13 files changed, 86 insertions, 78 deletions

diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index c9bc78e9c610..7429556eb8df 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -168,10 +168,10 @@ static size_t eeh_dump_dev_log(struct eeh_dev *edev, char *buf, size_t len)
         int n = 0, l = 0;
         char buffer[128];
 
-        n += scnprintf(buf+n, len-n, "%04x:%02x:%02x:%01x\n",
+        n += scnprintf(buf+n, len-n, "%04x:%02x:%02x.%01x\n",
                        edev->phb->global_number, pdn->busno,
                        PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn));
-        pr_warn("EEH: of node=%04x:%02x:%02x:%01x\n",
+        pr_warn("EEH: of node=%04x:%02x:%02x.%01x\n",
                 edev->phb->global_number, pdn->busno,
                 PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn));
 
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 41091fdf9bd8..df6d45eb4115 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -144,29 +144,14 @@ machine_check_pSeries_1:
          * vector
          */
         SET_SCRATCH0(r13)               /* save r13 */
-#ifdef CONFIG_PPC_P7_NAP
-BEGIN_FTR_SECTION
-        /* Running native on arch 2.06 or later, check if we are
-         * waking up from nap. We only handle no state loss and
-         * supervisor state loss. We do -not- handle hypervisor
-         * state loss at this time.
+        /*
+         * Running native on arch 2.06 or later, we may wakeup from winkle
+         * inside machine check. If yes, then last bit of HSPGR0 would be set
+         * to 1. Hence clear it unconditionally.
          */
-        mfspr   r13,SPRN_SRR1
-        rlwinm. r13,r13,47-31,30,31
-        OPT_GET_SPR(r13, SPRN_CFAR, CPU_FTR_CFAR)
-        beq     9f
-
-        mfspr   r13,SPRN_SRR1
-        rlwinm. r13,r13,47-31,30,31
-        /* waking up from powersave (nap) state */
-        cmpwi   cr1,r13,2
-        /* Total loss of HV state is fatal. let's just stay stuck here */
-        OPT_GET_SPR(r13, SPRN_CFAR, CPU_FTR_CFAR)
-        bgt     cr1,.
-9:
-        OPT_SET_SPR(r13, SPRN_CFAR, CPU_FTR_CFAR)
-END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
-#endif /* CONFIG_PPC_P7_NAP */
+        GET_PACA(r13)
+        clrrdi  r13,r13,1
+        SET_PACA(r13)
         EXCEPTION_PROLOG_0(PACA_EXMC)
 BEGIN_FTR_SECTION
         b       machine_check_powernv_early
@@ -1273,25 +1258,51 @@ machine_check_handle_early:
          * Check if thread was in power saving mode. We come here when any
          * of the following is true:
          * a. thread wasn't in power saving mode
-         * b. thread was in power saving mode with no state loss or
-         *    supervisor state loss
+         * b. thread was in power saving mode with no state loss,
+         *    supervisor state loss or hypervisor state loss.
          *
-         * Go back to nap again if (b) is true.
+         * Go back to nap/sleep/winkle mode again if (b) is true.
          */
         rlwinm. r11,r12,47-31,30,31     /* Was it in power saving mode? */
         beq     4f                      /* No, it wasn;t */
         /* Thread was in power saving mode. Go back to nap again. */
         cmpwi   r11,2
-        bne     3f
-        /* Supervisor state loss */
+        blt     3f
+        /* Supervisor/Hypervisor state loss */
         li      r0,1
         stb     r0,PACA_NAPSTATELOST(r13)
 3:      bl      machine_check_queue_event
         MACHINE_CHECK_HANDLER_WINDUP
         GET_PACA(r13)
         ld      r1,PACAR1(r13)
-        li      r3,PNV_THREAD_NAP
-        b       pnv_enter_arch207_idle_mode
+        /*
+         * Check what idle state this CPU was in and go back to same mode
+         * again.
+         */
+        lbz     r3,PACA_THREAD_IDLE_STATE(r13)
+        cmpwi   r3,PNV_THREAD_NAP
+        bgt     10f
+        IDLE_STATE_ENTER_SEQ(PPC_NAP)
+        /* No return */
+10:
+        cmpwi   r3,PNV_THREAD_SLEEP
+        bgt     2f
+        IDLE_STATE_ENTER_SEQ(PPC_SLEEP)
+        /* No return */
+
+2:
+        /*
+         * Go back to winkle. Please note that this thread was woken up in
+         * machine check from winkle and have not restored the per-subcore
+         * state. Hence before going back to winkle, set last bit of HSPGR0
+         * to 1. This will make sure that if this thread gets woken up
+         * again at reset vector 0x100 then it will get chance to restore
+         * the subcore state.
+         */
+        ori     r13,r13,1
+        SET_PACA(r13)
+        IDLE_STATE_ENTER_SEQ(PPC_WINKLE)
+        /* No return */
 4:
 #endif
         /*
diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S
index ba79d15f4ddd..2265c6398a17 100644
--- a/arch/powerpc/kernel/idle_book3s.S
+++ b/arch/powerpc/kernel/idle_book3s.S
@@ -44,18 +44,6 @@
                                 PSSCR_PSLL_MASK | PSSCR_TR_MASK | \
                                 PSSCR_MTL_MASK
 
-/* Idle state entry routines */
-
-#define IDLE_STATE_ENTER_SEQ(IDLE_INST)                         \
-        /* Magic NAP/SLEEP/WINKLE mode enter sequence */        \
-        std     r0,0(r1);                                       \
-        ptesync;                                                \
-        ld      r0,0(r1);                                       \
-1:      cmp     cr0,r0,r0;                                      \
-        bne     1b;                                             \
-        IDLE_INST;                                              \
-        b       .
-
         .text
 
 /*
@@ -363,8 +351,8 @@ _GLOBAL(power9_idle_stop)
  * cr3 - set to gt if waking up with partial/complete hypervisor state loss
  */
 _GLOBAL(pnv_restore_hyp_resource)
-        ld      r2,PACATOC(r13);
 BEGIN_FTR_SECTION
+        ld      r2,PACATOC(r13);
         /*
          * POWER ISA 3. Use PSSCR to determine if we
          * are waking up from deep idle state
@@ -395,6 +383,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
          */
         clrldi  r5,r13,63
         clrrdi  r13,r13,1
+
+        /* Now that we are sure r13 is corrected, load TOC */
+        ld      r2,PACATOC(r13);
         cmpwi   cr4,r5,1
         mtspr   SPRN_HSPRG0,r13
 
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index ef267fd9dd22..5e7ece0fda9f 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -92,7 +92,8 @@ void save_mce_event(struct pt_regs *regs, long handled,
         mce->in_use = 1;
 
         mce->initiator = MCE_INITIATOR_CPU;
-        if (handled)
+        /* Mark it recovered if we have handled it and MSR(RI=1). */
+        if (handled && (regs->msr & MSR_RI))
                 mce->disposition = MCE_DISPOSITION_RECOVERED;
         else
                 mce->disposition = MCE_DISPOSITION_NOT_RECOVERED;
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index a5c0153ede37..7fdf324d5b51 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -78,6 +78,7 @@ EXPORT_SYMBOL(get_pci_dma_ops);
 static int get_phb_number(struct device_node *dn)
 {
         int ret, phb_id = -1;
+        u32 prop_32;
         u64 prop;
 
         /*
@@ -86,8 +87,10 @@ static int get_phb_number(struct device_node *dn)
          * reading "ibm,opal-phbid", only present in OPAL environment.
          */
         ret = of_property_read_u64(dn, "ibm,opal-phbid", &prop);
-        if (ret)
-                ret = of_property_read_u32_index(dn, "reg", 1, (u32 *)&prop);
+        if (ret) {
+                ret = of_property_read_u32_index(dn, "reg", 1, &prop_32);
+                prop = prop_32;
+        }
 
         if (!ret)
                 phb_id = (int)(prop & (MAX_PHBS - 1));
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 58ccf86415b4..9ee2623e0f67 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1074,26 +1074,6 @@ static inline void restore_sprs(struct thread_struct *old_thread,
 #endif
 }
 
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-void flush_tmregs_to_thread(struct task_struct *tsk)
-{
-        /*
-         * Process self tracing is not yet supported through
-         * ptrace interface. Ptrace generic code should have
-         * prevented this from happening in the first place.
-         * Warn once here with the message, if some how it
-         * is attempted.
-         */
-        WARN_ONCE(tsk == current,
-                "Not expecting ptrace on self: TM regs may be incorrect\n");
-
-        /*
-         * If task is not current, it should have been flushed
-         * already to it's thread_struct during __switch_to().
-         */
-}
-#endif
-
 struct task_struct *__switch_to(struct task_struct *prev,
         struct task_struct *new)
 {
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index 6ee4b72cda42..4e74fc588a3f 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -2940,7 +2940,7 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4,
 
         /* Don't print anything after quiesce under OPAL, it crashes OFW */
         if (of_platform != PLATFORM_OPAL) {
-                prom_printf("Booting Linux via __start() ...\n");
+                prom_printf("Booting Linux via __start() @ 0x%lx ...\n", kbase);
                 prom_debug("->dt_header_start=0x%x\n", hdr);
         }
 
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index 4f3c5756cc09..bf91658a8a40 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -38,6 +38,7 @@
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/switch_to.h>
+#include <asm/tm.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/syscalls.h>
@@ -118,6 +119,24 @@ static const struct pt_regs_offset regoffset_table[] = {
         REG_OFFSET_END,
 };
 
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+static void flush_tmregs_to_thread(struct task_struct *tsk)
+{
+        /*
+         * If task is not current, it will have been flushed already to
+         * it's thread_struct during __switch_to().
+         *
+         * A reclaim flushes ALL the state.
+         */
+
+        if (tsk == current && MSR_TM_SUSPENDED(mfmsr()))
+                tm_reclaim_current(TM_CAUSE_SIGNAL);
+
+}
+#else
+static inline void flush_tmregs_to_thread(struct task_struct *tsk) { }
+#endif
+
 /**
  * regs_query_register_offset() - query register offset from its name
  * @name:       the name of a register
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index c3e861df4b20..24ec3ea4b3a2 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -93,15 +93,16 @@ notrace unsigned long __init early_init(unsigned long dt_ptr)
  * and we are running with enough of the MMU enabled to have our
  * proper kernel virtual addresses
  *
- * Find out what kind of machine we're on and save any data we need
- * from the early boot process (devtree is copied on pmac by prom_init()).
- * This is called very early on the boot process, after a minimal
- * MMU environment has been set up but before MMU_init is called.
+ * We do the initial parsing of the flat device-tree and prepares
+ * for the MMU to be fully initialized.
  */
 extern unsigned int memset_nocache_branch; /* Insn to be replaced by NOP */
 
 notrace void __init machine_init(u64 dt_ptr)
 {
+        /* Configure static keys first, now that we're relocated. */
+        setup_feature_keys();
+
         /* Enable early debugging if any specified (see udbg.h) */
         udbg_early_init();
 
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index eafb9a79e011..7ac8e6eaab5b 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -300,6 +300,7 @@ void __init early_setup(unsigned long dt_ptr)
 
         /* Apply all the dynamic patching */
         apply_feature_fixups();
+        setup_feature_keys();
 
         /* Initialize the hash table or TLB handling */
         early_init_mmu();
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index 6767605ea8da..4111d30badfa 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -22,6 +22,7 @@
 #include <linux/security.h>
 #include <linux/memblock.h>
 
+#include <asm/cpu_has_feature.h>
 #include <asm/pgtable.h>
 #include <asm/processor.h>
 #include <asm/mmu.h>
diff --git a/arch/powerpc/kernel/vdso32/Makefile b/arch/powerpc/kernel/vdso32/Makefile
index cbabd143acae..78a7449bf489 100644
--- a/arch/powerpc/kernel/vdso32/Makefile
+++ b/arch/powerpc/kernel/vdso32/Makefile
@@ -30,7 +30,7 @@ CPPFLAGS_vdso32.lds += -P -C -Upowerpc
 $(obj)/vdso32_wrapper.o : $(obj)/vdso32.so
 
 # link rule for the .so file, .lds has to be first
-$(obj)/vdso32.so.dbg: $(src)/vdso32.lds $(obj-vdso32)
+$(obj)/vdso32.so.dbg: $(src)/vdso32.lds $(obj-vdso32) FORCE
         $(call if_changed,vdso32ld)
 
 # strip rule for the .so file
@@ -39,12 +39,12 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE
         $(call if_changed,objcopy)
 
 # assembly rules for the .S files
-$(obj-vdso32): %.o: %.S
+$(obj-vdso32): %.o: %.S FORCE
         $(call if_changed_dep,vdso32as)
 
 # actual build commands
 quiet_cmd_vdso32ld = VDSO32L $@
-      cmd_vdso32ld = $(CROSS32CC) $(c_flags) -Wl,-T $^ -o $@
+      cmd_vdso32ld = $(CROSS32CC) $(c_flags) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^)
 quiet_cmd_vdso32as = VDSO32A $@
       cmd_vdso32as = $(CROSS32CC) $(a_flags) -c -o $@ $<
 
diff --git a/arch/powerpc/kernel/vdso64/Makefile b/arch/powerpc/kernel/vdso64/Makefile
index c710802b8fb6..366ae09b14c1 100644
--- a/arch/powerpc/kernel/vdso64/Makefile
+++ b/arch/powerpc/kernel/vdso64/Makefile
@@ -23,7 +23,7 @@ CPPFLAGS_vdso64.lds += -P -C -U$(ARCH)
 $(obj)/vdso64_wrapper.o : $(obj)/vdso64.so
 
 # link rule for the .so file, .lds has to be first
-$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64)
+$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64) FORCE
         $(call if_changed,vdso64ld)
 
 # strip rule for the .so file
@@ -32,12 +32,12 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE
         $(call if_changed,objcopy)
 
 # assembly rules for the .S files
-$(obj-vdso64): %.o: %.S
+$(obj-vdso64): %.o: %.S FORCE
         $(call if_changed_dep,vdso64as)
 
 # actual build commands
 quiet_cmd_vdso64ld = VDSO64L $@
-      cmd_vdso64ld = $(CC) $(c_flags) -Wl,-T $^ -o $@
+      cmd_vdso64ld = $(CC) $(c_flags) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^)
 quiet_cmd_vdso64as = VDSO64A $@
       cmd_vdso64as = $(CC) $(a_flags) -c -o $@ $<