Merge branch 'merge' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc

Pull powerpc fixes from Benjamin Herrenschmidt:
 "Here are a few fixes for 3.6 that were piling up while I was away or
  busy (I was mostly MIA a week or two before San Diego).

  Some fixes from Anton fixing up issues with our relatively new DSCR
  control feature, and a few other fixes that are either regressions or
  bugs nasty enough to warrant not waiting."

* 'merge' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc:
  powerpc: Don't use __put_user() in patch_instruction
  powerpc: Make sure IPI handlers see data written by IPI senders
  powerpc: Restore correct DSCR in context switch
  powerpc: Fix DSCR inheritance in copy_thread()
  powerpc: Keep thread.dscr and thread.dscr_inherit in sync
  powerpc: Update DSCR on all CPUs when writing sysfs dscr_default
  powerpc/powernv: Always go into nap mode when CPU is offline
  powerpc: Give hypervisor decrementer interrupts their own handler
  powerpc/vphn: Fix arch_update_cpu_topology() return value

15 files changed, 68 insertions, 34 deletions

diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index 53b6dfa8334..54b73a28c20 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -386,6 +386,7 @@ extern unsigned long cpuidle_disable;
 enum idle_boot_override {IDLE_NO_OVERRIDE = 0, IDLE_POWERSAVE_OFF};
 
 extern int powersave_nap;       /* set if nap mode can be used in idle loop */
+extern void power7_nap(void);
 
 #ifdef CONFIG_PSERIES_IDLE
 extern void update_smt_snooze_delay(int snooze);
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 85b05c463fa..e8995727b1c 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -76,6 +76,7 @@ int main(void)
         DEFINE(SIGSEGV, SIGSEGV);
         DEFINE(NMI_MASK, NMI_MASK);
         DEFINE(THREAD_DSCR, offsetof(struct thread_struct, dscr));
+        DEFINE(THREAD_DSCR_INHERIT, offsetof(struct thread_struct, dscr_inherit));
 #else
         DEFINE(THREAD_INFO, offsetof(struct task_struct, stack));
 #endif /* CONFIG_PPC64 */
diff --git a/arch/powerpc/kernel/dbell.c b/arch/powerpc/kernel/dbell.c
index 5b25c8060fd..a892680668d 100644
--- a/arch/powerpc/kernel/dbell.c
+++ b/arch/powerpc/kernel/dbell.c
@@ -28,6 +28,8 @@ void doorbell_setup_this_cpu(void)
 
 void doorbell_cause_ipi(int cpu, unsigned long data)
 {
+        /* Order previous accesses vs. msgsnd, which is treated as a store */
+        mb();
         ppc_msgsnd(PPC_DBELL, 0, data);
 }
 
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 4b01a25e29e..b40e0b4815b 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -370,6 +370,12 @@ _GLOBAL(ret_from_fork)
         li      r3,0
         b       syscall_exit
 
+        .section        ".toc","aw"
+DSCR_DEFAULT:
+        .tc dscr_default[TC],dscr_default
+
+        .section        ".text"
+
 /*
  * This routine switches between two different tasks.  The process
  * state of one is saved on its kernel stack.  Then the state
@@ -509,9 +515,6 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
         mr      r1,r8           /* start using new stack pointer */
         std     r7,PACAKSAVE(r13)
 
-        ld      r6,_CCR(r1)
-        mtcrf   0xFF,r6
-
 #ifdef CONFIG_ALTIVEC
 BEGIN_FTR_SECTION
         ld      r0,THREAD_VRSAVE(r4)
@@ -520,14 +523,22 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 #endif /* CONFIG_ALTIVEC */
 #ifdef CONFIG_PPC64
 BEGIN_FTR_SECTION
+        lwz     r6,THREAD_DSCR_INHERIT(r4)
+        ld      r7,DSCR_DEFAULT@toc(2)
         ld      r0,THREAD_DSCR(r4)
-        cmpd    r0,r25
-        beq     1f
+        cmpwi   r6,0
+        bne     1f
+        ld      r0,0(r7)
+1:      cmpd    r0,r25
+        beq     2f
         mtspr   SPRN_DSCR,r0
-1:      
+2:
 END_FTR_SECTION_IFSET(CPU_FTR_DSCR)
 #endif
 
+        ld      r6,_CCR(r1)
+        mtcrf   0xFF,r6
+
         /* r3-r13 are destroyed -- Cort */
         REST_8GPRS(14, r1)
         REST_10GPRS(22, r1)
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index e894515e77b..39aa97d3ff8 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -186,7 +186,7 @@ hardware_interrupt_hv:
         KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x800)
 
         MASKABLE_EXCEPTION_PSERIES(0x900, 0x900, decrementer)
-        MASKABLE_EXCEPTION_HV(0x980, 0x982, decrementer)
+        STD_EXCEPTION_HV(0x980, 0x982, hdecrementer)
 
         STD_EXCEPTION_PSERIES(0xa00, 0xa00, trap_0a)
         KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xa00)
@@ -486,6 +486,7 @@ machine_check_common:
 
         STD_EXCEPTION_COMMON_ASYNC(0x500, hardware_interrupt, do_IRQ)
         STD_EXCEPTION_COMMON_ASYNC(0x900, decrementer, .timer_interrupt)
+        STD_EXCEPTION_COMMON(0x980, hdecrementer, .hdec_interrupt)
         STD_EXCEPTION_COMMON(0xa00, trap_0a, .unknown_exception)
         STD_EXCEPTION_COMMON(0xb00, trap_0b, .unknown_exception)
         STD_EXCEPTION_COMMON(0xd00, single_step, .single_step_exception)
diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S
index 7140d838339..e11863f4e59 100644
--- a/arch/powerpc/kernel/idle_power7.S
+++ b/arch/powerpc/kernel/idle_power7.S
@@ -28,7 +28,9 @@ _GLOBAL(power7_idle)
         lwz     r4,ADDROFF(powersave_nap)(r3)
         cmpwi   0,r4,0
         beqlr
+        /* fall through */
 
+_GLOBAL(power7_nap)
         /* NAP is a state loss, we create a regs frame on the
          * stack, fill it up with the state we care about and
          * stick a pointer to it in PACAR1. We really only
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 710f400476d..1a1f2ddfb58 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -802,16 +802,8 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
 #endif /* CONFIG_PPC_STD_MMU_64 */
 #ifdef CONFIG_PPC64 
         if (cpu_has_feature(CPU_FTR_DSCR)) {
-                if (current->thread.dscr_inherit) {
-                        p->thread.dscr_inherit = 1;
-                        p->thread.dscr = current->thread.dscr;
-                } else if (0 != dscr_default) {
-                        p->thread.dscr_inherit = 1;
-                        p->thread.dscr = dscr_default;
-                } else {
-                        p->thread.dscr_inherit = 0;
-                        p->thread.dscr = 0;
-                }
+                p->thread.dscr_inherit = current->thread.dscr_inherit;
+                p->thread.dscr = current->thread.dscr;
         }
 #endif
 
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 0321007086f..8d4214afc21 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -198,8 +198,15 @@ void smp_muxed_ipi_message_pass(int cpu, int msg)
         struct cpu_messages *info = &per_cpu(ipi_message, cpu);
         char *message = (char *)&info->messages;
 
+        /*
+         * Order previous accesses before accesses in the IPI handler.
+         */
+        smp_mb();
         message[msg] = 1;
-        mb();
+        /*
+         * cause_ipi functions are required to include a full barrier
+         * before doing whatever causes the IPI.
+         */
         smp_ops->cause_ipi(cpu, info->data);
 }
 
@@ -211,7 +218,7 @@ irqreturn_t smp_ipi_demux(void)
         mb();   /* order any irq clear */
 
         do {
-                all = xchg_local(&info->messages, 0);
+                all = xchg(&info->messages, 0);
 
 #ifdef __BIG_ENDIAN
                 if (all & (1 << (24 - 8 * PPC_MSG_CALL_FUNCTION)))
diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index 3529446c2ab..8302af64921 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -194,6 +194,14 @@ static ssize_t show_dscr_default(struct device *dev,
         return sprintf(buf, "%lx\n", dscr_default);
 }
 
+static void update_dscr(void *dummy)
+{
+        if (!current->thread.dscr_inherit) {
+                current->thread.dscr = dscr_default;
+                mtspr(SPRN_DSCR, dscr_default);
+        }
+}
+
 static ssize_t __used store_dscr_default(struct device *dev,
                 struct device_attribute *attr, const char *buf,
                 size_t count)
@@ -206,6 +214,8 @@ static ssize_t __used store_dscr_default(struct device *dev,
                 return -EINVAL;
         dscr_default = val;
 
+        on_each_cpu(update_dscr, NULL, 1);
+
         return count;
 }
 
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index be171ee73bf..e49e93191b6 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -535,6 +535,15 @@ void timer_interrupt(struct pt_regs * regs)
         trace_timer_interrupt_exit(regs);
 }
 
+/*
+ * Hypervisor decrementer interrupts shouldn't occur but are sometimes
+ * left pending on exit from a KVM guest.  We don't need to do anything
+ * to clear them, as they are edge-triggered.
+ */
+void hdec_interrupt(struct pt_regs *regs)
+{
+}
+
 #ifdef CONFIG_SUSPEND
 static void generic_suspend_disable_irqs(void)
 {
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 158972341a2..ae0843fa7a6 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -972,8 +972,9 @@ static int emulate_instruction(struct pt_regs *regs)
                         cpu_has_feature(CPU_FTR_DSCR)) {
                 PPC_WARN_EMULATED(mtdscr, regs);
                 rd = (instword >> 21) & 0x1f;
-                mtspr(SPRN_DSCR, regs->gpr[rd]);
+                current->thread.dscr = regs->gpr[rd];
                 current->thread.dscr_inherit = 1;
+                mtspr(SPRN_DSCR, current->thread.dscr);
                 return 0;
         }
 #endif
diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c
index dd223b3eb33..17e5b236431 100644
--- a/arch/powerpc/lib/code-patching.c
+++ b/arch/powerpc/lib/code-patching.c
@@ -20,7 +20,7 @@ int patch_instruction(unsigned int *addr, unsigned int instr)
 {
         int err;
 
-        err = __put_user(instr, addr);
+        __put_user_size(instr, addr, 4, err);
         if (err)
                 return err;
         asm ("dcbst 0, %0; sync; icbi 0,%0; sync; isync" : : "r" (addr));
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 39b159751c3..59213cfaeca 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -1436,11 +1436,11 @@ static long vphn_get_associativity(unsigned long cpu,
 
 /*
  * Update the node maps and sysfs entries for each cpu whose home node
- * has changed.
+ * has changed. Returns 1 when the topology has changed, and 0 otherwise.
  */
 int arch_update_cpu_topology(void)
 {
-        int cpu, nid, old_nid;
+        int cpu, nid, old_nid, changed = 0;
         unsigned int associativity[VPHN_ASSOC_BUFSIZE] = {0};
         struct device *dev;
 
@@ -1466,9 +1466,10 @@ int arch_update_cpu_topology(void)
                 dev = get_cpu_device(cpu);
                 if (dev)
                         kobject_uevent(&dev->kobj, KOBJ_CHANGE);
+                changed = 1;
         }
 
-        return 1;
+        return changed;
 }
 
 static void topology_work_fn(struct work_struct *work)
diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c
index 3ef46254c35..7698b6e13c5 100644
--- a/arch/powerpc/platforms/powernv/smp.c
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -106,14 +106,6 @@ static void pnv_smp_cpu_kill_self(void)
 {
         unsigned int cpu;
 
-        /* If powersave_nap is enabled, use NAP mode, else just
-         * spin aimlessly
-         */
-        if (!powersave_nap) {
-                generic_mach_cpu_die();
-                return;
-        }
-
         /* Standard hot unplug procedure */
         local_irq_disable();
         idle_task_exit();
@@ -128,7 +120,7 @@ static void pnv_smp_cpu_kill_self(void)
          */
         mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~(u64)LPCR_PECE1);
         while (!generic_check_cpu_restart(cpu)) {
-                power7_idle();
+                power7_nap();
                 if (!generic_check_cpu_restart(cpu)) {
                         DBG("CPU%d Unexpected exit while offline !\n", cpu);
                         /* We may be getting an IPI, so we re-enable
diff --git a/arch/powerpc/sysdev/xics/icp-hv.c b/arch/powerpc/sysdev/xics/icp-hv.c
index 14469cf9df6..df0fc582146 100644
--- a/arch/powerpc/sysdev/xics/icp-hv.c
+++ b/arch/powerpc/sysdev/xics/icp-hv.c
@@ -65,7 +65,11 @@ static inline void icp_hv_set_xirr(unsigned int value)
 static inline void icp_hv_set_qirr(int n_cpu , u8 value)
 {
         int hw_cpu = get_hard_smp_processor_id(n_cpu);
-        long rc = plpar_hcall_norets(H_IPI, hw_cpu, value);
+        long rc;
+
+        /* Make sure all previous accesses are ordered before IPI sending */
+        mb();
+        rc = plpar_hcall_norets(H_IPI, hw_cpu, value);
         if (rc != H_SUCCESS) {
                 pr_err("%s: bad return code qirr cpu=%d hw_cpu=%d mfrr=0x%x "
                         "returned %ld\n", __func__, n_cpu, hw_cpu, value, rc);