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

@@ -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

@@ -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 */

@@ -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)

@@ -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

@@ -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

@@ -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,

@@ -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

@@ -1,6 +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

@@ -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

@@ -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)

@@ -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();
 }