(void); + +#ifdef CONFIG_RCU_USER_QS extern void rcu_user_enter(void); extern void rcu_user_exit(void); extern void rcu_user_enter_after_irq(void); extern void rcu_user_exit_after_irq(void); +#else +static inline void rcu_user_enter(void) { } +static inline void rcu_user_exit(void) { } +static inline void rcu_user_enter_after_irq(void) { } +static inline void rcu_user_exit_after_irq(void) { } +#endif /* CONFIG_RCU_USER_QS */ + extern void exit_rcu(void); /** diff --git a/init/Kconfig b/init/Kconfig index af6c7f8ba01..f6a1830165c 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -441,6 +441,16 @@ config PREEMPT_RCU This option enables preemptible-RCU code that is common between the TREE_PREEMPT_RCU and TINY_PREEMPT_RCU implementations. +config RCU_USER_QS + bool "Consider userspace as in RCU extended quiescent state" + depends on HAVE_RCU_USER_QS && SMP + help + This option sets hooks on kernel / userspace boundaries and + puts RCU in extended quiescent state when the CPU runs in + userspace. It means that when a CPU runs in userspace, it is + excluded from the global RCU state machine and thus doesn't + to keep the timer tick on for RCU. + config RCU_FANOUT int "Tree-based hierarchical RCU fanout value" range 2 64 if 64BIT diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 4138f59fa2f..79fa2db1595 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -400,6 +400,7 @@ void rcu_idle_enter(void) } EXPORT_SYMBOL_GPL(rcu_idle_enter); +#ifdef CONFIG_RCU_USER_QS /** * rcu_user_enter - inform RCU that we are resuming userspace. * @@ -424,7 +425,6 @@ void rcu_user_enter(void) rcu_eqs_enter(1); } - /** * rcu_user_enter_after_irq - inform RCU that we are going to resume userspace * after the current irq returns. @@ -445,6 +445,7 @@ void rcu_user_enter_after_irq(void) rdtp->dynticks_nesting = 1; local_irq_restore(flags); } +#endif /* CONFIG_RCU_USER_QS */ /** * rcu_irq_exit - inform RCU that current CPU is exiting irq towards idle @@ -548,6 +549,7 @@ void rcu_idle_exit(void) } EXPORT_SYMBOL_GPL(rcu_idle_exit); +#ifdef CONFIG_RCU_USER_QS /** * rcu_user_exit - inform RCU that we are exiting userspace. * @@ -591,6 +593,7 @@ void rcu_user_exit_after_irq(void) rdtp->dynticks_nesting += DYNTICK_TASK_EXIT_IDLE; local_irq_restore(flags); } +#endif /* CONFIG_RCU_USER_QS */ /** * rcu_irq_enter - inform RCU that current CPU is entering irq away from idle -- cgit v1.2.3 From 04e7e951532b390b16feb070be9972b8fad2fc57 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Mon, 16 Jul 2012 15:06:40 -0700 Subject: rcu: Switch task's syscall hooks on context switch Clear the syscalls hook of a task when it's scheduled out so that if the task migrates, it doesn't run the syscall slow path on a CPU that might not need it. Also set the syscalls hook on the next task if needed. Signed-off-by: Frederic Weisbecker Cc: Alessio Igor Bogani Cc: Andrew Morton Cc: Avi Kivity Cc: Chris Metcalf Cc: Christoph Lameter Cc: Geoff Levand Cc: Gilad Ben Yossef Cc: Hakan Akkan Cc: H. Peter Anvin Cc: Ingo Molnar Cc: Josh Triplett Cc: Kevin Hilman Cc: Max Krasnyansky Cc: Peter Zijlstra Cc: Stephen Hemminger Cc: Steven Rostedt Cc: Sven-Thorsten Dietrich Cc: Thomas Gleixner Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- arch/um/drivers/mconsole_kern.c | 1 + include/linux/rcupdate.h | 2 ++ include/linux/sched.h | 8 ++++++++ kernel/rcutree.c | 15 +++++++++++++++ kernel/sched/core.c | 1 + 5 files changed, 27 insertions(+) (limited to 'arch') diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c index 664a60e8dfb..c17de0db673 100644 --- a/arch/um/drivers/mconsole_kern.c +++ b/arch/um/drivers/mconsole_kern.c @@ -705,6 +705,7 @@ static void stack_proc(void *arg) struct task_struct *from = current, *to = arg; to->thread.saved_task = from; + rcu_switch(from, to); switch_to(from, to, from); } diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index f5034f22e94..7c968e4f929 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -197,6 +197,8 @@ extern void rcu_user_enter(void); extern void rcu_user_exit(void); extern void rcu_user_enter_after_irq(void); extern void rcu_user_exit_after_irq(void); +extern void rcu_user_hooks_switch(struct task_struct *prev, + struct task_struct *next); #else static inline void rcu_user_enter(void) { } static inline void rcu_user_exit(void) { } diff --git a/include/linux/sched.h b/include/linux/sched.h index 23bddac4bad..335720a1fc3 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1885,6 +1885,14 @@ static inline void rcu_copy_process(struct task_struct *p) #endif +static inline void rcu_switch(struct task_struct *prev, + struct task_struct *next) +{ +#ifdef CONFIG_RCU_USER_QS + rcu_user_hooks_switch(prev, next); +#endif +} + static inline void tsk_restore_flags(struct task_struct *task, unsigned long orig_flags, unsigned long flags) { diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 6b82a956514..d2e74c8d4b0 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -717,6 +717,21 @@ int rcu_is_cpu_idle(void) } EXPORT_SYMBOL(rcu_is_cpu_idle); +#ifdef CONFIG_RCU_USER_QS +void rcu_user_hooks_switch(struct task_struct *prev, + struct task_struct *next) +{ + struct rcu_dynticks *rdtp; + + /* Interrupts are disabled in context switch */ + rdtp = &__get_cpu_var(rcu_dynticks); + if (!rdtp->ignore_user_qs) { + clear_tsk_thread_flag(prev, TIF_NOHZ); + set_tsk_thread_flag(next, TIF_NOHZ); + } +} +#endif /* #ifdef CONFIG_RCU_USER_QS */ + #if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU) /* diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 1a48cdbc863..ea2213b07d9 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2081,6 +2081,7 @@ context_switch(struct rq *rq, struct task_struct *prev, #endif /* Here we just switch the register state and the stack. */ + rcu_switch(prev, next); switch_to(prev, next, prev); barrier(); -- cgit v1.2.3 From bf5a3c13b939813d28ce26c01425054c740d6731 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 11 Jul 2012 20:26:34 +0200 Subject: x86: Syscall hooks for userspace RCU extended QS Add syscall slow path hooks to notify syscall entry and exit on CPUs that want to support userspace RCU extended quiescent state. Signed-off-by: Frederic Weisbecker Cc: Alessio Igor Bogani Cc: Andrew Morton Cc: Avi Kivity Cc: Chris Metcalf Cc: Christoph Lameter Cc: Geoff Levand Cc: Gilad Ben Yossef Cc: Hakan Akkan Cc: H. Peter Anvin Cc: Ingo Molnar Cc: Josh Triplett Cc: Kevin Hilman Cc: Max Krasnyansky Cc: Peter Zijlstra Cc: Stephen Hemminger Cc: Steven Rostedt Cc: Sven-Thorsten Dietrich Cc: Thomas Gleixner Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- arch/x86/include/asm/thread_info.h | 10 +++++++--- arch/x86/kernel/ptrace.c | 5 +++++ 2 files changed, 12 insertions(+), 3 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 89f794f007e..c535d847e3b 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -89,6 +89,7 @@ struct thread_info { #define TIF_NOTSC 16 /* TSC is not accessible in userland */ #define TIF_IA32 17 /* IA32 compatibility process */ #define TIF_FORK 18 /* ret_from_fork */ +#define TIF_NOHZ 19 /* in adaptive nohz mode */ #define TIF_MEMDIE 20 /* is terminating due to OOM killer */ #define TIF_DEBUG 21 /* uses debug registers */ #define TIF_IO_BITMAP 22 /* uses I/O bitmap */ @@ -114,6 +115,7 @@ struct thread_info { #define _TIF_NOTSC (1 << TIF_NOTSC) #define _TIF_IA32 (1 << TIF_IA32) #define _TIF_FORK (1 << TIF_FORK) +#define _TIF_NOHZ (1 << TIF_NOHZ) #define _TIF_DEBUG (1 << TIF_DEBUG) #define _TIF_IO_BITMAP (1 << TIF_IO_BITMAP) #define _TIF_FORCED_TF (1 << TIF_FORCED_TF) @@ -126,12 +128,13 @@ struct thread_info { /* work to do in syscall_trace_enter() */ #define _TIF_WORK_SYSCALL_ENTRY \ (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU | _TIF_SYSCALL_AUDIT | \ - _TIF_SECCOMP | _TIF_SINGLESTEP | _TIF_SYSCALL_TRACEPOINT) + _TIF_SECCOMP | _TIF_SINGLESTEP | _TIF_SYSCALL_TRACEPOINT | \ + _TIF_NOHZ) /* work to do in syscall_trace_leave() */ #define _TIF_WORK_SYSCALL_EXIT \ (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SINGLESTEP | \ - _TIF_SYSCALL_TRACEPOINT) + _TIF_SYSCALL_TRACEPOINT | _TIF_NOHZ) /* work to do on interrupt/exception return */ #define _TIF_WORK_MASK \ @@ -141,7 +144,8 @@ struct thread_info { /* work to do on any return to user space */ #define _TIF_ALLWORK_MASK \ - ((0x0000FFFF & ~_TIF_SECCOMP) | _TIF_SYSCALL_TRACEPOINT) + ((0x0000FFFF & ~_TIF_SECCOMP) | _TIF_SYSCALL_TRACEPOINT | \ + _TIF_NOHZ) /* Only used for 64 bit */ #define _TIF_DO_NOTIFY_MASK \ diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index c4c6a5c2bf0..9f94f8ec26e 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -21,6 +21,7 @@ #include #include #include +#include #include #include @@ -1463,6 +1464,8 @@ long syscall_trace_enter(struct pt_regs *regs) { long ret = 0; + rcu_user_exit(); + /* * If we stepped into a sysenter/syscall insn, it trapped in * kernel mode; do_debug() cleared TF and set TIF_SINGLESTEP. @@ -1526,4 +1529,6 @@ void syscall_trace_leave(struct pt_regs *regs) !test_thread_flag(TIF_SYSCALL_EMU); if (step || test_thread_flag(TIF_SYSCALL_TRACE)) tracehook_report_syscall_exit(regs, step); + + rcu_user_enter(); } -- cgit v1.2.3 From ef3f628872c838933a279d0d7e63e707783c9710 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Mon, 24 Sep 2012 21:05:52 +0200 Subject: x86: Unspaghettize do_general_protection() There is some unnatural label based layout in this function. Convert the unnecessary goto to readable conditional blocks. Signed-off-by: Frederic Weisbecker Cc: Thomas Gleixner Cc: H. Peter Anvin Cc: Ingo Molnar --- arch/x86/kernel/traps.c | 38 ++++++++++++++++---------------------- 1 file changed, 16 insertions(+), 22 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index b481341c936..74850e55944 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -258,13 +258,25 @@ do_general_protection(struct pt_regs *regs, long error_code) conditional_sti(regs); #ifdef CONFIG_X86_32 - if (regs->flags & X86_VM_MASK) - goto gp_in_vm86; + if (regs->flags & X86_VM_MASK) { + local_irq_enable(); + handle_vm86_fault((struct kernel_vm86_regs *) regs, error_code); + return; + } #endif tsk = current; - if (!user_mode(regs)) - goto gp_in_kernel; + if (!user_mode(regs)) { + if (fixup_exception(regs)) + return; + + tsk->thread.error_code = error_code; + tsk->thread.trap_nr = X86_TRAP_GP; + if (!notify_die(DIE_GPF, "general protection fault", regs, error_code, + X86_TRAP_GP, SIGSEGV) == NOTIFY_STOP) + die("general protection fault", regs, error_code); + return; + } tsk->thread.error_code = error_code; tsk->thread.trap_nr = X86_TRAP_GP; @@ -280,24 +292,6 @@ do_general_protection(struct pt_regs *regs, long error_code) force_sig(SIGSEGV, tsk); return; - -#ifdef CONFIG_X86_32 -gp_in_vm86: - local_irq_enable(); - handle_vm86_fault((struct kernel_vm86_regs *) regs, error_code); - return; -#endif - -gp_in_kernel: - if (fixup_exception(regs)) - return; - - tsk->thread.error_code = error_code; - tsk->thread.trap_nr = X86_TRAP_GP; - if (notify_die(DIE_GPF, "general protection fault", regs, error_code, - X86_TRAP_GP, SIGSEGV) == NOTIFY_STOP) - return; - die("general protection fault", regs, error_code); } /* May run on IST stack. */ -- cgit v1.2.3 From 6ba3c97a38803883c2eee489505796cb0a727122 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 11 Jul 2012 20:26:35 +0200 Subject: x86: Exception hooks for userspace RCU extended QS Add necessary hooks to x86 exception for userspace RCU extended quiescent state support. This includes traps, page fault, debug exceptions, etc... Signed-off-by: Frederic Weisbecker Cc: Alessio Igor Bogani Cc: Andrew Morton Cc: Avi Kivity Cc: Chris Metcalf Cc: Christoph Lameter Cc: Geoff Levand Cc: Gilad Ben Yossef Cc: Hakan Akkan Cc: H. Peter Anvin Cc: Ingo Molnar Cc: Josh Triplett Cc: Kevin Hilman Cc: Max Krasnyansky Cc: Peter Zijlstra Cc: Stephen Hemminger Cc: Steven Rostedt Cc: Sven-Thorsten Dietrich Cc: Thomas Gleixner Signed-off-by: Paul E. McKenney --- arch/x86/include/asm/rcu.h | 20 ++++++++++++ arch/x86/kernel/traps.c | 81 +++++++++++++++++++++++++++++++--------------- arch/x86/mm/fault.c | 13 ++++++-- 3 files changed, 86 insertions(+), 28 deletions(-) create mode 100644 arch/x86/include/asm/rcu.h (limited to 'arch') diff --git a/arch/x86/include/asm/rcu.h b/arch/x86/include/asm/rcu.h new file mode 100644 index 00000000000..439815b35ce --- /dev/null +++ b/arch/x86/include/asm/rcu.h @@ -0,0 +1,20 @@ +#ifndef _ASM_X86_RCU_H +#define _ASM_X86_RCU_H + +#include +#include + +static inline void exception_enter(struct pt_regs *regs) +{ + rcu_user_exit(); +} + +static inline void exception_exit(struct pt_regs *regs) +{ +#ifdef CONFIG_RCU_USER_QS + if (user_mode(regs)) + rcu_user_enter(); +#endif +} + +#endif diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 74850e55944..378967578f2 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -55,6 +55,7 @@ #include #include #include +#include #include @@ -180,11 +181,15 @@ vm86_trap: #define DO_ERROR(trapnr, signr, str, name) \ dotraplinkage void do_##name(struct pt_regs *regs, long error_code) \ { \ - if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \ - == NOTIFY_STOP) \ + exception_enter(regs); \ + if (notify_die(DIE_TRAP, str, regs, error_code, \ + trapnr, signr) == NOTIFY_STOP) { \ + exception_exit(regs); \ return; \ + } \ conditional_sti(regs); \ do_trap(trapnr, signr, str, regs, error_code, NULL); \ + exception_exit(regs); \ } #define DO_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr) \ @@ -195,11 +200,15 @@ dotraplinkage void do_##name(struct pt_regs *regs, long error_code) \ info.si_errno = 0; \ info.si_code = sicode; \ info.si_addr = (void __user *)siaddr; \ - if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \ - == NOTIFY_STOP) \ + exception_enter(regs); \ + if (notify_die(DIE_TRAP, str, regs, error_code, \ + trapnr, signr) == NOTIFY_STOP) { \ + exception_exit(regs); \ return; \ + } \ conditional_sti(regs); \ do_trap(trapnr, signr, str, regs, error_code, &info); \ + exception_exit(regs); \ } DO_ERROR_INFO(X86_TRAP_DE, SIGFPE, "divide error", divide_error, FPE_INTDIV, @@ -222,12 +231,14 @@ DO_ERROR_INFO(X86_TRAP_AC, SIGBUS, "alignment check", alignment_check, /* Runs on IST stack */ dotraplinkage void do_stack_segment(struct pt_regs *regs, long error_code) { + exception_enter(regs); if (notify_die(DIE_TRAP, "stack segment", regs, error_code, - X86_TRAP_SS, SIGBUS) == NOTIFY_STOP) - return; - preempt_conditional_sti(regs); - do_trap(X86_TRAP_SS, SIGBUS, "stack segment", regs, error_code, NULL); - preempt_conditional_cli(regs); + X86_TRAP_SS, SIGBUS) != NOTIFY_STOP) { + preempt_conditional_sti(regs); + do_trap(X86_TRAP_SS, SIGBUS, "stack segment", regs, error_code, NULL); + preempt_conditional_cli(regs); + } + exception_exit(regs); } dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) @@ -235,6 +246,7 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) static const char str[] = "double fault"; struct task_struct *tsk = current; + exception_enter(regs); /* Return not checked because double check cannot be ignored */ notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV); @@ -255,27 +267,28 @@ do_general_protection(struct pt_regs *regs, long error_code) { struct task_struct *tsk; + exception_enter(regs); conditional_sti(regs); #ifdef CONFIG_X86_32 if (regs->flags & X86_VM_MASK) { local_irq_enable(); handle_vm86_fault((struct kernel_vm86_regs *) regs, error_code); - return; + goto exit; } #endif tsk = current; if (!user_mode(regs)) { if (fixup_exception(regs)) - return; + goto exit; tsk->thread.error_code = error_code; tsk->thread.trap_nr = X86_TRAP_GP; - if (!notify_die(DIE_GPF, "general protection fault", regs, error_code, - X86_TRAP_GP, SIGSEGV) == NOTIFY_STOP) + if (notify_die(DIE_GPF, "general protection fault", regs, error_code, + X86_TRAP_GP, SIGSEGV) != NOTIFY_STOP) die("general protection fault", regs, error_code); - return; + goto exit; } tsk->thread.error_code = error_code; @@ -291,7 +304,8 @@ do_general_protection(struct pt_regs *regs, long error_code) } force_sig(SIGSEGV, tsk); - return; +exit: + exception_exit(regs); } /* May run on IST stack. */ @@ -306,15 +320,16 @@ dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_co ftrace_int3_handler(regs)) return; #endif + exception_enter(regs); #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP, SIGTRAP) == NOTIFY_STOP) - return; + goto exit; #endif /* CONFIG_KGDB_LOW_LEVEL_TRAP */ if (notify_die(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP, SIGTRAP) == NOTIFY_STOP) - return; + goto exit; /* * Let others (NMI) know that the debug stack is in use @@ -325,6 +340,8 @@ dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_co do_trap(X86_TRAP_BP, SIGTRAP, "int3", regs, error_code, NULL); preempt_conditional_cli(regs); debug_stack_usage_dec(); +exit: + exception_exit(regs); } #ifdef CONFIG_X86_64 @@ -385,6 +402,8 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) unsigned long dr6; int si_code; + exception_enter(regs); + get_debugreg(dr6, 6); /* Filter out all the reserved bits which are preset to 1 */ @@ -400,7 +419,7 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) /* Catch kmemcheck conditions first of all! */ if ((dr6 & DR_STEP) && kmemcheck_trap(regs)) - return; + goto exit; /* DR6 may or may not be cleared by the CPU */ set_debugreg(0, 6); @@ -415,7 +434,7 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) if (notify_die(DIE_DEBUG, "debug", regs, PTR_ERR(&dr6), error_code, SIGTRAP) == NOTIFY_STOP) - return; + goto exit; /* * Let others (NMI) know that the debug stack is in use @@ -431,7 +450,7 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) X86_TRAP_DB); preempt_conditional_cli(regs); debug_stack_usage_dec(); - return; + goto exit; } /* @@ -452,7 +471,8 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) preempt_conditional_cli(regs); debug_stack_usage_dec(); - return; +exit: + exception_exit(regs); } /* @@ -549,14 +569,17 @@ dotraplinkage void do_coprocessor_error(struct pt_regs *regs, long error_code) #ifdef CONFIG_X86_32 ignore_fpu_irq = 1; #endif - + exception_enter(regs); math_error(regs, error_code, X86_TRAP_MF); + exception_exit(regs); } dotraplinkage void do_simd_coprocessor_error(struct pt_regs *regs, long error_code) { + exception_enter(regs); math_error(regs, error_code, X86_TRAP_XF); + exception_exit(regs); } dotraplinkage void @@ -623,6 +646,7 @@ EXPORT_SYMBOL_GPL(math_state_restore); dotraplinkage void __kprobes do_device_not_available(struct pt_regs *regs, long error_code) { + exception_enter(regs); #ifdef CONFIG_MATH_EMULATION if (read_cr0() & X86_CR0_EM) { struct math_emu_info info = { }; @@ -631,6 +655,7 @@ do_device_not_available(struct pt_regs *regs, long error_code) info.regs = regs; math_emulate(&info); + exception_exit(regs); return; } #endif @@ -638,12 +663,15 @@ do_device_not_available(struct pt_regs *regs, long error_code) #ifdef CONFIG_X86_32 conditional_sti(regs); #endif + exception_exit(regs); } #ifdef CONFIG_X86_32 dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code) { siginfo_t info; + + exception_enter(regs); local_irq_enable(); info.si_signo = SIGILL; @@ -651,10 +679,11 @@ dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code) info.si_code = ILL_BADSTK; info.si_addr = NULL; if (notify_die(DIE_TRAP, "iret exception", regs, error_code, - X86_TRAP_IRET, SIGILL) == NOTIFY_STOP) - return; - do_trap(X86_TRAP_IRET, SIGILL, "iret exception", regs, error_code, - &info); + X86_TRAP_IRET, SIGILL) != NOTIFY_STOP) { + do_trap(X86_TRAP_IRET, SIGILL, "iret exception", regs, error_code, + &info); + } + exception_exit(regs); } #endif diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 76dcd9d8e0b..7dde46d68a2 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -18,6 +18,7 @@ #include /* pgd_*(), ... */ #include /* kmemcheck_*(), ... */ #include /* VSYSCALL_START */ +#include /* exception_enter(), ... */ /* * Page fault error code bits: @@ -1000,8 +1001,8 @@ static int fault_in_kernel_space(unsigned long address) * and the problem, and then passes it off to one of the appropriate * routines. */ -dotraplinkage void __kprobes -do_page_fault(struct pt_regs *regs, unsigned long error_code) +static void __kprobes +__do_page_fault(struct pt_regs *regs, unsigned long error_code) { struct vm_area_struct *vma; struct task_struct *tsk; @@ -1209,3 +1210,11 @@ good_area: up_read(&mm->mmap_sem); } + +dotraplinkage void __kprobes +do_page_fault(struct pt_regs *regs, unsigned long error_code) +{ + exception_enter(regs); + __do_page_fault(regs, error_code); + exception_exit(regs); +} -- cgit v1.2.3 From 0430499ce9d78691f3985962021b16bf8f8a8048 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 11 Jul 2012 20:26:38 +0200 Subject: x86: Use the new schedule_user API on userspace preemption This way we can exit the RCU extended quiescent state before we schedule a new task from irq/exception exit. Signed-off-by: Frederic Weisbecker Cc: Alessio Igor Bogani Cc: Andrew Morton Cc: Avi Kivity Cc: Chris Metcalf Cc: Christoph Lameter Cc: Geoff Levand Cc: Gilad Ben Yossef Cc: Hakan Akkan Cc: H. Peter Anvin Cc: Ingo Molnar Cc: Josh Triplett Cc: Kevin Hilman Cc: Max Krasnyansky Cc: Peter Zijlstra Cc: Stephen Hemminger Cc: Steven Rostedt Cc: Sven-Thorsten Dietrich Cc: Thomas Gleixner Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- arch/x86/include/asm/rcu.h | 12 ++++++++++++ arch/x86/kernel/entry_64.S | 9 +++++---- 2 files changed, 17 insertions(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/rcu.h b/arch/x86/include/asm/rcu.h index 439815b35ce..d1ac07a2397 100644 --- a/arch/x86/include/asm/rcu.h +++ b/arch/x86/include/asm/rcu.h @@ -1,6 +1,8 @@ #ifndef _ASM_X86_RCU_H #define _ASM_X86_RCU_H +#ifndef __ASSEMBLY__ + #include #include @@ -17,4 +19,14 @@ static inline void exception_exit(struct pt_regs *regs) #endif } +#else /* __ASSEMBLY__ */ + +#ifdef CONFIG_RCU_USER_QS +# define SCHEDULE_USER call schedule_user +#else +# define SCHEDULE_USER call schedule +#endif + +#endif /* !__ASSEMBLY__ */ + #endif diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 69babd8c834..1a8f3cbb6ee 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -56,6 +56,7 @@ #include #include #include +#include #include /* Avoid __ASSEMBLER__'ifying just for this. */ @@ -565,7 +566,7 @@ sysret_careful: TRACE_IRQS_ON ENABLE_INTERRUPTS(CLBR_NONE) pushq_cfi %rdi - call schedule + SCHEDULE_USER popq_cfi %rdi jmp sysret_check @@ -678,7 +679,7 @@ int_careful: TRACE_IRQS_ON ENABLE_INTERRUPTS(CLBR_NONE) pushq_cfi %rdi - call schedule + SCHEDULE_USER popq_cfi %rdi DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF @@ -974,7 +975,7 @@ retint_careful: TRACE_IRQS_ON ENABLE_INTERRUPTS(CLBR_NONE) pushq_cfi %rdi - call schedule + SCHEDULE_USER popq_cfi %rdi GET_THREAD_INFO(%rcx) DISABLE_INTERRUPTS(CLBR_NONE) @@ -1449,7 +1450,7 @@ paranoid_userspace: paranoid_schedule: TRACE_IRQS_ON ENABLE_INTERRUPTS(CLBR_ANY) - call schedule + SCHEDULE_USER DISABLE_INTERRUPTS(CLBR_ANY) TRACE_IRQS_OFF jmp paranoid_userspace -- cgit v1.2.3 From edf55fda35c7dc7f2d9241c3abaddaf759b457c6 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 11 Jul 2012 20:26:39 +0200 Subject: x86: Exit RCU extended QS on notify resume do_notify_resume() may be called on irq or exception exit. But at that time the exception has already called rcu_user_enter() and the irq has already called rcu_irq_exit(). Since it can use RCU read side critical section, we must call rcu_user_exit() before doing anything there. Then we must call back rcu_user_enter() after this function because we know we are going to userspace from there. This complete support for userspace RCU extended quiescent state in x86-64. Signed-off-by: Frederic Weisbecker Cc: Alessio Igor Bogani Cc: Andrew Morton Cc: Avi Kivity Cc: Chris Metcalf Cc: Christoph Lameter Cc: Geoff Levand Cc: Gilad Ben Yossef Cc: Hakan Akkan Cc: H. Peter Anvin Cc: Ingo Molnar Cc: Josh Triplett Cc: Kevin Hilman Cc: Max Krasnyansky Cc: Peter Zijlstra Cc: Stephen Hemminger Cc: Steven Rostedt Cc: Sven-Thorsten Dietrich Cc: Thomas Gleixner Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- arch/x86/Kconfig | 1 + arch/x86/kernel/signal.c | 4 ++++ 2 files changed, 5 insertions(+) (limited to 'arch') diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 50a1d1f9b6d..20c49b8450b 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -97,6 +97,7 @@ config X86 select KTIME_SCALAR if X86_32 select GENERIC_STRNCPY_FROM_USER select GENERIC_STRNLEN_USER + select HAVE_RCU_USER_QS if X86_64 config INSTRUCTION_DECODER def_bool (KPROBES || PERF_EVENTS || UPROBES) diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index b280908a376..bca0ab903e5 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -779,6 +779,8 @@ static void do_signal(struct pt_regs *regs) void do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags) { + rcu_user_exit(); + #ifdef CONFIG_X86_MCE /* notify userspace of pending MCEs */ if (thread_info_flags & _TIF_MCE_NOTIFY) @@ -804,6 +806,8 @@ do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags) #ifdef CONFIG_X86_32 clear_thread_flag(TIF_IRET); #endif /* CONFIG_X86_32 */ + + rcu_user_enter(); } void signal_fault(struct pt_regs *regs, void __user *frame, char *where) -- cgit v1.2.3