Merge tag 'powerpc-4.11-2' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull more powerpc updates from Michael Ellerman:
 "Highlights include:

   - an update of the disassembly code used by xmon to the latest
     versions in binutils. We've received permission from all the
     authors of the relevant binutils changes to relicense their changes
     to the relevant files from GPLv3 to GPLv2, for inclusion in Linux.
     Thanks to Peter Bergner for doing the leg work to get permission
     from everyone.

   - addition of the "architected" Power9 CPU table entry, allowing us
     to boot in Power9 architected mode under a hypervisor.

   - updates to the Power9 PMU code.

   - implementation of clear_bit_unlock_is_negative_byte() to optimise
     unlock_page().

   - Freescale updates from Scott: "Highlights include 8xx breakpoints
     and perf, t1042rdb display support, and board updates."

  Thanks to:
    Al Viro, Andrew Donnellan, Aneesh Kumar K.V, Balbir Singh, Douglas
    Miller, Frédéric Weisbecker, Gavin Shan, Madhavan Srinivasan,
    Michael Roth, Nathan Fontenot, Naveen N. Rao, Nicholas Piggin, Peter
    Bergner, Paul E. McKenney, Rashmica Gupta, Russell Currey, Sahil
    Mehta, Stewart Smith"

* tag 'powerpc-4.11-2' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (48 commits)
  powerpc: Remove leftover cputime_to_nsecs call causing build error
  powerpc/mm/hash: Always clear UPRT and Host Radix bits when setting up CPU
  powerpc/optprobes: Fix TOC handling in optprobes trampoline
  powerpc/pseries: Advertise Hot Plug Event support to firmware
  cxl: fix nested locking hang during EEH hotplug
  powerpc/xmon: Dump memory in CPU endian format
  powerpc/pseries: Revert 'Auto-online hotplugged memory'
  powerpc/powernv: Make PCI non-optional
  powerpc/64: Implement clear_bit_unlock_is_negative_byte()
  powerpc/powernv: Remove unused variable in pnv_pci_sriov_disable()
  powerpc/kernel: Remove error message in pcibios_setup_phb_resources()
  powerpc/mm: Fix typo in set_pte_at()
  pci/hotplug/pnv-php: Disable MSI and PCI device properly
  pci/hotplug/pnv-php: Disable surprise hotplug capability on conflicts
  pci/hotplug/pnv-php: Remove WARN_ON() in pnv_php_put_slot()
  powerpc: Add POWER9 architected mode to cputable
  powerpc/perf: use is_kernel_addr macro in perf_get_misc_flags()
  powerpc/perf: Avoid FAB_*_MATCH checks for power9
  powerpc/perf: Add restrictions to PMC5 in power9 DD1
  powerpc/perf: Use Instruction Counter value
  ...

5 files changed, 91 insertions, 27 deletions

diff --git a/drivers/misc/cxl/cxl.h b/drivers/misc/cxl/cxl.h
index 6c722d96b775..79e60ec70bd3 100644
--- a/drivers/misc/cxl/cxl.h
+++ b/drivers/misc/cxl/cxl.h
@@ -418,8 +418,9 @@ struct cxl_afu {
 	struct dentry *debugfs;
 	struct mutex contexts_lock;
 	spinlock_t afu_cntl_lock;
-	/* Used to block access to AFU config space while deconfigured */
-	struct rw_semaphore configured_rwsem;
+
+	/* -1: AFU deconfigured/locked, >= 0: number of readers */
+	atomic_t configured_state;
 
 	/* AFU error buffer fields and bin attribute for sysfs */
 	u64 eb_len, eb_offset;
diff --git a/drivers/misc/cxl/main.c b/drivers/misc/cxl/main.c
index 2a6bf1d0a3a4..cc1706a92ace 100644
--- a/drivers/misc/cxl/main.c
+++ b/drivers/misc/cxl/main.c
@@ -268,8 +268,7 @@ struct cxl_afu *cxl_alloc_afu(struct cxl *adapter, int slice)
 	idr_init(&afu->contexts_idr);
 	mutex_init(&afu->contexts_lock);
 	spin_lock_init(&afu->afu_cntl_lock);
-	init_rwsem(&afu->configured_rwsem);
-	down_write(&afu->configured_rwsem);
+	atomic_set(&afu->configured_state, -1);
 	afu->prefault_mode = CXL_PREFAULT_NONE;
 	afu->irqs_max = afu->adapter->user_irqs;
 
diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c
index cca938845ffd..91f645992c94 100644
--- a/drivers/misc/cxl/pci.c
+++ b/drivers/misc/cxl/pci.c
@@ -1129,7 +1129,7 @@ static int pci_configure_afu(struct cxl_afu *afu, struct cxl *adapter, struct pc
 	if ((rc = cxl_native_register_psl_irq(afu)))
 		goto err2;
 
-	up_write(&afu->configured_rwsem);
+	atomic_set(&afu->configured_state, 0);
 	return 0;
 
 err2:
@@ -1142,7 +1142,14 @@ err1:
 
 static void pci_deconfigure_afu(struct cxl_afu *afu)
 {
-	down_write(&afu->configured_rwsem);
+	/*
+	 * It's okay to deconfigure when AFU is already locked, otherwise wait
+	 * until there are no readers
+	 */
+	if (atomic_read(&afu->configured_state) != -1) {
+		while (atomic_cmpxchg(&afu->configured_state, 0, -1) != -1)
+			schedule();
+	}
 	cxl_native_release_psl_irq(afu);
 	if (afu->adapter->native->sl_ops->release_serr_irq)
 		afu->adapter->native->sl_ops->release_serr_irq(afu);
diff --git a/drivers/misc/cxl/vphb.c b/drivers/misc/cxl/vphb.c
index 639a343b7836..512a4897dbf6 100644
--- a/drivers/misc/cxl/vphb.c
+++ b/drivers/misc/cxl/vphb.c
@@ -83,6 +83,16 @@ static inline struct cxl_afu *pci_bus_to_afu(struct pci_bus *bus)
 	return phb ? phb->private_data : NULL;
 }
 
+static void cxl_afu_configured_put(struct cxl_afu *afu)
+{
+	atomic_dec_if_positive(&afu->configured_state);
+}
+
+static bool cxl_afu_configured_get(struct cxl_afu *afu)
+{
+	return atomic_inc_unless_negative(&afu->configured_state);
+}
+
 static inline int cxl_pcie_config_info(struct pci_bus *bus, unsigned int devfn,
 				       struct cxl_afu *afu, int *_record)
 {
@@ -107,7 +117,7 @@ static int cxl_pcie_read_config(struct pci_bus *bus, unsigned int devfn,
 
 	afu = pci_bus_to_afu(bus);
 	/* Grab a reader lock on afu. */
-	if (afu == NULL || !down_read_trylock(&afu->configured_rwsem))
+	if (afu == NULL || !cxl_afu_configured_get(afu))
 		return PCIBIOS_DEVICE_NOT_FOUND;
 
 	rc = cxl_pcie_config_info(bus, devfn, afu, &record);
@@ -132,7 +142,7 @@ static int cxl_pcie_read_config(struct pci_bus *bus, unsigned int devfn,
 	}
 
 out:
-	up_read(&afu->configured_rwsem);
+	cxl_afu_configured_put(afu);
 	return rc ? PCIBIOS_DEVICE_NOT_FOUND : PCIBIOS_SUCCESSFUL;
 }
 
@@ -144,7 +154,7 @@ static int cxl_pcie_write_config(struct pci_bus *bus, unsigned int devfn,
 
 	afu = pci_bus_to_afu(bus);
 	/* Grab a reader lock on afu. */
-	if (afu == NULL || !down_read_trylock(&afu->configured_rwsem))
+	if (afu == NULL || !cxl_afu_configured_get(afu))
 		return PCIBIOS_DEVICE_NOT_FOUND;
 
 	rc = cxl_pcie_config_info(bus, devfn, afu, &record);
@@ -166,7 +176,7 @@ static int cxl_pcie_write_config(struct pci_bus *bus, unsigned int devfn,
 	}
 
 out:
-	up_read(&afu->configured_rwsem);
+	cxl_afu_configured_put(afu);
 	return rc ? PCIBIOS_SET_FAILED : PCIBIOS_SUCCESSFUL;
 }
 
diff --git a/drivers/pci/hotplug/pnv_php.c b/drivers/pci/hotplug/pnv_php.c
index d2961ef39a3a..7c203198b582 100644
--- a/drivers/pci/hotplug/pnv_php.c
+++ b/drivers/pci/hotplug/pnv_php.c
@@ -35,9 +35,11 @@ static void pnv_php_register(struct device_node *dn);
 static void pnv_php_unregister_one(struct device_node *dn);
 static void pnv_php_unregister(struct device_node *dn);
 
-static void pnv_php_disable_irq(struct pnv_php_slot *php_slot)
+static void pnv_php_disable_irq(struct pnv_php_slot *php_slot,
+				bool disable_device)
 {
 	struct pci_dev *pdev = php_slot->pdev;
+	int irq = php_slot->irq;
 	u16 ctrl;
 
 	if (php_slot->irq > 0) {
@@ -56,10 +58,14 @@ static void pnv_php_disable_irq(struct pnv_php_slot *php_slot)
 		php_slot->wq = NULL;
 	}
 
-	if (pdev->msix_enabled)
-		pci_disable_msix(pdev);
-	else if (pdev->msi_enabled)
-		pci_disable_msi(pdev);
+	if (disable_device || irq > 0) {
+		if (pdev->msix_enabled)
+			pci_disable_msix(pdev);
+		else if (pdev->msi_enabled)
+			pci_disable_msi(pdev);
+
+		pci_disable_device(pdev);
+	}
 }
 
 static void pnv_php_free_slot(struct kref *kref)
@@ -68,7 +74,7 @@ static void pnv_php_free_slot(struct kref *kref)
 					struct pnv_php_slot, kref);
 
 	WARN_ON(!list_empty(&php_slot->children));
-	pnv_php_disable_irq(php_slot);
+	pnv_php_disable_irq(php_slot, false);
 	kfree(php_slot->name);
 	kfree(php_slot);
 }
@@ -76,7 +82,7 @@ static void pnv_php_free_slot(struct kref *kref)
 static inline void pnv_php_put_slot(struct pnv_php_slot *php_slot)
 {
 
-	if (WARN_ON(!php_slot))
+	if (!php_slot)
 		return;
 
 	kref_put(&php_slot->kref, pnv_php_free_slot);
@@ -430,9 +436,21 @@ static int pnv_php_enable(struct pnv_php_slot *php_slot, bool rescan)
 	if (ret)
 		return ret;
 
-	/* Proceed if there have nothing behind the slot */
-	if (presence == OPAL_PCI_SLOT_EMPTY)
+	/*
+	 * Proceed if there have nothing behind the slot. However,
+	 * we should leave the slot in registered state at the
+	 * beginning. Otherwise, the PCI devices inserted afterwards
+	 * won't be probed and populated.
+	 */
+	if (presence == OPAL_PCI_SLOT_EMPTY) {
+		if (!php_slot->power_state_check) {
+			php_slot->power_state_check = true;
+
+			return 0;
+		}
+
 		goto scan;
+	}
 
 	/*
 	 * If the power supply to the slot is off, we can't detect
@@ -705,10 +723,15 @@ static irqreturn_t pnv_php_interrupt(int irq, void *data)
 	if (sts & PCI_EXP_SLTSTA_DLLSC) {
 		pcie_capability_read_word(pdev, PCI_EXP_LNKSTA, &lsts);
 		added = !!(lsts & PCI_EXP_LNKSTA_DLLLA);
-	} else if (sts & PCI_EXP_SLTSTA_PDC) {
+	} else if (!(php_slot->flags & PNV_PHP_FLAG_BROKEN_PDC) &&
+		   (sts & PCI_EXP_SLTSTA_PDC)) {
 		ret = pnv_pci_get_presence_state(php_slot->id, &presence);
-		if (!ret)
+		if (ret) {
+			dev_warn(&pdev->dev, "PCI slot [%s] error %d getting presence (0x%04x), to retry the operation.\n",
+				 php_slot->name, ret, sts);
 			return IRQ_HANDLED;
+		}
+
 		added = !!(presence == OPAL_PCI_SLOT_PRESENT);
 	} else {
 		return IRQ_NONE;
@@ -752,6 +775,7 @@ static irqreturn_t pnv_php_interrupt(int irq, void *data)
 static void pnv_php_init_irq(struct pnv_php_slot *php_slot, int irq)
 {
 	struct pci_dev *pdev = php_slot->pdev;
+	u32 broken_pdc = 0;
 	u16 sts, ctrl;
 	int ret;
 
@@ -759,29 +783,44 @@ static void pnv_php_init_irq(struct pnv_php_slot *php_slot, int irq)
 	php_slot->wq = alloc_workqueue("pciehp-%s", 0, 0, php_slot->name);
 	if (!php_slot->wq) {
 		dev_warn(&pdev->dev, "Cannot alloc workqueue\n");
-		pnv_php_disable_irq(php_slot);
+		pnv_php_disable_irq(php_slot, true);
 		return;
 	}
 
+	/* Check PDC (Presence Detection Change) is broken or not */
+	ret = of_property_read_u32(php_slot->dn, "ibm,slot-broken-pdc",
+				   &broken_pdc);
+	if (!ret && broken_pdc)
+		php_slot->flags |= PNV_PHP_FLAG_BROKEN_PDC;
+
 	/* Clear pending interrupts */
 	pcie_capability_read_word(pdev, PCI_EXP_SLTSTA, &sts);
-	sts |= (PCI_EXP_SLTSTA_PDC | PCI_EXP_SLTSTA_DLLSC);
+	if (php_slot->flags & PNV_PHP_FLAG_BROKEN_PDC)
+		sts |= PCI_EXP_SLTSTA_DLLSC;
+	else
+		sts |= (PCI_EXP_SLTSTA_PDC | PCI_EXP_SLTSTA_DLLSC);
 	pcie_capability_write_word(pdev, PCI_EXP_SLTSTA, sts);
 
 	/* Request the interrupt */
 	ret = request_irq(irq, pnv_php_interrupt, IRQF_SHARED,
 			  php_slot->name, php_slot);
 	if (ret) {
-		pnv_php_disable_irq(php_slot);
+		pnv_php_disable_irq(php_slot, true);
 		dev_warn(&pdev->dev, "Error %d enabling IRQ %d\n", ret, irq);
 		return;
 	}
 
 	/* Enable the interrupts */
 	pcie_capability_read_word(pdev, PCI_EXP_SLTCTL, &ctrl);
-	ctrl |= (PCI_EXP_SLTCTL_HPIE |
-		 PCI_EXP_SLTCTL_PDCE |
-		 PCI_EXP_SLTCTL_DLLSCE);
+	if (php_slot->flags & PNV_PHP_FLAG_BROKEN_PDC) {
+		ctrl &= ~PCI_EXP_SLTCTL_PDCE;
+		ctrl |= (PCI_EXP_SLTCTL_HPIE |
+			 PCI_EXP_SLTCTL_DLLSCE);
+	} else {
+		ctrl |= (PCI_EXP_SLTCTL_HPIE |
+			 PCI_EXP_SLTCTL_PDCE |
+			 PCI_EXP_SLTCTL_DLLSCE);
+	}
 	pcie_capability_write_word(pdev, PCI_EXP_SLTCTL, ctrl);
 
 	/* The interrupt is initialized successfully when @irq is valid */
@@ -793,6 +832,14 @@ static void pnv_php_enable_irq(struct pnv_php_slot *php_slot)
 	struct pci_dev *pdev = php_slot->pdev;
 	int irq, ret;
 
+	/*
+	 * The MSI/MSIx interrupt might have been occupied by other
+	 * drivers. Don't populate the surprise hotplug capability
+	 * in that case.
+	 */
+	if (pci_dev_msi_enabled(pdev))
+		return;
+
 	ret = pci_enable_device(pdev);
 	if (ret) {
 		dev_warn(&pdev->dev, "Error %d enabling device\n", ret);