Merge tag 'powerpc-4.12-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "Highlights include:

   - Larger virtual address space on 64-bit server CPUs. By default we
     use a 128TB virtual address space, but a process can request access
     to the full 512TB by passing a hint to mmap().

   - Support for the new Power9 "XIVE" interrupt controller.

   - TLB flushing optimisations for the radix MMU on Power9.

   - Support for CAPI cards on Power9, using the "Coherent Accelerator
     Interface Architecture 2.0".

   - The ability to configure the mmap randomisation limits at build and
     runtime.

   - Several small fixes and cleanups to the kprobes code, as well as
     support for KPROBES_ON_FTRACE.

   - Major improvements to handling of system reset interrupts,
     correctly treating them as NMIs, giving them a dedicated stack and
     using a new hypervisor call to trigger them, all of which should
     aid debugging and robustness.

   - Many fixes and other minor enhancements.

  Thanks to: Alastair D'Silva, Alexey Kardashevskiy, Alistair Popple,
  Andrew Donnellan, Aneesh Kumar K.V, Anshuman Khandual, Anton
  Blanchard, Balbir Singh, Ben Hutchings, Benjamin Herrenschmidt,
  Bhupesh Sharma, Chris Packham, Christian Zigotzky, Christophe Leroy,
  Christophe Lombard, Daniel Axtens, David Gibson, Gautham R. Shenoy,
  Gavin Shan, Geert Uytterhoeven, Guilherme G. Piccoli, Hamish Martin,
  Hari Bathini, Kees Cook, Laurent Dufour, Madhavan Srinivasan, Mahesh J
  Salgaonkar, Mahesh Salgaonkar, Masami Hiramatsu, Matt Brown, Matthew
  R. Ochs, Michael Neuling, Naveen N. Rao, Nicholas Piggin, Oliver
  O'Halloran, Pan Xinhui, Paul Mackerras, Rashmica Gupta, Russell
  Currey, Sukadev Bhattiprolu, Thadeu Lima de Souza Cascardo, Tobin C.
  Harding, Tyrel Datwyler, Uma Krishnan, Vaibhav Jain, Vipin K Parashar,
  Yang Shi"

* tag 'powerpc-4.12-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (214 commits)
  powerpc/64s: Power9 has no LPCR[VRMASD] field so don't set it
  powerpc/powernv: Fix TCE kill on NVLink2
  powerpc/mm/radix: Drop support for CPUs without lockless tlbie
  powerpc/book3s/mce: Move add_taint() later in virtual mode
  powerpc/sysfs: Move #ifdef CONFIG_HOTPLUG_CPU out of the function body
  powerpc/smp: Document irq enable/disable after migrating IRQs
  powerpc/mpc52xx: Don't select user-visible RTAS_PROC
  powerpc/powernv: Document cxl dependency on special case in pnv_eeh_reset()
  powerpc/eeh: Clean up and document event handling functions
  powerpc/eeh: Avoid use after free in eeh_handle_special_event()
  cxl: Mask slice error interrupts after first occurrence
  cxl: Route eeh events to all drivers in cxl_pci_error_detected()
  cxl: Force context lock during EEH flow
  powerpc/64: Allow CONFIG_RELOCATABLE if COMPILE_TEST
  powerpc/xmon: Teach xmon oops about radix vectors
  powerpc/mm/hash: Fix off-by-one in comment about kernel contexts ids
  powerpc/pseries: Enable VFIO
  powerpc/powernv: Fix iommu table size calculation hook for small tables
  powerpc/powernv: Check kzalloc() return value in pnv_pci_table_alloc
  powerpc: Add arch/powerpc/tools directory
  ...

10 files changed, 155 insertions, 25 deletions

diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig
index 30ec04f1c67c..913c54e23eea 100644
--- a/arch/powerpc/platforms/pseries/Kconfig
+++ b/arch/powerpc/platforms/pseries/Kconfig
@@ -17,9 +17,10 @@ config PPC_PSERIES
 	select PPC_UDBG_16550
 	select PPC_NATIVE
 	select PPC_DOORBELL
-	select HOTPLUG_CPU if SMP
+	select HOTPLUG_CPU
 	select ARCH_RANDOM
 	select PPC_DOORBELL
+	select FORCE_SMP
 	default y
 
 config PPC_SPLPAR
diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c
index 193e052fa0dd..bda18d8e1674 100644
--- a/arch/powerpc/platforms/pseries/dlpar.c
+++ b/arch/powerpc/platforms/pseries/dlpar.c
@@ -288,7 +288,6 @@ int dlpar_detach_node(struct device_node *dn)
 	if (rc)
 		return rc;
 
-	of_node_put(dn); /* Must decrement the refcount */
 	return 0;
 }
 
diff --git a/arch/powerpc/platforms/pseries/dtl.c b/arch/powerpc/platforms/pseries/dtl.c
index 6b04e3f0f982..18014cdeb590 100644
--- a/arch/powerpc/platforms/pseries/dtl.c
+++ b/arch/powerpc/platforms/pseries/dtl.c
@@ -21,13 +21,12 @@
  */
 
 #include <linux/slab.h>
-#include <linux/debugfs.h>
 #include <linux/spinlock.h>
 #include <asm/smp.h>
 #include <linux/uaccess.h>
 #include <asm/firmware.h>
 #include <asm/lppaca.h>
-#include <asm/debug.h>
+#include <asm/debugfs.h>
 #include <asm/plpar_wrappers.h>
 #include <asm/machdep.h>
 
diff --git a/arch/powerpc/platforms/pseries/hvCall_inst.c b/arch/powerpc/platforms/pseries/hvCall_inst.c
index f02ec3ab428c..957ae347b0b3 100644
--- a/arch/powerpc/platforms/pseries/hvCall_inst.c
+++ b/arch/powerpc/platforms/pseries/hvCall_inst.c
@@ -29,6 +29,16 @@
 #include <asm/trace.h>
 #include <asm/machdep.h>
 
+/* For hcall instrumentation. One structure per-hcall, per-CPU */
+struct hcall_stats {
+	unsigned long	num_calls;	/* number of calls (on this CPU) */
+	unsigned long	tb_total;	/* total wall time (mftb) of calls. */
+	unsigned long	purr_total;	/* total cpu time (PURR) of calls. */
+	unsigned long	tb_start;
+	unsigned long	purr_start;
+};
+#define HCALL_STAT_ARRAY_SIZE	((MAX_HCALL_OPCODE >> 2) + 1)
+
 DEFINE_PER_CPU(struct hcall_stats[HCALL_STAT_ARRAY_SIZE], hcall_stats);
 
 /*
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 4d757eaa46bf..8374adee27e3 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -74,6 +74,7 @@ static struct iommu_table_group *iommu_pseries_alloc_group(int node)
 		goto fail_exit;
 
 	INIT_LIST_HEAD_RCU(&tbl->it_group_list);
+	kref_init(&tbl->it_kref);
 	tgl->table_group = table_group;
 	list_add_rcu(&tgl->next, &tbl->it_group_list);
 
@@ -115,7 +116,7 @@ static void iommu_pseries_free_group(struct iommu_table_group *table_group,
 		BUG_ON(table_group->group);
 	}
 #endif
-	iommu_free_table(tbl, node_name);
+	iommu_tce_table_put(tbl);
 
 	kfree(table_group);
 }
@@ -550,6 +551,7 @@ static void iommu_table_setparms(struct pci_controller *phb,
 static void iommu_table_setparms_lpar(struct pci_controller *phb,
 				      struct device_node *dn,
 				      struct iommu_table *tbl,
+				      struct iommu_table_group *table_group,
 				      const __be32 *dma_window)
 {
 	unsigned long offset, size;
@@ -563,6 +565,9 @@ static void iommu_table_setparms_lpar(struct pci_controller *phb,
 	tbl->it_type = TCE_PCI;
 	tbl->it_offset = offset >> tbl->it_page_shift;
 	tbl->it_size = size >> tbl->it_page_shift;
+
+	table_group->tce32_start = offset;
+	table_group->tce32_size = size;
 }
 
 struct iommu_table_ops iommu_table_pseries_ops = {
@@ -651,8 +656,38 @@ static void pci_dma_bus_setup_pSeries(struct pci_bus *bus)
 	pr_debug("ISA/IDE, window size is 0x%llx\n", pci->phb->dma_window_size);
 }
 
+#ifdef CONFIG_IOMMU_API
+static int tce_exchange_pseries(struct iommu_table *tbl, long index, unsigned
+				long *tce, enum dma_data_direction *direction)
+{
+	long rc;
+	unsigned long ioba = (unsigned long) index << tbl->it_page_shift;
+	unsigned long flags, oldtce = 0;
+	u64 proto_tce = iommu_direction_to_tce_perm(*direction);
+	unsigned long newtce = *tce | proto_tce;
+
+	spin_lock_irqsave(&tbl->large_pool.lock, flags);
+
+	rc = plpar_tce_get((u64)tbl->it_index, ioba, &oldtce);
+	if (!rc)
+		rc = plpar_tce_put((u64)tbl->it_index, ioba, newtce);
+
+	if (!rc) {
+		*direction = iommu_tce_direction(oldtce);
+		*tce = oldtce & ~(TCE_PCI_READ | TCE_PCI_WRITE);
+	}
+
+	spin_unlock_irqrestore(&tbl->large_pool.lock, flags);
+
+	return rc;
+}
+#endif
+
 struct iommu_table_ops iommu_table_lpar_multi_ops = {
 	.set = tce_buildmulti_pSeriesLP,
+#ifdef CONFIG_IOMMU_API
+	.exchange = tce_exchange_pseries,
+#endif
 	.clear = tce_freemulti_pSeriesLP,
 	.get = tce_get_pSeriesLP
 };
@@ -689,7 +724,8 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus)
 	if (!ppci->table_group) {
 		ppci->table_group = iommu_pseries_alloc_group(ppci->phb->node);
 		tbl = ppci->table_group->tables[0];
-		iommu_table_setparms_lpar(ppci->phb, pdn, tbl, dma_window);
+		iommu_table_setparms_lpar(ppci->phb, pdn, tbl,
+				ppci->table_group, dma_window);
 		tbl->it_ops = &iommu_table_lpar_multi_ops;
 		iommu_init_table(tbl, ppci->phb->node);
 		iommu_register_group(ppci->table_group,
@@ -1143,7 +1179,8 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
 	if (!pci->table_group) {
 		pci->table_group = iommu_pseries_alloc_group(pci->phb->node);
 		tbl = pci->table_group->tables[0];
-		iommu_table_setparms_lpar(pci->phb, pdn, tbl, dma_window);
+		iommu_table_setparms_lpar(pci->phb, pdn, tbl,
+				pci->table_group, dma_window);
 		tbl->it_ops = &iommu_table_lpar_multi_ops;
 		iommu_init_table(tbl, pci->phb->node);
 		iommu_register_group(pci->table_group,
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 8b1fe895daa3..6541d0b03e4c 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -958,3 +958,64 @@ int h_get_mpp_x(struct hvcall_mpp_x_data *mpp_x_data)
 
 	return rc;
 }
+
+static unsigned long vsid_unscramble(unsigned long vsid, int ssize)
+{
+	unsigned long protovsid;
+	unsigned long va_bits = VA_BITS;
+	unsigned long modinv, vsid_modulus;
+	unsigned long max_mod_inv, tmp_modinv;
+
+	if (!mmu_has_feature(MMU_FTR_68_BIT_VA))
+		va_bits = 65;
+
+	if (ssize == MMU_SEGSIZE_256M) {
+		modinv = VSID_MULINV_256M;
+		vsid_modulus = ((1UL << (va_bits - SID_SHIFT)) - 1);
+	} else {
+		modinv = VSID_MULINV_1T;
+		vsid_modulus = ((1UL << (va_bits - SID_SHIFT_1T)) - 1);
+	}
+
+	/*
+	 * vsid outside our range.
+	 */
+	if (vsid >= vsid_modulus)
+		return 0;
+
+	/*
+	 * If modinv is the modular multiplicate inverse of (x % vsid_modulus)
+	 * and vsid = (protovsid * x) % vsid_modulus, then we say:
+	 *   protovsid = (vsid * modinv) % vsid_modulus
+	 */
+
+	/* Check if (vsid * modinv) overflow (63 bits) */
+	max_mod_inv = 0x7fffffffffffffffull / vsid;
+	if (modinv < max_mod_inv)
+		return (vsid * modinv) % vsid_modulus;
+
+	tmp_modinv = modinv/max_mod_inv;
+	modinv %= max_mod_inv;
+
+	protovsid = (((vsid * max_mod_inv) % vsid_modulus) * tmp_modinv) % vsid_modulus;
+	protovsid = (protovsid + vsid * modinv) % vsid_modulus;
+
+	return protovsid;
+}
+
+static int __init reserve_vrma_context_id(void)
+{
+	unsigned long protovsid;
+
+	/*
+	 * Reserve context ids which map to reserved virtual addresses. For now
+	 * we only reserve the context id which maps to the VRMA VSID. We ignore
+	 * the addresses in "ibm,adjunct-virtual-addresses" because we don't
+	 * enable adjunct support via the "ibm,client-architecture-support"
+	 * interface.
+	 */
+	protovsid = vsid_unscramble(VRMA_VSID, MMU_SEGSIZE_1T);
+	hash__reserve_context_id(protovsid >> ESID_BITS_1T);
+	return 0;
+}
+machine_device_initcall(pseries, reserve_vrma_context_id);
diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c
index 904a677208d1..bb70b26334f0 100644
--- a/arch/powerpc/platforms/pseries/ras.c
+++ b/arch/powerpc/platforms/pseries/ras.c
@@ -386,6 +386,10 @@ int pSeries_system_reset_exception(struct pt_regs *regs)
 		}
 		fwnmi_release_errinfo();
 	}
+
+	if (smp_handle_nmi_ipi(regs))
+		return 1;
+
 	return 0; /* need to perform reset */
 }
 
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index b4d362ed03a1..b5d86426e97b 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -87,6 +87,10 @@ static void pSeries_show_cpuinfo(struct seq_file *m)
 		model = of_get_property(root, "model", NULL);
 	seq_printf(m, "machine\t\t: CHRP %s\n", model);
 	of_node_put(root);
+	if (radix_enabled())
+		seq_printf(m, "MMU\t\t: Radix\n");
+	else
+		seq_printf(m, "MMU\t\t: Hash\n");
 }
 
 /* Initialize firmware assisted non-maskable interrupts if
diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c
index f6f83aeccaaa..52ca6b311d44 100644
--- a/arch/powerpc/platforms/pseries/smp.c
+++ b/arch/powerpc/platforms/pseries/smp.c
@@ -55,11 +55,6 @@
  */
 static cpumask_var_t of_spin_mask;
 
-/*
- * If we multiplex IPI mechanisms, store the appropriate XICS IPI mechanism here
- */
-static void  (*xics_cause_ipi)(int cpu, unsigned long data);
-
 /* Query where a cpu is now.  Return codes #defined in plpar_wrappers.h */
 int smp_query_cpu_stopped(unsigned int pcpu)
 {
@@ -143,8 +138,6 @@ static void smp_setup_cpu(int cpu)
 {
 	if (cpu != boot_cpuid)
 		xics_setup_cpu();
-	if (cpu_has_feature(CPU_FTR_DBELL))
-		doorbell_setup_this_cpu();
 
 	if (firmware_has_feature(FW_FEATURE_SPLPAR))
 		vpa_init(cpu);
@@ -187,28 +180,50 @@ static int smp_pSeries_kick_cpu(int nr)
 	return 0;
 }
 
-/* Only used on systems that support multiple IPI mechanisms */
-static void pSeries_cause_ipi_mux(int cpu, unsigned long data)
+static void smp_pseries_cause_ipi(int cpu)
 {
-	if (cpumask_test_cpu(cpu, cpu_sibling_mask(smp_processor_id())))
-		doorbell_cause_ipi(cpu, data);
-	else
-		xics_cause_ipi(cpu, data);
+	/* POWER9 should not use this handler */
+	if (doorbell_try_core_ipi(cpu))
+		return;
+
+	icp_ops->cause_ipi(cpu);
+}
+
+static int pseries_cause_nmi_ipi(int cpu)
+{
+	int hwcpu;
+
+	if (cpu == NMI_IPI_ALL_OTHERS) {
+		hwcpu = H_SIGNAL_SYS_RESET_ALL_OTHERS;
+	} else {
+		if (cpu < 0) {
+			WARN_ONCE(true, "incorrect cpu parameter %d", cpu);
+			return 0;
+		}
+
+		hwcpu = get_hard_smp_processor_id(cpu);
+	}
+
+	if (plapr_signal_sys_reset(hwcpu) == H_SUCCESS)
+		return 1;
+
+	return 0;
 }
 
 static __init void pSeries_smp_probe(void)
 {
 	xics_smp_probe();
 
-	if (cpu_has_feature(CPU_FTR_DBELL)) {
-		xics_cause_ipi = smp_ops->cause_ipi;
-		smp_ops->cause_ipi = pSeries_cause_ipi_mux;
-	}
+	if (cpu_has_feature(CPU_FTR_DBELL))
+		smp_ops->cause_ipi = smp_pseries_cause_ipi;
+	else
+		smp_ops->cause_ipi = icp_ops->cause_ipi;
 }
 
 static struct smp_ops_t pseries_smp_ops = {
 	.message_pass	= NULL,	/* Use smp_muxed_ipi_message_pass */
 	.cause_ipi	= NULL,	/* Filled at runtime by pSeries_smp_probe() */
+	.cause_nmi_ipi	= pseries_cause_nmi_ipi,
 	.probe		= pSeries_smp_probe,
 	.kick_cpu	= smp_pSeries_kick_cpu,
 	.setup_cpu	= smp_setup_cpu,
diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c
index 720493932486..28b09fd797ec 100644
--- a/arch/powerpc/platforms/pseries/vio.c
+++ b/arch/powerpc/platforms/pseries/vio.c
@@ -1318,7 +1318,7 @@ static void vio_dev_release(struct device *dev)
 	struct iommu_table *tbl = get_iommu_table_base(dev);
 
 	if (tbl)
-		iommu_free_table(tbl, of_node_full_name(dev->of_node));
+		iommu_tce_table_put(tbl);
 	of_node_put(dev->of_node);
 	kfree(to_vio_dev(dev));
 }