These changes are a raw update to a vanilla kernel 4.1.10, with the

recently announced rt patch patch-4.1.10-rt10.patch. No further changes
needed.

Change-Id: I9a0cf084498133b10771e744b6da4b29dff706ba
Signed-off-by: José Pekkarinen <jose.pekkarinen@nokia.com>

12 files changed, 78 insertions, 18 deletions

diff --git a/kernel/arch/powerpc/boot/Makefile b/kernel/arch/powerpc/boot/Makefile
index 73eddda53..4eec430d8 100644
--- a/kernel/arch/powerpc/boot/Makefile
+++ b/kernel/arch/powerpc/boot/Makefile
@@ -28,6 +28,9 @@ BOOTCFLAGS	+= -m64
 endif
 ifdef CONFIG_CPU_BIG_ENDIAN
 BOOTCFLAGS	+= -mbig-endian
+else
+BOOTCFLAGS	+= -mlittle-endian
+BOOTCFLAGS	+= $(call cc-option,-mabi=elfv2)
 endif
 
 BOOTAFLAGS	:= -D__ASSEMBLY__ $(BOOTCFLAGS) -traditional -nostdinc
diff --git a/kernel/arch/powerpc/include/asm/pgtable-ppc64.h b/kernel/arch/powerpc/include/asm/pgtable-ppc64.h
index 43e6ad424..88d27e325 100644
--- a/kernel/arch/powerpc/include/asm/pgtable-ppc64.h
+++ b/kernel/arch/powerpc/include/asm/pgtable-ppc64.h
@@ -135,7 +135,19 @@
 #define pte_iterate_hashed_end() } while(0)
 
 #ifdef CONFIG_PPC_HAS_HASH_64K
-#define pte_pagesize_index(mm, addr, pte)	get_slice_psize(mm, addr)
+/*
+ * We expect this to be called only for user addresses or kernel virtual
+ * addresses other than the linear mapping.
+ */
+#define pte_pagesize_index(mm, addr, pte)			\
+	({							\
+		unsigned int psize;				\
+		if (is_kernel_addr(addr))			\
+			psize = MMU_PAGE_4K;			\
+		else						\
+			psize = get_slice_psize(mm, addr);	\
+		psize;						\
+	})
 #else
 #define pte_pagesize_index(mm, addr, pte)	MMU_PAGE_4K
 #endif
diff --git a/kernel/arch/powerpc/include/asm/rtas.h b/kernel/arch/powerpc/include/asm/rtas.h
index 7a4ede16b..b77ef369c 100644
--- a/kernel/arch/powerpc/include/asm/rtas.h
+++ b/kernel/arch/powerpc/include/asm/rtas.h
@@ -343,6 +343,7 @@ extern void rtas_power_off(void);
 extern void rtas_halt(void);
 extern void rtas_os_term(char *str);
 extern int rtas_get_sensor(int sensor, int index, int *state);
+extern int rtas_get_sensor_fast(int sensor, int index, int *state);
 extern int rtas_get_power_level(int powerdomain, int *level);
 extern int rtas_set_power_level(int powerdomain, int level, int *setlevel);
 extern bool rtas_indicator_present(int token, int *maxindex);
diff --git a/kernel/arch/powerpc/include/asm/switch_to.h b/kernel/arch/powerpc/include/asm/switch_to.h
index 58abeda64..15cca17cb 100644
--- a/kernel/arch/powerpc/include/asm/switch_to.h
+++ b/kernel/arch/powerpc/include/asm/switch_to.h
@@ -29,6 +29,7 @@ static inline void save_early_sprs(struct thread_struct *prev) {}
 
 extern void enable_kernel_fp(void);
 extern void enable_kernel_altivec(void);
+extern void enable_kernel_vsx(void);
 extern int emulate_altivec(struct pt_regs *);
 extern void __giveup_vsx(struct task_struct *);
 extern void giveup_vsx(struct task_struct *);
diff --git a/kernel/arch/powerpc/kernel/eeh.c b/kernel/arch/powerpc/kernel/eeh.c
index 9ee61d156..cb565ad0a 100644
--- a/kernel/arch/powerpc/kernel/eeh.c
+++ b/kernel/arch/powerpc/kernel/eeh.c
@@ -310,11 +310,26 @@ void eeh_slot_error_detail(struct eeh_pe *pe, int severity)
 	if (!(pe->type & EEH_PE_PHB)) {
 		if (eeh_has_flag(EEH_ENABLE_IO_FOR_LOG))
 			eeh_pci_enable(pe, EEH_OPT_THAW_MMIO);
+
+		/*
+		 * The config space of some PCI devices can't be accessed
+		 * when their PEs are in frozen state. Otherwise, fenced
+		 * PHB might be seen. Those PEs are identified with flag
+		 * EEH_PE_CFG_RESTRICTED, indicating EEH_PE_CFG_BLOCKED
+		 * is set automatically when the PE is put to EEH_PE_ISOLATED.
+		 *
+		 * Restoring BARs possibly triggers PCI config access in
+		 * (OPAL) firmware and then causes fenced PHB. If the
+		 * PCI config is blocked with flag EEH_PE_CFG_BLOCKED, it's
+		 * pointless to restore BARs and dump config space.
+		 */
 		eeh_ops->configure_bridge(pe);
-		eeh_pe_restore_bars(pe);
+		if (!(pe->state & EEH_PE_CFG_BLOCKED)) {
+			eeh_pe_restore_bars(pe);
 
-		pci_regs_buf[0] = 0;
-		eeh_pe_traverse(pe, eeh_dump_pe_log, &loglen);
+			pci_regs_buf[0] = 0;
+			eeh_pe_traverse(pe, eeh_dump_pe_log, &loglen);
+		}
 	}
 
 	eeh_ops->get_log(pe, severity, pci_regs_buf, loglen);
@@ -1118,9 +1133,6 @@ void eeh_add_device_late(struct pci_dev *dev)
 		return;
 	}
 
-	if (eeh_has_flag(EEH_PROBE_MODE_DEV))
-		eeh_ops->probe(pdn, NULL);
-
 	/*
 	 * The EEH cache might not be removed correctly because of
 	 * unbalanced kref to the device during unplug time, which
@@ -1144,6 +1156,9 @@ void eeh_add_device_late(struct pci_dev *dev)
 		dev->dev.archdata.edev = NULL;
 	}
 
+	if (eeh_has_flag(EEH_PROBE_MODE_DEV))
+		eeh_ops->probe(pdn, NULL);
+
 	edev->pdev = dev;
 	dev->dev.archdata.edev = edev;
 
diff --git a/kernel/arch/powerpc/kernel/process.c b/kernel/arch/powerpc/kernel/process.c
index febb50dd5..0596373cd 100644
--- a/kernel/arch/powerpc/kernel/process.c
+++ b/kernel/arch/powerpc/kernel/process.c
@@ -204,8 +204,6 @@ EXPORT_SYMBOL_GPL(flush_altivec_to_thread);
 #endif /* CONFIG_ALTIVEC */
 
 #ifdef CONFIG_VSX
-#if 0
-/* not currently used, but some crazy RAID module might want to later */
 void enable_kernel_vsx(void)
 {
 	WARN_ON(preemptible());
@@ -220,7 +218,6 @@ void enable_kernel_vsx(void)
 #endif /* CONFIG_SMP */
 }
 EXPORT_SYMBOL(enable_kernel_vsx);
-#endif
 
 void giveup_vsx(struct task_struct *tsk)
 {
diff --git a/kernel/arch/powerpc/kernel/rtas.c b/kernel/arch/powerpc/kernel/rtas.c
index 7a488c108..caffb10e7 100644
--- a/kernel/arch/powerpc/kernel/rtas.c
+++ b/kernel/arch/powerpc/kernel/rtas.c
@@ -584,6 +584,23 @@ int rtas_get_sensor(int sensor, int index, int *state)
 }
 EXPORT_SYMBOL(rtas_get_sensor);
 
+int rtas_get_sensor_fast(int sensor, int index, int *state)
+{
+	int token = rtas_token("get-sensor-state");
+	int rc;
+
+	if (token == RTAS_UNKNOWN_SERVICE)
+		return -ENOENT;
+
+	rc = rtas_call(token, 2, 2, state, sensor, index);
+	WARN_ON(rc == RTAS_BUSY || (rc >= RTAS_EXTENDED_DELAY_MIN &&
+				    rc <= RTAS_EXTENDED_DELAY_MAX));
+
+	if (rc < 0)
+		return rtas_error_rc(rc);
+	return rc;
+}
+
 bool rtas_indicator_present(int token, int *maxindex)
 {
 	int proplen, count, i;
diff --git a/kernel/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/kernel/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index b027a8973..c6d601cc9 100644
--- a/kernel/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/kernel/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -421,14 +421,20 @@ long kvmppc_do_h_remove(struct kvm *kvm, unsigned long flags,
 	rev = real_vmalloc_addr(&kvm->arch.revmap[pte_index]);
 	v = pte & ~HPTE_V_HVLOCK;
 	if (v & HPTE_V_VALID) {
-		u64 pte1;
-
-		pte1 = be64_to_cpu(hpte[1]);
 		hpte[0] &= ~cpu_to_be64(HPTE_V_VALID);
-		rb = compute_tlbie_rb(v, pte1, pte_index);
+		rb = compute_tlbie_rb(v, be64_to_cpu(hpte[1]), pte_index);
 		do_tlbies(kvm, &rb, 1, global_invalidates(kvm, flags), true);
-		/* Read PTE low word after tlbie to get final R/C values */
-		remove_revmap_chain(kvm, pte_index, rev, v, pte1);
+		/*
+		 * The reference (R) and change (C) bits in a HPT
+		 * entry can be set by hardware at any time up until
+		 * the HPTE is invalidated and the TLB invalidation
+		 * sequence has completed.  This means that when
+		 * removing a HPTE, we need to re-read the HPTE after
+		 * the invalidation sequence has completed in order to
+		 * obtain reliable values of R and C.
+		 */
+		remove_revmap_chain(kvm, pte_index, rev, v,
+				    be64_to_cpu(hpte[1]));
 	}
 	r = rev->guest_rpte & ~HPTE_GR_RESERVED;
 	note_hpte_modification(kvm, rev);
diff --git a/kernel/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/kernel/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 4d70df26c..3b2d2c5b6 100644
--- a/kernel/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/kernel/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1127,6 +1127,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 	cmpwi	r12, BOOK3S_INTERRUPT_H_DOORBELL
 	bne	3f
 	lbz	r0, HSTATE_HOST_IPI(r13)
+	cmpwi	r0, 0
 	beq	4f
 	b	guest_exit_cont
 3:
diff --git a/kernel/arch/powerpc/mm/hugepage-hash64.c b/kernel/arch/powerpc/mm/hugepage-hash64.c
index 43dafb9d6..4d87122cf 100644
--- a/kernel/arch/powerpc/mm/hugepage-hash64.c
+++ b/kernel/arch/powerpc/mm/hugepage-hash64.c
@@ -85,7 +85,6 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid,
 	BUG_ON(index >= 4096);
 
 	vpn = hpt_vpn(ea, vsid, ssize);
-	hash = hpt_hash(vpn, shift, ssize);
 	hpte_slot_array = get_hpte_slot_array(pmdp);
 	if (psize == MMU_PAGE_4K) {
 		/*
@@ -101,6 +100,7 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid,
 	valid = hpte_valid(hpte_slot_array, index);
 	if (valid) {
 		/* update the hpte bits */
+		hash = hpt_hash(vpn, shift, ssize);
 		hidx =  hpte_hash_index(hpte_slot_array, index);
 		if (hidx & _PTEIDX_SECONDARY)
 			hash = ~hash;
@@ -126,6 +126,7 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid,
 	if (!valid) {
 		unsigned long hpte_group;
 
+		hash = hpt_hash(vpn, shift, ssize);
 		/* insert new entry */
 		pa = pmd_pfn(__pmd(old_pmd)) << PAGE_SHIFT;
 		new_pmd |= _PAGE_HASHPTE;
diff --git a/kernel/arch/powerpc/platforms/pseries/ras.c b/kernel/arch/powerpc/platforms/pseries/ras.c
index 02e4a1745..3b6647e57 100644
--- a/kernel/arch/powerpc/platforms/pseries/ras.c
+++ b/kernel/arch/powerpc/platforms/pseries/ras.c
@@ -189,7 +189,8 @@ static irqreturn_t ras_epow_interrupt(int irq, void *dev_id)
 	int state;
 	int critical;
 
-	status = rtas_get_sensor(EPOW_SENSOR_TOKEN, EPOW_SENSOR_INDEX, &state);
+	status = rtas_get_sensor_fast(EPOW_SENSOR_TOKEN, EPOW_SENSOR_INDEX,
+				      &state);
 
 	if (state > 3)
 		critical = 1;		/* Time Critical */
diff --git a/kernel/arch/powerpc/platforms/pseries/setup.c b/kernel/arch/powerpc/platforms/pseries/setup.c
index df6a70419..e6e8b241d 100644
--- a/kernel/arch/powerpc/platforms/pseries/setup.c
+++ b/kernel/arch/powerpc/platforms/pseries/setup.c
@@ -268,6 +268,11 @@ static int pci_dn_reconfig_notifier(struct notifier_block *nb, unsigned long act
 			eeh_dev_init(PCI_DN(np), pci->phb);
 		}
 		break;
+	case OF_RECONFIG_DETACH_NODE:
+		pci = PCI_DN(np);
+		if (pci)
+			list_del(&pci->list);
+		break;
 	default:
 		err = NOTIFY_DONE;
 		break;