[RFC PATCH 0/5] powerpc: Support context tracking for Power pSeries

[RFC PATCH 0/5] powerpc: Support context tracking for Power pSeries

[Li Zhong]

These patches try to support context tracking for Power arch, beginning with 
64-bit pSeries. The codes are ported from that of the x86_64, and in each
patch, I listed the corresponding patch for x86.

Would you please help review and give your comments?

Thanks, Zhong

Li Zhong (5):
  powerpc: Syscall hooks for context tracking subsystem
  powerpc: Exception hooks for context tracking subsystem
  powerpc: Exit user context on notify resume
  powerpc: Use the new schedule_user API on userspace preemption
  powerpc: select HAVE_CONTEXT_TRACKING for pSeries

 arch/powerpc/include/asm/context_tracking.h |   31 +++++++++++
 arch/powerpc/include/asm/thread_info.h      |    7 ++-
 arch/powerpc/kernel/entry_64.S              |    3 +-
 arch/powerpc/kernel/exceptions-64s.S        |    4 +-
 arch/powerpc/kernel/ptrace.c                |    5 ++
 arch/powerpc/kernel/signal.c                |    5 ++
 arch/powerpc/kernel/traps.c                 |   79 ++++++++++++++++++++-------
 arch/powerpc/mm/fault.c                     |   15 ++++-
 arch/powerpc/mm/hash_utils_64.c             |   17 ++++++
 arch/powerpc/platforms/pseries/Kconfig      |    1 +
 10 files changed, 141 insertions(+), 26 deletions(-)
 create mode 100644 arch/powerpc/include/asm/context_tracking.h

-- 
1.7.9.5

[RFC PATCH 1/5] powerpc: Syscall hooks for context tracking subsystem

[Li Zhong]

This is the syscall slow path hooks for context tracking subsystem,
corresponding to
[PATCH] x86: Syscall hooks for userspace RCU extended QS
  commit bf5a3c13b939813d28ce26c01425054c740d6731

TIF_MEMDIE is moved to the second 16-bits (with value 17), as it seems there
is no asm code using it. TIF_NOHZ is added to _TIF_SYCALL_T_OR_A, so it is
better for it to be in the same 16 bits with others in the group, so in the
asm code, andi. with this group could work.

Signed-off-by: Li Zhong <zhong@linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/thread_info.h |    7 +++++--
 arch/powerpc/kernel/ptrace.c           |    5 +++++
 2 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
index 406b7b9..414a261 100644
--- a/arch/powerpc/include/asm/thread_info.h
+++ b/arch/powerpc/include/asm/thread_info.h
@@ -97,7 +97,7 @@ static inline struct thread_info *current_thread_info(void)
 #define TIF_PERFMON_CTXSW	6	/* perfmon needs ctxsw calls */
 #define TIF_SYSCALL_AUDIT	7	/* syscall auditing active */
 #define TIF_SINGLESTEP		8	/* singlestepping active */
-#define TIF_MEMDIE		9	/* is terminating due to OOM killer */
+#define TIF_NOHZ		9	/* in adaptive nohz mode */
 #define TIF_SECCOMP		10	/* secure computing */
 #define TIF_RESTOREALL		11	/* Restore all regs (implies NOERROR) */
 #define TIF_NOERROR		12	/* Force successful syscall return */
@@ -106,6 +106,7 @@ static inline struct thread_info *current_thread_info(void)
 #define TIF_SYSCALL_TRACEPOINT	15	/* syscall tracepoint instrumentation */
 #define TIF_EMULATE_STACK_STORE	16	/* Is an instruction emulation
 						for stack store? */
+#define TIF_MEMDIE		17	/* is terminating due to OOM killer */
 
 /* as above, but as bit values */
 #define _TIF_SYSCALL_TRACE	(1<<TIF_SYSCALL_TRACE)
@@ -124,8 +125,10 @@ static inline struct thread_info *current_thread_info(void)
 #define _TIF_UPROBE		(1<<TIF_UPROBE)
 #define _TIF_SYSCALL_TRACEPOINT	(1<<TIF_SYSCALL_TRACEPOINT)
 #define _TIF_EMULATE_STACK_STORE	(1<<TIF_EMULATE_STACK_STORE)
+#define _TIF_NOHZ		(1<<TIF_NOHZ)
 #define _TIF_SYSCALL_T_OR_A	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
-				 _TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT)
+				 _TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT | \
+				 _TIF_NOHZ)
 
 #define _TIF_USER_WORK_MASK	(_TIF_SIGPENDING | _TIF_NEED_RESCHED | \
 				 _TIF_NOTIFY_RESUME | _TIF_UPROBE)
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index c497000..62238dd 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -32,6 +32,7 @@
 #include <trace/syscall.h>
 #include <linux/hw_breakpoint.h>
 #include <linux/perf_event.h>
+#include <linux/context_tracking.h>
 
 #include <asm/uaccess.h>
 #include <asm/page.h>
@@ -1745,6 +1746,8 @@ long do_syscall_trace_enter(struct pt_regs *regs)
 {
 	long ret = 0;
 
+	user_exit();
+
 	secure_computing_strict(regs->gpr[0]);
 
 	if (test_thread_flag(TIF_SYSCALL_TRACE) &&
@@ -1789,4 +1792,6 @@ void do_syscall_trace_leave(struct pt_regs *regs)
 	step = test_thread_flag(TIF_SINGLESTEP);
 	if (step || test_thread_flag(TIF_SYSCALL_TRACE))
 		tracehook_report_syscall_exit(regs, step);
+
+	user_enter();
 }
-- 
1.7.9.5

Re: [RFC PATCH 1/5] powerpc: Syscall hooks for context tracking subsystem

[Frederic Weisbecker]

2013/2/1 Li Zhong <zhong@linux.vnet.ibm.com>:
> This is the syscall slow path hooks for context tracking subsystem,
> corresponding to
> [PATCH] x86: Syscall hooks for userspace RCU extended QS
>   commit bf5a3c13b939813d28ce26c01425054c740d6731
>
> TIF_MEMDIE is moved to the second 16-bits (with value 17), as it seems there
> is no asm code using it. TIF_NOHZ is added to _TIF_SYCALL_T_OR_A, so it is
> better for it to be in the same 16 bits with others in the group, so in the
> asm code, andi. with this group could work.
>
> Signed-off-by: Li Zhong <zhong@linux.vnet.ibm.com>
> ---
>  arch/powerpc/include/asm/thread_info.h |    7 +++++--
>  arch/powerpc/kernel/ptrace.c           |    5 +++++
>  2 files changed, 10 insertions(+), 2 deletions(-)
>
> diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
> index 406b7b9..414a261 100644
> --- a/arch/powerpc/include/asm/thread_info.h
> +++ b/arch/powerpc/include/asm/thread_info.h
> @@ -97,7 +97,7 @@ static inline struct thread_info *current_thread_info(void)
>  #define TIF_PERFMON_CTXSW      6       /* perfmon needs ctxsw calls */
>  #define TIF_SYSCALL_AUDIT      7       /* syscall auditing active */
>  #define TIF_SINGLESTEP         8       /* singlestepping active */
> -#define TIF_MEMDIE             9       /* is terminating due to OOM killer */
> +#define TIF_NOHZ               9       /* in adaptive nohz mode */
>  #define TIF_SECCOMP            10      /* secure computing */
>  #define TIF_RESTOREALL         11      /* Restore all regs (implies NOERROR) */
>  #define TIF_NOERROR            12      /* Force successful syscall return */
> @@ -106,6 +106,7 @@ static inline struct thread_info *current_thread_info(void)
>  #define TIF_SYSCALL_TRACEPOINT 15      /* syscall tracepoint instrumentation */
>  #define TIF_EMULATE_STACK_STORE        16      /* Is an instruction emulation
>                                                 for stack store? */
> +#define TIF_MEMDIE             17      /* is terminating due to OOM killer */
>
>  /* as above, but as bit values */
>  #define _TIF_SYSCALL_TRACE     (1<<TIF_SYSCALL_TRACE)
> @@ -124,8 +125,10 @@ static inline struct thread_info *current_thread_info(void)
>  #define _TIF_UPROBE            (1<<TIF_UPROBE)
>  #define _TIF_SYSCALL_TRACEPOINT        (1<<TIF_SYSCALL_TRACEPOINT)
>  #define _TIF_EMULATE_STACK_STORE       (1<<TIF_EMULATE_STACK_STORE)
> +#define _TIF_NOHZ              (1<<TIF_NOHZ)
>  #define _TIF_SYSCALL_T_OR_A    (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
> -                                _TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT)
> +                                _TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT | \
> +                                _TIF_NOHZ)
>
>  #define _TIF_USER_WORK_MASK    (_TIF_SIGPENDING | _TIF_NEED_RESCHED | \
>                                  _TIF_NOTIFY_RESUME | _TIF_UPROBE)
> diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
> index c497000..62238dd 100644
> --- a/arch/powerpc/kernel/ptrace.c
> +++ b/arch/powerpc/kernel/ptrace.c
> @@ -32,6 +32,7 @@
>  #include <trace/syscall.h>
>  #include <linux/hw_breakpoint.h>
>  #include <linux/perf_event.h>
> +#include <linux/context_tracking.h>
>
>  #include <asm/uaccess.h>
>  #include <asm/page.h>
> @@ -1745,6 +1746,8 @@ long do_syscall_trace_enter(struct pt_regs *regs)
>  {
>         long ret = 0;
>
> +       user_exit();
> +
>         secure_computing_strict(regs->gpr[0]);
>
>         if (test_thread_flag(TIF_SYSCALL_TRACE) &&
> @@ -1789,4 +1792,6 @@ void do_syscall_trace_leave(struct pt_regs *regs)
>         step = test_thread_flag(TIF_SINGLESTEP);
>         if (step || test_thread_flag(TIF_SYSCALL_TRACE))
>                 tracehook_report_syscall_exit(regs, step);
> +
> +       user_enter();

In x86-64, schedule_user() and do_notify_resume() can be called before
syscall_trace_leave(). As a result we may be entering
syscall_trace_leave() in user mode (from a context tracking POV). To
fix this I added a call to user_exit() on the very beginning of that
function.

You can find the details in 2c5594df344cd1ff0cc9bf007dea3235582b3acf
("rcu: Fix unrecovered RCU user mode in syscall_trace_leave()").

Could this problem happen in ppc as well?

Thanks.

Re: [RFC PATCH 1/5] powerpc: Syscall hooks for context tracking subsystem

[Li Zhong]

On Thu, 2013-02-07 at 01:29 +0100, Frederic Weisbecker wrote:
> 2013/2/1 Li Zhong <zhong@linux.vnet.ibm.com>:
> > This is the syscall slow path hooks for context tracking subsystem,
> > corresponding to
> > [PATCH] x86: Syscall hooks for userspace RCU extended QS
> >   commit bf5a3c13b939813d28ce26c01425054c740d6731
> >
> > TIF_MEMDIE is moved to the second 16-bits (with value 17), as it seems there
> > is no asm code using it. TIF_NOHZ is added to _TIF_SYCALL_T_OR_A, so it is
> > better for it to be in the same 16 bits with others in the group, so in the
> > asm code, andi. with this group could work.
> >
> > Signed-off-by: Li Zhong <zhong@linux.vnet.ibm.com>
> > ---
> >  arch/powerpc/include/asm/thread_info.h |    7 +++++--
> >  arch/powerpc/kernel/ptrace.c           |    5 +++++
> >  2 files changed, 10 insertions(+), 2 deletions(-)
> >
> > diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
> > index 406b7b9..414a261 100644
> > --- a/arch/powerpc/include/asm/thread_info.h
> > +++ b/arch/powerpc/include/asm/thread_info.h
> > @@ -97,7 +97,7 @@ static inline struct thread_info *current_thread_info(void)
> >  #define TIF_PERFMON_CTXSW      6       /* perfmon needs ctxsw calls */
> >  #define TIF_SYSCALL_AUDIT      7       /* syscall auditing active */
> >  #define TIF_SINGLESTEP         8       /* singlestepping active */
> > -#define TIF_MEMDIE             9       /* is terminating due to OOM killer */
> > +#define TIF_NOHZ               9       /* in adaptive nohz mode */
> >  #define TIF_SECCOMP            10      /* secure computing */
> >  #define TIF_RESTOREALL         11      /* Restore all regs (implies NOERROR) */
> >  #define TIF_NOERROR            12      /* Force successful syscall return */
> > @@ -106,6 +106,7 @@ static inline struct thread_info *current_thread_info(void)
> >  #define TIF_SYSCALL_TRACEPOINT 15      /* syscall tracepoint instrumentation */
> >  #define TIF_EMULATE_STACK_STORE        16      /* Is an instruction emulation
> >                                                 for stack store? */
> > +#define TIF_MEMDIE             17      /* is terminating due to OOM killer */
> >
> >  /* as above, but as bit values */
> >  #define _TIF_SYSCALL_TRACE     (1<<TIF_SYSCALL_TRACE)
> > @@ -124,8 +125,10 @@ static inline struct thread_info *current_thread_info(void)
> >  #define _TIF_UPROBE            (1<<TIF_UPROBE)
> >  #define _TIF_SYSCALL_TRACEPOINT        (1<<TIF_SYSCALL_TRACEPOINT)
> >  #define _TIF_EMULATE_STACK_STORE       (1<<TIF_EMULATE_STACK_STORE)
> > +#define _TIF_NOHZ              (1<<TIF_NOHZ)
> >  #define _TIF_SYSCALL_T_OR_A    (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
> > -                                _TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT)
> > +                                _TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT | \
> > +                                _TIF_NOHZ)
> >
> >  #define _TIF_USER_WORK_MASK    (_TIF_SIGPENDING | _TIF_NEED_RESCHED | \
> >                                  _TIF_NOTIFY_RESUME | _TIF_UPROBE)
> > diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
> > index c497000..62238dd 100644
> > --- a/arch/powerpc/kernel/ptrace.c
> > +++ b/arch/powerpc/kernel/ptrace.c
> > @@ -32,6 +32,7 @@
> >  #include <trace/syscall.h>
> >  #include <linux/hw_breakpoint.h>
> >  #include <linux/perf_event.h>
> > +#include <linux/context_tracking.h>
> >
> >  #include <asm/uaccess.h>
> >  #include <asm/page.h>
> > @@ -1745,6 +1746,8 @@ long do_syscall_trace_enter(struct pt_regs *regs)
> >  {
> >         long ret = 0;
> >
> > +       user_exit();
> > +
> >         secure_computing_strict(regs->gpr[0]);
> >
> >         if (test_thread_flag(TIF_SYSCALL_TRACE) &&
> > @@ -1789,4 +1792,6 @@ void do_syscall_trace_leave(struct pt_regs *regs)
> >         step = test_thread_flag(TIF_SINGLESTEP);
> >         if (step || test_thread_flag(TIF_SYSCALL_TRACE))
> >                 tracehook_report_syscall_exit(regs, step);
> > +
> > +       user_enter();
> 
> In x86-64, schedule_user() and do_notify_resume() can be called before
> syscall_trace_leave(). As a result we may be entering
> syscall_trace_leave() in user mode (from a context tracking POV). To
> fix this I added a call to user_exit() on the very beginning of that
> function.
> 
> You can find the details in 2c5594df344cd1ff0cc9bf007dea3235582b3acf
> ("rcu: Fix unrecovered RCU user mode in syscall_trace_leave()").

Hi Frederic, 

Thank you very much for the reminding. 

> 
> Could this problem happen in ppc as well?

I checked the code(64 bit) today, it seems to me that it won't happen.
But fortunately, we are in the ppc mailing list, please correct me if my
understanding is wrong.

By the way, I enabled CONTEXT_TRACKING_FORCE and PROVE_RCU, so if it
could happen, I think there should be some illegal RCU usage complaints
reported.  

Thanks, Zhong

> Thanks.
> 

Re: [RFC PATCH 1/5] powerpc: Syscall hooks for context tracking subsystem

[Frederic Weisbecker]

2013/2/7 Li Zhong <zhong@linux.vnet.ibm.com>:
> On Thu, 2013-02-07 at 01:29 +0100, Frederic Weisbecker wrote:
>> In x86-64, schedule_user() and do_notify_resume() can be called before
>> syscall_trace_leave(). As a result we may be entering
>> syscall_trace_leave() in user mode (from a context tracking POV). To
>> fix this I added a call to user_exit() on the very beginning of that
>> function.
>>
>> You can find the details in 2c5594df344cd1ff0cc9bf007dea3235582b3acf
>> ("rcu: Fix unrecovered RCU user mode in syscall_trace_leave()").
>
> Hi Frederic,
>
> Thank you very much for the reminding.
>
>>
>> Could this problem happen in ppc as well?
>
> I checked the code(64 bit) today, it seems to me that it won't happen.
> But fortunately, we are in the ppc mailing list, please correct me if my
> understanding is wrong.

Ah indeed. Looking at syscall_exit_work label in entry_64.S,
do_syscall_trace_leave is called before ret_from_except which is where
we handle user preemption and do_notify_resume. So that looks fine.

>
> By the way, I enabled CONTEXT_TRACKING_FORCE and PROVE_RCU, so if it
> could happen, I think there should be some illegal RCU usage complaints
> reported.

Ok.

Thanks.

Re: [RFC PATCH 1/5] powerpc: Syscall hooks for context tracking subsystem

[Frederic Weisbecker]

2013/2/1 Li Zhong <zhong@linux.vnet.ibm.com>:
> This is the syscall slow path hooks for context tracking subsystem,
> corresponding to
> [PATCH] x86: Syscall hooks for userspace RCU extended QS
>   commit bf5a3c13b939813d28ce26c01425054c740d6731
>
> TIF_MEMDIE is moved to the second 16-bits (with value 17), as it seems there
> is no asm code using it. TIF_NOHZ is added to _TIF_SYCALL_T_OR_A, so it is
> better for it to be in the same 16 bits with others in the group, so in the
> asm code, andi. with this group could work.
>
> Signed-off-by: Li Zhong <zhong@linux.vnet.ibm.com>

Looks good. Thanks.

Acked-by: Frederic Weisbecker <fweisbec@gmail.com>

> ---
>  arch/powerpc/include/asm/thread_info.h |    7 +++++--
>  arch/powerpc/kernel/ptrace.c           |    5 +++++
>  2 files changed, 10 insertions(+), 2 deletions(-)
>
> diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
> index 406b7b9..414a261 100644
> --- a/arch/powerpc/include/asm/thread_info.h
> +++ b/arch/powerpc/include/asm/thread_info.h
> @@ -97,7 +97,7 @@ static inline struct thread_info *current_thread_info(void)
>  #define TIF_PERFMON_CTXSW      6       /* perfmon needs ctxsw calls */
>  #define TIF_SYSCALL_AUDIT      7       /* syscall auditing active */
>  #define TIF_SINGLESTEP         8       /* singlestepping active */
> -#define TIF_MEMDIE             9       /* is terminating due to OOM killer */
> +#define TIF_NOHZ               9       /* in adaptive nohz mode */
>  #define TIF_SECCOMP            10      /* secure computing */
>  #define TIF_RESTOREALL         11      /* Restore all regs (implies NOERROR) */
>  #define TIF_NOERROR            12      /* Force successful syscall return */
> @@ -106,6 +106,7 @@ static inline struct thread_info *current_thread_info(void)
>  #define TIF_SYSCALL_TRACEPOINT 15      /* syscall tracepoint instrumentation */
>  #define TIF_EMULATE_STACK_STORE        16      /* Is an instruction emulation
>                                                 for stack store? */
> +#define TIF_MEMDIE             17      /* is terminating due to OOM killer */
>
>  /* as above, but as bit values */
>  #define _TIF_SYSCALL_TRACE     (1<<TIF_SYSCALL_TRACE)
> @@ -124,8 +125,10 @@ static inline struct thread_info *current_thread_info(void)
>  #define _TIF_UPROBE            (1<<TIF_UPROBE)
>  #define _TIF_SYSCALL_TRACEPOINT        (1<<TIF_SYSCALL_TRACEPOINT)
>  #define _TIF_EMULATE_STACK_STORE       (1<<TIF_EMULATE_STACK_STORE)
> +#define _TIF_NOHZ              (1<<TIF_NOHZ)
>  #define _TIF_SYSCALL_T_OR_A    (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
> -                                _TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT)
> +                                _TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT | \
> +                                _TIF_NOHZ)
>
>  #define _TIF_USER_WORK_MASK    (_TIF_SIGPENDING | _TIF_NEED_RESCHED | \
>                                  _TIF_NOTIFY_RESUME | _TIF_UPROBE)
> diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
> index c497000..62238dd 100644
> --- a/arch/powerpc/kernel/ptrace.c
> +++ b/arch/powerpc/kernel/ptrace.c
> @@ -32,6 +32,7 @@
>  #include <trace/syscall.h>
>  #include <linux/hw_breakpoint.h>
>  #include <linux/perf_event.h>
> +#include <linux/context_tracking.h>
>
>  #include <asm/uaccess.h>
>  #include <asm/page.h>
> @@ -1745,6 +1746,8 @@ long do_syscall_trace_enter(struct pt_regs *regs)
>  {
>         long ret = 0;
>
> +       user_exit();
> +
>         secure_computing_strict(regs->gpr[0]);
>
>         if (test_thread_flag(TIF_SYSCALL_TRACE) &&
> @@ -1789,4 +1792,6 @@ void do_syscall_trace_leave(struct pt_regs *regs)
>         step = test_thread_flag(TIF_SINGLESTEP);
>         if (step || test_thread_flag(TIF_SYSCALL_TRACE))
>                 tracehook_report_syscall_exit(regs, step);
> +
> +       user_enter();
>  }
> --
> 1.7.9.5
>

[RFC PATCH 2/5] powerpc: Exception hooks for context tracking subsystem

[Li Zhong]

This is the exception hooks for context tracking subsystem, including
data access, program check, single step, instruction breakpoint, machine check,
alignment, fp unavailable, altivec assist, unknown exception, whose handlers
might use RCU.

This patch corresponds to
[PATCH] x86: Exception hooks for userspace RCU extended QS
  commit 6ba3c97a38803883c2eee489505796cb0a727122

Signed-off-by: Li Zhong <zhong@linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/context_tracking.h |   20 +++++++
 arch/powerpc/kernel/exceptions-64s.S        |    4 +-
 arch/powerpc/kernel/traps.c                 |   79 ++++++++++++++++++++-------
 arch/powerpc/mm/fault.c                     |   15 ++++-
 arch/powerpc/mm/hash_utils_64.c             |   17 ++++++
 5 files changed, 112 insertions(+), 23 deletions(-)
 create mode 100644 arch/powerpc/include/asm/context_tracking.h

diff --git a/arch/powerpc/include/asm/context_tracking.h b/arch/powerpc/include/asm/context_tracking.h
new file mode 100644
index 0000000..3adccd8
--- /dev/null
+++ b/arch/powerpc/include/asm/context_tracking.h
@@ -0,0 +1,20 @@
+#ifndef _ASM_POWERPC_CONTEXT_TRACKING_H
+#define _ASM_POWERPC_CONTEXT_TRACKING_H
+
+#include <linux/context_tracking.h>
+#include <asm/ptrace.h>
+
+static inline void exception_enter(struct pt_regs *regs)
+{
+	user_exit();
+}
+
+static inline void exception_exit(struct pt_regs *regs)
+{
+#ifdef CONFIG_CONTEXT_TRACKING
+	if (user_mode(regs))
+		user_enter();
+#endif
+}
+
+#endif
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 4665e82..b877cf2 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1184,15 +1184,17 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_SLB)
 	rlwimi	r4,r0,32-13,30,30	/* becomes _PAGE_USER access bit */
 	ori	r4,r4,1			/* add _PAGE_PRESENT */
 	rlwimi	r4,r5,22+2,31-2,31-2	/* Set _PAGE_EXEC if trap is 0x400 */
+	addi	r6,r1,STACK_FRAME_OVERHEAD
 
 	/*
 	 * r3 contains the faulting address
 	 * r4 contains the required access permissions
 	 * r5 contains the trap number
+	 * r6 contains the address of pt_regs
 	 *
 	 * at return r3 = 0 for success, 1 for page fault, negative for error
 	 */
-	bl	.hash_page		/* build HPTE if possible */
+	bl	.hash_page_ct		/* build HPTE if possible */
 	cmpdi	r3,0			/* see if hash_page succeeded */
 
 	/* Success */
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 3251840..d7c0414 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -59,6 +59,7 @@
 #include <asm/fadump.h>
 #include <asm/switch_to.h>
 #include <asm/debug.h>
+#include <asm/context_tracking.h>
 
 #if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC)
 int (*__debugger)(struct pt_regs *regs) __read_mostly;
@@ -660,6 +661,8 @@ void machine_check_exception(struct pt_regs *regs)
 {
 	int recover = 0;
 
+	exception_enter(regs);
+
 	__get_cpu_var(irq_stat).mce_exceptions++;
 
 	/* See if any machine dependent calls. In theory, we would want
@@ -674,7 +677,7 @@ void machine_check_exception(struct pt_regs *regs)
 		recover = cur_cpu_spec->machine_check(regs);
 
 	if (recover > 0)
-		return;
+		goto exit;
 
 #if defined(CONFIG_8xx) && defined(CONFIG_PCI)
 	/* the qspan pci read routines can cause machine checks -- Cort
@@ -684,20 +687,23 @@ void machine_check_exception(struct pt_regs *regs)
 	 * -- BenH
 	 */
 	bad_page_fault(regs, regs->dar, SIGBUS);
-	return;
+	goto exit;
 #endif
 
 	if (debugger_fault_handler(regs))
-		return;
+		goto exit;
 
 	if (check_io_access(regs))
-		return;
+		goto exit;
 
 	die("Machine check", regs, SIGBUS);
 
 	/* Must die if the interrupt is not recoverable */
 	if (!(regs->msr & MSR_RI))
 		panic("Unrecoverable Machine check");
+
+exit:
+	exception_exit(regs);
 }
 
 void SMIException(struct pt_regs *regs)
@@ -707,20 +713,29 @@ void SMIException(struct pt_regs *regs)
 
 void unknown_exception(struct pt_regs *regs)
 {
+	exception_enter(regs);
+
 	printk("Bad trap at PC: %lx, SR: %lx, vector=%lx\n",
 	       regs->nip, regs->msr, regs->trap);
 
 	_exception(SIGTRAP, regs, 0, 0);
+
+	exception_exit(regs);
 }
 
 void instruction_breakpoint_exception(struct pt_regs *regs)
 {
+	exception_enter(regs);
+
 	if (notify_die(DIE_IABR_MATCH, "iabr_match", regs, 5,
 					5, SIGTRAP) == NOTIFY_STOP)
-		return;
+		goto exit;
 	if (debugger_iabr_match(regs))
-		return;
+		goto exit;
 	_exception(SIGTRAP, regs, TRAP_BRKPT, regs->nip);
+
+exit:
+	exception_exit(regs);
 }
 
 void RunModeException(struct pt_regs *regs)
@@ -730,15 +745,20 @@ void RunModeException(struct pt_regs *regs)
 
 void __kprobes single_step_exception(struct pt_regs *regs)
 {
+	exception_enter(regs);
+
 	clear_single_step(regs);
 
 	if (notify_die(DIE_SSTEP, "single_step", regs, 5,
 					5, SIGTRAP) == NOTIFY_STOP)
-		return;
+		goto exit;
 	if (debugger_sstep(regs))
-		return;
+		goto exit;
 
 	_exception(SIGTRAP, regs, TRAP_TRACE, regs->nip);
+
+exit:
+	exception_exit(regs);
 }
 
 /*
@@ -993,32 +1013,34 @@ void __kprobes program_check_exception(struct pt_regs *regs)
 	unsigned int reason = get_reason(regs);
 	extern int do_mathemu(struct pt_regs *regs);
 
+	exception_enter(regs);
+
 	/* We can now get here via a FP Unavailable exception if the core
 	 * has no FPU, in that case the reason flags will be 0 */
 
 	if (reason & REASON_FP) {
 		/* IEEE FP exception */
 		parse_fpe(regs);
-		return;
+		goto exit;
 	}
 	if (reason & REASON_TRAP) {
 		/* Debugger is first in line to stop recursive faults in
 		 * rcu_lock, notify_die, or atomic_notifier_call_chain */
 		if (debugger_bpt(regs))
-			return;
+			goto exit;
 
 		/* trap exception */
 		if (notify_die(DIE_BPT, "breakpoint", regs, 5, 5, SIGTRAP)
 				== NOTIFY_STOP)
-			return;
+			goto exit;
 
 		if (!(regs->msr & MSR_PR) &&  /* not user-mode */
 		    report_bug(regs->nip, regs) == BUG_TRAP_TYPE_WARN) {
 			regs->nip += 4;
-			return;
+			goto exit;
 		}
 		_exception(SIGTRAP, regs, TRAP_BRKPT, regs->nip);
-		return;
+		goto exit;
 	}
 
 	/* We restore the interrupt state now */
@@ -1036,16 +1058,16 @@ void __kprobes program_check_exception(struct pt_regs *regs)
 	switch (do_mathemu(regs)) {
 	case 0:
 		emulate_single_step(regs);
-		return;
+		goto exit;
 	case 1: {
 			int code = 0;
 			code = __parse_fpscr(current->thread.fpscr.val);
 			_exception(SIGFPE, regs, code, regs->nip);
-			return;
+			goto exit;
 		}
 	case -EFAULT:
 		_exception(SIGSEGV, regs, SEGV_MAPERR, regs->nip);
-		return;
+		goto exit;
 	}
 	/* fall through on any other errors */
 #endif /* CONFIG_MATH_EMULATION */
@@ -1056,10 +1078,10 @@ void __kprobes program_check_exception(struct pt_regs *regs)
 		case 0:
 			regs->nip += 4;
 			emulate_single_step(regs);
-			return;
+			goto exit;
 		case -EFAULT:
 			_exception(SIGSEGV, regs, SEGV_MAPERR, regs->nip);
-			return;
+			goto exit;
 		}
 	}
 
@@ -1067,12 +1089,17 @@ void __kprobes program_check_exception(struct pt_regs *regs)
 		_exception(SIGILL, regs, ILL_PRVOPC, regs->nip);
 	else
 		_exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
+
+exit:
+	exception_exit(regs);
 }
 
 void alignment_exception(struct pt_regs *regs)
 {
 	int sig, code, fixed = 0;
 
+	exception_enter(regs);
+
 	/* We restore the interrupt state now */
 	if (!arch_irq_disabled_regs(regs))
 		local_irq_enable();
@@ -1084,7 +1111,7 @@ void alignment_exception(struct pt_regs *regs)
 	if (fixed == 1) {
 		regs->nip += 4;	/* skip over emulated instruction */
 		emulate_single_step(regs);
-		return;
+		goto exit;
 	}
 
 	/* Operand address was bad */
@@ -1099,6 +1126,9 @@ void alignment_exception(struct pt_regs *regs)
 		_exception(sig, regs, code, regs->dar);
 	else
 		bad_page_fault(regs, regs->dar, sig);
+
+exit:
+	exception_exit(regs);
 }
 
 void StackOverflow(struct pt_regs *regs)
@@ -1127,23 +1157,32 @@ void trace_syscall(struct pt_regs *regs)
 
 void kernel_fp_unavailable_exception(struct pt_regs *regs)
 {
+	exception_enter(regs);
+
 	printk(KERN_EMERG "Unrecoverable FP Unavailable Exception "
 			  "%lx at %lx\n", regs->trap, regs->nip);
 	die("Unrecoverable FP Unavailable Exception", regs, SIGABRT);
+
+	exception_exit(regs);
 }
 
 void altivec_unavailable_exception(struct pt_regs *regs)
 {
+	exception_enter(regs);
+
 	if (user_mode(regs)) {
 		/* A user program has executed an altivec instruction,
 		   but this kernel doesn't support altivec. */
 		_exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
-		return;
+		goto exit;
 	}
 
 	printk(KERN_EMERG "Unrecoverable VMX/Altivec Unavailable Exception "
 			"%lx at %lx\n", regs->trap, regs->nip);
 	die("Unrecoverable VMX/Altivec Unavailable Exception", regs, SIGABRT);
+
+exit:
+	exception_exit(regs);
 }
 
 void vsx_unavailable_exception(struct pt_regs *regs)
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 3a8489a..b1b9542 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -42,6 +42,7 @@
 #include <asm/tlbflush.h>
 #include <asm/siginfo.h>
 #include <asm/debug.h>
+#include <asm/context_tracking.h>
 #include <mm/mmu_decl.h>
 
 #include "icswx.h"
@@ -193,8 +194,8 @@ static int mm_fault_error(struct pt_regs *regs, unsigned long addr, int fault)
  * The return value is 0 if the fault was handled, or the signal
  * number if this is a kernel fault that can't be handled here.
  */
-int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
-			    unsigned long error_code)
+static int __kprobes __do_page_fault(struct pt_regs *regs,
+				unsigned long address, unsigned long error_code)
 {
 	struct vm_area_struct * vma;
 	struct mm_struct *mm = current->mm;
@@ -475,6 +476,16 @@ bad_area_nosemaphore:
 
 }
 
+int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
+			    unsigned long error_code)
+{
+	int ret;
+	exception_enter(regs);
+	ret = __do_page_fault(regs, address, error_code);
+	exception_exit(regs);
+	return ret;
+}
+
 /*
  * bad_page_fault is called when we have a bad access from the kernel.
  * It is called from the DSI and ISI handlers in head.S and from some
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 3a292be..447e5a7 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -55,6 +55,7 @@
 #include <asm/code-patching.h>
 #include <asm/fadump.h>
 #include <asm/firmware.h>
+#include <asm/context_tracking.h>
 
 #ifdef DEBUG
 #define DBG(fmt...) udbg_printf(fmt)
@@ -1083,6 +1084,18 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
 }
 EXPORT_SYMBOL_GPL(hash_page);
 
+int hash_page_ct(unsigned long ea, unsigned long access,
+		 unsigned long trap, struct pt_regs *regs)
+{
+	int ret;
+
+	exception_enter(regs);
+	ret = hash_page(ea, access, trap);
+	exception_exit(regs);
+
+	return ret;
+}
+
 void hash_preload(struct mm_struct *mm, unsigned long ea,
 		  unsigned long access, unsigned long trap)
 {
@@ -1194,6 +1207,8 @@ void flush_hash_range(unsigned long number, int local)
  */
 void low_hash_fault(struct pt_regs *regs, unsigned long address, int rc)
 {
+	exception_enter(regs);
+
 	if (user_mode(regs)) {
 #ifdef CONFIG_PPC_SUBPAGE_PROT
 		if (rc == -2)
@@ -1203,6 +1218,8 @@ void low_hash_fault(struct pt_regs *regs, unsigned long address, int rc)
 			_exception(SIGBUS, regs, BUS_ADRERR, address);
 	} else
 		bad_page_fault(regs, address, SIGBUS);
+
+	exception_exit(regs);
 }
 
 #ifdef CONFIG_DEBUG_PAGEALLOC
-- 
1.7.9.5

Re: [RFC PATCH 2/5] powerpc: Exception hooks for context tracking subsystem

[Frederic Weisbecker]

2013/2/1 Li Zhong <zhong@linux.vnet.ibm.com>:
> This is the exception hooks for context tracking subsystem, including
> data access, program check, single step, instruction breakpoint, machine check,
> alignment, fp unavailable, altivec assist, unknown exception, whose handlers
> might use RCU.
>
> This patch corresponds to
> [PATCH] x86: Exception hooks for userspace RCU extended QS
>   commit 6ba3c97a38803883c2eee489505796cb0a727122
>
> Signed-off-by: Li Zhong <zhong@linux.vnet.ibm.com>

Looks good!

I guess we should move exception_enter/exit definition to the generic
code. They should be the same for all archs after all. Also we are
relying on user_mode(regs) but this may be buggy with some corner
cases. For example if an exception happen after a call to user_exit()
(on syscall exit) but before we actually resume in userspace, the
exception will exit in kernel mode from the context tracking POV.

So instead on relying on the regs, which are not sync with the context
tracking state, we should use something like:

prev_state = exception_enter();
...
exception_exit(prev_state);

Also preempt_schedule_irq() is concerned as well by this problem. So I
should convert it to that scheme as well. I'm going to prepare some
patches.

Feel free to merge this patch in the powerpc tree, I'll do the
conversion along the way.

Thanks.

Re: [RFC PATCH 2/5] powerpc: Exception hooks for context tracking subsystem

[Li Zhong]

On Sun, 2013-02-10 at 15:10 +0100, Frederic Weisbecker wrote:
> 2013/2/1 Li Zhong <zhong@linux.vnet.ibm.com>:
> > This is the exception hooks for context tracking subsystem, including
> > data access, program check, single step, instruction breakpoint, machine check,
> > alignment, fp unavailable, altivec assist, unknown exception, whose handlers
> > might use RCU.
> >
> > This patch corresponds to
> > [PATCH] x86: Exception hooks for userspace RCU extended QS
> >   commit 6ba3c97a38803883c2eee489505796cb0a727122
> >
> > Signed-off-by: Li Zhong <zhong@linux.vnet.ibm.com>
> 
> Looks good!
> 
> I guess we should move exception_enter/exit definition to the generic
> code. They should be the same for all archs after all. 

Indeed.

> Also we are
> relying on user_mode(regs) but this may be buggy with some corner
> cases. For example if an exception happen after a call to user_exit()

I guess you mean user_enter() here, or am I confused?

> (on syscall exit) but before we actually resume in userspace, the
> exception will exit in kernel mode from the context tracking POV.
> 
> So instead on relying on the regs, which are not sync with the context
> tracking state, we should use something like:
> 
> prev_state = exception_enter();
> ...
> exception_exit(prev_state);
> 
> Also preempt_schedule_irq() is concerned as well by this problem. So I
> should convert it to that scheme as well. I'm going to prepare some
> patches.
> 
> Feel free to merge this patch in the powerpc tree, I'll do the
> conversion along the way.

Or if your patches gets merged earlier than these, I can update my code
according to yours.

Thanks, Zhong

> 
> Thanks.
> 

[RFC PATCH 3/5] powerpc: Exit user context on notify resume

[Li Zhong]

This patch allows RCU usage in do_notify_resume, e.g. signal handling.
It corresponds to
[PATCH] x86: Exit RCU extended QS on notify resume
  commit edf55fda35c7dc7f2d9241c3abaddaf759b457c6

Signed-off-by: Li Zhong <zhong@linux.vnet.ibm.com>
---
 arch/powerpc/kernel/signal.c |    5 +++++
 1 file changed, 5 insertions(+)

diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c
index 3b99711..c1eaea2 100644
--- a/arch/powerpc/kernel/signal.c
+++ b/arch/powerpc/kernel/signal.c
@@ -13,6 +13,7 @@
 #include <linux/signal.h>
 #include <linux/uprobes.h>
 #include <linux/key.h>
+#include <linux/context_tracking.h>
 #include <asm/hw_breakpoint.h>
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
@@ -158,6 +159,8 @@ static int do_signal(struct pt_regs *regs)
 
 void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags)
 {
+	user_exit();
+
 	if (thread_info_flags & _TIF_UPROBE)
 		uprobe_notify_resume(regs);
 
@@ -168,6 +171,8 @@ void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags)
 		clear_thread_flag(TIF_NOTIFY_RESUME);
 		tracehook_notify_resume(regs);
 	}
+
+	user_enter();
 }
 
 long sys_sigaltstack(const stack_t __user *uss, stack_t __user *uoss,
-- 
1.7.9.5

[RFC PATCH 4/5] powerpc: Use the new schedule_user API on userspace preemption

[Li Zhong]

This patch corresponds to
[PATCH] x86: Use the new schedule_user API on userspace preemption
  commit 0430499ce9d78691f3985962021b16bf8f8a8048

Signed-off-by: Li Zhong <zhong@linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/context_tracking.h |   11 +++++++++++
 arch/powerpc/kernel/entry_64.S              |    3 ++-
 2 files changed, 13 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/include/asm/context_tracking.h b/arch/powerpc/include/asm/context_tracking.h
index 3adccd8..2e042ba 100644
--- a/arch/powerpc/include/asm/context_tracking.h
+++ b/arch/powerpc/include/asm/context_tracking.h
@@ -1,6 +1,7 @@
 #ifndef _ASM_POWERPC_CONTEXT_TRACKING_H
 #define _ASM_POWERPC_CONTEXT_TRACKING_H
 
+#ifndef __ASSEMBLY__
 #include <linux/context_tracking.h>
 #include <asm/ptrace.h>
 
@@ -17,4 +18,14 @@ static inline void exception_exit(struct pt_regs *regs)
 #endif
 }
 
+#else /* __ASSEMBLY__ */
+
+#ifdef CONFIG_CONTEXT_TRACKING
+#define SCHEDULE_USER bl	.schedule_user
+#else
+#define SCHEDULE_USER bl	.schedule
+#endif
+
+#endif /* !__ASSEMBLY__ */
+
 #endif
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 3d990d3..91f09ec 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -33,6 +33,7 @@
 #include <asm/irqflags.h>
 #include <asm/ftrace.h>
 #include <asm/hw_irq.h>
+#include <asm/context_tracking.h>
 
 /*
  * System calls.
@@ -595,7 +596,7 @@ _GLOBAL(ret_from_except_lite)
 	andi.	r0,r4,_TIF_NEED_RESCHED
 	beq	1f
 	bl	.restore_interrupts
-	bl	.schedule
+	SCHEDULE_USER
 	b	.ret_from_except_lite
 
 1:	bl	.save_nvgprs
-- 
1.7.9.5

[RFC PATCH 5/5] powerpc: select HAVE_CONTEXT_TRACKING for pSeries

[Li Zhong]

Start context tracking support from pSeries.

Signed-off-by: Li Zhong <zhong@linux.vnet.ibm.com>
---
 arch/powerpc/platforms/pseries/Kconfig |    1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig
index 837cf49..a9570fe 100644
--- a/arch/powerpc/platforms/pseries/Kconfig
+++ b/arch/powerpc/platforms/pseries/Kconfig
@@ -17,6 +17,7 @@ config PPC_PSERIES
 	select PPC_NATIVE
 	select PPC_PCI_CHOICE if EXPERT
 	select ZLIB_DEFLATE
+	select HAVE_CONTEXT_TRACKING
 	default y
 
 config PPC_SPLPAR
-- 
1.7.9.5