Merge tag 'powerpc-4.8-4' of git://git.kernel.org/pub/scm/linux/kerne…

…l/git/powerpc/linux

Pull powerpc fixes from Ben Herrenschmidt:
 "This was meant to be sent early last week, but I has a change pending
  on one of the fixes and other things made me forget all about.  Ugh.

  We have some misc fixes for powerpc 4.8.  Some trivial bits and some
  regressions, and a trivial cleanup or two that I saw no point in
  letting rot in patchwork"

* tag 'powerpc-4.8-4' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux:
  powerpc: signals: Discard transaction state from signal frames
  powerpc/powernv : Drop reference added by kset_find_obj()
  powerpc/tm: do not use r13 for tabort_syscall
  powerpc: move hmi.c to arch/powerpc/kvm/
  powerpc: sysdev: cpm: fix gpio save_regs functions
  powerpc/pseries: PACA save area fix for MCE vs MCE
  powerpc/pseries: PACA save area fix for general exception vs MCE
  powerpc/prom: Fix sub-processor option passed to ibm, client-architecture-support
  powerpc, hotplug: Avoid to touch non-existent cpumasks.
  powerpc: migrate exception table users off module.h and onto extable.h
  powerpc/powernv/pci: fix iterator signedness
  powerpc/pseries: use pci_host_bridge.release_fn() to kfree(phb)
  cxl: use pcibios_free_controller_deferred() when removing vPHBs
  powerpc: mpc8349emitx: Delete unnecessary assignment for the field "owner"
  powerpc/512x: Delete unnecessary assignment for the field "owner"
  drivers/macintosh: Delete owner assignment
  powerpc: cputhreads: Add missing include file

Documentation/powerpc/transactional_memory.txt

@@ -167,6 +167,8 @@ signal will be rolled back anyway.
 For signals taken in non-TM or suspended mode, we use the
 normal/non-checkpointed stack pointer.
 
+Any transaction initiated inside a sighandler and suspended on return
+from the sighandler to the kernel will get reclaimed and discarded.
 
 Failure cause codes used by kernel
 ==================================

arch/powerpc/include/asm/cputhreads.h

@@ -3,6 +3,7 @@
 
 #ifndef __ASSEMBLY__
 #include <linux/cpumask.h>
+#include <asm/cpu_has_feature.h>
 
 /*
  * Mapping of threads to cores

arch/powerpc/include/asm/hmi.h

@@ -21,7 +21,7 @@
 #ifndef __ASM_PPC64_HMI_H__
 #define __ASM_PPC64_HMI_H__
 
-#ifdef CONFIG_PPC_BOOK3S_64
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 
 #define	CORE_TB_RESYNC_REQ_BIT		63
 #define MAX_SUBCORE_PER_CORE		4

arch/powerpc/include/asm/paca.h

@@ -183,11 +183,6 @@ struct paca_struct {
 	 */
 	u16 in_mce;
 	u8 hmi_event_available;		 /* HMI event is available */
-	/*
-	 * Bitmap for sibling subcore status. See kvm/book3s_hv_ras.c for
-	 * more details
-	 */
-	struct sibling_subcore_state *sibling_subcore_state;
 #endif
 
 	/* Stuff for accurate time accounting */
@@ -202,6 +197,13 @@ struct paca_struct {
 	struct kvmppc_book3s_shadow_vcpu shadow_vcpu;
 #endif
 	struct kvmppc_host_state kvm_hstate;
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+	/*
+	 * Bitmap for sibling subcore status. See kvm/book3s_hv_ras.c for
+	 * more details
+	 */
+	struct sibling_subcore_state *sibling_subcore_state;
+#endif
 #endif
 };
 

arch/powerpc/include/asm/pci-bridge.h

@@ -301,6 +301,7 @@ extern void pci_process_bridge_OF_ranges(struct pci_controller *hose,
 /* Allocate & free a PCI host bridge structure */
 extern struct pci_controller *pcibios_alloc_controller(struct device_node *dev);
 extern void pcibios_free_controller(struct pci_controller *phb);
+extern void pcibios_free_controller_deferred(struct pci_host_bridge *bridge);
 
 #ifdef CONFIG_PCI
 extern int pcibios_vaddr_is_ioport(void __iomem *address);

arch/powerpc/kernel/Makefile

@@ -41,7 +41,7 @@ obj-$(CONFIG_VDSO32)		+= vdso32/
 obj-$(CONFIG_HAVE_HW_BREAKPOINT)	+= hw_breakpoint.o
 obj-$(CONFIG_PPC_BOOK3S_64)	+= cpu_setup_ppc970.o cpu_setup_pa6t.o
 obj-$(CONFIG_PPC_BOOK3S_64)	+= cpu_setup_power.o
-obj-$(CONFIG_PPC_BOOK3S_64)	+= mce.o mce_power.o hmi.o
+obj-$(CONFIG_PPC_BOOK3S_64)	+= mce.o mce_power.o
 obj-$(CONFIG_PPC_BOOK3E_64)	+= exceptions-64e.o idle_book3e.o
 obj-$(CONFIG_PPC64)		+= vdso64/
 obj-$(CONFIG_ALTIVEC)		+= vecemu.o

arch/powerpc/kernel/entry_64.S

@@ -368,22 +368,22 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 tabort_syscall:
 	/* Firstly we need to enable TM in the kernel */
 	mfmsr	r10
-	li	r13, 1
-	rldimi	r10, r13, MSR_TM_LG, 63-MSR_TM_LG
+	li	r9, 1
+	rldimi	r10, r9, MSR_TM_LG, 63-MSR_TM_LG
 	mtmsrd	r10, 0
 
 	/* tabort, this dooms the transaction, nothing else */
-	li	r13, (TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT)
-	TABORT(R13)
+	li	r9, (TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT)
+	TABORT(R9)
 
 	/*
 	 * Return directly to userspace. We have corrupted user register state,
 	 * but userspace will never see that register state. Execution will
 	 * resume after the tbegin of the aborted transaction with the
 	 * checkpointed register state.
 	 */
-	li	r13, MSR_RI
-	andc	r10, r10, r13
+	li	r9, MSR_RI
+	andc	r10, r10, r9
 	mtmsrd	r10, 1
 	mtspr	SPRN_SRR0, r11
 	mtspr	SPRN_SRR1, r12

arch/powerpc/kernel/exceptions-64s.S

@@ -485,7 +485,23 @@ machine_check_fwnmi:
 	EXCEPTION_PROLOG_0(PACA_EXMC)
 machine_check_pSeries_0:
 	EXCEPTION_PROLOG_1(PACA_EXMC, KVMTEST, 0x200)
-	EXCEPTION_PROLOG_PSERIES_1(machine_check_common, EXC_STD)
+	/*
+	 * The following is essentially EXCEPTION_PROLOG_PSERIES_1 with the
+	 * difference that MSR_RI is not enabled, because PACA_EXMC is being
+	 * used, so nested machine check corrupts it. machine_check_common
+	 * enables MSR_RI.
+	 */
+	ld	r12,PACAKBASE(r13)
+	ld	r10,PACAKMSR(r13)
+	xori	r10,r10,MSR_RI
+	mfspr	r11,SPRN_SRR0
+	LOAD_HANDLER(r12, machine_check_common)
+	mtspr	SPRN_SRR0,r12
+	mfspr	r12,SPRN_SRR1
+	mtspr	SPRN_SRR1,r10
+	rfid
+	b	.	/* prevent speculative execution */
+
 	KVM_HANDLER_SKIP(PACA_EXMC, EXC_STD, 0x200)
 	KVM_HANDLER_SKIP(PACA_EXGEN, EXC_STD, 0x300)
 	KVM_HANDLER_SKIP(PACA_EXSLB, EXC_STD, 0x380)
@@ -969,14 +985,17 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
 machine_check_common:
 
 	mfspr	r10,SPRN_DAR
-	std	r10,PACA_EXGEN+EX_DAR(r13)
+	std	r10,PACA_EXMC+EX_DAR(r13)
 	mfspr	r10,SPRN_DSISR
-	stw	r10,PACA_EXGEN+EX_DSISR(r13)
+	stw	r10,PACA_EXMC+EX_DSISR(r13)
 	EXCEPTION_PROLOG_COMMON(0x200, PACA_EXMC)
 	FINISH_NAP
 	RECONCILE_IRQ_STATE(r10, r11)
-	ld	r3,PACA_EXGEN+EX_DAR(r13)
-	lwz	r4,PACA_EXGEN+EX_DSISR(r13)
+	ld	r3,PACA_EXMC+EX_DAR(r13)
+	lwz	r4,PACA_EXMC+EX_DSISR(r13)
+	/* Enable MSR_RI when finished with PACA_EXMC */
+	li	r10,MSR_RI
+	mtmsrd 	r10,1
 	std	r3,_DAR(r1)
 	std	r4,_DSISR(r1)
 	bl	save_nvgprs

arch/powerpc/kernel/kprobes.c

@@ -29,7 +29,7 @@
 #include <linux/kprobes.h>
 #include <linux/ptrace.h>
 #include <linux/preempt.h>
-#include <linux/module.h>
+#include <linux/extable.h>
 #include <linux/kdebug.h>
 #include <linux/slab.h>
 #include <asm/code-patching.h>

arch/powerpc/kernel/pci-common.c

@@ -153,6 +153,42 @@ void pcibios_free_controller(struct pci_controller *phb)
 }
 EXPORT_SYMBOL_GPL(pcibios_free_controller);
 
+/*
+ * This function is used to call pcibios_free_controller()
+ * in a deferred manner: a callback from the PCI subsystem.
+ *
+ * _*DO NOT*_ call pcibios_free_controller() explicitly if
+ * this is used (or it may access an invalid *phb pointer).
+ *
+ * The callback occurs when all references to the root bus
+ * are dropped (e.g., child buses/devices and their users).
+ *
+ * It's called as .release_fn() of 'struct pci_host_bridge'
+ * which is associated with the 'struct pci_controller.bus'
+ * (root bus) - it expects .release_data to hold a pointer
+ * to 'struct pci_controller'.
+ *
+ * In order to use it, register .release_fn()/release_data
+ * like this:
+ *
+ * pci_set_host_bridge_release(bridge,
+ *                             pcibios_free_controller_deferred
+ *                             (void *) phb);
+ *
+ * e.g. in the pcibios_root_bridge_prepare() callback from
+ * pci_create_root_bus().
+ */
+void pcibios_free_controller_deferred(struct pci_host_bridge *bridge)
+{
+	struct pci_controller *phb = (struct pci_controller *)
+					 bridge->release_data;
+
+	pr_debug("domain %d, dynamic %d\n", phb->global_number, phb->is_dynamic);
+
+	pcibios_free_controller(phb);
+}
+EXPORT_SYMBOL_GPL(pcibios_free_controller_deferred);
+
 /*
  * The function is used to return the minimal alignment
  * for memory or I/O windows of the associated P2P bridge.

arch/powerpc/kernel/prom_init.c

@@ -695,7 +695,7 @@ unsigned char ibm_architecture_vec[] = {
 	OV4_MIN_ENT_CAP,		/* minimum VP entitled capacity */
 
 	/* option vector 5: PAPR/OF options */
-	VECTOR_LENGTH(18),		/* length */
+	VECTOR_LENGTH(21),		/* length */
 	0,				/* don't ignore, don't halt */
 	OV5_FEAT(OV5_LPAR) | OV5_FEAT(OV5_SPLPAR) | OV5_FEAT(OV5_LARGE_PAGES) |
 	OV5_FEAT(OV5_DRCONF_MEMORY) | OV5_FEAT(OV5_DONATE_DEDICATE_CPU) |
@@ -726,8 +726,11 @@ unsigned char ibm_architecture_vec[] = {
 	0,
 	0,
 	OV5_FEAT(OV5_PFO_HW_RNG) | OV5_FEAT(OV5_PFO_HW_ENCR) |
-	OV5_FEAT(OV5_PFO_HW_842),
-	OV5_FEAT(OV5_SUB_PROCESSORS),
+	OV5_FEAT(OV5_PFO_HW_842),				/* Byte 17 */
+	0,							/* Byte 18 */
+	0,							/* Byte 19 */
+	0,							/* Byte 20 */
+	OV5_FEAT(OV5_SUB_PROCESSORS),				/* Byte 21 */
 
 	/* option vector 6: IBM PAPR hints */
 	VECTOR_LENGTH(3),		/* length */

arch/powerpc/kernel/signal_32.c

@@ -1226,7 +1226,21 @@ long sys_rt_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8,
 		(regs->gpr[1] + __SIGNAL_FRAMESIZE + 16);
 	if (!access_ok(VERIFY_READ, rt_sf, sizeof(*rt_sf)))
 		goto bad;
+
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	/*
+	 * If there is a transactional state then throw it away.
+	 * The purpose of a sigreturn is to destroy all traces of the
+	 * signal frame, this includes any transactional state created
+	 * within in. We only check for suspended as we can never be
+	 * active in the kernel, we are active, there is nothing better to
+	 * do than go ahead and Bad Thing later.
+	 * The cause is not important as there will never be a
+	 * recheckpoint so it's not user visible.
+	 */
+	if (MSR_TM_SUSPENDED(mfmsr()))
+		tm_reclaim_current(0);
+
 	if (__get_user(tmp, &rt_sf->uc.uc_link))
 		goto bad;
 	uc_transact = (struct ucontext __user *)(uintptr_t)tmp;

arch/powerpc/kernel/signal_64.c

@@ -676,7 +676,21 @@ int sys_rt_sigreturn(unsigned long r3, unsigned long r4, unsigned long r5,
 	if (__copy_from_user(&set, &uc->uc_sigmask, sizeof(set)))
 		goto badframe;
 	set_current_blocked(&set);
+
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	/*
+	 * If there is a transactional state then throw it away.
+	 * The purpose of a sigreturn is to destroy all traces of the
+	 * signal frame, this includes any transactional state created
+	 * within in. We only check for suspended as we can never be
+	 * active in the kernel, we are active, there is nothing better to
+	 * do than go ahead and Bad Thing later.
+	 * The cause is not important as there will never be a
+	 * recheckpoint so it's not user visible.
+	 */
+	if (MSR_TM_SUSPENDED(mfmsr()))
+		tm_reclaim_current(0);
+
 	if (__get_user(msr, &uc->uc_mcontext.gp_regs[PT_MSR]))
 		goto badframe;
 	if (MSR_TM_ACTIVE(msr)) {

arch/powerpc/kernel/smp.c

@@ -830,7 +830,7 @@ int __cpu_disable(void)
 
 	/* Update sibling maps */
 	base = cpu_first_thread_sibling(cpu);
-	for (i = 0; i < threads_per_core; i++) {
+	for (i = 0; i < threads_per_core && base + i < nr_cpu_ids; i++) {
 		cpumask_clear_cpu(cpu, cpu_sibling_mask(base + i));
 		cpumask_clear_cpu(base + i, cpu_sibling_mask(cpu));
 		cpumask_clear_cpu(cpu, cpu_core_mask(base + i));

arch/powerpc/kernel/traps.c

@@ -25,7 +25,8 @@
 #include <linux/user.h>
 #include <linux/interrupt.h>
 #include <linux/init.h>
-#include <linux/module.h>
+#include <linux/extable.h>
+#include <linux/module.h>	/* print_modules */
 #include <linux/prctl.h>
 #include <linux/delay.h>
 #include <linux/kprobes.h>

arch/powerpc/kvm/Makefile

@@ -78,6 +78,7 @@ kvm-book3s_64-builtin-xics-objs-$(CONFIG_KVM_XICS) := \
 
 ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) += \
+	book3s_hv_hmi.o \
 	book3s_hv_rmhandlers.o \
 	book3s_hv_rm_mmu.o \
 	book3s_hv_ras.o \

arch/powerpc/mm/fault.c

@@ -26,7 +26,7 @@
 #include <linux/mm.h>
 #include <linux/interrupt.h>
 #include <linux/highmem.h>
-#include <linux/module.h>
+#include <linux/extable.h>
 #include <linux/kprobes.h>
 #include <linux/kdebug.h>
 #include <linux/perf_event.h>

arch/powerpc/platforms/512x/mpc512x_lpbfifo.c

@@ -528,7 +528,6 @@ static struct platform_driver mpc512x_lpbfifo_driver = {
 	.remove = mpc512x_lpbfifo_remove,
 	.driver = {
 		.name = DRV_NAME,
-		.owner = THIS_MODULE,
 		.of_match_table = mpc512x_lpbfifo_match,
 	},
 };

arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c

@@ -222,7 +222,6 @@ static const struct of_device_id mcu_of_match_table[] = {
 static struct i2c_driver mcu_driver = {
 	.driver = {
 		.name = "mcu-mpc8349emitx",
-		.owner = THIS_MODULE,
 		.of_match_table = mcu_of_match_table,
 	},
 	.probe = mcu_probe,

arch/powerpc/platforms/embedded6xx/holly.c

@@ -26,7 +26,7 @@
 #include <linux/tty.h>
 #include <linux/serial_core.h>
 #include <linux/of_platform.h>
-#include <linux/module.h>
+#include <linux/extable.h>
 
 #include <asm/time.h>
 #include <asm/machdep.h>

arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c

@@ -23,7 +23,7 @@
 #include <linux/pci.h>
 #include <linux/kdev_t.h>
 #include <linux/console.h>
-#include <linux/module.h>
+#include <linux/extable.h>
 #include <linux/delay.h>
 #include <linux/irq.h>
 #include <linux/seq_file.h>

arch/powerpc/platforms/powernv/opal-dump.c

@@ -370,6 +370,7 @@ static irqreturn_t process_dump(int irq, void *data)
 	uint32_t dump_id, dump_size, dump_type;
 	struct dump_obj *dump;
 	char name[22];
+	struct kobject *kobj;
 
 	rc = dump_read_info(&dump_id, &dump_size, &dump_type);
 	if (rc != OPAL_SUCCESS)
@@ -381,8 +382,12 @@ static irqreturn_t process_dump(int irq, void *data)
 	 * that gracefully and not create two conflicting
 	 * entries.
 	 */
-	if (kset_find_obj(dump_kset, name))
+	kobj = kset_find_obj(dump_kset, name);
+	if (kobj) {
+		/* Drop reference added by kset_find_obj() */
+		kobject_put(kobj);
 		return 0;
+	}
 
 	dump = create_dump_obj(dump_id, dump_size, dump_type);
 	if (!dump)

arch/powerpc/platforms/powernv/opal-elog.c

@@ -247,6 +247,7 @@ static irqreturn_t elog_event(int irq, void *data)
 	uint64_t elog_type;
 	int rc;
 	char name[2+16+1];
+	struct kobject *kobj;
 
 	rc = opal_get_elog_size(&id, &size, &type);
 	if (rc != OPAL_SUCCESS) {
@@ -269,8 +270,12 @@ static irqreturn_t elog_event(int irq, void *data)
 	 * that gracefully and not create two conflicting
 	 * entries.
 	 */
-	if (kset_find_obj(elog_kset, name))
+	kobj = kset_find_obj(elog_kset, name);
+	if (kobj) {
+		/* Drop reference added by kset_find_obj() */
+		kobject_put(kobj);
 		return IRQ_HANDLED;
+	}
 
 	create_elog_obj(log_id, elog_size, elog_type);
 

arch/powerpc/platforms/powernv/pci-ioda.c

@@ -149,7 +149,7 @@ static void pnv_ioda_reserve_pe(struct pnv_phb *phb, int pe_no)
 
 static struct pnv_ioda_pe *pnv_ioda_alloc_pe(struct pnv_phb *phb)
 {
-	unsigned long pe = phb->ioda.total_pe_num - 1;
+	long pe;
 
 	for (pe = phb->ioda.total_pe_num - 1; pe >= 0; pe--) {
 		if (!test_and_set_bit(pe, phb->ioda.pe_alloc))

arch/powerpc/platforms/pseries/pci.c

@@ -119,6 +119,10 @@ int pseries_root_bridge_prepare(struct pci_host_bridge *bridge)
 
 	bus = bridge->bus;
 
+	/* Rely on the pcibios_free_controller_deferred() callback. */
+	pci_set_host_bridge_release(bridge, pcibios_free_controller_deferred,
+					(void *) pci_bus_to_host(bus));
+
 	dn = pcibios_get_phb_of_node(bus);
 	if (!dn)
 		return 0;