Merge branch 'tracking-linux-3.x.y' into merge-manifest

11 files changed, 206 insertions, 31 deletions

diff --git a/arch/powerpc/kernel/cpu_setup_power.S b/arch/powerpc/kernel/cpu_setup_power.S
index ea847abb0d0..116700886b3 100644
--- a/arch/powerpc/kernel/cpu_setup_power.S
+++ b/arch/powerpc/kernel/cpu_setup_power.S
@@ -66,6 +66,7 @@ _GLOBAL(__restore_cpu_power8)
 	bl	__init_FSCR
 	mfmsr	r3
 	rldicl.	r0,r3,4,63
+	mtlr	r11
 	beqlr
 	li	r0,0
 	mtspr	SPRN_LPID,r0
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index e514de57a12..4498467ac38 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -851,7 +851,7 @@ resume_kernel:
 	/* check current_thread_info, _TIF_EMULATE_STACK_STORE */
 	CURRENT_THREAD_INFO(r9, r1)
 	lwz	r8,TI_FLAGS(r9)
-	andis.	r8,r8,_TIF_EMULATE_STACK_STORE@h
+	andis.	r0,r8,_TIF_EMULATE_STACK_STORE@h
 	beq+	1f
 
 	addi	r8,r1,INT_FRAME_SIZE	/* Get the kprobed function entry */
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 56bd92362ce..3bbe7edf639 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -797,7 +797,7 @@ hardware_interrupt_relon_hv:
 		_MASKABLE_RELON_EXCEPTION_PSERIES(0x502, hardware_interrupt, EXC_HV, SOFTEN_TEST_HV)
 	FTR_SECTION_ELSE
 		_MASKABLE_RELON_EXCEPTION_PSERIES(0x500, hardware_interrupt, EXC_STD, SOFTEN_TEST_PR)
-	ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_206)
+	ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE)
 	STD_RELON_EXCEPTION_PSERIES(0x4600, 0x600, alignment)
 	STD_RELON_EXCEPTION_PSERIES(0x4700, 0x700, program_check)
 	STD_RELON_EXCEPTION_PSERIES(0x4800, 0x800, fp_unavailable)
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index 0886ae6dd5b..b61363d557b 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -509,6 +509,7 @@ _GLOBAL(copy_and_flush)
 	sync
 	addi	r5,r5,8
 	addi	r6,r6,8
+	isync
 	blr
 
 .align 8
diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c
index 466a2908bb6..611acdf3009 100644
--- a/arch/powerpc/kernel/machine_kexec_64.c
+++ b/arch/powerpc/kernel/machine_kexec_64.c
@@ -17,6 +17,7 @@
 #include <linux/errno.h>
 #include <linux/kernel.h>
 #include <linux/cpu.h>
+#include <linux/hardirq.h>
 
 #include <asm/page.h>
 #include <asm/current.h>
@@ -335,10 +336,13 @@ void default_machine_kexec(struct kimage *image)
 	pr_debug("kexec: Starting switchover sequence.\n");
 
 	/* switch to a staticly allocated stack.  Based on irq stack code.
+	 * We setup preempt_count to avoid using VMX in memcpy.
 	 * XXX: the task struct will likely be invalid once we do the copy!
 	 */
 	kexec_stack.thread_info.task = current_thread_info()->task;
 	kexec_stack.thread_info.flags = 0;
+	kexec_stack.thread_info.preempt_count = HARDIRQ_OFFSET;
+	kexec_stack.thread_info.cpu = current_thread_info()->cpu;
 
 	/* We need a static PACA, too; copy this CPU's PACA over and switch to
 	 * it.  Also poison per_cpu_offset to catch anyone using non-static
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index 1fd6e7b2f39..52add6f3e20 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -19,6 +19,7 @@
 #include <linux/init.h>
 #include <linux/capability.h>
 #include <linux/delay.h>
+#include <linux/cpu.h>
 #include <linux/smp.h>
 #include <linux/completion.h>
 #include <linux/cpumask.h>
@@ -807,6 +808,95 @@ static void rtas_percpu_suspend_me(void *info)
 	__rtas_suspend_cpu((struct rtas_suspend_me_data *)info, 1);
 }
 
+enum rtas_cpu_state {
+	DOWN,
+	UP,
+};
+
+#ifndef CONFIG_SMP
+static int rtas_cpu_state_change_mask(enum rtas_cpu_state state,
+				cpumask_var_t cpus)
+{
+	if (!cpumask_empty(cpus)) {
+		cpumask_clear(cpus);
+		return -EINVAL;
+	} else
+		return 0;
+}
+#else
+/* On return cpumask will be altered to indicate CPUs changed.
+ * CPUs with states changed will be set in the mask,
+ * CPUs with status unchanged will be unset in the mask. */
+static int rtas_cpu_state_change_mask(enum rtas_cpu_state state,
+				cpumask_var_t cpus)
+{
+	int cpu;
+	int cpuret = 0;
+	int ret = 0;
+
+	if (cpumask_empty(cpus))
+		return 0;
+
+	for_each_cpu(cpu, cpus) {
+		switch (state) {
+		case DOWN:
+			cpuret = cpu_down(cpu);
+			break;
+		case UP:
+			cpuret = cpu_up(cpu);
+			break;
+		}
+		if (cpuret) {
+			pr_debug("%s: cpu_%s for cpu#%d returned %d.\n",
+					__func__,
+					((state == UP) ? "up" : "down"),
+					cpu, cpuret);
+			if (!ret)
+				ret = cpuret;
+			if (state == UP) {
+				/* clear bits for unchanged cpus, return */
+				cpumask_shift_right(cpus, cpus, cpu);
+				cpumask_shift_left(cpus, cpus, cpu);
+				break;
+			} else {
+				/* clear bit for unchanged cpu, continue */
+				cpumask_clear_cpu(cpu, cpus);
+			}
+		}
+	}
+
+	return ret;
+}
+#endif
+
+int rtas_online_cpus_mask(cpumask_var_t cpus)
+{
+	int ret;
+
+	ret = rtas_cpu_state_change_mask(UP, cpus);
+
+	if (ret) {
+		cpumask_var_t tmp_mask;
+
+		if (!alloc_cpumask_var(&tmp_mask, GFP_TEMPORARY))
+			return ret;
+
+		/* Use tmp_mask to preserve cpus mask from first failure */
+		cpumask_copy(tmp_mask, cpus);
+		rtas_offline_cpus_mask(tmp_mask);
+		free_cpumask_var(tmp_mask);
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL(rtas_online_cpus_mask);
+
+int rtas_offline_cpus_mask(cpumask_var_t cpus)
+{
+	return rtas_cpu_state_change_mask(DOWN, cpus);
+}
+EXPORT_SYMBOL(rtas_offline_cpus_mask);
+
 int rtas_ibm_suspend_me(struct rtas_args *args)
 {
 	long state;
@@ -814,6 +904,8 @@ int rtas_ibm_suspend_me(struct rtas_args *args)
 	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
 	struct rtas_suspend_me_data data;
 	DECLARE_COMPLETION_ONSTACK(done);
+	cpumask_var_t offline_mask;
+	int cpuret;
 
 	if (!rtas_service_present("ibm,suspend-me"))
 		return -ENOSYS;
@@ -837,11 +929,24 @@ int rtas_ibm_suspend_me(struct rtas_args *args)
 		return 0;
 	}
 
+	if (!alloc_cpumask_var(&offline_mask, GFP_TEMPORARY))
+		return -ENOMEM;
+
 	atomic_set(&data.working, 0);
 	atomic_set(&data.done, 0);
 	atomic_set(&data.error, 0);
 	data.token = rtas_token("ibm,suspend-me");
 	data.complete = &done;
+
+	/* All present CPUs must be online */
+	cpumask_andnot(offline_mask, cpu_present_mask, cpu_online_mask);
+	cpuret = rtas_online_cpus_mask(offline_mask);
+	if (cpuret) {
+		pr_err("%s: Could not bring present CPUs online.\n", __func__);
+		atomic_set(&data.error, cpuret);
+		goto out;
+	}
+
 	stop_topology_update();
 
 	/* Call function on all CPUs.  One of us will make the
@@ -857,6 +962,14 @@ int rtas_ibm_suspend_me(struct rtas_args *args)
 
 	start_topology_update();
 
+	/* Take down CPUs not online prior to suspend */
+	cpuret = rtas_offline_cpus_mask(offline_mask);
+	if (cpuret)
+		pr_warn("%s: Could not restore CPUs to offline state.\n",
+				__func__);
+
+out:
+	free_cpumask_var(offline_mask);
 	return atomic_read(&data.error);
 }
 #else /* CONFIG_PPC_PSERIES */
diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c
index cf12eae02de..78760b81350 100644
--- a/arch/powerpc/kernel/signal.c
+++ b/arch/powerpc/kernel/signal.c
@@ -17,6 +17,7 @@
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
 #include <asm/debug.h>
+#include <asm/tm.h>
 
 #include "signal.h"
 
@@ -29,13 +30,13 @@ int show_unhandled_signals = 0;
 /*
  * Allocate space for the signal frame
  */
-void __user * get_sigframe(struct k_sigaction *ka, struct pt_regs *regs,
+void __user * get_sigframe(struct k_sigaction *ka, unsigned long sp,
 			   size_t frame_size, int is_32)
 {
         unsigned long oldsp, newsp;
 
         /* Default to using normal stack */
-        oldsp = get_clean_sp(regs, is_32);
+        oldsp = get_clean_sp(sp, is_32);
 
 	/* Check for alt stack */
 	if ((ka->sa.sa_flags & SA_ONSTACK) &&
@@ -170,3 +171,38 @@ void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags)
 		tracehook_notify_resume(regs);
 	}
 }
+
+unsigned long get_tm_stackpointer(struct pt_regs *regs)
+{
+	/* When in an active transaction that takes a signal, we need to be
+	 * careful with the stack.  It's possible that the stack has moved back
+	 * up after the tbegin.  The obvious case here is when the tbegin is
+	 * called inside a function that returns before a tend.  In this case,
+	 * the stack is part of the checkpointed transactional memory state.
+	 * If we write over this non transactionally or in suspend, we are in
+	 * trouble because if we get a tm abort, the program counter and stack
+	 * pointer will be back at the tbegin but our in memory stack won't be
+	 * valid anymore.
+	 *
+	 * To avoid this, when taking a signal in an active transaction, we
+	 * need to use the stack pointer from the checkpointed state, rather
+	 * than the speculated state.  This ensures that the signal context
+	 * (written tm suspended) will be written below the stack required for
+	 * the rollback.  The transaction is aborted becuase of the treclaim,
+	 * so any memory written between the tbegin and the signal will be
+	 * rolled back anyway.
+	 *
+	 * For signals taken in non-TM or suspended mode, we use the
+	 * normal/non-checkpointed stack pointer.
+	 */
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	if (MSR_TM_ACTIVE(regs->msr)) {
+		tm_enable();
+		tm_reclaim(&current->thread, regs->msr, TM_CAUSE_SIGNAL);
+		if (MSR_TM_TRANSACTIONAL(regs->msr))
+			return current->thread.ckpt_regs.gpr[1];
+	}
+#endif
+	return regs->gpr[1];
+}
diff --git a/arch/powerpc/kernel/signal.h b/arch/powerpc/kernel/signal.h
index ec84c901cea..c69b9aeb9f2 100644
--- a/arch/powerpc/kernel/signal.h
+++ b/arch/powerpc/kernel/signal.h
@@ -12,7 +12,7 @@
 
 extern void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags);
 
-extern void __user * get_sigframe(struct k_sigaction *ka, struct pt_regs *regs,
+extern void __user * get_sigframe(struct k_sigaction *ka, unsigned long sp,
 				  size_t frame_size, int is_32);
 
 extern int handle_signal32(unsigned long sig, struct k_sigaction *ka,
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index 95068bf569a..201385c3a1a 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -503,12 +503,6 @@ static int save_tm_user_regs(struct pt_regs *regs,
 {
 	unsigned long msr = regs->msr;
 
-	/* tm_reclaim rolls back all reg states, updating thread.ckpt_regs,
-	 * thread.transact_fpr[], thread.transact_vr[], etc.
-	 */
-	tm_enable();
-	tm_reclaim(&current->thread, msr, TM_CAUSE_SIGNAL);
-
 	/* Make sure floating point registers are stored in regs */
 	flush_fp_to_thread(current);
 
@@ -965,7 +959,7 @@ int handle_rt_signal32(unsigned long sig, struct k_sigaction *ka,
 
 	/* Set up Signal Frame */
 	/* Put a Real Time Context onto stack */
-	rt_sf = get_sigframe(ka, regs, sizeof(*rt_sf), 1);
+	rt_sf = get_sigframe(ka, get_tm_stackpointer(regs), sizeof(*rt_sf), 1);
 	addr = rt_sf;
 	if (unlikely(rt_sf == NULL))
 		goto badframe;
@@ -1403,7 +1397,7 @@ int handle_signal32(unsigned long sig, struct k_sigaction *ka,
 	unsigned long tramp;
 
 	/* Set up Signal Frame */
-	frame = get_sigframe(ka, regs, sizeof(*frame), 1);
+	frame = get_sigframe(ka, get_tm_stackpointer(regs), sizeof(*frame), 1);
 	if (unlikely(frame == NULL))
 		goto badframe;
 	sc = (struct sigcontext __user *) &frame->sctx;
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index c1794286098..345947367ec 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -154,11 +154,12 @@ static long setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs,
  * As above, but Transactional Memory is in use, so deliver sigcontexts
  * containing checkpointed and transactional register states.
  *
- * To do this, we treclaim to gather both sets of registers and set up the
- * 'normal' sigcontext registers with rolled-back register values such that a
- * simple signal handler sees a correct checkpointed register state.
- * If interested, a TM-aware sighandler can examine the transactional registers
- * in the 2nd sigcontext to determine the real origin of the signal.
+ * To do this, we treclaim (done before entering here) to gather both sets of
+ * registers and set up the 'normal' sigcontext registers with rolled-back
+ * register values such that a simple signal handler sees a correct
+ * checkpointed register state.  If interested, a TM-aware sighandler can
+ * examine the transactional registers in the 2nd sigcontext to determine the
+ * real origin of the signal.
  */
 static long setup_tm_sigcontexts(struct sigcontext __user *sc,
 				 struct sigcontext __user *tm_sc,
@@ -184,16 +185,6 @@ static long setup_tm_sigcontexts(struct sigcontext __user *sc,
 
 	BUG_ON(!MSR_TM_ACTIVE(regs->msr));
 
-	/* tm_reclaim rolls back all reg states, saving checkpointed (older)
-	 * GPRs to thread.ckpt_regs and (if used) FPRs to (newer)
-	 * thread.transact_fp and/or VRs to (newer) thread.transact_vr.
-	 * THEN we save out FP/VRs, if necessary, to the checkpointed (older)
-	 * thread.fr[]/vr[]s.  The transactional (newer) GPRs are on the
-	 * stack, in *regs.
-	 */
-	tm_enable();
-	tm_reclaim(&current->thread, msr, TM_CAUSE_SIGNAL);
-
 	flush_fp_to_thread(current);
 
 #ifdef CONFIG_ALTIVEC
@@ -711,7 +702,7 @@ int handle_rt_signal64(int signr, struct k_sigaction *ka, siginfo_t *info,
 	unsigned long newsp = 0;
 	long err = 0;
 
-	frame = get_sigframe(ka, regs, sizeof(*frame), 0);
+	frame = get_sigframe(ka, get_tm_stackpointer(regs), sizeof(*frame), 0);
 	if (unlikely(frame == NULL))
 		goto badframe;
 
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 37cc40ef504..1c22b2d580b 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -52,6 +52,7 @@
 #ifdef CONFIG_PPC64
 #include <asm/firmware.h>
 #include <asm/processor.h>
+#include <asm/tm.h>
 #endif
 #include <asm/kexec.h>
 #include <asm/ppc-opcode.h>
@@ -913,6 +914,28 @@ static int emulate_isel(struct pt_regs *regs, u32 instword)
 	return 0;
 }
 
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+static inline bool tm_abort_check(struct pt_regs *regs, int cause)
+{
+        /* If we're emulating a load/store in an active transaction, we cannot
+         * emulate it as the kernel operates in transaction suspended context.
+         * We need to abort the transaction.  This creates a persistent TM
+         * abort so tell the user what caused it with a new code.
+	 */
+	if (MSR_TM_TRANSACTIONAL(regs->msr)) {
+		tm_enable();
+		tm_abort(cause);
+		return true;
+	}
+	return false;
+}
+#else
+static inline bool tm_abort_check(struct pt_regs *regs, int reason)
+{
+	return false;
+}
+#endif
+
 static int emulate_instruction(struct pt_regs *regs)
 {
 	u32 instword;
@@ -952,6 +975,9 @@ static int emulate_instruction(struct pt_regs *regs)
 
 	/* Emulate load/store string insn. */
 	if ((instword & PPC_INST_STRING_GEN_MASK) == PPC_INST_STRING) {
+		if (tm_abort_check(regs,
+				   TM_CAUSE_EMULATE | TM_CAUSE_PERSISTENT))
+			return -EINVAL;
 		PPC_WARN_EMULATED(string, regs);
 		return emulate_string_inst(regs, instword);
 	}
@@ -970,7 +996,10 @@ static int emulate_instruction(struct pt_regs *regs)
 
 #ifdef CONFIG_PPC64
 	/* Emulate the mfspr rD, DSCR. */
-	if (((instword & PPC_INST_MFSPR_DSCR_MASK) == PPC_INST_MFSPR_DSCR) &&
+	if ((((instword & PPC_INST_MFSPR_DSCR_USER_MASK) ==
+		PPC_INST_MFSPR_DSCR_USER) ||
+	     ((instword & PPC_INST_MFSPR_DSCR_MASK) ==
+		PPC_INST_MFSPR_DSCR)) &&
 			cpu_has_feature(CPU_FTR_DSCR)) {
 		PPC_WARN_EMULATED(mfdscr, regs);
 		rd = (instword >> 21) & 0x1f;
@@ -978,7 +1007,10 @@ static int emulate_instruction(struct pt_regs *regs)
 		return 0;
 	}
 	/* Emulate the mtspr DSCR, rD. */
-	if (((instword & PPC_INST_MTSPR_DSCR_MASK) == PPC_INST_MTSPR_DSCR) &&
+	if ((((instword & PPC_INST_MTSPR_DSCR_USER_MASK) ==
+		PPC_INST_MTSPR_DSCR_USER) ||
+	     ((instword & PPC_INST_MTSPR_DSCR_MASK) ==
+		PPC_INST_MTSPR_DSCR)) &&
 			cpu_has_feature(CPU_FTR_DSCR)) {
 		PPC_WARN_EMULATED(mtdscr, regs);
 		rd = (instword >> 21) & 0x1f;
@@ -1118,6 +1150,9 @@ void alignment_exception(struct pt_regs *regs)
 	if (!arch_irq_disabled_regs(regs))
 		local_irq_enable();
 
+	if (tm_abort_check(regs, TM_CAUSE_ALIGNMENT | TM_CAUSE_PERSISTENT))
+		goto bail;
+
 	/* we don't implement logging of alignment exceptions */
 	if (!(current->thread.align_ctl & PR_UNALIGN_SIGBUS))
 		fixed = fix_alignment(regs);